Compressed air energy storage system fault diagnosis method and device

Abstract

The invention discloses a compressed air energy storage system fault diagnosis method and device, and the method comprises the steps: building a double-field coupling dynamic model based on the thermal characteristics of a working medium in a compressed air energy storage system and the flow characteristics of a fluid; based on the target operation parameter data, utilizing a double-field coupling dynamic model to simulate a plurality of operation conditions of the system to obtain operation parameter characteristic data under different operation conditions, thereby constructing a state space model to obtain state characteristic data; inputting the test data into the state space model to obtain simulation data, and calculating a residual value between the simulation data and actual data; combining the state feature data and the residual values to obtain a training data set; and training a pre-constructed support vector machine model by using the training data set to obtain a parameter fault classification model. According to the parameter fault classification model obtained in the invention, the mapping relation between the target operation parameters and the fault types is established, online monitoring and diagnosis can be realized, and the fault types and positions can be quickly positioned.

Description

Technical Field

[0001] The present application relates to the technical field of fault identification, and in particular to a method and device for diagnosing faults in a compressed air energy storage system. Background Art

[0002] Compressed Air Energy Storage (CAES) is a new large-scale clean energy storage technology that can effectively improve the serious wind and solar power abandonment problems of renewable energy. However, after a long period of operation, the compressed air energy storage system will have different faults due to changes in conditions such as pressure, temperature and flow, which seriously affect the safe and efficient operation of the entire energy storage system. Summary of the invention

[0003] The present disclosure provides a method, device, equipment and storage medium for diagnosing faults in a compressed air energy storage system, so as to at least solve the above technical problems existing in the prior art.

[0004] According to a first aspect of the present application, a method for diagnosing a fault in a compressed air energy storage system is provided, the method comprising:

[0005] Based on the thermodynamic characteristics of the working fluid and the flow characteristics of the fluid inside the compressed air energy storage system, a dual-field coupling dynamic model is constructed; the dual-field coupling dynamic model is used to characterize the operating characteristics of the compressed air energy storage system that change over time;

[0006] Based on the target operating parameter data, the dual-field coupled dynamic model is used to simulate multiple operating conditions of the compressed air energy storage system to obtain operating parameter characteristic data under different operating conditions; wherein the operating parameter characteristic data includes normal operating characteristic data and fault operating characteristic data;

[0007] constructing a state space model using the target operating parameter data and corresponding operating parameter characteristic data to obtain state characteristic data;

[0008] Inputting the test data into the state space model to obtain simulation data, and calculating the residual value between the simulation data and the actual data;

[0009] Obtaining a training data set according to the state feature data and the residual value;

[0010] The pre-built support vector machine model is trained using the training data set to obtain a parameter fault classification model.

[0011] In one possible implementation, the compressed air energy storage system includes an energy storage stage and an energy release stage; the dual-field coupling dynamic model includes:

[0012] A first model is used to characterize the time-varying operating characteristics of the compressed air energy storage system during the energy storage stage;

[0013] The second model is used to characterize the time-varying operating characteristics of the compressed air energy storage system during the energy release phase.

[0014] In one possible implementation manner, after constructing the dual-field coupling dynamic model, the method further includes:

[0015] The model parameters of the dual-field coupled dynamic model are updated using experimental data; the model parameters include compressor efficiency, heat transfer coefficient of the heat exchanger and heat capacity of the gas storage tank.

[0016] In one embodiment, the target operating parameters include pressure, temperature and flow rate; the dual-field coupled dynamic model is used to simulate multiple operating conditions of the compressed air energy storage system based on the target operating parameters to obtain operating parameter characteristic data under different operating conditions, including:

[0017] Under the conditions of adjusting pressure, temperature and flow, the dual-field coupled dynamic model is used to simulate the compressed air energy storage system under four operating conditions: normal, surge, abnormal temperature difference and abnormal pressure difference, and obtain the operating parameter characteristic data under different operating conditions;

[0018] The operating parameter characteristic data include pressure characteristic data, temperature characteristic data and flow characteristic data at the inlet of the compressed air energy storage system, and pressure characteristic data, temperature characteristic data and flow characteristic data at the outlet of the compressed air energy storage system.

