Online monitoring method and system for network-forming type energy storage system

Abstract

The invention provides an online monitoring method and system for a network-building type energy storage system, and belongs to the technical field of energy storage monitoring, and the method comprises the steps: fusing the operation data of the network-building type energy storage system to obtain integrated data, the operation data being data obtained by monitoring a plurality of electrical parameters of the network-building type energy storage system through different monitoring devices; performing feature extraction on the comprehensive data to obtain target state feature data, and determining the state of the network-forming energy storage system based on the target state feature data; and monitoring the networking type energy storage system based on the state of the networking type energy storage system. According to the online monitoring method and system for the network-building type energy storage system provided by the invention, the comprehensiveness and accuracy of state evaluation are improved, and the accurate monitoring of the operation state of the network-building type energy storage system is realized.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of energy storage monitoring, and more specifically, relates to an online monitoring method and system for a network-forming energy storage system. Background Art

[0002] With the rapid development of new energy technologies, network-forming energy storage systems are increasingly widely used in power systems. The stability of their operating states directly affects the reliability and security of the power grid. Traditional monitoring methods for energy storage systems usually rely on threshold judgments of single parameters (such as voltage and current), and cannot comprehensively evaluate multi-dimensional data dynamically, and lack effective fusion analysis of environmental factors and equipment historical states. In addition, existing technologies are difficult to make precise adjustments according to real-time states, resulting in inaccurate monitoring results. Summary of the Invention

[0003] The purpose of the present disclosure is to provide an online monitoring method and system for a network-forming energy storage system to achieve precise evaluation of the operating state of the network-forming energy storage system and improve the reliability and maintenance efficiency of the operation of the network-forming energy storage system.

[0004] In the first aspect of the embodiments of the present disclosure, an online monitoring method for a network-forming energy storage system is provided, including: Fusing the operation data of the network-forming energy storage system to obtain comprehensive data, where the operation data is data obtained by different monitoring devices monitoring multiple electrical parameters of the network-forming energy storage system; Extracting features from the comprehensive data to obtain target state feature data, and determining the state of the network-forming energy storage system based on the target state feature data; Monitoring the network-forming energy storage system based on the state of the network-forming energy storage system.

[0005] In the second aspect of the embodiments of the present disclosure, an online monitoring system for a network-forming energy storage system is provided, including: A data processing module for fusing the operation data of the network-forming energy storage system to obtain comprehensive data, where the operation data is data obtained by different monitoring devices monitoring multiple electrical parameters of the network-forming energy storage system; A state determination module for extracting features from the comprehensive data to obtain target state feature data and determining the state of the network-forming energy storage system based on the target state feature data; A monitoring module for monitoring the network-forming energy storage system based on the state of the network-forming energy storage system.

[0006] The beneficial effects of the online monitoring method and system for the network-forming energy storage system provided by the embodiments of the present disclosure are as follows: By fusing the monitored operation data, comprehensive data is obtained, which accurately and comprehensively reflects the operation status of the network-forming energy storage system; extracting the target state feature data from the comprehensive data can capture the key information in the system operation more accurately, accurately judge the state of the system, and monitor the network-forming energy storage system based on the determined system state, which can make the monitoring more targeted and effective; realizing the accurate monitoring of the operation state of the network-forming energy storage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0008] Figure 1 It is a schematic flowchart of the online monitoring method for the network-forming energy storage system provided by an embodiment of the present disclosure; Figure 2 It is a structural block diagram of the online monitoring system for the network-forming energy storage system provided by an embodiment of the present disclosure; Figure 3 It is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0009] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present disclosure. However, those skilled in the art should clearly understand that the present disclosure can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present disclosure.

[0010] To make the objectives, technical solutions, and advantages of the present disclosure clearer, the following will be described through specific embodiments with reference to the drawings.

[0011] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of the online monitoring method for the network-forming energy storage system provided by an embodiment of the present disclosure. The method includes: S101: Fusing the operation data of the network-forming energy storage system to obtain comprehensive data, where the operation data is the data obtained by different monitoring devices for monitoring multiple electrical parameters of the network-forming energy storage system.

[0012] In this embodiment, operating data is obtained from multiple data acquisition points of the network-forming energy storage system. The operating data is the electrical parameters of the network-forming energy storage system, specifically including data such as current, voltage, frequency, power, state of charge (SOC), depth of discharge (DOD), etc.

