Compressed air energy storage power station operation state evaluation method and system

Through Spearman correlation analysis and BP neural network model, the problem of operating status evaluation of compressed air energy storage power station equipment is solved, and the automatic evaluation of operating status of power station is realized, which improves safety and stability, reduces data redundancy, and improves the Model accuracy.

CN118981665AInactive Publication Date: 2024-11-19中能建数字科技集团有限公司
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411087591.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-11-19
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

After a long period of operation of the compressed air energy storage power station, the key equipment will experience fatigue, resulting in corrosion, scaling, air leakage and other faults, making it difficult to determine the location and cause of the fault, affecting the safe and stable operation of the power station.

Method used

The Spearman correlation analysis method was used to screen the factors influencing the operating status of the equipment, and combined with the KMeans clustering and BP neural network model, an operating status evaluation model for compressors, air turbines, heat exchangers, heat storage tanks and gas storage was established. Through data acquisition and model optimization, an automated evaluation of the operating status of the power station is achieved.

Benefits of technology

It realizes a timely understanding of the health of key equipment of compressed air energy storage power stations, promptly discovering problems, improves the safety and stability of the power station, reduces data redundancy, and improves the accuracy of model modeling and operation status judgment. .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118981665A_ABST
    Figure CN118981665A_ABST
Patent Text Reader

Abstract

The invention discloses a compressed air energy storage power station operation state evaluation method and system, and belongs to the technical field of energy storage, and the method achieves the evaluation of the operation state of a compressed air energy storage power station through data collection, feature selection, data classification, model construction and optimization, and operation state evaluation. According to the method, a Spearman correlation analysis method is adopted to analyze operation data, a KMeans method is adopted to cluster load sections of each type of equipment, a BP neural network method is adopted to carry out model construction on each type of data of each type of equipment, evaluation models of the operation states of a compressor, an air turbine, a heat exchanger, a heat storage tank and a gas storage are established respectively, and the operation states of the compressor, the air turbine, the heat exchanger, the heat storage tank and the gas storage are evaluated. The method is a fully automatic method, the health degree of each kind of equipment can be known in time, problems can be found in time, and the safety and stability of power station operation are effectively improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of energy storage, and in particular relates to a method and system for evaluating the operating status of a compressed air energy storage power station. Background Art

[0002] Renewable energy has become the main source of energy. The addition of a high proportion of new energy makes the power system present a "double high" feature, bringing about the problem of unbalanced power generation. Energy storage is the key support for building a new power system. Different energy storage technologies differ in power scale, energy storage density, cycle efficiency, response time, etc. Compressed air energy storage, as a new energy storage technology, has the characteristics of large capacity, high safety, long service life, and low construction cost. It has a wide range of applications in auxiliary services such as peak regulation, frequency regulation, peak shaving and valley filling, which can effectively improve the utilization rate of new energy and reduce the phenomenon of wind and solar abandonment.

[0003] At present, most power stations are under construction, and few are put into operation. Therefore, the current research focus of compressed air energy storage technology is on process optimization design, equipment development, system integration, etc., while there is relatively little research on power station operation. After a long period of operation, the key equipment of the compressed air energy storage power station, such as the compressor, expander, heat exchanger, gas storage and other subsystems, will show fatigue, resulting in equipment corrosion, scaling, leakage and other faults, which will inevitably affect the safe and stable operation of the power station. Due to the complex structure of the entire power station system, it is difficult for operators to easily determine the location and cause of the power station fault.

[0004] Therefore, it is urgent to carry out research on the operating status assessment method of compressed air energy storage power stations, so as to timely understand the operating status of related equipment and provide safety guarantees for the operation of compressed air energy storage power stations. Summary of the invention

[0005] In view of the above-mentioned problems, the present invention discloses a method and system for evaluating the operating status of a compressed air energy storage power station.

