Intelligent test method and system for BMS lithium battery protection board

Abstract

The invention relates to the technical field of lithium batteries, in particular to an intelligent test method and system for a BMS lithium battery protection board. Matching in the knowledge base according to the actual identification area image to obtain a preset test scheme for testing the BMS lithium battery protection board to be tested and a preset test parameter set of various test parameters in the test process; controlling the test work station to test the BMS lithium battery protection board to be tested according to a preset test scheme; clustering the actual test parameters fed back by the to-be-tested BMS lithium battery protection board to obtain an actual test parameter set of various test parameters of the to-be-tested BMS lithium battery protection board in the test process; performing similarity analysis on the actual test parameter set of the various test parameters and a preset test parameter set; and according to the state conditions of various test parameters of the to-be-tested BMS lithium battery protection board in the test process, a test result is generated, automation and standardization of the BMS lithium battery protection board test process are realized, and the test accuracy and the test efficiency are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of lithium batteries, and in particular to a BMS lithium battery protection board intelligent testing method and system. Background Art

[0002] The BMS lithium battery protection board is a device used to protect lithium-ion batteries. Its main function is to monitor the battery status, such as voltage, current, temperature, etc., and to promptly cut off the battery's charge and discharge circuit when the battery is overcharged, over-discharged, over-current, short-circuited, etc., to prevent battery damage or safety accidents. The BMS lithium battery protection board is usually composed of a battery management chip, a MOSFET switch tube, a current sensor, a voltage sensor, a temperature sensor, etc. The BMS lithium battery protection board can be connected to the battery pack and controlled according to the preset protection strategy.

[0003] With the continuous expansion of lithium battery application fields and the growing market demand, the existing BMS lithium battery protection board testing methods face some technical obstacles: First, traditional testing equipment and methods are often unable to comprehensively and accurately test the various test parameters of the BMS lithium battery protection board, which makes the test results unable to fully reflect the actual performance of the BMS, resulting in the accuracy and reliability of the test results being affected. Secondly, when dealing with large-scale, high-concurrency test tasks, existing test methods often face bottlenecks in data processing and analysis, and the test efficiency is low, making it difficult to meet the needs of modern battery production and application. Summary of the invention

[0004] In order to overcome the technical barriers of the above-mentioned BMS lithium battery protection board testing method, the present invention provides a BMS lithium battery protection board intelligent testing method and system.

[0005] To achieve the above object, the present invention discloses a BMS lithium battery protection board intelligent testing method, comprising the following steps: Acquire an actual identification area image of the BMS lithium battery protection board to be tested, and obtain a preset test scheme for testing the BMS lithium battery protection board to be tested and a preset test parameter set of various test parameters during the test process by matching the actual identification area image in the knowledge base; Send the preset test plan to the controller of the test station, control the test station to test the BMS lithium battery protection board to be tested according to the preset test plan, and obtain the actual test parameters fed back by the BMS lithium battery protection board to be tested at each preset test time node; After the test is completed, the actual test parameters fed back by the BMS lithium battery protection board to be tested are clustered to obtain the actual test parameter set of various test parameters of the BMS lithium battery protection board to be tested during the test process; Perform similarity analysis on the actual test parameter set and the preset test parameter set of various test parameters, and analyze the status of various test parameters of the BMS lithium battery protection board to be tested during the test process; Generate test results according to the status of various test parameters of the BMS lithium battery protection board to be tested during the test process, and transfer the BMS lithium battery protection board to be tested to the corresponding production center according to the test results; Among them, the test parameters include the operating voltage, operating current, operating temperature, anti-interference ability, short-circuit protection response speed, over-temperature protection response speed, over-charge protection response speed and over-discharge protection response speed of the BMS lithium battery protection board.

[0006] More specifically, a preset test scheme for testing the BMS lithium battery protection board to be tested and a preset test parameter set of various test parameters during the test are obtained by matching the actual identification area image in the knowledge base, specifically: Obtain the characteristic identification area images of various specifications of BMS lithium battery protection boards in the production workshop, and formulate preset test plans for testing various specifications of BMS lithium battery protection boards; And formulate preset test parameter sets for various test parameters in the test process of BMS lithium battery protection boards of various specifications through corresponding preset test schemes; Construct a knowledge base, and divide the knowledge base into a plurality of storage spaces, and store the characteristic identification area images, preset test schemes, and preset test parameter sets of various test parameters of the same specification of BMS lithium battery protection board in the corresponding storage spaces respectively; Obtain an actual identification area image of the BMS lithium battery protection board to be tested, calculate the cosine similarity between the actual identification area image and the characteristic identification area image in each storage space, and obtain a plurality of cosine similarities; Constructing a size sorting table, and performing size sorting processing on a plurality of cosine similarities through the size sorting table to sort out the maximum cosine similarity; Acquire the actual identification area image corresponding to the maximum cosine similarity, and locate the storage space of the actual identification area image corresponding to the maximum cosine similarity in the knowledge base; The corresponding preset test scheme and the preset test parameter set of various test parameters are extracted from the located storage space, so as to match the preset test scheme for testing the BMS lithium battery protection board to be tested and the preset test parameter set of various test parameters during the test process.

