JP7845482B2 - Integration systems, organizational servers, integration methods, analysis methods, and programs - Google Patents

Description

This disclosure relates to integrated systems, etc.

In some cases, predictive maintenance may be performed on the equipment. Predictive maintenance is a maintenance method that involves continuously measuring and monitoring the condition of the equipment to understand or predict its deterioration and then replacing or repairing parts accordingly.

Furthermore, Patent Document 1 discloses a method for obtaining local models from each of multiple nodes, statistically processing the local models, and generating a global model. Patent Document 2 also describes integrating the learned models using secure computation.

Japanese Patent Publication No. 2022-076277 Japanese Patent Publication No. 2020-115311

When organizations such as companies or departments perform predictive maintenance on equipment, it is likely that their own organizations have had few past instances of equipment failure, or have experienced parts replacement or repair due to equipment deterioration. In particular, newly introduced equipment may have never experienced failure or parts replacement or repair due to deterioration. Therefore, even if the equipment status is measured and monitored, it may not be possible to understand or predict equipment failure or equipment deterioration. Furthermore, it may be possible to identify equipment usage by referring to the operational data of each organization. For this reason, it is difficult for each organization to provide operational data to other organizations. Thus, when using predictive maintenance based on operational data of a single organization, there is a problem in that the accuracy of predictive maintenance may be low.

One example of the purpose of this disclosure is to provide an integrated system that improves the accuracy of predictive maintenance.

An integrated system in one aspect of the present disclosure includes: acquisition means for each of a plurality of organizational servers, which acquires confidential parameters of a local model learned based on operational data relating to a predetermined device, and which can output fault diagnosis results for the predetermined device when operational data is input; integration means for generating a global model by integrating the confidential parameters for each of the plurality of organizational servers; and providing means for providing the plurality of organizational servers with the integrated parameters of the generated global model.

An organizational server in one aspect of this disclosure includes: a model generation means that learns a local model capable of outputting fault diagnosis results for a predetermined device when operational data representing the operating status of the predetermined device is input; an anonymization means that conceals the parameters of the local model using secure computation; an output means that outputs the anonymized parameters of the local model to an integrated system; a parameter acquisition means that acquires parameters of a global model integrated in the integrated system from the integrated system; and an analysis means that inputs new operational data into the global model based on the acquired parameters to acquire fault diagnosis results for the predetermined device.

An integration method in one aspect of the present disclosure involves obtaining, for each of a plurality of organizational servers, the confidential parameters of a local model learned based on operational data relating to a predetermined device, which is capable of outputting fault diagnosis results for the predetermined device when operational data is input; integrating the confidential parameters for each of the plurality of organizational servers to generate a global model; and providing the plurality of organizational servers with the integrated parameters of the generated global model.

An analysis method in one aspect of this disclosure involves learning a local model capable of outputting fault diagnosis results for a predetermined device based on operational data representing the operating status of the predetermined device, learning a local model capable of outputting fault diagnosis results for the predetermined device when operational data is input, concealing the parameters of the local model using secure computation, outputting the concealed parameters of the local model to an integrated system, obtaining parameters of a global model integrated in the integrated system from the integrated system, and inputting new operational data into the global model based on the obtained parameters to obtain fault diagnosis results for the predetermined device.

A program in one aspect of this disclosure provides a computer with access to anonymized parameters of a local model learned for each of a plurality of organizational servers based on operational data relating to a predetermined device, the local model being capable of outputting fault diagnosis results for the predetermined device when operational data is input; a global model generated by integrating the anonymous parameters for each of the plurality of organizational servers; and the integrated parameters of the generated global model provided to the plurality of organizational servers.

A program in one aspect of this disclosure learns a local model that can output fault diagnosis results for a predetermined device when operational data representing the operating status of the predetermined device is input to a computer; the parameters of the local model are made secret using secure computation; the secreted parameters of the local model are output to an integrated system; parameters of a global model are obtained from the integrated system; and new operational data is input to the global model based on the obtained parameters to obtain fault diagnosis results for the predetermined device.

Each program may be stored on a non-temporary storage medium that is readable by the computer.

According to this disclosure, it is possible to improve the accuracy of predictive maintenance.

This is a block diagram showing an example configuration of an information processing system according to Embodiment 1. This is a flowchart showing an example of operation of the integrated system according to Embodiment 1. This is an explanatory diagram showing an example of how to connect each device in an information processing system. This is a block diagram showing an example configuration of an information processing system according to Embodiment 2. This is an explanatory diagram showing an example of how fault diagnosis results are displayed in a terminal device. This is a flowchart showing an example of an operation of the information processing system according to Embodiment 2. This flowchart shows an example of an operation involving analysis and parts ordering by an organizational server. This is an explanatory diagram showing an example of a computer hardware configuration.

Embodiments of the information processing system, integration system, organizational server, integration method, analysis method, program, and non-temporary recording medium for recording the program relating to this disclosure will be described in detail below with reference to the drawings. These embodiments are not intended to limit the technology of the disclosure.

(Embodiment 1)
First, the basic functions of the information processing system will be described in Embodiment 1. Figure 1 is a block diagram showing an example configuration of the information processing system according to Embodiment 1. The information processing system 1 is a system for integrating parameters of a local model for predictive maintenance of a predetermined device, using operational data held by an organization that uses the predetermined device. The information processing system 1 comprises an integration system 10 and a plurality of organization servers 11. In the following description, when local models and global models are not specified, they may simply be referred to as models.

