JPH061206B2 - Plant equipment diagnosis system - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION Object of the Invention (Industrial field of application) The present invention relates to a plant facility diagnosis system for diagnosing, for example, deterioration signs of thermal power plant equipment and supporting preventive maintenance.

(Prior art) In thermal power plants, in order to grasp the power generation efficiency and the efficiency of each component of the plant as an important indicator of economic efficiency, operation data is periodically collected for performance evaluation and analysis. An evaluation is done. This allows us to grasp the deterioration status of the entire plant over time and the performance of main equipment, estimate the abnormal status of equipment from the operation plan and deterioration status including other plants, and perform detailed inspections and repairs for preventive maintenance. It is a plan.

However, the performance of periodic performance evaluation is done by using a computer at each stage such as data collection, analysis evaluation, performance calculation, etc., but setting of performance test for data collection, calculation data details, Judgment etc. is done by hand and requires a lot of labor.

Therefore, various diagnostic systems have been proposed so far for automating the functions of monitoring and abnormality diagnosis of thermal power plants. For example, in the management computer system, the measurement data from various sensors recorded for control and monitoring of steam temperature, pressure, temperature of each extraction part, feed water flow rate, generator output, etc. are periodically saved, Based on the data, performance evaluation is carried out upon request.

FIG. 7 shows a conventional example of a facility diagnostic system for a thermal power plant. In FIG. 7, thermal power plant 1
Is composed of a boiler 2, a turbine 3, a generator 4, a condenser 5, a condenser pump 6, a low-pressure feed water heater 7, a deaerator 8, a feed water pump 9, a high-pressure feed water heater 10, and the like. A control computer 12, an operation panel 13, and a management computer 14 are connected to the thermal power plant 1. Management computer 14
Is a data processing unit 15, a performance calculation unit 16, a data bank 1
7, a result display unit 18, an external information input unit 19, and the like.

The data processing unit 15 extracts necessary measurement data from the database of the data bank 17 which is stored at the time of request and periodically, and also performs an averaging process for preventing measurement error of the sensor and calculates the dispersion of data by standard deviation or the like. It has functions such as processing, detection and elimination of irrational numerical values that occur due to sensor abnormalities such as breakage.

The performance calculation unit 16 calculates the entropy and the like from the steam table from the steam temperature and pressure, analyzes based on the performance calculation formula given in advance, and calculates the correction coefficient and the like based on the measurement conditions such as atmospheric pressure and cooling water temperature. To do.

Further, the result display unit 18 displays and outputs the performance calculation result and various data displays as a list or the like.

If the deterioration of each equipment is progressing based on this display result, for example, as a means that can be done during operation, from the standpoint of preventive maintenance, such as backwash operation for cleaning the condenser thin tube Detailed inspection plans and repair plans for deteriorated equipment are implemented.

(Problems to be Solved by the Invention) In order to grasp the tendency of long-term deterioration by performance evaluation of a plant and to perform preventive maintenance of each device constituting the plant, it is necessary to judge the state of change together with the judgment of deterioration. Is essential. That is, even if the deterioration is about the same,
The abnormality factor inside the device differs depending on whether the change is a gradual progress (hereinafter referred to as a gradual change) or a rapid progress after a certain period (hereinafter referred to as a sudden change). For example, the first of the internal efficiencies of a steam turbine
At the gradual stage where the internal efficiency of the paragraph gradually changes, it is considered that the erosion or scale adhesion of the first stage nozzle is a factor. In this case, it is necessary to take measures in accordance with a relatively long-term plan and measures such as water quality control, which is the cause of occurrence, based on the history of past regular inspections. On the other hand, in the case of sudden change, loss of the first stage nozzle, damage to the moving blade, clogging of foreign matter,
Or, there may be an abnormality in the valves, etc., and urgent precision inspection is required.

Judgment based on such measurement data and performance evaluation data is conventionally performed by a skilled driver or a person in charge of repair, etc., and depends on individual judgment criteria. In addition, regarding the algorithm for determining the change state of abnormal signs, for example, in an abnormality diagnosis system that diagnoses abnormal signs based on changes in shaft vibration, whether the repeated data changes after detecting the abnormal signs in the data. Since you can check
For example, there is a means disclosed in Japanese Patent Application No. 62-260193.

However, even if it processes periodic data such as deterioration diagnosis, the same algorithm cannot be used for a long period in which the measurement interval is given in units of one day or one week. I had no choice but to rely on Judgment.

The present invention has been made in view of such a situation, by automating the determination of the change situation in the deterioration diagnosis that has been performed mainly by humans so far, on a performance evaluation system by a computer, of each plant constituent device An object of the present invention is to provide a plant facility diagnosis system that enables determination of deterioration factors, ensures reliable support for preventive maintenance of each device, and improves plant operation efficiency and further safety.

