Retired power lithium battery detection system and method

Abstract

The present invention proposes a retired power lithium battery detection system and method, which relates to the technical field of lithium battery state prediction. The system includes: a retired power lithium battery big data warehouse, a retired power lithium battery feature library, a first computer vision recognition system, a transmission system, and a detector. Based on the retired power lithium battery big data warehouse and the first computer vision recognition system, qualified target retired power lithium batteries are identified; and transported to the detector through the transmission system; the target model of the target retired power lithium battery is identified through the second computer vision recognition system of the detector; and the battery capacity gradient value of the target retired power lithium battery of the target model is calculated through the electrochemical monitoring system of the detector. Thus, the digital empowerment of retired power lithium battery detection is realized by using big data, machine learning and Internet technology, and the rapid and accurate classification of the battery capacity of retired power lithium batteries is realized, avoiding the power loss and safety problems of multiple cycles of charge and discharge.

Description

Technical Field

[0001] The present invention relates to the technical field of lithium battery state prediction, and in particular to a retired power lithium battery detection system and method. Background Art

[0002] The retirement period of power lithium batteries of new energy vehicles is generally 6 to 8 years. In the face of the huge new energy vehicle industry, recycling and reusing retired power lithium batteries has huge economic, environmental and social benefits. Therefore, rapid capacity detection of retired power lithium batteries is of great significance to the recycling industry of retired power lithium batteries.

[0003] In the related technologies, the common capacity detection technology for retired power lithium batteries often adopts the traditional cyclic charging and discharging method, using capacity detection cabinets, capacity detection boxes, discharge machines and other equipment to detect retired power lithium batteries. The capacity detection efficiency is low, time-consuming, energy-intensive, and has high safety risks. Summary of the invention

[0004] The present invention aims to solve one of the technical problems in the related art to a certain extent.

[0005] To this end, the first object of the present invention is to provide a retired power lithium battery detection system, the retired power lithium battery rapid detection system comprises: a retired power lithium battery big data warehouse, a retired power lithium battery feature library, a first computer vision recognition system, a transmission system, and a detector, wherein:

[0006] The retired power lithium battery big data warehouse is used to store characteristic parameters of various types of lithium batteries;

[0007] The retired power lithium battery feature library is used to store abnormal feature indicators of retired power lithium batteries;

[0008] The first computer vision recognition system is used to match the characteristic indicators of the retired power lithium battery with the abnormal characteristic indicators to identify qualified target retired power lithium batteries;

[0009] The transmission system is used to transport the target retired power lithium battery to the detector;

[0010] The detector is composed of a second computer vision recognition system and an electrochemical monitoring system, wherein the second computer vision recognition system is used to match the battery parameters of the target retired power lithium battery with the characteristic parameters of the lithium battery to identify the target model of the target retired power lithium battery;

[0011] The electrochemical monitoring system is used to detect the electrochemical parameters of the target retired power lithium battery corresponding to the target model, so as to calculate the battery capacity gradient value of the target retired power lithium battery of the target model according to the electrochemical parameters.

[0012] In one embodiment of the present invention, the characteristic parameters of the lithium battery include: lithium battery type, lithium battery model, lithium battery size, distance between positive and negative electrodes of the lithium battery, rated voltage of the lithium battery cell, rated capacity of the lithium battery cell, rated current of the lithium battery cell, and lithium battery resistance.

[0013] In one embodiment of the present invention, the abnormal characteristic indicators include: bulging, deformation, aging, corrosion, rust, water ingress, fire, and overweight.

[0014] In one embodiment of the present invention, the first computer vision recognition system is also used to match the characteristic indicators of retired power lithium batteries with the abnormal characteristic indicators to identify unqualified abnormal retired power lithium batteries, and regenerate or scrap the abnormal retired power lithium batteries.