[0007] More specifically, the actual test parameters fed back by the BMS lithium battery protection board to be tested are clustered to obtain the actual test parameter set of various test parameters of the BMS lithium battery protection board to be tested during the test process, specifically: Based on the principal component analysis method, the actual test parameters fed back by the BMS lithium battery protection board to be tested are mapped into a two-dimensional space, so that each actual test parameter is represented in the form of a point in the two-dimensional space, and a number of parameter points are obtained; Count the total number of other parameter points existing in the preset neighborhood range of each parameter point in the two-dimensional space; If the total number of other parameter points in the preset neighborhood of a parameter point in the two-dimensional space is greater than the preset number of points, the parameter point is marked as a core point; if the total number of other parameter points in the preset neighborhood of a parameter point in the two-dimensional space is not greater than the preset number of points, the parameter point is marked as a non-core point By analogy, all parameter points in the two-dimensional space are traversed to mark each parameter point in the two-dimensional space as a core point or a non-core point; Calculate the Euclidean distance between each non-core point and the core point, and divide each non-core point into a preset neighborhood of the core point with the closest Euclidean distance; After all non-core points are divided, each core point and its non-core points in the preset area are regarded as a parameter clustering set, and several parameter clustering sets are obtained. Each parameter clustering set is evaluated and corrected to obtain a clustering result. According to the clustering result, an actual test parameter set of various test parameters of the BMS lithium battery protection board to be tested during the test process is obtained.

[0008] More specifically, each parameter clustering set is evaluated and corrected to obtain a clustering result, which is: Calculate the silhouette coefficient of each parameter cluster set, and compare the silhouette coefficient of each parameter cluster set with a preset value; If the silhouette coefficient of a parameter clustering set is greater than or equal to a preset value, it means that the compactness of the parameter clustering set meets the standard, and the clustering effect state of the parameter clustering set is marked as normal; If the silhouette coefficient of a parameter clustering set is less than the preset value, it means that the compactness of the parameter clustering set does not meet the standard, and the clustering effect state of the parameter clustering set is marked as abnormal; Obtain parameter clustering sets whose clustering effect states are marked as abnormal states, which are defined as parameter clustering sets to be corrected; calculate the Pearson correlation coefficients between each non-core point and the core point in each parameter clustering set to be corrected; If the Pearson correlation coefficient between a non-core point and a core point in a parameter cluster set to be corrected is not greater than a preset coefficient threshold, the non-core point is demarcated from the parameter cluster set to be corrected, and the demarcated non-core point is marked as a cluster abnormal non-core point; Calculate the Pearson correlation coefficient between the cluster abnormal non-core point and the core points in the remaining parameter clustering sets to be corrected; if the Pearson correlation coefficient between the cluster abnormal non-core point and the core points in the remaining parameter clustering sets to be corrected is not greater than the preset coefficient threshold, then mark the cluster abnormal non-core point as a noise point and completely delete the noise point; If the Pearson correlation coefficient between the cluster abnormal non-core point and one or more core points in the remaining parameter clustering sets to be corrected is greater than the preset coefficient threshold, the cluster abnormal non-core point is reclassified into the parameter clustering set to be corrected with the largest Pearson correlation coefficient; Repeat the above steps until the cluster abnormal non-core points in each parameter cluster set to be corrected are identified and all cluster abnormal non-core points are corrected, then complete the evaluation and correction process for each parameter cluster set and output the clustering results.

[0009] More specifically, a similarity analysis is performed on the actual test parameter set and the preset test parameter set of various test parameters, and the status of various test parameters of the BMS lithium battery protection board to be tested during the test is analyzed, specifically: Calculate the Jaccard similarity coefficient between the actual test parameter set and the preset test parameter set for various test parameters; and compare the Jaccard similarity coefficient between the actual test parameter set and the preset test parameter set for various test parameters with the preset similarity coefficient; If the Jaccard similarity coefficient between the actual test parameter set and the preset test parameter set of a certain test parameter is greater than the preset similarity coefficient, the test parameter of the BMS lithium battery protection board to be tested is marked as normal; If the Jaccard similarity coefficient between the actual test parameter set and the preset test parameter set of a certain test parameter is not greater than the preset similarity coefficient, the test parameter of the BMS lithium battery protection board to be tested is marked as an abnormal state.

[0010] More specifically, the test results are generated according to the status of various test parameters of the BMS lithium battery protection board to be tested during the test process, and the BMS lithium battery protection board to be tested is transferred to the corresponding production center according to the test results, specifically: Obtain the status of various test parameters of the BMS lithium battery protection board under test during the test process; If the states of various test parameters of the BMS lithium battery protection board to be tested are all normal during the test process, the BMS lithium battery protection board to be tested is marked as a qualified product, and a first test result is generated, and the BMS lithium battery protection board marked as a qualified product is transferred to the packaging center; If at least one test parameter of the BMS lithium battery protection board to be tested is in an abnormal state during the test process, the BMS lithium battery protection board to be tested is marked as unqualified, and a second test result is generated, and the BMS lithium battery protection board marked as unqualified is transferred to a repair center.

[0011] In addition, to achieve the above-mentioned purpose, the present invention also discloses a BMS lithium battery protection board intelligent testing system, the BMS lithium battery protection board intelligent testing system comprises a memory and a processor, the memory stores a BMS lithium battery protection board intelligent testing method program, when the BMS lithium battery protection board intelligent testing method program is executed by the processor, the following steps are implemented: Acquire an actual identification area image of the BMS lithium battery protection board to be tested, and obtain a preset test scheme for testing the BMS lithium battery protection board to be tested and a preset test parameter set of various test parameters during the test process by matching the actual identification area image in the knowledge base; Send the preset test plan to the controller of the test station, control the test station to test the BMS lithium battery protection board to be tested according to the preset test plan, and obtain the actual test parameters fed back by the BMS lithium battery protection board to be tested at each preset test time node; After the test is completed, the actual test parameters fed back by the BMS lithium battery protection board to be tested are clustered to obtain the actual test parameter set of various test parameters of the BMS lithium battery protection board to be tested during the test process; Perform similarity analysis on the actual test parameter set and the preset test parameter set of various test parameters, and analyze the status of various test parameters of the BMS lithium battery protection board to be tested during the test process; Generate test results according to the status of various test parameters of the BMS lithium battery protection board to be tested during the test process, and transfer the BMS lithium battery protection board to be tested to the corresponding production center according to the test results; Among them, the test parameters include the operating voltage, operating current, operating temperature, anti-interference ability, short-circuit protection response speed, over-temperature protection response speed, over-charge protection response speed and over-discharge protection response speed of the BMS lithium battery protection board.