[0019] In one possible implementation manner, before constructing the state space model using the target operating parameter data and the corresponding operating parameter characteristic data, the method further includes:

[0020] Performing denoising processing on the target operating parameter data and the corresponding operating parameter characteristic data;

[0021] The denoised target operating parameter data and the corresponding operating parameter characteristic data are standardized; and the state space model is constructed using the standardized data.

[0022] In one possible implementation manner, the using the target operating parameter data and the corresponding operating parameter characteristic data to construct a state space model to obtain state characteristic data includes:

[0023] Acquiring the target operating parameter data and corresponding operating parameter characteristic data under different working conditions;

[0024] Performing a multivariate regression analysis on the target operating parameter data and the corresponding operating parameter characteristic data under the different operating conditions to determine the state space model;

[0025] State characteristic data is determined based on the state space model.

[0026] In one possible implementation manner, before obtaining the training data set, the method further includes:

[0027] Preprocessing the state characteristic data and residual value; the preprocessing includes data cleaning, interpolation and normalization;

[0028] Labels of different working conditions are established for the processed state characteristic data and residual values.

[0029] In one possible implementation, model parameters of the trained support vector machine model are optimized to obtain an optimized parameter fault classification model.

[0030] In one possible implementation manner, after obtaining the optimized parameter fault classification model, the method further includes:

[0031] Obtaining data to be diagnosed;

[0032] Inputting the data to be diagnosed into the parameter fault classification model to obtain the fault type;

[0033] Based on the fault type, a fault alarm is issued and maintenance suggestions are made.

[0034] According to a second aspect of the present application, a compressed air energy storage system fault diagnosis device is provided, the device comprising:

[0035] The first construction module is used to construct a dual-field coupling dynamic model based on the thermodynamic characteristics of the working fluid and the flow characteristics of the fluid inside the compressed air energy storage system; the dual-field coupling dynamic model is used to characterize the operation characteristics of the compressed air energy storage system that change over time;

[0036] A parameter simulation module, used to simulate multiple operating conditions of the compressed air energy storage system using the dual-field coupled dynamic model based on the target operating parameter data, and obtain operating parameter characteristic data under different operating conditions; wherein the operating parameter characteristic data includes normal operating characteristic data and fault operating characteristic data;

[0037] A second construction module is used to construct a state space model using the target operating parameter data and the corresponding operating parameter characteristic data to obtain state characteristic data;

[0038] A data simulation module, used for inputting test data into the state space model to obtain simulation data, and calculating the residual value between the simulation data and the actual data;

[0039] A data acquisition module, used to obtain a training data set according to the state feature data and the residual value;

[0040] The model training module is used to train the pre-built support vector machine model using the training data set to obtain a parameter fault classification model.

[0041] According to a third aspect of the present application, an electronic device is provided, including:

[0042] at least one processor; and

[0043] a memory communicatively connected to the at least one processor; wherein,

[0044] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the present application.

[0045] According to a fourth aspect of the present application, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the present application.

[0046] According to a fifth aspect of the present application, a computer program product is provided, comprising a computer program or instructions, which implement the method described in the present application when executed by a processor.

[0047] By using the technical solution of the present application, the mapping relationship between operating parameters and fault types can be realized. Real-time diagnosis can be achieved through online monitoring, and the fault type and location can be quickly located.

[0048] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, wherein:

[0050] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts.

