JP7813677B2 - Information processing device, index value calculation method, and index value calculation program - Google Patents

Description

The present invention relates to a technology for estimating the residence time of a liquid containing suspended solids inside a dehydrator when the liquid is dehydrated using the dehydrator.

Sludge treatment carried out at wastewater treatment facilities such as sewage treatment plants includes a process of dehydrating the sludge using a dehydrator. For efficient sludge treatment, it is important to maintain the moisture content of the dehydrated cake obtained by dehydration within a specified range. However, when dehydration is performed under constant operating conditions for the dehydrator, the moisture content of the dehydrated cake fluctuates due to factors such as the inconsistency of the properties of the supplied sludge, making it difficult to maintain the moisture content of the dehydrated cake within the specified range.

For this reason, efforts have been made to develop technology to predict the moisture content of dehydrated cake. If the moisture content can be predicted, it will be possible to maintain the moisture content within a predetermined range through feedforward control. For example, Patent Document 1 below discloses a technology for estimating the moisture content by creating a moisture content estimation model using multiple parameters, such as the amount of sludge supplied to a centrifugal dehydrator and values related to the centrifugal effect of the dehydrator.

Japanese Patent Application Laid-Open No. 2020-114569

When generating a moisture content estimation model like the one described above, training data is required that matches various parameters (explanatory variables) related to the sludge supplied to the dehydrator and the operating conditions of various equipment with the moisture content of the dehydrated cake (target variable), but achieving this correspondence is not easy. This is because there is a time lag between the time the sludge is supplied to the dehydrator (i.e., the time the explanatory variables are determined) and the time the supplied sludge is discharged as dehydrated cake (i.e., the time the target variable is determined), and it is difficult to actually measure this time lag (i.e., the residence time of the sludge in the dehydrator). This problem is not limited to sludge, but is a common issue that arises in the dehydration process of any liquid containing suspended solids.

One aspect of the present invention aims to realize an information processing device or the like that is capable of calculating an index value that indicates the retention time of a liquid containing suspended solids in a dehydrator.

To solve the above problem, an information processing device according to one aspect of the present invention includes a data acquisition unit that acquires a first time-series index value relating to the properties of a liquid containing suspended solids that is supplied to a dehydrator and a second time-series index value that reflects the dehydration of a dehydrated cake that is discharged after the liquid is dehydrated in the dehydrator; and an index value calculation unit that calculates a third index value that indicates the residence time of the liquid inside the dehydrator based on the shift in the time axis between the time-series changes of the first index value and the time-series changes of the second index value.

In addition, in order to solve the above-mentioned problems, an index value calculation method according to one aspect of the present invention is an index value calculation method executed by one or more information processing devices, and includes a data acquisition step of acquiring a first time-series index value relating to the properties of a liquid containing suspended solids that is supplied to a dehydrator and a second time-series index value that reflects the dehydration of a dehydrated cake that is discharged after the liquid is dehydrated in the dehydrator, and an index value calculation step of calculating a third index value that indicates the residence time of the liquid inside the dehydrator based on the difference in the time axis direction between the time-series changes of the first index value and the time-series changes of the second index value.

According to one aspect of the present invention, a third index value can be calculated, which is an index value indicating the retention time of liquid containing suspended solids in the dehydrator.

1 is a block diagram showing an example of a main configuration of an information processing device according to an embodiment of the present invention; FIG. 10 is a diagram illustrating an example of the configuration of a control system including the information processing device. 10 is a diagram showing time-series measurement result data of the flow rate per unit time of the liquid supplied to the flocculator and time-series measurement result data of the opening degree of the back pressure plate. FIG. 10A and 10B are diagrams illustrating an increase/decrease match number analysis and an increase/decrease match rate analysis. FIG. 10 is a diagram showing time-series measurement result data of the flow rate per unit time of the liquid supplied to the flocculator and time-series measurement result data of the opening degree of the back pressure plate when the screw rotation speed is changed during dehydration processing. 10 is a flowchart illustrating an example of processing executed by the information processing device.

[System Configuration]
The configuration of a control system according to one embodiment of the present invention will be described with reference to Figure 2. Figure 2 is a diagram showing an example of the configuration of a control system 100. The control system 100 is a system used in a plant that adds an agent that coagulates suspended solids to a liquid to be treated in a coagulation tank to form flocs, and then performs solid-liquid separation of the liquid to be treated in which the flocs have formed. In the following, an example will be described in which the liquid to be treated is sludge, but the control system 100 can also be applied to plants that treat liquids other than sludge. Note that sludge is a liquid containing fine solids that is generated during wastewater treatment, etc., and can also be called a slurry.

As will be explained in more detail below, the control system 100 performs each step in the sludge treatment process, from the step of converting the sludge to be treated into flocculated sludge by agglomerating suspended solids in the sludge to form flocs, to the step of dewatering the flocculated sludge to obtain dehydrated sludge (also called dehydrated cake) and dehydrated filtrate. As shown in Figure 2, the control system 100 includes an information processing device 1, a control device 3, a flocculator 5, and a dehydrator 9.