[0012] The present invention solves the technical defects existing in the background technology, and has the following beneficial effects: a preset test scheme for testing the BMS lithium battery protection board to be tested and a preset test parameter set of various test parameters during the test process are obtained by matching in a knowledge base according to an actual identification area image; the test station is controlled to test the BMS lithium battery protection board to be tested according to the preset test scheme; the actual test parameters fed back by the BMS lithium battery protection board to be tested are clustered to obtain the actual test parameter set of various test parameters of the BMS lithium battery protection board to be tested during the test process; the actual test parameter set of various test parameters and the preset test parameter set are analyzed for similarity; the test results are generated according to the status of various test parameters of the BMS lithium battery protection board to be tested during the test process, and the BMS lithium battery protection board to be tested is transferred to the corresponding production center according to the test results. The method realizes the automation and standardization of the BMS lithium battery protection board test process, and effectively improves the test accuracy and test efficiency of the BMS lithium battery protection board. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] 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 or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0014] Figure 1 This is a flow chart of the overall method of an intelligent testing method for a BMS lithium battery protection board; Figure 2 This is a partial method flow chart of a BMS lithium battery protection board intelligent testing method; Figure 3 The system block diagram of a BMS lithium battery protection board intelligent test system. DETAILED DESCRIPTION

[0015] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0016] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0017] like Figure 1 As shown, the present invention discloses a BMS lithium battery protection board intelligent testing method, comprising the following steps: S102: Acquire an actual identification area image of the BMS lithium battery protection board to be tested, and obtain a preset test scheme for testing the BMS lithium battery protection board to be tested and a preset test parameter set of various test parameters during the test process by matching the actual identification area image in a knowledge base; S104: Sending the preset test plan to the controller of the test station, controlling the test station to test the BMS lithium battery protection board to be tested according to the preset test plan, and obtaining the actual test parameters fed back by the BMS lithium battery protection board to be tested at each preset test time node; S106: After the test is completed, clustering is performed on the actual test parameters fed back by the BMS lithium battery protection board to be tested, so as to obtain an actual test parameter set of various test parameters of the BMS lithium battery protection board to be tested during the test process; S108: performing similarity analysis on the actual test parameter set and the preset test parameter set of various test parameters, and analyzing to obtain the status of various test parameters of the BMS lithium battery protection board to be tested during the test process; S110: Generate test results according to the status of various test parameters of the BMS lithium battery protection board to be tested during the test process, and transfer the BMS lithium battery protection board to be tested to the corresponding production center according to the test results; Among them, the test parameters include the operating voltage, operating current, operating temperature, anti-interference ability, short-circuit protection response speed, over-temperature protection response speed, over-charge protection response speed and over-discharge protection response speed of the BMS lithium battery protection board.

[0018] It should be noted that the identification area is a characteristic area used to identify the model and specifications of the BMS lithium battery protection board, such as a QR code area, a barcode area, and a nameplate area.

[0019] More specifically, a preset test scheme for testing the BMS lithium battery protection board to be tested and a preset test parameter set of various test parameters during the test are obtained by matching the actual identification area image in the knowledge base, specifically: Obtain the characteristic identification area images of various specifications of BMS lithium battery protection boards in the production workshop, and formulate preset test plans for testing various specifications of BMS lithium battery protection boards; And formulate preset test parameter sets for various test parameters in the test process of BMS lithium battery protection boards of various specifications through corresponding preset test schemes; Construct a knowledge base, and divide the knowledge base into a plurality of storage spaces, and store the characteristic identification area images, preset test schemes, and preset test parameter sets of various test parameters of the same specification of BMS lithium battery protection board in the corresponding storage spaces respectively; Obtain an actual identification area image of the BMS lithium battery protection board to be tested, calculate the cosine similarity between the actual identification area image and the characteristic identification area image in each storage space, and obtain a plurality of cosine similarities; Constructing a size sorting table, and performing size sorting processing on a plurality of cosine similarities through the size sorting table to sort out the maximum cosine similarity; Acquire the actual identification area image corresponding to the maximum cosine similarity, and locate the storage space of the actual identification area image corresponding to the maximum cosine similarity in the knowledge base; The corresponding preset test scheme and the preset test parameter set of various test parameters are extracted from the located storage space, so as to match the preset test scheme for testing the BMS lithium battery protection board to be tested and the preset test parameter set of various test parameters during the test process.

[0020] It should be noted that, first, the characteristic identification area images of various specifications of BMS lithium battery protection boards are collected through image acquisition technology, and preset test plans for different specifications of BMS lithium battery protection boards are formulated by relevant technical personnel, such as the maximum current, average current and peak current settings for various specifications of BMS lithium battery protection boards when verifying the control ability of various specifications of BMS lithium battery protection boards during charging and discharging; such as the internal temperature setting of the battery when evaluating the control ability of various specifications of BMS lithium battery protection boards on battery temperature. And a preset test parameter set is established for each preset test plan by relevant technical personnel, such as the preset operating temperature, preset anti-interference ability, preset short-circuit protection response speed and preset over-temperature protection response speed of the BMS lithium battery protection board during the test.