[0051] Figure 1 A schematic diagram of a flow chart of a method for diagnosing a fault of a compressed air energy storage system in an embodiment of the present application is shown;

[0052] Figure 2 A schematic diagram of the simulation of the dynamic characteristics of the temperature of a fault-free heat storage tank in an embodiment of the present application is shown; Figure 3 A schematic diagram of the simulation of the dynamic characteristics of the temperature of the heat storage tank in the case of a compressor pressure failure in an embodiment of the present application is shown;

[0053] Figure 4 A schematic diagram of the simulation of the dynamic characteristics of the temperature of the heat storage tank in the case of a compressor temperature failure in an embodiment of the present application is shown;

[0054] Figure 5 A schematic diagram of the simulation of the dynamic characteristics of the temperature of the heat storage tank in the case of a compressor flow failure in an embodiment of the present application is shown;

[0055] Figure 6 A schematic diagram of the structure of a fault diagnosis device for a compressed air energy storage system in an embodiment of the present application is shown;

[0056] Figure 7 A schematic diagram of the structure of an electronic device in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0057] In order to make the purpose, features, and advantages of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0058] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0059] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0060] In the following description, the terms "first\second" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0062] It should be understood that in the various embodiments of the present application, the size of the serial number of each implementation process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0063] like Figure 1 As shown, the present application provides a method for diagnosing a fault of a compressed air energy storage system, the method comprising:

[0064] S101, constructing a dual-field coupling dynamic model based on the thermodynamic characteristics of the working fluid and the flow characteristics of the fluid inside the compressed air energy storage system; the dual-field coupling dynamic model is used to characterize the operation characteristics of the compressed air energy storage system that change over time;

[0065] In this application, a dual-field coupling dynamic model is constructed based on the thermodynamic characteristics of the internal working fluid of the compressed air energy storage system and the flow characteristics of the fluid. The dual-field coupling dynamic model can describe the changes of the system over time and can provide reference trajectories under different operating conditions when the system is operating normally. It is understandable that when a minor fault occurs in the compressed air energy storage system, the changes in its operating parameters may be very subtle, making it difficult to detect system failures. However, by comparing the normal trajectory predicted by the dual-field coupling dynamic model provided by this application, deviations in the system can be discovered in time. In other words, the dual-field coupling dynamic model constructed using this application can detect deviations in the system immediately.

[0066] Among them, the main equipment of the compressed air energy storage system includes a compressor, an air storage tank, a heat exchanger and a turbine. It can be understood that the compressed air energy storage system also includes other equipment. The embodiment of the present application mainly analyzes the energy changes of the compressor, the air storage tank, the heat exchanger and the turbine.

[0067] In some embodiments, the compressed air energy storage system includes an energy storage stage and an energy release stage; the dual-field coupling dynamic model includes:

[0068] A first model is used to characterize the time-varying operating characteristics of the compressed air energy storage system during the energy storage stage;

[0069] The second model is used to characterize the time-varying operating characteristics of the compressed air energy storage system during the energy release phase.

[0070] It is understandable that the compressed air energy storage system includes an energy storage stage and an energy release stage. Since the energy storage stage and the energy release stage are usually impossible to work at the same time, they are modeled separately. Specifically, by adopting a modeling method of rational decomposition of components, a minimum simulation unit with independent physical functions and mathematical independence is constructed, which effectively reduces the complexity of the model and improves the flexibility and scalability of the model. Based on the modeling of each major subsystem, the present application can adopt a modular modeling method to construct sub-models of key equipment such as compressors, gas tanks, turbines, heat exchangers, etc. one by one, and finally combine them into a complete first model and a second model.

[0071] The main coupling relationships analyzed by the first model or the second model in this application include the pressure matching between the compressor and the gas storage tank, the energy release between the gas storage tank and the expander, and the real-time monitoring and adjustment of each subsystem by the control system. This application uses the MATLAB simulation tool to numerically solve the dual-field coupling dynamic model, and analyzes in detail the changes in the thermal state of the working fluid inside the system, the flow characteristics of the fluid, and the coupling effect between the two.

[0072] In some embodiments, after constructing the dual-field coupling dynamic model, the method further includes:

[0073] The model parameters of the dual-field coupled dynamic model are updated using experimental data; the model parameters include compressor efficiency, heat transfer coefficient of the heat exchanger and heat capacity of the gas storage tank.