The flocculator 5 is a device that adds a chemical agent that coagulates suspended solids to the liquid being treated in a coagulation tank and moderately stirs it to form flocs. Specifically, the flocculator 5 uses sludge as the liquid being treated and coagulates the suspended solids in the sludge to form flocs, thereby producing coagulated sludge. The flocculator 5 in Figure 2 is equipped with a coagulation tank 51, agitator blades 52, a motor 53, and an inspection window 54. The flocculator 5 also has a sludge inlet 55, a chemical agent inlet 56, and a discharge outlet 57.

Furthermore, a photographing device 72 and a lighting device 71 for photography are attached to the inspection window 54. The photographing device 72 needs to be capable of at least taking still images. It is preferable that the coagulation tank 51 is opaque so that the way light hits the flocs does not change while the control system 100 is in operation. Furthermore, it is preferable that the photographing device 72 and lighting device 71 be housed in a light-tight dark box that is open on the inspection window 54 side, as in the example shown.

The dehydrator 9 is a device that performs solid-liquid separation of the liquid to be treated in which flocs have formed. Specifically, the dehydrator 9 is disposed downstream of the flocculator 5 and performs solid-liquid separation by dehydrating the flocculated sludge discharged from the flocculator 5. The dehydrator 9 in Figure 2 is a screw press type dehydrator equipped with an outer screen 91 and a screw 92. The dehydrator 9 also has a sludge inlet 93, a filtrate outlet 94, and a dehydrated cake outlet 95. Although not shown, the dehydrator 9 also includes a motor for rotating the screw 92. Of course, the dehydrator 9 is not limited to a screw press type as long as it is capable of dehydrating flocculated sludge. For example, a centrifugal dehydrator, a filter press dehydrator, or a belt press dehydrator can also be used.

In the control system 100, the sludge to be treated is continuously or intermittently supplied from the sludge inlet 55 into the coagulation tank 51 of the flocculator 5 by a supply device (not shown), and the sludge pushed out of the coagulation tank 51 is supplied to the dehydrator 9. Therefore, the flow rate of sludge supplied to the coagulation tank 51 and the flow rate of sludge supplied to the dehydrator 9 are the same at the same time. The sludge supply rate may be automatically controlled by the supply device or its control device 3 in accordance with the sludge treatment rate by the flocculator 5 and the dehydrator 9.

Then, chemicals (including at least a flocculant) for flocculating the sludge are added to the sludge in the flocculation tank 51 through the chemical inlet 56. In this state, the motor 53 is driven to rotate the agitator blades 52, agitating the sludge and chemicals and forming flocs. The flocculated sludge, which is a mixture of the formed flocs and the water contained in the sludge, is discharged through the outlet 57.

The flocculated sludge is then fed into the outer screen 91 through the sludge inlet 93 of the dehydrator 9. Inside the dehydrator 9, the flocculated sludge is dehydrated under pressure by the screw 92, and the filtrate is discharged through the filtrate outlet 94. A dehydrated cake, which is a mass of dehydrated flocculated sludge, is discharged through the dehydrated cake outlet 95.

As will be explained in more detail below, the information processing device 1 acquires a first time-series index value relating to the properties of the liquid containing suspended solids that is supplied to the dehydrator 9, and a second time-series index value that reflects the dehydration of the dehydrated cake that is discharged after the liquid is dehydrated in the dehydrator 9. The information processing device 1 then calculates a third index value that indicates the residence time of the liquid inside the dehydrator 9, based on the deviation in the time axis direction between the time-series changes in the first index value and the time-series changes in the second index value.

The first time-series index value relating to the properties of the liquid containing suspended solids is a value determined at the time the liquid is supplied to the dehydrator 9, while the second time-series index value reflecting the dehydration of the dehydrated cake is a value determined after or during dehydration. Because the dehydration of the dehydrated cake is affected by the properties of the liquid supplied to the dehydrator, the second index value changes in conjunction with the first index value, and the shift in the time axis of this change corresponds to the residence time of the liquid containing suspended solids in the dehydrator 9. Therefore, the information processing device 1 can calculate an index value indicating the residence time of the liquid containing suspended solids in the dehydrator 9.

The information processing device 1 can also control the operation of various devices that are components of the control system 100 (e.g., the flocculator 5, the dehydrator 9, and a chemical supply device (not shown)) via the control device 3. The control device 3 controls the operation of various devices that are components of the control system 100. The control device 3 may be, for example, a PLC (Programmable Logic Controller).

[Device configuration]
The configuration of the information processing device 1 will be described with reference to Fig. 1. Fig. 1 is a block diagram showing an example of the main configuration of the information processing device 1. As shown in the figure, the information processing device 1 includes a control unit 10 that controls each unit of the information processing device 1, and a storage unit 11 that stores various data used by the information processing device 1. The information processing device 1 also includes a communication unit 12 that enables the information processing device 1 to communicate with other devices, an input unit 13 that accepts input of various data to the information processing device 1, and an output unit 14 that enables the information processing device 1 to output various data.

