Method and system for evaluating health degree of speed regulation system of hydroelectric generating set

Abstract

The invention provides a hydroelectric generating set speed regulation system health degree evaluation method and system. Core indexes covering a speed regulation oil system (oil pressure stability and oil mass sufficiency), working condition performance (guide vane closing time, primary frequency modulation response time and unit slip load), historical states (operation age limit and maintenance record) and the like are established from power plant monitoring data; and obtaining subjective and objective weights of the indexes by using an analytic hierarchy process and an entropy weight method, calculating a combined weight countermeasure model through a game theory, determining an optimization function, and solving an optimal combined coefficient. And respectively defining positive and negative ideal solutions of each index through a TOPSIS health assessment model, calculating Euclidean distances from an assessment object to the positive and negative ideal solutions, and quantifying the health state of the equipment through relative proximity. A dynamic health score is calculated to quantify the health degree of the speed regulation system, three-level threshold values are divided, corresponding maintenance strategies are formulated according to different threshold values, instantaneous interference misinformation is restrained in combination with a time decay factor, and more accurate health degree evaluation of the speed regulation system of the hydroelectric generating set is achieved.

Description

Technical Field

[0001] The present invention relates to a method and system for evaluating the health of a hydropower unit speed regulation system, and belongs to the field of fault feature extraction and status evaluation of hydropower units. Background Art

[0002] As the core control equipment of a hydropower plant, the health of a hydropower unit's speed regulation system directly impacts the stability of key parameters such as the unit's speed and frequency, which in turn affects the stability and power supply quality of the entire power grid. Accurately assessing the health of the speed regulation system can promptly identify potential faults and implement preventative maintenance measures to avoid grid fluctuations or even power outages caused by speed regulation system failures. Health assessments can help rationally plan equipment maintenance and overhauls, avoiding over- or under-repair, extending equipment life, improving operational efficiency, reducing operating costs, and enhancing the economic benefits of the hydropower plant.

[0003] Current technical approaches to evaluating the health of hydropower unit speed regulation systems primarily focus on establishing health assessment models based on big data platforms and evaluating the health of speed regulation systems based on prior knowledge. Data-based assessment methods primarily rely on the large amounts of data generated during the operation of the speed regulation system. Through data collection, feature extraction, model building, and training, the health status of the speed regulation system can be assessed and predicted. Prior knowledge represents the knowledge and experience of domain experts regarding speed regulation system fault diagnosis and health assessment in the form of rules and frameworks, building the expert system's knowledge base and inference engine. When the speed regulation system's operating data or fault symptoms are input, the expert system can infer and judge based on the rules in the knowledge base, providing a health status assessment result and corresponding maintenance recommendations for the speed regulation system.

[0004] The method of building a health assessment model based on a big data platform relies on a large amount of high-quality operating data. However, in actual applications, the data may be noisy, missing, or incomplete, affecting the availability of the data and the reliability of the assessment results. At the same time, extracting effective fault characteristics from massive amounts of data is also a challenge, requiring in-depth domain knowledge and data analysis skills. Otherwise, important fault information may be missed or irrelevant information may be extracted. Methods based on prior knowledge are highly dependent on the experience and knowledge of domain experts, but expert knowledge is often subjective and limited, and may differ between different experts, making it difficult to fully cover all possible fault conditions. In addition, with the iterative updates of the unit, the expert system may be unable to make accurate diagnoses and assessments in a timely manner when faced with new problems. Summary of the Invention

[0005] This invention provides a method and system for evaluating the health of a hydropower unit's speed regulation system. This system utilizes the operating parameters of relevant components of the system to construct health evaluation indicators. Game theory is used to weight the indicators of each component, and a TOPSIS method is used to establish a health assessment model. This approach aims to provide a more effective new approach for evaluating the health of hydropower unit speed regulation systems. This approach addresses the problems discussed in the background art.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0007] A method for evaluating the health of a hydropower unit speed control system:

[0008] Obtain monitoring data of the hydropower unit speed control system;

[0009] Constructing a comprehensive evaluation indicator system based on the monitoring data;

[0010] The combined weighting method based on game theory determines the weight of each indicator;

[0011] Input the combined weighted indicators into the pre-built TOPSIS health evaluation model,

[0012] The TOPSIS health evaluation model calculates the health score of the hydropower unit speed control system;

[0013] The health condition of the speed control system of the hydropower unit is evaluated according to the health level grade of the health score.

