Lithium ion power battery echelon utilization consistency analysis method

Abstract

The invention relates to a lithium ion power battery echelon utilization consistency analysis method, and belongs to the technical field of battery echelon utilization analys.The lithium ion power battery echelon utilization consistency analysis method comprises the steps that the performance data membership degree of a lithium ion power battery is obtained, and echelon utilization grades of the lithium ion power battery are divided according to the performance data membership degree of the lithium ion power battery; and obtaining a grading result, positioning the corresponding lithium ion power battery, obtaining echelon utilization demand information of the target area, and carrying out recycling distribution on the lithium ion power battery according to the grading result and the echelon utilization demand information of the target area. According to the method, massive performance data of the lithium-ion power battery are evaluated through a specific algorithm, rapid division of the performance data of the lithium-ion power battery can be improved, the processing efficiency of the data of the lithium-ion power battery and the robustness of model processing are improved, and gradient utilization consistency analysis of the lithium-ion power battery is rapidly completed.

Description

Technical Field

[0001] The present invention relates to the technical field of battery recycling analysis, and in particular to a lithium-ion power battery recycling consistency analysis method. Background Art

[0002] The growing production and sales of new energy vehicles have led to an increase in the demand for power batteries. After 3 to 5 years of use, power batteries are usually retired because their capacity and power have decreased and cannot meet driving requirements. The first peak of power battery retirement is coming. If retired batteries are directly processed without metal recycling, it will cause heavy metal pollution in the soil, and large-scale battery recycling will bring great environmental pressure. Since retired power batteries still have about 80% of their capacity margin, there is still room for utilization in other application scenarios. The residual economic value brought by them has spawned the development of cascade utilization technology, that is, after relevant testing of retired batteries, they are applied to low-rate application scenarios such as grid energy storage and household energy. The research on cascade utilization technology can effectively alleviate the environmental pressure brought by recycling, extend the service life of power batteries, and have considerable economic and social benefits. However, the analysis speed and accuracy of the consistency analysis of lithium-ion power batteries are low. At present, the mainstream screening clustering technology adopts machine learning methods, but there are often contradictions between accuracy and speed, and the model generalization ability is insufficient and the robustness is poor. Summary of the invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a method for analyzing the consistency of lithium-ion power battery recycling.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] A first aspect of the present invention provides a lithium-ion power battery recycling consistency analysis method, comprising the following steps:

[0006] Constructing a lithium-ion power battery performance data identification model, identifying the lithium-ion power battery through the lithium-ion power battery performance data identification model, and obtaining the performance data of the lithium-ion power battery at the current timestamp;

[0007] Introducing a support vector machine algorithm, and evaluating and analyzing the performance data of the lithium battery power battery at the current timestamp by using the support vector machine algorithm to obtain a hyperplane partition set, and optimizing the hyperplane partition set to obtain an optimized hyperplane partition set;

[0008] Performing membership evaluation based on the optimized hyperplane partition set to obtain the performance data membership of the lithium-ion power battery, classifying the lithium-ion power battery into tiered utilization levels according to the performance data membership of the lithium-ion power battery, obtaining the level classification result, and locating the corresponding lithium-ion power battery;

[0009] Obtain the cascade utilization demand information of the target area, and allocate the recycling of lithium-ion power batteries according to the grade classification results and the cascade utilization demand information of the target area.

[0010] Furthermore, in this method, a lithium-ion power battery performance data recognition model is constructed, specifically:

[0011] A lithium-ion power battery performance data recognition model is constructed based on a recursive neural network, and a Markov model is introduced to obtain historical performance data of the lithium-ion power battery at each timestamp within a preset time, and the historical performance data of the lithium-ion power battery at each timestamp is mapped to the interval of [0,1] to construct a performance data vector;

[0012] Constructing a performance data vector matrix based on the performance data vector, inputting the performance data vector matrix into the Markov model for calculation, calculating a state transition probability value of each performance data vector transferring to another performance data vector, and presetting a state transition probability threshold;

[0013] Determine whether the state transition probability value is greater than the state transition probability threshold, and when the state transition probability value is greater than the state transition probability threshold, update the performance data vector matrix according to another performance data vector, and input the updated performance data vector matrix into the lithium-ion power battery performance data recognition model for learning;

[0014] When the state transition probability value is not greater than the state transition probability threshold, the performance data vector is maintained unchanged, and the performance data vector matrix is ​​input into the lithium-ion power battery performance data recognition model for learning.

[0015] Furthermore, in this method, the lithium-ion power battery is identified by the lithium-ion power battery performance data identification model to obtain the performance data of the lithium-ion power battery at the current timestamp, specifically:

[0016] Acquire performance data of the lithium-ion power battery at each timestamp within a preset time, and input the performance data of the lithium-ion power battery at each timestamp within the preset time into the lithium-ion power battery performance data recognition model for recognition;

[0017] Through identification, the performance data of the lithium battery power battery at the current timestamp is obtained, and the performance data of the lithium battery power battery at the current timestamp is output.