[0006] The present invention adopts the following technical solution:

[0007] A method for evaluating the operating status of a compressed air energy storage power station, the method is used to evaluate the operating status of a compressor, an air turbine, a heat exchanger, a heat storage tank and a gas storage device, and the method comprises the following steps:

[0008] S1: Data collection: collect the operating data of the compressor, air turbine, heat exchanger, heat storage tank and gas storage respectively;

[0009] S2: Feature selection: using the Spearman correlation analysis method to analyze the operation data, screen out the characteristic operation data that has a greater impact on the operation status of each device, and determine the characteristic operation data as the characteristic parameters for subsequent model calculation;

[0010] S3: Data classification: The KMeans method is used to cluster the load segments of each device, and the characteristic operation data is divided into three types of data according to the load segments;

[0011] S4: Model construction and optimization: A BP neural network method is used to construct a model for each of the three types of data for each type of equipment, and evaluation models for the operating status of the compressor, air turbine, heat exchanger, heat storage tank and gas storage are established respectively; the weight and bias parameters of the BP neural network method are optimized using a parameter optimization algorithm;

[0012] S5: Operation status evaluation: collect the current characteristic operation data of each device, input the characteristic operation data into the evaluation model, obtain the operation status of each device, and then evaluate the operation status of the compressed air energy storage power station.

[0013] Furthermore, the operating data of the compressor include: compressor input air temperature, compressor exhaust temperature, compressor input air flow, compressor exhaust flow, compressor input air pressure, and compressor exhaust pressure; the operating data of the air turbine include: air turbine input air temperature, air turbine exhaust temperature, air turbine input air flow, air turbine exhaust flow, air turbine input air pressure, and air turbine exhaust pressure; the operating data of the heat exchanger include: heat exchanger input air temperature, heat exchanger output air temperature, heat exchanger input cold medium temperature, and heat exchanger output cold medium temperature; the operating data of the heat storage tank include: heat storage tank body inlet medium temperature, and heat storage tank body inlet medium pressure; the operating data of the gas storage reservoir include: gas storage reservoir inlet air pressure, gas storage reservoir inlet air temperature, gas storage reservoir outlet air temperature, and gas storage reservoir outlet air pressure.

[0014] Furthermore, the Spearman correlation analysis method described in S2 includes: calculating the correlation between the operating data to evaluate the influencing factors of the equipment operating status, converting the influencing factors of the equipment into rankings, calculating the difference between each pair of influencing factor rankings, and using the formula The correlation coefficient is calculated. The absolute value of the correlation coefficient is greater than 0.85, which indicates a high correlation. A variable with a high correlation is selected to participate in the subsequent model calculation. In the formula, ρ is the Spearman correlation coefficient, m is the number of influencing factors for each device, t is the influencing factor for each device, and n is the number of collected operation data.

[0015] Further, the characteristic operation data include: compressor input air temperature, compressor exhaust temperature, compressor input air pressure, compressor exhaust pressure, air turbine input air temperature, air turbine exhaust temperature, air turbine input air pressure, air turbine exhaust pressure, heat exchanger input air temperature, heat exchanger output air temperature, heat exchanger input cold medium temperature, heat exchanger output cold medium temperature, heat storage tank body inlet medium temperature, heat storage tank body inlet medium pressure, gas storage reservoir inlet air pressure, gas storage reservoir inlet air temperature, gas storage reservoir outlet air temperature, gas storage reservoir outlet air pressure.

[0016] Furthermore, the load segment in S3 is three interval segments equally divided according to the total load amount.

[0017] Furthermore, the model construction described in S3 includes: a multi-layer feedforward neural network based on a gradient descent algorithm, adopting a three-layer network architecture of 1 input layer, 1 hidden layer and 1 output layer, the calculation process includes a forward calculation process and a reverse training process, and the model parameters include weights and bias parameters between different layers.

[0018] Furthermore, the forward calculation process includes: inputting the characteristic operation data into the input layer, obtaining the calculated value of the output layer through the given weights and bias initial values ​​between different layers, and then calculating the error value between the calculated value and the actual value in the characteristic operation data; the reverse training process includes: adjusting the weights and biases between the layers according to the error value, and establishing a BP neural network model through forward and reverse calculations.

[0019] Furthermore, the parameter optimization algorithm described in S4 includes a marine predator algorithm, a genetic algorithm or an ant colony algorithm.

[0020] Furthermore, S5 includes: inputting the characteristic operation data of the compressor, air turbine, heat exchanger, heat storage tank, and gas storage reservoir into the evaluation model to obtain the operating status of the corresponding equipment, and an output value of 1 indicates that the current equipment is operating safely, and an output value of 0 indicates that the current equipment has a safety hazard; if the output value of any device among the compressor, air turbine, heat exchanger, heat storage tank, and gas storage reservoir is 0, it indicates that there is a safety hazard in the operating status of the compressed air energy storage power station.