[Structure of Invention]

(Means for Solving the Problem) The present invention relates to a plant equipment diagnostic system for performing performance evaluation of a plant based on data during operation of the plant, data processing means for processing data during operation, and processing. Calculation analysis means for performing calculation analysis of the data, factor diagnosis means for diagnosing deterioration factors based on reliability of the data and transition time of data change, data bank for storing measured data and analysis result information, and The factor diagnosing means includes a data displaying means for displaying data, and the factor diagnosing means uses the data reliability evaluating means for evaluating the reliability of the data, and the predicted value of the current data and the variation degree of the data by using the data for a certain period in the past. The sudden change judgment is made based on whether or not the current calculated data exceeds the range of the sudden change reference margin defined by the above. It is within the fixed standard margin, and the diagnostic target value obtained by including the current data is the initial value defined when starting the deterioration diagnosis and the standard margin for judging the presence or absence of change defined by the data for a certain period of the initial stage. The sudden change / gradual change determining means for making a gradual change determination depending on whether or not it is within the range, the factor determining means for estimating the factor that has led to deterioration, and the reliability evaluation of the measurement data and the reliability of the factor determination are added. And a diagnostic reliability evaluation means for making a comprehensive evaluation.

(Operation) In the present invention, the operating state value of the plant is always taken in as data from the sensor, and when the operating conditions are satisfied, diagnosis / evaluation is performed at regular intervals.

In performance evaluation and the like, first, necessary operation state data is sent from the data bang to the data processing unit, and necessary preprocessing such as average value calculation for performance calculation is performed. This result is stored in a data bank and sent to the diagnostic means used, and whether the change is sudden or gradual, based on the reliability of the data and the transit time of the data change. Etc. are diagnosed. The result is displayed on the data display means.

(Embodiment) An embodiment of the present invention will be described below with reference to FIGS. 1 to 5. In addition, this embodiment is intended for a thermal power plant, and the portions common to the conventional ones are also referred to FIG. 7, and the duplicated description will be omitted.

FIG. 1 shows the procedure of the plant equipment diagnosis system. That is, the plant performance evaluation system 20 for carrying out this method includes a data processing unit 15 as a data processing means for processing data during operation, and a performance (efficiency) calculation as a calculation analysis means for carrying out calculation analysis of the processed data. Part 1
6. Factor diagnosing unit 2 as factor diagnosing means for evaluating reliability of data after evaluating reliability of data and determining factors
1, result display unit 18, data recalculation unit 22 for performing recalculation of data from display result or completion procedure after confirmation, data bank 17 for storing measurement data and analysis result and giving comparison data if necessary, sensor replacement information And a sensor management unit 23 that manages revision information of the system external environment such as device exchange information.

The factor diagnosis unit 21 is composed of a data reliability evaluation means 24, a sudden change / gradual change judgment means 25, a factor judgment means 26, and a diagnosis reliability evaluation means 27.

In the special variation / gradual variation determination means 25, the determination of a stub is that the calculated data this time exceeds the average value of the data for a certain fixed period in the past stored in the data bank and the stub determination reference value obtained from the degree of variation. Done in. Similarly, the determination of the gradual edge is performed when the predicted value (first-order approximation value) based on the above data exceeds the determination reference value recognized in the initial data at the time when the deterioration diagnosis is started. Can be automatically determined. That is, as shown in FIG. 2, the judgment of the sudden change uses the data of the past fixed period (one month in FIG. 2) and extrapolates using the least square method or the like to predict the predicted value AOS ′ of the present data. It is determined by whether or not the data A calculated this time exceeds the range defined by the sudden change criterion tolerance DAO defined by the variation degree of the data. This reference margin is calculated by standard deviation or the like, and is the following condition.

| A−AOS ′ | ≧ DAO One method, the judgment of the gradual change is, as shown in FIG. 3, the predicted value AO of the present data obtained by extrapolation based on the data of the past certain period.
The current data A is within the range defined by S ′ and the sudden change criterion tolerance DAO, and the diagnosis target value AOS obtained by including this data is the initial value AO defined when starting the deterioration diagnosis. In addition, the judgment reference margin DA1 for the presence or absence of change defined by the data for a certain period of time (one month in FIG. 3) at the initial stage
When it is out of the range specified in, it is judged to be gradual.

That is, | A-AOS '| <DAO AND | AO-AOS | ≧ DA1.

Next, the factor determining means 21 presents a method of estimating the factor that led to deterioration based on the determination of the deterioration status of each part.

FIG. 4 shows an outline of an embodiment of the judging means. That is, after evaluation of a series of changes in overall efficiency such as performance of each block, for example, high-pressure turbine section or feed water heater performance, if improvement is recognized, means for modification / repair determination routine supported by the sensor management unit 23. If there is no deterioration or change, evaluate the change in efficiency of each part.