[0013] In this embodiment, preliminary preprocessing is performed on the obtained operating data, including data cleaning and data normalization operations. During the data cleaning process, abnormal data generated due to reasons such as sensor failures and communication interferences is identified and removed, such as current and voltage values that significantly exceed the normal range. The preprocessed operating data is subjected to fusion processing to obtain comprehensive data. The fusion processing is integrated according to the fusion method or fusion strategy, enabling different electrical parameters to cooperate with each other to form a process of an information set that can more comprehensively and accurately reflect the state. Methods such as the weighted average method, Kalman filtering method, and neural network fusion method can be used during the fusion process.

[0014] S102: Feature extraction is performed on the comprehensive data to obtain target state feature data, and the state of the network-forming energy storage system is determined based on the target state feature data.

[0015] In this embodiment, the comprehensive data is first subjected to smoothing processing and normalization operations to eliminate the noise and random fluctuations in the data and eliminate the differences in dimension and numerical range among different electrical parameter data. A variety of feature extraction algorithms are used to extract target state feature data from the normalized comprehensive data. Time-domain feature extraction: Calculate time-domain features such as the mean, variance, standard deviation, peak value, and valley value of the data. Frequency-domain feature extraction: The time-domain data is converted to the frequency domain through fast Fourier transform, and frequency-domain features such as the main frequency components and frequency amplitudes in the spectrum are extracted. Time-frequency domain feature extraction: Time-frequency analysis methods such as wavelet transform are used to perform multi-resolution analysis on the data and extract features within different time scales and frequency ranges.

[0016] In this embodiment, by establishing a state evaluation model, the target state feature data is input into the model for analysis and judgment to determine the state of the network-forming energy storage system. The state evaluation model can be constructed based on machine learning algorithms (such as decision trees, support vector machines, neural networks, etc.) or expert systems. The training data of the model comes from the historical operating data and fault case data of the network-forming energy storage system. Or a preset state library is established to process the target state feature data, and according to the processing results, the corresponding state in the state library is selected.

[0017] S103: Monitor the network-forming energy storage system based on the state of the network-forming energy storage system.

[0018] In this embodiment, the rules in the system state and policy rule library are matched according to different system states to determine the corresponding target policies. For complex system states, a multi-objective optimization algorithm can be used to further optimize the policies.

[0019] For example, when the network-forming energy storage system is in a normal operation state, the target policies mainly focus on regular inspections and preventive maintenance; regularly check and test the equipment, including battery performance detection, sensor calibration, communication line inspection, etc., to promptly discover potential problems and handle them; formulate a reasonable charge and discharge plan based on the operation data and historical records of the system.

[0020] When the network-forming energy storage system is in a warning state, it is necessary to strengthen the monitoring and analysis of the system and promptly take measures to eliminate potential fault hazards. Deeply analyze the reasons for the warning to determine whether it is caused by an abnormal electrical parameter or the combined effect of multiple parameters; increase the monitoring frequency and closely monitor the state changes to ensure that the network-forming energy storage system can return to a normal operation state.

[0021] When the network-forming energy storage system is in a fault state, it is necessary to immediately take emergency treatment measures, quickly cut off the power supply of the faulty part to prevent the fault from expanding; conduct a detailed diagnosis and analysis of the fault to determine the specific location and cause of the fault.

[0022] It can be concluded from the above that the online monitoring method of the network-forming energy storage system provided by the embodiments of the present disclosure obtains comprehensive data by fusing the monitored operation data, which accurately and comprehensively reflects the operation status of the network-forming energy storage system; extracting target state feature data from the comprehensive data can more precisely capture the key information in the system operation, accurately judge the state of the system, and monitor the network-forming energy storage system based on the determined system state, which can make the monitoring more targeted and effective; realizing the precise monitoring of the operation state of the network-forming energy storage system.

[0023] In an embodiment of the present disclosure, the electrical parameters include: current, voltage, and state of charge data; The operation data is fused to obtain comprehensive data, including: based on a preset weight allocation rule, fusing the current, voltage, and state of charge data to obtain comprehensive data.