[0015] In one embodiment of the present invention, the transmission system is based on a conveyor belt and is equipped with a lithium battery size identification device and a lithium battery correction device, wherein:

[0016] Lithium battery correction device, used to correct the battery position of the target retired power lithium battery, so as to keep the fixed battery position and transport it to the tester

[0017] A lithium battery size identification device, used to identify the target size of a target retired power lithium battery, and send the target size to a retired power lithium battery big data warehouse, and match it with the lithium battery characteristic parameters. If there is no match, the retired power lithium battery big data warehouse records the target size;

[0018] The second computer vision recognition system is further used to match the target size with the characteristic parameters of the lithium battery, and when a match is found, output a target model of the target retired power lithium battery corresponding to the target size.

[0019] In one embodiment of the present invention, the second computer vision recognition system is further used to send the unrecognized sample model of the target retired power lithium battery to a retired power lithium battery big data warehouse;

[0020] The lithium battery big data warehouse is also used to store the sample model and the battery parameters of the target retired power lithium battery corresponding to the sample model.

[0021] The present invention proposes a retired power lithium battery detection system, which includes: a retired power lithium battery big data warehouse, a retired power lithium battery feature library, a first computer vision recognition system, a transmission system, and a detector, wherein: based on the retired power lithium battery big data warehouse and the first computer vision recognition system, qualified target retired power lithium batteries are identified; and transported to the detector through the transmission system; the target model of the target retired power lithium battery is identified through the second computer vision recognition system of the detector; and the battery capacity gradient value of the target retired power lithium battery of the target model is calculated through the electrochemical monitoring system of the detector. Thus, big data, machine learning and Internet technologies are utilized to realize the digital empowerment of retired power lithium battery detection, and to realize the rapid and accurate grading of the battery capacity of retired power lithium batteries, avoiding the power loss and safety problems of multiple cycles of charge and discharge.

[0022] To this end, the second object of the present invention is to provide a retired power lithium battery detection method, the method comprising:

[0023] Obtain characteristic parameters of various types of lithium battery and abnormal characteristic indicators of retired power lithium batteries;

[0024] Matching the characteristic indicators of the retired power lithium battery with the abnormal characteristic indicators to identify qualified target retired power lithium batteries;

[0025] Matching the battery parameters of the target retired power lithium battery with the lithium battery characteristic parameters to identify the target model of the target retired power lithium battery;

[0026] The electrochemical parameters of the target retired power lithium battery corresponding to the target model are detected, so as to calculate the battery capacity gradient value of the target retired power lithium battery of the target model according to the electrochemical parameters.

[0027] In one embodiment of the present invention, the method further comprises:

[0028] When the battery capacity gradient value is greater than or equal to a first available threshold value and less than or equal to a second available threshold value, the target retired power lithium battery is applied to multiple low-level fields in a stepwise manner, wherein the first available threshold value is less than the second available threshold value;

[0029] When the battery capacity gradient value is less than the first available threshold, the target retired power lithium battery should be recycled.

[0030] The present invention proposes a retired power lithium battery detection method, which obtains and stores lithium battery characteristic parameters of various types of retired power lithium batteries, as well as abnormal characteristic indicators; matches the characteristic indicators of retired power lithium batteries with abnormal characteristic indicators to identify qualified target retired power lithium batteries; matches the battery parameters of the target retired power lithium batteries with the lithium battery characteristic parameters to identify the target model of the target retired power lithium batteries; detects the electrochemical parameters of the target retired power lithium batteries corresponding to the target model, and calculates the battery capacity gradient value of the target retired power lithium batteries of the target model according to the electrochemical parameters. Thus, the battery capacity of retired power lithium batteries can be quickly and accurately graded, the capacity division efficiency is higher, and the power loss and safety problems of multiple cycles of charge and discharge are avoided.

[0031] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0033] Figure 1 A schematic diagram of the structure of a retired power lithium battery detection system provided by an embodiment of the present invention;

[0034] Figure 2 A schematic diagram of establishing a big data warehouse for retired power lithium batteries provided by an embodiment of the present invention;

[0035] Figure 3 A schematic diagram of establishing and using a retired power lithium battery feature library provided by an embodiment of the present invention;

[0036] Figure 4 A schematic diagram of a transmission system for retired power lithium batteries provided in an embodiment of the present invention;

[0037] Figure 5 A schematic diagram of the relationship between a retired power lithium battery detection system and the entire industry provided by an embodiment of the present invention;

[0038] Figure 6 A schematic flow chart of a retired power lithium battery detection method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0040] The following describes a retired power lithium battery detection system according to an embodiment of the present invention with reference to the accompanying drawings.

