Energy storage power station state evaluation method, device and equipment and storage medium

Abstract

The invention relates to an energy storage power station state evaluation method, device and equipment and a storage medium, and the method comprises the following steps: obtaining state data used for evaluating the state of an energy storage power station, and carrying out the preprocessing of the state data, and obtaining the preprocessing data; the pre-processed data comprises real-time pre-processed data and historical pre-processed data; an LSTM neural network model is adopted to process the real-time preprocessed data and the historical preprocessed data, the conformity degree of the real-time preprocessed data and the historical preprocessed data is confirmed, and if the real-time preprocessed data and the historical preprocessed data are not conformed, the real-time preprocessed data is adopted as current data; if yes, integrating the real-time preprocessed data and the historical preprocessed data to obtain current data; calculating weights of different state data in the current data through an AHP (Analytic Hierarchy Process); and combining the current data with the weight to evaluate the state of the energy storage power station. The evaluation accuracy is improved, the evaluation workload is reduced, and the operation and maintenance efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the field of electric power and energy technology, and specifically relates to a method, device, equipment and storage medium for evaluating the state of an energy storage power station. Background Art

[0002] As the concept of new power systems continues to gain popularity, a new situation of source, grid, load and storage is taking shape. The rise of electrochemical energy storage in recent years has brought about an energy revolution. As new energy sources such as solar energy and wind energy continue to be connected to the power grid, it has also brought challenges to the stability of the power grid. Energy storage systems can effectively suppress grid disturbances, thus attracting major energy companies to build energy storage power stations.

[0003] However, energy storage power stations have many energy storage units, and on-site operation and maintenance are difficult, especially for large energy storage power stations with more than several hundred megawatt hours. There are many inspection items and there may be situations where inspections are not in place.

[0004] CN202410979956.4 discloses a method and system for evaluating the health status of distribution equipment. The method collects multi-dimensional operating data of the distribution equipment through a sensor network, pre-processes the collected multi-dimensional operating data, extracts multi-modal feature parameters from the pre-processed data, and uses multi-source data fusion technology to weightedly fuse the extracted multi-modal features to calculate the comprehensive health index of the distribution equipment. Based on the comprehensive health index, a health status evaluation model for the distribution equipment is established using a deep learning algorithm and historical operating data. When an abnormal health status of the equipment is monitored, intelligent early warning information is generated, and intelligent fault diagnosis is performed in combination with historical data and fault characteristics to determine the fault type, location and cause, and generate maintenance recommendations. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a method, device, equipment and storage medium for evaluating the status of an energy storage power station, so as to improve the accuracy of the evaluation, reduce the workload of the evaluation and improve the operation and maintenance efficiency.

[0006] The embodiment of the present invention provides a method for evaluating the state of an energy storage power station, comprising the following steps: Acquire status data for evaluating the status of the energy storage power station, preprocess the status data to obtain preprocessed data, the status data at least including noise, temperature and fire gas concentration of the energy storage power station; the preprocessed data includes real-time preprocessed data and historical preprocessed data; The real-time preprocessed data and the historical preprocessed data are processed by using an LSTM neural network model to confirm the degree of consistency between the real-time preprocessed data and the historical preprocessed data. If they are inconsistent, the real-time preprocessed data is used as the current data; if they are consistent, the real-time preprocessed data and the historical preprocessed data are integrated to obtain the current data; Calculate the weights of different status data in the current data by AHP; The current data and the weight are combined to evaluate the state of the energy storage power station to obtain an evaluation value, which is used as the evaluation result of the state of the energy storage power station.

[0007] Optionally, preprocessing the state data to obtain the preprocessed data includes comparing the value of the state data with a minimum value allowed during normal operation of the energy storage power station, and obtaining processed data according to the comparison result; The pre-processed data is an average matrix of multiple processed data.