[0074] In the present application, the compressed air energy storage system can be experimented with to obtain experimental data, and then the model parameters of the dual-field coupled dynamic model can be identified using the experimental data using an inversion algorithm, and the model parameters that affect the behaviors of subsystems such as the compressor, the gas tank, and the turbine are derived. The model parameters include the compressor efficiency, the heat transfer coefficient of the heat exchanger, and the heat capacity of the gas tank. Then, the model parameters of the dual-field coupled dynamic model are updated by optimizing the fitting error.

[0075] This application updates the model parameters through reverse update of experimental data, ensuring that the dual-field coupled dynamic model can maintain high accuracy under different operating conditions of the compressed air energy storage system. Compared with the traditional static parameter modeling method, dynamic parameter identification and correction greatly improves the accuracy and adaptability of the model. Driven by the inversion algorithm and experimental data, a high-quality dual-field coupled dynamic model can be quickly obtained without a lot of trial and error and parameter assumptions.

[0076] S102, based on the target operating parameter data, using the dual-field coupled dynamic model to simulate multiple operating conditions of the compressed air energy storage system to obtain operating parameter characteristic data under different operating conditions; wherein the operating parameter characteristic data includes normal operating characteristic data and fault operating characteristic data;

[0077] In some embodiments, the target operating parameter data includes pressure, temperature and flow rate; the dual-field coupled dynamic model is used to simulate multiple operating conditions of the compressed air energy storage system based on the target operating parameters to obtain operating parameter characteristic data under different operating conditions, including:

[0078] Under the conditions of adjusting pressure, temperature and flow, the dual-field coupled dynamic model is used to simulate the compressed air energy storage system under four operating conditions: normal, surge, abnormal temperature difference and abnormal pressure difference, and obtain the operating parameter characteristic data under different operating conditions;

[0079] Among them, the pressure, temperature and flow parameter data are used as the pressure characteristic data, temperature characteristic data and flow characteristic data at the inlet of the compressed air energy storage system, and the obtained operating parameter characteristic data are the pressure characteristic data, temperature characteristic data and flow characteristic data at the outlet.

[0080] Specifically, the present application adjusts the target operating parameters of the dual-field coupled dynamic model, which are specifically pressure, temperature, and flow, and uses them as inlet pressure characteristic data, inlet temperature characteristic data, and inlet flow characteristic data. Through the dual-field coupled dynamic model, the compressed air energy storage system is simulated under four operating conditions: normal, surge, abnormal temperature difference, and abnormal pressure difference, thereby obtaining different operating parameter characteristic data under different operating conditions. The operating parameter characteristic data includes characteristic data such as outlet pressure, temperature, and flow.

[0081] For the main equipment of the compressed air energy storage system, such as compressors, air tanks, heat exchangers, and turbines, the following key operating parameters are selected for adjustment based on the thermodynamic and fluid dynamic characteristics: inlet pressure (determines the suction characteristics of the compressor and air tank), inlet temperature (affects the thermal efficiency of the heat exchanger and the system) and inlet flow rate (directly related to the load characteristics of the system). The following parameters of the compressed air system are collected as outlet parameters and as fault characteristics: outlet pressure (reflects the efficiency of energy storage or release of the system), outlet temperature (indicates heat exchange effect and fault characteristics) and outlet flow rate (reflects the stability of the energy storage and release stages). The specifics for different working conditions are as follows:

[0082] Under normal working conditions, the inlet pressure, temperature and flow rate remain stable, and the outlet parameters are close to the theoretical values, with no obvious abnormalities;

[0083] Surge condition: The outlet pressure and flow rate oscillate periodically, the outlet temperature fluctuates greatly, and the system efficiency drops sharply;

[0084] Abnormal temperature difference: the outlet temperature deviates from the set value, the heat exchanger efficiency is significantly reduced, and the thermal system has heat accumulation or overcooling problems;

[0085] Abnormal pressure difference conditions: The gas tank pressure does not reach the energy release threshold or is too high or the turbine energy release efficiency is significantly reduced, and the outlet flow fluctuates.

