Abnormality detection method and apparatus for battery cell encasing, and electronic device and storage medium
By generating and analyzing the curve to be detected during the battery cell inlet, the problem of low accuracy and intelligence of abnormal detection of battery cell inlet in the existing technology is solved, and more efficient abnormal detection and battery cell quality control are achieved .
Patent Information
- Application Number
- PCT/CN2024/091511
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-16
- Filing Date
- 2024-05-07
- Publication Date
- 2024-11-21
AI Technical Summary
The existing abnormal detection methods during the battery cell are poorly accurate and have low intelligence, resulting in a decrease in battery cell quality and safety impact.
By obtaining the detection data during the battery cell entry process, analyzing these curves based on the historical detection data, determining the abnormal results of the battery cell entry into the shell, and improving the accuracy and intelligence of the detection.
It improves the accuracy and efficiency of abnormal detection of battery cell inlet, reduces the dependence of manual inspection, can more effectively identify major abnormal problems in the production process, and improves the intelligence of battery cell detection process.
Smart Images

Figure CN2024091511_21112024_PF_FP_ABST
Abstract
Description
Abnormal detection method, device, electronic device and storage medium for battery cell shell insertion
[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on May 16, 2023, with application number 202310556999.7 and application name “Battery Shell Abnormality Detection Method, Device, Electronic Device and Storage Medium”, the entire contents of which are incorporated by reference into this application. Technical Field
[0002] The present disclosure relates to the field of industrial detection technology, and in particular to a method, device, electronic device, and storage medium for detecting abnormalities in battery cell insertion into a shell. Background Art
[0003] With the continuous development of industrial products, people's quality inspection requirements for industrial products are also becoming increasingly higher. In related battery assembly technologies, battery cells are required to be installed into the battery casing using a shell insertion machine. During the shell insertion process, the battery cells may experience abnormalities such as jamming or burrs. These abnormalities can lead to reduced cell quality and affect the performance and safety of the finished battery. In actual production processes, the thrust value of the battery cell during the shell insertion process is usually monitored, and cells with abnormal thrust values are manually inspected to determine whether there is any abnormality. This abnormality detection method has poor accuracy and low intelligence.
[0004] Summary of the Invention
[0005] The embodiments of the present disclosure provide a method, device, electronic device, and storage medium for detecting abnormalities in the process of battery cell shell insertion, which can improve the intelligence and accuracy of abnormality detection in the process of battery cell shell insertion.
[0006] According to a first aspect of an embodiment of the present disclosure, a method for detecting abnormalities in battery cell insertion into a shell is provided, the method comprising:
[0007] Obtain detection data during the process of the battery cell being pushed into the battery casing;
[0008] generating one or more curves to be detected according to the detection data;
[0009] The one or more curves to be detected are respectively detected according to historical detection data to obtain a detection result corresponding to each curve to be detected; the historical detection data is the detection data when no abnormality occurs during the process of the battery cell being pushed into the battery housing;
[0010] The abnormal result of the battery cell entering the shell is determined according to the detection result corresponding to each of the curves to be detected.
[0011] Optionally, the detection data includes a displacement value and / or a thrust value of the battery cell being pushed into the battery housing;
[0012] Generating one or more curves to be detected according to the detection data includes:
[0013] A curve to be detected corresponding to the thrust value is generated according to the thrust value, and / or a curve to be detected corresponding to the displacement value is generated according to the displacement value.
[0014] Optionally, the detecting the one or more curves to be detected respectively according to the historical detection data to obtain a detection result corresponding to each curve to be detected includes:
[0015] Generating a standard curve corresponding to each of the curves to be tested according to the historical detection data, and determining a slope threshold corresponding to each of the standard curves according to each of the standard curves;
[0016] Determining the slope of each of the curves to be detected, and comparing the slope of each of the curves to be detected with a corresponding slope threshold to obtain a slope comparison result of each of the curves to be detected;
[0017] Determining the similarity between each of the curves to be tested and the corresponding standard curve, and comparing each of the similarities with a similarity threshold to obtain a similarity comparison result for each of the curves to be tested;
[0018] According to the slope comparison result and the similarity comparison result of each of the curves to be detected, a detection result corresponding to each of the curves to be detected is obtained.
[0019] Optionally, the method further includes:
[0020] Determining abnormal data corresponding to each of the curves to be detected based on the detection data;
[0021] The detecting the one or more curves to be detected respectively according to the historical detection data to obtain a detection result corresponding to each curve to be detected includes:
[0022] Determine abnormal data thresholds based on historical detection data;
[0023] The abnormal data corresponding to each of the curves to be detected is compared with the abnormal data threshold to obtain a detection result corresponding to each of the curves to be detected.