[0008] Optionally, if the value of the status data is within 2 times the minimum value allowed during normal operation of the energy storage power station, the processed data is 2-ratio, where the ratio is the ratio of the value of the status data to the minimum value allowed during normal operation of the energy storage power station; otherwise, the processed data is 0.

[0009] Optionally, the fire fighting gas is hydrogen or carbon monoxide.

[0010] Optionally, the real-time preprocessed data and the historical preprocessed data are processed using an LSTM neural network model, and the probability distribution of the real-time preprocessed data and the probability distribution of the historical preprocessed data are calculated respectively to obtain the difference M between the probability distribution of the real-time preprocessed data and the probability distribution of the historical preprocessed data. i , if the difference M i If the real-time preprocessing data is greater than the threshold value M, the real-time preprocessing data and the historical preprocessing data are inconsistent; otherwise, the real-time preprocessing data and the historical preprocessing data are consistent.

[0011] Optionally, if they match, the real-time preprocessed data and the historical preprocessed data are integrated to obtain the current data, including combining the real-time preprocessed data with multiple historical preprocessed data to obtain the total data, calculating the average matrix of the total data, and taking the average matrix of the total data as the current data.

[0012] Optionally, the weights of different state data in the current data are calculated by AHP, including constructing a judgment matrix and performing expert scoring, and using the sum-product method to calculate the weights of corresponding state data.

[0013] An embodiment of the present invention provides a device for evaluating the state of an energy storage power station, comprising: A collection module, wherein the collection unit obtains status data for evaluating the status of the energy storage power station; A preprocessing module, used to preprocess the state data to obtain preprocessed data, wherein the state data at least includes noise, temperature and fire gas concentration of the energy storage power station; the preprocessed data includes real-time preprocessed data and historical preprocessed data; A processing module, wherein the processing unit uses an LSTM neural network model to process the real-time preprocessed data and the historical preprocessed data, confirms the degree of consistency between the real-time preprocessed data and the historical preprocessed data, and if they do not match, uses the real-time preprocessed data as the current data; if they match, combines the real-time preprocessed data and the historical preprocessed data to obtain the current data; A weight calculation module is used to calculate the weights of different state data in the current data by using AHP hierarchical analysis method; An evaluation module combines the current data and the weight to evaluate the state of the energy storage power station, obtains an evaluation value, and uses the evaluation value as the evaluation result of the state of the energy storage power station.

[0014] An embodiment of the present invention provides an electronic device, including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the energy storage power station status assessment method as described.

[0015] An embodiment of the present invention provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the energy storage power station status assessment method.

[0016] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method described above.

[0017] The beneficial effect of the present invention is that the present invention selects the core data that affect the state of the energy storage power station, namely noise, temperature and fire gas concentration, which can more accurately reflect the state of the energy storage power station. The present invention preprocesses these state data by comparing them with the minimum value allowed during the normal operation of the energy storage power station, and the processed data output is either 0 or a 2-ratio, which can fully reflect the state of the energy storage power station.

[0018] The present invention takes into account both historical data and real-time data to avoid partial data deviation due to normal aging, so the introduction of historical data can increase the reliability of judgment. When introducing historical data, the present invention does not simply use historical data as a reference, but will comprehensively compare the accuracy of real-time status data and historical status data in evaluating the status of the energy storage power station, and combine the two to make it more accurate in evaluating the status of the energy storage power station. Combined with the AHP hierarchical analysis method to calculate the weights of different status data in the current data, the evaluation results obtained can more accurately evaluate the status of the energy storage power station and improve the accuracy of the evaluation.

[0019] The present invention is mainly aimed at on-site operation and maintenance personnel of energy storage stations. Considering that there are many on-site energy storage units and the operation and maintenance workload is large, it is easy to cause negligence or omission of certain units. The present invention is easy to carry due to its compact and lightweight physical characteristics, and can make a preliminary comprehensive evaluation of the energy storage system to match the preliminary work of operation and maintenance, and can upload the operation and maintenance records to the background system for storage to ensure that no units are missed. It can greatly improve the efficiency of operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which: Figure 1 It is a structural schematic diagram of the handheld energy storage inspection instrument of the present invention.