[0086] For example, the present application uses a dual-field coupled dynamic model to simulate a compressed air energy storage system, taking the temperature dynamic characteristics of a heat storage tank as an example. Figure 2 The following is the dynamic temperature characteristics of the heat storage tank without any faults, as shown in Figure 3 The figure shows the dynamic characteristics of the heat storage tank temperature when the compressor pressure fails. Figure 4 The figure shows the dynamic characteristics of the heat storage tank temperature when the compressor temperature fails. Figure 5 Shown is the dynamic characteristics of the thermal storage tank temperature during compressor flow failure.

[0087] In some embodiments, before constructing the state space model using the target operating parameter data and the corresponding operating parameter characteristic data, the method further includes:

[0088] Performing denoising processing on the target operating parameter data and the corresponding operating parameter characteristic data;

[0089] The denoised target operating parameter data and the corresponding operating parameter characteristic data are standardized; and the state space model is constructed using the standardized data.

[0090] Specifically, before constructing the state-space model, the target operating parameter data and the corresponding operating parameter characteristic data are preprocessed, that is, the inlet pressure characteristic data, the inlet temperature characteristic data and the inlet flow characteristic data, the outlet pressure characteristic data, the outlet temperature characteristic data and the outlet flow characteristic data are preprocessed; then the target operating parameter data, namely the inlet pressure characteristic data, the inlet temperature characteristic data and the inlet flow characteristic data are used as the input data of the state-space model, and the corresponding operating parameter characteristic data, namely the outlet pressure characteristic data, the outlet temperature characteristic data and the outlet flow characteristic data are used as the output data of the state-space model. The preprocessing specifically includes using a low-pass filter to remove the high-frequency noise of the operating parameter characteristic data to ensure the smoothness of the input and output data; standardizing the input and output data to eliminate the influence of the dimensional difference on the identification of the state-space model; ensuring that the input and output data are strictly corresponding in time series to avoid modeling errors caused by time delays.

[0091] S103, constructing a state space model using the target operating parameter data and the corresponding operating parameter characteristic data to obtain state characteristic data;

[0092] It can be understood that the order of the state space model in the present application is first order. Based on the state space description of the linear system, the state sequence of the system is directly estimated by constructing an observation subspace, thereby obtaining the state characteristic data of the system.

[0093] In some embodiments, the use of the target operating parameter data and the corresponding operating parameter characteristic data to construct a state space model to obtain state characteristic data includes:

[0094] Acquiring the target operating parameter data and corresponding operating parameter characteristic data under different working conditions;

[0095] Performing a multivariate regression analysis on the target operating parameter data and the corresponding operating parameter characteristic data under the different operating conditions to determine the state space model;

[0096] State characteristic data is determined based on the state space model.

[0097] It can be understood that in the present application, the inlet temperature characteristic data, the inlet pressure characteristic data, and the inlet flow characteristic data in the target operating parameter data are used as input data, and the outlet temperature characteristic data, the outlet pressure characteristic data, and the outlet flow characteristic data in the corresponding operating parameter characteristic data are used as output data, and are input into the following multivariate equation;

[0098]

[0099] y(t)=Cx(t)+Du(t)+e(t)

[0100] in, is the time derivative, y(t) corresponds to the output data, x(t) is the state parameter which can be set as needed, u(t) is the input data, corresponding to the inlet temperature characteristic data, inlet pressure characteristic data, inlet flow characteristic data of the input data, e(t) is the error, for example, the input data can be the inlet temperature characteristic data, inlet pressure characteristic data, inlet flow characteristic data corresponding to one of the working conditions, the output data can be the outlet temperature characteristic data, outlet pressure characteristic data, outlet flow characteristic data corresponding to the working condition; the present application obtains the values ​​of A, B, C, D, K through the N4sid algorithm. Among them, A, B, C, D, K are all matrices. It can be understood that each set of data inlet and outlet corresponding data can obtain a set of corresponding state space matrices, that is, A, B, C, D, K values. The state characteristics of A, B, C, D, K under different working conditions will be different, and each position parameter of A, B, C, D, K is used as the state characteristic data of the parameter fault classification model.

