A consistency assessment method for operating status of energy storage system

The operating status of the battery pack of the energy storage system is evaluated through the k-means algorithm and classifier, which solves the problem of inconsistent battery cell performance in low temperature environments, improves the long-term load capacity and reliability of the energy storage system, and ensures the consistency of the battery pack .

CN117743920BActive Publication Date: 2024-11-19STATE GRID QINGHAI PROVINCE ELECTRIC POWER CO CLEAN ENERGY DEVELOPMENT RESEARCH INSTITUTE +3
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202311728442.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-12-13
Publication Date
2024-11-19
Estimated Expiration
2043-12-13

AI Technical Summary

Technical Problem

In low temperature environments, the performance of battery cells in the energy storage system is inconsistent, which affects the consistency between batteries and leads to a decrease in the long-term load capacity and reliability of the energy storage system.

Method used

The k-means algorithm is used to cluster the load samples, determine the load clustering center and normal load fluctuation range, and predict the operating status of the energy storage unit by training the classifier, evaluate its consistency, and combine the temperature rise effect and weather data to predict Future operating temperature and load information.

Benefits of technology

It improves the long-term load capacity and reliability of the energy storage system, improves the operating efficiency of the energy storage unit, and ensures the consistency of the operating status of the battery pack.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117743920B_ABST
    Figure CN117743920B_ABST
Patent Text Reader

Abstract

The present application discloses a method for evaluating the consistency of the operating status of an energy storage system, including: obtaining the historical load data of each energy storage unit of the energy storage system under the corresponding total load demand at each operating environment temperature to form multiple load samples in each temperature interval; clustering the load samples in each temperature interval by the k-means algorithm to determine the load clustering center in each temperature interval; taking the load clustering center in each temperature interval as the center of the circle, determining the normal load fluctuation range of any energy storage unit in the corresponding temperature interval; determining positive samples and negative samples based on the normal load fluctuation range; training a classifier; predicting the operating temperature and load information of each energy storage unit in the future period, and inputting the trained classifier to complete the consistency evaluation. The method of the present application is used to realize the consistency evaluation of the operating status of the energy storage system, improve the long-term load carrying capacity and reliability of the energy storage system, and improve the operating efficiency of the energy storage unit.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of energy storage systems, and in particular to a method for evaluating the consistency of operating status of an energy storage system. Background Art

[0002] An energy storage system includes at least a plurality of battery modules, each of which is composed of a number of battery cells connected in series or in parallel, and each battery module is equipped with a battery management system for collecting the battery module voltage, current and temperature information. An energy storage system includes at least a plurality of battery modules, each of which is composed of a number of battery cells connected in series or in parallel, and each battery module is equipped with a battery management system for collecting the battery module voltage, current and temperature information.

[0003] In actual production applications, although the structure of each battery pack of the energy storage unit is the same, different battery packs have differences due to the different operating environments and assigned loads. Especially in winter, cold areas, and low temperature environments, as the number of charge and discharge times increases, the performance of battery cells becomes inconsistent, affecting the consistency between batteries. Summary of the invention

[0004] The embodiment of the present application provides a method for evaluating the consistency of the operating status of an energy storage system, which is used to implement consistency evaluation of the operating status of an energy storage unit battery pack of the energy storage system, improve the long-term load-carrying capacity and reliability of the energy storage system, and improve the operating efficiency of the energy storage unit.

[0005] The present application embodiment provides a method for evaluating the consistency of the operating status of an energy storage system, including:

[0006] Acquire historical load data of each energy storage unit of the energy storage system under corresponding total load requirements at each operating environment temperature to form a plurality of load samples in each temperature interval, wherein the temperature interval is a temperature interval divided based on a low temperature range of interest to the user;

[0007] The load samples in each temperature range are clustered by the k-means algorithm to determine the load clustering center in each temperature range;

[0008] Taking the load clustering center in each temperature interval as the center of the circle, determining the normal load interval radius for each temperature interval, so as to determine the normal load fluctuation range of any energy storage unit in the corresponding temperature interval based on the center of the circle and the radius;

[0009] Determine positive samples based on the normal load fluctuation range, and determine negative samples based on the normal load fluctuation range, and add tags, wherein the added tags include historical time information, temperature information, and load information;

[0010] Training a classifier based on the positive samples and the negative samples in a chronological order;

[0011] For each energy storage unit of the energy storage system to be predicted, the operating temperature and load information of each energy storage unit in the future period are predicted, and input into the trained classifier to use the classifier to complete the consistency evaluation of the operating status of each energy storage unit.