Here, the specified device is a device such as a manufacturing device, robot, or pump, and is not particularly limited. For example, the integrated system 10 is a system of a supplying company that manufactures, sells, or leases the specified device or components contained in the specified device. An organization is a company or a department within a company that uses the specified device. For example, an organization is a customer of the supplying company. If the organization server 11 is not specified, it is simply referred to as the organization server 11. The organization server 11 is a device for generating a local model using operational data held by the organization. The organization servers 11 may be separated by organization, for example, and in Figure 1, the number of organization servers 11 is shown as two, but is not particularly limited.

Here, parameters are values acquired after the model has been trained, and they represent the weights of the operational data in the model. For example, if the operational data is a specific current value in a given device, then the weights of this current value are the parameters.

The model is a model for predictive maintenance of a predetermined device. The model may, for example, output the results of predictive maintenance when operational data is input. Alternatively, the model may, for example, output whether a specific part needs to be replaced or repaired when the difference between a reference value and operational data is input. A specific example of operational data will be described in detail using Embodiment 2.

The integrated system 10 comprises an acquisition unit 101, an integration unit 102, and a provision unit 103. The organization server 11 comprises a local model generation unit 111, an anonymization unit 112, an output unit 113, a parameter acquisition unit 114, and an analysis unit 116. The organization server 11 also comprises a model storage unit 115. The model storage unit 115 stores, for example, each model.

First, let's briefly explain the organization server 11. The local model generation unit 111 generates a local model learned based on operational data related to a predetermined device. The local model is a local model that can output fault diagnosis results for a predetermined device when operational data is input. For example, the local model generation unit 111 stores the generated local model in a model storage unit 115 or the like.

Here, the models include, but are not limited to, decision tree models, linear regression models, logistic regression models, and neural network models.

Next, the concealment unit 112 conceals the parameters of the local model generated by the local model generation unit 111 using secure computation. Concealment is synonymous with encryption. Secure computation is a technique for performing calculations while concealing the data. The output unit 113 outputs the concealed parameters to the integrated system 10. The integrated system 10, which is the basic function of Embodiment 1, will be described in detail below.

In the integrated system 10, the acquisition unit 101 acquires confidential parameters of the local model from each of the multiple organization servers 11. Specifically, for example, the acquisition unit 101 receives confidential parameters of the trained local model from each of the multiple organization servers 11. The acquisition unit 101 may receive confidential parameters triggered by an operation by the service provider to integrate the model parameters. Alternatively, the acquisition unit 101 may periodically receive confidential parameters from the organization servers 11.

In the integrated system 10, the integration unit 102 generates a global model by integrating multiple concealed parameters. The integration unit 102 may change the weights of the parameters corresponding to each local model depending on the characteristics of each local model when integrating the multiple concealed parameters.

The integration of multiple concealed parameters involves the information processing system 1 performing machine learning (federated learning) in a distributed state across each organizational server 11, and then integrating the parameters of the trained local models. Here, integration refers to a method of combining data from different entities so that it can be widely utilized. In this way, the information processing system 1 can integrate each parameter while keeping it concealed. As for the method of secure computation, special encryption corresponding to specific processing, such as homomorphic encryption, a Trusted Execution Environment that processes in an isolated state on hardware, or multi-party computation that performs computation while secretly sharing data across multiple servers (secret sharing computation) can be used.

An example of using secure computation in multi-party computing is as follows: When using secure computation in multi-party computing, the integrated system 10 may have multiple servers to realize the functions of the integrated unit 102. For example, the number of servers may be three. For example, one of the multiple servers secretly distributes confidential data a, which is a parameter obtained from an arbitrary organization server 11, into distributed values x1, y1, ... and sends x1, y1, ... to different servers. Also, one of the multiple servers secretly distributes confidential data b, which is a parameter obtained from another organization server 11, into distributed values x2, y2, ... and sends x2, y2, ... to different servers. The multiple servers communicate with each other and proceed with the computation while the confidential data a and confidential data b remain secretly distributed. Finally, the distributed values u, v, ... of the output, which are the computation results of each server, are collected and restored to obtain the computation result F(a, b). This computation result becomes the parameter of the global model, which integrates the parameters of each local model. Multi-party computation eliminates the need for cryptographic key management and isolated environments, resulting in faster computation.

The provisioning unit 103 provides, for example, the parameters of the global model to each organization server 11. Specifically, as a method of provision, for example, the provisioning unit 103 transmits the parameters of the global model to each organization server 11.

Then, in the organizational server 11, the parameter acquisition unit 114 acquires the parameters of the global model. Specifically, as a method of acquisition, the parameter acquisition unit 114 receives the parameters of the global model from the integrated system 10, for example.

The timing at which the parameter acquisition unit 114 acquires the parameters of the global model is not particularly limited. For example, the parameter acquisition unit 114 may receive parameters that are periodically transmitted from the integrated system 10. The parameter acquisition unit 114 may request the integrated system 10 to transmit the parameters of the global model and receive the parameters of the global model from the integrated system 10 in response to the request.

The parameter acquisition unit 114 can obtain the global model by setting the acquired global model parameters to the local model parameters. This allows each organization to use the global model. Alternatively, the parameter acquisition unit 114 may acquire the global model itself. For example, the parameter acquisition unit 114 may store the global model in a model storage unit 115 or the like.

The analysis unit 116 then inputs new operational data into the global model and obtains the fault diagnosis results for a predetermined device from the global model. Examples of how each organization utilizes the global model will be described in detail in Embodiment 2.