[0101] S104, inputting the test data into the state space model to obtain simulation data, and calculating the residual value between the simulation data and the actual data;

[0102] In this application, the state space model simulates the test data and calculates the residual between the simulated output and the actual output, where the actual output is the export data obtained from the operating parameter characteristic data. The mean square error (MSE) and autocorrelation of the residual are used to evaluate the fitting accuracy of the model. The dynamic response of the state space model to different input signals (such as step input, random input) is compared with the consistency of the experimental data, and the generalization ability of the model is tested under different operating conditions (such as surge, temperature difference abnormality).

[0103] S105, obtaining a training data set according to the state feature data and the residual value;

[0104] In some embodiments, before obtaining the training data set, the method further includes:

[0105] Preprocessing the state characteristic data and residual value; the preprocessing includes data cleaning, interpolation and normalization;

[0106] Labels of different working conditions are established for the processed state characteristic data and residual values.

[0107] In the fault diagnosis process of compressed air energy storage system (CAES), in order to ensure the accuracy and robustness of the classification algorithm, the state space model parameters and residual values ​​obtained under different working conditions are used as feature inputs of the classification algorithm. After sufficient data preprocessing, a training data set of a structured parameter fault classification model is constructed.

[0108] Among them, preprocessing includes steps such as data cleaning, interpolation and normalization, which effectively eliminates data noise and inconsistency. This is because the input and output signals may be affected by external environmental interference, such as vibration and temperature fluctuation, resulting in increased data noise. Sensors have sensitivity and resolution limitations, which may lead to extreme values ​​or deviation data. There may be data loss or recording errors in some time steps. Therefore, the embodiment of the present application performs comprehensive data preprocessing to improve data quality and model applicability. Statistical methods are used to detect and eliminate obviously abnormal data points, such as extreme values ​​exceeding 3 times the standard deviation; linear interpolation methods are used to fill missing time step data to ensure the continuity of the time series; it is suitable for scenarios with a small continuous missing range, and the sample is directly removed for large-scale missing; in order to eliminate the dimensional differences between different features, all features are mapped to a fixed range, such as [0,1]; the preprocessed data is further denoised by sliding average filtering or low-pass filtering. After preprocessing the initial state feature data and residual values, a fault classification model data set is established; 70% of them are used as training sets and 30% as test sets, and labels are established for different working condition data. Perform principal component analysis (PCA) or linear discriminant analysis (LDA) on the extracted features to verify the separability of the features of different working conditions. Visualize the working condition classification boundaries to ensure that the features have good distinguishability.

[0109] S106, using the training data set to train the pre-built support vector machine model to obtain a parameter fault classification model.

[0110] Specifically, the present application uses a training data set to train a support vector machine model, wherein the kernel function of the support vector machine model selects a radial basis kernel function, and uses NRBO (Newton-Raphson-based optimizer) to search for the hyperparameter penalty factor and kernel function of the support vector machine model within a given reasonable range, and the optimization goal is the classification accuracy of the support vector machine on the existing data set.

[0111] In some embodiments, model parameters of the trained support vector machine model are optimized to obtain an optimized parameter fault classification model.

[0112] After the optimized hyperparameters are determined, they are input into the support vector machine model to obtain the trained support vector machine model, which can be used to effectively and accurately and reliably classify normal, surge, abnormal temperature difference and abnormal pressure difference.

[0113] In some embodiments, after obtaining the optimized parameter fault classification model, the method further includes:

[0114] Obtaining data to be diagnosed;

[0115] Inputting the data to be diagnosed into the parameter fault classification model to obtain the fault type;

[0116] Based on the fault type, a fault alarm is issued and maintenance suggestions are made.

[0117] It is understandable that the present application realizes real-time diagnosis through online monitoring, quickly locates the fault type and location, and provides fault alarms and maintenance suggestions.

