Soft measurement method and system for safe operation risk monitoring point of energy storage power station

Abstract

The invention discloses a soft measurement method and system for a safe operation risk monitoring point of an energy storage power station, and the method comprises the steps: determining the position and type of a fault sensor in the energy storage power station, selecting and obtaining a fault measurement point corresponding to the fault sensor, and selecting and obtaining an associated measurement point in the fault measurement point according to the integrated structure and characteristics of the energy storage power station; based on the soft measurement model, obtaining a mapping relation between the fault measurement point and the associated measurement point; and collecting real-time data of the associated measuring points, selecting the real-time data of the corresponding associated measuring points as input variables of the soft measurement model, calculating to obtain numerical values of the fault measuring points, and completing soft measurement of the fault measuring points in the energy storage power station. When the energy storage power station has a relatively large number of batteries and a large number of measuring points and sensors, the state of the fault sensor in the energy storage power station can be monitored in real time, potential risks can be found in time, accidents can be prevented, and the overall operation safety of the energy storage power station is improved. And the method has certain applicability.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent operation and maintenance of battery energy storage power stations, and specifically relates to a soft measurement method and system for monitoring points of safe operation risks of energy storage power stations. Background Art

[0002] With the rapid development of new energy power, especially the large-scale application of wind and solar energy, the demand for energy storage is also increasing. Energy storage power stations can effectively solve the intermittent and instability problems of new energy power and improve the operating efficiency and reliability of the power system. As battery energy storage technology continues to advance, lithium-ion batteries have become the mainstream technology for energy storage power stations due to their high energy density, long life, and environmental protection. At the same time, new battery technologies such as solid-state batteries and sodium-ion batteries are also under development, which is expected to further improve the performance of energy storage power stations.

[0003] Battery energy storage power stations are a key component in the field of new energy, and their safety is crucial to the stable operation of the power system. During the use of batteries, safety hazards such as overheating, overcharging or short circuit may occur, so safety management and technical protection measures must be strengthened. By enhancing safety risk monitoring, potential safety hazards can be quickly discovered and warned, thereby effectively preventing accidents and ensuring the safe and stable operation of the power system.

[0004] However, due to the large number of equipment in battery energy storage power stations, the number of measuring points is relatively large. A single energy storage power station may integrate hundreds of thousands or even millions of batteries, and the number of measuring points is often several times the number of batteries. During the long-term operation of the battery energy storage power station, some sensor measuring points may fail due to aging or failure, resulting in the inability to continue monitoring, which in turn seriously affects the reliability of the power station operation. Therefore, in summary, the current energy storage power station has a relatively large number of batteries, measuring points and sensors. During the long-term operation, it may be impossible to continue monitoring due to aging or failure of some sensor measuring points, which may affect the reliability of the operation of the entire battery energy storage power station. Summary of the invention

[0005] The present invention provides a soft measurement method and system for monitoring points of safe operation risks of energy storage power stations, aiming to solve the problem that the current energy storage power stations have a relatively large number of batteries, many measuring points and sensors, and in the long-term operation process, some sensor measuring points may age or fail, resulting in the inability to continue monitoring, which may affect the reliability of the operation of the entire battery energy storage power station. In order to achieve the above object, the present invention adopts the following technical scheme: The present invention provides a soft measurement method for monitoring points of safe operation risks of energy storage power stations, comprising the following steps: S1. Determine the location and type of the fault sensor in the energy storage power station, select the fault measuring point corresponding to the fault sensor, and select the associated measuring point among the fault measuring points according to the integrated structure and characteristics of the energy storage power station; S2. Based on the soft measurement model, the mapping relationship between the fault measurement point and the associated measurement point is obtained; Among them, the soft measurement model is constructed by using the neural network method based on the historical data of the fault measurement points and related measurement points obtained from the database, and then formed after training; S3. Collect the real-time data of the associated measuring points. Based on the mapping relationship between the fault measuring points and the associated measuring points, select the real-time data of the corresponding associated measuring points as the input variables of the soft measurement model, calculate the value of the fault measuring point, and complete the soft measurement of the fault measuring point in the energy storage power station.