(flowchart)
Figure 2 is a flowchart illustrating an example of the operation of the integrated system 10 according to Embodiment 1. In the integrated system 10, the acquisition unit 101 acquires confidential parameters for each of the multiple local models (step S101). The integration unit 102 integrates the confidential parameters (step S102). The provision unit 103 provides the parameters for the global model (step S103). The integrated system 10 terminates processing.

As mentioned above, referring to the operational data and failure history of each organization may allow for the identification of equipment usage, and this operational data and failure history may constitute trade secrets. Therefore, as previously stated, it is difficult for each organization to provide operational data to other organizations. Thus, when using predictive maintenance based on the operational data of a single organization, there is a problem in that the accuracy of predictive maintenance may be low.

In the first embodiment described above, the integrated system 10 acquires, for each of the multiple organization servers 11, the concealed parameters of a local model learned based on operational data relating to a predetermined device, which can output fault diagnosis results for the predetermined device when operational data is input, integrates the concealed parameters, and provides the integrated parameters to the multiple organization servers 11. For example, the fault diagnosis result is the result of the maintenance need for the parts included in the predetermined device. As a result, the integrated system 10 can obtain a global model without acquiring operational data from each organization. Furthermore, each organization can perform analysis using the global model without providing operational data, etc., thereby improving the accuracy of predictive maintenance.

(Embodiment 2)
Next, Embodiment 2 will be described in detail with reference to the drawings. Embodiment 2 describes an example of analyzing predictive maintenance. In Embodiment 2, explanations that overlap with the above explanation will be omitted to the extent that the explanation of Embodiment 2 does not become unclear.

Figure 3 is an explanatory diagram showing an example of the connection of each device in the information processing system 1. The information processing system 1 comprises an integrated system 10, a plurality of organizational servers 11, and a plurality of terminal devices 12. The integrated system 10, the plurality of organizational servers 11, and the plurality of terminal devices 12 are connected, for example, via a communication network NT. Note that the communication network may be a plurality of communication networks. For example, the communication network to which the integrated system 10 and organizational server 11a are connected may be different from the communication network to which the integrated system 10 and organizational server 11b are connected.

The terminal device 12 is, for example, the terminal device 12 of an organization's representative. The terminal device 12 is a device for notifying about arrangements necessary for parts maintenance, etc. For this reason, there may be, for example, a separate terminal device 12 for each organization. If the terminal device 12 is not specified, it is simply referred to as terminal device 12. The type of terminal device 12 is not particularly limited and can be a smartphone, a tablet terminal device 12, a PC (Personal Computer), etc. The terminal device 12 and the organization server 11 may be a single device.

Figure 4 is a block diagram showing an example configuration of the information processing system 1 according to Embodiment 2. The integrated system 10 comprises the integrated system 10 and a plurality of organizational servers 11, as described in Embodiment 1.

Furthermore, the organization server 11 includes an output control unit 117 and a maintenance execution unit 118, in addition to the functional unit of the organization server 11 in Embodiment 1. Detailed explanations of each functional unit described in Embodiment 1 are omitted here. The analysis unit 116, the output control unit 117, and the maintenance execution unit 118 will be described in detail.

In the organizational server 11, for example, the analysis unit 116 provides operational data as input to a global model and obtains the results of a fault diagnosis of the components included in a predetermined device from the global model. The components included in a predetermined device include not only individual components used in the predetermined device, but also specific units containing multiple components. Here, the fault diagnosis results represent the maintenance necessity of the components included in the predetermined device. That is, the analysis unit 116 estimates the maintenance necessity of components that correlate with the operational data.

The operational data used by the analysis unit 116 may, for example, be operational data obtained by monitoring a newly designated device.

Here, the operational data used for learning and analysis is information about the environment for each position or component within a given device. This environmental information may include, for example, at least one of the following: current values, voltage values, vibration values, temperature values, humidity values, pressure values, power values, and sound. For example, the environmental information may be information acquired by various sensors. For example, vibration values may be total amplitude values or acceleration values. Also, for example, the operational data may be information about the sound for each component within the given device. Furthermore, if the given device includes a motor, the operational data may be the motor's rotational speed.

Next, we will explain using the example of a semiconductor manufacturing device. For example, if the device is a semiconductor manufacturing device, the operational data representing the operating status of the semiconductor manufacturing device is classified into process data and operating status data. Process data is, for example, a value measured for a physical quantity inside the manufacturing device when the semiconductor manufacturing device is in operation, and is obtained from sensor values attached to the semiconductor manufacturing device. Examples of sensors include current sensors, temperature sensors, vibration sensors, or acceleration sensors. Examples of process data include the current consumption and vibration intensity within a specific unit in the semiconductor manufacturing device. Other process data for thin-film deposition equipment includes, for example, gas flow rate, deposition time, substrate temperature, Vpp (Voltage peak to peak) voltage and Vdc (Voltage direct current) voltage (Plasma CVD (Chemical Vapor Deposition), dry etching), DC (Direct Current) bias (sputtering), and pressure. Examples of process data for semiconductor manufacturing equipment other than thin-film deposition include, for example, cleaning and etching equipment, cleaning degree and etching depth; for diffusion and thermal oxidation equipment, oxide film depth, thickness, and sheet resistance; for ion implantation/annealing equipment, profile sheet resistance; and for coater/developer equipment, resist pattern.