[0018] Furthermore, in this method, a support vector machine algorithm is introduced, and the performance data of the lithium battery power battery of the current timestamp is evaluated and analyzed by the support vector machine algorithm to obtain a hyperplane partition set, and the hyperplane partition set is optimized to obtain an optimized hyperplane partition set, which specifically includes:

[0019] Introducing a support vector machine algorithm, setting a penalty parameter and a kernel parameter, and performing a dimensional processing on the performance data of the lithium battery power battery at the current timestamp through the PCA algorithm to obtain an n-dimensional vector;

[0020] Performing hyperplane partitioning on the n-dimensional vector based on the penalty parameter and the kernel parameter to obtain a plurality of hyperplane partitioning sets, introducing a Jaccard similarity coefficient measurement method, and calculating the Jaccard similarity coefficient between the hyperplane partitioning sets based on the Jaccard similarity coefficient measurement method;

[0021] Preset a Jaccard similarity coefficient threshold, determine whether the Jaccard similarity coefficient is greater than the Jaccard similarity coefficient threshold, and output a hyperplane partition set when the Jaccard similarity coefficient is not greater than the Jaccard similarity coefficient threshold;

[0022] When the Jaccard similarity coefficient is greater than the Jaccard similarity coefficient threshold, the penalty parameter and the kernel parameter are readjusted until the Jaccard similarity coefficient is not greater than the Jaccard similarity coefficient threshold, and the optimized hyperplane partition set is output.

[0023] Furthermore, in this method, the membership evaluation is performed based on the optimized hyperplane partition set to obtain the performance data membership of the lithium-ion power battery, specifically:

[0024] Presetting a number of fuzzy performance membership threshold range evaluation indicators, and performing membership evaluation on the sample data in the optimized hyperplane partition set based on the fuzzy performance membership threshold range evaluation indicators;

[0025] The degree of membership of the performance data of the lithium-ion power battery corresponding to each sample data is obtained through membership evaluation, and the degree of membership of the performance data of the lithium-ion power battery is output.

[0026] Furthermore, in this method, the lithium-ion power battery is classified into a cascade utilization level according to the degree of membership of the performance data of the lithium-ion power battery, the level classification result is obtained, and the corresponding lithium-ion power battery is located, specifically:

[0027] Setting a number of cascade utilization level indicators, and performing cascade utilization level evaluation on the performance data membership of the lithium-ion power battery according to the cascade utilization level indicators to obtain a corresponding cascade utilization level;

[0028] Repositioning the corresponding lithium-ion power batteries based on the corresponding cascade utilization level, obtaining the cascade utilization level of each lithium-ion power battery, and removing the lithium-ion power batteries corresponding to the cascade utilization level lower than the preset cascade utilization level;

[0029] The lithium-ion power batteries whose cascade utilization level is not lower than that corresponding to the preset cascade utilization level are regarded as lithium-ion power batteries that can be recycled, and the cascade utilization level of each lithium-ion power battery is output.

[0030] Furthermore, in this method, the cascade utilization demand information of the target area is obtained, and the recycling and utilization allocation of lithium-ion power batteries is performed according to the grade classification result and the cascade utilization demand information of the target area, specifically:

[0031] Obtaining the cascade utilization demand information of the target area, randomly selecting lithium-ion power batteries according to the cascade utilization demand information of the target area, constructing a lithium-ion power battery recycling and utilization allocation combination, obtaining the cascade utilization level of each lithium-ion power battery in the lithium-ion power battery recycling and utilization allocation combination, and introducing a genetic algorithm;

[0032] Setting a genetic generation based on the genetic algorithm, and determining whether the cascade utilization level of each lithium-ion power battery in the lithium-ion power battery recycling allocation combination meets the cascade utilization demand information of the target area;

[0033] When the cascade utilization level of each lithium-ion power battery in the lithium-ion power battery recycling allocation combination meets the cascade utilization demand information of the target area, outputting the lithium-ion power battery recycling allocation combination, and recycling and allocating the lithium-ion power batteries according to the lithium-ion power battery recycling allocation combination;

[0034] When the cascade utilization level of each lithium-ion power battery in the lithium-ion power battery recycling allocation combination does not all meet the cascade utilization demand information of the target area, the lithium-ion power battery recycling allocation combination is reselected until all meet the cascade utilization demand information of the target area.

[0035] A second aspect of the present invention provides a lithium-ion power battery cascade utilization consistency analysis system, the system comprising a memory and a processor, the memory comprising a lithium-ion power battery cascade utilization consistency analysis method program, and when the lithium-ion power battery cascade utilization consistency analysis method program is executed by the processor, the steps of any one of the lithium-ion power battery cascade utilization consistency analysis methods are implemented.

[0036] A third aspect of the present invention provides an electronic device, comprising:

[0037] The lithium-ion power battery performance data analysis module is responsible for constructing a lithium-ion power battery performance data identification model, identifying the lithium-ion power battery through the lithium-ion power battery performance data identification model, and obtaining the performance data of the lithium-ion power battery at the current timestamp;

[0038] A classification module is responsible for introducing a support vector machine algorithm, and evaluating and analyzing the performance data of the lithium battery power battery at the current timestamp through the support vector machine algorithm, obtaining a hyperplane partition set, and optimizing the hyperplane partition set to obtain an optimized hyperplane partition set;

[0039] A recycling tier level analysis module is responsible for performing membership evaluation based on the optimized hyperplane partition set, obtaining the performance data membership of the lithium-ion power battery, classifying the lithium-ion power battery into tiered utilization levels according to the performance data membership of the lithium-ion power battery, obtaining the level classification results, and locating the corresponding lithium-ion power battery;

[0040] The recycling allocation analysis module is responsible for obtaining the cascade utilization demand information of the target area, and allocates the recycling and utilization of lithium-ion power batteries according to the grade classification results and the cascade utilization demand information of the target area.