[0021] A compressed air energy storage power station operation status evaluation system, the evaluation system is used to implement the above evaluation method, the evaluation system comprises:

[0022] Data acquisition module, used to collect operating data of compressor, air turbine, heat exchanger, heat storage tank and gas storage;

[0023] A feature selection module is used for selecting feature operation data, and uses the Spearman correlation analysis method to analyze the operation data, screen out the feature operation data that has a greater impact on the operation status of each device, and determine the feature operation data as the feature parameter for subsequent model calculation;

[0024] A data classification module is used for data classification. The KMeans method is used to cluster the load segments of each device, and the characteristic operation data is divided into three types of data according to the load segments.

[0025] The model building and optimization module is used for model building and optimization. The BP neural network method is used to build a model for each of the three types of data for each type of equipment, and evaluation models for the operating status of the compressor, air turbine, heat exchanger, heat storage tank and gas storage are established respectively; the weight and bias parameters of the BP neural network method are optimized using a parameter optimization algorithm;

[0026] The operating status evaluation module is used for operating status evaluation, collects the current characteristic operating data of each device, inputs the characteristic operating data into the evaluation model, obtains the operating status of each device, and then evaluates the operating status of the compressed air energy storage power station.

[0027] Beneficial effects:

[0028] The present invention discloses a method and system for evaluating the operating status of a compressed air energy storage power station. The evaluation method evaluates the operating status of each key device and then determines the operating status of the power station. It is a fully automated method that can timely understand the health status of each device and discover problems in a timely manner, thereby effectively improving the safety and stability of the power station operation.

[0029] The present invention provides a Spearman correlation analysis method for influencing factor analysis before model construction. The method analyzes the correlation between each influencing factor, and selects and retains one of the parameters with higher correlation, thereby reducing redundancy between data and improving model building accuracy.

[0030] The present invention classifies the operating data before model construction, classifies the data, and establishes different data models under different loads to improve the accuracy of the model. The data characteristics under different loads of the power station are quite different. If the data under all loads participate in the same model construction, the model representativeness is poor.

[0031] The present invention also provides an optimization algorithm for the model, which optimizes the model parameters and improves the construction accuracy of the model, so as to more accurately judge the operating status of the power station. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 It is a flow chart of a method for evaluating the operating status of a compressed air energy storage power station according to the present invention;

[0034] Figure 2-1 This is a schematic diagram of the evaluation model construction in the compressed air energy storage power station operation status evaluation method of the present invention. Figure 1 ;

[0035] Figure 2-2 This is a second schematic diagram of constructing an evaluation model in a method for evaluating the operating status of a compressed air energy storage power station according to the present invention;

[0036] Figure 2-3 This is a schematic diagram of the evaluation model construction in the compressed air energy storage power station operation status evaluation method of the present invention. Figure 3 ;

[0037] Figure 2-4 This is a fourth schematic diagram of constructing an evaluation model in a method for evaluating the operating status of a compressed air energy storage power station according to the present invention;

[0038] Figure 2-5 This is a schematic diagram 5 of constructing an evaluation model in a method for evaluating the operating status of a compressed air energy storage power station according to the present invention;

[0039] Figure 2-6 This is a sixth schematic diagram of constructing an evaluation model in a method for evaluating the operating status of a compressed air energy storage power station according to the present invention;

[0040] Figure 3 It is a schematic diagram of an operating status evaluation system for a compressed air energy storage power station according to the present invention. DETAILED DESCRIPTION

[0041] In order to better understand the technical solution of the present invention, the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0042] It should be clear that the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] Example 1

[0044] like Figure 1As shown, a flow chart of a method for evaluating the operating status of a compressed air energy storage power station is provided. A method for evaluating the operating status of a compressed air energy storage power station is provided. The evaluation method is used to evaluate the operating status of a compressor, an air turbine, a heat exchanger, a heat storage tank and a gas storage device. The evaluation method comprises the following steps:

[0045] S1: Data collection: collect the operating data of the compressor, air turbine, heat exchanger, heat storage tank and gas storage respectively;

[0046] S2: Feature selection: using the Spearman correlation analysis method to analyze the operation data, screen out the characteristic operation data that has a greater impact on the operation status of each device, and determine the characteristic operation data as the characteristic parameters for subsequent model calculation;

[0047] The above S1 and S2 processes refer to Figure 2-1 .