Operating status data refers to parameters that indicate the setting conditions when semiconductor manufacturing equipment is in operation. Examples of operating status data for thin-film deposition-related equipment include: for plasma CVD, input power, reflected wave → 0 (closeness to 0 of the reflection coefficient), achievable vacuum level in the chamber, and heating lamp power. For dry etching equipment, achievable vacuum level and heating lamp power. For RF plasma, incident wave Pf, reflected wave Pr, variable capacitor value, and heating lamp power. For sputtering equipment, input power, reflected wave, achievable vacuum level, and heating lamp electrode. For CVD, heating lamp power. Examples of operating status data for equipment other than thin-film deposition-related equipment include, for example, ion implantation/annealing equipment, for example, vacuum level and infrared lamp power. For exposure equipment, for example, light source output. For coater/developer equipment, for example, acceleration.

Next, the output control unit 117 outputs the fault diagnosis results. Here, outputting the fault diagnosis results includes the process of outputting the fault diagnosis results to an external device such as a terminal device 12. The output format may be audio output, display output on a screen, etc. Also, for example, the output control unit 117 notifies the acquired fault diagnosis results. For example, the output control unit 117 may provide notification according to the acquired fault diagnosis results. For the notification method, email or electronic message may be used. Specifically, for example, the output control unit 117 may notify the person in charge of maintenance of a predetermined device of the fault diagnosis results. Also, specifically, for example, the output control unit 117 may notify the person in charge that maintenance is necessary if the fault diagnosis results indicate that maintenance of a predetermined device is necessary. On the other hand, specifically, for example, the output control unit 117 may notify the person in charge that maintenance is not necessary if the fault diagnosis results indicate that maintenance of a predetermined device is not necessary.

The maintenance execution unit 118 makes arrangements for the maintenance of a specified device based on the results of the fault diagnosis obtained. Arrangements for the maintenance of a specified device include, in the case of replacing a part included in the specified device, ordering the part included in the specified device, and repairing the part included in the specified device. In the case of repairing a part, the arrangements for the maintenance of the specified device may also include arranging for a maintenance worker to repair the part.

Here, we will explain using the ordering of parts as an example. For example, the maintenance execution unit 118 orders the necessary parts for a specified device based on the results of the fault diagnosis obtained. Alternatively, the maintenance execution unit 118 may receive ordering instructions for parts of a specified device through user operations via the terminal device 12 and place orders for parts according to the received ordering instructions. Existing technologies may be used for the specific ordering method.

Here, we will describe an example in which the output control unit 117 displays the fault diagnosis results on the display device of the terminal device 12.

Figure 5 is an explanatory diagram showing an example of how the fault diagnosis results are displayed in the terminal device 12. For example, the output control unit 117 causes the fault diagnosis results to be displayed on the display device of the terminal device 12. The terminal device 12 displays the fault diagnosis results according to the control of the output control unit 117.

In Figure 5, the screen displays the message, "The current value at output pin d of component A is increasing . We recommend replacing component A." as a result of the fault diagnosis. The screen also displays the message, "Do you want to order component A?" Furthermore, Figure 5 includes an order button on the screen. For example, when the order button is tapped, the maintenance execution unit 118 places an order for component A. The screen may also display operational data that forms the basis for the abnormality diagnosis. For example, in Figure 5, the screen displays a graph with the measurement date on the horizontal axis and the current value at output pin d on the vertical axis.

Returning to the description of the function, for example, the maintenance execution unit 118 may place an order for a specific device part from the manufacturer of that part based on the inventory quantity of that part in the organization. For example, if the inventory quantity is below a predetermined value, the maintenance execution unit 118 will place an order for that part from the manufacturer of the specific device part.

(flowchart)
Figure 6 is a flowchart showing an example of the operation of the information processing system 1 according to Embodiment 2. The model generation unit generates a local model based on the operational data (step S201). The concealment unit 112 conceals the parameters of the local model using secure computation (step S202). The output unit 113 outputs the concealed parameters to the integrated system 10 (step S203).

In the integrated system 10, the acquisition unit 101 acquires anonymized parameters from each of the multiple organization servers 11 (step S204). The integration unit 102 integrates the parameters of the multiple local models (step S205). The provision unit 103 provides the anonymized parameters of the global model to the multiple organization servers 11 (step S206).

In the organization server 11, the parameter acquisition unit 114 acquires parameters of the global model from the integrated system 10 (step S207). Then, the analysis unit 116 performs analysis using the global model (step S208). The specific processing after the analysis will be explained with reference to Figure 7.

Figure 7 is a flowchart showing an example of an operation related to analysis and parts ordering by the organizational server 11. The analysis unit 116 analyzes predictive maintenance of parts using a global model (step S211). Note that step S211 in Figure 7 is the same as step S208 in Figure 6.

The analysis unit 116 determines whether the part needs to be maintained (step S212). If it is determined that the part does not need to be maintained (step S212: No), the analysis unit 116 returns to step S211. The output control unit 117 notifies the terminal device 12 that the part needs to be maintained (step S213).

The maintenance execution unit 118 determines whether it has received the order for the parts (step S214). If the order for the parts has not been received (step S214: No), the analysis unit 116 returns to step S211. If the order for the parts has been received (step S214: Yes), the maintenance execution unit 118 places the order for the parts (step S215) and returns to step S211.

In Embodiment 2, the operational data is information about the environment for each position or component within a predetermined device. For example, the environmental information includes at least one of the following: current value, voltage value, vibration value, temperature value, humidity value, pressure value, and sound. This makes it possible to improve the accuracy of predictive maintenance based on the environment of the predetermined device.

If the specified device includes a motor, the operating data is the motor's rotational speed. This allows for improved accuracy in predictive maintenance of devices including motors.