[0012] Optionally, also include:

[0013] The acquired historical ambient temperature data is fitted at a specified time interval to obtain a historical temperature fitting curve;

[0014] For any energy storage unit, sort its corresponding positive samples and possible negative samples in chronological order;

[0015] Based on the time relationship, the positive samples and possible negative samples are associated with the historical temperature fitting curve; and,

[0016] Based on the historical temperature fitting curve, determining a partial fitting curve of any energy storage unit that changes from a positive sample to a negative sample;

[0017] Feature information of the partial fitting curve is extracted and combined with the extracted corresponding negative sample feature information to train a classifier.

[0018] Optionally, based on the historical temperature fitting curve, determining a partial fitting curve of any energy storage unit that changes from a positive sample to a negative sample includes:

[0019] Determine the inflection point region where any energy storage unit changes from a positive sample to a negative sample, and based on the inflection point region, select the historical temperature fitting curves of the specified time range respectively before and after to determine the partial fitting curve, wherein the time length selected forward is greater than the time length selected backward;

[0020] Extracting characteristic information of the partial fitting curve and combining it with the extracted corresponding negative sample characteristic information includes: configuring a temperature influence weight for the extracted characteristic information of the partial fitting curve, and the longer the time that any energy storage unit continues to behave as a negative sample after the inflection point area, the greater the configured temperature influence weight, but the temperature influence weight does not exceed the upper limit of the weight.

[0021] Optionally, for each energy storage unit of the energy storage system to be predicted, predicting the operating temperature and load information of each energy storage unit in the future period and inputting the trained classifier includes:

[0022] According to future energy consumption demand, predict the load information of future energy storage system;

[0023] Distributing the load information to each energy storage unit in an estimated manner to determine an estimated load of each energy storage unit;

[0024] Predicting the temperature rise effect of the energy storage system based on the estimated load of each energy storage unit;

[0025] Based on the predicted ambient temperature of the energy storage system in the future period and the temperature rise effect of the energy storage system, the operating temperature of the energy storage system in the future period is determined.

[0026] Optionally, predicting the temperature rise effect of the energy storage system based on the estimated load of each energy storage unit includes:

[0027] Calculate the load current of any energy storage unit based on the estimated load of any energy storage unit;

[0028] Determining the heat generated by any energy storage unit according to the calculated load current and the internal resistance of any energy storage unit;

[0029] Accumulate the calorific value of each energy storage unit of the energy storage system to determine the total calorific value; and,

[0030] Determine the effective environmental space volume from the ground to the height associated with the energy storage unit;

[0031] Based on the effective environmental space volume and the total heating value, the temperature rise effect of the energy storage system is predicted.

[0032] Optionally, determining the effective environmental space volume according to the height from the ground to the height associated with the energy storage unit includes:

[0033] Determining an effective temperature rise impact area based on the floor area of ​​the energy storage unit; and

[0034] The height of the energy storage unit α times the height from the ground is taken as the associated height, where α is 1.2-1.8;

[0035] The effective environmental space volume is determined based on the associated height and the effective temperature rise impact area.

[0036] Optionally, based on the predicted ambient temperature of the energy storage system in the future period and the temperature rise effect of each energy storage unit, determining the operating temperature of the energy storage system in the future period includes:

[0037] Obtain weather data at the location of the energy storage system in a future period, and extract temperature data at the energy storage system from the weather data;

[0038] The temperature rise effect of the energy storage system is superimposed on the air temperature data to serve as the predicted operating temperature of the energy storage system in the future period.

[0039] Optionally, for each energy storage unit of the energy storage system to be predicted, predicting the operating temperature and load information of each energy storage unit in the future period and inputting the information into the trained classifier also includes:

[0040] Fitting the predicted operating temperature of the energy storage system in the future period and splitting it according to the specified time intervals to obtain the temperature fitting curve of the future period split;

[0041] The characteristic information of the split temperature fitting curve and the load characteristic information of any energy storage unit of the energy storage system at the corresponding time node are extracted and input into the trained classifier to complete the consistency evaluation.