[0041] A fourth aspect of the present invention provides a computer-readable storage medium, which includes a lithium-ion power battery cascade utilization consistency analysis method program. When the lithium-ion power battery cascade utilization consistency analysis method program is executed by a processor, the steps of any one of the lithium-ion power battery cascade utilization consistency analysis methods are implemented.

[0042] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0043] The present invention constructs a lithium-ion power battery performance data identification model, identifies the lithium-ion power battery through the lithium-ion power battery performance data identification model, obtains the performance data of the lithium-ion power battery of the current timestamp, introduces a support vector machine algorithm, and evaluates and analyzes the performance data of the lithium-ion power battery of the current timestamp through the support vector machine algorithm, obtains a hyperplane partition set, optimizes the hyperplane partition set, obtains the optimized hyperplane partition set, performs membership evaluation based on the optimized hyperplane partition set, obtains the performance data membership of the lithium-ion power battery, divides the lithium-ion power battery into cascade utilization levels according to the performance data membership of the lithium-ion power battery, obtains the level division result, locates the corresponding lithium-ion power battery, obtains the cascade utilization demand information of the target area, and recycles and allocates the lithium-ion power battery according to the level division result and the cascade utilization demand information of the target area. The present invention evaluates the performance data of a large amount of lithium-ion power batteries through a specific algorithm, can improve the rapid division of the performance data of the lithium-ion power batteries, improves the processing efficiency of the lithium-ion power battery data and the robustness of the model processing, and quickly completes the consistency analysis of the cascade utilization of lithium-ion power batteries. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] 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.

[0045] Figure 1 The overall flow chart of the lithium-ion power battery recycling consistency analysis method is shown;

[0046] Figure 2 A partial flow chart of a lithium-ion power battery recycling consistency analysis method is shown;

[0047] Figure 3 The system block diagram of the lithium-ion power battery recycling consistency analysis system is shown;

[0048] Figure 4 A schematic diagram of an electronic device is shown; DETAILED DESCRIPTION

[0049] 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.

[0050] 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.

[0051] like Figure 1 As shown, the first aspect of the present invention provides a lithium-ion power battery cascade utilization consistency analysis method, comprising the following steps:

[0052] S102: constructing a lithium-ion power battery performance data identification model, identifying the lithium-ion power battery through the lithium-ion power battery performance data identification model, and obtaining performance data of the lithium-ion power battery at the current timestamp;

[0053] S104: introducing a support vector machine algorithm, and evaluating and analyzing the performance data of the lithium battery power battery at the current timestamp by using the support vector machine algorithm, obtaining a hyperplane partition set, and optimizing the hyperplane partition set to obtain an optimized hyperplane partition set;

[0054] S106: performing membership evaluation based on the optimized hyperplane partition set, obtaining the performance data membership of the lithium-ion power battery, classifying the lithium-ion power battery into tiered utilization levels according to the performance data membership of the lithium-ion power battery, obtaining the level classification result, and locating the corresponding lithium-ion power battery;

[0055] S108: Obtaining the cascade utilization demand information of the target area, and allocating the recycling of lithium-ion power batteries according to the grade classification result and the cascade utilization demand information of the target area.

[0056] It should be noted that the present invention evaluates the performance data of a large amount of lithium-ion power batteries through a specific algorithm, which can improve the rapid division of the performance data of lithium-ion power batteries, improve the processing efficiency of lithium-ion power battery data and the robustness of model processing, and quickly complete the consistency analysis of lithium-ion power battery cascade utilization. Among them, the performance data of lithium-ion power batteries includes the voltage, capacity, internal resistance, energy, power, output efficiency, self-discharge rate and other data of the power battery.

[0057] Furthermore, in this method, a lithium-ion power battery performance data recognition model is constructed, specifically:

[0058] A lithium-ion power battery performance data recognition model is constructed based on a recursive neural network, and a Markov model is introduced to obtain the historical performance data of the lithium-ion power battery at each timestamp within a preset time, and the historical performance data of the lithium-ion power battery at each timestamp is mapped to the interval of [0,1] to construct a performance data vector;

[0059] Constructing a performance data vector matrix based on the performance data vector, inputting the performance data vector matrix into the Markov model for calculation, calculating the state transition probability value of each performance data vector transferring to another performance data vector, and presetting the state transition probability threshold;

[0060] Determine whether the state transition probability value is greater than a state transition probability threshold value. When the state transition probability value is greater than the state transition probability threshold value, update the performance data vector matrix according to another performance data vector, and input the updated performance data vector matrix into the lithium-ion power battery performance data recognition model for learning;

[0061] When the state transition probability value is not greater than the state transition probability threshold, the performance data vector is maintained unchanged, and the performance data vector matrix is ​​input into the lithium-ion power battery performance data recognition model for learning.

[0062] It should be noted that, first of all, it is necessary to test the power battery, and to build a lithium-ion power battery performance data recognition model by integrating the Markov model and the deep neural network, and to collect data in a time series process. In a time series, the collected power battery performance data fluctuates, which conforms to the properties of the Markov model, that is, it transfers from one performance state to another. Through this method, a lithium-ion power battery performance data recognition model can be constructed, thereby more accurately identifying the real-time performance data of the lithium-ion power battery.