[0041] Figure 1 This is a schematic diagram of the structure of a retired power lithium battery detection system provided by an embodiment of the present invention. Figure 1 As shown, the retired power lithium battery detection system includes: a retired power lithium battery big data warehouse 11, a retired power lithium battery feature library 12, a first computer visual recognition system 13, a transmission system 14, and a detector 15, wherein:

[0042] The retired power lithium battery big data warehouse 11 is used to store characteristic parameters of various types of lithium batteries.

[0043] In some embodiments, the method for constructing the retired power lithium battery big data warehouse 11 can be as follows: Figure 2 As shown, typical ternary lithium and lithium iron phosphate batteries can be selected, and their typical lithium battery characteristic parameters can be obtained through the corresponding lithium battery manual and other information. Furthermore, the lithium battery characteristic parameters include lithium battery type (brand), lithium battery model, lithium battery size, lithium battery positive and negative electrode spacing, lithium battery cell rated voltage, lithium battery cell rated capacity, lithium battery cell rated current, and lithium battery resistance. An initial basic retired power lithium battery big data warehouse is constructed, and then the retired power lithium battery big data warehouse capacity is gradually strengthened through the feedback system. The feedback system includes a first computer vision recognition system 13 and a detector 15. The first computer vision recognition system 13 is to identify the size of lithium batteries through a sensor system (physical feedback), and the detector 15 is electrochemical feedback, and outputs the retired power lithium battery big data warehouse 11.

[0044] The retired power lithium battery feature library 12 is used to store abnormal feature indicators of retired power lithium batteries.

[0045] In some embodiments, the method for establishing and using the retired power lithium battery feature library 12 can be as follows: Figure 3 As shown, the retired power lithium battery feature library 12 is a battery initial screening guidance system, which uses computer vision technology to quickly identify fake batteries, defective batteries, high-risk batteries and unusable batteries, thereby reducing the workload of subsequent detection lines of the detector 15 and further improving the detection efficiency of the production line.

[0046] Furthermore, abnormal characteristic indicators include: bulging, deformation, aging, corrosion, rust, water ingress, fire, and overweight.

[0047] Specifically, Figure 3As shown, unqualified batteries (retired power lithium batteries) can be obtained from the retired power lithium battery cluster through manual screening. The abnormal characteristic indicators (features) of unqualified batteries include bulging, deformation, aging, corrosion, rust, water ingress, fire, and overweight. Therefore, based on the above abnormal characteristic indicators, a retired power lithium battery feature library 12 is established to guide the first computer vision system to identify unqualified abnormal retired power lithium batteries and qualified target retired power lithium batteries, regenerate the real batteries in the abnormal retired power lithium batteries, scrap the fake batteries, and transmit the target retired power lithium batteries to the detector 15.

[0048] The first computer vision recognition system 13 is used to match the characteristic indicators of the retired power lithium batteries with the abnormal characteristic indicators to identify qualified target retired power lithium batteries.

[0049] In some embodiments, the first computer vision recognition system 13 is a system that uses computer vision technology to understand images or videos. It extracts and analyzes features in the image through image processing, pattern recognition, machine learning and other technologies, thereby identifying qualified target retired power lithium batteries.

[0050] Alternatively, if Figure 1 As shown, the first computer vision recognition system 13 performs feature recognition on retired power lithium batteries to obtain feature indicators of retired power lithium batteries, and matches (screens) the feature indicators based on the retired power lithium battery feature library 12 to identify qualified target retired power lithium batteries.

[0051] The transmission system 14 is used to transport the target retired power lithium battery to the detector 15.

[0052] In some embodiments, optionally, the transmission system 14 is based on a conveyor belt and is equipped with a lithium battery size identification device and a lithium battery correction device, wherein:

[0053] The lithium battery correction device is used to correct the battery position of the target retired power lithium battery so as to maintain the fixed battery position for transportation to the detector 15.