[0021] The characteristic identification area images, preset test schemes and preset test parameter sets of various test parameters of BMS lithium battery protection boards of various specifications are stored in the corresponding storage space of the knowledge base. The construction of the knowledge base adopts a distributed storage method to ensure the organization and retrieval efficiency of information. When it is necessary to test the BMS lithium battery protection board to be tested, the system first obtains its actual identification area image. Then, by calculating the cosine similarity between the actual identification area image and all stored images in the knowledge base, the BMS lithium battery protection board with the same specifications as the BMS lithium battery protection board to be tested is found in the knowledge base. Among them, the calculation of cosine similarity is a commonly used text and image similarity measurement method, which can effectively compare the similarity of two images in the vector space. After finding the BMS lithium battery protection board with the same specifications, the preset test scheme and preset test parameter sets of various test parameters that match it are extracted from the knowledge base. In this way, the system can provide a highly personalized test plan for the BMS lithium battery protection board to be tested, ensuring that the test process is both efficient and accurate. This process not only saves time and resources in developing and implementing customized test solutions, but also improves the standardization and consistency of testing, helping to ensure the quality control of BMS lithium battery protection boards throughout the production process. In this way, the system can effectively manage a large number of test requirements while maintaining precise control of the test process for each product, effectively improving the efficiency and accuracy of BMS lithium battery protection board testing.

[0022] More specifically, the actual test parameters fed back by the BMS lithium battery protection board to be tested are clustered to obtain the actual test parameter set of various test parameters of the BMS lithium battery protection board to be tested during the test process, specifically: Based on the principal component analysis method, the actual test parameters fed back by the BMS lithium battery protection board to be tested are mapped into a two-dimensional space, so that each actual test parameter is represented in the form of a point in the two-dimensional space, and a number of parameter points are obtained; Count the total number of other parameter points existing in the preset neighborhood range of each parameter point in the two-dimensional space; If the total number of other parameter points in the preset neighborhood of a parameter point in the two-dimensional space is greater than the preset number of points, the parameter point is marked as a core point; if the total number of other parameter points in the preset neighborhood of a parameter point in the two-dimensional space is not greater than the preset number of points, the parameter point is marked as a non-core point By analogy, all parameter points in the two-dimensional space are traversed to mark each parameter point in the two-dimensional space as a core point or a non-core point; Calculate the Euclidean distance between each non-core point and the core point, and divide each non-core point into a preset neighborhood of the core point with the closest Euclidean distance; After all non-core points are divided, each core point and its non-core points in the preset area are regarded as a parameter clustering set, and several parameter clustering sets are obtained. Each parameter clustering set is evaluated and corrected to obtain a clustering result. According to the clustering result, an actual test parameter set of various test parameters of the BMS lithium battery protection board to be tested during the test process is obtained.

[0023] It should be noted that the principal component analysis method is used to map the multi-dimensional actual test parameters into a two-dimensional space, which simplifies the complexity of the parameters and makes each set of parameters represented as a point in the two-dimensional space. The principal component analysis method reduces the dimension of the original parameters through principal component analysis, while retaining the maximum variation information of the data, making the subsequent processing more intuitive and easy to understand.

[0024] In two-dimensional space, by counting the number of points in the preset neighborhood of each parameter point, the "importance" or "representativeness" of the point can be preliminarily judged. If a point has more other points in its preset neighborhood (that is, the total number of points is greater than the preset number of points), the point is regarded as a "core point", representing a set of relatively concentrated test parameter features; conversely, if a point has only a few points in its preset neighborhood, it is regarded as a "non-core point", representing a relatively sparse or marginal test parameter feature. Next, by calculating the Euclidean distance between the non-core point and the core point, the non-core point is divided into the preset neighborhood of the core point closest to it. This process further refines the parameter clustering process, making the clustering of the test parameters more accurate. Finally, all non-core points are clustered according to the core points to which they belong to form multiple parameter clustering sets. Then, by evaluating and correcting these clustering sets, the final clustering results can be obtained. This clustering result not only reflects the inherent structure of the test parameters, but also provides a summary and classification of various actual test parameter sets of the BMS lithium battery protection board to be tested during the test process, thereby completing the clustering process of the actual test parameters collected, such as clustering all the collected working currents into one parameter set, and clustering all the collected working temperatures into another parameter set. This method can not only effectively simplify and visualize multi-dimensional test parameters, but also reveal the inherent correlation and grouping characteristics between parameters through cluster analysis, providing strong data support for performance evaluation, fault diagnosis, and optimization and improvement of the BMS lithium battery protection board. Through the clustering results, various test parameters of the BMS lithium battery protection board to be tested can be compared and analyzed more quickly and accurately, which can effectively improve the test efficiency and the reliability of the test results.

[0025] More specifically, each parameter clustering set is evaluated and corrected to obtain a clustering result, which is: Calculate the silhouette coefficient of each parameter cluster set, and compare the silhouette coefficient of each parameter cluster set with a preset value; If the silhouette coefficient of a parameter clustering set is greater than or equal to a preset value, it means that the compactness of the parameter clustering set meets the standard, and the clustering effect state of the parameter clustering set is marked as normal; If the silhouette coefficient of a parameter clustering set is less than the preset value, it means that the compactness of the parameter clustering set does not meet the standard, and the clustering effect state of the parameter clustering set is marked as abnormal; Obtain parameter clustering sets whose clustering effect states are marked as abnormal states, which are defined as parameter clustering sets to be corrected; calculate the Pearson correlation coefficients between each non-core point and the core point in each parameter clustering set to be corrected; If the Pearson correlation coefficient between a non-core point and a core point in a parameter cluster set to be corrected is not greater than a preset coefficient threshold, the non-core point is demarcated from the parameter cluster set to be corrected, and the demarcated non-core point is marked as a cluster abnormal non-core point; Calculate the Pearson correlation coefficient between the cluster abnormal non-core point and the core points in the remaining parameter clustering sets to be corrected; if the Pearson correlation coefficient between the cluster abnormal non-core point and the core points in the remaining parameter clustering sets to be corrected is not greater than the preset coefficient threshold, then mark the cluster abnormal non-core point as a noise point and completely delete the noise point; If the Pearson correlation coefficient between the cluster abnormal non-core point and one or more core points in the remaining parameter clustering sets to be corrected is greater than the preset coefficient threshold, the cluster abnormal non-core point is reclassified into the parameter clustering set to be corrected with the largest Pearson correlation coefficient; Repeat the above steps until the cluster abnormal non-core points in each parameter cluster set to be corrected are identified and all cluster abnormal non-core points are corrected, then complete the evaluation and correction process for each parameter cluster set and output the clustering results.