[0063] Furthermore, in this method, the lithium-ion power battery is identified by a lithium-ion power battery performance data identification model to obtain the performance data of the lithium-ion power battery at the current timestamp, specifically:

[0064] Acquire the performance data of the lithium-ion power battery at each time stamp within a preset time, and input the performance data of the lithium-ion power battery at each time stamp within the preset time into the lithium-ion power battery performance data recognition model for recognition;

[0065] Through identification, the performance data of the lithium battery power battery at the current timestamp is obtained, and the performance data of the lithium battery power battery at the current timestamp is output.

[0066] like Figure 2 As shown, further, in this method, a support vector machine algorithm is introduced, and the performance data of the lithium battery power battery at the current timestamp is evaluated and analyzed by the support vector machine algorithm to obtain a hyperplane partition set, and the hyperplane partition set is optimized to obtain an optimized hyperplane partition set, specifically including:

[0067] S202: introducing a support vector machine algorithm, setting a penalty parameter and a kernel parameter, and performing a dimensional processing on the performance data of the lithium battery power battery at the current timestamp through the PCA algorithm to obtain an n-dimensional vector;

[0068] S204: performing hyperplane partitioning on the n-dimensional vector based on the penalty parameter and the kernel parameter, obtaining a plurality of hyperplane partitioning sets, introducing the Jaccard similarity coefficient measurement method, and calculating the Jaccard similarity coefficient between the hyperplane partitioning sets based on the Jaccard similarity coefficient measurement method;

[0069] S206: Preset a Jaccard similarity coefficient threshold, determine whether the Jaccard similarity coefficient is greater than the Jaccard similarity coefficient threshold, and when the Jaccard similarity coefficient is not greater than the Jaccard similarity coefficient threshold, output a hyperplane partition set;

[0070] S208: When the Jaccard similarity coefficient is greater than the Jaccard similarity coefficient threshold, the penalty parameter and the kernel parameter are readjusted until the Jaccard similarity coefficient is not greater than the Jaccard similarity coefficient threshold, and the optimized hyperplane partition set is output.

[0071] It should be noted that the support vector machine algorithm uses hyperplanes to classify the performance data of lithium battery power batteries, and the selection of penalty parameters and kernel parameters will affect the division of the hyperplane. The Jaccard similarity coefficient between the hyperplane division sets is integrated with the Jaccard similarity coefficient measurement method. When the Jaccard similarity coefficient is not greater than the Jaccard similarity coefficient threshold, it means that the classification is normal. When the Jaccard similarity coefficient is greater than the Jaccard similarity coefficient threshold, it means that the classification is abnormal. By integrating the Jaccard similarity coefficient measurement method, the support vector machine algorithm can be optimized to improve the accuracy of data classification.

[0072] Furthermore, in this method, the membership evaluation is performed based on the optimized hyperplane partition set to obtain the performance data membership of the lithium-ion power battery, specifically:

[0073] Preset a number of fuzzy performance membership threshold range evaluation indicators, and perform membership evaluation on sample data in the optimized hyperplane partition set based on the fuzzy performance membership threshold range evaluation indicators;

[0074] Through the membership evaluation, the performance data membership of the lithium-ion power battery corresponding to each sample data is obtained, and the performance data membership of the lithium-ion power battery is output.

[0075] It should be noted that, for example, the power battery discharge capacity threshold range indicator, the charging voltage threshold indicator, and the discharge voltage indicator threshold range can be set, and different indicators correspond to different performance data memberships. For example, the power battery discharge capacity performance membership includes a high power battery discharge capacity performance membership, a medium power battery discharge capacity performance membership, a low power battery discharge capacity performance membership, etc. Different performance indicators correspond to different performance data memberships.

[0076] Furthermore, in this method, the lithium-ion power battery is classified into a cascade utilization level according to the degree of membership of the performance data of the lithium-ion power battery, the level classification result is obtained, and the corresponding lithium-ion power battery is located, specifically:

[0077] Set a number of cascade utilization level indicators, and evaluate the cascade utilization level of the performance data of the lithium-ion power battery according to the cascade utilization level indicators to obtain the corresponding cascade utilization level;

[0078] Reposition the corresponding lithium-ion power batteries based on the corresponding cascade utilization level, obtain the cascade utilization level of each lithium-ion power battery, and remove the lithium-ion power batteries corresponding to the cascade utilization level lower than the preset cascade utilization level;

[0079] The lithium-ion power batteries whose cascade utilization level is not lower than that corresponding to the preset cascade utilization level are regarded as lithium-ion power batteries that can be recycled, and the cascade utilization level of each lithium-ion power battery is output.

[0080] It should be noted that according to the scrapping principle, lithium-ion power batteries with different performances correspond to different tiered utilization and recycling levels, such as the first tier utilization level and the second tier utilization level. The higher the level, the worse the performance. Lithium batteries with a tiered utilization level not lower than the preset tiered utilization level are regarded as recyclable lithium-ion power batteries, otherwise they are non-recyclable lithium-ion power batteries.