Furthermore, the organization server learns the local model, conceals the parameters of the local model, outputs the concealed parameters of the local model to the integrated system, and retrieves the parameters of the global model integrated in the integrated system. Then, the organization server inputs new operational data into the global model based on the retrieved parameters and obtains the fault diagnosis results for the specified equipment. As a result, each organization can perform analysis using the global model without providing operational data, thereby improving the accuracy of predictive maintenance.

The organizational server makes arrangements for the maintenance of a specified device based on the results of the fault diagnosis obtained. For example, the organizational server orders the necessary parts for a specified device based on the results of the fault diagnosis obtained.

This concludes the description of each embodiment. The embodiments may be used in combination as appropriate.

Furthermore, in each embodiment, the integrated system 10 may be configured to include a portion of each functional unit and information.

Furthermore, the embodiments are not limited to the examples described above and can be modified in various ways. Also, the configuration of the integrated system 10 in each embodiment is not particularly limited. For example, the integrated system 10 may be implemented by a single device, such as a single server. When each functional part of the integrated system 10 is implemented by a single device, the single device may be called, for example, an integration device, an information processing device, etc., and is not particularly limited. Alternatively, the integrated system 10 in each embodiment may be implemented by different devices for each function or data. For example, each functional part may be composed of multiple servers, and the integrated system 10 may be implemented as having multiple servers. For example, the integrated system 10 may be implemented by a database server including each DB (DataBase) and servers having each functional part. Also, the organization server 11 may be composed of multiple devices and implemented as an organization system, or it may be composed of a single device.

Furthermore, in each embodiment, each piece of information and each database may include a portion of the aforementioned information. Also, each piece of information and each database may include information other than the aforementioned information. Each piece of information and each database may be further divided into multiple databases or multiple pieces of information. Thus, the method of implementing each piece of information and each database is not particularly limited.

Furthermore, each screen is merely an example and is not particularly limited. Buttons, lists, checkboxes, information display fields, input fields, etc., not shown in the illustrations, may be added to each screen. Also, the background color of the screen may be changed.

Furthermore, the process of generating information to be displayed on the user's terminal device 12 may be performed by the output control unit 117 of the organization server 11. Alternatively, this process may be performed by the user's terminal device 12.

(Example of computer hardware configuration)
Next, we will describe hardware configuration examples when each of the devices described in each embodiment, such as the integrated system 10, organizational server 11, and terminal device 12, is implemented using a computer. Figure 8 is an explanatory diagram showing an example of computer hardware configuration. Some or all of each device can also be implemented using any combination of computer 80 and program, for example, as shown in Figure 8.

The computer 80 includes, for example, a processor 801, a ROM (Read Only Memory) 802, a RAM (Random Access Memory) 803, and a storage device 804. The computer 80 also includes a communication interface 805 and an input/output interface 806. Each component is connected, for example, via a bus 807. The number of components is not particularly limited, and each component may be one or more.

The processor 801 controls the entire computer 80. Examples of the processor 801 include a CPU (Central Processing Unit), a DSP (Digital Signal Processor), and a GPU (Graphics Processing Unit). The computer 80 has memory units such as a ROM 802, RAM 803, and a storage device 804. Examples of the storage device 804 include semiconductor memory such as flash memory, an HDD (Hard Disk Drive), and an SSD (Solid State Drive). For example, the storage device 804 stores the OS (Operating System) program, application programs, and programs related to each embodiment. Alternatively, the ROM 802 stores application programs and programs related to each embodiment. The RAM 803 is then used as the work area for the processor 801.

Furthermore, the processor 801 loads programs stored in the storage device 804, ROM 802, etc. Then, the processor 801 executes each process coded in the program. The processor 801 may also download various programs via the communication network NT. The processor 801 also functions as part or all of the computer 80. The processor 801 may also execute processes or instructions in the illustrated flowchart based on the program.

The communication interface 805 is connected to a communication network NT, such as a LAN (Local Area Network) or WAN (Wide Area Network), via a wireless or wired communication line. The communication network NT may be composed of multiple communication networks NT. This allows the computer 80 to connect to external devices and external computers 80 via the communication network NT. The communication interface 805 manages the interface between the communication network NT and the internal workings of the computer 80. Furthermore, the communication interface 805 controls the input and output of data from external devices and external computers 80.

Furthermore, the input/output interface 806 is connected to at least one of the input device, output device, and input/output device. The connection method may be wireless or wired. Examples of input devices include keyboards, mice, and microphones. Examples of output devices include display devices, lighting devices, and audio output devices. Examples of input/output devices include touch panel displays. The input device, output device, and input/output device may be built into the computer 80 or may be external.

The hardware configuration of computer 80 is an example. Computer 80 may have some of the components shown in Figure 8. Computer 80 may have components other than those shown in Figure 8. For example, computer 80 may have a drive device. The processor 801 may read programs and data stored on a recording medium mounted on the drive device into RAM 803. Examples of non-temporary tangible recording media include optical discs, flexible discs, magneto-optical discs, and USB (Universal Serial Bus) memory. Also, as mentioned above, computer 80 may have input devices such as a keyboard and a mouse. Computer 80 may have output devices such as a display. Furthermore, computer 80 may have input devices, output devices, and input/output devices, respectively.

Furthermore, the computer 80 may have various sensors (not shown). The type of sensor is not particularly limited. The computer 80 may also be equipped with an imaging device capable of capturing images or videos.

This concludes the description of the hardware configuration of each device. Furthermore, there are various variations in how each device can be implemented. For example, each device may be implemented using any combination of different computers and programs for each component. Alternatively, the multiple components of each device may be implemented using any combination of a single computer and program.