[0021] Figure 2 This is a program running logic block diagram of the handheld energy storage inspection instrument of the present invention.

[0022] Figure 3 It is a flow chart of the energy storage power station status assessment method of the present invention. DETAILED DESCRIPTION

[0023] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. In the subsequent description, suffixes such as "module", "component" or "unit" used to represent elements are used only to facilitate the description of the present invention, and have no specific meaning in themselves. Therefore, "module", "component" or "unit" can be used in a mixed manner. In this subsequent description, the continuous numbering of the method steps is for the convenience of review and understanding. In combination with the overall technical solution of the present invention and the logical relationship between the various steps, adjusting the implementation order between the steps will not affect the technical effect achieved by the technical solution of the present invention. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limitations of the present invention.

[0024] Example 1 A method for evaluating the state of an energy storage power station comprises the following steps: 1. Obtain status data for evaluating the status of the energy storage power station, preprocess the status data to obtain preprocessed data, wherein the status data at least includes noise, temperature and fire gas concentration of the energy storage power station; the preprocessed data includes real-time preprocessed data and historical preprocessed data.

[0025] Specifically, preprocessing the state data to obtain the preprocessed data includes comparing the value of the state data with the minimum value allowed during normal operation of the energy storage power station, and obtaining processed data according to the comparison result; If the value of the status data is within 2 times the minimum value allowed during normal operation of the energy storage power station, the processed data is 2-ratio, where the ratio is the ratio of the value of the status data to the minimum value allowed during normal operation of the energy storage power station; otherwise, the processed data is 0.

[0026] The firefighting gas is hydrogen or carbon monoxide.

[0027] The specific calculation process and formula are as follows: i) When hour, The value is obtained according to the following algorithm; , ( ) ii) When hour, as follows; , ( ) in, is the processed data of each status data, is the current value of the collected status data (since only the running status is evaluated, Should be greater than or equal to Value, if it is less than that, it is considered as standby or shutdown state and does not participate in the evaluation). is the minimum value allowed for normal operation. Indicates Test data.

[0028] The pre-processed data is an average matrix of multiple processed data.

[0029] Specifically, for historical data, i) When the amount of data is small ( ), calculate the average matrix of the historical data matrix: Assume that the historical data matrix , then the mean matrix ,and ; ii) When the amount of data is large ( ), first calculate the isometric matrix of historical data: Historical data Perform equidistant sampling and filter out 100 data at different levels, that is, , and then find the average matrix of the data .

[0030] For real-time data, directly calculate the average matrix of real-time data .

[0031] 2. Use the LSTM neural network model to process the real-time preprocessed data and the historical preprocessed data, and confirm the consistency between the real-time preprocessed data and the historical preprocessed data. If they are inconsistent, use the real-time preprocessed data as the current data; if they are consistent, combine the real-time preprocessed data and the historical preprocessed data to obtain the current data; Specifically, first build an LSTM neural network model; input the real-time preprocessed data collected in real time into the LSTM neural network model to observe the output results, and set the difference threshold M by calculating the difference Mi between the probability distribution of the real-time preprocessed data generated by the model and the probability distribution of the historical preprocessed data.

[0032] Specifically, the real-time preprocessing data and the historical preprocessing data are processed by using the LSTM neural network model, and the probability distribution of the real-time preprocessing data and the probability distribution of the historical preprocessing data are calculated respectively, and the difference M between the probability distribution of the real-time preprocessing data and the probability distribution of the historical preprocessing data is obtained. i , if the difference M i If the real-time preprocessing data is greater than the threshold value M, the real-time preprocessing data and the historical preprocessing data are inconsistent; otherwise, the real-time preprocessing data and the historical preprocessing data are consistent.