[0054] The lithium battery size identification device is used to identify the target size of the target retired power lithium battery, and send the target size to the retired power lithium battery big data warehouse 11, and match it with the lithium battery characteristic parameters. If there is no match, the retired power lithium battery big data warehouse 11 records the target size.

[0055] Furthermore, the transmission system 14 of the retired power lithium battery is as follows Figure 4As shown, the transmission system 14 can be based on a uniform speed conveyor belt, equipped with a lithium battery size recognition device and a lithium battery correction device, and coupled with a back-end detector 15, and data can be uniformly transmitted back. After the target retired power lithium battery passes through the feeding system (through the pallet for feeding), it enters the lithium battery size recognition device, adapts to the battery size through the adjustable baffle, and corrects the battery orientation through the lithium battery correction device. At the same time, the target size of the target retired power lithium battery is recorded and fed back to the retired power lithium battery big data warehouse 11. The known target size will retrieve data from the retired power lithium battery big data warehouse 11 to match the target model. The non-target model (sample model) is marked as unknown, and the lithium battery model is further determined by the second computer vision recognition system 151 (visual module) and the electrochemical monitoring system 152 in the subsequent detector 15. For the detectable target model, the corresponding electrochemical detection method is called out, and for the undetectable sample model, a new class is created for the electrochemical data (battery parameters) after the electrochemical detection and coupled with the lithium battery size recognition device, so that the target size and electrochemical data are uniformly transmitted back to the retired power lithium battery big data warehouse 11, and the retired power lithium battery big data warehouse 11 data is added for subsequent detection.

[0056] In addition, if Figure 1 As shown, the transmission system 14 communicates with the retired power lithium battery big data warehouse 11. The transmission system 14 feeds back the target size of the target retired power lithium battery to the retired power lithium battery big data warehouse 11 to add data to the retired power lithium battery big data warehouse 11. The retired power lithium battery big data warehouse 11 directs the transmission system 14 to identify the lithium battery size.

[0057] The detector 15 is composed of a second computer vision recognition system 151 and an electrochemical monitoring system 152. The second computer vision recognition system 151 is used to match the battery parameters of the target retired power lithium battery with the lithium battery characteristic parameters to identify the target model of the target retired power lithium battery.

[0058] The electrochemical monitoring system 152 is used to detect the electrochemical parameters of the target retired power lithium battery corresponding to the target model, so as to calculate the battery capacity gradient value of the target retired power lithium battery of the target model according to the electrochemical parameters.

[0059] In some embodiments, the detector 15 can be located at the end of the transmission system 14, which is a functional extension of the first computer vision recognition system 13. For deep detection, this step can realize the battery model identification and battery capacity gradient value calculation functions of the target retired power lithium battery.

[0060] Furthermore, the second computer vision recognition system 151 mainly uses computer vision technology to match data with the retired power lithium battery big data warehouse 11 to identify the target model of the target retired power lithium battery, which is used as a pre-processing of the electrochemical monitoring system 152. The method for electrochemical detection is called in, and the visual detection is completed and the electrochemical detection starts immediately. According to the method call-in, the target retired power lithium battery is matched. The electrochemical detection system mainly detects important electrochemical parameters such as the cut-off voltage and resistance of the target retired power lithium battery. Therefore, there is no need to adopt a cyclic charge and discharge method. The battery capacity gradient value (State of Charge, SOH) of the target retired power lithium battery can be inferred through the electrochemical formula. At the same time, the retired power lithium battery detection device is gradually corrected through deep learning and big data technology, so that the retired power lithium battery can be detected quickly and with high accuracy.

[0061] Alternatively, if Figure 1 As shown, the detector 15 feeds back the sample model and the battery parameters of the target retired power lithium battery corresponding to the sample model to the retired power lithium battery big data warehouse 11 to increase the data of the retired power lithium battery big data warehouse 11. The retired power lithium battery big data warehouse 11 instructs the detector 15 to perform target model identification and electrochemical detection.