[0026] It should be noted that the silhouette coefficient of each parameter clustering set is calculated, and the silhouette coefficient of each parameter clustering set is compared with the preset value to determine whether the compactness of each clustering set meets the standard, thereby marking the state of the clustering effect. The silhouette coefficient is an indicator to measure the quality and compactness of clustering. When the silhouette coefficient is greater than or equal to the preset value, it means that the compactness inside the clustering set meets the standard and the state is normal; otherwise, it means that the compactness inside the clustering set is insufficient and the state is abnormal. For the parameter clustering set marked as abnormal state, that is, the parameter clustering set to be corrected, the process is further analyzed in depth. First, the Pearson correlation coefficient between the non-core points and the core points in each clustering set to be corrected is calculated to identify those non-core points with low correlation with the core points, and mark them as clustering abnormal non-core points. Then, these clustering abnormal non-core points are further analyzed. If it is found that they have the same low correlation with the core points in other parameter clustering sets to be corrected, then these points are marked as noise points and completely deleted from the data set. On the contrary, if there is a high correlation between one or some parameter cluster sets to be corrected and these cluster abnormal non-core points, then these points will be reclassified into the parameter cluster set with the highest correlation to be corrected. The entire process iterates the above steps until all cluster abnormal non-core points are identified and appropriately corrected. Finally, the evaluation and correction processing of all parameter cluster sets is completed, and the corrected clustering results are output. This process not only improves the accuracy and reliability of cluster analysis, but also effectively eliminates noise data, ensuring the high quality and practicality of cluster results, thereby providing more reliable data support for subsequent analysis steps and further improving the reliability of test results.

[0027] More specifically, if Figure 2 As shown, the actual test parameter set of various test parameters and the preset test parameter set are analyzed for similarity, and the status of various test parameters of the BMS lithium battery protection board to be tested during the test process is obtained by analysis, specifically: S202: Calculate the Jaccard similarity coefficient between the actual test parameter set and the preset test parameter set for various test parameters; and compare the Jaccard similarity coefficient between the actual test parameter set and the preset test parameter set for various test parameters with the preset similarity coefficient; S204: If the Jaccard similarity coefficient between the actual test parameter set and the preset test parameter set of a certain test parameter is greater than the preset similarity coefficient, the test parameter of the BMS lithium battery protection board to be tested is marked as a normal state; S206: If the Jaccard similarity coefficient between the actual test parameter set and the preset test parameter set of a certain test parameter is not greater than the preset similarity coefficient, the test parameter of the BMS lithium battery protection board to be tested is marked as an abnormal state.

[0028] More specifically, the test results are generated according to the status of various test parameters of the BMS lithium battery protection board to be tested during the test process, and the BMS lithium battery protection board to be tested is transferred to the corresponding production center according to the test results, specifically: Obtain the status of various test parameters of the BMS lithium battery protection board under test during the test process; If the states of various test parameters of the BMS lithium battery protection board to be tested are all normal during the test process, the BMS lithium battery protection board to be tested is marked as a qualified product, and a first test result is generated, and the BMS lithium battery protection board marked as a qualified product is transferred to the packaging center; If at least one test parameter of the BMS lithium battery protection board to be tested is in an abnormal state during the test process, the BMS lithium battery protection board to be tested is marked as unqualified, and a second test result is generated, and the BMS lithium battery protection board marked as unqualified is transferred to a repair center.

[0029] It should be noted that the performance consistency and stability of the BMS lithium battery protection board are evaluated by calculating the Jaccard similarity coefficient (Jaccard similarity coefficient) between the two parameter sets. First, by calculating the Jaccard similarity coefficient between the actual test parameter set and the preset test parameter set, the degree of content matching between the two is measured. The Jaccard similarity coefficient is an indicator based on set theory, which is particularly suitable for comparing the ratio of the intersection and union of two types of data. The Jaccard similarity coefficient can intuitively reflect the degree of fit of the test parameter set on key indicators. Next, according to the comparison results of the calculated Jaccard similarity coefficient and the preset similarity coefficient, the test parameter status of the BMS lithium battery protection board is classified. If the similarity coefficient is higher than the preset threshold, it means that the actual test parameter set is highly consistent with the preset parameter set, which means that the performance of the test parameter of the BMS lithium battery protection board is good, and the status is marked as "normal" at this time; conversely, if the similarity coefficient is lower than the preset threshold, it means that there is a significant difference between the actual parameter set and the preset parameter set, which may mean that there is a problem with the performance of the test parameter of the BMS lithium battery protection board, and the status is marked as "abnormal". Based on the above test results, the BMS lithium battery protection board can be classified. For products marked as "qualified", they can be directly transferred to the packaging center for subsequent packaging and delivery processes; for products marked as "unqualified", they need to be transferred to the repair center for necessary repairs or adjustments to meet quality standards. This test classification processing mechanism not only improves test efficiency, but also ensures product quality and realizes refined management and optimization of production processes. In general, this method realizes the automation and standardization of the BMS lithium battery protection board test process by introducing quantitative evaluation tools (Jaccard similarity coefficient) and clear decision rules, effectively improving the accuracy and efficiency of the test, and also providing strong support for subsequent product quality control.