[0033] If they match, the real-time preprocessed data and the historical preprocessed data are integrated to obtain the current data, including combining the real-time preprocessed data with multiple historical preprocessed data to obtain the total data, calculating the average matrix of the total data, and taking the average matrix of the total data as the current data.

[0034] The specific steps are as follows: When Mi>M, it is considered that the real-time data is inconsistent with the historical data. At this time:

[0035] When Mi ≤M, the real-time data is considered to be consistent with the historical data. At this time:

[0036] And at this time, the real-time data needs to be loaded into the historical data, that is:

[0037] α and β are the weights of historical preprocessed data and real-time preprocessed data, respectively.

[0038] 3. Calculate the weights of different state data in the current data by AHP. Specifically, calculate the weights of different state data in the current data by AHP, including constructing a judgment matrix and performing expert scoring, and using the sum-product method to calculate the weights of the corresponding state data.

[0039] Specifically, the weight ratio of noise, temperature and fire gas concentration is: .

[0040] Construct a judgment matrix: a) Define the quantitative value regulations for comparison between indicators:

[0041] b) Target layer and indicator layer judgment matrix, and expert scoring:

[0042] c) Use the sum-product method to find the weight of the corresponding indicator:

[0043] in , .

[0044] d)Consistency check: Let the matrix ,vector , calculate ,(in for Eigenvalues, is the order), check Analytical Hierarchy Process Table, get ; Analytical Hierarchy Process The table is as follows:

[0045] calculate ,when , the consistency check passed.

[0046] 4. Combining the current data with the weight to evaluate the state of the energy storage power station, obtaining an evaluation value, and using the evaluation value as the evaluation result of the state of the energy storage power station.

[0047] Specifically, the pre-processed data read and collected is brought into the energy storage system status assessment model to calculate the health score. The energy storage system status assessment model is as follows: .

[0048] Perform corresponding operations according to the health comparison table. The health comparison table is as follows:

[0049] Example 2 A handheld energy storage inspection instrument includes a hardware part and an operating program. The hardware part is mainly composed of the following modules: a noise collector 3, an infrared temperature sensor 4, a fire gas detector 5, a camera 6, a display screen 2, a battery 1, a microprocessor 8, a memory card 9 and a communication module 7.

[0050] The noise collector 3 is mainly composed of a microphone, an operational amplifier, etc. to form a sound intensity detector. The collected sound signal is amplified, filtered, and analog-to-digital converted before being transmitted to the microprocessor 8 for calculation. At the same time, the data is stored for easy display and viewing.

[0051] The infrared temperature sensor 4 uses the thermal radiation phenomenon of the object to feedback the object temperature through the different infrared intensity. The collected temperature signal is also amplified, filtered, and analog-to-digital converted and then transmitted to the microprocessor 8 for calculation, while the temperature information of each part of the object within the detection range is displayed using thermal imaging technology.

[0052] The fire gas detector 5 uses the principles of catalytic combustion and electrochemical reaction to collect fire gases such as hydrogen and carbon monoxide that are easily generated when the energy storage unit fails, and transmits the data to the microprocessor 8 for calculation after data processing.

[0053] The camera 6 is used to obtain the current physical state of the energy storage unit, and can take videos and photos of the energy storage unit and store them in the memory card 9 for subsequent use.

[0054] Display screen 2 is used to display the analog quantities collected previously, and can also display the images taken by camera 1, and supports touch screen operation, viewing, sending and printing information.

[0055] The storage battery 1 is used to provide an energy source for the energy storage inspection instrument. The storage battery 1 is a detachable device. If it needs to be used for a long time, a spare battery can be added for easy replacement.

[0056] The microprocessor 8 is a central computing unit, which performs logic and mathematical operations on the analog quantities collected above, obtains a comprehensive evaluation result, and prints the result on a display screen.

[0057] The memory card 9 provides data storage, and can store the aforementioned collected analog information, videos and photos as well as the comprehensive evaluation results calculated by the processor for subsequent retrieval.

