Battery performance detection system based on big data analysis

Abstract

The invention discloses a battery performance detection system based on big data analysis, which relates to the technical field of battery performance detection and comprises a data acquisition module, a data transmission module, a battery analysis module and a user interaction module. The method can plan the replacement or maintenance plan of the battery in advance, optimizes the operation cost and reliability of energy storage, can track the degradation process of the battery performance along with time and use conditions, and helps an enterprise to know the performance of a battery product in actual use in advance. Meanwhile, the product design and the production process can be timely adjusted for enterprises, and the product quality is improved; for a user, the use and maintenance of the battery can be better arranged, and the effective service cycle of the battery is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of battery performance detection, and in particular to a battery performance detection system based on big data analysis. Background Art

[0002] With the rapid development of new energy vehicles, energy storage systems and other industries, batteries, as key components, have a direct impact on the reliability, safety and economy of the entire system. For example, in new energy vehicles, battery performance indicators such as range and charging and discharging efficiency are the focus of consumer attention and one of the key factors in the development of the industry. It is estimated that by 2025, retired batteries will reach 93GWh, and the number of retired battery packs will exceed 1 million per year. Retired batteries have high residual capacity and reuse value, but their performance needs to be accurately evaluated to achieve cascade utilization and maximize value, while avoiding environmental pollution and waste of resources. Therefore, the demand for battery performance testing is becoming increasingly urgent to ensure the quality and performance of these new energy products.

[0003] At present, the battery performance detection often adopts voltage detection: simple operation and low cost, but it can only reflect the static voltage state of the battery, and cannot fully evaluate the key indicators such as battery capacity, internal resistance, charge and discharge performance, and cannot accurately judge the performance and life of the battery in actual work. And internal resistance detection: it can indirectly reflect the health of the battery, but the measurement of internal resistance is affected by many factors, such as temperature, charge and discharge status, etc., and the internal resistance standards of batteries of different types and specifications are different, requiring professional equipment and technicians to operate, and the accuracy and reliability of the measurement results need to be improved. Another example is load testing: it can be closer to the actual working situation and evaluate the performance of the battery under load, but the operation is relatively complicated, requiring professional equipment and certain technical knowledge. And the selection of load needs to accurately match the specifications and usage scenarios of the battery, otherwise the test results may be inaccurate. However, its detection standards mostly focus on the static performance indicators of the battery, and lack clear specifications and requirements for the performance changes and safety assessment of the battery during dynamic use. With the increasing complexity and diversity of battery application scenarios, it is necessary to establish more complete dynamic detection standards to ensure the safe and reliable operation of batteries.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In view of the problems in the related art, the present invention proposes a battery performance detection system based on big data analysis to overcome the above-mentioned technical problems existing in the existing related art.

[0006] The technical solution of the present invention is achieved in this way:

[0007] A battery performance detection system based on big data analysis includes: a data acquisition module, a data transmission module, a battery analysis module and a user interaction module, wherein;

[0008] The data acquisition module collects influencing factors of the current battery in advance through a preset acquisition terminal, wherein the influencing factors at least include: initial capacity of the battery, number of charge and discharge times, charge and discharge rate, operating temperature and storage time;

[0009] The data transmission module transmits the collected impact factors to the battery analysis module;

[0010] The battery analysis module is used to construct a linear regression model to predict the battery performance of the influencing factors and obtain the prediction results, which at least include: predicting the remaining life and predicting the capacity attenuation trend;

[0011] The user interaction module is used to perform visual presentation based on the prediction results.

[0012] Furthermore, a linear regression model is constructed, including the following steps:

[0013] Pre-acquire samples containing influencing factors and corresponding battery remaining life and capacity attenuation data, including: calibrating n samples, each sample can be expressed as: (x i1 ,x i2 ,…,x ip ,y i1 ,y i2 );

[0014] Among them, x ij represents the jth impact factor of the i-th sample, y i1 represents the remaining battery life of the i-th sample, y i2 Indicates the battery capacity attenuation degree of the i-th sample;

[0015] Construct a remaining life prediction model and a capacity attenuation trend prediction model.

[0016] Furthermore, a remaining life prediction model is constructed, including the following steps:

[0017] Pre-calibrate the remaining battery life 1 With p impact factors x 1 ,x 2 ,…,x p The linear relationship between them can be expressed as:

[0018] y 1i =β 01 +β 11 x i1 +β 21 xi2 +…+β p1 x ip + ∈ 1i ;

[0019] Among them, β 01, β 11, … , β p1 is the estimated coefficient, ∈ 1i is the error term.

[0020] Furthermore, the following steps are included: calibrating the remaining life model parameter estimation, expressed as:

[0021]

[0022] Get the normal equations: Where X is an n×(p+1) matrix, is the estimated coefficient vector.