[0030] In addition, the BMS lithium battery protection board intelligent testing method also includes the following steps: Obtain the electrical characteristic information of each electrical component in the BMS lithium battery protection board to be tested, and perform feature engineering extraction processing on various test parameters in the BMS lithium battery protection board to be tested to obtain feature engineering information of various test parameters; Calculate the attention score between the electrical characteristic information of each electrical component and the feature engineering information of various test parameters based on the local sensitive attention mechanism; If the attention score between the electrical characteristic information of a certain electrical component and the characteristic engineering information of a certain test parameter is greater than a preset score threshold, the electrical component is defined as the correlation electrical component of the test parameter; and so on, the correlation electrical components of various test parameters are obtained; Constructing a feature database and importing relevant electrical components of various test parameters into the feature database; If the test result of the BMS lithium battery protection board to be tested is a defective product, the test parameters marked as abnormal in the defective product are obtained; Importing the test parameters marked as abnormal in the unqualified product into the feature database for matching, obtaining the relevant electrical components with the test parameters marked as abnormal, and defining the matched relevant electrical components as the faulty electrical components of the unqualified product; The location information of the faulty electrical component is obtained, a fault analysis report is generated according to the location information of the faulty electrical component, and the fault analysis report is sent to a repair center.

[0031] It should be noted that a comprehensive data foundation is constructed by obtaining the electrical characteristic information of the electrical components in the BMS lithium battery protection board to be tested and the feature engineering information of various test parameters. Then, the attention score between the electrical characteristic information of the electrical components and the feature engineering information of the test parameters is calculated through the local sensitive attention mechanism to identify the correlation between the electrical components and the test parameters. If the attention score between the electrical characteristic information of a certain electrical component and the feature engineering information of a certain test parameter exceeds the preset score threshold, then the electrical component is defined as a key electrical component related to the test parameter. This process traverses all electrical components and test parameters, and finally obtains the relevant electrical components of various test parameters. Next, by constructing a feature database, the relevant electrical components of various test parameters are imported into it for subsequent query use. When the test result of the BMS lithium battery protection board to be tested is displayed as a defective product, this method will further obtain the test parameters marked as abnormal in the defective product, and import these abnormal test parameters into the feature database for matching. Through matching, the key electrical components associated with the abnormal test parameters are found, and these electrical components are defined as faulty electrical components. Finally, the location information of the faulty electrical component is obtained, and a detailed fault analysis report is generated. Then, the fault analysis report will be sent to the repair center to provide a direct reference for subsequent repairs and troubleshooting. This method can not only efficiently identify the faulty electrical component, but also provide the repair center with accurate fault location and possible fault causes through the fault analysis report, thereby accelerating the fault resolution process and improving the repair efficiency and quality. At the same time, by establishing a feature database, this method also provides a data basis for future fault prediction and prevention, which helps to take preventive measures before the problem occurs and reduce the possibility of failure.

[0032] In addition, the BMS lithium battery protection board intelligent testing method also includes the following steps: Obtain a three-dimensional structural model diagram of the BMS lithium battery protection board to be tested, and obtain electrical characteristic information of each electrical component in the BMS lithium battery protection board to be tested; Performing format conversion processing on the electrical characteristic information of each electrical component in the BMS lithium battery protection board to be tested to obtain the electrical characteristic information in STEP format, and importing the electrical characteristic information in STEP format into the three-dimensional structure model diagram to obtain a three-dimensional simulation model diagram; If the test result of the BMS lithium battery protection board to be tested is unqualified, the location information of the faulty electrical component and the model name of the faulty electrical component are obtained; According to the location information and model name of the faulty electrical component, a number of repair solutions for repairing the defective product are retrieved in the big data network; Based on SolidWorks software, each repair scheme is sequentially imported into the three-dimensional simulation model diagram for simulated repair, and the simulated repair time of each repair scheme is obtained; The repair plan with the shortest simulated repair time is sent to the repair center as the recommended repair plan.

[0033] It should be noted that an intuitive physical model is constructed by obtaining the three-dimensional structural model diagram of the BMS lithium battery protection board to be tested and the electrical characteristic information of each electrical component. Then, the electrical characteristic information of the electrical component is converted into a format to make it compatible with the three-dimensional structural model, forming a three-dimensional simulation model diagram that combines physical structure and electrical characteristics. If the test results show that the BMS lithium battery protection board is a defective product, the system will further obtain the location information and model name of the faulty electrical component. Next, the big data network is used to retrieve possible repair solutions based on the location information and model name of the faulty electrical component. These repair solutions come from various knowledge bases or historical cases and are designed to solve specific electrical component failures. Subsequently, these repair solutions are imported into the three-dimensional simulation model diagram for simulated repair, which is implemented through SolidWorks software. During the simulated repair process, the system records the repair time of each solution, which is a virtual operation based on the model without actual contact with the hardware. Finally, the system analyzes the efficiency of all simulated repair solutions, selects the solution with the shortest time as the recommended repair solution, and delivers it to the repair center. The advantage of this method is that it can predict the effects of different repair plans in advance, avoiding the blindness and uncertainty in the actual repair process, thereby improving repair efficiency, reducing costs, and reducing damage to hardware. In addition, through simulated repair, the performance after repair can also be evaluated in advance to ensure that the repaired BMS lithium battery protection board can meet the expected usage requirements, thereby improving the overall maintenance quality.