[0024] Optionally, the abnormal data includes a jamming value and a glitch value, and the abnormal data threshold includes a jamming threshold and a glitch threshold;
[0025] The step of comparing the abnormal data corresponding to each of the curves to be detected with an abnormal data threshold to obtain a detection result corresponding to each of the curves to be detected includes:
[0026] Comparing the jam value corresponding to each of the curves to be detected with the jam threshold value to obtain a jam comparison result corresponding to each of the curves to be detected;
[0027] Comparing the burr value corresponding to each of the curves to be detected with the burr threshold to obtain a burr comparison result corresponding to each of the curves to be detected;
[0028] According to the jam comparison result corresponding to each of the curves to be detected and the burr comparison result corresponding to each of the curves to be detected, a detection result corresponding to each of the curves to be detected is obtained.
[0029] Optionally, the method further includes:
[0030] Determining, based on a jam comparison result corresponding to a target curve to be detected, a first number of the target curves to be detected whose jam values are greater than the jam threshold value; the target curve to be detected is any of the curves to be detected;
[0031] Determine, based on a burr comparison result corresponding to the target curve to be detected, a second number of burr values in the target curve to be detected that are greater than the burr threshold;
[0032] Determining an anomaly score corresponding to the target curve to be detected based on the first number, the weight of the jam comparison result, the second number, and the weight of the burr comparison result; wherein the weight of the jam comparison result is greater than the weight of the burr comparison result;
[0033] The abnormality level of the battery cell shell insertion is determined according to the abnormality score corresponding to each of the curves to be detected.
[0034] Optionally, after generating one or more curves to be detected according to the detection data, the method further includes:
[0035] According to the battery cell shelling process, each of the curves to be tested is divided into multiple sub-curves; the multiple sub-curves correspond one-to-one to the multiple shelling sub-processes of the battery cell shelling process;
[0036] The detecting the one or more curves to be detected respectively according to the historical detection data to obtain a detection result corresponding to each curve to be detected includes:
[0037] Each sub-curve of each curve to be detected is detected according to historical detection data to obtain a detection result corresponding to each sub-curve of each curve to be detected, and a detection result corresponding to each curve to be detected is determined according to the detection result corresponding to each sub-curve.
[0038] According to a second aspect of an embodiment of the present disclosure, a device for detecting abnormalities in battery cell insertion into a shell is provided, the device comprising:
[0039] A data acquisition module is used to obtain detection data during the process of the battery cell being pushed into the battery casing;
[0040] A curve construction module, configured to generate one or more curves to be detected based on the detection data;
[0041] a curve detection module, configured to detect the one or more curves to be detected respectively based on historical detection data, and obtain a detection result corresponding to each curve to be detected; the historical detection data is detection data when no abnormality occurs during the process of the battery cell being pushed into the battery housing;
[0042] The abnormality detection module is used to determine the abnormality result of the battery cell entering the shell according to the detection result corresponding to each of the curves to be detected.
[0043] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the method described in the first aspect of the embodiment of the present disclosure.
[0044] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, which stores a computer program, wherein when the computer program is executed by a processor, the processor executes the method according to the first aspect of the embodiment of the present disclosure.
[0045] Compared with the related art, the embodiments of the present disclosure have the following beneficial effects:
[0046] Acquire detection data during the process of the battery cell being pushed into the battery shell, generate one or more curves to be detected based on these detection data, and detect the generated curves to be detected based on historical detection data, that is, detection data when no abnormality occurred during the process of the battery cell being pushed into the battery shell, respectively, to obtain the detection results corresponding to each curve to be detected, and finally determine the abnormal results of the battery cell entering the shell based on the detection results corresponding to each curve to be detected. By implementing the embodiment of the present disclosure, the specific situation of the battery cell being pushed into the battery shell can be intuitively reflected by generating the curve to be detected, and the accuracy of abnormal battery cell judgment can be improved by comparing and analyzing the curve to be detected through historical detection data, and combining the detection results of each curve to be detected. The above judgment process does not require manual inspection, which improves the intelligence level of the battery cell detection process. In addition, by analyzing the curve to be detected through historical detection data, the main abnormal problems in the production process can be effectively determined for targeted solutions, which can improve the accuracy and efficiency of abnormality detection during the battery cell entering the shell. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0048] FIG1 is a schematic diagram of an application scenario of a method for detecting abnormalities in battery cell insertion into a shell provided by an embodiment of the present disclosure;
[0049] FIG2 is a flow chart of a method for detecting abnormalities in battery cell insertion into a shell according to an embodiment of the present disclosure;
[0050] FIG3 is a flow chart of another method for detecting abnormalities in battery cell insertion into a shell provided by an embodiment of the present disclosure;
[0051] FIG4 is a flow chart of another method for detecting abnormalities in battery cell insertion into a shell according to an embodiment of the present disclosure;
[0052] FIG5 is a flow chart of another method for detecting abnormalities in battery cell insertion into a shell provided by an embodiment of the present disclosure;
[0053] FIG6 is a schematic diagram of a curve anomaly detection process provided by an embodiment of the present disclosure;
[0054] FIG7 is a schematic diagram of a jamming and glitch detection process provided by an embodiment of the present disclosure;
[0055] FIG8 is a schematic structural diagram of a device for detecting abnormalities in battery cell insertion into a shell according to an embodiment of the present disclosure;
[0056] FIG9 is an architecture diagram of a battery cell shell abnormality detection system provided by an embodiment of the present disclosure;
[0057] FIG10 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION
[0058] The following will clearly and completely describe the technical solutions in the embodiments of the present disclosure in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present disclosure without making any creative efforts shall fall within the scope of protection of the present disclosure.