[0014] Furthermore, the comprehensive evaluation index system includes oil system indicators:

[0015] ;

[0016] ;

[0017] ;

[0018] ;

[0019] ;

[0020] ;

[0021] in, represents the pressure fluctuation rate during stable operation, Indicates the maximum pressure during the observation period, Indicates the minimum pressure value during the observation period, Indicates the rated pressure set by the system; Indicates the oil-gas volume ratio in the pressure tank, represents the volume of gas, Indicates oil volume; Indicates the proportion of time that the oil temperature is in the safe operating range, Indicates the cumulative running time when the oil temperature is within the range of 10-50℃. Indicates the total running time; Indicates the cooling system's efficiency in regulating oil temperature. Indicates the cooler inlet oil temperature, Indicates the cooler outlet oil temperature, Indicates the ambient temperature; Indicates the oil pump efficiency, 、 Respectively represent the pressure of the pressure tank at the beginning and end of the oil pump operation. 、 Respectively represent the start time and end time of the oil pump; Indicates the oil-water ratio, 、 represent the volume of oil and the volume of water respectively.

[0022] Furthermore, the comprehensive evaluation index system includes operating performance indicators:

[0023] ;

[0024] ;

[0025] ;

[0026] ;

[0027] ;

[0028] ;

[0029] in, 、 、 They represent the closing speed of guide vane segment 1 and segment 2 and the linear closing speed respectively. 、 They represent the maximum guide vane opening and the guide vane segment closing turning opening respectively. 、 、 They represent the moment when the guide vane opens to the maximum, the turning point and the fully closed moment respectively; Indicates the delay from when the grid frequency crosses the dead zone to when the unit’s active power starts to change. Indicates the time it takes for active power to become stable and the fluctuation is ≤±1%. 、 、 They respectively represent the moment when the active power changes for the first time, the moment when the frequency crosses the dead zone, and the moment when the active power stabilizes; Indicates the instantaneous drop ratio of the unit when the load drops. 、 、 They represent the load before disturbance, the lowest load during regulation, and the given power respectively.

[0030] Furthermore, the comprehensive evaluation index system includes historical status index statistics of the number of actions of various relays and components of the speed control system, such as the number of times the emergency oil source valve is switched, the number of times the main distribution maintenance valve is switched, the number of times the main oil supply valve is switched, the number of times the isolation valve is switched, the number of times the lock spindle is withdrawn, the number of times the pump is run, etc. Expected lifespan and usage times The difference is the estimated remaining service life of components and relays. .

[0031] Furthermore, the method of determining the weight of each indicator based on the combined weighting method of game theory includes:

[0032] The analytic hierarchy process is used to determine the subjective weight vector of each evaluation index and establish the judgment matrix A, which is as follows:

[0033] ;

[0034] in, The importance of factor i to j is expressed by comparing each factor pairwise, using a 1-9 scale to quantify the importance: 1 means that both factors are equally important, 3 means that factor i is slightly more important than j, 5 means that factor i is significantly more important than j, 7 means that factor i is strongly more important than j, 9 means that factor i is extremely more important than j, 2, 4, 6, and 8 are the center values ​​of adjacent scales, and the reciprocal means that if j is more important than i, then ;

[0035] Calculate the weight vector and use the geometric mean method to take the nth root of the product of each row element to get , after normalization, the weight vector W1 is obtained, which is calculated as follows:

[0036] ;

[0037] ;