[0034] In addition, to achieve the above purpose, Figure 3As shown, the present invention also discloses a BMS lithium battery protection board intelligent testing system, the BMS lithium battery protection board intelligent testing system includes a memory 41 and a processor 62, the memory 41 stores a BMS lithium battery protection board intelligent testing method program, when the BMS lithium battery protection board intelligent testing method program is executed by the processor 62, the following steps are implemented: Acquire an actual identification area image of the BMS lithium battery protection board to be tested, and obtain a preset test scheme for testing the BMS lithium battery protection board to be tested and a preset test parameter set of various test parameters during the test process by matching the actual identification area image in the knowledge base; Send the preset test plan to the controller of the test station, control the test station to test the BMS lithium battery protection board to be tested according to the preset test plan, and obtain the actual test parameters fed back by the BMS lithium battery protection board to be tested at each preset test time node; After the test is completed, the actual test parameters fed back by the BMS lithium battery protection board to be tested are clustered to obtain the actual test parameter set of various test parameters of the BMS lithium battery protection board to be tested during the test process; Perform similarity analysis on the actual test parameter set and the preset test parameter set of various test parameters, and analyze the status of various test parameters of the BMS lithium battery protection board to be tested during the test process; Generate test results according to the status of various test parameters of the BMS lithium battery protection board to be tested during the test process, and transfer the BMS lithium battery protection board to be tested to the corresponding production center according to the test results; Among them, the test parameters include the operating voltage, operating current, operating temperature, anti-interference ability, short-circuit protection response speed, over-temperature protection response speed, over-charge protection response speed and over-discharge protection response speed of the BMS lithium battery protection board.

[0035] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0036] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0037] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0038] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0039] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0040] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A BMS lithium battery protection board intelligent testing method, characterized in that: The following steps are involved: Acquire an actual identification area image of the BMS lithium battery protection board to be tested, and obtain a preset test scheme for testing the BMS lithium battery protection board to be tested and a preset test parameter set of various test parameters during the test process by matching the actual identification area image in the knowledge base; Send the preset test plan to the controller of the test station, control the test station to test the BMS lithium battery protection board to be tested according to the preset test plan, and obtain the actual test parameters fed back by the BMS lithium battery protection board to be tested at each preset test time node; After the test is completed, the actual test parameters fed back by the BMS lithium battery protection board to be tested are clustered to obtain the actual test parameter set of various test parameters of the BMS lithium battery protection board to be tested during the test process; Perform similarity analysis on the actual test parameter set and the preset test parameter set of various test parameters, and analyze the status of various test parameters of the BMS lithium battery protection board to be tested during the test process; Generate test results according to the status of various test parameters of the BMS lithium battery protection board to be tested during the test process, and transfer the BMS lithium battery protection board to be tested to the corresponding production center according to the test results; Among them, the test parameters include the operating voltage, operating current, operating temperature, anti-interference ability, short-circuit protection response speed, over-temperature protection response speed, over-charge protection response speed and over-discharge protection response speed of the BMS lithium battery protection board.

2. A BMS lithium battery protection board intelligent testing method according to claim 1, characterized in that: According to the actual identification area image, a preset test scheme for testing the BMS lithium battery protection board to be tested and a preset test parameter set of various test parameters during the test process are obtained by matching in the knowledge base, specifically: Obtain the characteristic identification area images of various specifications of BMS lithium battery protection boards in the production workshop, and formulate preset test plans for testing various specifications of BMS lithium battery protection boards; And formulate preset test parameter sets for various test parameters in the test process of BMS lithium battery protection boards of various specifications through corresponding preset test schemes; Construct a knowledge base, and divide the knowledge base into a plurality of storage spaces, and store the characteristic identification area images, preset test schemes, and preset test parameter sets of various test parameters of the same specification of BMS lithium battery protection board in the corresponding storage spaces respectively; Obtain an actual identification area image of the BMS lithium battery protection board to be tested, calculate the cosine similarity between the actual identification area image and the characteristic identification area image in each storage space, and obtain a plurality of cosine similarities; Constructing a size sorting table, and performing size sorting processing on a plurality of cosine similarities through the size sorting table to sort out the maximum cosine similarity; Acquire the actual identification area image corresponding to the maximum cosine similarity, and locate the storage space of the actual identification area image corresponding to the maximum cosine similarity in the knowledge base; The corresponding preset test scheme and the preset test parameter set of various test parameters are extracted from the located storage space, so as to match the preset test scheme for testing the BMS lithium battery protection board to be tested and the preset test parameter set of various test parameters during the test process.

3. A BMS lithium battery protection board intelligent testing method according to claim 1, characterized in that: The actual test parameters fed back by the BMS lithium battery protection board to be tested are clustered to obtain the actual test parameter set of various test parameters of the BMS lithium battery protection board to be tested during the test process, specifically: Based on the principal component analysis method, the actual test parameters fed back by the BMS lithium battery protection board to be tested are mapped into a two-dimensional space, so that each actual test parameter is represented in the form of a point in the two-dimensional space, and a number of parameter points are obtained; Count the total number of other parameter points existing in the preset neighborhood range of each parameter point in the two-dimensional space; If the total number of other parameter points existing in the preset neighborhood of a parameter point in the two-dimensional space is greater than the preset number of points, the parameter point is marked as a core point; If the total number of other parameter points within the preset neighborhood of a parameter point in the two-dimensional space is not greater than the preset number of points, the parameter point is marked as a non-core point. By analogy, all parameter points in the two-dimensional space are traversed to mark each parameter point in the two-dimensional space as a core point or a non-core point; Calculate the Euclidean distance between each non-core point and the core point, and divide each non-core point into a preset neighborhood of the core point with the closest Euclidean distance; After all non-core points are divided, each core point and its non-core points in the preset area are regarded as a parameter clustering set, and several parameter clustering sets are obtained. Each parameter clustering set is evaluated and corrected to obtain a clustering result. According to the clustering result, an actual test parameter set of various test parameters of the BMS lithium battery protection board to be tested during the test process is obtained.

