Method for diagnosing and evaluating health state of energy storage battery pack

Abstract

The invention discloses an energy storage battery pack health state diagnosis and evaluation method, which belongs to the technical field of battery pack health state diagnosis, and comprises the following steps: data acquisition, preprocessing, feature extraction, evaluation model construction, real-time evaluation and state judgment, and result analysis and processing. Wherein the data acquisition comprises the following steps: S1, acquiring key parameter data such as voltage, current, temperature, internal resistance and the like of the energy storage battery pack in the charging and discharging process, the health state of the energy storage battery pack can be evaluated more accurately by acquiring abundant real-time data and adopting advanced signal processing and machine learning algorithms; the health state change of the battery pack can be comprehensively reflected, and the evaluation accuracy is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of health status diagnosis of battery packs, and specifically relates to a health status diagnosis and evaluation method for an energy storage battery pack. Background Art

[0002] As the scale of energy storage power stations expands and the number of charge and discharge cycles increases, energy storage battery packs face the risk of capacity decline, performance degradation, and even failure. These risks not only affect the energy efficiency of energy storage power stations, but may also cause safety accidents such as fires. Therefore, it is of great significance to accurately evaluate the health status of energy storage battery packs. However, existing evaluation methods have problems such as insufficient training data capacity and large influence of sample set division, resulting in inaccurate evaluation results. Summary of the invention

[0003] The object of the present invention is to provide a method for diagnosing and evaluating the health status of an energy storage battery pack to solve the problems raised in the above-mentioned background technology.

[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solution: comprising the following steps: data collection, preprocessing, feature extraction, building an evaluation model, real-time evaluation and state judgment, and result analysis and processing;

[0005] The data collection includes: S1: collecting key parameter data such as voltage, current, temperature, internal resistance, etc. of the energy storage battery pack during the charging and discharging process;

[0006] As a further preferred embodiment of the present technical solution: the preprocessing comprises: S2: cleaning and preprocessing the collected data to remove noise and outliers to ensure the accuracy and reliability of the data;

[0007] As a further preferred embodiment of the technical solution: the feature extraction includes: S3: using an improved wavelet transform method to extract characteristic parameters such as fluctuation amplitude characteristics and frequency distribution characteristics that can reflect the health status of the battery pack from the pre-processed data;

[0008] As a further preferred embodiment of the present technical solution: the constructing of the evaluation model includes: S4 constructing an evaluation model of the health status of the battery pack using a support vector machine (SVM) or other suitable machine learning algorithm based on the extracted feature parameters;

[0009] S5: Train the model using battery pack data with known health status and validate it with an independent dataset to ensure the accuracy and generalization of the model.

[0010] As a further preferred embodiment of the present technical solution: the real-time evaluation and status judgment includes: S6: inputting the real-time collected battery pack data into the trained evaluation model to obtain the health status evaluation result of the battery pack, wherein the health status = f(V(t), I(t), T(t), R(t)), wherein V(t) is the voltage of the battery pack at time tt, I(t) is the current of the battery pack at time t, T(t) is the temperature of the battery pack at time t, and R(t) is the internal resistance of the battery pack at time t;

[0011] S7: Determine whether the battery pack is in a healthy, sub-healthy or faulty state based on the evaluation results, and give corresponding treatment suggestions;

[0012] As a further preferred embodiment of the technical solution: the result analysis and processing includes: S8: conducting an in-depth analysis of the evaluation results to understand the changing trend and potential problems of the health status of the battery pack;

[0013] S9: Formulate appropriate treatment measures based on the evaluation results, such as repairing or replacing battery cells or the entire battery pack;

[0014] As a further preferred embodiment of the present technical solution: the evaluation method further includes optimization and improvement, and the optimization and improvement include: regularly updating and optimizing the evaluation model, improving the accuracy and timeliness of the evaluation, introducing new data and technical means, and continuously improving the evaluation method to improve its applicability under complex working conditions;

[0015] As a further preferred embodiment of the present technical solution: the data processing further includes adopting corresponding data standardization or normalization methods for different types of data to ensure data consistency, wherein the calculation formula for data standardization is: The calculation formula for data normalization is:

[0016] As a further preferred embodiment of the technical solution: the data acquisition further comprises using data fusion technology to fuse the pre-processed multi-source data to form a feature vector that comprehensively reflects the health status of the battery pack;

[0017] Among them, in the process of data fusion, the correlation and complementarity between different data sources are considered, and methods such as weighted fusion, feature-level fusion or decision-level fusion are adopted;

[0018] As a further preferred embodiment of the present technical solution: the construction of the evaluation model also includes adopting cross-validation, regularization and other technologies to prevent the model from overfitting and improve the generalization ability of the model.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] 1. By collecting rich real-time data and adopting advanced signal processing and machine learning algorithms, the present invention can more accurately evaluate the health status of the energy storage battery pack, comprehensively reflect the changes in the health status of the battery pack, and improve the accuracy of the evaluation.