[0059] It should be noted that the terms "including," "having," and any variations thereof in the embodiments of the present disclosure and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to the process, method, product, or apparatus.
[0060] In related battery assembly technologies, battery cells need to be installed into battery casings using a shell inserter. The method for detecting abnormal battery cells is to monitor the thrust value during the shell insertion process and manually inspect the battery cells with abnormal thrust values to determine whether the battery cells have abnormalities. This abnormality detection method has poor accuracy and a low level of intelligence. The disclosed embodiments provide a method, device, electronic device, and storage medium for detecting abnormalities in battery cell shell insertion, which can improve the accuracy of product abnormality detection. These are described in detail below.
[0061] Please refer to Figure 1, which is a schematic diagram of an application scenario of a method for detecting abnormalities in battery cell entry into the battery shell provided by an embodiment of the present disclosure. As shown in Figure 1, it may include an electronic device 10, a battery cell 20 and a pushing device 30. The electronic device 10 may be equipped with a processor, but is not limited to this. The pushing device 30 may be equipped with sensing devices such as encoders and pressure sensors to collect detection data during the process of the pushing device 30 pushing the battery cell 20 into the battery shell, and the electronic device 10 may be communicatively connected to the pushing device 30. Alternatively, the electronic device 10 may be communicatively connected to an external detection device, and the external detection device is used to collect detection data during the process of the pushing device 30 pushing the battery cell 20 into the battery shell.
[0062] The electronic device 10 can obtain detection data from the process of the battery cell 20 being pushed into the battery casing by the pushing device 30 or an external detection device, and generate one or more curves to be detected based on the detection data. The electronic device 10 then detects the generated one or more curves to be detected based on historical detection data to obtain a detection result corresponding to each curve to be detected; wherein the historical detection data is the detection data of the battery cell being pushed into the battery casing by the pushing device 30 without any abnormality. Finally, the electronic device 10 determines the abnormal result of the battery cell 20 entering the casing based on the detection result corresponding to each curve to be detected.
[0063] Please refer to Figure 2, which is a flow chart of a method for detecting abnormalities in battery cell insertion provided by an embodiment of the present disclosure. The method can be applied to the aforementioned electronic device 10. As shown in Figure 2, the method may include the following steps:
[0064] 210. Obtain detection data during the process of the battery cell being pushed into the battery casing.
[0065] In an embodiment of the present disclosure, the battery cell can be pushed into the battery shell by a pushing device in the shell-entering machine. The pushing device may be equipped with a built-in sensing device, which may include an encoder and a pressure sensor, etc. The pushing device collects detection data of the process in which the pushing device itself pushes the battery cell into the battery shell through the built-in sensing device, and sends the collected detection data to the electronic device, so that the electronic device obtains detection data of the process in which the battery cell is pushed into the battery shell by the pushing device. Alternatively, the external device of the pushing device has a sensing device, and the sensing device collects detection data of the process in which the battery cell is pushed into the battery shell by the pushing device, and sends the collected detection data to the electronic device, so that the electronic device obtains detection data of the process in which the battery cell is pushed into the battery shell by the pushing device. Among them, the detection data can be data reflecting the process in which the pushing device pushes the battery cell into the battery shell, such as displacement data of the battery cell, speed data of the battery cell, thrust data of the pushing device pushing the battery cell, and angle data of the pushing device pushing the battery cell, etc.
[0066] In an embodiment of the present disclosure, the sensing device can collect and send detection data according to preset collection rules. For example, the sensing device can continuously collect detection data, or the sensing device can collect detection data at certain time intervals; the sensing device can send the collected detection data to the electronic device in real time, or it can send the collected detection data to the electronic device at certain time intervals.
[0067] 220. Generate one or more curves to be detected based on the detection data.