[0038] ;

[0039] Perform consistency test on judgment matrix A and determine consistency index And the random consistency index RI:

[0040] ;

[0041] ;

[0042] in, is the maximum eigenvalue of the matrix, CR is the random consistency ratio, when CR is less than 0.1, it proves that the weight distribution of each indicator is reasonable, otherwise it is redistributed;

[0043] Use the entropy weight method to calculate the objective weight vector of each indicator, and calculate the proportion of each sample in the indicator after standardizing the data And calculate the information entropy of the indicator , calculated as follows:

[0044] ;

[0045] ;

[0046] ;

[0047] A game theory model is constructed to minimize the sum of squares of the subjective and objective weight differences obtained through the AHP and entropy weight method. The calculation formula is as follows:

[0048] ;

[0049] ;

[0050] in, represents the final combination weight, is the subjective weight obtained through the hierarchical analysis method, represents the objective weight obtained by the entropy weight method, 、 represents the combination coefficient, and the constraints are that the sum of the weights and the sum of the combination coefficients are 1;

[0051] The optimization function is constructed by Lagrange multiplier method to find the optimal combination coefficient L; ;

[0052] In the formula is the Lagrange multiplier;

[0053] Respectively , Find the partial derivatives and solve the simultaneous equations to get the combination coefficients as follows:

[0054] ;

[0055] ;

[0056] ;

[0057] The calculated combination weight is .

[0058] Furthermore, the method for calculating the health score of the hydropower unit speed control system using the TOPSIS health evaluation model includes:

[0059] The index data after portfolio weighting is processed positively, and extremely small and interval data are converted into extremely large data. The calculation method is as follows:

[0060] ;

[0061] ;

[0062] The obtained extremely large indicators are normalized to eliminate the dimension and a weighted matrix is ​​constructed based on the combined weights obtained in S2 The specific calculation method is as follows:

[0063] ;

[0064] ;

[0065] Calculate the optimal solution of the indicator and the worst solution , calculated as follows:

[0066] ;

[0067] ;

[0068] Calculate separately Euclidean distance to the forward ideal solution The Euclidean distance between the sum and the negative ideal solution ;

[0069] ;

[0070] ;

[0071] Calculating Healthy Fit , The closer to 1, the better the health status:

[0072] ;

[0073] Health score of hydropower unit speed control system .

[0074] Furthermore, the method for evaluating the health status of the hydropower unit speed control system according to the health level classification of the health score includes:

[0075] Health threshold settings: Yellow warning: 80 ≤ S < 90: The threshold corresponds to the 90th percentile of the historical health data score, indicating a slight performance fluctuation of the device; Orange warning: 60 ≤ S < 80: The threshold corresponds to the 70th percentile, indicating a continuous deviation of key parameters; Red warning: S < 60: The threshold corresponds to the 50th percentile, indicating the risk of core function failure;

[0076] The time decay factor is introduced to perform confidence-weighted calculation on the system health to suppress false alarms caused by transient interference. The calculation method is as follows:

[0077] ;

[0078] in, represents the time decay factor, represents the weighted health score, only if If the value remains below the threshold for 3 minutes, the warning is confirmed to be effective.

[0079] A second aspect of the present invention provides a health evaluation system for a hydropower unit speed control system, comprising:

[0080] Data module, used to obtain monitoring data of the hydropower unit speed control system;

[0081] An indicator construction module, used to construct a comprehensive evaluation indicator system based on the monitoring data;

[0082] The combined weighting module is used to determine the weight of each indicator based on the combined weighting method of game theory;

[0083] The health assessment module is used to input the combined weighted indicators into a pre-built TOPSIS health assessment model, wherein the TOPSIS health assessment model calculates the health score of the hydropower unit speed regulation system; and evaluates the health status of the hydropower unit speed regulation system according to the health level classification of the health score.