[0006] In some embodiments, in S1, according to the integrated structure and characteristics of the energy storage power station, specifically including: when selecting the associated measuring points among the fault measuring points of the energy storage power station, it is necessary to consider the physical correlation or logical correlation between the fault measuring points and the associated measuring points, as well as the degree of influence of the fault measuring points and the associated measuring points on the safe operation of the energy storage power station.

[0007] In some implementations, in S2, when constructing the soft measurement model, the operating conditions of the energy storage power station are considered so that the acquired historical data can cover the typical conditions of the energy storage power station.

[0008] In some implementations, in S2, when constructing the soft sensor model, it is constructed by using a radial basis neural network.

[0009] Furthermore, in S2, the radial basis neural network includes an input layer, a hidden layer and an output layer; wherein the input layer is used to receive the associated measuring points as input variables and pass them to the hidden layer; the hidden layer is used to perform nonlinear transformation on the input variables, and the output layer is used to output the predicted value of the fault measuring point.

[0010] Furthermore, in S2, in the hidden layer, the input variables are nonlinearly transformed and the input features are mapped to a high-dimensional space, and the hidden neural units in each hidden layer adopt radial basis functions as activation functions.

[0011] In some implementations, in S2, when constructing the soft measurement model, firstly cluster the training samples of the soft measurement model to obtain the centers and dispersions of all clusters, and then determine the diffusion factor of the radial basis function.

[0012] Furthermore, in S2, the training of the soft sensor model specifically includes: For the input sample x , the output of the network is given by the following formula (1): (1); in, The radial basis neural network The output, that is, Fault point value , To connect hidden layer nodes to The weights of the output layer nodes, For the The center of the hidden nodes, is the diffusion factor, i.e. The activation level of the radial basis function, For the The bias of the output layer nodes, is the Euclidean norm, is the activation function; Activation Function The definition of is as follows: (2); Diffusion Factor σ The standard deviation of the corresponding Gaussian function indicates the degree of activation of the activation function.

[0013] Furthermore, in S2, determining the diffusion factor of the radial basis function specifically includes: When constructing a soft sensor model, the training samples of the soft sensor model are first clustered to obtain the center and dispersion of all clusters, and then the diffusion factor of the radial basis function is determined. First, the training samples of the soft sensor model are clustered, and the center and dispersion of all clusters are obtained using the following formula (3): (3); In the formula, For the The dispersion of class samples, For the The number of samples of the class, For the Class samples, For the The center of the class sample, the diffusion factor of the radial basis neural network with Gaussian kernel is determined by the following formula (4): (4); in, For the The diffusion factor of the radial basis function, is a constant coefficient, d max is the maximum distance between any two classes, is the number of sample classes, p n For the n The dispersion of the clusters, 、 、 They are d max , , p n The exponential coefficient of .

[0014] The present invention also provides a soft measurement system for monitoring points of safe operation risks of energy storage power stations, the system comprising a measurement point selection and data acquisition module, a soft measurement model construction module and a soft measurement calculation module, wherein: The measurement point selection and data acquisition module is used to determine the location and type of the fault sensor in the energy storage power station, select the fault measurement point and its associated measurement points, and collect real-time data of the associated measurement points; The soft measurement model building module is used to build a soft measurement model using a neural network method based on the fault measurement point and related measurement point historical data obtained from the database; The soft measurement calculation module is used to receive the real-time data of the associated measuring points as input variables, calculate the value of the fault measuring point based on the constructed soft measurement model and the mapping relationship between the fault measuring point and the associated measuring points, and complete the soft measurement of the fault measuring point in the energy storage power station.