[0042] The method of the embodiment of the present application determines positive and negative samples through a clustering algorithm and trains a classifier, thereby using the trained classifier to perform consistency evaluation on the operating status of the energy storage unit battery pack of the energy storage system, thereby improving the long-term load-carrying capacity and reliability of the energy storage system and improving the operating efficiency of the energy storage unit.

[0043] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0045] Figure 1 The following is a basic flow chart of the method for evaluating the consistency of the operating status of an energy storage system according to this embodiment. DETAILED DESCRIPTION

[0046] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0047] The present application embodiment proposes a method for evaluating the consistency of the operating status of an energy storage system, such as Figure 1 As shown, the following steps are included:

[0048] In step S101, historical load data of each energy storage unit of the energy storage system under the corresponding total load demand at each operating environment temperature is obtained to form multiple load samples in each temperature interval, wherein the temperature interval is a temperature interval divided based on the low temperature range that the user is interested in. The method of the present application comprehensively considers the operating environment temperature of each energy storage unit of the energy storage system and the load of the energy storage unit to determine multiple load samples in each temperature interval based on historical power data. For example, the temperature interval can be between -15°C and 10°C, and of course it can also be other temperature ranges of interest to the user, and the temperature range is divided into multiple temperature intervals.

[0049] In step S102, the load samples in each temperature interval are clustered by the k-means algorithm to determine the load cluster center in each temperature interval. In the embodiment of the present application, cluster analysis is performed on the operating conditions of any energy storage unit in each operating period in the corresponding temperature interval, so that the same energy storage unit may appear multiple times in the cluster, representing the operating conditions of the energy storage unit in different historical operating times. The specific clustering algorithm is an existing method and will not be described in detail here.

[0050] In step S103, the normal load interval radius is determined for each temperature interval with the load clustering center in each temperature interval as the center of the circle, so as to determine the normal load fluctuation range of any energy storage unit in the corresponding temperature interval based on the center of the circle and the radius.

[0051] In step S104, positive samples are determined based on the normal load fluctuation range, and negative samples are determined based on the normal load fluctuation range, and tags are added, wherein the added tags include historical time information, temperature information, and load information. In the embodiment of the present application, a method of determining positive and negative samples based on the cluster center is proposed, which can be specifically implemented by setting the radius. In some embodiments, setting the temperature information can be associated with the subsequent fitting temperature, thereby introducing the influence of the ambient temperature on the energy storage system.

[0052] In step S105, a classifier is trained based on the positive samples and negative samples in a time sequence.

[0053] In step S106, for each energy storage unit of the energy storage system to be predicted, the operating temperature and load information of each energy storage unit in the future period are predicted, and the trained classifier is input to complete the consistency evaluation of the operating status of each energy storage unit using the classifier.

[0054] The method of the embodiment of the present application determines positive and negative samples through a clustering algorithm and trains a classifier, thereby using the trained classifier to perform consistency evaluation on the operating status of the energy storage unit battery pack of the energy storage system, thereby improving the long-term load-carrying capacity and reliability of the energy storage system and improving the operating efficiency of the energy storage unit.

[0055] In some embodiments, it also includes:

[0056] The acquired historical ambient temperature data is fitted at a specified time interval to obtain a historical temperature fitting curve. In some specific examples, the historical ambient temperature data at a specified time interval may be fitted according to the number of sampling points.

[0057] For any energy storage unit, its corresponding positive samples and possible negative samples are sorted in chronological order. In some embodiments, for some energy storage units, in the operation instance, for example, the load may be evenly distributed, the load rate is low, and other factors, these energy storage units may always appear as positive samples. Such samples are also sorted in chronological order, so that the classifier can be trained according to the time relationship and load trend during training.

[0058] In some embodiments, based on the time relationship, the positive samples and possible negative samples are associated with the historical temperature fitting curve. The specific association method can be a label method. In some embodiments, it is sufficient to associate the positive samples. Of course, feature extraction can also be performed on the historical temperature fitting curve corresponding to the positive samples, which is not limited here.