[0084] A third aspect of the present invention provides a computer-readable storage medium storing one or more programs, characterized in that: the one or more programs include instructions, which, when executed by a computing device, enable the computing device to perform any of the above methods.

[0085] A fourth invention of the present invention provides a computing device, comprising:

[0086] One or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs include instructions for performing any of the methods described above.

[0087] The beneficial effects achieved by the present invention are:

[0088] This invention proposes a method and system for evaluating the health of a hydropower unit's speed regulation system. Core indicators, including the speed regulation oil system (such as oil pressure stability and oil adequacy), operating performance (such as guide vane closing time, primary frequency regulation response time, and unit slippage load), and historical status (operating age and maintenance records), are established from power plant monitoring data. The subjective and objective weights of these indicators are determined using the analytic hierarchy process (AHP) and entropy weighting method. A combined weighted game model is then calculated using game theory to determine the optimization function and solve for the optimal combination coefficient, ultimately yielding the combined weights. A health assessment model is constructed using TOPSIS, defining positive and negative ideal solutions for each indicator. The Euclidean distance from the assessment object to the positive and negative ideal solutions is calculated, and the equipment health is quantified using relative proximity. A dynamic health score is calculated to quantify the health of the speed regulation system. Three threshold levels are then assigned, and corresponding maintenance strategies are developed based on these thresholds. A time decay factor is then incorporated to suppress false alarms from transient disturbances, enabling more accurate health assessment of the hydropower unit's speed regulation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 This is a flow chart of a method for evaluating the health of a hydropower unit speed control system according to the present invention;

[0090] Figure 2 This is a schematic diagram of the combination weighting process in the present invention;

[0091] Figure 3 Schematic diagram of the calculation process of the TOPSIS health assessment model in the present invention;

[0092] Figure 4 Schematic diagram of the health evaluation system of the hydropower unit speed control system of the present invention. DETAILED DESCRIPTION

[0093] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and are not intended to limit the scope of protection of the present invention.

[0094] Example 1:

[0095] The embodiment of the present invention proposes a method for evaluating the health of a hydropower unit speed control system based on game theory combined weighting and TOPSIS, as shown in FIG. Figure 1-3 , the specific implementation steps are as follows:

[0096] Step 1: Establish a comprehensive evaluation index system. Based on the power plant monitoring data, establish core indicators covering the speed control oil system (such as oil pressure stability and oil adequacy), operating performance (such as guide vane closing time, primary frequency regulation response time, unit load), and historical status (operating years, maintenance records). The establishment process is as follows:

[0097] (1) Constructing oil system indicators including: steady-state pressure fluctuation rate , oil-gas ratio stability , oil temperature qualified rate , oil cooling efficiency , oil pump operating efficiency , oil-water ratio .

[0098] in, represents the pressure fluctuation rate during stable operation, Indicates the maximum pressure during the observation period, Indicates the minimum pressure value during the observation period, Indicates the rated pressure set by the system; Indicates the oil-gas volume ratio in the pressure tank, represents the volume of gas, Indicates oil volume; Indicates the proportion of time that the oil temperature is in the safe operating range, Indicates the cumulative running time when the oil temperature is within the range of 10-50℃. Indicates the total running time; Indicates the cooling system's efficiency in regulating oil temperature. Indicates the cooler inlet oil temperature, Indicates the cooler outlet oil temperature, Indicates the ambient temperature; Indicates the oil pump efficiency, 、 Respectively represent the pressure of the pressure tank at the beginning and end of the oil pump operation. 、 Respectively represent the start time and end time of the oil pump; Indicates the oil-water ratio, 、 represent the volume of oil and the volume of water respectively.

[0099] (2) The performance indicators of the constructed working conditions include: guide vane closing speed (segmented closing, linear closing) 、 、 , one frequency modulation response time (response lag time, complete response time) 、 , the unit runs at slip load .