[0081] Furthermore, in this method, the cascade utilization demand information of the target area is obtained, and the recycling and utilization allocation of lithium-ion power batteries is performed according to the grade classification result and the cascade utilization demand information of the target area, specifically:

[0082] Obtaining the cascade utilization demand information of the target area, randomly selecting lithium-ion power batteries according to the cascade utilization demand information of the target area, constructing a lithium-ion power battery recycling and utilization allocation combination, obtaining the cascade utilization level of each lithium-ion power battery in the lithium-ion power battery recycling and utilization allocation combination, and introducing a genetic algorithm;

[0083] Setting genetic generations based on the genetic algorithm and judging whether the cascade utilization level of each lithium-ion power battery in the lithium-ion power battery recycling allocation combination meets the cascade utilization demand information of the target area;

[0084] When the cascade utilization level of each lithium-ion power battery in the lithium-ion power battery recycling allocation combination meets the cascade utilization demand information of the target area, the lithium-ion power battery recycling allocation combination is output, and the lithium-ion power batteries are recycled and allocated according to the lithium-ion power battery recycling allocation combination;

[0085] When the cascade utilization level of each lithium-ion power battery in the lithium-ion power battery recycling and utilization allocation combination does not all meet the cascade utilization demand information of the target area, the lithium-ion power battery recycling and utilization allocation combination is reselected until it all meets the cascade utilization demand information of the target area.

[0086] It should be noted that the cascade utilization demand information of the target area includes demand data such as voltage, capacity, internal resistance, energy, power, output efficiency, and self-discharge rate. The genetic algorithm can be used to seek high-quality solutions and optimize the lithium-ion power battery recycling and utilization distribution combination to meet the cascade utilization demand information of the target area.

[0087] In addition, the method may further include:

[0088] Obtain environmental characteristic data in the target area and information on lithium-ion power battery models in the lithium-ion power battery recycling and utilization allocation combination, and obtain working characteristic data of each lithium-ion power battery model under each environmental characteristic data through big data, and build a working characteristic data prediction model for lithium-ion power batteries based on a deep neural network;

[0089] The environmental feature data is used as the first node, the lithium-ion power battery model is used as the second node, and the working characteristic data is used as the third node to construct a directed description relationship, and the first node, the second node, and the third node are connected based on the directed description relationship to construct a topological structure diagram;

[0090] Acquiring a relevant adjacency matrix based on the topological structure diagram, inputting the relevant adjacency matrix into the working characteristic data prediction model of the lithium-ion power battery for encoding learning, and acquiring a trained working characteristic data prediction model of the lithium-ion power battery;

[0091] Inputting the environmental characteristic data in the target area and the model information of the lithium-ion power batteries in the lithium-ion power battery recycling allocation combination into the working characteristic data prediction model of the lithium-ion power battery for prediction, and obtaining the working characteristic data of the model information of the lithium-ion power batteries in the lithium-ion power battery recycling allocation combination in the target area;

[0092] The actual performance attribute data of the lithium-ion power battery is updated according to the working characteristic data of the lithium-ion power battery model information in the target area in the lithium-ion power battery recycling allocation combination, and the lithium-ion power battery recycling allocation combination is reselected until it meets the cascade utilization demand information of the target area.

[0093] It should be noted that different target areas have different environmental data (such as temperature, humidity, etc.), and the working characteristics of batteries in different environments (such as the actual power utilization efficiency) are inconsistent. This method can further improve the rationality of cascade utilization allocation and optimize the lithium-ion power battery recycling and utilization allocation combination.

[0094] In addition, the method further comprises:

[0095] Acquire historical environmental change characteristic data in the target area, and acquire historical minimum temperature and historical maximum temperature characteristics of the target area based on the historical environmental change characteristic data in the target area;

[0096] Inputting the historical minimum temperature and the historical maximum temperature characteristics of the target area into the working characteristic data prediction model of the lithium-ion power battery for prediction, and obtaining the variation range of the working characteristic data of the lithium-ion power battery;

[0097] Acquire the maximum value of the operating characteristic data of the lithium-ion power battery according to the variation range of the operating characteristic data of the lithium-ion power battery;

[0098] The cascade utilization demand information of the target area is updated according to the operating characteristic data of the lithium-ion power battery with the maximum value, and the lithium-ion power battery recycling allocation combination is re-optimized based on the updated cascade utilization demand information of the target area.

[0099] It should be noted that, in fact, the cascade utilization demand information is a numerical value, and this numerical value is not fixed. The environment is changing, and changes in the environment will cause changes in the cascade utilization demand information. For example, the actual demand is for a battery with a power of 900 kWh, but due to environmental changes, the utilization rate can only reach 90% under this environment (only 810 kWh of demand can be achieved). At this time, it is necessary to change the cascade utilization demand information, so as to obtain the historical minimum temperature and historical maximum temperature characteristics of the target area through historical environmental change characteristic data, so as to obtain the cascade utilization demand information of the actual demand in the target area, and then further optimize the lithium-ion power battery recycling and utilization distribution combination.

[0100] like Figure 3As shown, the second aspect of the present invention provides a lithium-ion power battery cascade utilization consistency analysis system 4, the system 4 includes a memory 41 and a processor 42, the memory 41 includes a lithium-ion power battery cascade utilization consistency analysis method program, and when the lithium-ion power battery cascade utilization consistency analysis method program is executed by the processor 42, any step of the lithium-ion power battery cascade utilization consistency analysis method is implemented.