[0048] S3: Data classification: The KMeans method is used to cluster the load segments of each device, and the characteristic operation data is divided into three types of data according to the load segments;

[0049] S4: Model construction and optimization: A BP neural network method is used to construct a model for each of the three types of data for each type of equipment, and evaluation models for the operating status of the compressor, air turbine, heat exchanger, heat storage tank and gas storage are established respectively; the weight and bias parameters of the BP neural network method are optimized using a parameter optimization algorithm;

[0050] The above S3 and S4 processes refer to Figure 2-2 , Figure 2-3 , Figure 2-4 , Figure 2-5 and Figure 2-6 .

[0051] S5: Operation status evaluation: collect the current characteristic operation data of each device, input the characteristic operation data into the evaluation model, obtain the operation status of each device, and then evaluate the operation status of the compressed air energy storage power station.

[0052] Furthermore, the operating data of the compressor include: compressor input air temperature, compressor exhaust temperature, compressor input air flow, compressor exhaust flow, compressor input air pressure, and compressor exhaust pressure; the operating data of the air turbine include: air turbine input air temperature, air turbine exhaust temperature, air turbine input air flow, air turbine exhaust flow, air turbine input air pressure, and air turbine exhaust pressure; the operating data of the heat exchanger include: heat exchanger input air temperature, heat exchanger output air temperature, heat exchanger input cold medium temperature, and heat exchanger output cold medium temperature; the operating data of the heat storage tank include: heat storage tank body inlet medium temperature, and heat storage tank body inlet medium pressure; the operating data of the gas storage reservoir include: gas storage reservoir inlet air pressure, gas storage reservoir inlet air temperature, gas storage reservoir outlet air temperature, and gas storage reservoir outlet air pressure.

[0053] Furthermore, the Spearman correlation analysis method described in S2 includes: calculating the correlation between the operating data to evaluate the influencing factors of the equipment operating status, converting the influencing factors of the equipment into rankings, calculating the difference between each pair of influencing factor rankings, and using the formula The correlation coefficient is calculated. The absolute value of the correlation coefficient is greater than 0.85, which indicates a high correlation. A variable with a high correlation is selected to participate in the subsequent model calculation. In the formula, ρ is the Spearman correlation coefficient, m is the number of influencing factors for each device, t is the influencing factor for each device, and n is the number of collected operation data.

[0054] Further, the characteristic operation data include: compressor input air temperature, compressor exhaust temperature, compressor input air pressure, compressor exhaust pressure, air turbine input air temperature, air turbine exhaust temperature, air turbine input air pressure, air turbine exhaust pressure, heat exchanger input air temperature, heat exchanger output air temperature, heat exchanger input cold medium temperature, heat exchanger output cold medium temperature, heat storage tank body inlet medium temperature, heat storage tank body inlet medium pressure, gas storage reservoir inlet air pressure, gas storage reservoir inlet air temperature, gas storage reservoir outlet air temperature, gas storage reservoir outlet air pressure.

[0055] Furthermore, the load segment in S3 is three interval segments equally divided according to the total load amount.

[0056] Furthermore, the model construction described in S3 includes: a multi-layer feedforward neural network based on a gradient descent algorithm, adopting a three-layer network architecture of 1 input layer, 1 hidden layer and 1 output layer, the calculation process includes a forward calculation process and a reverse training process, and the model parameters include weights and bias parameters between different layers.

[0057] Furthermore, the forward calculation process includes: inputting the characteristic operation data into the input layer, obtaining the calculated value of the output layer through the given weights and bias initial values ​​between different layers, and then calculating the error value between the calculated value and the actual value in the characteristic operation data; the reverse training process includes: adjusting the weights and biases between the layers according to the error value, and establishing a BP neural network model through forward and reverse calculations.

[0058] Furthermore, the parameter optimization algorithm described in S4 includes a marine predator algorithm, a genetic algorithm or an ant colony algorithm. Figure 2-2 , Figure 2-3 , Figure 2-4 , Figure 2-5 and Figure 2-6 As shown, the evaluation model constructed in the figure is optimized in parameters through the ocean predator algorithm, genetic algorithm or ant colony algorithm.

[0059] Furthermore, S5 includes: inputting the characteristic operation data of the compressor, air turbine, heat exchanger, heat storage tank, and gas storage reservoir into the evaluation model to obtain the operating status of the corresponding equipment, and an output value of 1 indicates that the current equipment is operating safely, and an output value of 0 indicates that the current equipment has a safety hazard; if the output value of any device among the compressor, air turbine, heat exchanger, heat storage tank, and gas storage reservoir is 0, it indicates that there is a safety hazard in the operating status of the compressed air energy storage power station.