[0100] in, 、 、 They represent the guide vane segmented closing speed and linear closing speed respectively. 、 They represent the maximum guide vane opening and the guide vane segment closing turning opening respectively. 、 、 They represent the moment when the guide vane opens to the maximum, the turning point and the fully closed moment respectively; Indicates the delay from when the grid frequency crosses the dead zone to when the unit’s active power starts to change. Indicates the time it takes for active power to become stable and the fluctuation is ≤±1%. 、 、 They respectively represent the moment when the active power changes for the first time, the moment when the frequency crosses the dead zone, and the moment when the active power stabilizes; Indicates the instantaneous drop ratio of the unit when the load drops. 、 、 They represent the load before disturbance, the lowest load during regulation, and the given power respectively.

[0101] (3) Establish historical status indicators, including statistics on the number of actions of various relays and components in the speed control system, such as the number of times the emergency oil source valve is switched on and off, the number of times the main distribution maintenance valve is switched on and off, the number of times the main oil supply valve is switched on and off, the number of times the isolation valve is switched on and off, the number of times the lock spindle is withdrawn, the number of times the pump is run, etc., and the number of times it has been used Expected lifespan and usage times The difference is the estimated remaining service life of components and relays. : .

[0102] Step 2: Using game theory to combine weights, we first need to determine the subjective and objective weights of each indicator. The subjective weights are determined by the analytic hierarchy process, and the objective weights are confirmed by the entropy weight method. Then, a combined weight strategy model is constructed to determine the optimization function and solve the optimal combination coefficient to finally obtain the combined weight.

[0103] Step 21: Use the analytic hierarchy process to determine the subjective weight vector of each evaluation index. First, establish the judgment matrix A. ,in To express the importance of factor i to j, we compare each factor pairwise and use the 1-9 scale to quantify the importance. The specific table is as follows:

[0104]

[0105] Step 22: Calculate the weight vector and use the geometric mean method to take the nth root of the product of each row element to get , , normalization processing , and then get the weight vector .

[0106] Step 23: Perform consistency test on the judgment matrix A and determine the consistency index And the random consistency index RI, calculate the random consistency ratio ,in is the maximum eigenvalue of the matrix, CR is the random consistency ratio, when CR is less than 0.1, it proves that the weight distribution of each indicator is reasonable, otherwise it is redistributed.

[0107] Step 24: Use the entropy weight method to calculate the objective weight vector of each indicator, standardize the data and calculate the proportion of each sample in the indicator And calculate the information entropy of the indicator , and finally get the objective weight ,in Represents the original value of the jth indicator of the i-th sample.

[0108] Step 25: Construct a game theory model to minimize the sum of squares of the subjective and objective weight differences obtained by the AHP and entropy weight method. The calculation method is:

[0109] ;

[0110] ;

[0111] in, represents the final combination weight, is the subjective weight obtained through the hierarchical analysis method, represents the objective weight obtained by the entropy weight method, 、 Represents the combination coefficient. The constraints are that the sum of the weights and the sum of the combination coefficients must be 1.

[0112] Step 26: Use the Lagrange multiplier method to construct an optimization function to find the optimal combination coefficient. The specific calculation method is as follows:

[0113] ;

[0114] in, is the Lagrange multiplier.

[0115] Step 27: , Find partial derivatives Simultaneous equations Solve to get the combination coefficient .

[0116] Step 28: Calculate the final combination weight .

[0117] Step 3: Establish a TOPSIS health assessment model. Build a weighted normalized matrix based on the combined weights. Define the positive and negative ideal solutions for each indicator, calculate the Euclidean distance from the assessment object to the positive and negative ideal solutions, and quantify the equipment health status through relative proximity. This allows for dynamic assessment based on the fusion of subjective and objective weights, eliminates dimensional differences, and enhances the interpretability of the degradation trend. The establishment method is as follows:

[0118] Step 31: Perform positive processing on the indicator data to convert extremely small and interval data into extremely large data. The specific calculation method is as follows:

[0119] ;

[0120] ;

[0121] Step 32: Normalize the obtained extremely large indicators, eliminate the dimension and construct the weighting matrix based on the combined weights obtained in step 2 The specific calculation method is as follows:

[0122] ;

[0123] ;

[0124] Step 33: Calculate the optimal solution of the indicator (Forward ideal solution) and worst solution (Negative ideal solution).