[0059] Based on the historical temperature fitting curve, a partial fitting curve of any energy storage unit changing from a positive sample to a negative sample is determined. In an embodiment of the present application, a partial fitting curve of any energy storage unit changing from a positive sample to a negative sample can be determined according to the time sequence, thereby focusing on the state change of any energy storage unit.

[0060] Feature information of the partial fitting curve is extracted and combined with the extracted corresponding negative sample feature information to train a classifier.

[0061] In some embodiments, based on the historical temperature fitting curve, determining a partial fitting curve of any energy storage unit that changes from a positive sample to a negative sample includes:

[0062] Determine the inflection point area where any energy storage unit changes from a positive sample to a negative sample. Based on the inflection point area, select historical temperature fitting curves of a specified time range before and after, respectively, to determine the partial fitting curve, wherein the time length selected forward is greater than the time length selected backward. Through such a design, on the one hand, the time length of the positive sample can be reduced, and on the other hand, more historical temperature fitting curves can be selected later. Therefore, for example, in some examples, the noise caused by the possible existence of a certain energy storage unit having only one negative sample conversion rather than continuously becoming a negative sample can be excluded, and the focus can be placed on the characteristics of the energy storage unit that continuously becomes a negative sample.

[0063] Extracting the characteristic information of the partial fitting curve and combining it with the extracted corresponding negative sample characteristic information includes: configuring a temperature influence weight for the extracted characteristic information of the partial fitting curve, and the longer the time that any energy storage unit continues to behave as a negative sample after the inflection point area, the greater the configured temperature influence weight, but the temperature influence weight does not exceed the upper limit of the weight. The method of the present application takes into account the influence of weather factors and the introduction of ambient temperature factors on the energy storage system, and implements consistency evaluation through a classifier. In a specific example, the longer the time that any energy storage unit continues to behave as a negative sample after the inflection point area, the greater the configured temperature influence weight, and the focus can be placed on the influence of ambient temperature, especially low temperature operation, on the consistency of the operating state of the energy storage unit. However, temperature is an external operating factor of the energy storage unit. In the embodiment of the present application, the temperature influence weight is further set not to exceed the upper limit of the weight, which can avoid the excessive weight of the ambient temperature interfering with the classification effect of the classifier, thereby improving the recognition effect of the trained classifier.

[0064] In some embodiments, for each energy storage unit of the energy storage system to be predicted, predicting the operating temperature and load information of each energy storage unit in the future period and inputting the information into the trained classifier includes:

[0065] According to future energy consumption demand, predict the load information of future energy storage system;

[0066] The load information is distributed to each energy storage unit in an estimated manner to determine the estimated load of each energy storage unit. For example, in some examples, the estimated load of each energy storage unit can be determined according to the previous operation mode or operation habits according to the future energy consumption demand.

[0067] The temperature rise effect of the energy storage system is predicted based on the estimated load of each energy storage unit.

[0068] Based on the predicted ambient temperature of the energy storage system in the future period and the temperature rise effect of the energy storage system, the operating temperature of the energy storage system in the future period is determined.

[0069] In some embodiments, predicting the temperature rise effect of the energy storage system based on the estimated load of each energy storage unit includes:

[0070] Calculate the load current of any energy storage unit based on the estimated load of any energy storage unit;

[0071] The heat generated by any energy storage unit is determined according to the calculated load current and the internal resistance of any energy storage unit. In some specific embodiments, for example, the heat effect I of the current can be used to determine the heat generated by any energy storage unit. 2 Rt is used to determine the heat generated by any energy storage unit over a certain period of time.

[0072] Accumulate the calorific value of each energy storage unit of the energy storage system to determine the total calorific value; and

[0073] The effective environmental space volume is determined based on the height from the ground to the height associated with the energy storage unit.

[0074] Based on the effective environmental space volume and the total heating value, the temperature rise effect of the energy storage system is predicted.