[0101] like Figure 4 As shown, the third aspect of the present invention provides an electronic device, including:

[0102] The lithium-ion power battery performance data analysis module 10 is responsible for constructing a lithium-ion power battery performance data identification model, identifying the lithium-ion power battery through the lithium-ion power battery performance data identification model, and obtaining the performance data of the lithium-ion power battery at the current timestamp;

[0103] The classification module 20 is responsible for introducing the support vector machine algorithm, and evaluating and analyzing the performance data of the lithium battery power battery at the current timestamp through the support vector machine algorithm, obtaining a hyperplane partition set, and optimizing the hyperplane partition set to obtain an optimized hyperplane partition set;

[0104] The recycling tier level analysis module 30 is responsible for evaluating the membership based on the optimized hyperplane partition set, obtaining the membership of the performance data of the lithium-ion power battery, classifying the lithium-ion power battery into tiers according to the membership of the performance data of the lithium-ion power battery, obtaining the classification result, and locating the corresponding lithium-ion power battery;

[0105] The recycling allocation analysis module 40 is responsible for obtaining the cascade utilization demand information of the target area, and allocates the recycling of lithium-ion power batteries according to the grade classification result and the cascade utilization demand information of the target area.

[0106] Furthermore, in this device, a lithium-ion power battery performance data recognition model is constructed, specifically:

[0107] A lithium-ion power battery performance data recognition model is constructed based on a recursive neural network, and a Markov model is introduced to obtain the historical performance data of the lithium-ion power battery at each timestamp within a preset time, and the historical performance data of the lithium-ion power battery at each timestamp is mapped to the interval of [0,1] to construct a performance data vector;

[0108] Constructing a performance data vector matrix based on the performance data vector, inputting the performance data vector matrix into the Markov model for calculation, calculating the state transition probability value of each performance data vector transferring to another performance data vector, and presetting the state transition probability threshold;

[0109] Determine whether the state transition probability value is greater than a state transition probability threshold value. When the state transition probability value is greater than the state transition probability threshold value, update the performance data vector matrix according to another performance data vector, and input the updated performance data vector matrix into the lithium-ion power battery performance data recognition model for learning;

[0110] When the state transition probability value is not greater than the state transition probability threshold, the performance data vector is maintained unchanged, and the performance data vector matrix is ​​input into the lithium-ion power battery performance data recognition model for learning.

[0111] Furthermore, in this device, the lithium-ion power battery is identified by the lithium-ion power battery performance data identification model, and the performance data of the lithium-ion power battery at the current timestamp is obtained, specifically:

[0112] Acquire the performance data of the lithium-ion power battery at each time stamp within a preset time, and input the performance data of the lithium-ion power battery at each time stamp within the preset time into the lithium-ion power battery performance data recognition model for recognition;

[0113] Through identification, the performance data of the lithium battery power battery at the current timestamp is obtained, and the performance data of the lithium battery power battery at the current timestamp is output.

[0114] Furthermore, in this device, a support vector machine algorithm is introduced, and the performance data of the lithium battery power battery at the current timestamp is evaluated and analyzed by the support vector machine algorithm to obtain a hyperplane partition set, and the hyperplane partition set is optimized to obtain an optimized hyperplane partition set, specifically including:

[0115] The support vector machine algorithm is introduced, and the penalty parameters and kernel parameters are set. The performance data of the lithium battery power battery at the current timestamp is processed by the PCA algorithm to obtain an n-dimensional vector;

[0116] Based on the penalty parameter and the kernel parameter, the n-dimensional vector is partitioned into hyperplanes to obtain several hyperplane partition sets, and the Jaccard similarity coefficient measurement method is introduced to calculate the Jaccard similarity coefficient between the hyperplane partition sets based on the Jaccard similarity coefficient measurement method;

[0117] Preset a Jaccard similarity coefficient threshold, determine whether the Jaccard similarity coefficient is greater than the Jaccard similarity coefficient threshold, and when the Jaccard similarity coefficient is not greater than the Jaccard similarity coefficient threshold, output a hyperplane partition set;

[0118] When the Jaccard similarity coefficient is greater than the Jaccard similarity coefficient threshold, the penalty parameter and the kernel parameter are readjusted until the Jaccard similarity coefficient is not greater than the Jaccard similarity coefficient threshold, and the optimized hyperplane partition set is output.

[0119] Furthermore, in this device, the membership evaluation is performed based on the optimized hyperplane partition set to obtain the performance data membership of the lithium-ion power battery, specifically:

[0120] Preset a number of fuzzy performance membership threshold range evaluation indicators, and perform membership evaluation on sample data in the optimized hyperplane partition set based on the fuzzy performance membership threshold range evaluation indicators;

[0121] Through the membership evaluation, the performance data membership of the lithium-ion power battery corresponding to each sample data is obtained, and the performance data membership of the lithium-ion power battery is output.

[0122] Furthermore, in the present device, the lithium-ion power battery is classified into a cascade utilization level according to the degree of membership of the performance data of the lithium-ion power battery, the level classification result is obtained, and the corresponding lithium-ion power battery is located, specifically:

[0123] Set a number of cascade utilization level indicators, and evaluate the cascade utilization level of the performance data of the lithium-ion power battery according to the cascade utilization level indicators to obtain the corresponding cascade utilization level;

[0124] Reposition the corresponding lithium-ion power batteries based on the corresponding cascade utilization level, obtain the cascade utilization level of each lithium-ion power battery, and remove the lithium-ion power batteries corresponding to the cascade utilization level lower than the preset cascade utilization level;

[0125] The lithium-ion power batteries whose cascade utilization level is not lower than that corresponding to the preset cascade utilization level are regarded as lithium-ion power batteries that can be recycled, and the cascade utilization level of each lithium-ion power battery is output.