The control unit 10 also includes a data acquisition unit 101, a conversion unit 102, an index value calculation unit 103, a teacher data generation unit 104, and an equipment control unit 105. The conversion unit 102, teacher data generation unit 104, and equipment control unit 105 will be described below in the sections "Conversion," "Generation of teacher data," and "Control for varying index values," respectively.

The data acquisition unit 101 acquires a first time-series index value relating to the properties of the liquid containing suspended solids supplied to the dehydrator 9, and a second time-series index value reflecting the dehydration of the dehydrated cake discharged after the liquid is dehydrated in the dehydrator 9. The first and second index values are explained below in the section "Regarding the First and Second Index Values."

The index value calculation unit 103 calculates a third index value indicating the retention time of the liquid inside the dehydrator 9 based on the time axis difference between the time series change of the first index value and the time series change of the second index value. Specific calculation methods for the third index value will be described later in the section "Calculation method of the third index value."

As such, the information processing device 1 according to this embodiment includes a data acquisition unit 101 that acquires a first time-series index value relating to the properties of the liquid containing suspended solids that is supplied to the dehydrator 9 and a second time-series index value that reflects the dehydration of the dehydrated cake that is discharged after the liquid is dehydrated in the dehydrator 9, and an index value calculation unit 103 that calculates a third index value that indicates the residence time of the liquid inside the dehydrator 9 based on the shift in the time axis direction between the time-series change of the first index value and the time-series change of the second index value. This makes it possible to calculate the third index value, which is an index value that indicates the residence time of the liquid containing suspended solids that is retained inside the dehydrator 9.

[Regarding the first index value and the second index value]
The first index value may be time-series data relating to the properties of the liquid containing suspended solids supplied to the dehydrator 9. For example, the flow rate per unit time of the liquid supplied to the dehydrator 9 may be used as the first index value. This is because, when the supply pressure of the liquid to the dehydrator 9 is controlled to be constant, the flow rate of the liquid supplied to the dehydrator 9 reflects the properties of the liquid. For example, if the dehydration property of the liquid is high, the supply flow rate to the dehydrator 9 will be high, and if the dehydration property of the liquid is low, the supply flow rate will be low. Furthermore, for example, the supply flow rate of the liquid to the flocculator 5 will be high if the dehydration property of the liquid is high and low if the dehydration property of the liquid is low. Therefore, the flow rate per unit time of the liquid supplied to the flocculator 5 may be used as the first index value.

The first index value may also be a value that exhibits similar behavior to the flow rate per unit time of the liquid supplied to the dehydrator 9. For example, the first index value may be the value obtained by dividing the flow rate per unit time of the liquid supplied to the dehydrator 9 by the screw rotation speed of the dehydrator 9.

On the other hand, the second index value may be time-series data that reflects the dehydration of the dehydrated cake discharged after the liquid is dehydrated in the dehydrator 9. For example, the opening between the back pressure plate that applies back pressure in the discharge section of the dehydrator 9 and the discharge section (hereinafter referred to as the back pressure plate opening) may be used as the second index value. If the dehydration of the dehydrated cake is high, the opening of the back pressure plate will be low, and if the dehydration of the dehydrated cake is low, the opening of the back pressure plate will be high, so the opening of the back pressure plate is appropriate as the second index value.

In addition, the current value driving the screw of the dehydrator 9 and the driving torque of the screw will be lower if the dehydration of the dehydrated cake is low, and will be higher if the dehydration of the dehydrated cake is high, so these values can also be used as second index values.

As a result of experiments conducted by the inventors of the present application, it has been confirmed that a valid third index value can be calculated by applying the flow rate per unit time of the liquid supplied to the dehydrator 9 as the first index value and the opening degree of the back pressure plate as the second index value. Therefore, a valid third index value can be calculated by applying the flow rate per unit time of the liquid supplied to the dehydrator 9 as the first index value and the opening degree of the back pressure plate as the second index value.

Of course, the flow rate per unit time of the liquid supplied to the dehydrator 9 is merely one example of the first index value, and the opening of the back pressure plate is merely one example of the second index value. The first index value may be time-series data relating to the properties of the liquid containing suspended solids supplied to the dehydrator 9, and the second index value may be time-series data reflecting the dehydration of the dehydrated cake discharged after the liquid is dehydrated in the dehydrator 9.

When the flow rate per unit time of the liquid supplied to the flocculator 5 is used as the first index value, there is a slight time lag before the liquid supplied to the flocculator 5 reaches the dehydrator 9. However, because this time lag is short compared to the residence time of the liquid in the dehydrator 9, there is no problem in using the flow rate per unit time of the liquid supplied to the flocculator 5 as the first index value. Of course, the third index value may be calculated taking this time lag into account. For example, the index value calculation unit 103 may calculate the final third index value by subtracting a predetermined time equivalent to the time lag (residence time in the flocculator 5) from the third index value calculated by applying the flow rate per unit time of the liquid supplied to the flocculator 5 as the first index value.