[0118] The method for fault diagnosis of compressed air energy storage system provided in the present application constructs the dynamic relationship of thermal field and flow field coupling of compressed air energy storage system based on physical model, including pressure, temperature, flow rate, etc.; inversely solves the relevant parameters of the model according to the experimental operation data; changes the key operating parameters (pressure, temperature, flow rate) of the compressed air energy storage system, and constructs a multi-parameter operation status database. The N4SID (subspace identification method) is used for system identification to accurately identify the key parameters such as the state matrix, input matrix, output matrix of the system, and use the matrix parameters and residuals as the feature input of the fault diagnosis model; the NRBO-SVM is used in the feature space to establish the mapping relationship between the operating parameters and the fault type. Real-time diagnosis is achieved through online monitoring, the fault type and location are quickly located, and fault alarm and maintenance suggestions are provided. The present invention has the advantages of high diagnostic accuracy, fast response speed, and adaptability to a variety of complex working conditions, and can be widely used in the operation and maintenance of compressed air energy storage systems.

[0119] like Figure 6 As shown, the present application provides a compressed air energy storage system fault diagnosis device, the device comprising:

[0120] The first construction module 601 is used to construct a dual-field coupling dynamic model based on the thermodynamic characteristics of the working medium and the flow characteristics of the fluid inside the compressed air energy storage system; the dual-field coupling dynamic model is used to characterize the operation characteristics of the compressed air energy storage system that change over time;

[0121] A parameter simulation module 602 is used to simulate multiple operating conditions of the compressed air energy storage system using the dual-field coupled dynamic model based on the target operating parameter data to obtain operating parameter characteristic data under different operating conditions; wherein the operating parameter characteristic data includes normal operating characteristic data and fault operating characteristic data;

[0122] The second construction module 603 is used to construct a state space model using the target operating parameter data and the corresponding operating parameter characteristic data to obtain state characteristic data;

[0123] A data simulation module 604 is used to input the test data into the state space model to obtain simulation data, and calculate the residual value between the simulation data and the actual data;

[0124] A data acquisition module 605 is used to obtain a training data set according to the state feature data and the residual value;

[0125] The model training module 606 is used to train the pre-built support vector machine model using the training data set to obtain a parameter fault classification model.

[0126] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

[0127] The electronic device includes at least one processor; and a memory in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the compressed air energy storage system fault diagnosis method described in the present application. The computer instructions are used to enable the computer to execute the compressed air energy storage system fault diagnosis method described in the present application.

[0128] The present application also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the compressed air energy storage system fault diagnosis method of the present application.

[0129] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0130] like Figure 7 As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0131] A number of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0132] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as a compressed air energy storage system fault diagnosis method. For example, in some embodiments, the compressed air energy storage system fault diagnosis method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the compressed air energy storage system fault diagnosis method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to execute the compressed air energy storage system fault diagnosis method in any other appropriate manner (for example, by means of firmware).

[0133] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0134] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0135] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0136] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0137] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0138] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0139] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for diagnosing a fault in a compressed air energy storage system, characterized in that: The method comprises: Based on the thermodynamic characteristics of the working fluid and the flow characteristics of the fluid inside the compressed air energy storage system, a dual-field coupling dynamic model is constructed; the dual-field coupling dynamic model is used to characterize the operating characteristics of the compressed air energy storage system that change over time; Based on the target operating parameter data, the dual-field coupled dynamic model is used to simulate multiple operating conditions of the compressed air energy storage system to obtain operating parameter characteristic data under different operating conditions; wherein the operating parameter characteristic data includes normal operating characteristic data and fault operating characteristic data; constructing a state space model using the target operating parameter data and corresponding operating parameter characteristic data to obtain state characteristic data; Inputting the test data into the state space model to obtain simulation data, and calculating the residual value between the simulation data and the actual data; Obtaining a training data set according to the state feature data and the residual value; The pre-built support vector machine model is trained using the training data set to obtain a parameter fault classification model.