[0126] Furthermore, in this device, the cascade utilization demand information of the target area is obtained, and the lithium-ion power batteries are recycled and allocated according to the grade classification result and the cascade utilization demand information of the target area, specifically:

[0127] Obtaining the cascade utilization demand information of the target area, randomly selecting lithium-ion power batteries according to the cascade utilization demand information of the target area, constructing a lithium-ion power battery recycling and utilization allocation combination, obtaining the cascade utilization level of each lithium-ion power battery in the lithium-ion power battery recycling and utilization allocation combination, and introducing a genetic algorithm;

[0128] Setting genetic generations based on the genetic algorithm and judging whether the cascade utilization level of each lithium-ion power battery in the lithium-ion power battery recycling allocation combination meets the cascade utilization demand information of the target area;

[0129] When the cascade utilization level of each lithium-ion power battery in the lithium-ion power battery recycling allocation combination meets the cascade utilization demand information of the target area, the lithium-ion power battery recycling allocation combination is output, and the lithium-ion power batteries are recycled and allocated according to the lithium-ion power battery recycling allocation combination;

[0130] When the cascade utilization level of each lithium-ion power battery in the lithium-ion power battery recycling and utilization allocation combination does not all meet the cascade utilization demand information of the target area, the lithium-ion power battery recycling and utilization allocation combination is reselected until it all meets the cascade utilization demand information of the target area.

[0131] A fourth aspect of the present invention provides a computer-readable storage medium, which includes a lithium-ion power battery cascade utilization consistency analysis method program. When the lithium-ion power battery cascade utilization consistency analysis method program is executed by a processor, any step of the lithium-ion power battery cascade utilization consistency analysis method is implemented.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiments 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 embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical disks, and other media that can store program codes.

[0136] 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, a server, or a 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.

[0137] 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 method for analyzing the consistency of lithium-ion power battery recycling. It is characterized in that The following steps are involved: Constructing a lithium-ion power battery performance data identification model, identifying the lithium-ion power battery through the lithium-ion power battery performance data identification model, and obtaining the performance data of the lithium-ion power battery at the current timestamp; Introducing a support vector machine algorithm, and evaluating and analyzing the performance data of the lithium battery power battery at the current timestamp by using the support vector machine algorithm to obtain a hyperplane partition set, and optimizing the hyperplane partition set to obtain an optimized hyperplane partition set; Performing membership evaluation based on the optimized hyperplane partition set to obtain the performance data membership of the lithium-ion power battery, classifying the lithium-ion power battery into tiered utilization levels according to the performance data membership of the lithium-ion power battery, obtaining the level classification result, and locating the corresponding lithium-ion power battery; Obtain the cascade utilization demand information of the target area, and allocate the recycling of lithium-ion power batteries according to the grade classification results and the cascade utilization demand information of the target area.

2. A lithium-ion power battery recycling consistency analysis method according to claim 1, It is characterized in that Construct a lithium-ion power battery performance data recognition model, specifically: A lithium-ion power battery performance data recognition model is constructed based on a recursive neural network, and a Markov model is introduced to obtain historical performance data of the lithium-ion power battery at each timestamp within a preset time, and the historical performance data of the lithium-ion power battery at each timestamp is mapped to the interval of [0,1] to construct a performance data vector; Constructing a performance data vector matrix based on the performance data vector, inputting the performance data vector matrix into the Markov model for calculation, calculating a state transition probability value of each performance data vector transferring to another performance data vector, and presetting a state transition probability threshold; Determine whether the state transition probability value is greater than the state transition probability threshold, and when the state transition probability value is greater than the state transition probability threshold, update the performance data vector matrix according to another performance data vector, and input the updated performance data vector matrix into the lithium-ion power battery performance data recognition model for learning; When the state transition probability value is not greater than the state transition probability threshold, the performance data vector is maintained unchanged, and the performance data vector matrix is ​​input into the lithium-ion power battery performance data recognition model for learning.

3. A lithium-ion power battery recycling consistency analysis method according to claim 1, It is characterized in that The lithium-ion power battery is identified by the lithium-ion power battery performance data identification model to obtain the performance data of the lithium-ion power battery at the current timestamp, specifically: Acquire performance data of the lithium-ion power battery at each timestamp within a preset time, and input the performance data of the lithium-ion power battery at each timestamp within the preset time into the lithium-ion power battery performance data recognition model for recognition; Through identification, the performance data of the lithium battery power battery at the current timestamp is obtained, and the performance data of the lithium battery power battery at the current timestamp is output.