[0068] In an embodiment of the present disclosure, the electronic device generates one or more curves to be detected based on the acquired detection data. If the detection data includes only one data category, the electronic device can generate one curve to be detected, or it can generate multiple curves to be detected according to a certain acquisition time length; if the detection data includes more than one data category, the electronic device can generate multiple curves to be detected according to the number of data categories. The data category can be data representing different contents, such as displacement data, thrust data, speed data, and angle data. The curve to be detected can be a curve obtained by performing line segment fitting based on the acquired detection data. The curve to be detected is a curve that reflects the changes in the detection data.
[0069] 230. Detect one or more curves to be detected respectively according to historical detection data to obtain a detection result corresponding to each curve to be detected; the historical detection data is detection data when no abnormality occurs during the process of the battery cell being pushed into the battery housing.
[0070] In the disclosed embodiment, after the electronic device determines that no abnormality occurs during the process of the battery cell being pushed into the battery housing by the pushing device, the electronic device stores the detection data during the process of the pushing device pushing the battery cell into the battery housing in a database as historical detection data. The database can be a database internal to the electronic device or a database external to the electronic device.
[0071] The electronic device detects one or more curves to be detected generated based on the detection data according to the stored historical detection data to obtain the detection result corresponding to each curve to be detected. In specific implementation, the electronic device can draw a standard curve based on the historical detection data, and compare the standard curve with each curve to be detected to obtain the detection result corresponding to each curve to be detected. For example, if the difference between a curve to be detected and the standard curve is large, then the detection result corresponding to the curve to be detected is considered to be abnormal. The electronic device can also compare the historical detection data with each peak (or the highest peak) and / or each trough (or the lowest trough) in each curve to be detected, and / or the number of peaks / troughs in the curve to be detected to obtain the detection result corresponding to each curve to be detected. For example, if the highest peak of a curve to be detected is greater than the historical detection data, then the detection result corresponding to the curve to be detected is considered to be abnormal. Wherein, the standard curve is a curve that reflects the changes in historical detection data.
[0072] 240. Determine an abnormal result of the battery cell entering the shell based on the test result corresponding to each curve to be tested.
[0073] In the embodiment of the present disclosure, the electronic device can determine the abnormal result of the battery cell entering the shell based on the detection result corresponding to each curve to be detected. In specific implementation, if only one curve to be detected is generated, then the detection result corresponding to the curve to be detected is abnormal, and the battery cell entering the shell process is determined to be abnormal; the detection result corresponding to the curve to be detected is normal, and the battery cell entering the shell process is determined to be normal. If more than one curve to be detected is generated, the electronic device can determine that the battery cell entering the shell process is abnormal when the detection result corresponding to any one of the curves to be detected is abnormal; the electronic device can also determine that the battery cell entering the shell process is abnormal when the detection results corresponding to all the curves to be detected are abnormal; the electronic device can also determine that the battery cell entering the shell process is abnormal when the detection results corresponding to more than a certain number of curves to be detected are abnormal.
[0074] By adopting the above embodiment, the specific situation of the battery cell being pushed into the battery shell can be intuitively reflected by generating a curve to be detected, and the accuracy of abnormal battery cell judgment can be improved by comparing and analyzing the curve to be detected through historical detection data, and integrating the detection results of each curve to be detected. The above judgment process does not require manual inspection, which improves the intelligence level of the battery cell detection process. In addition, by analyzing the curve to be detected through historical detection data, the main abnormal problems in the production process can be effectively determined for targeted solutions, which can improve the accuracy and efficiency of abnormal detection in the battery cell shell process.
[0075] In some embodiments, the electronic device may perform detection on one or more curves to be detected based on historical detection data to obtain a detection result corresponding to each curve to be detected, which may include the following steps:
[0076] Generate a standard curve corresponding to each curve to be tested based on historical test data, and determine the slope threshold corresponding to each standard curve based on each standard curve;
[0077] Determine the slope of each curve to be detected, and compare the slope of each curve to be detected with a corresponding slope threshold to obtain a slope comparison result of each curve to be detected;
[0078] Determine the similarity between each curve to be tested and the corresponding standard curve, and compare each similarity with a similarity threshold to obtain a similarity comparison result for each curve to be tested;
[0079] According to the slope comparison result and the similarity comparison result of each curve to be detected, the detection result corresponding to each curve to be detected is obtained.
[0080] In an embodiment of the present disclosure, the electronic device can generate one or more standard curves based on historical detection data, and the standard curves correspond to the curves to be detected one by one. For example, if the electronic device generates three curves to be detected based on detection data of three data categories, then the electronic device can generate three standard curves based on the historical detection data of the corresponding data categories. The electronic device then determines the slope threshold corresponding to each standard curve. In specific implementation, for each standard curve, the electronic device can generate multiple basic curves based on a number of historical detection data, such as 500, calculate the slope of each basic curve and sort them in order from small to large or from large to small, select the 50% basic curves with slopes in the middle, calculate the average value of these basic curves as the slope threshold of the standard curve, and fit the standard curve by numerical method. Among them, the basic curve is a curve generated based on the detection data of any historical battery cell.