[Third index value calculation method]
(1) Cross-correlation analysis The index value calculation unit 103 may derive a first function that indicates a time series change in the first index value and a second function that indicates a time series change in the second index value, and calculate the third index value by performing cross-correlation analysis using the derived first function and second function.

In this case, when the derived first function is f(t) and the derived second function is g(t), the index value calculation unit 103 calculates τ that maximizes h(τ), which is expressed by the cross-correlation function (CCF) below. Note that t is time. The τ calculated in this way indicates the shift in the time axis direction between the time series changes of the first index value and the time series changes of the second index value, and can be used as a third index value. This will be explained based on Figure 3.

Figure 3 shows time-series measurement result data for the flow rate per unit time of the liquid supplied to the dehydrator 9 and time-series measurement result data for the opening degree of the back pressure plate. Specifically, measurement result data D1 shows the time-series measurement results for the flow rate per unit time of the liquid supplied to the dehydrator 9, and measurement result data D2 shows the time-series measurement results for the opening degree of the back pressure plate. Furthermore, data D3 is data obtained by shifting measurement result data D2 by τ along the time axis.

The index value calculation unit 103 can derive a function f(t) that indicates the time-series change in the flow rate per unit time of the liquid supplied to the dehydrator 9 from the measurement result data D1. Similarly, the index value calculation unit 103 can derive a function g(t) that indicates the time-series change in the opening degree of the back pressure plate from the measurement result data D2. As shown in the figure, the peaks of the functions f(t) and g(t) appear similarly, but the peak of function g(t) appears later than that of function f(t).

This indicates that there is a time lag between when the flow rate per unit time of the liquid supplied to the dehydrator 9 changes and when that change is reflected in the opening of the back pressure plate. This time lag is roughly equal to the residence time of the liquid in the dehydrator 9.

This time difference can be rephrased as the deviation along the time axis between the time series change in the flow rate per unit time of the liquid supplied to the dehydrator 9, shown by function f(t), and the time series change in the opening of the back pressure plate, shown by function g(t). τ in the cross-correlation function can be said to represent this deviation. Therefore, τ calculated using the cross-correlation function can be used as a third index value. As shown in the figure, the peak positions and shapes of function f(t) and function g(t+τ), obtained by shifting function g(t) by τ along the time axis, are roughly the same.

(2) Increase/Decrease Match Number Analysis/Increase/Decrease Match Rate Analysis The index value calculation unit 103 may also calculate the third index value by increase/decrease match number analysis or increase/decrease match rate analysis. The increase/decrease match number analysis or increase/decrease match rate analysis determines the amount of shift when the time-series second index value is shifted along the time axis so as to maximize the number of matches in the increase/decrease patterns between the first index value and the second index value. The increase/decrease match rate analysis determines the amount of shift when the time-series second index value is shifted along the time axis so as to maximize the match rate in the increase/decrease patterns between the first index value and the second index value.

The increase/decrease match number analysis and increase/decrease match rate analysis will be explained based on Figure 4. Figure 4 is a diagram explaining the increase/decrease match number analysis and increase/decrease match rate analysis.

The graph shown at the top of Figure 4 shows time-series measurement result data D1 of the flow rate per unit time of the liquid supplied to the flocculator 5, and time-series measurement result data D2 of the opening degree of the back pressure plate. Note that measurement result data D1 is the first index value in the time series, and measurement result data D2 is the second index value in the time series. Figure 4 also shows an enlarged view of the section from 125 minutes to 140 minutes in measurement result data D1 and measurement result data D2.

When performing an increase/decrease match count analysis, the index value calculation unit 103 classifies each of the first index values that make up the measurement result data D1 into either an increase from the previous value, a decrease, or no change. The index value calculation unit 103 also classifies the second index values that make up the measurement result data D2 in the same way. In Figure 4, an increase from the previous value is represented by "+", a decrease by "-", and no change by "0".

Next, the index value calculation unit 103 determines whether the classification results of the first index value and the second index value measured at the same time match. For example, as shown in the enlarged view of Figure 4, from 125 minutes to 134 minutes, both measurement result data D1 and measurement result data D2 increase monotonically, so the above determination result is "match." On the other hand, from 135 minutes onwards, measurement result data D1 begins to decrease, while measurement result data D2 continues to increase, so the above determination result is "mismatch."

The index value calculation unit 103 then calculates the number of increases/decreases in match count or the increase/decrease match rate based on the above judgment results. The number of increases/decreases in match count is the total number of times a "match" was judged, and the increase/decrease match rate is the number of times a "match" was judged divided by the total number of judgments.

The index value calculation unit 103 repeats the above process while changing the amount of shift in the time axis direction of the measurement result data D2, and determines the amount of shift that maximizes the number of increase/decrease matches or the increase/decrease match rate.