[0125] Step 34: Calculate separately Euclidean distance to the forward ideal solution The Euclidean distance between the sum and the negative ideal solution .

[0126] Step 35: Calculate the fit The closer the fit is to 1, the better the health condition.

[0127] Step 4: System health graded warning: further calculate the system health score based on the TOPSIS health closeness obtained in S3, suppress instantaneous false alarms through the time decay factor, set the health threshold and give graded response measures.

[0128] Step 41: Calculate the health score based on the fit obtained from the TOPSIS health evaluation model , calculate the system health score .

[0129] Step 42: Health threshold setting: Yellow warning (80 ≤ S < 90): The threshold corresponds to the 90th percentile of the historical health data score, indicating that the equipment has a slight performance fluctuation (such as abnormal oil pressure pulsation but not exceeding the limit); Orange warning (60 ≤ S < 80): The threshold corresponds to the 70th percentile, indicating that key parameters continue to deviate (such as a guide vane opening response delay exceeding 10%); Red warning (S < 60): The threshold corresponds to the 50th percentile, indicating the risk of core function failure (such as a main pressure regulating valve stuck and causing regulation failure).

[0130] Step 43: Introduce the time decay factor to perform confidence-weighted calculation on the system health to suppress false alarms caused by transient interference. The specific calculation method is:

[0131]

[0132] in represents the time decay factor, represents the weighted health score, only if The warning is considered valid only when the value is below the threshold for 3 consecutive minutes.

[0133] Example 2:

[0134] See also Figure 4 The embodiment of the present invention proposes a health evaluation system for a hydropower unit speed regulation system based on game theory combined weighting and TOPSIS, the system comprising:

[0135] The data acquisition module is responsible for real-time acquisition of multi-source data from the speed control system (such as main pressure regulating valve displacement, oil pressure pulsation, and guide vane opening commands). It integrates sensor signals such as vibration and temperature with SCADA system operating parameters. Noise is removed from the data through sliding window filtering (such as 10ms window averaging). High-frequency sampled data (≥10Hz) is stored in a time series database and annotated with operating condition labels (such as rated load and transient process) to provide standardized input for subsequent analysis.

[0136] The indicator construction module establishes core indicators such as the speed control oil system (such as oil pressure stability and oil adequacy), operating performance (such as guide vane closing time, primary frequency regulation response time, unit slip load) and historical status (operating years, maintenance records) based on the collected data.

[0137] The combined weighting module generates subjective weights based on the Analytic Hierarchy Process (AHP) method and objective weights using the entropy weighting method. The optimal overall weight (for example, the displacement weight of the main pressure regulating valve accounts for 28%) is determined using the game theory Nash equilibrium model. Dynamic weight updates (monthly calibration) and manual intervention (emergency bias) are supported to ensure that weights adapt to equipment aging trends.

[0138] The health assessment module constructs a weighted normalized matrix based on the combined weights, defines the positive and negative ideal solutions of each indicator respectively, calculates the Euclidean distance from the assessment object to the positive and negative ideal solutions, quantifies the health status of the equipment through relative proximity, and further calculates the health score of the system using TOPSIS health proximity. It also suppresses instantaneous false alarms through the time decay factor, sets health thresholds, and provides graded response measures.

[0139] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

[0140] Example 3:

[0141] This embodiment provides a computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions. When the instructions are executed by a computing device, the computing device executes a method for evaluating the health of a hydropower unit speed control system based on game theory combined weighting and TOPSIS.

[0142] Example 4:

[0143] This embodiment provides a computing device, comprising one or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and are configured to be executed by the one or more processors, and the one or more programs include instructions for executing a method for evaluating the health of a hydropower unit speed control system based on game theory combined weighting and TOPSIS.