[0075] In some embodiments, determining the effective environmental space volume from the ground to the height associated with the energy storage unit includes:

[0076] Determining an effective temperature rise impact area based on the floor area of ​​the energy storage unit; and

[0077] The height of the energy storage unit α times the height from the ground is taken as the associated height, where α is 1.2-1.8;

[0078] The effective environmental space volume is determined based on the associated height and the effective temperature rise influence area, for example, effective environmental space volume=Sh, wherein S is the effective temperature rise influence area, and h is the associated height.

[0079] In some embodiments, based on the predicted ambient temperature of the energy storage system in the future period and the temperature rise effect of each energy storage unit, determining the operating temperature of the energy storage system in the future period includes:

[0080] Obtain weather data at the location of the energy storage system in a future period, and extract temperature data at the energy storage system from the weather data;

[0081] The temperature rise effect of the energy storage system is superimposed on the air temperature data to predict the operating temperature of the energy storage system in the future period. In some embodiments, if the energy storage unit operates in an environment including a temperature control system, the weather data can be considered to perform the constant temperature and temperature rise effect steps.

[0082] In some embodiments, for each energy storage unit of the energy storage system to be predicted, predicting the operating temperature and load information of each energy storage unit in the future period and inputting the information into the trained classifier further includes:

[0083] Fitting the predicted operating temperature of the energy storage system in the future period and splitting it according to the specified time intervals to obtain the temperature fitting curve of the future period split;

[0084] The characteristic information of the split temperature fitting curve and the load characteristic information of any energy storage unit of the energy storage system at the corresponding time node are extracted and input into the trained classifier to complete the consistency evaluation.

[0085] Similar to the training step, in the embodiment of the present application, the operating temperature of the energy storage system in the future time period is fitted, so as to extract the characteristic information after the time period is split, and the load characteristic information of any energy storage unit of the energy storage system in the corresponding time period is extracted, so as to complete the consistency evaluation through the trained classifier.

[0086] The method of the embodiment of the present application takes into account the operating environment of each energy storage unit of the energy storage system, especially for the low temperature range, and considers the actual impact of the ambient temperature and the heat generation of the energy storage unit on the operation of the energy storage unit through a design method, and completes the consistency evaluation based on the trained classifier, so as to guide the energy storage unit to better realize the energy storage consistency control, improve the long-term load-carrying capacity and reliability of the energy storage system, and improve the operating efficiency of the energy storage unit.

[0087] In addition, although exemplary embodiments have been described herein, the scope includes any and all embodiments based on the present disclosure with equivalent elements, modifications, omissions, combinations (e.g., various embodiments intersecting schemes), adaptations or changes. It is not limited to the examples described in this specification or during the implementation of this application, and its examples will be interpreted as non-exclusive.

[0088] The above description is intended to be illustrative rather than restrictive. For example, the above examples (or one or more of them) can be used in combination with each other. For example, those of ordinary skill in the art may use other embodiments when reading the above description.

[0089] The above embodiments are merely exemplary embodiments of the present disclosure. Those skilled in the art may make various modifications or equivalent substitutions to the present invention within the essence and protection scope of the present disclosure, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present invention.

Claims

1. A method for evaluating the consistency of the operating status of an energy storage system, characterized in that: include: Acquire historical load data of each energy storage unit of the energy storage system under corresponding total load requirements at each operating environment temperature to form a plurality of load samples in each temperature interval, wherein the temperature interval is a temperature interval divided based on a low temperature range of interest to the user; The load samples in each temperature range are clustered by the k-means algorithm to determine the load clustering center in each temperature range; Taking the load clustering center in each temperature interval as the center of the circle, determining the normal load interval radius for each temperature interval, so as to determine the normal load fluctuation range of any energy storage unit in the corresponding temperature interval based on the center of the circle and the radius; Determine positive samples based on the normal load fluctuation range, and determine negative samples based on the normal load fluctuation range, and add tags, wherein the added tags include historical time information, temperature information, and load information; Training a classifier based on the positive samples and the negative samples in a chronological order; For each energy storage unit of the energy storage system to be predicted, predict the operating temperature and load information of each energy storage unit in the future period, and input the trained classifier to use the classifier to complete the consistency evaluation of the operating status of each energy storage unit; Also includes: The acquired historical ambient temperature data is fitted at a specified time interval to obtain a historical temperature fitting curve; For any energy storage unit, sort its corresponding positive samples and possible negative samples in chronological order; Based on the time relationship, the positive samples and possible negative samples are associated with the historical temperature fitting curve; and, Based on the historical temperature fitting curve, determining a partial fitting curve of any energy storage unit that changes from a positive sample to a negative sample; Feature information of the partial fitting curve is extracted and combined with the extracted corresponding negative sample feature information to train a classifier.