The graph at the bottom of Figure 4 shows the measurement result data D1 and D2 described above, as well as data D3, which is measurement result data D2 shifted along the time axis to maximize the number of increase/decrease matches. As shown in the enlarged view of the section from 125 minutes to 140 minutes, the increase/decrease patterns of measurement result data D1 and data D3 are generally consistent. Note that data obtained by shifting measurement result data D2 along the time axis to maximize the increase/decrease match rate will usually be roughly similar to data D3.

As described above, the index value calculation unit 103 may calculate the third index value based on the shift amount τ when the second function g(t) is shifted in the time axis direction so as to maximize the correlation between the first function f(t) indicating the time series change in the first index value and the second function g(t) indicating the time series change in the second index value.

The index value calculation unit 103 may also calculate the third index value based on the amount of shift when the second index value in the time series is shifted along the time axis so that the number of matches or the rate of matches between the first index value and the second index value in terms of the increase/decrease patterns from the immediately preceding value in chronological order is maximized.

Experiments conducted by the inventors of the present application have confirmed that an appropriate third index value can be calculated regardless of which of the above methods is applied. Therefore, with the above configuration, an appropriate third index value can be calculated.

(Exclusion of measurements from unstable periods)
3 and 4, the flow rate per unit time of the liquid supplied to the dehydrator 9 is unstable for the first 30 minutes or so. Therefore, the index value calculation unit 103 may calculate the third index value without using the measurement value (first index value) during this period when the flow rate is unstable. This is the same when the above-mentioned cross-correlation analysis is applied, and also when the increase/decrease match number analysis or the increase/decrease match rate analysis is applied.

(Combining multiple different methods)
The index value calculation unit 103 may also calculate the third index value using a plurality of different methods and calculate a final third index value based on the calculation results. For example, the index value calculation unit 103 may calculate the third index value using three methods: cross-correlation analysis, increase/decrease match number analysis, and increase/decrease match rate analysis. For each of the three methods, the index value calculation unit 103 may calculate the third index value for both a pattern that uses measured values from the period when the flow rate is unstable and a pattern that does not use measured values. This allows six different third index values to be calculated.

By calculating the final third index value based on these six different third index values, the index value calculation unit 103 can calculate a more stable third index value than when only one third index value is calculated using one method. For example, the index value calculation unit 103 may calculate, as the final third index value, the average of the remaining two third index values, excluding the largest and second largest, and the smallest and second smallest, of the six different third index values. Of course, this calculation method is just one example, and the index value calculation unit 103 may, for example, calculate the average or median of multiple third index values calculated using multiple methods as the final third index value.

[Conversion]
If the dehydrator 9 is a screw press dehydrator, the screw rotation speed of the dehydrator 9 may change during the measurement period of the first index value and the second index value. As will be explained in detail below, the screw rotation speed is an operating condition that affects the residence time of sludge in the dehydrator 9, so if the screw rotation speed changes, it may become difficult to calculate an appropriate third index value. The conversion unit 102 is provided to deal with such problems.

Specifically, the conversion unit 102 converts the measurement time of the first index value in the time series into the integrated value of the screw rotation speed of the dehydrator 9 up to that measurement time. Similarly, the conversion unit 102 converts the measurement time of the second index value in the time series into the integrated value of the screw rotation speed of the dehydrator 9 up to that measurement time. The index value calculation unit 103 then calculates the third index value using the value obtained by converting the measurement times of the first index value and the second index value into the integrated value of the screw rotation speed of the dehydrator 9 up to that measurement time.

As a result, the third index value is calculated based on the time axis shift of the time-series change taking into account changes in the screw rotation speed, making it possible to calculate an appropriate third index value even when the screw rotation speed is changed.

Figure 5 shows time-series measurement result data D1 of the flow rate per unit time of the liquid supplied to the dehydrator 9 when the screw rotation speed is changed during the dehydration process, and time-series measurement result data D2 of the opening degree of the back pressure plate. Note that while the horizontal axis in the graphs shown in Figures 3 and 4 is in units of time, the horizontal axis of the graph in Figure 5 is the cumulative screw rotation speed.

In this example, as shown by the dashed-dotted line in Figure 5, the screw rotation speed is changed from 0.15 (rpm) to 0.20 (rpm) when the cumulative screw rotation speed reaches R. This change in the screw rotation speed (more accurately, the number of rotations per unit time) affects the time-series changes in both the flow rate per unit time of the liquid supplied to the dehydrator 9 and the opening of the back pressure plate, but there is a lag in the timing at which this effect appears. For this reason, if the horizontal axis of the graph representing measurement result data D1 and D2 were to be in units of time, moving measurement result data D2 along the time axis would not match the pattern of measurement result data D1, making it difficult to calculate a valid third index value.