[0021] 2. The present invention can timely discover potential problems of the battery pack and take corresponding treatment measures, effectively avoiding the occurrence of safety accidents such as fire, and uses a deep learning algorithm to build an evaluation model, which can achieve accurate prediction of the health status of the battery pack.

[0022] 3. The present invention can ensure the stable operation of the energy storage battery pack under complex working conditions, continuously monitor various parameters of the battery pack, and immediately trigger the early warning mechanism once abnormal data or trends are detected to notify the operation and maintenance personnel to conduct inspections and maintenance, thereby improving the energy efficiency and reliability of the entire system. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of a method for diagnosing and evaluating the health status of an energy storage battery pack according to the present invention Figure 1 ;

[0024] Figure 2 The process of the health status diagnosis and evaluation method of the energy storage battery pack of the present invention is as follows Figure 1 ;

[0025] Figure 3 The process of the health status diagnosis and evaluation method of the energy storage battery pack of the present invention is as follows Figure 2 . DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] Example

[0028] See also Figure 1-Figure 3 As shown, the present invention provides a technical solution: comprising the following steps: data collection, preprocessing, feature extraction, building an evaluation model, real-time evaluation and state judgment, and result analysis and processing;

[0029] Among them, data collection includes: S1: collecting key parameter data such as voltage, current, temperature, internal resistance, etc. of the energy storage battery pack during the charging and discharging process. By collecting rich real-time data and using advanced signal processing and machine learning algorithms, the health status of the energy storage battery pack can be more accurately evaluated, and the changes in the health status of the battery pack can be fully reflected, thereby improving the accuracy of the evaluation;

[0030] In this embodiment, specifically: preprocessing includes: S2: cleaning and preprocessing the collected data to remove noise and outliers to ensure the accuracy and reliability of the data;

[0031] In this embodiment, specifically: feature extraction includes: S3: using the improved wavelet transform method to extract characteristic parameters such as fluctuation amplitude characteristics and frequency distribution characteristics that can reflect the health status of the battery pack from the pre-processed data, so as to timely discover potential problems of the battery pack and take corresponding treatment measures, effectively avoid the occurrence of safety accidents such as fire, and use a deep learning algorithm to build an evaluation model, so as to achieve accurate prediction of the health status of the battery pack;

[0032] In this embodiment, specifically: constructing the evaluation model includes: S4 constructing an evaluation model of the health status of the battery pack using a support vector machine (SVM) or other suitable machine learning algorithm based on the extracted feature parameters;

[0033] S5: Train the model using battery pack data with known health status and validate it with an independent dataset to ensure the accuracy and generalization of the model

[0034] In this embodiment, specifically: the real-time evaluation and status judgment includes: S6: inputting the real-time collected battery pack data into the trained evaluation model to obtain the health status evaluation result of the battery pack, wherein the health status = f(V(t), I(t), T(t), R(t)), wherein V(t) is the voltage of the battery pack at time tt, I(t) is the current of the battery pack at time t, T(t) is the temperature of the battery pack at time t, and R(t) is the internal resistance of the battery pack at time t;

[0035] S7: Determine whether the battery pack is in a healthy, sub-healthy or faulty state based on the evaluation results, and give corresponding treatment suggestions;

[0036] In this embodiment, specifically: result analysis and processing include: S8: in-depth analysis of the evaluation results to understand the changing trend and potential problems of the health status of the battery pack;

[0037] S9: Formulate corresponding treatment measures based on the evaluation results, such as repairing or replacing battery cells or the entire battery pack, to ensure the stable operation of the energy storage battery pack under complex working conditions, improve the energy efficiency and reliability of the entire system, and provide visual reports or early warning information to facilitate operation and maintenance personnel to understand the health status of the battery pack in a timely manner;

[0038] In this embodiment, specifically: the evaluation method also includes optimization and improvement, and the optimization and improvement include: regularly updating and optimizing the evaluation model, improving the accuracy and timeliness of the evaluation, introducing new data and technical means, and constantly improving the evaluation method to improve its applicability under complex working conditions;

[0039] In this embodiment, specifically: data processing also includes adopting corresponding data standardization or normalization methods for different types of data to ensure data consistency, wherein the calculation formula for data standardization is: The calculation formula for data normalization is:

[0040] In this embodiment, specifically: data collection also includes using data fusion technology to fuse the pre-processed multi-source data to form a feature vector that comprehensively reflects the health status of the battery pack;

[0041] Among them, in the process of data fusion, the correlation and complementarity between different data sources are considered, and methods such as weighted fusion, feature-level fusion or decision-level fusion are adopted;

[0042] In this embodiment, specifically: constructing the evaluation model also includes using cross-validation, regularization and other technologies to prevent the model from overfitting and improve the generalization ability of the model.