[0060] A compressed air energy storage power station operation status evaluation system, the evaluation system is used to implement the above evaluation method, the evaluation system comprises:

[0061] Data acquisition module, used to collect operating data of compressor, air turbine, heat exchanger, heat storage tank and gas storage;

[0062] A feature selection module is used for selecting feature operation data, and uses the Spearman correlation analysis method to analyze the operation data, screen out the feature operation data that has a greater impact on the operation status of each device, and determine the feature operation data as the feature parameter for subsequent model calculation;

[0063] A data classification module is used for data classification. The KMeans method is used to cluster the load segments of each device, and the characteristic operation data is divided into three types of data according to the load segments.

[0064] The model building and optimization module is used for model building and optimization. The BP neural network method is used to build a model for each of the three types of data for each type of equipment, and evaluation models for the operating status of the compressor, air turbine, heat exchanger, heat storage tank and gas storage are established respectively; the weight and bias parameters of the BP neural network method are optimized using a parameter optimization algorithm;

[0065] The operating status evaluation module is used for operating status evaluation, collects the current characteristic operating data of each device, inputs the characteristic operating data into the evaluation model, obtains the operating status of each device, and then evaluates the operating status of the compressed air energy storage power station. Figure 3 shown.

[0066] Example 2

[0067] like Figure 1 As shown, a flow chart of a method for evaluating the operating status of a compressed air energy storage power station is provided. The present invention provides a method for evaluating the operating status of a compressed air energy storage power station. The method for evaluating the operating status of a compressed air energy storage power station is used to evaluate the operating status of a compressor, an air turbine, a heat exchanger, a heat storage tank, and a gas storage device. The evaluation method comprises the following steps:

[0068] S1: Data collection: According to the operating mechanism of compressor, air turbine, heat exchanger, heat storage tank and gas storage, analyze the influencing factors of the operating status evaluation of each equipment, and collect the operating data of different influencing factors of each equipment.

[0069] S2: Feature optimization: The Spearman correlation analysis method is used to analyze the influencing factors of each device, and the influencing factors that have a greater impact on the operating status of each device are screened out, that is, the influencing factors that have a greater impact on the operating status of the equipment. The operating data corresponding to the influencing factor is the characteristic operating data, and the characteristic operating data is determined as the characteristic parameters for subsequent model calculations.

[0070] S3: Data classification: The KMeans method is used to cluster the load data of each device, and the collected data is divided into three categories according to the load segment.

[0071] S4: Model construction and optimization: A BP neural network method is used to construct a model for each type of data of each device, wherein each type of data is any one of the three types of data, and an evaluation model of the operating status of the compressor, air turbine, heat exchanger, heat storage tank, and gas storage reservoir is established respectively. The weight and bias parameters of the BP neural network method can be optimized using a parameter optimization algorithm.

[0072] S5: Operation status evaluation: Collect the current characteristic operation data of each device at the current moment, input it into the evaluation model constructed in S4, obtain the operation status of each device, and then evaluate the operation status of the compressed air energy storage power station.

[0073] The step S1 collects the operating data of the influencing factors of each device, including: the compressor collects the compressor input air temperature, compressor exhaust temperature, compressor input air flow, compressor exhaust flow, compressor input air pressure, and compressor exhaust pressure; the air turbine collects the air turbine input air temperature, air turbine exhaust temperature, air turbine input air flow, air turbine exhaust flow, air turbine input air pressure, and air turbine exhaust pressure; the heat exchanger collects the heat exchanger input air temperature, heat exchanger output air temperature, heat exchanger input cold medium temperature, and heat exchanger output cold medium temperature; the heat storage tank collects the heat storage tank body inlet medium temperature and the heat storage tank body inlet medium pressure; the gas storage reservoir collects the gas storage reservoir inlet air pressure, the gas storage reservoir inlet air temperature, the gas storage reservoir outlet air temperature, and the gas storage reservoir outlet air pressure.

[0074] The Spearman correlation analysis method in step S2 evaluates the relationship between the influencing factors by calculating the correlation between the parameters of each influencing factor. The Spearman correlation analysis method converts each influencing factor into a ranking, calculates the difference between each pair of influencing factor rankings, and calculates the correlation coefficient using formula 1. The absolute value of the correlation coefficient greater than 0.85 indicates a high correlation. One of the variables with a high correlation is selected to participate in the subsequent model calculation.