In contrast, when the horizontal axis of the graph representing measurement result data D1 and D2 is expressed in units of the cumulative number of screw rotations, as shown in Figure 5, the peaks of measurement result data D1 and data D3, which is measurement result data D2 shifted by r along the time axis, overlap and their patterns match. Therefore, r can be said to indicate the shift along the time axis between the time series changes in the first index value and the time series changes in the second index value, and the index value calculation unit 103 can calculate this r as the third index value.

The index value calculation unit 103 may also convert the calculated r into time. For example, if r = 3 when the screw rotation speed is 0.20 (revolutions/minute), the index value calculation unit 103 may set the third index value to 15 minutes. Note that even when conversion is performed, the third index value can be calculated using the same method as when conversion is not performed.

[Generation of training data]
The following describes a method for generating training data by the training data generating unit 104. The training data generated by the training data generating unit 104 is training data for generating a prediction model that predicts the moisture content of the dehydrated cake from index values related to the properties of the liquid (liquid containing suspended solids) supplied to the dehydrator 9.

The index value may be any value related to the moisture content of the dehydrated cake. For example, the index value may be at least one of the following: data on the flow rate per unit time of the liquid supplied to the dehydrator 9 or the concentration of suspended solids; data on the chemicals supplied to the flocculator 5 (chemical supply flow rate, ratio of the amount of chemical to the amount of liquid, i.e., chemical dosing rate, etc.); data on the liquid in the flocculator 5 (floc size or various index values related thereto); data indicating the operating conditions of the flocculator 5 (agitation speed, etc.); and data indicating the operating conditions of the dehydrator 9 (screw rotation speed, operating time, input pressure, etc.). The index value related to the liquid in the flocculator 5 may be obtained, for example, by analyzing images captured by the image capture device 72 shown in FIG. 2. The value used to calculate the third index value can be used for the flow rate per unit time of the liquid supplied to the dehydrator 9.

These index values may be time-series data measured during the measurement period of the first index value and the second index value. Furthermore, even index values measured after the measurement period of the first index value and the second index value can be used to generate training data, as long as the dwell time at the time the index value was measured has not changed significantly from the dwell time indicated by the third index value.

For example, suppose the properties of the liquid to be treated change from day to day and multiple dehydration processes are performed in one day. In this case, the first index value and the second index value may be measured during one of the multiple dehydration processes. The training data generation unit 104 may then generate training data using a third index value calculated from the measured first index value and second index value, and the index values measured during each dehydration process performed that day.

The teacher data generation unit 104 selects an index value from the time series of index values to be associated with the measured moisture content of the dehydrated cake based on the residence time indicated by the third index value. For example, the teacher data generation unit 104 may associate the moisture content of dehydrated cake discharged at a certain time with an index value measured at a time point that is the residence time indicated by the third index value before that time, and use this as teacher data.

For example, if the residence time indicated by the third index value is 45 minutes, the training data generation unit 104 may associate the moisture content measured for the dehydrated cake discharged at 12:00 with the index value measured at 11:15, and use this as training data. Note that, when the moisture content is measured with a moisture meter, the measurement time is used as the moisture content and the discharge time of the dehydrated cake. For example, when the user collects the dehydrated cake and measures it manually, the user may input the time the dehydrated cake was collected via the input unit 13.

Furthermore, if the third index value indicates the screw rotation speed of the dehydrator 9, the training data generation unit 104 can calculate the residence time from the screw rotation speed indicated by the third index value and the screw rotation speed (number of rotations per unit time). Note that the process of calculating the residence time from the screw rotation speed may be performed by the index value calculation unit 103 or the conversion unit 102.

As described above, the training data generation unit 104 associates the moisture content of the dehydrated cake discharged from the dehydrator 9 at a certain time with an index value related to the liquid properties measured at a time derived based on the residence time identified using the third index value and the certain time, and generates training data to be used in training a prediction model that predicts the moisture content of the dehydrated cake from the index value. This makes it possible to automatically generate training data to be used in training a prediction model that predicts the moisture content of the dehydrated cake.

The information processing device 1 may also be equipped with a learning unit that uses the training data generated as described above to generate a prediction model that predicts the moisture content of dehydrated cake or to update an already generated prediction model. This makes it possible to generate or update a prediction model using newly measured index values as frequently as necessary without requiring the user's effort, and also makes it possible to maintain high moisture content prediction accuracy.

Here, as described above, the index value calculation unit 103 may calculate the third index value using a plurality of different methods. When the index value calculation unit 103 calculates the third index value using a plurality of different methods, the teacher data generation unit 104 may generate teacher data based on at least one of the third index values if the difference between the plurality of third index values calculated using the plurality of different methods is within a predetermined tolerance range.

If the calculation method changes, the calculated third index value may also differ. If the calculated multiple third index values deviate from each other, it is possible that any or all of those third index values are invalid.

In this regard, as described above, if a configuration is adopted in which, when the difference between multiple third index values calculated using multiple different methods is within a predetermined tolerance range, training data is generated based on at least one of the third index values, the possibility of generating inappropriate training data based on an inappropriate third index value can be reduced.