[0015] Compared with the prior art, the soft measurement method and system for monitoring points of safe operation risks of energy storage power stations of the present invention have the following beneficial effects: The present invention provides a soft measurement method for monitoring points of safe operation risks of energy storage power stations. The present invention provides a soft measurement method for monitoring points of safe operation risks of energy storage power stations, comprising the following steps: S1, determining the position and type of a fault sensor in the energy storage power station, selecting a fault measurement point corresponding to the fault sensor, and selecting an associated measurement point in the fault measurement point according to the integrated structure and characteristics of the energy storage power station; S2, obtaining a mapping relationship between the fault measurement point and the associated measurement point based on a soft measurement model; wherein the soft measurement model is constructed by using a neural network method based on the historical data of the fault measurement point and the associated measurement point obtained from a database, and then formed after training; S3, collecting real-time data of the associated measurement point, based on the mapping relationship between the fault measurement point and the associated measurement point, selecting the real-time data of the corresponding associated measurement point as the input variable of the soft measurement model, calculating the value of the fault measurement point, and completing the soft measurement of the fault measurement point in the energy storage power station. The present invention first determines the associated measurement point of the fault measurement point through professional knowledge, and obtains the input and output of the mapping model. Then, based on the historical data of the fault measurement point and the associated measurement point, a soft measurement model is constructed to obtain the mapping relationship between the fault measurement point and the associated measurement point. Finally, based on the established soft measurement model and the measurement values ​​of the associated measurement points, the fault measurement point values ​​are calculated in real time, thereby realizing the monitoring of the energy storage power station. The present invention can replace the fault measurement point hardware to realize the indirect measurement of the measurement point. The method accurately screens the associated measurement points and determines the effective model input through the integration of the algorithm and artificial intelligence. On this basis, a soft measurement model is constructed, which effectively reduces the complexity of the model and increases the robustness of the model, so that the model can monitor the energy storage power station during long-term operation when there are relatively many batteries in the energy storage power station and many measurement points and sensors, ensuring its reliability. Through the soft measurement method of the present invention, the status of the faulty sensor in the energy storage power station can be monitored in real time, potential safety risks can be discovered in time, which helps to prevent accidents and improve the safety of the overall operation of the energy storage power station. The method of the present invention can be applied to the soft measurement of fault measurement points in various types of energy storage power stations, and has good applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings in the specification are used to provide further understanding of the present invention and constitute a part of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0017] Figure 1 The present invention is a soft measurement method for monitoring points of safe operation risks of energy storage power stations and a schematic diagram of the architecture of a radial basis function neural network model in the system. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0019] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. 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.

[0020] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0021] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0022] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0023] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0024] How to provide a measurement model and method suitable for energy storage power stations so that they can monitor energy storage power stations during long-term operation to ensure their reliability when there are relatively many batteries, measurement points and sensors in the energy storage power stations.

[0025] like Figure 1 As shown, the present invention provides a soft measurement method for monitoring points of safe operation risks of energy storage power stations, comprising the following steps: S1. Determine the location and type of the fault sensor in the energy storage power station, select the fault measuring point corresponding to the fault sensor, and select the associated measuring point among the fault measuring points according to the integrated structure and characteristics of the energy storage power station; S2. Based on the soft measurement model, the mapping relationship between the fault measurement point and the associated measurement point is obtained; Among them, the soft sensor model is constructed by using the neural network method based on the historical data of the fault measurement points and related measurement points obtained from the database, and then obtained after training; S3. Collect the real-time data of the associated measuring points. Based on the mapping relationship between the fault measuring points and the associated measuring points, select the real-time data of the corresponding associated measuring points as the input variables of the soft measurement model, calculate the value of the fault measuring point, and complete the soft measurement of the fault measuring point in the energy storage power station.