4. A lithium-ion power battery recycling consistency analysis method according to claim 1, It is characterized in that Introducing a support vector machine algorithm, and evaluating and analyzing the performance data of the lithium battery power battery of the current timestamp by the support vector machine algorithm, obtaining a hyperplane partition set, and optimizing the hyperplane partition set to obtain an optimized hyperplane partition set, specifically including: Introducing a support vector machine algorithm, setting a penalty parameter and a kernel parameter, and performing a dimensional processing on the performance data of the lithium battery power battery at the current timestamp through the PCA algorithm to obtain an n-dimensional vector; Performing hyperplane partitioning on the n-dimensional vector based on the penalty parameter and the kernel parameter to obtain a plurality of hyperplane partition sets, introducing a Jaccard similarity coefficient measurement method, and calculating the Jaccard similarity coefficient between the hyperplane partition sets based on the Jaccard similarity coefficient measurement method; Preset a Jaccard similarity coefficient threshold, determine whether the Jaccard similarity coefficient is greater than the Jaccard similarity coefficient threshold, and output a hyperplane partition set when the Jaccard similarity coefficient is not greater than the Jaccard similarity coefficient threshold; When the Jaccard similarity coefficient is greater than the Jaccard similarity coefficient threshold, the penalty parameter and the kernel parameter are readjusted until the Jaccard similarity coefficient is not greater than the Jaccard similarity coefficient threshold, and the optimized hyperplane partition set is output.

5. A lithium-ion power battery recycling consistency analysis method according to claim 1, It is characterized in that Based on the optimized hyperplane partition set, membership evaluation is performed to obtain the performance data membership of the lithium-ion power battery, specifically: Presetting a number of fuzzy performance membership threshold range evaluation indicators, and performing membership evaluation on the sample data in the optimized hyperplane partition set based on the fuzzy performance membership threshold range evaluation indicators; The degree of membership of the performance data of the lithium-ion power battery corresponding to each sample data is obtained through membership evaluation, and the degree of membership of the performance data of the lithium-ion power battery is output.

6. A lithium-ion power battery recycling consistency analysis method according to claim 1, It is characterized in that The lithium-ion power battery is classified into a cascade utilization level according to the performance data membership of the lithium-ion power battery, the level classification result is obtained, and the corresponding lithium-ion power battery is located, specifically: Setting a number of cascade utilization level indicators, and performing cascade utilization level evaluation on the performance data membership of the lithium-ion power battery according to the cascade utilization level indicators to obtain a corresponding cascade utilization level; Repositioning the corresponding lithium-ion power batteries based on the corresponding cascade utilization levels, obtaining the cascade utilization level of each lithium-ion power battery, and removing the lithium-ion power batteries corresponding to the cascade utilization level lower than the preset cascade utilization level; The lithium-ion power batteries whose cascade utilization level is not lower than that corresponding to the preset cascade utilization level are regarded as lithium-ion power batteries that can be recycled, and the cascade utilization level of each lithium-ion power battery is output.

7. A lithium-ion power battery recycling consistency analysis method according to claim 1, It is characterized in that Obtain the cascade utilization demand information of the target area, and allocate the recycling of lithium-ion power batteries according to the grading results and the cascade utilization demand information of the target area, specifically: Obtaining cascade utilization demand information of a target area, randomly selecting lithium-ion power batteries according to the cascade utilization demand information of the target area, constructing a lithium-ion power battery recycling and utilization allocation combination, obtaining a cascade utilization level of each lithium-ion power battery in the lithium-ion power battery recycling and utilization allocation combination, and introducing a genetic algorithm; Setting a genetic generation based on the genetic algorithm, and determining whether the cascade utilization level of each lithium-ion power battery in the lithium-ion power battery recycling allocation combination meets the cascade utilization demand information of the target area; When the cascade utilization level of each lithium-ion power battery in the lithium-ion power battery recycling allocation combination meets the cascade utilization demand information of the target area, outputting the lithium-ion power battery recycling allocation combination, and recycling and allocating the lithium-ion power batteries according to the lithium-ion power battery recycling allocation combination; When the cascade utilization level of each lithium ion power battery in the lithium ion power battery recycling allocation combination does not all meet the cascade utilization demand information of the target area, the lithium ion power battery recycling allocation combination is reselected until all meet the cascade utilization demand information of the target area.

8. A lithium-ion power battery recycling consistency analysis system, It is characterized in that The system includes a memory and a processor, wherein the memory includes a lithium-ion power battery cascade utilization consistency analysis method program, and when the lithium-ion power battery cascade utilization consistency analysis method program is executed by the processor, the steps of the lithium-ion power battery cascade utilization consistency analysis method as described in any one of claims 1 to 7 are implemented.

9. An electronic device, It is characterized in that include: The lithium-ion power battery performance data analysis module is responsible for constructing a lithium-ion power battery performance data identification model, identifying the lithium-ion power battery through the lithium-ion power battery performance data identification model, and obtaining the performance data of the lithium-ion power battery at the current timestamp; A classification module is responsible for introducing a support vector machine algorithm, and evaluating and analyzing the performance data of the lithium battery power battery at the current timestamp through the support vector machine algorithm, obtaining a hyperplane partition set, and optimizing the hyperplane partition set to obtain an optimized hyperplane partition set; A recycling tier level analysis module is responsible for performing membership evaluation based on the optimized hyperplane partition set, obtaining the performance data membership of the lithium-ion power battery, classifying the lithium-ion power battery into tiered utilization levels according to the performance data membership of the lithium-ion power battery, obtaining the level classification results, and locating the corresponding lithium-ion power battery; The recycling allocation analysis module is responsible for obtaining the cascade utilization demand information of the target area, and allocates the recycling and utilization of lithium-ion power batteries according to the grade classification results and the cascade utilization demand information of the target area.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a lithium-ion power battery cascade utilization consistency analysis method program. When the lithium-ion power battery cascade utilization consistency analysis method program is executed by a processor, the steps of the lithium-ion power battery cascade utilization consistency analysis method as described in any one of claims 1 to 7 are implemented.

Images