Note that if the index value calculation unit 103 calculates the third index value using three or more methods, the teacher data generation unit 104 may select two of the third index values and determine whether the difference between them is within a predetermined tolerance range. For example, the index value calculation unit 103 may calculate the third index value using six methods, and calculate the average of two third index values excluding the largest and second largest, and the smallest and second smallest, as the final third index value. In this case, the teacher data generation unit 104 may select two third index values to use in calculating the final third index value and determine whether the difference between them is within a predetermined tolerance range.

[Control to vary index value]
Here, the device control unit 105 will be described. The device control unit 105 controls the operation of various devices that are components of the control system 100. As shown in FIG. 2 , this control may be performed via the control device 3. Alternatively, the device control unit 105 may perform this control without the control device 3. As will be described below, the device control unit 105 may perform control to calculate an appropriate third index value.

Here, in order to accurately identify the time axis offset between the time series changes in the first index value and the time series changes in the second index value, it is desirable that both of these time series changes be distinctive (for example, have bumps and dips when graphed, as in the example of Figure 3, etc.). However, for example, if the properties of the liquid supplied to the dehydrator 9 are continuously stable, the time series changes in the first index value will be small, and the time series changes in the linked second index value will also be small, making it difficult to identify the time offset between them.

Therefore, the equipment control unit 105 may vary the first index value and the second index value by performing predetermined control on a predetermined device related to dehydration of a liquid containing suspended solids during the period in which the first index value and the second index value are measured.

This makes it easier to identify the time axis deviation between the time series changes in the first index value and the time series changes in the second index value, even when the properties of the liquid containing suspended solids being supplied remain stable, making it possible to calculate an appropriate third index value.

The above-mentioned specified device may be any device that can affect the time-series changes in the first index value and the second index value. For example, the device control unit 105 may control the drug supply device to the flocculator 5 to change the drug supply flow rate or drug injection rate during the measurement period of the first index value and the second index value. Also, for example, the device control unit 105 may control the flocculator 5 to change the stirring speed during that period.

[Processing flow]
The flow of the process (index value calculation method) executed by the information processing device 1 will be described with reference to Fig. 6. Fig. 6 is a flowchart showing an example of the process executed by the information processing device 1. Note that before the process of Fig. 6 starts, a spin-drying process is performed by the spin-drying machine 9, and the first index value and the second index value are measured during the process. During this period, the device control unit 105 may vary the first index value and the second index value by performing predetermined control on a predetermined device related to the spin-drying of the liquid.

In S1 (data acquisition step), the data acquisition unit 101 acquires a time-series first index value related to the properties of the liquid containing suspended solids that is supplied to the dehydrator 9, and a time-series second index value that reflects the dehydration of the dehydrated cake that is discharged after the liquid is dehydrated in the dehydrator 9. The method for acquiring the first index value is not particularly limited; for example, the data acquisition unit 101 may acquire the first index value input by the user via the input unit 13, or may acquire the first index value via the communication unit 12 from a device that measures the first index value. The same applies to the second index value.

In S2, the conversion unit 102 converts the measurement times of the first index value and the second index value acquired in S1 into the integrated value of the screw rotation speed of the dehydrator 9 up to the measurement time. Note that the data required for the conversion, such as the screw rotation speed, may be input by the user via the input unit 13, or may be acquired from the control device 3 or the like via the communication unit 12. Furthermore, if the screw rotation speed of the dehydrator 9 has not changed during the measurement period of the first index value and the second index value, or if the dehydrator 9 is not a screw press dehydrator, the processing of S2 is omitted.

In S3 (index value calculation step), the index value calculation unit 103 calculates a third index value indicating the retention time of the liquid inside the dehydrator 9 based on the deviation in the time axis direction between the time series change of the first index value and the time series change of the second index value. As explained in the section "Method for calculating the third index value," various methods can be applied to calculate the third index value.

In S4, the training data generation unit 104 uses the third index value calculated in S3 to generate training data to be used in training a prediction model that predicts the moisture content of the dehydrated cake, and the processing in Figure 6 is now complete. The method for generating training data is as described in the section "Generation of Training Data." Note that the processing in S4 may be performed by a device other than the information processing device 1, in which case the processing in S4 is omitted.

As described above, the index value calculation method of this embodiment includes a data acquisition step (S1) that acquires a first time-series index value related to the properties of the liquid containing suspended solids that is supplied to the dehydrator 9 and a second time-series index value that reflects the dehydration of the dehydrated cake that is discharged after the liquid is dehydrated in the dehydrator 9, and an index value calculation step (S3) that calculates a third index value that indicates the residence time of the liquid inside the dehydrator 9 based on the shift in the time axis between the time-series changes of the first index value and the time-series changes of the second index value. Therefore, it is possible to calculate the third index value, which is an index value that indicates the residence time of the liquid containing suspended solids that is retained inside the dehydrator 9.