[0023] Furthermore, a capacity decay trend prediction model is constructed, including the following steps:

[0024] Calibrate battery capacity decay y 2 With p impact factors x 1 ,x 2 ,…,x p The linear relationship between them can be expressed as:

[0025] y 2i =β 02 +β 12 x i1 +β 22 x i2 +…+β p2 x ip +∈ 2i .

[0026] Furthermore, the parameters of the calibration capacity decay trend model are estimated and expressed as:

[0027]

[0028] Get the normal equations: For estimating the coefficient vector

[0029] Further, the obtaining of prediction results includes: predicting battery performance for influencing factors, including: predicting remaining life and predicting capacity attenuation trend;

[0030] Among them, the remaining life prediction is carried out. The value of the influencing factor of the battery data is preprocessed and substituted into the remaining life prediction model to obtain the predicted value of the remaining life of the battery It is expressed as:

[0031]

[0032] Among them, the capacity attenuation trend is predicted. Similarly, the influencing factors of the battery data are substituted into the capacity attenuation trend prediction model to obtain the predicted value of the battery capacity attenuation trend. It is expressed as:

[0033]

[0034] Beneficial effects of the present invention:

[0035] The present invention collects the influencing factors of the current battery through a preset collection terminal, and transmits the collected influencing factors to the battery analysis module. The battery analysis module constructs a linear regression model to predict the battery performance of the influencing factors, and obtains the prediction results. At the same time, it presents the prediction results visually, realizing high-precision detection of battery performance. It can more comprehensively reflect the real state of the battery than the traditional single-dimensional detection method. It can not only plan the replacement or maintenance plan of the battery in advance, optimize the operating cost and reliability of energy storage, but also track the degradation process of battery performance over time and usage, helping enterprises to understand the performance of battery products in actual use in advance. At the same time, enterprises can adjust product design and production processes in time to improve product quality; for users, they can better arrange the use and maintenance of batteries and extend the effective use cycle of batteries.

[0036] In addition, evaluating the performance and remaining life of batteries provides a scientific basis for the cascade utilization of retired batteries, screens out retired batteries suitable for different application scenarios, gives full play to their residual value, improves the economic benefits and resource utilization of the battery recycling industry, and also helps reduce the pollution of the environment by waste batteries. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 is a schematic diagram of the principle of a battery performance detection system based on big data analysis according to an embodiment of the present invention;

[0039] Figure 2 It is a flow chart of a battery performance detection system based on big data analysis according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the accompanying 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 belong to the scope of protection of the present invention.

[0041] According to an embodiment of the present invention, a battery performance detection system based on big data analysis is provided.

[0042] like Figure 1-Figure 2 As shown, the battery performance detection system based on big data analysis according to an embodiment of the present invention includes: a data acquisition module 1, a data transmission module 2, a battery analysis module 3 and a user interaction module 4, wherein;

[0043] The data acquisition module 1 collects the influencing factors of the current battery in advance through a preset acquisition terminal, wherein the influencing factors at least include: the initial capacity of the battery, the number of charge and discharge times, the charge and discharge rate, the operating temperature and the storage time;

[0044] This technical solution, for the above-mentioned acquisition terminal, can adopt voltage acquisition terminal, current acquisition terminal, temperature acquisition terminal, internal resistance acquisition terminal and intelligent charge and discharge comprehensive tester. Specifically:

[0045] The voltage acquisition terminal, whose battery voltage is a key parameter, can reflect the remaining power of the battery, the charging and discharging status and many other information. The voltage acquisition terminal can accurately measure the potential difference between the positive and negative electrodes of the battery. For example, in the lithium battery management system, the battery cell voltage can be obtained in real time through a high-precision voltage acquisition chip, and the general measurement accuracy can reach ±1mV or even higher.

[0046] Current acquisition terminal: used to measure the current during the battery charging and discharging process. By detecting the current, the battery's charge and discharge rate, remaining power combined with voltage and other parameters can be calculated. Generally, a shunt or Hall effect sensor is used to achieve current acquisition. The Hall effect current sensor has the advantages of high precision and good isolation performance, and can accurately measure the battery charging and discharging current.

[0047] Temperature acquisition terminal: Temperature has a crucial impact on the performance and life of the battery. The temperature acquisition terminal can monitor the temperature of the battery surface or inside in real time in some batteries with built-in temperature sensors. Commonly used temperature sensors are thermistors NTC or PTC and thermocouples. Thermistors have the characteristics of low cost and high accuracy. They can change their own resistance value according to temperature changes, so that the temperature changes can be detected by the acquisition terminal.

[0048] Internal resistance acquisition terminal: Battery internal resistance is an important indicator to measure battery performance, which includes ohmic internal resistance and polarization internal resistance. The internal resistance acquisition terminal can measure the battery internal resistance by AC injection method or DC pulse method. The AC injection method is to inject a small AC signal into the battery, then measure the voltage and current response at both ends of the battery, and calculate the battery internal resistance.