[0075]

[0076] In formula 1, ρ is the Spearman correlation coefficient; m is the number of influencing factors of each device; and n is the number of collected operating data.

[0077] The step S3 clusters the collected load data of each device. Assuming a 60MW compressed air energy storage power station, it is divided into load segments of 0-20MW, 20MW-40MW, and 40-60MW. According to the divided load segments, the collected operation data is classified.

[0078] The BP neural network model construction in step S4 mainly includes a multi-layer feedforward neural network based on a gradient descent algorithm, using a three-layer network architecture of 1 input layer, 1 hidden layer, and 1 output layer. The calculation process includes forward calculation and reverse training process, and the model parameters mainly include weights and biases between different layers. The forward calculation process mainly inputs the operating data input value of the influencing factor into the input layer, obtains the calculated value of the output layer through the given initial values ​​of the weights and biases between different layers, and then calculates the error between the calculated value and the actual value in the operating data. The reverse training process mainly continuously adjusts the weights and biases between the layers according to the error value. Through continuous forward and reverse calculations, a BP neural network model is established.

[0079] The parameter optimization algorithm in step S4 includes a marine predator algorithm, a genetic algorithm or an ant colony algorithm.

[0080] The step S5 obtains the operation status of the equipment by inputting the characteristic operation data of the compressor, air turbine, heat exchanger, heat storage tank and gas storage reservoir at the current moment into the evaluation model constructed by value S4. The output value of 1 indicates that the current equipment is operating safely, and the output value of 0 indicates that the current equipment has a safety hazard. If the output value of any equipment among the compressor, air turbine, heat exchanger, heat storage tank and gas storage reservoir is 0, it indicates that there are certain safety hazards in the operation status of the compressed air energy storage power station.

[0081] like Figure 3 As shown, the present invention also provides a compressed air energy storage power station operation status evaluation system, which mainly includes a data acquisition module, a data discrimination module, a load division module, a data model construction module, and an operation status evaluation module.

[0082] The embodiments of the present invention are described in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for evaluating the operating status of a compressed air energy storage power station, characterized in that: The evaluation method is used to evaluate the operating status of a compressor, an air turbine, a heat exchanger, a heat storage tank and a gas storage device, and the evaluation method comprises the following steps: S1: Data collection: collect the operating data of the compressor, air turbine, heat exchanger, heat storage tank and gas storage respectively; S2: Feature selection: using the Spearman correlation analysis method to analyze the operation data, screen out the characteristic operation data that has a greater impact on the operation status of each device, and determine the characteristic operation data as the characteristic parameters for subsequent model calculation; S3: Data classification: The KMeans method is used to cluster the load segments of each device, and the characteristic operation data is divided into three types of data according to the load segments; S4: Model construction and optimization: A BP neural network method is used to construct a model for each of the three types of data for each type of equipment, and evaluation models for the operating status of the compressor, air turbine, heat exchanger, heat storage tank and gas storage are established respectively; the weight and bias parameters of the BP neural network method are optimized using a parameter optimization algorithm; S5: Operation status evaluation: collect the current characteristic operation data of each device, input the characteristic operation data into the evaluation model, obtain the operation status of each device, and then evaluate the operation status of the compressed air energy storage power station.

2. The evaluation method according to claim 1, characterized in that: The operating data of the compressor include: compressor input air temperature, compressor exhaust temperature, compressor input air flow, compressor exhaust flow, compressor input air pressure, and compressor exhaust pressure; the operating data of the air turbine include: air turbine input air temperature, air turbine exhaust temperature, air turbine input air flow, air turbine exhaust flow, air turbine input air pressure, and air turbine exhaust pressure; the operating data of the heat exchanger include: heat exchanger input air temperature, heat exchanger output air temperature, heat exchanger input cold medium temperature, and heat exchanger output cold medium temperature; the operating data of the heat storage tank include: heat storage tank body inlet medium temperature, and heat storage tank body inlet medium pressure; the operating data of the gas storage reservoir include: gas storage reservoir inlet air pressure, gas storage reservoir inlet air temperature, gas storage reservoir outlet air temperature, and gas storage reservoir outlet air pressure.