[0144] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0145] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0146] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0147] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0148] The above are merely embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are included in the scope of the claims of the present invention to be approved.

Claims

1. A method for evaluating the health of a hydropower unit speed control system, characterized by: Obtain monitoring data of the hydropower unit speed control system; Constructing a comprehensive evaluation indicator system based on the monitoring data; The combined weighting method based on game theory determines the weight of each indicator; Input the combined weighted indicators into the pre-built TOPSIS health evaluation model, The TOPSIS health evaluation model calculates the health score of the hydropower unit speed control system; The health condition of the speed control system of the hydropower unit is evaluated according to the health level grade of the health score.

2. The method for evaluating the health of a hydropower unit speed control system according to claim 1, characterized in that: The comprehensive evaluation index system includes oil system indicators: ； ； ； ； ； ； in, represents the pressure fluctuation rate during stable operation, Indicates the maximum pressure during the observation period, Indicates the minimum pressure value during the observation period, Indicates the rated pressure set by the system; Indicates the oil-gas volume ratio in the pressure tank, represents the volume of gas, Indicates oil volume; Indicates the proportion of time that the oil temperature is in the safe operating range, Indicates the cumulative running time when the oil temperature is within the range of 10-50℃. Indicates the total running time; Indicates the cooling system's efficiency in regulating oil temperature. Indicates the cooler inlet oil temperature, Indicates the cooler outlet oil temperature, Indicates the ambient temperature; Indicates the oil pump efficiency, 、 Respectively represent the pressure of the pressure tank at the beginning and end of the oil pump operation. 、 Respectively represent the start time and end time of the oil pump; Indicates the oil-water ratio, 、 represent the volume of oil and the volume of water respectively.

3. The method for evaluating the health of a hydropower unit speed control system according to claim 1, characterized in that: The comprehensive evaluation index system includes working condition performance indicators: ； ； ； ； ； ； in, 、 、 They represent the closing speed of guide vane segment 1 and segment 2 and the linear closing speed respectively. 、 They represent the maximum guide vane opening and the guide vane segment closing turning opening respectively. 、 、 They represent the moment when the guide vane opens to the maximum, the turning point and the fully closed moment respectively; Indicates the delay from when the grid frequency crosses the dead zone to when the unit’s active power starts to change. Indicates the time it takes for active power to become stable and the fluctuation is ≤±1%. 、 、 They respectively represent the moment when the active power changes for the first time, the moment when the frequency crosses the dead zone, and the moment when the active power stabilizes; Indicates the instantaneous drop ratio of the unit when the load drops. 、 、 They represent the load before disturbance, the lowest load during regulation, and the given power respectively.

4. The method for evaluating the health of a hydropower unit speed control system according to claim 1, characterized in that: The comprehensive evaluation index system includes historical status index statistics of the number of actions of various relays and components of the speed control system, such as the number of times the emergency oil source valve is switched, the number of times the main distribution maintenance valve is switched, the number of times the main oil supply valve is switched, the number of times the isolation valve is switched, the number of times the lock spindle is withdrawn, the number of times the pump is run, etc. has been used. Expected lifespan and usage times The difference is the estimated remaining service life of components and relays. .