[0081] The electronic device determines the slope of each curve to be detected and compares the slope of each curve to the slope threshold of the corresponding standard curve to obtain a slope comparison result for each curve to be detected. In a specific implementation, for a curve to be detected, if the slope of the curve to be detected is less than the slope threshold of the corresponding standard curve, the slope comparison result of the curve to be detected is determined to be abnormal; alternatively, if the slope of the curve to be detected is greater than the slope threshold of the corresponding standard curve, the slope comparison result of the curve to be detected is determined to be abnormal; this is not specifically limited here.
[0082] The electronic device can determine the similarity between each curve to be detected and the corresponding standard curve, and compare each similarity with a similarity threshold to obtain a similarity comparison result for each curve to be detected. In specific implementations, the similarity threshold is an empirical value. The electronic device can determine the similarity between each curve to be detected and the corresponding standard curve based on a point-based method, a shape-based method, or a segment-based method, and compare each similarity with a similarity threshold or a corresponding similarity threshold to obtain a similarity comparison result for each curve to be detected. For a curve to be detected, if the similarity of the curve to be detected is less than the corresponding similarity threshold, the slope comparison result of the curve to be detected is determined to be abnormal.
[0083] Through the above method, the electronic device can obtain the slope comparison result and similarity comparison result of each curve to be detected, and determine the detection result corresponding to each curve to be detected based on the slope comparison result and the similarity comparison result. In specific implementation, for a curve to be detected, if the slope comparison result or the similarity comparison result is abnormal, the detection result corresponding to the curve to be detected is determined to be abnormal; alternatively, if both the slope comparison result and the similarity comparison result are abnormal, the detection result corresponding to the curve to be detected is determined to be abnormal.
[0084] By adopting the above embodiment, by constructing a standard curve and comparing the slope and overall similarity between the curve to be detected and the corresponding standard curve, the accuracy of the analysis of the curve to be detected can be further improved, and the curve to be detected can be analyzed and detected more efficiently, thereby improving the efficiency of the entire anomaly detection process.
[0085] In one embodiment, please refer to FIG3 , which is a flow chart of another method for detecting abnormalities in battery cell insertion provided by an embodiment of the present disclosure. This method can be applied to the aforementioned electronic device 10. As shown in FIG3 , the method may include the following steps:
[0086] 310. Obtain a displacement value and / or a thrust value of the battery cell being pushed into the battery housing.
[0087] In the disclosed embodiments, the electronic device can use a sensing device, such as an encoder, to obtain a displacement value of a battery cell being pushed into the battery housing by a pushing device, and can use a sensing device, such as a pressure sensor, to obtain a thrust value of the pushing device pushing the battery cell into the battery housing. The electronic device can obtain the thrust value and displacement value according to a preset acquisition rule. The acquisition rule is the same as the aforementioned detection data acquisition process and will not be further described here.
[0088] 320. Generate a curve to be detected corresponding to the thrust value according to the thrust value, and / or generate a curve to be detected corresponding to the displacement value according to the displacement value.
[0089] In an embodiment of the present disclosure, the electronic device may generate a curve to be detected corresponding to the thrust value based on the thrust value, and may generate a curve to be detected corresponding to the displacement value based on the displacement value. In specific implementations, if the electronic device collects either the thrust value or the displacement value, it should generate a curve to be detected corresponding to the thrust value or a curve to be detected corresponding to the displacement value; if the electronic device collects both the thrust value and the displacement value, it may generate a curve to be detected corresponding to the thrust value and / or a curve to be detected corresponding to the displacement value.
[0090] 330. Detect the curve to be detected corresponding to the thrust value and / or the curve to be detected corresponding to the displacement value based on the historical detection data to obtain a detection result corresponding to each curve to be detected; the historical detection data is the detection data when no abnormality occurs during the process of the battery cell being pushed into the battery housing.
[0091] In an embodiment of the present disclosure, the historical detection data corresponding to the detection data may include historical thrust values and historical displacement values, wherein the historical thrust values are the thrust data when no abnormality occurs during the historical process of the battery cell being pushed into the battery shell by the pushing device, and the historical displacement values are the displacement data when no abnormality occurs during the historical process of the battery cell being pushed into the battery shell by the pushing device.