[0058] The communication module 7 can receive local weather service information to inform the operation and maintenance personnel of the recent climate conditions and assist the operation and maintenance personnel in determining whether to take relevant measures to deal with the next weather conditions. At the same time, the comprehensive evaluation results calculated by the microprocessor 8 will generate an electronic operation and maintenance log, which will record various analog quantity information, comprehensive evaluation results, weather conditions and date information, etc. These will be synchronized to the background operation and maintenance system through the communication module for subsequent reference and data collation.

[0059] When the operation and maintenance personnel conduct on-site maintenance, they first check the battery compartment in order. The items to be checked are as follows: first check the appearance to see if there is mechanical deformation or electrical fire that causes carbonization of the equipment; second check the fire-fighting equipment to see if there is a fire alarm or fault; then open the door to check the battery operation status and whether there is fire-fighting gas leakage, and use a temperature gun to scan and measure the temperature of the equipment to see if there is any abnormality; finally, use text records to archive the inspection items. This completes the inspection of one device, and a set of units of a 0.5P energy storage system generally contains two battery compartments and an integrated machine, that is, the above work needs to be doubled to complete the inspection of a set of energy storage units. For large energy storage power stations with dozens or hundreds of energy storage units, the operation and maintenance work required to be carried out requires considerable manpower and time, and often requires carrying a large number of testing tools, which is very cumbersome. The operation and maintenance data recorded in paper may cause data misrecording or data loss due to human factors or poor management in the later stage.

[0060] When the device of the present invention is used, the data collection, judgment and recording work all adopt one-button operation, which can effectively improve the operation and maintenance efficiency. On-site operation and maintenance personnel only need to start the device in the energy storage equipment area, press the button, and use advanced sensor technology, the equipment can automatically collect key parameters such as equipment noise, temperature and fire gas concentration, and perform accurate monitoring. And through the internal logic program of the device, intelligent calculation and analysis are performed to calculate the current operating status of the energy storage device, and assist the operation and maintenance personnel to judge the operating equipment. At the same time, the device of the invention uses digital recording of the operating data of the equipment and takes photos or videos of the equipment to automatically organize them into electronic operation and maintenance records and print them to the background management system, establish equipment files, and avoid operational errors caused by human records. This is convenient for storage and organization, and also convenient for later reference. If a fault analysis is performed, the electronic record will also restore the actual situation of the equipment at that time as much as possible. In addition, the device is light and convenient, easy to carry, and avoids the confusion of operation and maintenance personnel carrying a large number of detection tools.

[0061] From the perspective of time, since the present invention can collect all physical quantities of the energy storage device during operation at one time, the time originally required for manually measuring a single physical quantity is reduced.

[0062] From the perspective of operation and maintenance functions, the original operation and maintenance method requires the transcription of each detected physical quantity and manual analysis. The present invention uses a set of intelligent analysis algorithms to perform algorithmic analysis on the monitored physical quantities and output the results. This method has certain scientificity and higher repeatability.

[0063] From the data record point of view, the device of the present invention will collect and calculate the data to form an electronic operation and maintenance record, which can record the operation data of more units at the same time. It will also record the actual status of the equipment at that time (in the form of photos, videos, etc.), which is convenient for more accurate display of equipment information during later fault analysis or log query.

[0064] As described above, the device of the present invention reduces the burden of maintenance personnel in terms of time, maintenance functions and data records, and the electronic maintenance records formed can store and consult massive data, which is better than the management of paper records. Comprehensively considered, the device of the present invention can greatly improve maintenance efficiency.

[0065] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0066] The embodiment of the present invention also discloses a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the aforementioned dual satellite antenna and installation angle calibration method.

[0067] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features described may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions, and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0068] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0069] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0070] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0071] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0072] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0073] A person skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of protection of the present application is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of different aspects of one or more embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0074] One or more embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of the present application should be included in the protection scope of the present application.