[0062] In addition, if Figure 1 As shown, after solving the battery capacity gradient value (SOH) of the target retired power lithium battery, the target retired power lithium battery is further utilized according to the SOH value. Specifically, when the SOH is greater than or equal to 40% and less than or equal to 80%, the target retired power lithium battery can be applied in different fields such as low-level energy storage, low-speed electric vehicles, street lights, etc. according to different capacity levels; when the SOH is less than 40%, the target retired power lithium battery is recycled.

[0063] Optionally, the first computer vision recognition system 13 is also used to match the characteristic indicators of retired power lithium batteries with abnormal characteristic indicators to identify unqualified abnormal retired power lithium batteries, and regenerate or scrap the abnormal retired power lithium batteries.

[0064] Optionally, the second computer vision recognition system 151 is further used to match the target size with the characteristic parameters of the lithium battery, and when a match is found, output a target model of the target retired power lithium battery corresponding to the target size.

[0065] Optionally, the second computer vision recognition system 151 is also used to send the unrecognized sample model of the target retired power lithium battery to the retired power lithium battery big data warehouse 11.

[0066] The lithium battery big data warehouse is also used to store sample models and the battery parameters of the target retired power lithium batteries corresponding to the sample models.

[0067] The present invention proposes a retired power lithium battery detection system, which includes: a retired power lithium battery big data warehouse, a retired power lithium battery feature library, a first computer vision recognition system, a transmission system, and a detector, wherein: based on the retired power lithium battery big data warehouse and the first computer vision recognition system, qualified target retired power lithium batteries are identified; and transported to the detector through the transmission system; the target model of the target retired power lithium battery is identified through the second computer vision recognition system of the detector; and the battery capacity gradient value of the target retired power lithium battery of the target model is calculated through the electrochemical monitoring system of the detector. Thus, big data, machine learning and Internet technologies are utilized to realize the digital empowerment of retired power lithium battery detection, and to realize the rapid and accurate grading of the battery capacity of retired power lithium batteries, avoiding the power loss and safety problems of multiple cycles of charge and discharge.

[0068] It can be understood that the present invention also proposes a schematic diagram of the relationship between a retired power lithium battery detection system and the entire industry, such as Figure 5 As shown, for lithium batteries (ternary lithium and retired iron phosphate power lithium batteries), the battery pack is disassembled to obtain battery shells, aluminum shells, battery cells, electronic components, and plastics. The battery cells are tested for residual energy (battery capacity gradient value), and recycling or cascade utilization is determined based on the battery capacity gradient value. In the case of cascade utilization, lithium batteries can be used for energy storage containers, backup power supplies for communication equipment, solar street light energy storage devices, and low-speed vehicles.

[0069] The present invention also provides a flow chart of a retired power lithium battery detection method, such as Figure 6 shown.

[0070] like Figure 6 As shown, the method comprises the following steps:

[0071] Step 601, obtaining and storing lithium battery characteristic parameters of various types of retired power lithium batteries, as well as abnormal characteristic indicators.

[0072] Step 602, matching the characteristic indicators of retired power lithium batteries with abnormal characteristic indicators to identify qualified target retired power lithium batteries.

[0073] Step 603 , matching the battery parameters of the target retired power lithium battery with the lithium battery characteristic parameters to identify the target model of the target retired power lithium battery.

[0074] Step 604 , detecting the electrochemical parameters of the target retired power lithium battery corresponding to the target model, and calculating the battery capacity gradient value of the target retired power lithium battery of the target model according to the electrochemical parameters.

[0075] The present invention proposes a retired power lithium battery detection method, which obtains and stores lithium battery characteristic parameters of various types of retired power lithium batteries, as well as abnormal characteristic indicators; matches the characteristic indicators of retired power lithium batteries with abnormal characteristic indicators to identify qualified target retired power lithium batteries; matches the battery parameters of the target retired power lithium batteries with the lithium battery characteristic parameters to identify the target model of the target retired power lithium batteries; detects the electrochemical parameters of the target retired power lithium batteries corresponding to the target model, and calculates the battery capacity gradient value of the target retired power lithium batteries of the target model according to the electrochemical parameters. Thus, the battery capacity of retired power lithium batteries can be quickly and accurately graded, the capacity division efficiency is higher, and the power loss and safety problems of multiple cycles of charge and discharge are avoided.