[0092] The electronic device detects the curve to be detected corresponding to the thrust value and / or the curve to be detected corresponding to the displacement value based on the historical detection data, thereby obtaining a detection result corresponding to each curve to be detected. In a specific implementation, for the curve to be detected corresponding to the thrust value, the electronic device may use the historical thrust value to detect the curve to be detected corresponding to the thrust value to obtain a detection result of the curve to be detected corresponding to the thrust value; wherein the electronic device may draw a historical thrust value curve based on the historical thrust value, and compare the historical thrust value curve with the curve to be detected corresponding to the thrust value to obtain a detection result of the curve to be detected corresponding to the thrust value; or the electronic device may compare the historical thrust value with the thrust value of each peak (or the highest peak) and / or the thrust value of each trough (or the lowest trough) in the curve to be detected corresponding to the thrust value, and / or the number of peaks / troughs in the curve to be detected corresponding to the thrust value, to obtain a detection result of the curve to be detected corresponding to the thrust value. Similarly, for the curve to be detected corresponding to the displacement value, the electronic device can use the historical displacement value to detect the curve to be detected corresponding to the displacement value, and obtain the detection result of the curve to be detected corresponding to the displacement value; wherein, the electronic device can draw a historical displacement value curve according to the historical displacement value, and compare the historical displacement value curve with the curve to be detected corresponding to the displacement value to obtain the detection result of the curve to be detected corresponding to the displacement value; or, the electronic device can compare the displacement value of each peak (or the highest peak) in the curve to be detected corresponding to the displacement value, and / or the displacement value of each trough (or the lowest trough), and / or the number of peaks / troughs in the curve to be detected corresponding to the displacement value, to obtain the detection result of the curve to be detected corresponding to the displacement value.
[0093] 340. Determine the abnormal result of the battery cell entering the shell according to the test result corresponding to each curve to be tested.
[0094] In the embodiment of the present disclosure, if only the curve to be detected corresponding to the thrust value is generated, then the detection result of the curve to be detected corresponding to the thrust value is abnormal, and the battery cell shell-entry process is determined to be abnormal; if the detection result of the curve to be detected corresponding to the thrust value is normal, the battery cell shell-entry process is determined to be normal. If only the curve to be detected corresponding to the displacement value is generated, then the detection result of the curve to be detected corresponding to the displacement value is abnormal, and the battery cell shell-entry process is determined to be abnormal; if the detection result of the curve to be detected corresponding to the displacement value is normal, the battery cell shell-entry process is determined to be normal. If both the curve to be detected corresponding to the thrust value and the curve to be detected corresponding to the displacement value are generated, then the electronic device can determine that the battery cell shell-entry process is abnormal when the detection result of the curve to be detected corresponding to the thrust value is abnormal, or when the detection result of the curve to be detected corresponding to the displacement value is abnormal; the electronic device can also determine that the battery cell shell-entry process is abnormal when the detection result of the curve to be detected corresponding to the thrust value and the detection result of the curve to be detected corresponding to the displacement value are both abnormal.
[0095] The above embodiment uses pressure values and / or displacement values as test data, which can better reflect the process of the battery cell being pushed into the battery casing. Generating a corresponding curve to be tested based on the pressure values and / or displacement values, and testing the corresponding curve to be tested based on historical test data to ultimately determine the abnormal result of the battery cell insertion process, can more accurately determine the abnormal state of the battery cell insertion process, thereby improving the accuracy of the battery cell insertion abnormality judgment.
[0096] In some embodiments, the electronic device detects the curve to be detected corresponding to the thrust value and / or the curve to be detected corresponding to the displacement value based on the historical detection data, and obtains the detection result corresponding to each curve to be detected, which may include the following steps:
[0097] Generate a standard curve corresponding to the thrust value and / or a standard curve corresponding to the displacement value based on the historical detection data, and determine a slope threshold corresponding to each standard curve based on each standard curve;
[0098] Determine the slope of each curve to be detected, and compare the slope of each curve to be detected with a corresponding slope threshold value to obtain a slope comparison result of the curve to be detected corresponding to the thrust value and / or a slope comparison result of the curve to be detected corresponding to the displacement value;
[0099] Determine the similarity between each curve to be tested and the corresponding standard curve, and compare each similarity with a similarity threshold to obtain a similarity comparison result of the curve to be tested corresponding to the thrust value and / or a similarity comparison result of the curve to be tested corresponding to the displacement value;
[0100] According to the slope comparison result and the similarity comparison result of each curve to be detected, the detection result corresponding to each curve to be detected is obtained.
[0101] In an embodiment of the present disclosure, the historical detection data corresponding to the detection data may include historical thrust values and historical displacement values. The electronic device may generate a calibration curve corresponding to the thrust values based on the historical thrust values, and / or generate a calibration curve corresponding to the displacement values based on the historical displacement values. The electronic device then determines a slope threshold corresponding to each calibration curve.