[0026] The soft measurement method of the safe operation risk monitoring point of the energy storage power station of the present invention determines the location and type of the fault sensor, determines the corresponding fault measurement point, and selects the associated measurement point of the fault measurement point according to the integrated structure and characteristics of the power station; extracts the historical data of the fault measurement point and the associated measurement point, and establishes the mapping relationship between the fault measurement point and the associated measurement point according to the historical data; finally, according to the real-time data of the associated measurement point collected, the current data value of the fault measurement point is calculated to complete the soft measurement of the fault measurement point. The method of the present invention can be applied to various types of energy storage power stations such as electrochemical and compressed air energy storage. The present invention can realize the prediction and monitoring of fault measurement points through the soft measurement model, reduce the dependence on actual sensors and the replacement frequency, and thus reduce the maintenance cost of the energy storage power station.

[0027] In some embodiments, the soft measurement method of the energy storage power station safety operation risk monitoring point of the present invention takes into account the integrated structure and characteristics of the energy storage power station, as well as the physical or logical correlation between the fault measurement point and the associated measurement point, so that the soft measurement model is more in line with the actual operation of the energy storage power station, thereby improving the rationality of monitoring, thereby improving the safety factor of the energy storage power station.

[0028] Specifically, in model construction, the present invention uses a neural network method to construct a soft measurement model, which can make full use of the information in historical data and mine the potential relationship between data. In addition, the present invention determines the diffusion factor of the radial basis function through clustering and other methods, so that the soft measurement model can adapt to data changes under different working conditions, thereby improving the adaptability of the model.

[0029] The present invention also provides a soft measurement system for monitoring points of safe operation risks of energy storage power stations. The system includes a measurement point selection and data acquisition module, a soft measurement model construction module, and a soft measurement calculation module. The measurement point selection and data acquisition module is used to determine the location and type of fault sensors in the energy storage power station, select fault measurement points and their associated measurement points, and collect real-time data of associated measurement points; the soft measurement model construction module is used to construct a soft measurement model using a neural network method based on the historical data of fault measurement points and associated measurement points obtained from the database; the soft measurement calculation module is used to receive the real-time data of associated measurement points as input variables, calculate the value of the fault measurement point based on the constructed soft measurement model and the mapping relationship between the fault measurement point and the associated measurement point, and complete the soft measurement of the fault measurement point in the energy storage power station. The above system provides a modular carrier for the soft measurement method of the present invention, thereby realizing intelligent monitoring and early warning of energy storage power stations, and providing technical support for the overall operation and maintenance of energy storage power stations.

[0030] The soft measurement method and system for monitoring points of safe operation risks of energy storage power stations of the present invention are further described in detail below through specific embodiments.

[0031] Determine the fault measuring point and the associated measuring points; First, determine the type and location of the faulty sensor in the system. Take the failure of a battery cell temperature measurement point t in a battery energy storage power station as an example: Determine the location of the battery cell, then the rest of the battery pack where the battery cell is located n Battery cell temperature measurement point , is the associated measuring point of the fault measuring point; at the same time, the cell temperature is related to the thermal balance relationship between its heat generation and heat dissipation, so the cell charging current , battery compartment temperature (ambient temperature) is the associated measuring point of the fault measuring point. The associated measuring points of the fault measuring point are determined as follows: , that is, in the soft sensor model, Input sample X to the model, t Output sample y for the model.

[0032] Soft sensor modeling; The historical data of the fault measurement points are obtained from the database, and the historical data of the measurement points are associated. The principle of determining the time interval is to ensure that the data covers all typical working conditions. The radial basis function neural network method (RBFNN) method is used to build the soft measurement model.

[0033] A typical RBFNN consists of three layers: input layer, hidden layer, and output layer, as shown in the figure. The input layer receives the associated measurement points as input variables and passes them to the hidden layer. In the hidden layer, the input variables are nonlinearly transformed and the input features are mapped to a high-dimensional space. Each hidden neural unit uses a radial basis function (such as a Gaussian function) as an activation function. The output layer acts as a linear combiner, and the dependent variable is calculated as the linear weighted value of the hidden layer output. The weights and biases can be directly calculated by pseudo-inverse operations or determined by the back-propagation algorithm.