2. The method according to claim 1, characterized in that The compressed air energy storage system includes an energy storage stage and an energy release stage; the dual-field coupling dynamic model includes: A first model is used to characterize the time-varying operating characteristics of the compressed air energy storage system during the energy storage stage; The second model is used to characterize the time-varying operating characteristics of the compressed air energy storage system during the energy release phase.

3. The method according to claim 1, characterized in that After building the dual-field coupled dynamic model, it also includes: The model parameters of the dual-field coupled dynamic model are updated using experimental data; the model parameters include compressor efficiency, heat transfer coefficient of the heat exchanger and heat capacity of the gas storage tank.

4. The method according to claim 1, characterized in that The target operating parameters include pressure, temperature and flow rate; the dual-field coupled dynamic model is used to simulate multiple operating conditions of the compressed air energy storage system based on the target operating parameters to obtain operating parameter characteristic data under different operating conditions, including: Under the conditions of adjusting pressure, temperature and flow, the dual-field coupled dynamic model is used to simulate the compressed air energy storage system under four operating conditions: normal, surge, abnormal temperature difference and abnormal pressure difference, and obtain the operating parameter characteristic data under different operating conditions; The operating parameter characteristic data include pressure characteristic data, temperature characteristic data and flow characteristic data at the inlet of the compressed air energy storage system, and pressure characteristic data, temperature characteristic data and flow characteristic data at the outlet of the compressed air energy storage system.

5. The method according to claim 1, characterized in that Before constructing the state space model using the target operating parameter data and the corresponding operating parameter characteristic data, the method further includes: Performing denoising processing on the target operating parameter data and the corresponding operating parameter characteristic data; The denoised target operating parameter data and the corresponding operating parameter characteristic data are standardized; and the state space model is constructed using the standardized data.

6. The method according to claim 1, characterized in that The method of constructing a state space model using the target operating parameter data and the corresponding operating parameter characteristic data to obtain state characteristic data includes: Acquiring the target operating parameter data and corresponding operating parameter characteristic data under different operating conditions; Performing a multivariate regression analysis on the target operating parameter data and the corresponding operating parameter characteristic data under the different operating conditions to determine the state space model; State characteristic data is determined based on the state space model.

7. The method according to claim 1, characterized in that Before getting the training data set, it also includes: Preprocessing the state characteristic data and residual value; the preprocessing includes data cleaning, interpolation and normalization; Labels of different working conditions are established for the processed state characteristic data and residual values.

8. The method according to claim 1, characterized in that The model parameters of the support vector machine model after training are optimized to obtain an optimized parameter fault classification model.

9. The method according to claim 8, characterized in that After obtaining the optimized parameter fault classification model, it also includes: Obtaining data to be diagnosed; Inputting the data to be diagnosed into the parameter fault classification model to obtain the fault type; Based on the fault type, a fault alarm is issued and maintenance suggestions are made.

10. A compressed air energy storage system fault diagnosis device, characterized in that: The device comprises: The first construction module is used to construct a dual-field coupling dynamic model based on the thermodynamic characteristics of the working fluid and the flow characteristics of the fluid inside the compressed air energy storage system; the dual-field coupling dynamic model is used to characterize the operation characteristics of the compressed air energy storage system that change over time; A parameter simulation module, used to simulate multiple operating conditions of the compressed air energy storage system using the dual-field coupled dynamic model based on the target operating parameter data, and obtain operating parameter characteristic data under different operating conditions; wherein the operating parameter characteristic data includes normal operating characteristic data and fault operating characteristic data; A second construction module is used to construct a state space model using the target operating parameter data and the corresponding operating parameter characteristic data to obtain state characteristic data; A data simulation module, used for inputting test data into the state space model to obtain simulation data, and calculating the residual value between the simulation data and the actual data; A data acquisition module, used to obtain a training data set according to the state feature data and the residual value; The model training module is used to train the pre-built support vector machine model using the training data set to obtain a parameter fault classification model.

Images