Furthermore, some or all of the components of each device may be implemented by application-specific circuits. Alternatively, some or all of the components of each device may be implemented by general-purpose circuits, including processors such as FPGAs (Field Programmable Gate Arrays). Furthermore, some or all of the components of each device may be implemented by a combination of application-specific circuits and general-purpose circuits. These circuits may also be a single integrated circuit, or they may be divided into multiple integrated circuits. These multiple integrated circuits may be connected via a bus or the like.

Furthermore, if some or all of the components of each device are implemented by multiple computers or circuits, these computers or circuits may be centrally located or distributed.

The integration method described in each embodiment is implemented by the integration system 10. Alternatively, for example, the integration method can be implemented by a computer such as a server or terminal device executing a pre-prepared program. Furthermore, the analysis method described in each embodiment is implemented by the organization server 11. Alternatively, for example, the analysis method can be implemented by a computer such as a server or terminal device executing a pre-prepared program.

The programs described in each embodiment are recorded on a computer-readable recording medium such as an HDD, SSD, flexible disk, optical disk, magneto-optical disk, or USB memory. The programs are then executed by being read from the recording medium by a computer. Furthermore, the programs may be distributed via a communication network NT.

Each component of the integrated system 10 in each embodiment described above may be implemented using dedicated hardware, such as a computer. Alternatively, each component may be implemented using software. Alternatively, each component may be implemented using a combination of hardware and software. Similarly, each component of the organizational server 11 may be implemented in the same way.

The present disclosure has been described above with reference to the embodiments described herein, but the present disclosure is not limited to the embodiments described above. The structure and details of each present disclosure may include embodiments that apply various modifications that can be grasped by those skilled in the art within the scope of the present disclosure. The present disclosure may include embodiments that combine or substitute the matters described herein as appropriate. For example, matters described using a particular embodiment may be applied to other embodiments to the extent that they do not cause a contradiction. For example, although multiple operations are described sequentially in the form of a flowchart, the order in which they are described does not limit the order in which the multiple operations are performed. Therefore, when implementing each embodiment, the order of the multiple operations can be changed to the extent that it does not impair the content.

Some or all of the above embodiments may also be described as follows. However, some or all of the above embodiments are not limited to the following.

(Note 1)
For each of the multiple organizational servers, an acquisition means for acquiring confidential parameters of a local model that has been learned based on operational data relating to a predetermined device, and which can output fault diagnosis results for the predetermined device when operational data is input.
An integration means for generating a global model by integrating the confidential parameters for each of the aforementioned multiple organizational servers,
A means for providing the integrated parameters of the generated global model to the plurality of organizational servers,
An integrated system equipped with [the following features].
(Note 2)
The aforementioned operating data is information regarding the environment of at least one of each position and each component within the predetermined device.
The integrated system described in Appendix 1.
(Note 3)
The information relating to the environment includes at least one of the following: current value, voltage value, vibration value, temperature value, humidity value, pressure value, and sound.
The integrated system described in Appendix 2.
(Note 4)
If the predetermined device includes a motor, the operating data is the rotational speed of the motor.
An integrated system as described in any of the appendices 1 to 3.
(Note 5)
The result of the fault diagnosis is the result of the need for maintenance of the components included in the predetermined device.
An integrated system as described in any of the appendices 1 to 4.
(Note 6)
A model generation means learns a local model that can output the results of fault diagnosis of a predetermined device when operational data representing the operating status of the predetermined device is input.
The parameters of the local model are provided as an anonymization means for concealing them using secure computation,
An output means for outputting the confidential parameters of the local model to the integrated system,
A parameter acquisition means for acquiring parameters of a global model integrated in the integrated system from the integrated system,
An analysis means for inputting new operational data into the global model based on the acquired parameters and obtaining the result of fault diagnosis of the predetermined device,
Organizational servers equipped with these features.
(Note 7)
Output control means for notifying the acquired fault diagnosis results,
,
The organizational server described in Appendix 6, which is equipped with the following features.
(Note 8)
Based on the results of the fault diagnosis obtained, a maintenance execution means makes arrangements for the maintenance of the predetermined device.
An organizational server as described in Appendix 6 or 7, comprising the following features.
(Note 9)
The maintenance execution means orders the necessary parts for the predetermined device based on the results of the fault diagnosis obtained.
The organizational server described in Appendix 8.
(Note 10)
For each of the multiple organizational servers, a local model learned based on operational data relating to a predetermined device is obtained, and when operational data is input, the local model's concealed parameters are acquired, which can output the results of fault diagnosis for the predetermined device.
A global model is generated by integrating the confidential parameters for each of the aforementioned multiple organizational servers.
The integrated parameters of the generated global model are provided to the aforementioned multiple organizational servers.
Integration method.
(Note 11)
Based on operational data representing the operating status of a predetermined device, when operational data is input, a local model capable of outputting the results of fault diagnosis for the predetermined device is learned.
The parameters of the aforementioned local model are made secret using secure computation.
The confidential parameters of the local model are output to the integrated system.
From the aforementioned integrated system, obtain the parameters of the global model integrated in the aforementioned integrated system.
Based on the acquired parameters, new operational data is input to the global model to obtain the result of fault diagnosis for the predetermined device.
Analysis method.
(Note 12)
On the computer,
For each of the multiple organizational servers, a local model learned based on operational data relating to a predetermined device is obtained, and when operational data is input, the local model's concealed parameters are acquired, which can output the results of fault diagnosis for the predetermined device.
A global model is generated by integrating the confidential parameters for each of the aforementioned multiple organizational servers.
The integrated parameters of the generated global model are provided to the aforementioned multiple organizational servers.
A non-temporary recording medium readable by the computer, which records a program that executes a process.
(Note 13)
On the computer,
Based on operational data representing the operating status of a predetermined device, when operational data is input, a local model capable of outputting the results of fault diagnosis for the predetermined device is learned.
The parameters of the aforementioned local model are made secret using secure computation.
The confidential parameters of the local model are output to the integrated system.
From the aforementioned integrated system, obtain the parameters of the global model integrated in the aforementioned integrated system.
Based on the acquired parameters, new operational data is input to the global model to obtain the result of fault diagnosis for the predetermined device.
A non-temporary recording medium readable by the computer, which records a program that executes a process.
(Note 14)
On the computer,
For each of the multiple organizational servers, a local model learned based on operational data relating to a predetermined device is obtained, and when operational data is input, the local model's concealed parameters are acquired, which can output the results of fault diagnosis for the predetermined device.
A global model is generated by integrating the confidential parameters for each of the aforementioned multiple organizational servers.
The integrated parameters of the generated global model are provided to the aforementioned multiple organizational servers.
A program that executes a process.
(Note 15)
On the computer,
Based on operational data representing the operating status of a predetermined device, when operational data is input, a local model capable of outputting the results of fault diagnosis for the predetermined device is learned.
The parameters of the aforementioned local model are made secret using secure computation.
The confidential parameters of the local model are output to the integrated system.
From the aforementioned integrated system, obtain the parameters of the global model integrated in the aforementioned integrated system.
Based on the acquired parameters, new operational data is input to the global model to obtain the result of fault diagnosis for the predetermined device.
A program that executes a process.