[0034] For the input sample , the output of the network is given by the following formula (1): (1); in, The radial basis neural network The output, that is, Fault point value , To connect hidden layer nodes to The weights of the output layer nodes, For the The center of the hidden nodes, is the diffusion factor, i.e. The activation level of the radial basis function, For the The bias of the output layer nodes, is the Euclidean norm, is the activation function, Activation Function The definition of is as follows: (2); Diffusion Factor σ The standard deviation of the corresponding Gaussian function indicates the degree of activation of the activation function.

[0035] First, the training samples of the soft sensor model are clustered, and the center and dispersion of all clusters are obtained using the following formula (3): (3); In the formula, For the The dispersion of class samples, For the The number of samples of the class, For the Class samples, For the The center of the class sample. Then the diffusion factor of the RBFNN with Gaussian kernel is determined by the following formula (4): (4); in, For the The diffusion factor of the radial basis function, is a constant coefficient, d max is the maximum distance between any two classes, is the number of sample classes, p n For the n The dispersion of the clusters, 、 、 They are d max , , p n The exponential coefficient of .

[0036] Real-time calculation of fault measurement points After the soft measurement model is trained, real-time calculation of fault measurement points can be performed. Collect real-time data of related measurement points: , calculated by the soft sensor model: (5); Where t is the temperature measurement point of the battery cell, is the cell charging current, is the temperature inside the battery compartment.

[0037] Through the calculation of the soft measurement model, the soft measurement of the fault measurement point in the energy storage power station is finally completed, and then the energy storage power station can be monitored in real time.

[0038] The present invention provides a soft measurement method and system for monitoring points of safe operation risks of energy storage power stations, which realizes monitoring of safe operation risks of energy storage power stations by combining neural network modeling and selection of fault measurement points. Through this method, operation and maintenance personnel can relatively accurately understand the operating status of the energy storage power station, thereby improving operation and maintenance efficiency and work quality, and reducing maintenance costs, thereby improving the safety of the energy storage power station as a whole. At the same time, the present invention can also be applied to various types of energy storage power stations such as electrochemical and compressed air energy storage, and has certain applicability.

[0039] Finally, it should be noted that the above is only a preferred embodiment of the present invention and does not limit the present invention in any form. Any ordinary technician in the industry can smoothly implement the present invention as shown in the specification and described above, and any equivalent changes, modifications and evolutions made by using the technical content disclosed above are all equivalent embodiments of the present invention. At the same time, any equivalent changes, modifications and evolutions made to the above embodiments based on the essential technology of the present invention are still within the protection scope of the technical solution of the present invention.

Claims

1. A soft measurement method for monitoring points of safe operation risks of energy storage power stations, characterized in that: The steps include: S1. Determine the location and type of the fault sensor in the energy storage power station, select the fault measuring point corresponding to the fault sensor, and select the associated measuring point among the fault measuring points according to the integrated structure and characteristics of the energy storage power station; S2. Based on the soft measurement model, the mapping relationship between the fault measurement point and the associated measurement point is obtained; Among them, the soft measurement model is constructed by using the neural network method based on the historical data of the fault measurement points and related measurement points obtained from the database, and then formed after training; S3. Collect the real-time data of the associated measuring points. Based on the mapping relationship between the fault measuring points and the associated measuring points, select the real-time data of the corresponding associated measuring points as the input variables of the soft measurement model, calculate the value of the fault measuring point, and complete the soft measurement of the fault measuring point in the energy storage power station.

2. The soft measurement method for monitoring points of safe operation risks of energy storage power stations according to claim 1 is characterized in that: In said S1, according to the integrated structure and characteristics of the energy storage power station, specifically including: when selecting the associated measuring points among the fault measuring points of the energy storage power station, considering the physical or logical correlation between the fault measuring points and the associated measuring points, and the influence of the fault measuring points and the associated measuring points on the safe operation of the energy storage power station.