[0024] In this embodiment, the current data includes the current values of different circuits in the network-forming energy storage system. For example, the charging current and discharging current of the battery pack, as well as the input and output currents of the Power Conversion System (PCS). The voltage data includes the terminal voltage of the battery pack in the network-forming energy storage system, the AC side and DC side voltages of the PCS, etc. The state of charge data represents the percentage of the remaining battery charge to the rated charge and is an important indicator for measuring the available capacity of the energy storage battery.

[0025] In different operating conditions of the network-forming energy storage system, the influence degree of each electrical parameter on the system state will change. Therefore, a weight dynamic adjustment mechanism is established.

[0026] For example, at the initial stage of battery charging, the current data has a greater influence on the system state; while when approaching the full charge state, the importance of voltage and state of charge data relatively increases. By real-time monitoring the operating conditions of the system, the weights of each parameter are dynamically adjusted according to preset rules to ensure the accuracy and effectiveness of data fusion. Based on the preset weight allocation rules, weighted summation operations are performed on the current, voltage, and state of charge data to obtain preliminary fusion data.

[0027] The calculation formula for the fusion data is: R = w 1 i + w 2 v + w 3 s , where R is the preliminary fusion data, I is the current data, V is the voltage data, S is the state of charge data, w 1, w 2, w 3 are respectively the weight reference values of the current data, voltage data, and state of charge data.

[0028] The preliminary fusion data is further optimized to improve the quality and reliability of the data. For example, a filtering algorithm is used to smooth the preliminary fusion data to remove noise and interference; the weight reference values are corrected by introducing other parameters; and the final comprehensive data is obtained, which can more comprehensively and accurately reflect the operating state of the network-forming energy storage system.

[0029] In an embodiment of the present disclosure, the online monitoring method of the network-forming energy storage system further includes: Obtain the temperature data of the network-forming energy storage system, and input the temperature data into a preset influence factor calculation model to obtain a first weight adjustment coefficient; The weight reference value of the current data is corrected according to the first weight adjustment coefficient to obtain the weight base value of the current data; the weight reference value of the voltage data is corrected according to the first weight adjustment coefficient to obtain the weight base value of the voltage data; the weight reference value of the state of charge data is corrected according to the first weight adjustment coefficient to obtain the weight base value of the state of charge data.

[0030] In this embodiment, temperature sensors are arranged at multiple key positions of the grid-forming energy storage system, and the collected temperature data is preliminarily processed, including removing outliers. The preset influence factor calculation model is constructed based on a large amount of historical experimental data and theoretical analysis.

[0031] The influence factor calculation model can adopt various algorithms, such as neural network algorithms (e.g., BP neural network (Back-Propagation Neural Network), RBF neural network (Radial Basis Function Neural Network)), fuzzy logic algorithms, or regression analysis algorithms, etc. Taking the BP neural network as an example, the input layer nodes are the collected temperature data, and the output layer nodes are the first weight adjustment coefficient.

[0032] During the training process, historical temperature data and the corresponding optimal weight adjustment coefficient are used as training samples. By continuously adjusting the weights and thresholds of the neural network, the output of the model is made to be as close as possible to the true weight adjustment coefficient. The preprocessed temperature data is input into the constructed influence factor calculation model, and the first weight adjustment coefficient is calculated and output.

[0033] The first weight adjustment coefficient reflects the degree of influence of temperature on the weights of current, voltage, and state of charge data. For example, when the temperature is high, the performance of the battery will be affected. At this time, the weight of the state of charge data needs to be appropriately increased to more accurately evaluate the state of the battery, while the weights of the current and voltage data need to be adjusted accordingly.

[0034] In this embodiment, the weight reference value of the electrical parameters is corrected according to the calculated first weight adjustment coefficient and the correction formula; The correction formula is: ; Where is the weight base value of the j th data, , is the current data, is the voltage data, is the state of charge data, is the weight reference value of the j th data, is the first weight adjustment coefficient; is the current temperature, is the reference temperature, is the nonlinear influence coefficient.

[0035] The present disclosure introduces a nonlinear function to correct the weight reference value, so that the correction result is more accurate.

[0036] In one embodiment of the present disclosure, the online monitoring method for a grid-type energy storage system further includes: after obtaining the weighted base value of the current data, the weighted base value of the voltage data, and the weighted base value of the state of charge data: Establish a temperature-life decay correlation model to calculate the capacity decay coefficient in different temperature zones in real time; Couple the capacity decay coefficient with the state of charge data to generate a dynamic health factor. When a local temperature anomaly is detected, the thermal imaging detection module is activated to reconstruct the three-dimensional temperature field; The weight base value of the electrical parameter is modified according to the temperature gradient distribution characteristics.