[0102] The electronic device determines the slope of the curve to be detected corresponding to the thrust value, and compares the slope of the curve to be detected corresponding to the thrust value with a slope threshold of a standard curve corresponding to the thrust value, thereby obtaining a slope comparison result of the curve to be detected corresponding to the thrust value. And / or, the electronic device determines the slope of the curve to be detected corresponding to the displacement value, and compares the slope of the curve to be detected corresponding to the displacement value with a slope threshold of a standard curve corresponding to the displacement value, thereby obtaining a slope comparison result of the curve to be detected corresponding to the displacement value.
[0103] The electronic device may determine the similarity between the curve to be detected corresponding to the thrust value and a standard curve corresponding to the thrust value, and compare the similarity with a similarity threshold, thereby obtaining a similarity comparison result for the curve to be detected corresponding to the thrust value. And / or, the electronic device may determine the similarity between the curve to be detected corresponding to the displacement value and a standard curve corresponding to the displacement value, and compare the similarity with a similarity threshold, thereby obtaining a similarity comparison result for the curve to be detected corresponding to the displacement value.
[0104] Through the above method, the electronic device can obtain the slope comparison result and similarity comparison result of the curve to be detected corresponding to the thrust value, and / or the slope comparison result and similarity comparison result of the curve to be detected corresponding to the displacement value. The electronic device can jointly determine the detection result of the curve to be detected corresponding to the thrust value based on the slope comparison result and similarity comparison result of the curve to be detected corresponding to the thrust value. The electronic device can jointly determine the detection result of the curve to be detected corresponding to the displacement value based on the slope comparison result and similarity comparison result of the curve to be detected corresponding to the displacement value.
[0105] In a specific implementation, for a curve to be detected, if the slope comparison result or the similarity comparison result is abnormal, the detection result corresponding to the curve to be detected is determined to be abnormal; or, only when both the slope comparison result and the similarity comparison result are abnormal, the detection result corresponding to the curve to be detected is determined to be abnormal.
[0106] By adopting the above embodiment, by constructing a standard curve and / or displacement value corresponding to the thrust value, and comparing the slope and overall similarity between the curve to be detected and the corresponding standard curve, the accuracy of the analysis of the curve to be detected can be further improved, and the curve to be detected can be analyzed and detected more efficiently, thereby improving the efficiency of the entire battery cell shell abnormality detection process.
[0107] In one embodiment, please refer to FIG4 , which is a flow chart of another method for detecting abnormalities in battery cell insertion provided by an embodiment of the present disclosure. This method can be applied to the aforementioned electronic device 10. As shown in FIG4 , the method may include the following steps:
[0108] 410. Obtain detection data during the process of the battery cell being pushed into the battery casing.
[0109] 420. Generate one or more curves to be detected based on the detection data.
[0110] 430. Determine abnormal data corresponding to each curve to be detected based on the detection data.
[0111] In the disclosed embodiments, the electronic device determines abnormal data corresponding to each curve to be detected based on the detection data. In specific implementations, the electronic device may match the data features of the detection data with different data features corresponding to the abnormal data. Each data feature corresponding to the abnormal data may correspond to one piece of abnormal data. Each curve to be detected may correspond to one or more pieces of abnormal data.
[0112] 440. Determine an abnormal data threshold based on historical detection data.
[0113] In the disclosed embodiments, the abnormal data threshold can be determined based on historical detection data. For example, the electronic device can match the data characteristics of the historical detection data with different data characteristics corresponding to the abnormal data, and determine the abnormal data corresponding to the data characteristic with the greatest matching degree as the abnormal data threshold. Alternatively, the historical detection data can be filtered out to identify historical detection data that meets the data characteristics of the abnormal data, and the abnormal data threshold can be determined from the filtered historical detection data by selecting the maximum value or calculating the average value.
[0114] 450. Compare the abnormal data corresponding to each curve to be detected with the abnormal data threshold to obtain a detection result corresponding to each curve to be detected.
[0115] In the disclosed embodiments, the electronic device compares the abnormal data corresponding to each curve to be detected with an abnormal data threshold to obtain a detection result corresponding to each curve to be detected. In specific implementations, when the abnormal data corresponding to a curve to be detected is greater than the abnormal data threshold, the electronic device may determine the detection result corresponding to the curve to be detected as abnormal; alternatively, when the abnormal data corresponding to a curve to be detected is less than the abnormal data threshold, the electronic device may determine the detection result corresponding to the curve to be detected as abnormal; this is not specifically limited here.