4. A BMS lithium battery protection board intelligent testing method according to claim 3, characterized in that: Each parameter clustering set is evaluated and corrected to obtain the clustering results, which are as follows: Calculate the silhouette coefficient of each parameter cluster set, and compare the silhouette coefficient of each parameter cluster set with a preset value; If the silhouette coefficient of a parameter clustering set is greater than or equal to a preset value, it means that the compactness of the parameter clustering set meets the standard, and the clustering effect state of the parameter clustering set is marked as normal; If the silhouette coefficient of a parameter clustering set is less than the preset value, it means that the compactness of the parameter clustering set does not meet the standard, and the clustering effect state of the parameter clustering set is marked as abnormal; Obtain a parameter clustering set whose clustering effect status is marked as an abnormal state, and define it as a parameter clustering set to be corrected; Calculate the Pearson correlation coefficient between each non-core point and the core point in each parameter cluster set to be corrected; If the Pearson correlation coefficient between a non-core point and a core point in a parameter cluster set to be corrected is not greater than a preset coefficient threshold, the non-core point is demarcated from the parameter cluster set to be corrected, and the demarcated non-core point is marked as a cluster abnormal non-core point; Calculate the Pearson correlation coefficient between the abnormal non-core points of the cluster and the core points of the remaining parameter clusters to be corrected; If the Pearson correlation coefficients between the cluster abnormal non-core point and the core points in the remaining parameter clustering sets to be corrected are not greater than the preset coefficient threshold, the cluster abnormal non-core point is marked as a noise point and the noise point is completely deleted; If the Pearson correlation coefficient between the cluster abnormal non-core point and one or more core points in the remaining parameter clustering sets to be corrected is greater than the preset coefficient threshold, the cluster abnormal non-core point is reclassified into the parameter clustering set to be corrected with the largest Pearson correlation coefficient; Repeat the above steps until the cluster abnormal non-core points in each parameter cluster set to be corrected are identified and all cluster abnormal non-core points are corrected, then complete the evaluation and correction process for each parameter cluster set and output the clustering results.

5. A BMS lithium battery protection board intelligent testing method according to claim 1, characterized in that: The actual test parameter set and the preset test parameter set of various test parameters are analyzed similarly to obtain the status of various test parameters of the BMS lithium battery protection board to be tested during the test process, specifically: Calculate the Jaccard similarity coefficient between the actual test parameter set and the preset test parameter set for various test parameters; and comparing the Jaccard similarity coefficient and the preset similarity coefficient between the actual test parameter set and the preset test parameter set of various test parameters; If the Jaccard similarity coefficient between the actual test parameter set and the preset test parameter set of a certain test parameter is greater than the preset similarity coefficient, the test parameter of the BMS lithium battery protection board to be tested is marked as normal; If the Jaccard similarity coefficient between the actual test parameter set and the preset test parameter set of a certain test parameter is not greater than the preset similarity coefficient, the test parameter of the BMS lithium battery protection board to be tested is marked as an abnormal state.

6. A BMS lithium battery protection board intelligent testing method according to claim 5, characterized in that: Generate test results based on the status of various test parameters of the BMS lithium battery protection board during the test process, and transfer the BMS lithium battery protection board to the corresponding production center based on the test results, specifically: Obtain the status of various test parameters of the BMS lithium battery protection board under test during the test process; If the states of various test parameters of the BMS lithium battery protection board to be tested are all normal during the test process, the BMS lithium battery protection board to be tested is marked as a qualified product, and a first test result is generated, and the BMS lithium battery protection board marked as a qualified product is transferred to the packaging center; If at least one test parameter of the BMS lithium battery protection board to be tested is in an abnormal state during the test process, the BMS lithium battery protection board to be tested is marked as unqualified, and a second test result is generated, and the BMS lithium battery protection board marked as unqualified is transferred to a repair center.

7. A BMS lithium battery protection board intelligent testing system, characterized in that: The BMS lithium battery protection board intelligent test system includes a memory and a processor. The memory stores a BMS lithium battery protection board intelligent test method program. When the BMS lithium battery protection board intelligent test method program is executed by the processor, the following steps are implemented: Acquire an actual identification area image of the BMS lithium battery protection board to be tested, and obtain a preset test scheme for testing the BMS lithium battery protection board to be tested and a preset test parameter set of various test parameters during the test process by matching the actual identification area image in the knowledge base; Send the preset test plan to the controller of the test station, control the test station to test the BMS lithium battery protection board to be tested according to the preset test plan, and obtain the actual test parameters fed back by the BMS lithium battery protection board to be tested at each preset test time node; After the test is completed, the actual test parameters fed back by the BMS lithium battery protection board to be tested are clustered to obtain the actual test parameter set of various test parameters of the BMS lithium battery protection board to be tested during the test process; Perform similarity analysis on the actual test parameter set and the preset test parameter set of various test parameters, and analyze the status of various test parameters of the BMS lithium battery protection board to be tested during the test process; Generate test results according to the status of various test parameters of the BMS lithium battery protection board to be tested during the test process, and transfer the BMS lithium battery protection board to be tested to the corresponding production center according to the test results; Among them, the test parameters include the operating voltage, operating current, operating temperature, anti-interference ability, short-circuit protection response speed, over-temperature protection response speed, over-charge protection response speed and over-discharge protection response speed of the BMS lithium battery protection board.

Images