2. The method for evaluating the consistency of the operating status of an energy storage system according to claim 1, characterized in that: Based on the historical temperature fitting curve, determining a partial fitting curve of any energy storage unit that changes from a positive sample to a negative sample includes: Determine the inflection point region where any energy storage unit changes from a positive sample to a negative sample, and based on the inflection point region, select the historical temperature fitting curves of the specified time range respectively before and after to determine the partial fitting curve, wherein the time length selected forward is greater than the time length selected backward; Extracting characteristic information of the partial fitting curve and combining it with the extracted corresponding negative sample characteristic information includes: configuring a temperature influence weight for the extracted characteristic information of the partial fitting curve, and the longer the time that any energy storage unit continues to behave as a negative sample after the inflection point area, the greater the configured temperature influence weight, but the temperature influence weight does not exceed the upper limit of the weight.

3. The method for evaluating the consistency of the operating status of an energy storage system according to claim 1, characterized in that: For each energy storage unit of the energy storage system to be predicted, the operating temperature and load information of each energy storage unit in the future period are predicted, and the input of the trained classifier includes: According to future energy consumption demand, predict the load information of future energy storage system; Distributing the load information to each energy storage unit in an estimated manner to determine an estimated load of each energy storage unit; Predicting the temperature rise effect of the energy storage system based on the estimated load of each energy storage unit; Based on the predicted ambient temperature of the energy storage system in the future period and the temperature rise effect of the energy storage system, the operating temperature of the energy storage system in the future period is determined.

4. The method for evaluating the consistency of the operating status of an energy storage system according to claim 3, characterized in that: Predicting the temperature rise effect of the energy storage system based on the estimated load of each energy storage unit includes: Calculate the load current of any energy storage unit based on the estimated load of any energy storage unit; Determining the heat generated by any energy storage unit according to the calculated load current and the internal resistance of any energy storage unit; Accumulate the calorific value of each energy storage unit of the energy storage system to determine the total calorific value; and, Determine the effective environmental space volume from the ground to the height associated with the energy storage unit; Based on the effective environmental space volume and the total heating value, the temperature rise effect of the energy storage system is predicted.

5. The method for evaluating the consistency of the operating status of an energy storage system according to claim 4, characterized in that: Determining the effective environmental space volume from the ground to the height associated with the energy storage unit includes: Determining an effective temperature rise impact area based on the floor area of ​​the energy storage unit; and The height of the energy storage unit α times the height from the ground is taken as the associated height, where α is 1.2-1.8; The effective environmental space volume is determined based on the associated height and the effective temperature rise impact area.

6. The method for evaluating the consistency of the operating status of an energy storage system according to claim 4, characterized in that: Based on the predicted ambient temperature of the energy storage system in the future period and the temperature rise effect of each energy storage unit, the operating temperature of the energy storage system in the future period is determined including: Obtain weather data at the location of the energy storage system in a future period, and extract temperature data at the energy storage system from the weather data; The temperature rise effect of the energy storage system is superimposed on the air temperature data to serve as the predicted operating temperature of the energy storage system in the future period.

7. The method for evaluating the consistency of the operating status of an energy storage system according to claim 6, characterized in that: For each energy storage unit of the energy storage system to be predicted, the operating temperature and load information of each energy storage unit in the future period are predicted and input into the trained classifier, which also includes: Fitting the predicted operating temperature of the energy storage system in the future period and splitting it according to the specified time intervals to obtain the temperature fitting curve of the future period split; The characteristic information of the split temperature fitting curve and the load characteristic information of any energy storage unit of the energy storage system at the corresponding time node are extracted and input into the trained classifier to complete the consistency evaluation.

Citation Information

Cited By

  • Method for rapidly evaluating attenuation level and consistency of lithium ion storage battery

    CN122043234A