3. The evaluation method according to claim 2, characterized in that: S2 The Spearman correlation analysis method includes: calculating the correlation between the operating data to evaluate the influencing factors of the equipment operating status, converting the influencing factors of the equipment into rankings, calculating the difference between each pair of influencing factor rankings, and using the formula The correlation coefficient is calculated. The absolute value of the correlation coefficient is greater than 0.85, which indicates a high correlation. A variable with a high correlation is selected to participate in the subsequent model calculation. In the formula, ρ is the Spearman correlation coefficient, m is the number of influencing factors for each device, t is the influencing factor for each device, and n is the number of collected operation data.

4. The evaluation method according to claim 3, characterized in that: The characteristic operating data include: compressor input air temperature, compressor exhaust temperature, compressor input air pressure, compressor exhaust pressure, air turbine input air temperature, air turbine exhaust temperature, air turbine input air pressure, air turbine exhaust pressure, heat exchanger input air temperature, heat exchanger output air temperature, heat exchanger input cold medium temperature, heat exchanger output cold medium temperature, heat storage tank body inlet medium temperature, heat storage tank body inlet medium pressure, gas storage reservoir inlet air pressure, gas storage reservoir inlet air temperature, gas storage reservoir outlet air temperature, gas storage reservoir outlet air pressure.

5. The evaluation method according to claim 4, characterized in that: The load segment S3 is three interval segments evenly divided according to the total load amount.

6. The evaluation method according to claim 5, characterized in that: The model construction described in S4 includes: a multi-layer feedforward neural network based on a gradient descent algorithm, adopting a three-layer network architecture of 1 input layer, 1 hidden layer and 1 output layer, the calculation process includes a forward calculation process and a reverse training process, and the model parameters include weights and bias parameters between different layers.

7. The evaluation method according to claim 6, characterized in that: The forward calculation process includes: inputting the characteristic operation data into the input layer, obtaining the calculated value of the output layer through the given weights and bias initial values ​​between different layers, and then calculating the error value between the calculated value and the actual value in the characteristic operation data; the reverse training process includes: adjusting the weights and biases between the layers according to the error value, and establishing a BP neural network model through forward and reverse calculations.

8. The evaluation method according to claim 7, characterized in that: S4 The parameter optimization algorithm described in claim 4 includes a marine predator algorithm, a genetic algorithm or an ant colony algorithm.

9. The evaluation method according to claim 8, characterized in that: S5 includes: The characteristic operation data of the compressor, air turbine, heat exchanger, heat storage tank and gas storage reservoir are input into the evaluation model to obtain the operation status of the corresponding equipment. An output value of 1 indicates that the current equipment is operating safely, and an output value of 0 indicates that the current equipment has safety hazards; If the output value of any device in the compressor, air turbine, heat exchanger, heat storage tank, or gas storage reservoir is 0, it means that there are safety hazards in the operation of the compressed air energy storage power station.

10. A compressed air energy storage power station operation status assessment system, characterized in that: The evaluation system is used to implement the evaluation method according to any one of claims 1 to 9, and the evaluation system comprises: Data acquisition module, used to collect operating data of compressor, air turbine, heat exchanger, heat storage tank and gas storage; A feature selection module is used for selecting feature operation data, and uses the Spearman correlation analysis method to analyze the operation data, screen out the feature operation data that has a greater impact on the operation status of each device, and determine the feature operation data as the feature parameter for subsequent model calculation; A data classification module is used for data classification. The KMeans method is used to cluster the load segments of each device, and the characteristic operation data is divided into three types of data according to the load segments. The model building and optimization module is used for model building and optimization. The BP neural network method is used to build a model for each of the three types of data for each type of equipment, and evaluation models for the operating status of the compressor, air turbine, heat exchanger, heat storage tank and gas storage are established respectively; the weight and bias parameters of the BP neural network method are optimized using a parameter optimization algorithm; The operating status evaluation module is used for operating status evaluation, collects the current characteristic operating data of each device, inputs the characteristic operating data into the evaluation model, obtains the operating status of each device, and then evaluates the operating status of the compressed air energy storage power station.

Citation Information

Patent Citations

  • Distribution transformer anti-risk capability evaluation method

    CN112434929A

  • Refined monitoring and modeling method for electric cooling and hot air comprehensive energy utilization network

    CN113515898A

  • Compressed air energy storage system multi-stage compressor state evaluation method

    CN117909862A

  • Compressed air energy storage system state evaluation method based on digital twinborn model

    CN117993281A

  • Cascaded energy storage system and energy storage method

    WO2024131172A1