[0076] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0077] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0078] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0079] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0080] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0081] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0082] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A retired power lithium battery detection system, characterized in that: The retired power lithium battery rapid detection system comprises: a retired power lithium battery big data warehouse, a retired power lithium battery feature library, a first computer vision recognition system, a transmission system, and a detector, wherein: The retired power lithium battery big data warehouse is used to store characteristic parameters of various types of lithium batteries; The retired power lithium battery feature library is used to store abnormal feature indicators of retired power lithium batteries, and the abnormal feature indicators include: bulging, deformation, aging, corrosion, rust, water ingress, fire, and overweight; The first computer vision recognition system is used to match the characteristic indicators of the retired power lithium battery with the abnormal characteristic indicators to identify qualified target retired power lithium batteries; The transmission system is used to transport the target retired power lithium battery to the detector; The detector is composed of a second computer vision recognition system and an electrochemical monitoring system, wherein the second computer vision recognition system is used to match the battery parameters of the target retired power lithium battery with the characteristic parameters of the lithium battery to identify the target model of the target retired power lithium battery; The electrochemical monitoring system is used to detect the electrochemical parameters of the target retired power lithium battery corresponding to the target model, so as to calculate the battery capacity gradient value of the target retired power lithium battery of the target model through the electrochemical formula according to the electrochemical parameters, wherein the electrochemical parameters include the cut-off voltage and resistance of the target retired power lithium battery; The first computer vision recognition system is further used to: perform feature recognition on retired power lithium batteries to obtain feature indicators of retired power lithium batteries, match the feature indicators of retired power lithium batteries with the abnormal feature indicators to identify unqualified abnormal retired power lithium batteries, and regenerate or scrap the abnormal retired power lithium batteries; The transmission system is based on a conveyor belt and is equipped with a lithium battery size identification device and a lithium battery correction device, wherein: Lithium battery correction device, used to correct the battery position of the target retired power lithium battery, so as to keep the battery position fixed and transport it to the tester; A lithium battery size identification device, used to identify the target size of a target retired power lithium battery, and send the target size to a retired power lithium battery big data warehouse, and match it with the lithium battery characteristic parameters. If there is no match, the retired power lithium battery big data warehouse records the target size; The second computer vision recognition system is further used to match the target size with the characteristic parameters of the lithium battery, and when a match is found, output a target model of the target retired power lithium battery corresponding to the target size, as a pre-processing of the electrochemical monitoring system, for inputting the electrochemical detection method; The second computer vision recognition system is also used to send the unrecognized sample model of the target retired power lithium battery to the retired power lithium battery big data warehouse; The lithium battery big data warehouse is also used to store the sample model and the battery parameters of the target retired power lithium battery corresponding to the sample model.

2. The retired power lithium battery detection system according to claim 1, characterized in that: The characteristic parameters of lithium batteries include: lithium battery type, lithium battery model, lithium battery size, distance between positive and negative electrodes of lithium battery, rated voltage of lithium battery cell, rated capacity of lithium battery cell, rated current of lithium battery cell, and lithium battery resistance.

3. A method for detecting retired power lithium batteries based on the retired power lithium battery detection system according to any one of claims 1-2, characterized in that: The method comprises: Obtain characteristic parameters of various types of lithium battery and abnormal characteristic indicators of retired power lithium batteries; Matching the characteristic indicators of the retired power lithium battery with the abnormal characteristic indicators to identify qualified target retired power lithium batteries; Matching the battery parameters of the target retired power lithium battery with the lithium battery characteristic parameters to identify the target model of the target retired power lithium battery; The electrochemical parameters of the target retired power lithium battery corresponding to the target model are detected, so as to calculate the battery capacity gradient value of the target retired power lithium battery of the target model according to the electrochemical parameters.

4. The method according to claim 3, characterized in that The method further comprises: When the battery capacity gradient value is greater than or equal to a first available threshold value and less than or equal to a second available threshold value, the target retired power lithium battery is applied to multiple low-level fields in a stepwise manner, wherein the first available threshold value is less than the second available threshold value; When the battery capacity gradient value is less than the first available threshold, the target retired power lithium battery should be recycled.

Images