[0049] Intelligent charge and discharge comprehensive tester: It can set parameters such as voltage, current, time, capacity, etc., automatically complete the test and monitoring of various parameters of the battery pack, and can monitor and display all test data online in real time, including current, battery pack voltage, single cell voltage, time, capacity, etc., and then obtain the initial capacity of the battery. By setting the upper and lower limits of the discharge / charge current, duration, capacity and voltage, the discharge and charge process can be cycled once, thereby recording the number of charge and discharge times. In addition, it can also realize the control and monitoring of the charge and discharge rate, and test at different charge and discharge rates to obtain the performance data of the battery under various working conditions.

[0050] Data transmission module 2 transmits the collected influencing factors to battery analysis module 3;

[0051] In this technical solution, the transmission method can adopt CAN bus, Ethernet, ZigBee, etc., to ensure that data can be transmitted stably and quickly to meet real-time requirements.

[0052] The battery analysis module 3 is used to construct a linear regression model to predict the battery performance of the influencing factors and obtain the prediction results, which at least include: predicting the remaining life and predicting the capacity attenuation trend;

[0053] Among them, building a linear regression model includes the following steps:

[0054] Pre-acquire samples containing influencing factors and corresponding battery remaining life and capacity attenuation data, including: calibrating n samples, each sample can be expressed as: (x i1 ,x i2 ,…,x ip ,y i1 ,y i2 );

[0055] Among them, x ij represents the jth impact factor of the i-th sample, y i1 represents the remaining battery life of the i-th sample, y i2 Indicates the battery capacity attenuation degree of the i-th sample;

[0056] Construct a remaining life prediction model and a capacity attenuation trend prediction model. Specifically:

[0057] Among them, building a remaining life prediction model includes the following steps:

[0058] Pre-calibrate the remaining battery life 1 With p impact factors x 1 ,x 2 ,…,x p The linear relationship between them can be expressed as:

[0059] y 1i =β 01 +β 11 x i1 +β 21 x i2 +…+β p1 x ip +∈ 1i ;

[0060] Among them, β 01, β 11, … , β p1 is the estimated coefficient, ∈ 1i is the error term.

[0061] Among them, building a capacity attenuation trend prediction model includes the following steps:

[0062] Calibrate battery capacity decay y 2 With p impact factors x 1 ,x 2 ,…,x p The linear relationship between them can be expressed as:

[0063] y 2i =β 02 +β 12 x i1 +β 22 x i2 +…+β p2 x ip +∈ 2i .

[0064] Perform calibration model parameter estimation, which at least includes: calibration remaining life model parameter estimation and capacity decay trend model parameter estimation, specifically:

[0065] Among them, the remaining life model parameter estimation is calibrated. For the remaining life prediction model, the goal is to minimize the sum of squared errors, which is expressed as:

[0066]

[0067] This technical solution, through S 1 (β 1 ) for β 1Taking the partial derivative of and setting it to 0, we get the normal equation: Where X is an n×(p+1) matrix, with the first column all set to 1, representing β 01 , is the estimated coefficient vector.

[0068] Among them, the calibration capacity attenuation trend model parameter estimation includes:

[0069] Similarly, for the capacity decay trend prediction model, the sum of squared errors is minimized, expressed as:

[0070]

[0071] Get the normal equations: For estimating the coefficient vector

[0072] In addition, the battery performance is predicted based on the influencing factors, including: remaining life prediction and capacity attenuation trend prediction, specifically:

[0073] Among them, the remaining life prediction is carried out. The value of the influencing factor of the battery data is preprocessed and substituted into the remaining life prediction model to obtain the predicted value of the remaining life of the battery It is expressed as:

[0074]

[0075] Among them, the capacity attenuation trend is predicted. Similarly, the influencing factors of the battery data are substituted into the capacity attenuation trend prediction model to obtain the predicted value of the battery capacity attenuation trend. It is expressed as:

[0076]

[0077] Specifically, the above capacity attenuation trend prediction includes the following steps:

[0078] If the predicted value If it is positive, it means that the capacity is decreasing;

[0079] If the predicted value If it is negative, it may indicate that the model is abnormal or that the capacity has a tendency to recover under special circumstances. In practical applications, this situation is rare and requires further analysis, which will not be elaborated here.

[0080] User interaction module 4, used for visual presentation based on prediction results;

[0081] In this technical solution, users can view the real-time prediction results of the battery through this interface, and perform operations such as setting parameters for the preset acquisition terminal and starting the detection task.

[0082] In addition, when applied, it also includes: a data storage module 5, which is used to adopt distributed storage for the prediction results;

[0083] This technical solution can use the Hadoop distributed file system HDFS to efficiently store and manage battery influencing factors and prediction results.