3. The soft measurement method for monitoring points of safe operation risks of energy storage power stations according to claim 1 is characterized in that: In S2, when constructing the soft measurement model, the operating conditions of the energy storage power station are considered so that the acquired historical data can cover the typical conditions of the energy storage power station.

4. The soft measurement method for monitoring points of safe operation risks of energy storage power stations according to claim 1 is characterized in that: In S2, when constructing the soft sensor model, it is constructed by adopting a radial basis neural network.

5. The soft measurement method for monitoring points of safe operation risks of energy storage power stations according to claim 4 is characterized in that: In S2, the radial basis neural network includes an input layer, a hidden layer and an output layer; wherein the input layer is used to receive the associated measuring points as input variables and pass them to the hidden layer; the hidden layer is used to perform nonlinear transformation on the input variables, and the output layer is used to output the predicted value of the fault measuring point.

6. The soft measurement method for monitoring points of safe operation risks of energy storage power stations according to claim 5 is characterized in that: In S2, in the hidden layer, nonlinear transformation is performed on the input variables, and the input features are mapped to a high-dimensional space, and the hidden neural units in each hidden layer use radial basis functions as activation functions.

7. The soft measurement method for monitoring points of safe operation risks of energy storage power stations according to claim 1 is characterized in that: In S2, when constructing the soft measurement model, firstly cluster the training samples of the soft measurement model to obtain the centers and dispersions of all clusters, and then determine the diffusion factor of the radial basis function.

8. The soft measurement method for monitoring points of safe operation risks of energy storage power stations according to claim 7 is characterized in that: In S2, the training of the soft sensor model specifically includes: For the input sample , the output of the network is given by the following formula (1): （1）； in, The radial basis neural network The output, that is, Fault point value , To connect hidden layer nodes to The weights of the output layer nodes, For the The center of the hidden nodes, is the diffusion factor, i.e. The activation level of the radial basis function, For the The bias of the output layer nodes, is the Euclidean norm, is the activation function; Activation Function The definition of is as follows: （2）； Diffusion Factor σ The standard deviation of the corresponding Gaussian function indicates the degree of activation of the activation function.

9. The soft measurement method for monitoring points of safe operation risks of energy storage power stations according to claim 8 is characterized in that: In S2, determining the diffusion factor of the radial basis function specifically includes: When constructing a soft sensor model, the training samples of the soft sensor model are first clustered to obtain the center and dispersion of all clusters, and then the diffusion factor of the radial basis function is determined. First, the training samples of the soft sensor model are clustered, and the center and dispersion of all clusters are obtained using the following formula (3): （3）； In the formula, For the The dispersion of class samples, For the The number of samples of the class, For the Class samples, For the The center of the class sample, the diffusion factor of the radial basis neural network with Gaussian kernel is determined by the following formula (4): （4）； in, For the The diffusion factor of the radial basis function, is a constant coefficient, d max is the maximum distance between any two classes, is the number of sample classes, p n For the n The dispersion of the clusters, 、 、 They are d max , , p n The exponential coefficient of .

10. A system based on the soft measurement method for monitoring points of safe operation risks of energy storage power stations according to any one of claims 1 to 9, characterized in that: The system includes a measurement point selection and data acquisition module, a soft measurement model construction module and a soft measurement calculation module, wherein: The measurement point selection and data acquisition module is used to determine the location and type of the fault sensor in the energy storage power station, select the fault measurement point and its associated measurement points, and collect real-time data of the associated measurement points; The soft measurement model building module is used to build a soft measurement model using a neural network method based on the fault measurement point and related measurement point historical data obtained from the database; The soft measurement calculation module is used to receive the real-time data of the associated measuring points as input variables, calculate the value of the fault measuring point based on the constructed soft measurement model and the mapping relationship between the fault measuring point and the associated measuring points, and complete the soft measurement of the fault measuring point in the energy storage power station.

Images