1. Information Processing System 10. Integrated Systems 11, 11a, 11b. Organization Server 12. Terminal Device 80. Computer 101. Acquisition Unit 102. Integration Unit 103. Provision Unit 111. Local Model Generation Unit 112. Anonymization Unit 113. Output Unit 114. Parameter Acquisition Unit 115. Model Storage Unit 116. Analysis Unit 117. Output Control Unit 118. Maintenance Execution Unit 801. Processor 802. ROM.
803 RAM
804 Storage device 805 Communication interface 806 Input/output interface 807 Bus NT Communication network

Claims (13)

For each of the multiple organizational servers, an acquisition means for acquiring confidential parameters of a local model that has been learned based on operational data relating to a predetermined device, and which can output fault diagnosis results for the predetermined device when operational data is input.
An integration means for generating a global model by integrating confidential parameters for each of the aforementioned multiple organizational servers,
A means for providing the integrated parameters of the generated global model to the plurality of organizational servers,
Equipped with ,
The aforementioned predetermined apparatus is a semiconductor manufacturing apparatus,
The aforementioned operational data includes process data,
If the semiconductor manufacturing apparatus is a film deposition-related apparatus, the process data includes gas flow rate, film deposition time, substrate temperature, Vpp (Voltage peak to peak) voltage and Vdc (Voltage direct current) voltage, DC (Direct Current) bias, and pressure.
If the semiconductor manufacturing apparatus is a cleaning apparatus or an etching apparatus, the process data includes the degree of cleaning and the etching depth.
If the semiconductor manufacturing apparatus is a diffusion apparatus or a thermal oxidation apparatus, the process data includes the thickness of the oxide film and the sheet resistance.
If the semiconductor manufacturing apparatus is an ion implanter or an annealing apparatus, the process data includes sheet resistance.
If the semiconductor manufacturing equipment is a coater or developer, the process data includes a resist pattern.
Integrated system. The aforementioned operating data includes information regarding the environment of at least one of the components within the predetermined device.
The integrated system according to claim 1. The information relating to the environment includes at least one of the following: current value, voltage value, vibration value, temperature value, humidity value, pressure value, and sound.
The integrated system according to claim 2. If the predetermined device includes a motor , the operation data includes the rotational speed of the motor.
The integrated system according to any one of claims 1 to 3. The results of the fault diagnosis indicate the need for maintenance of the components included in the specified device.
The integrated system according to any one of claims 1 to 3. A model generation means learns a local model that can output the results of fault diagnosis of a predetermined device when operational data representing the operating status of the predetermined device is input.
The parameters of the local model are provided as an anonymization means for concealing them using secure computation,
An output means for outputting the confidential parameters of the local model to the integrated system,
A parameter acquisition means for acquiring parameters of a global model integrated in the integrated system from the integrated system,
An analysis means for inputting new operational data into the global model based on the acquired parameters and obtaining the result of fault diagnosis of the predetermined device,
Equipped with ,
The aforementioned predetermined apparatus is a semiconductor manufacturing apparatus,
The aforementioned operational data includes process data,
If the semiconductor manufacturing apparatus is a film deposition-related apparatus, the process data includes gas flow rate, film deposition time, substrate temperature, Vpp voltage and Vdc voltage, DC bias, and pressure.
If the semiconductor manufacturing apparatus is a cleaning apparatus or an etching apparatus, the process data includes the degree of cleaning and the etching depth.
If the semiconductor manufacturing apparatus is a diffusion apparatus or a thermal oxidation apparatus, the process data includes the thickness of the oxide film and the sheet resistance.
If the semiconductor manufacturing apparatus is an ion implanter or an annealing apparatus, the process data includes sheet resistance.
If the semiconductor manufacturing equipment is a coater or developer, the process data includes a resist pattern.
Organizational server. Output control means for notifying the acquired fault diagnosis results,
The organizational server according to claim 6, comprising: Based on the results of the fault diagnosis obtained, a maintenance execution means makes arrangements for the maintenance of the predetermined device.
The organizational server according to claim 6 or 7, comprising: The maintenance execution means orders the necessary parts for the predetermined device based on the results of the fault diagnosis obtained.
The organizational server according to claim 8. For each of the multiple organizational servers, a local model learned based on operational data relating to a predetermined device is obtained, and when operational data is input, the local model's concealed parameters are acquired, which can output the results of fault diagnosis for the predetermined device.
A global model is generated by integrating the confidential parameters for each of the aforementioned multiple organizational servers.
The integrated parameters of the generated global model are provided to the multiple organizational servers .
The aforementioned predetermined apparatus is a semiconductor manufacturing apparatus,