[0037] In this embodiment, a temperature-life decay correlation model is established based on the Arrhenius accelerated aging equation, and real-time temperature data and historical thermal stress distribution are input to calculate the capacity decay coefficient η( T d ), the expression is:

[0038] in, is the battery material constant, is the activation energy, is the Boltzmann constant, T d is the absolute temperature, Equivalent number of cycles at the current temperature.

[0039] Perform time-domain convolution of the capacity decay coefficient with real-time state of charge (SOC) data to generate a dynamic health factor H ( t ):

[0040] in, is the calibration coefficient, is the effective value of current, and Δt is the length of the time window.

[0041] According to the reconstruction results of the three-dimensional temperature field, the spatial weighted method is used to correct the weight base value.

[0042] In this embodiment, according to the temperature gradient distribution characteristics reconstructed from the three-dimensional temperature field, the weight base values of current, voltage, and state of charge data are corrected to form a temperature compensation type data fusion strategy. The temperature gradient distribution characteristics reflect the non-uniformity of the internal temperature of the energy storage system, and the temperature differences in different parts will have different effects on the performance of the battery. For example, if the temperature in a certain area is too high, the internal resistance of the battery in that area may increase, and the charge and discharge efficiency will decrease. At this time, the weight of the temperature data related to this area can be appropriately increased, while adjusting the weights of current, voltage, and state of charge data.

[0043] In an embodiment of the present disclosure, the online monitoring method of the grid-forming energy storage system further includes: after obtaining the weight base values of current data, voltage data, and state of charge data: Calculate the confidence indicators of current, voltage, and state of charge data respectively; Calculate the second weight adjustment coefficient according to the confidence indicator of current data and the sliding time window; calculate the third weight adjustment coefficient according to the confidence indicator of voltage data and the sliding time window; calculate the fourth weight adjustment coefficient according to the confidence indicator of state of charge data and the sliding time window; Correct the weight base value of current data according to the second weight adjustment coefficient to obtain the weight of current; correct the weight base value of voltage data according to the third weight adjustment coefficient to obtain the weight of voltage; correct the weight base value of state of charge data according to the fourth weight adjustment coefficient to obtain the weight of state of charge data.

[0044] In this embodiment, calculate the confidence indicators of each electrical parameter; Voltage confidence indicator

[0045] Wherein, is the variance of the 10ms sliding window of voltage data, is the absolute value ratio of the voltage mutation amount to the mutation time.

[0046] Current confidence indicator

[0047] Wherein, is the initial current, is the filtered current, is the rating of the current.

[0048] SOC confidence indicator

[0049] Calculate the weight adjustment coefficient through the sliding time window (window length τ = 5min): [[ID= , is the second weight adjustment coefficient, is the third weight adjustment coefficient, is the fourth weight adjustment coefficient.

[0050] The final weight calculation formula for each electrical parameter is: ; where, is the weight of the j th data.

[0051] As time goes by and the data is continuously updated, the sliding time window slides continuously, and the second weight adjustment coefficient also changes continuously. Therefore, it is necessary to dynamically adjust the weights of current, voltage, and state of charge data in real time to ensure that during the data fusion process, the weights can be reasonably allocated according to the confidence of the data, improving the accuracy and reliability of the comprehensive data, and thus more accurately reflecting the operating state of the network-forming energy storage system.

[0052] In an embodiment of the present disclosure, determining the state of the network-forming energy storage system based on the comprehensive data includes: Calculating the target similarity between the target state feature data and each state in the state library; Determining the state of the network-forming energy storage system based on the target similarity.

[0053] In this embodiment, the comprehensive data is first subjected to smoothing processing and normalization operations to eliminate the noise and random fluctuations in the data, and eliminate the differences in dimension and numerical range among different electrical parameter data.

[0054] Apply a variety of feature extraction algorithms to extract the target state feature data from the normalized comprehensive data.

[0055] Time-domain feature extraction: Calculate time-domain features such as the mean, variance, standard deviation, peak value, and valley value of the data.