[0084] Specifically, during application, the data storage module 5 can also store historical data for long-term analysis and comparison.

[0085] In summary, with the help of the above technical solution of the present invention, the following effects can be achieved:

[0086] The present invention collects the influencing factors of the current battery through a preset collection terminal, and transmits the collected influencing factors to the battery analysis module 3. The battery analysis module 3 constructs a linear regression model to predict the battery performance of the influencing factors, and obtains the prediction results. At the same time, it presents the prediction results visually, realizing high-precision detection of battery performance. It can more comprehensively reflect the real state of the battery than the traditional single-dimensional detection method. It can not only plan the replacement or maintenance plan of the battery in advance, optimize the operating cost and reliability of energy storage, but also track the degradation process of battery performance over time and usage, helping enterprises to understand the performance of battery products in actual use in advance. At the same time, enterprises can adjust product design and production processes in time to improve product quality; for users, they can better arrange the use and maintenance of batteries and extend the effective use cycle of batteries.

[0087] In addition, evaluating the performance and remaining life of batteries provides a scientific basis for the cascade utilization of retired batteries, screens out retired batteries suitable for different application scenarios, gives full play to their residual value, improves the economic benefits and resource utilization of the battery recycling industry, and also helps reduce the pollution of the environment by waste batteries.

[0088] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. After considering the disclosure of the specification and the examples, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and the examples are only regarded as exemplary, and the true scope and spirit of the present disclosure are indicated by the claims.

[0089] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A battery performance detection system based on big data analysis, characterized in that: include: A data acquisition module (1), a data transmission module (2), a battery analysis module (3) and a user interaction module (4), wherein; The data acquisition module (1) collects influencing factors of the current battery in advance through a preset acquisition terminal, wherein the influencing factors at least include: initial capacity of the battery, number of charge and discharge times, charge and discharge rate, operating temperature and storage time; The data transmission module (2) transmits the collected impact factors to the battery analysis module (3); The battery analysis module (3) is used to construct a linear regression model to predict the battery performance of the influencing factors and obtain the prediction results, which at least include: predicting the remaining life and predicting the capacity attenuation trend; The user interaction module (4) is used to perform visual presentation based on the prediction results.

2. The battery performance detection system based on big data analysis according to claim 1 is characterized in that: Building a linear regression model includes the following steps: Pre-acquire samples containing influencing factors and corresponding battery remaining life and capacity attenuation data, including: calibrating n samples, each sample can be expressed as: (x i1 ,x i2 ,…,x ip ,y i1 ,y i2 ); Among them, x ij represents the jth impact factor of the i-th sample, y i1 represents the remaining battery life of the i-th sample, y i2 Indicates the battery capacity attenuation degree of the i-th sample; Construct a remaining life prediction model and a capacity attenuation trend prediction model.

3. The battery performance detection system based on big data analysis according to claim 2 is characterized in that: Building a remaining life prediction model includes the following steps: Pre-calibrate the remaining battery life y1 and p influencing factors x1, x2, ..., x p The linear relationship between them can be expressed as: y 1i =b 01 +b 11 x i1 +b 21 x i2 +…+b p1 x ip +∈ 1i ; Among them, β 01 ,β 11 ,…,β p1 is the estimated coefficient, ∈ 1i is the error term.

4. The battery performance detection system based on big data analysis according to claim 3 is characterized in that: The following steps are also included: The parameter estimation of the calibrated remaining life model is expressed as: Get the normal equations: Where X is an n×(p+1) matrix, is the estimated coefficient vector.

5. The battery performance detection system based on big data analysis according to claim 2 is characterized in that: Building a capacity decay trend prediction model includes the following steps: Calibrate battery capacity attenuation y2 and p influencing factors x1, x2, …, x p The linear relationship between them can be expressed as: y 2i =b 02 +b 12 x i1 +b 22 x i2 +…+b p2 x ip +∈ 2i 。 6. The battery performance detection system based on big data analysis according to claim 5, characterized in that: The parameter estimation of the calibration capacity decay trend model is expressed as: Get the normal equations: For estimating the coefficient vector 7. The battery performance detection system based on big data analysis according to claim 1, characterized in that: The obtaining of prediction results includes: predicting battery performance for influencing factors, including: predicting remaining life and predicting capacity attenuation trend; Among them, the remaining life prediction is carried out. The value of the influencing factor of the battery data is preprocessed and substituted into the remaining life prediction model to obtain the predicted value of the remaining life of the battery It is expressed as: Among them, the capacity attenuation trend is predicted. Similarly, the influencing factors of the battery data are substituted into the capacity attenuation trend prediction model to obtain the predicted value of the battery capacity attenuation trend. It is expressed as:

Images