The aforementioned operational data includes process data,
If the semiconductor manufacturing apparatus is a film deposition-related apparatus, the process data includes gas flow rate, film deposition time, substrate temperature, Vpp voltage and Vdc voltage, DC bias, and pressure.
If the semiconductor manufacturing apparatus is a cleaning apparatus or an etching apparatus, the process data includes the degree of cleaning and the etching depth.
If the semiconductor manufacturing apparatus is a diffusion apparatus or a thermal oxidation apparatus, the process data includes the thickness of the oxide film and the sheet resistance.
If the semiconductor manufacturing apparatus is an ion implanter or an annealing apparatus, the process data includes sheet resistance.
If the semiconductor manufacturing equipment is a coater or developer, the process data includes a resist pattern.
Integration method. Based on operational data representing the operating status of a predetermined device, when operational data is input, a local model capable of outputting the results of fault diagnosis for the predetermined device is learned.
The parameters of the aforementioned local model are made secret using secure computation.
The confidential parameters of the local model are output to the integrated system.
From the aforementioned integrated system, obtain the parameters of the global model integrated in the aforementioned integrated system.
Based on the acquired parameters, new operating data is input to the global model to obtain the result of fault diagnosis for the predetermined device .
The aforementioned predetermined apparatus is a semiconductor manufacturing apparatus,
The aforementioned operational data includes process data,
If the semiconductor manufacturing apparatus is a film deposition-related apparatus, the process data includes gas flow rate, film deposition time, substrate temperature, Vpp voltage and Vdc voltage, DC bias, and pressure.
If the semiconductor manufacturing apparatus is a cleaning apparatus or an etching apparatus, the process data includes the degree of cleaning and the etching depth.
If the semiconductor manufacturing apparatus is a diffusion apparatus or a thermal oxidation apparatus, the process data includes the thickness of the oxide film and the sheet resistance.
If the semiconductor manufacturing apparatus is an ion implanter or an annealing apparatus, the process data includes sheet resistance.
If the semiconductor manufacturing equipment is a coater or developer, the process data includes a resist pattern.
Analysis method. On the computer,
For each of the multiple organizational servers, a local model learned based on operational data relating to a predetermined device is obtained, and when operational data is input, the local model's concealed parameters are acquired, which can output the results of fault diagnosis for the predetermined device.
A global model is generated by integrating the confidential parameters for each of the aforementioned multiple organizational servers.
The integrated parameters of the generated global model are provided to the aforementioned multiple organizational servers.
Execute the process ,
The aforementioned predetermined apparatus is a semiconductor manufacturing apparatus,
The aforementioned operational data includes process data,
If the semiconductor manufacturing apparatus is a film deposition-related apparatus, the process data includes gas flow rate, film deposition time, substrate temperature, Vpp voltage and Vdc voltage, DC bias, and pressure.
If the semiconductor manufacturing apparatus is a cleaning apparatus or an etching apparatus, the process data includes the degree of cleaning and the etching depth.
If the semiconductor manufacturing apparatus is a diffusion apparatus or a thermal oxidation apparatus, the process data includes the thickness of the oxide film and the sheet resistance.
If the semiconductor manufacturing apparatus is an ion implanter or an annealing apparatus, the process data includes sheet resistance.
If the semiconductor manufacturing equipment is a coater or developer, the process data includes a resist pattern.
program. On the computer,
Based on operational data representing the operating status of a predetermined device, when operational data is input, a local model capable of outputting the results of fault diagnosis for the predetermined device is learned.
The parameters of the aforementioned local model are made secret using secure computation.
The confidential parameters of the local model are output to the integrated system.
From the aforementioned integrated system, obtain the parameters of the global model integrated in the aforementioned integrated system.
Based on the acquired parameters, new operational data is input to the global model to obtain the result of fault diagnosis for the predetermined device.
Execute the process ,
The aforementioned predetermined apparatus is a semiconductor manufacturing apparatus,
The aforementioned operational data includes process data,
If the semiconductor manufacturing apparatus is a film deposition-related apparatus, the process data includes gas flow rate, film deposition time, substrate temperature, Vpp voltage and Vdc voltage, DC bias, and pressure.
If the semiconductor manufacturing apparatus is a cleaning apparatus or an etching apparatus, the process data includes the degree of cleaning and the etching depth.
If the semiconductor manufacturing apparatus is a diffusion apparatus or a thermal oxidation apparatus, the process data includes the thickness of the oxide film and the sheet resistance.
If the semiconductor manufacturing apparatus is an ion implanter or an annealing apparatus, the process data includes sheet resistance.
If the semiconductor manufacturing equipment is a coater or developer, the process data includes a resist pattern.
program.