[0056] Frequency-domain feature extraction: Convert the time-domain data to the frequency domain through fast Fourier transform, and extract frequency-domain features such as the main frequency components and frequency amplitudes in the spectrum.

[0057] Time-frequency domain feature extraction: Use time-frequency analysis methods such as wavelet transform to perform multi-resolution analysis on the data and extract features in different time scales and frequency ranges.

[0058] Collect historical data of the grid-forming energy storage system in different operating states, including various states such as normal operation, minor faults, and severe faults. Perform the same preprocessing and feature extraction operations on these historical data as the above comprehensive data to obtain a set of feature data corresponding to each state, and construct a state library. Each state in the state library has its unique feature vector representation, and these feature vectors serve as the reference standard for subsequent similarity calculations.

[0059] Adopt a suitable similarity calculation method to calculate the target similarity between the target state feature data and each state in the state library. For example: Calculate the Euclidean distance between the target state feature data vector and each state feature vector in the state library. The smaller the distance, the more similar the two vectors are, that is, the closer the target state is to the state in the state library.

[0060] Calculate the cosine similarity between the target state feature data vector and each state feature vector in the state library. The cosine similarity measures the similarity between two vectors by calculating the cosine value of the angle between them.

[0061] If the similarity between the target state feature data and a certain state in the state library meets the set threshold condition, and this similarity is significantly higher than the similarities of other states, then determine this state as the current state of the grid-forming energy storage system.

[0062] When a single similarity judgment cannot clearly determine the system state, comprehensively consider multiple similarity metrics such as Euclidean distance and cosine similarity. For example, different weights can be assigned to different similarity metrics, calculate the comprehensive similarity score, and determine the current state of the system according to the state with the highest score.

[0063] In an embodiment of the present disclosure, determining the state of the grid-forming energy storage system based on the target state feature data includes: Fuse the environmental data around the grid-forming energy storage system and the target state feature data to obtain the target state data; Input the target state data into the state monitoring model to determine the state of the grid-forming energy storage system; wherein, the state monitoring model is trained based on the historical target state data of the grid-forming energy storage system.

[0064] In this embodiment, collect the environmental data around the grid-forming energy storage system, and the types of environmental data include but are not limited to temperature, humidity, air pressure, light intensity, wind speed, etc. These environmental factors will have a significant impact on the performance and operating state of the energy storage system.

[0065] For example, a high-humidity environment may trigger insulation failures in electrical equipment. The original environmental data collected is preprocessed, including data cleaning and data calibration. A data fusion method is used to fuse the preprocessed environmental data with the target state feature data to generate more comprehensive and accurate target state data. The data fusion methods include the weighted average method, the principal component analysis method, the neural network fusion method, etc.

[0066] A state monitoring model is constructed, and the fused target state data is input into this model to determine the state of the network-forming energy storage system. The state monitoring model can be constructed based on machine learning algorithms (such as decision trees, support vector machines, random forests, deep learning models, etc.) or expert systems. The state evaluation model is trained using the target state data of the historical network-forming energy storage system and the corresponding actual state labels. For example, for a deep learning model, a large amount of historical data is used for training, and by continuously adjusting the parameters of the model, the model can accurately predict the state of the energy storage system according to the target state data.

[0067] Environmental factors are constantly changing, and their impact on the state of the energy storage system also changes over time. For example, during different time periods of a day, the light intensity and temperature change significantly, and these changes affect the charge and discharge efficiency and performance of the battery. By monitoring and analyzing the dynamic changes of environmental factors in real time, the state of the energy storage system can be evaluated more accurately.

[0068] In an embodiment of the present disclosure, monitoring the network-forming energy storage system based on the state of the network-forming energy storage system includes: Determine the corresponding level identifier according to the state of the network-forming energy storage system, and match the level identifier with the policy trigger conditions in the preset policy rule library to obtain the target policy. There are various policies stored in the policy rule library.

[0069] In this embodiment, a detailed state grading standard is formulated according to the different operating states of the network-forming energy storage system. This standard comprehensively considers various factors such as the safety of the system, performance indicators, and severity of faults. For example, the system state is divided into a normal operating state (Level I), a minor anomaly warning state (Level II), a moderate fault state (Level III), and a severe fault state (Level IV). The minor anomaly warning state means that some parameters of the system have shown minor fluctuations or deviated from the normal range, but have not significantly affected the normal operation of the system. The moderate fault state means that the system has encountered a certain degree of fault, and some functions may be affected, but the basic operation can still be maintained. The severe fault state indicates that the system has encountered a serious fault, which may cause the system to be unable to work properly and even pose a safety hazard.

[0070] There are various policies stored in the policy rule library. Each policy corresponds to a specific status level and triggering condition, and also includes a detailed policy description and execution steps. Match the level identifier with the policy triggering conditions in the preset policy rule library to find the policy that matches the current system status level identifier.

[0071] When the level identifier matches multiple policies in the preset policy rule library, sort the multiple policies according to the preset priority ranking in the policy rule library to obtain the first sorted list, and determine the target policy based on the first sorted list.

[0072] Specifically, for example, if the system status is identified as level III, there may be multiple policies in the policy rule library whose triggering conditions match the level III status, and these policies will be used as candidate target policies.

[0073] Sort the multiple candidate target policies according to the preset priority ranking in the policy rule library to generate the first sorted list. The sorting process is strictly carried out according to the priority ranking rules to ensure that the policies in the list are arranged from high to low in priority. For example, if three candidate target policies A, B, and C are matched, according to the priority ranking rules, candidate target policy A is the most critical for ensuring system security, candidate target policy B can quickly restore part of the system performance, and candidate target policy C has a lower maintenance cost but relatively less improvement in system performance, then the order of the first sorted list is A, B, C; select the policy with the highest priority in the list as the target policy.

[0074] The present disclosure realizes the automatic generation of monitoring policies by matching the status of the network-forming energy storage system with the preset policy rule library. There is no need to manually analyze data item by item or formulate plans, reducing the subjectivity and delay of human judgment, significantly improving the operation and maintenance efficiency. It also enhances the reliability and security of the network-forming energy storage system.

[0075] Corresponding to the online monitoring method of the network-forming energy storage system in the above embodiment, Figure 2 This is a structural block diagram of the online monitoring system of the network-forming energy storage system provided by an embodiment of the present disclosure. For the sake of convenience of description, only the parts related to the embodiments of the present disclosure are shown. Refer to Figure 2 The online monitoring system 20 of the network-forming energy storage system includes: a data processing module 21, a status determination module 22, and a monitoring module 23; where The data processing module 21 is used to fuse the operation data of the network-forming energy storage system to obtain comprehensive data, and the operation data is the data obtained by different monitoring devices monitoring multiple electrical parameters of the network-forming energy storage system; The status determination module 22 is used to extract the feature of the comprehensive data to obtain the target status feature data, and determine the status of the network-forming energy storage system based on the target status feature data; The monitoring module 23 is used to monitor the grid-forming energy storage system based on the state of the grid-forming energy storage system.

[0076] In one embodiment of the present disclosure, the data processing module 21 is specifically configured to: Fuse the operation data of the grid-forming energy storage system to obtain comprehensive data, including: Based on a preset weight allocation rule, perform data fusion on current, voltage, and state of charge data to obtain comprehensive data.

[0077] In one embodiment of the present disclosure, the data processing module 21 is specifically configured to: Obtain the temperature data of the grid-forming energy storage system, input the temperature data into a preset influence factor calculation model, and obtain a first weight adjustment coefficient; According to the first weight adjustment coefficient, correct the weight reference value of the current to obtain the weight base value of the current; according to the first weight adjustment coefficient, correct the weight reference value of the voltage to obtain the weight base value of the voltage; according to the first weight adjustment coefficient, correct the weight reference value of the state of charge data to obtain the weight base value of the state of charge data.

[0078] In one embodiment of the present disclosure, the data processing module 21 is specifically configured to: Correct the weight reference value of the electrical parameter based on the correction formula; The correction formula is: ; Wherein, is the weight base value of the j th data, , is the current data, is the voltage data, is the state of charge data, is the weight reference value of the j th data, is the first weight adjustment coefficient; is the current temperature, is the reference temperature, is the non-linear influence coefficient.

[0079] In one embodiment of the present disclosure, the data processing module 21 is specifically configured to: Calculate the confidence index of the current, voltage, and state of charge data respectively; Calculate a second weight adjustment coefficient based on the confidence index of the current data and the sliding time window; calculate a third weight adjustment coefficient based on the confidence index of the voltage data and the sliding time window; calculate a fourth weight adjustment coefficient based on the confidence index of the state of charge data and the sliding time window; Modify the weight base value of the current data according to the second weight adjustment coefficient to obtain the weight of the current; modify the weight base value of the voltage data according to the third weight adjustment coefficient to obtain the weight of the voltage; modify the weight base value of the state of charge data according to the fourth weight adjustment coefficient to obtain the weight of the state of charge data.

[0080] In an embodiment of the present disclosure, the state determination module 22 is specifically configured to: Calculate the target similarity between the target state feature data and each state in the state library; Sort the multiple target similarities, and determine the state of the network-forming energy storage system according to the sorting result.

[0081] In an embodiment of the present disclosure, the state determination module 22 is specifically configured to: Fuse the environmental data around the network-forming energy storage system and the target state feature data to obtain the target state data; Input the target state data into the state monitoring model to determine the state of the network-forming energy storage system; wherein, the state monitoring model is trained based on the historical target state data of the network-forming energy storage system.

[0082] In an embodiment of the present disclosure, the monitoring module 23 is specifically configured to: Determine the corresponding level identifier according to the state of the network-forming energy storage system, and match the level identifier with the policy trigger conditions in the preset policy rule library to obtain the target policy, and multiple policies are stored in the policy rule library; Monitor the network-forming energy storage system based on the target policy.

[0083] In an embodiment of the present disclosure, the monitoring module 23 is specifically configured to: When the level identifier matches multiple policies in the preset policy rule library, sort the multiple policies according to the preset priority sorting in the policy rule library to obtain the first sorted list, and determine the target policy based on the first sorted list.

[0084] The online monitoring system of the network-forming energy storage system provided by the embodiments of the present disclosure improves the comprehensiveness and accuracy of state evaluation through multi-source data fusion and dynamic weight adjustment, realizes the accurate evaluation of the operating state of the network-forming energy storage system, and improves the accuracy of the operation monitoring of the network-forming energy storage system; it can automatically match the monitoring policy according to the real-time state.

[0085] See Figure 3 , Figure 3 which is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. As Figure 3The electronic device 300 in the present embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The above-mentioned processors 301, input devices 302, output devices 303, and memories 304 communicate with each other through a communication bus 305. The memory 304 is used to store a computer program, and the computer program includes program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. Among them, the processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above device embodiments, for example Figure 2 the functions of the data processing module 21, the status determination module 22, and the monitoring module 23 shown.

[0086] It should be understood that in the embodiments of the present disclosure, the so-called processor 301 may be a central processing unit (CPU), and this processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0087] The input device 302 may include a touchpad, a fingerprint acquisition sensor (for acquiring the fingerprint information and the direction information of the fingerprint of the user), a microphone, etc., and the output device 303 may include a display (such as an LCD), a speaker, etc.

[0088] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A part of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0089] In specific implementation, the processors 301, input devices 302, and output devices 303 described in the embodiments of the present disclosure may execute the implementation manners described in the first and second embodiments of the online monitoring method of the grid-connected energy storage system provided by the embodiments of the present disclosure, and may also execute the implementation manner of the electronic device described in the embodiments of the present disclosure, which will not be elaborated here.

[0090] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, all or part of the processes in the method of the foregoing embodiment are implemented. It can also be completed by instructing related hardware through the computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the foregoing method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0091] The computer-readable storage medium can be the internal storage unit of the electronic device in any of the foregoing embodiments, such as the hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. Further, the computer-readable storage medium can also include both the internal storage unit and the external storage device of the electronic device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store the data that has been output or will be output.

[0092] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to functions in the foregoing description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0093] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described electronic devices and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0094] In several embodiments provided by the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection between each other can be an indirect coupling or communication connection through some interfaces or units, or can also be an electrical, mechanical or other form of connection.

[0095] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can also be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present disclosure.

[0096] In addition, in each embodiment of the present disclosure, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0097] The above is only the specific implementation manner of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. An online monitoring method for a network-forming energy storage system, characterized in that, Including: Fusing the operation data of the network-forming energy storage system to obtain comprehensive data, where the operation data is data obtained by different monitoring devices monitoring multiple electrical parameters of the network-forming energy storage system; Performing feature extraction on the comprehensive data to obtain target state feature data, and determining the state of the network-forming energy storage system based on the target state feature data; Monitoring the network-forming energy storage system based on the state of the network-forming energy storage system.

2. The online monitoring method of the network-forming energy storage system according to claim 1, characterized in that, The multiple electrical parameters include current, voltage, and state of charge data; The fusing the operation data of the network-forming energy storage system to obtain comprehensive data includes: Based on a preset weight allocation rule, performing data fusion on current, voltage, and state of charge data to obtain comprehensive data.

3. The online monitoring method of the network-forming energy storage system according to claim 2, characterized in that, Also including: Obtaining the temperature data of the network-forming energy storage system, and inputting the temperature data into a preset influence factor calculation model to obtain a first weight adjustment coefficient; Correcting the weight reference value of the current data according to the first weight adjustment coefficient to obtain the weight base value of the current data; correcting the weight reference value of the voltage data according to the first weight adjustment coefficient to obtain the weight base value of the voltage data; Correcting the weight reference value of the state of charge data according to the first weight adjustment coefficient to obtain the weight base value of the state of charge data.

4. The online monitoring method of the network-forming energy storage system according to claim 3, characterized in that, Also including: Correcting the weight reference value of the electrical parameter based on a correction formula; The correction formula is: ； Among them, is the weight base value of the j th data, , is the current data, is the voltage data, is the state of charge data, is the weight reference value of the j th data, is the first weight adjustment coefficient; is the current temperature, is the reference temperature, is the non-linear influence coefficient.

5. The online monitoring method of the network-forming energy storage system according to claim 3, characterized in that, Also including: Calculating the confidence index of current, voltage, and state of charge data respectively; Calculating a second weight adjustment coefficient according to the confidence index of the current data and a sliding time window; Calculating a third weight adjustment coefficient according to the confidence index of the voltage data and a sliding time window; calculating a fourth weight adjustment coefficient according to the confidence index of the state of charge data and a sliding time window; Correcting the weight base value of the current data according to the second weight adjustment coefficient to obtain the weight of the current; Correcting the weight base value of the voltage data according to the third weight adjustment coefficient to obtain the weight of the voltage; Correcting the weight base value of the state of charge data according to the fourth weight adjustment coefficient to obtain the weight of the state of charge data.

6. The online monitoring method of the network-forming energy storage system according to claim 1, characterized in that, The determining the state of the network-forming energy storage system based on the target state feature data includes: Calculating the target similarity between the target state feature data and each state in the state library; Sorting multiple target similarities, and determining the state of the network-forming energy storage system according to the sorting result.

7. The on-line monitoring method of the network-forming energy storage system according to claim 1, characterized in that, The determining the state of the network-forming energy storage system based on the target state feature data includes: Fusing the environmental data around the network-forming energy storage system and the target state feature data to obtain target state data; Inputting the target state data into a state monitoring model to determine the state of the network-forming energy storage system; where the state monitoring model is trained based on historical target state data of the network-forming energy storage system.

8. The online monitoring method of the network-forming energy storage system according to claim 1, characterized in that Monitoring the network-forming energy storage system based on the state of the network-forming energy storage system includes: Determine the corresponding level identifier according to the state of the network-forming energy storage system, and match the level identifier with the policy trigger conditions in the preset policy rule library to obtain the target policy. Multiple policies are stored in the policy rule library. Monitor the network-forming energy storage system based on the target policy.

9. The online monitoring method of the network-forming energy storage system according to claim 8, characterized in that, The matching of the level identifier with the policy trigger conditions in the preset policy rule library to obtain the target policy includes: When the level identifier matches multiple policies in the preset policy rule library, sort the multiple policies according to the preset priority order in the policy rule library to obtain the first sorted list, and determine the target policy based on the first sorted list.

10. An online monitoring system for a network-forming energy storage system, characterized in that, Includes: A data processing module for fusing the operation data of the network-forming energy storage system to obtain comprehensive data. The operation data is the data obtained by different monitoring devices monitoring multiple electrical parameters of the network-forming energy storage system. A state determination module for extracting features from the comprehensive data to obtain target state feature data, and determining the state of the network-forming energy storage system based on the target state feature data. A monitoring module for monitoring the network-forming energy storage system based on the state of the network-forming energy storage system.

Images