[0043] Working principle or structural principle: First, data collection is carried out to collect key parameter data such as voltage, current, temperature, internal resistance, etc. of the energy storage battery pack during the charging and discharging process. Then, the collected data is cleaned and preprocessed to remove noise and outliers to ensure the accuracy and reliability of the data. The wavelet transform improvement method is used to extract characteristic parameters that can reflect the health status of the battery pack, such as fluctuation amplitude characteristics and frequency distribution characteristics, from the preprocessed data. At this time, based on the extracted characteristic parameters, a support vector machine (SVM) or other suitable machine learning algorithm is used to build an evaluation model for the health status of the battery pack. When building the evaluation model, the model is trained by using battery pack data with known health status, and is tested through an independent data set. Verification ensures the accuracy and generalization ability of the model, and then inputs the real-time collected battery pack data into the trained evaluation model to obtain the health status evaluation results of the battery pack. At this time, judge whether the battery pack is in a healthy, sub-healthy or faulty state based on the evaluation results, and give corresponding processing suggestions. Finally, conduct an in-depth analysis of the evaluation results to understand the changing trends and potential problems of the battery pack health status, and formulate corresponding processing measures based on the evaluation results, such as repairing or replacing battery cells or the entire battery pack. When diagnosing the health status of the battery pack, regularly update and optimize the evaluation model to improve the accuracy and timeliness of the evaluation, introduce new data and technical means, and continuously improve the evaluation method to improve its applicability under complex working conditions.

[0044] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for diagnosing and evaluating the health status of an energy storage battery pack, characterized in that: The following steps are involved: Data collection, preprocessing, feature extraction, building evaluation models, real-time evaluation and status judgment, result analysis and processing; The data collection includes: S1: collecting key parameter data such as voltage, current, temperature, internal resistance, etc. of the energy storage battery pack during the charging and discharging process.

2. The method for diagnosing and evaluating the health status of an energy storage battery pack according to claim 1, characterized in that: The preprocessing includes: S2: cleaning and preprocessing the collected data to remove noise and outliers to ensure the accuracy and reliability of the data.

3. A method for diagnosing and evaluating the health status of an energy storage battery pack according to claim 2, characterized in that: The feature extraction includes: S3: using an improved wavelet transform method to extract characteristic parameters such as fluctuation amplitude characteristics and frequency distribution characteristics that can reflect the health status of the battery pack from the pre-processed data.

4. The method for diagnosing and evaluating the health status of an energy storage battery pack according to claim 3, characterized in that: The constructing of the evaluation model includes: S4 constructing an evaluation model of the health status of the battery pack using a support vector machine (SVM) or other suitable machine learning algorithm based on the extracted feature parameters; S5: The model is trained using battery pack data with known health status and validated using an independent dataset to ensure the accuracy and generalization of the model.

5. The method for diagnosing and evaluating the health status of an energy storage battery pack according to claim 4, characterized in that: The real-time evaluation and status judgment include: S6: inputting the real-time collected battery pack data into the trained evaluation model to obtain the health status evaluation result of the battery pack, where the health status = f(V(t), I(t), T(t), R(t)), where V(t) is the voltage of the battery pack at time tt, I(t) is the current of the battery pack at time t, T(t) is the temperature of the battery pack at time t, and R(t) is the internal resistance of the battery pack at time t. S7: Determine whether the battery pack is in a healthy, sub-healthy or faulty state based on the evaluation results, and give corresponding treatment suggestions.

6. A method for diagnosing and evaluating the health status of an energy storage battery pack according to claim 5, characterized in that: The result analysis and processing includes: S8: conducting an in-depth analysis of the evaluation results to understand the changing trend and potential problems of the health status of the battery pack; S9: Develop appropriate treatment measures based on the evaluation results, such as repairing or replacing battery cells or the entire battery pack.

7. A method for diagnosing and evaluating the health status of an energy storage battery pack according to claim 6, characterized in that: The evaluation method also includes optimization and improvement, which includes: regularly updating and optimizing the evaluation model, improving the accuracy and timeliness of the evaluation, introducing new data and technical means, and constantly improving the evaluation method to improve its applicability under complex working conditions.

8. The method for diagnosing and evaluating the health status of an energy storage battery pack according to claim 7, characterized in that: The data processing also includes adopting corresponding data standardization or normalization methods for different types of data to ensure data consistency, wherein the calculation formula for data standardization is: The calculation formula for data normalization is:

9. A method for diagnosing and evaluating the health status of an energy storage battery pack according to claim 8, characterized in that: The data collection also includes using data fusion technology to fuse the pre-processed multi-source data to form a feature vector that comprehensively reflects the health status of the battery pack; In the process of data fusion, the correlation and complementarity between different data sources are considered, and methods such as weighted fusion, feature-level fusion or decision-level fusion are adopted.

10. A method for diagnosing and evaluating the health status of an energy storage battery pack according to claim 9, characterized in that: The construction of the evaluation model also includes adopting cross-validation, regularization and other techniques to prevent the model from overfitting and improve the generalization ability of the model.

Images