5. The method for evaluating the health of a hydropower unit speed control system according to claim 1, characterized in that: The methods for determining the weights of each indicator based on the combined weighting method of game theory include: The analytic hierarchy process is used to determine the subjective weight vector of each evaluation index and establish the judgment matrix A, which is as follows: ； in, The importance of factor i to j is expressed by comparing each factor pairwise, using a 1-9 scale to quantify importance: 1 means that both factors are equally important, 3 means that factor i is slightly more important than j, 5 means that factor i is significantly more important than j, 7 means that factor i is strongly more important than j, 9 means that factor i is extremely more important than j, 2, 4, 6, and 8 are the center values ​​of adjacent scales, and the reciprocal means that if j is more important than i, then ; Calculate the weight vector and use the geometric mean method to take the nth root of the product of each row element to get , after normalization, the weight vector W1 is obtained, which is calculated as follows: ； ； ； Perform consistency test on judgment matrix A and determine consistency index And the random consistency index RI: ； ； in, is the maximum eigenvalue of the matrix, CR is the random consistency ratio, when CR is less than 0.1, it proves that the weight distribution of each indicator is reasonable, otherwise it is redistributed; Use the entropy weight method to calculate the objective weight vector of each indicator, and calculate the proportion of each sample in the indicator after standardizing the data And calculate the information entropy of the indicator , calculated as follows: ； ； ； A game theory model is constructed to minimize the sum of squares of the subjective and objective weight differences obtained through the AHP and entropy weight method. The calculation formula is as follows: ； ； in, represents the final combination weight, is the subjective weight obtained through the hierarchical analysis method, represents the objective weight obtained by the entropy weight method, 、 represents the combination coefficient, and the constraints are that the sum of the weights and the sum of the combination coefficients are 1; The optimization function is constructed by Lagrange multiplier method to find the optimal combination coefficient L; ; In the formula is the Lagrange multiplier; Respectively , Find the partial derivatives and solve the simultaneous equations to get the combination coefficients as follows: ； ； ； The calculated combination weight is .

6. The method for evaluating the health of a hydropower unit speed control system according to claim 1, characterized in that: The method for calculating the health score of the hydropower unit speed regulation system using the TOPSIS health evaluation model includes: The index data after portfolio weighting is processed positively, and extremely small and interval data are converted into extremely large data. The calculation method is as follows: ； ； The obtained extremely large indicators are normalized to eliminate the dimension and a weighted matrix is ​​constructed based on the combined weights obtained in S2 The specific calculation method is as follows: ； ； Calculate the optimal solution of the indicator and the worst solution , calculated as follows: ； ； Calculate separately Euclidean distance to the forward ideal solution The Euclidean distance between the sum and the negative ideal solution ; ； ； Calculating Healthy Fit , The closer to 1, the better the health status: ； Health score of hydropower unit speed control system .

7. The method for evaluating the health of a hydropower unit speed control system according to claim 6, characterized in that: The method for evaluating the health status of the speed control system of a hydropower unit according to the health level classification of the health score includes: Health threshold settings: Yellow warning: 80 ≤ S < 90: The threshold corresponds to the 90th percentile of the historical health data score, indicating a slight performance fluctuation of the device; Orange warning: 60 ≤ S < 80: The threshold corresponds to the 70th percentile, indicating a continuous deviation of key parameters; Red warning: S < 60: The threshold corresponds to the 50th percentile, indicating the risk of core function failure; The time decay factor is introduced to perform confidence-weighted calculation on the system health to suppress false alarms caused by transient interference. The calculation method is as follows: ； in, represents the time decay factor, represents the weighted health score, only if If the value remains below the threshold for 3 minutes, the warning is confirmed to be effective.

8. A health evaluation system for a hydropower unit speed control system, characterized in that: include: Data module, used to obtain monitoring data of the hydropower unit speed control system; An indicator construction module, used to construct a comprehensive evaluation indicator system based on the monitoring data; The combined weighting module is used to determine the weight of each indicator based on the combined weighting method of game theory; The health assessment module is used to input the combined weighted indicators into a pre-built TOPSIS health assessment model, wherein the TOPSIS health assessment model calculates the health score of the hydropower unit speed regulation system; and evaluates the health status of the hydropower unit speed regulation system according to the health level classification of the health score.

9. A computer-readable storage medium storing one or more programs, characterized in that: The one or more programs include instructions that, when executed by a computing device, cause the computing device to perform any one of the methods according to claims 1 to 7.

10. A computing device, characterized in that include: One or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing any of the methods according to claims 1 to 7.

Images