Claims

1. A method for evaluating the state of an energy storage power station, characterized in that: The following steps are included: Acquire status data for evaluating the status of the energy storage power station, preprocess the status data to obtain preprocessed data, the status data at least including noise, temperature and fire gas concentration of the energy storage power station; the preprocessed data includes real-time preprocessed data and historical preprocessed data; The real-time preprocessed data and the historical preprocessed data are processed by using an LSTM neural network model to confirm the degree of consistency between the real-time preprocessed data and the historical preprocessed data. If they are inconsistent, the real-time preprocessed data is used as the current data; if they are consistent, the real-time preprocessed data and the historical preprocessed data are integrated to obtain the current data; Calculate the weights of different status data in the current data by AHP; The current data and the weight are combined to evaluate the state of the energy storage power station to obtain an evaluation value, which is used as the evaluation result of the state of the energy storage power station.

2. The energy storage power station status assessment method according to claim 1, characterized in that: Preprocessing the state data to obtain the preprocessed data includes comparing the value of the state data with the minimum value allowed during normal operation of the energy storage power station, and obtaining processed data according to the comparison result; The pre-processed data is an average matrix of multiple processed data.

3. The energy storage power station status assessment method according to claim 2, characterized in that: If the value of the status data is within 2 times the minimum value allowed during normal operation of the energy storage power station, the processed data is 2-ratio, where the ratio is the ratio of the value of the status data to the minimum value allowed during normal operation of the energy storage power station; otherwise, the processed data is 0.

4. The energy storage power station status assessment method according to claim 1, characterized in that: The firefighting gas is hydrogen or carbon monoxide.

5. The energy storage power station status assessment method according to claim 1, characterized in that: The real-time preprocessing data and the historical preprocessing data are processed by using the LSTM neural network model, and the probability distribution of the real-time preprocessing data and the probability distribution of the historical preprocessing data are calculated respectively, and the difference M between the probability distribution of the real-time preprocessing data and the probability distribution of the historical preprocessing data is obtained. i , if the difference M i If it is greater than the threshold value M, the real-time preprocessing data and the historical preprocessing data do not match; Otherwise, the real-time preprocessed data and the historical preprocessed data are consistent.

6. The energy storage power station status assessment method according to any one of claims 1 to 5, characterized in that: If they match, the real-time preprocessed data and the historical preprocessed data are integrated to obtain the current data, including combining the real-time preprocessed data with multiple historical preprocessed data to obtain the total data, calculating the average matrix of the total data, and taking the average matrix of the total data as the current data.

7. The energy storage power station status assessment method according to any one of claims 1 to 5, characterized in that: The weights of different state data in the current data are calculated by AHP hierarchical analysis method. This includes constructing a judgment matrix and performing expert scoring, and using the sum-product method to find the weights of the corresponding status data.

8. A device for evaluating the state of an energy storage power station, characterized in that: include: A collection module, wherein the collection unit obtains status data for evaluating the status of the energy storage power station; A preprocessing module, used to preprocess the state data to obtain preprocessed data, wherein the state data at least includes noise, temperature and fire gas concentration of the energy storage power station; the preprocessed data includes real-time preprocessed data and historical preprocessed data; A processing module, wherein the processing unit uses an LSTM neural network model to process the real-time preprocessed data and the historical preprocessed data, confirms the degree of consistency between the real-time preprocessed data and the historical preprocessed data, and if they do not match, uses the real-time preprocessed data as the current data; if they match, combines the real-time preprocessed data and the historical preprocessed data to obtain the current data; A weight calculation module is used to calculate the weights of different state data in the current data by using AHP hierarchical analysis method; An evaluation module combines the current data and the weight to evaluate the state of the energy storage power station, obtains an evaluation value, and uses the evaluation value as the evaluation result of the state of the energy storage power station.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the energy storage power station status assessment method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the energy storage power station status assessment method according to any one of claims 1 to 7.

Images