Also here, if it is improved, the modification / repair determination routine is executed, if deterioration is recognized, the factor determination A routine is executed, and if there is no change, the factor determination B routine for checking the sensor abnormality etc. is executed. When the efficiency of each part is sequentially changed and the overall determination is completed, the result output stage is reached.

FIG. 5 shows an example of the judgment criteria used for the factor judgment A.
Judgment of change status is the main item of factor judgment.

The diagnostic reliability evaluation means 27 adds the reliability evaluation of the measurement data and the like and the reliability of the factor determination, etc., described above, and makes a comprehensive evaluation.

The following deterioration diagnosis and factor determination results are in data bank 1
7 and display the result via the man-machine interface.

Based on this display result, it is possible to complete the procedure after confirmation or change the judgment criteria or irrational data to perform the procedure for recalculation of diagnosis.

Further, the sensor management unit 23 inputs and outputs the sensor replacement information, instrumental error correction data, and history data of remodeling / repair of the device to be diagnosed, which are important factors for diagnosis, and continuously manages the data. .

As described above, by adding the sudden change / gradual change determining means in the plant equipment diagnosing system of the present embodiment, it is possible to determine the change state in the deterioration tendency without human intervention, and subsequently by the factor determining means, It is possible to estimate the factors that led to deterioration.

In the gradual change criterion shown in FIG. 3, it was determined that all data for a certain period can be used as data for calculating the sudden change criterion tolerance DAO. However, it can be seen that the reference data of the present system, which requires comparatively long-term history data, shows an abnormal value such as a sudden change during a predetermined period. FIG. 6 illustrates such a state, and the data of the state B is the value that is diagnosed as a sudden change. Therefore, when it is determined that such an abnormal value is set, a predetermined flag is set in the data bank when the data is stored, and the data can be restricted when the reference data is created.

Further, although the performance evaluation was targeted in the previous example, the present invention is not limited to this, and is applied to various automated systems for managing long-term change trends such as remaining life management and determining factors depending on the change state. can do.

〔The invention's effect〕

As described above, according to the present invention, it is possible to automatically determine the change state in the deterioration tendency such as the determination of sudden change / gradual change, and it is possible to reliably obtain the index of the factor determination that is indispensable for diagnosis. The effect that driving support and preventive maintenance can be effectively performed is exhibited.

[Brief description of drawings]

FIG. 1 is a plant performance evaluation system diagram showing an embodiment of the present invention, FIGS. 2 and 3 are graphs for explaining a method of determining a sudden change and a gradual change, and FIG. 4 is a factor determining means. FIG. 5 is a system diagram shown in FIG.
FIG. 6 is a graph for explaining another embodiment of the present invention,
FIG. 7 is a functional block diagram for explaining a conventional example. 1 ... Thermal power plant, 2 ... High / medium pressure turbine, 3 ... Low pressure turbine, 4 ... Generator, 5 ... Condenser, 6 ... Condensate pump, 7 ... Low pressure feed water heater, 8 ... Deaerator, 9 ... water supply pump, 10 ... high-pressure water heater, 11 ... boiler, 12 ... control computer, 13 ... operation panel, 14 ... management computer, 15 ... data processing means (data processing unit), 16 ... calculation analysis means (performance ( Efficiency) calculation unit), 17 ... data bank, 18 ...
Data display means (display section), 19 ... External information input section, 2
0 ... Performance evaluation system, 21 ... Factor diagnosis means (factor diagnosis section), 22 ... Recalculation section, 23 ... Sensor management section, 24 ... Data reliability evaluation means, 25 ... Sudden variation / gradual change determination means, 26
... factor determination means, 27 ... diagnostic reliability evaluation means.

Claims (1)

[Claims] 1. A plant facility diagnostic system for evaluating the performance of a plant based on the operating data of the plant, and a data processing means for processing the operating data, and a calculation for analyzing the processed data. Analysis means, factor diagnosis means for diagnosing deterioration factors based on reliability of the data and transition time of data change, data bank for storing measurement data and analysis result information, and data display means for displaying these data The factor diagnosing means comprises a data reliability evaluating means for evaluating the reliability of the data, and a sudden change reference margin defined by the predicted value of the current data and the degree of variation of the data using data of a certain period in the past. The sudden change judgment is made depending on whether or not the calculated data exceeds the range of this time, and the present time data is within the range of the sudden change judgment reference margin, 2) The value to be diagnosed including the data this time is gradually changed depending on whether it is within the range of the initial value defined when starting the deterioration diagnosis and the judgment reference margin for the presence or absence of change defined by the data for a certain period in the initial stage. A sudden change / gradual change determining means for making a determination, a factor determining means for estimating a factor leading to deterioration, and a diagnostic reliability evaluating means for adding a reliability evaluation of measurement data and a reliability of factor determination to make a comprehensive evaluation. A plant equipment diagnostic system comprising: