Energy storage system state monitoring method, system and related device

Abstract

The invention discloses an energy storage system state monitoring method and system and a related device, and belongs to the technical field of battery safety. Performing prediction residual analysis on the energy storage system monitoring related data to obtain an average value and a standard deviation of the energy storage system monitoring related data; calculating a residual error mean value and a residual error standard deviation according to the mean value and the standard deviation of the monitoring related data of each energy storage system so as to set a multi-level warning threshold value; and performing hierarchical warning according to the multi-level warning threshold values to complete state monitoring of the energy storage system. According to the method, by formulating a unified multi-level warning threshold and a response process, standardization and normalization of operation and maintenance work of the energy storage system are promoted, the operation and maintenance efficiency and quality are improved, the risk of human errors is reduced, it is ensured that enough resources are provided for handling in emergency situations, meanwhile, resource waste in non-emergency situations is avoided, and the economic benefit is improved. The bottleneck and low-efficiency links in the energy storage system are identified through residual analysis, the charging and discharging strategy is optimized, and the power supply reliability and stability are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of battery safety, and in particular relates to a method, system and related devices for monitoring the state of an energy storage system. Background Art

[0002] As the core technology and basic equipment for building a new power system and promoting the green and low-carbon transformation of energy, the importance of new energy storage is self-evident. With the continuous increase in the proportion of new energy power generation, new energy storage technology has ushered in unprecedented development opportunities, but it also faces severe safety challenges.

[0003] So far, there have been many fire accidents in energy storage systems around the world. These accidents not only caused huge economic losses, but also posed a serious threat to people's lives and safety. In-depth analysis of the causes of these accidents shows that in addition to the safety issues of the energy storage batteries themselves, the lack of effective safety protection measures and monitoring platforms is also an important reason for the frequent accidents.

[0004] The inherent safety issues of energy storage batteries cannot be ignored, but more importantly, a complete safety protection system needs to be established. This includes advanced monitoring technology, early warning systems, and emergency response mechanisms. By monitoring the operating status of the energy storage system in real time, potential safety hazards can be discovered and handled in a timely manner, effectively avoiding accidents.

[0005] Therefore, accelerating the research and development of energy storage safety technology and improving energy storage safety monitoring methods have become urgent tasks for the energy storage industry. At the same time, strengthening safety risk prevention awareness and improving the safety quality of practitioners are also important guarantees for ensuring the safe operation of energy storage systems. Summary of the invention

[0006] The purpose of the present invention is to provide a method, system and related devices for monitoring the state of an energy storage system in order to solve the problems in the prior art and establish a complete and comprehensive monitoring system to avoid frequent safety accidents of the energy storage system.

[0007] In order to achieve the above object, the present invention has the following technical solutions:

[0008] A method for monitoring the state of an energy storage system, comprising:

[0009] Obtain relevant data on energy storage system monitoring;

[0010] Perform prediction residual analysis on the energy storage system monitoring related data to obtain the average value and standard deviation of each energy storage system monitoring related data;

[0011] Calculate the residual mean and residual standard deviation based on the average and standard deviation of the monitoring data of each energy storage system to set multi-level warning thresholds;

[0012] Perform hierarchical warnings based on multi-level warning thresholds to complete the state monitoring of the energy storage system.

[0013] As a preferred solution, the relevant data monitored by the energy storage system includes:

[0014] Any one or more of the single battery voltage, single battery temperature, battery module voltage, battery module temperature, battery cluster voltage, battery cluster temperature, remaining capacity of the single battery, and concentration of volatile organic compound (VOC) in the battery compartment.

[0015] As a preferred solution, the step of performing predictive residual analysis on the relevant data monitored by the energy storage system to obtain the average value and standard deviation of each relevant data monitored by the energy storage system is calculated according to the following expression:

[0016]

[0017] In the formula, is the average value of each relevant data monitored by the energy storage system; S is the standard deviation of each relevant data monitored by the energy storage system; N is the number of each relevant data monitored by the energy storage system; is the predicted value; y is the actual value; e t is the difference between the predicted value and the actual value at the corresponding moment in the sliding window method.

[0018] As a preferred solution, the step of calculating the mean residual and standard deviation of the residual according to the average value and standard deviation of each relevant data monitored by the energy storage system to set the multi-level warning threshold is calculated according to the following expression for the multi-level warning threshold:

[0019]

[0020]

[0021] In the formula, is the maximum value of the average value of each relevant data monitored by the energy storage system; S max is the maximum value of the standard deviation of each relevant data monitored by the energy storage system; X P is the upper or lower limit of the first-level warning of the mean residual; S P is the upper limit of the first-level warning of the standard deviation of the residual; X S is the upper or lower limit of the second-level warning of the mean residual; S S is the upper limit of the second-level warning of the standard deviation of the residual.

[0022] As a preferred solution, the step of performing hierarchical warnings according to the multi-level warning thresholds includes:

[0023] The first-level warning rule is set as follows:

[0024]

[0025] The secondary warning rule is set as follows:

[0026]

[0027] Wherein, X R is the average value of the residuals of the monitoring-related data of each energy storage system, and S R is the standard deviation of the residuals of the monitoring-related data of each energy storage system;

[0028] When X R or S R exceeds the set warning threshold, multi-level warning is executed.

[0029] As a preferred solution, in the step of performing hierarchical warning according to the multi-level warning threshold to complete the state monitoring of the energy storage system:

[0030] When a primary warning occurs, indicating that the battery has a primary risk, after checking and finding no abnormalities, continue to operate;

[0031] When a secondary warning occurs, indicating that the battery has a secondary risk, stop the battery charging and discharging, and perform maintenance;

[0032] The severity of the secondary risk is higher than that of the primary risk.

[0033] Second, a state monitoring system for an energy storage system is provided, including:

[0034] A monitoring data acquisition module for acquiring monitoring-related data of the energy storage system;

[0035] A prediction residual analysis module for performing prediction residual analysis on the monitoring-related data of the energy storage system to obtain the average value and standard deviation of the monitoring-related data of each energy storage system;

[0036] A multi-level warning threshold setting module for calculating the residual mean value and residual standard deviation according to the average value and standard deviation of the monitoring-related data of each energy storage system to set the multi-level warning threshold;

[0037] A hierarchical warning module for performing hierarchical warning according to the multi-level warning threshold to complete the state monitoring of the energy storage system.

[0038] As a preferred solution, the monitoring-related data of the energy storage system acquired by the monitoring data acquisition module includes:

[0039] Any one or more of the single-cell voltage of the battery, the single-cell temperature of the battery, the module voltage of the battery, the module temperature of the battery, the cluster voltage of the battery, the cluster temperature of the battery, the remaining capacity of the single-cell of the battery, and the concentration of volatile organic compound VOC in the battery compartment.

[0040] As a preferred solution, the prediction residual analysis module calculates the mean value and standard deviation of the monitoring-related data of each energy storage system according to the following expression:

[0041]

[0042] In the formula, is the mean value of the monitoring-related data of each energy storage system; S is the standard deviation of the monitoring-related data of each energy storage system; N is the number of the monitoring-related data of each energy storage system; is the predicted value; y is the actual value; e t is the difference between the predicted value and the actual value at the corresponding moment in the sliding window method.

[0043] As a preferred solution, the multi-level warning threshold setting module calculates the multi-level warning threshold according to the following expression:

[0044]

[0045] In the formula, is the maximum value of the mean values of the monitoring-related data of each energy storage system; S max is the maximum value of the standard deviations of the monitoring-related data of each energy storage system; X P is the upper or lower limit of the first-level warning of the residual mean value; S P is the upper limit of the first-level warning of the residual standard deviation; X S is the upper or lower limit of the second-level warning of the residual mean value; S S is the upper limit of the second-level warning of the residual standard deviation.

[0046] As a preferred solution, the hierarchical warning module sets the first-level warning rule according to the following relational expression:

[0047]

[0048] Sets the second-level warning rule according to the following relational expression:

[0049]

[0050] In the formula, X R is the mean value of the residuals of the monitoring-related data of each monitored energy storage system, and S R is the standard deviation of the residuals of the monitoring-related data of each monitored energy storage system;

[0051] When X R or S R exceeds the set warning threshold, multi-level warnings are executed.

[0052] As a preferred solution, when the hierarchical warning module performs hierarchical warnings according to the multi-level warning threshold and completes the state monitoring of the energy storage system:

[0053] When a first-level warning appears, it indicates that the battery has a first-level risk. After checking and finding no abnormalities, continue to operate;

[0054] When a second-level warning appears, it indicates that the battery has a second-level risk. Stop the charging and discharging of the battery and perform maintenance;

[0055] The severity of the second-level risk is higher than that of the first-level risk.

[0056] In a third aspect, an electronic device is provided, including a processor and a memory. The processor is configured to execute a computer program stored in the memory to implement the energy storage system state monitoring method described above.

[0057] In a fourth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the energy storage system state monitoring method described above is implemented.

[0058] Compared with the prior art, the first aspect of the present invention has at least the following beneficial effects:

[0059] By performing predictive residual analysis on the data related to the monitoring of the energy storage system, obtaining the average value and standard deviation of each data related to the monitoring of the energy storage system, and calculating the residual mean and residual standard deviation based on the average value and standard deviation of each data related to the monitoring of the energy storage system to set multi-level warning thresholds, and performing hierarchical warnings according to the multi-level warning thresholds, the severity of the problem can be quickly identified, thereby triggering corresponding response measures. This helps the operation and maintenance personnel quickly locate and take actions, reduce the fault handling time, and improve the reliability and stability of the overall system. Different warning levels correspond to different levels of urgency and resource requirements. Through hierarchical warnings, operation and maintenance resources can be reasonably allocated to ensure that there are sufficient resources to respond in case of emergencies, while avoiding wasting resources in non-emergency situations. Hierarchical warnings provide clear and quantitative information about the state of the energy storage battery, which helps decision-makers make more informed decisions. For example, when deciding whether to upgrade equipment, adjust operation and maintenance strategies, or perform preventive maintenance, hierarchical warnings can be used as an important reference. For users relying on the energy storage system for power supply, hierarchical warnings can reduce the power outage time caused by faults and improve the power supply reliability and stability. By formulating unified multi-level warning thresholds and response processes, the standardization and regularization of the operation and maintenance work of the energy storage system can be promoted. This helps improve the operation and maintenance efficiency and quality and reduce the risk of human errors. Residual analysis can help identify bottlenecks and inefficient links in the energy storage system, optimize the charging and discharging strategies. By performing predictive residual analysis on the data related to the monitoring of the energy storage system and completing the multi-parameter comprehensive analysis of the energy storage system state monitoring accordingly, it can significantly improve the efficiency of the energy storage system, optimize resource allocation, predict energy demand, achieve risk early warning, assist in decision-making, and reduce operating costs and other benefits.

[0060] It can be understood that the beneficial effects of the second to fourth aspects described above can be referred to the relevant descriptions in the first aspect, and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0062] Figure 1 Flow chart of the energy storage system state monitoring method in the embodiment of the present invention;

[0063] Figure 2 Block diagram of the energy storage system state monitoring system in the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] In the following description, specific details such as specific system structures and technologies are proposed for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should understand that the present application 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 application.

[0065] Please refer to Figure 1 , an energy storage system state monitoring method is proposed in the embodiment of the present invention, which can comprehensively reflect the working state of the energy storage system and timely detect abnormalities, so as to take measures for processing in time, including the following steps:

[0066] S1. Obtain the data related to the energy storage system monitoring;

[0067] S2. Conduct predictive residual analysis on the data related to the energy storage system monitoring, and obtain the average value and standard deviation of each data related to the energy storage system monitoring;

[0068] S3. Calculate the residual mean value and residual standard deviation according to the average value and standard deviation of each data related to the energy storage system monitoring, so as to set multi-level warning thresholds;

[0069] S4. Conduct hierarchical warnings according to the multi-level warning thresholds to complete the energy storage system state monitoring.

[0070] In a possible implementation, the relevant data monitored by the energy storage system includes the voltage of each battery cell, the temperature of each battery cell, the voltage of each battery module, the temperature of each battery module, the voltage of each battery cluster, the temperature of each battery cluster, the remaining capacity of each battery cell, and the concentration of VOC (Volatile Organic Compounds) in the battery compartment, etc. The VOC concentration in the battery compartment is a key environmental parameter, which is of great significance for evaluating the air quality in the battery compartment, ensuring battery safety, and preventing potential risks. By monitoring the VOC concentration in the battery compartment, potential safety hazards such as battery leakage can be detected in a timely manner to ensure the safe operation of the battery.

[0071] In a possible implementation, the step S2 of performing predictive residual analysis on the relevant data monitored by the energy storage system to obtain the average value and standard deviation of each relevant data monitored by the energy storage system is calculated according to the following expression:

[0072]

[0073] In the formula, is the average value of each relevant data monitored by the energy storage system; S is the standard deviation of each relevant data monitored by the energy storage system; N is the number of each relevant data monitored by the energy storage system; is the predicted value; y is the actual value; e t is the difference between the predicted value and the actual value at the corresponding moment in the sliding window method.

[0074] The sliding window method adapts to different problem requirements by adjusting the start and end positions of the window. The implementation of the sliding window mainly relies on double pointers or iterators to identify the current processed subsequence (window). In the processing of arrays or strings, the window moves step by step, and corresponding operations (such as calculating the maximum value, minimum value, or other aggregation functions) are performed at each position.

[0075] According to whether the window size is fixed, the sliding window can be divided into a fixed window and a variable window. A fixed window means that the window size remains unchanged and is suitable for problems that need to process subsequences or substrings of a fixed length. A variable window means that the window size is adjusted according to specific conditions and is suitable for problems that need to dynamically change the window size to adapt to different data changes.

[0076] The characteristics of the sliding window method lie in its high efficiency and flexibility. By reducing the nested depth of loops, the sliding window method can reduce the time complexity of the algorithm. At the same time, it allows dynamic adjustment of the window size to adapt to different data changes and problem requirements. The basic steps of the sliding window algorithm usually include:

[0077] Initializing the window: Use two pointers (such as left and right) to represent the boundaries of the window. Initially, the window can be empty, or contain one or more elements.

[0078] Moving window: According to the specific problem requirements, move the left boundary of the window to the right (shrink the window) or the right boundary to the right (expand the window).

[0079] Update result: Each time the window is moved, update the result to be calculated based on the new elements and / or removed elements in the window.

[0080] The implementation method may vary according to different specific problems. For example, when solving the problem of the longest substring without repeating characters, a hash table can be used to record the number of occurrences of characters, and a window without repeating characters can be maintained by moving the left and right pointers.

[0081] In a possible implementation manner, step S3 calculates the residual mean and residual standard deviation according to the average value and standard deviation of the monitoring-related data of each energy storage system to set the multi-level warning threshold, and calculates the multi-level warning threshold according to the following expression:

[0082]

[0083] In the formula, is the maximum value of the average value of the monitoring-related data of each energy storage system; S max is the maximum value of the standard deviation of the monitoring-related data of each energy storage system; X P is the upper or lower limit of the first-level warning of the residual mean; S P is the upper limit of the first-level warning of the residual standard deviation; X S is the upper or lower limit of the second-level warning of the residual mean; S S is the upper limit of the second-level warning of the residual standard deviation.

[0084] In the maximum value of the average value of the monitoring-related data of each energy storage system max and the maximum value S of the standard deviation of the monitoring-related data of each energy storage system, first calculate the data average value of each item of parameter and then select the maximum value. There is a standardized calculation process in the sliding window method.

[0085] 1. Initialize the window and statistics:

[0086] 1.1 Set the window size N;

[0087] 1.2 Initialize a data structure (such as a queue or an array) to store the data points within the current window;

[0088] 1.3 Initialize variables to store the average value (mean) and the sum of variances (sum_of_squares, used for subsequent calculation of the standard deviation) of the current window;

[0089] 1.4 Initialize variables to track the maximum average and maximum standard deviation encountered so far.

[0090] 2. Update the window when data arrives:

[0091] When a new data point arrives, check if the window is full.

[0092] If the window is not full, add the new data point to the window and update the mean and sum_of_squares (extra calculations may be required to maintain the efficiency of updating these statistics).

[0093] If the window is full, remove the oldest data point from the window (usually the head of the queue), add the new data point, and recalculate the mean and sum_of_squares.

[0094] For efficient calculation, Welford's online algorithm can be used to update the mean and variance instead of recalculating the average and variance of the entire window each time.

[0095] Furthermore, Welford's online algorithm is a method for recursively calculating the sample mean and variance (or standard deviation). Welford's online algorithm is particularly suitable for data streams or scenarios where statistics need to be updated in real time, as it can calculate the statistics of all samples step by step without storing all samples.

[0096] Mean update:

[0097] Assume the mean of the first n samples is xn ˉ .

[0098] When the (n + 1)-th sample xn+1 arrives, the updated mean xn+1 ˉ can be calculated by the following formula:

[0099] xn+1 - = xn - + (xn+1 - xn - ) / (n + 1)

[0100] This formula means that the new mean is the sum of the old mean and the difference between the new sample value and the old mean divided by (the number of samples + 1).

[0101] Variance update:

[0102] Assume the variance of the first n samples is σn2 (note that here the variance is calculated based on samples, so the denominator is n - 1, but in the Welford algorithm, a quantity related to the variance is actually maintained and then converted at the end).

[0103] When the (n + 1)-th sample \(x_{n+1}\) arrives, instead of directly calculating the new variance, the variance is updated through an intermediate quantity \(M_{2,n+1}\). \(M_{2,n+1}\) represents the sum of squared differences of the first \(n + 1\) samples (or called "corrected sum of squares").

[0104] The update formula is: \(M_{2,n+1}=M_{2,n}+(x_{n + 1}-\overline{x}_{n}\) ˉ \()(x_{n + 1}-\overline{x}_{n+1}\) ˉ )

[0105] where \(\overline{x}_{n+1}\) ˉ is the updated mean, and \(M_{2,n}\) is the sum of squared differences of the first \(n\) samples.

[0106] Note that the formula here is slightly different from the formula for directly calculating the variance, but it allows for the incremental update of the variance without storing all the samples.

[0107] Finally, when the variance is needed, it can be approximated by \(M_{2,n} / n\) (for sample variance, it should be \(M_{2,n} / (n - 1)\), but the Welford's algorithm is usually used for streaming data, so the difference between \(n - 1\) and \(n\) is negligible for large datasets). (Note that this is an approximation because in streaming processing, usually not all historical data is stored to calculate the sample variance exactly, but this method is used as an estimate). However, in practical applications, for the sake of consistency, \(M_{2,n} / n\) may continue to be used as an estimate of the variance, especially when the data arrives continuously and the statistics within the current window are of concern).

[0108] 3. Calculate the standard deviation:

[0109] 3.1 Calculate the variance using the sum_of_squares, the window size \(N\), and the current mean (variance = sum_of_squares / \(N\)-mean²).

[0110] 3.2 Take the square root of the variance to get the standard deviation (standard deviation = sqrt(variance)).

[0111] 4. Update the maximum statistic:

[0112] Compare the mean of the current window with the maximum mean so far. If it is larger, update the maximum mean.

[0113] Compare the standard deviation of the current window with the maximum standard deviation so far. If it is larger, update the maximum standard deviation.

[0114] Repeat steps 2 - 4 for each newly arrived data point: until all data is processed.

[0115] 5. Output result:

[0116] After processing all the data, output the maximum average value and the maximum standard deviation encountered so far.

[0117] In a possible implementation manner, the step of performing hierarchical warning according to the multi-level warning threshold in step S4 includes:

[0118] The first-level warning rule is set as follows:

[0119]

[0120] The second-level warning rule is set as follows:

[0121]

[0122] In the formula, X R is the average value of the residuals of the monitoring-related data of each energy storage system monitored, and S R is the standard deviation of the residuals of the monitoring-related data of each energy storage system monitored;

[0123] When X R or S R exceeds the set warning threshold, perform multi-level warning.

[0124] Furthermore, the first-level warning indicates that the battery has a first-level risk. After checking and finding no abnormalities, continue to operate;

[0125] The second-level warning indicates that the battery has a second-level risk. Stop the battery charging and discharging, take strengthening measures to ensure safety, and perform regular maintenance on the battery according to the requirements of the maintenance regulations; after the rectification is completed, conduct acceptance approval and then put it into operation;

[0126] The third-level warning indicates that the battery has a third-level risk. Stop the operation of the power station to prevent the spread of thermal runaway; if the thermal runaway cannot be controlled, trigger the alarm system for safety protection;

[0127] Among them, the severity of the first-level risk, the second-level risk, and the third-level risk increases in sequence.

[0128] The energy storage system state monitoring method proposed in the embodiment of the present invention performs hierarchical warning according to the multi-level warning threshold, can quickly identify the severity of the problem, and thus trigger corresponding response measures at different levels. This helps the operation and maintenance personnel quickly locate and take actions, reduces the fault handling time, and improves the reliability and stability of the overall system. Different warning levels correspond to different levels of urgency and resource requirements. Through hierarchical warning, the operation and maintenance resources can be reasonably allocated to ensure that there are sufficient resources to respond in case of emergencies, and at the same time avoid wasting resources in non-emergency situations. The hierarchical warning provides clear and quantitative information about the state of the energy storage battery, which helps decision-makers make more informed decisions.

[0129] Please refer to Figure 2 , another embodiment of the present invention provides a state monitoring system for an energy storage system, including:

[0130] A monitoring data acquisition module 101, configured to acquire data related to the monitoring of the energy storage system;

[0131] A prediction residual analysis module 102, configured to perform prediction residual analysis on the data related to the monitoring of the energy storage system, and obtain the average value and standard deviation of each data related to the monitoring of the energy storage system;

[0132] A multi-level warning threshold setting module 103, configured to calculate the mean residual and the standard deviation of the residual according to the average value and the standard deviation of each data related to the monitoring of the energy storage system, so as to set multi-level warning thresholds;

[0133] A hierarchical warning module 104, configured to perform hierarchical warnings according to the multi-level warning thresholds to complete the state monitoring of the energy storage system.

[0134] In a possible implementation manner, the data related to the monitoring of the energy storage system acquired by the monitoring data acquisition module 101 includes:

[0135] Any one or more of the single-cell voltage of the battery, the single-cell temperature of the battery, the module voltage of the battery, the module temperature of the battery, the cluster voltage of the battery, the cluster temperature of the battery, the remaining capacity of the single cell of the battery, and the concentration of volatile organic compounds (VOC) in the battery compartment.

[0136] In a possible implementation manner, the prediction residual analysis module 102 calculates the average value and standard deviation of each data related to the monitoring of the energy storage system according to the following expression:

[0137]

[0138] In the formula, is the average value of each data related to the monitoring of the energy storage system; S is the standard deviation of each data related to the monitoring of the energy storage system; N is the number of each data related to the monitoring of the energy storage system; is the predicted value; y is the actual value; e t is the difference between the predicted value and the actual value at the corresponding moment in the sliding window method.

[0139] In a possible implementation manner, the multi-level warning threshold setting module 103 calculates the multi-level warning thresholds according to the following expression:

[0140]

[0141] In the formula, is the maximum value of the average value of each data related to the monitoring of the energy storage system; S max is the maximum value of the standard deviation of each data related to the monitoring of the energy storage system; XP is the upper or lower limit of the first-level warning of the residual mean; S P is the upper limit of the first-level warning of the residual standard deviation; X S is the upper or lower limit of the second-level warning of the residual mean; S S is the upper limit of the second-level warning of the residual standard deviation.

[0142] In a possible implementation manner, the hierarchical warning module 104 sets the first-level warning rule according to the following relational expression:

[0143]

[0144] Sets the second-level warning rule according to the following relational expression:

[0145]

[0146] In the formula, X R is the average value of the residuals of the monitoring-related data of each energy storage system monitored, S R is the standard deviation of the residuals of the monitoring-related data of each energy storage system monitored;

[0147] When X R or S R exceeds the set warning threshold, multi-level warnings are executed.

[0148] Furthermore, the first-level warning indicates that the battery has a first-level risk. After checking and finding no abnormalities, continue to operate;

[0149] The second-level warning indicates that the battery has a second-level risk. Stop the charging and discharging of the battery, take strengthening measures to ensure safety, and regularly maintain the battery according to the requirements of the maintenance regulations; after the rectification is completed, conduct an acceptance approval and then put it into operation;

[0150] The third-level warning indicates that the battery has a third-level risk. Stop the operation of the power station to prevent the spread of thermal runaway; if the thermal runaway cannot be controlled, trigger the alarm system for safety protection;

[0151] Among them, the severity of the first-level risk, the second-level risk, and the third-level risk increases in sequence.

[0152] As the core component of the power station, the safety of the energy storage battery is directly related to the stable operation of the entire power station. During the charging and discharging process of the battery, heat, gas, etc. may be generated. If not handled properly or there are design defects, it may cause fire or explosion. In addition, problems such as battery aging, short circuit, overcharging and over-discharging are also common safety hazards.

[0153] At present, many energy storage systems still lack comprehensive and real-time safety monitoring means. Traditional monitoring methods can often only detect faults that have occurred or are about to occur, but cannot provide early warnings and prevention. In addition, there are also certain problems with the accuracy and reliability of monitoring data, which further increases the safety risks of the power station.

[0154] To improve the safety of energy storage systems, it is necessary to accelerate the research and development of energy storage safety technologies. This includes aspects such as improving battery materials, optimizing battery management systems, and enhancing thermal management technologies. Through technological improvements, the probability of battery failures can be reduced from the source, and the overall safety of the power station can be improved.

[0155] To achieve comprehensive monitoring and early warning of energy storage systems, a more perfect safety monitoring system needs to be established. This includes real-time monitoring of battery state parameters (such as voltage, current, temperature, etc.), analyzing the health status of the battery, and predicting potential failures. At the same time, advanced data analysis technologies and algorithms also need to be introduced to improve the accuracy and reliability of monitoring data.

[0156] In addition to improvements at the technical level, strengthening awareness of safety risk prevention is also crucial. This includes regularly conducting safety inspections and maintenance of the power station, training operators to master safety knowledge and skills, formulating emergency plans and conducting regular drills, etc. By improving the safety awareness and emergency response capabilities of personnel, the occurrence of safety accidents can be reduced to a certain extent.

[0157] In the future, with the continuous development of energy storage technologies and the continuous expansion of application fields, the safety of energy storage systems will receive increasing attention. Therefore, the energy storage industry needs to continuously strengthen technology research and development and safety management to ensure the safe and stable operation of energy storage systems.

[0158] Another embodiment of the present invention also proposes an electronic device, including a processor and a memory, and the processor is used to execute a computer program stored in the memory to implement the energy storage system state monitoring method described above.

[0159] Another embodiment of the present invention also proposes a computer-readable storage medium, and the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the energy storage system state monitoring method described above is implemented.

[0160] The computer program includes computer program code, which may be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable storage medium may include: any entity or device, medium, USB flash drive, removable hard disk, magnetic disk, optical disc, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice within the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals. For the convenience of description, only the parts related to the embodiments of the present invention are shown above. For the specific technical details not disclosed, please refer to the method part of the embodiments of the present invention. This computer-readable storage medium is non-transitory and can be stored in a storage device formed by various electronic devices, and can implement the execution process recorded in the method of the embodiments of the present invention.

[0161] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can be in the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0162] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be realized by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be realized. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one or more flows Figure 1 or multiple flows and / or blocks

[0163] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device realizes the functions specified in Figure 1 one or more flows Figure 1 or multiple flows and / or blocks

[0164] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable apparatus provide steps for realizing the functions specified in one process or a plurality of processes and / or one block or a plurality of blocks. Figure 1 one process or a plurality of processes and / or Figure 1 one block or a plurality of blocks.

[0165] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the protection scope of the claims of the present invention.

Claims

1. A method for monitoring the state of an energy storage system, characterized in that, Including: Obtaining data related to the monitoring of the energy storage system; Performing predictive residual analysis on the data related to the monitoring of the energy storage system to obtain the average value and standard deviation of each data related to the monitoring of the energy storage system; Calculating the mean residual and standard deviation of the residual according to the average value and standard deviation of each data related to the monitoring of the energy storage system to set multi-level warning thresholds; Performing hierarchical warnings according to the multi-level warning thresholds to complete the status monitoring of the energy storage system.

2. The method for monitoring the state of the energy storage system according to claim 1, wherein The data related to the monitoring of the energy storage system includes: Any one or more of the cell voltage, cell temperature, battery module voltage, battery module temperature, battery cluster voltage, battery cluster temperature, remaining capacity of the cell, and concentration of volatile organic compound (VOC) in the battery compartment.

3. The method for monitoring the state of the energy storage system according to claim 1, wherein The step of performing predictive residual analysis on the data related to the monitoring of the energy storage system to obtain the average value and standard deviation of each data related to the monitoring of the energy storage system is calculated according to the following expression: In the formula, is the average value of the monitoring-related data of each energy storage system; S is the standard deviation of the monitoring-related data of each energy storage system; N is the number of the monitoring-related data of each energy storage system; is the predicted value; y is the actual value; e t is the difference between the predicted value and the actual value at the corresponding moment in the sliding window method.

4. The energy storage system state monitoring method according to claim 1, characterized in that, The step of calculating the mean residual and standard deviation of the residual according to the average value and standard deviation of each data related to the monitoring of the energy storage system to set multi-level warning thresholds calculates the multi-level warning thresholds according to the following expression: In the formula, is the maximum value of the average of the monitoring related data of each energy storage system; S max is the maximum value of the standard deviation of the monitoring related data of each energy storage system; X P is the upper or lower limit of the first-level warning of the residual mean; S P is the upper limit of the first-level warning of the residual standard deviation; X S is the upper or lower limit of the second-level warning of the residual mean; S S is the upper limit of the second-level warning of the residual standard deviation.

5. The method for monitoring the state of the energy storage system according to claim 4, wherein The step of performing hierarchical warnings according to the multi-level warning thresholds includes: The first-level warning rule is set as follows: The second-level warning rule is set as follows: Wherein, X R is the average value of the residuals of the monitoring-related data of each monitored energy storage system, and S R is the standard deviation of the residuals of the monitoring-related data of each monitored energy storage system; When X R or S R exceeds the set warning threshold, multi-level warnings are executed.

6. The method for monitoring the state of the energy storage system according to claim 5, wherein In the step of performing hierarchical warnings according to the multi-level warning thresholds to complete the status monitoring of the energy storage system: When a first-level warning occurs, it indicates that the battery has a first-level risk. After checking and finding no abnormality, continue to operate; When a second-level warning occurs, it indicates that the battery has a second-level risk. Stop the battery charging and discharging and perform maintenance; The severity of the second-level risk is higher than that of the first-level risk.

7. A state monitoring system for an energy storage system, characterized in that, Including: A monitoring data acquisition module for obtaining data related to the monitoring of the energy storage system; A predictive residual analysis module for performing predictive residual analysis on the data related to the monitoring of the energy storage system to obtain the average value and standard deviation of each data related to the monitoring of the energy storage system; A multi-level warning threshold setting module for calculating the mean residual and standard deviation of the residual according to the average value and standard deviation of each data related to the monitoring of the energy storage system to set multi-level warning thresholds; A hierarchical warning module for performing hierarchical warnings according to the multi-level warning thresholds to complete the status monitoring of the energy storage system.

8. The energy storage system state monitoring system according to claim 7, characterized in that, The data related to the monitoring of the energy storage system obtained by the monitoring data acquisition module includes: Any one or more of the cell voltage, cell temperature, battery module voltage, battery module temperature, battery cluster voltage, battery cluster temperature, remaining capacity of the cell, and concentration of volatile organic compound (VOC) in the battery compartment.

9. The energy storage system state monitoring system according to claim 7, wherein The predictive residual analysis module calculates the average value and standard deviation of each data related to the monitoring of the energy storage system according to the following expression: In the formula, is the average value of the monitoring-related data of each energy storage system; S is the standard deviation of the monitoring-related data of each energy storage system; N is the number of the monitoring-related data of each energy storage system; is the predicted value; y is the actual value; e t is the difference between the predicted value and the actual value at the corresponding moment in the sliding window method.

10. The energy storage system state monitoring system according to claim 7, characterized in that, The multi-level warning threshold setting module calculates the multi-level warning thresholds according to the following expression: In the formula, is the maximum value of the average of the monitoring related data of each energy storage system; S max is the maximum value of the standard deviation of the monitoring related data of each energy storage system; X P is the upper or lower limit of the first-level warning of the residual mean; S P is the upper limit of the first-level warning of the residual standard deviation; X S is the upper or lower limit of the second-level warning of the residual mean; S S is the upper limit of the second-level warning of the residual standard deviation.

11. The energy storage system state monitoring system according to claim 10, wherein The hierarchical warning module sets the first-level warning rule according to the following relationship: Sets the second-level warning rule according to the following relationship: where X R is the average value of the residuals of the monitoring-related data of each monitored energy storage system, and S R is the standard deviation of the residuals of the monitoring-related data of each monitored energy storage system; When X R or S R exceeds the set warning threshold, multi-level warnings are executed.

12. The energy storage system state monitoring system according to claim 11, wherein When the hierarchical warning module performs hierarchical warnings according to the multi-level warning thresholds to complete the status monitoring of the energy storage system: When a first-level warning occurs, it indicates that the battery has a first-level risk. After checking and finding no abnormality, continue to operate; When a second-level warning occurs, it indicates that the battery has a second-level risk. Stop the battery charging and discharging and perform maintenance; The severity of the second-level risk is higher than that of the first-level risk.

13. An electronic device, characterized in that, It includes a processor and a memory. The processor is configured to execute a computer program stored in the memory to implement the energy storage system state monitoring method according to any one of claims 1 to 6.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, it implements the energy storage system state monitoring method according to any one of claims 1 to 6.

Images