[Modification]
The execution entity of each process described in the above embodiment is arbitrary and is not limited to the above example. For example, each step of the index value calculation method shown in Figure 6 can be shared among multiple information processing devices. In other words, the index value calculation method may be executed by one information processing device 1 or by multiple information processing devices.

[Software implementation example]
The functions of the information processing device 1 (hereinafter referred to as the "device") can be realized by a program for causing a computer to function as the device, and a program (index value calculation program) for causing a computer to function as each control block of the device (particularly each part included in the control unit 10).

In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., a memory) as hardware for executing the program. The functions described in each of the above embodiments are realized by executing the program using this control device and storage device.

The above program may be stored non-transitory on one or more computer-readable storage media. These storage media may or may not be included in the device. In the latter case, the program may be supplied to the device via any wired or wireless transmission medium.

Furthermore, some or all of the functions of each of the above control blocks can be realized by logic circuits. For example, integrated circuits incorporating logic circuits that function as each of the above control blocks are also included in the scope of the present invention. Additionally, the functions of each of the above control blocks can also be realized by, for example, a quantum computer.

The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention.

REFERENCE SIGNS LIST 1 Information processing device 101 Data acquisition unit 103 Index value calculation unit 104 Teacher data generation unit 105 Device control unit

Claims (8)

a data acquisition unit that acquires a plurality of first index values relating to the properties of a liquid containing suspended solids that is supplied to the dehydrator, the plurality of first index values being measured over time, and a plurality of second index values that reflect the dehydration of a dehydrated cake that is discharged after the liquid is dehydrated in the dehydrator , the plurality of second index values being measured over time ;
an index value calculation unit that calculates a third index value indicating a retention time of the liquid inside the dehydrator based on a time axis shift between a pattern of change over time of the first index value and a similar pattern of change over time of the second index value ,
The index value calculation unit
(1) A shift amount obtained by cross-correlation analysis using a first function that indicates a change over time in the first index value, derived from the plurality of first index values measured over time, and a second function that indicates a change over time in the second index value, derived from the plurality of second index values measured over time, when the second function is shifted in the time axis direction so as to maximize the correlation between the first function and the second function; and
(2) An information processing device that calculates the third index value based on at least one of the amount of shift when the second index value in the time series is shifted along the time axis so that the number of matches or the rate of matches of the increase/decrease patterns from the previous value in chronological order for the first index value and the second index value are maximized . the dehydrator is a screw press dehydrator,
2. The information processing device according to claim 1, wherein the index value calculation unit calculates the third index value using a value obtained by converting the measurement times of the first index value and the second index value into an integrated value of the screw rotation speed of the dehydrator up to the measurement time. the first index value indicates a flow rate per unit time of the liquid supplied to the dehydrator;
3. The information processing apparatus according to claim 1, wherein the second index value indicates an opening degree between a back pressure plate that applies back pressure in a discharge section of the dehydrator and the discharge section. The information processing device of claim 1 or 2 further comprises a training data generation unit that associates the moisture content of the dehydrated cake discharged from the dehydrator at a certain time with an index value related to the properties of the liquid measured at a time derived based on the residence time identified using the third index value and the certain time, and generates training data to be used in training a prediction model that predicts the moisture content of the dehydrated cake from the index value. the index value calculation unit calculates the third index value using a plurality of different methods;
5. The information processing device according to claim 4, wherein the teacher data generation unit generates the teacher data based on at least any of the third index values calculated by a plurality of different methods when a difference between the third index values is within a predetermined tolerance range. The information processing device of claim 1 or 2, further comprising an equipment control unit that performs predetermined control on a predetermined device related to dehydration of the liquid during the period in which the first index value and the second index value are measured, thereby varying the first index value and the second index value. An index value calculation method executed by one or more information processing devices,
a data acquisition step of acquiring a plurality of first index values in a time series relating to the properties of a liquid containing suspended solids supplied to a dehydrator, the plurality of first index values being measured over time, and a plurality of second index values reflecting the dehydration of a dehydrated cake discharged after the liquid is dehydrated in the dehydrator , the plurality of second index values being measured over time ;
an index value calculation step of calculating a third index value indicating a retention time of the liquid inside the dehydrator based on a time axis difference between a pattern of change over time of the first index value and a similar pattern of change over time of the second index value ,
In the index value calculation step,
(1) A shift amount obtained by cross-correlation analysis using a first function that indicates a change over time in the first index value, derived from the plurality of first index values measured over time, and a second function that indicates a change over time in the second index value, derived from the plurality of second index values measured over time, when the second function is shifted in the time axis direction so as to maximize the correlation between the first function and the second function; and
(2) An index value calculation method in which the third index value is calculated based on at least one of the amount of shift when the second index value in the time series is shifted along the time axis so that the number of matches or the rate of matches of the increase/decrease patterns from the previous value in chronological order for the first index value and the second index value are maximized. An index value calculation program for causing a computer to function as the information processing device described in claim 1, the index value calculation program causing a computer to function as the data acquisition unit and the index value calculation unit.