[0116] By adopting the above embodiment, the abnormal data corresponding to the curve to be detected is determined, and the detection result corresponding to each curve to be detected is determined based on the comparison result between the abnormal data corresponding to the curve to be detected and the abnormal data threshold determined by the historical detection data. The abnormal situation of the battery cell entering the shell is judged by comparing the specific data, which can more accurately judge the abnormal state of the battery cell entering the shell process, thereby improving the accuracy of the judgment of the battery cell entering the shell abnormality.
[0117] In some embodiments, the abnormal data includes a jamming value and a glitch value, and the abnormal data threshold includes a jamming threshold and a glitch threshold.
[0118] The electronic device performs the step of comparing the abnormal data corresponding to each curve to be detected with the abnormal data threshold to obtain the detection result corresponding to each curve to be detected, which may include the following steps:
[0119] Compare the jamming value corresponding to each curve to be detected with the jamming threshold to obtain the jamming comparison result corresponding to each curve to be detected;
[0120] Compare the glitch value corresponding to each curve to be detected with the glitch threshold to obtain the glitch comparison result corresponding to each curve to be detected;
[0121] According to the jam comparison result corresponding to each curve to be detected and the burr comparison result corresponding to each curve to be detected, the detection result corresponding to each curve to be detected is obtained.
[0122] In an embodiment of the present disclosure, the electronic device determines the jam value and glitch value of the curve to be detected based on the detection data, such as thrust value and displacement value, used to generate the curve to be detected. In a specific implementation, the electronic device can detect the peak of the curve to be detected to match the peak with the characteristic curve shape of the glitch and jam. If the match is successful, the jam value and glitch value of the curve to be detected are determined based on the detection data corresponding to the peak. Each curve to be detected may include multiple jam values and glitch values.
[0123] The electronic device determines a glitch threshold and a jam threshold based on historical detection data. The electronic device may generate a standard curve based on the historical detection data, and determine the jam value and glitch value of the standard curve according to the above method for determining the jam value and glitch value of the curve to be detected, and determine the jam threshold based on each jam value, and determine the glitch threshold based on each glitch value. For example, the maximum jam value of the standard curve is determined as the jam threshold, and the maximum glitch value of the standard curve is determined as the glitch threshold.
[0124] The electronic device compares the jam value corresponding to each curve to be detected with the jam threshold value to obtain a jam comparison result corresponding to each curve to be detected; and compares the glitch value corresponding to each curve to be detected with the glitch threshold value to obtain a glitch comparison result corresponding to each curve to be detected. The electronic device obtains a detection result corresponding to each curve to be detected based on the jam comparison result corresponding to each curve to be detected and the glitch comparison result corresponding to each curve to be detected.
[0125] During specific implementation, for a curve to be detected, if the curve to be detected has only one jam value, the electronic device can determine the jam comparison result of the curve to be detected based on the jam value; if the curve to be detected contains more than one jam value, the electronic device can determine the jam comparison result of the curve to be detected based on the number of jam values that do not meet the jam threshold. For example, if more than half of the jam values are greater than the jam threshold, the jam comparison result is abnormal. Similarly, for a curve to be detected, if the curve to be detected has only one glitch value, the electronic device can determine the glitch comparison result of the curve to be detected based on the glitch value; if the curve to be detected contains more than one glitch value, the electronic device can determine the glitch comparison result of the curve to be detected based on the number of glitch values that do not meet the glitch threshold.
[0126] The electronic device obtains a detection result corresponding to each curve to be detected based on the jam comparison result and the glitch comparison result corresponding to each curve to be detected. In a specific implementation, for a curve to be detected, if the jam comparison result or the glitch comparison result corresponding to the curve to be detected is abnormal, the detection result corresponding to the curve to be detected is determined to be abnormal; alternatively, if both the jam comparison result and the glitch comparison result corresponding to the curve to be detected are abnormal, the detection result corresponding to the curve to be detected is determined to be abnormal.
[0127] Since burrs and jams are the main abnormalities in the battery cell assembly process, the above embodiment is adopted to determine the detection result corresponding to each curve to be detected by comparing the burr value with the jam value, which can more accurately judge the abnormal state of the battery cell shell insertion process and improve the accuracy of the battery cell shell insertion abnormality judgment.
[0128] 460. Determine the abnormal result of the battery cell entering the shell based on the test result corresponding to each curve to be tested.
[0129] In some embodiments, the anomaly detection method may further include the following steps:
[0130] Determining, based on a jam comparison result corresponding to a target curve to be detected, a first number of the target curves to be detected whose jam values are greater than a jam threshold value; the target curve to be detected is any curve to be detected;
[0131] Determine, based on the burr comparison result corresponding to the target curve to be detected, a second number of burr values in the target curve to be detected that are greater than a burr threshold;
[0132] Determining an anomaly score corresponding to the target curve to be detected based on the first number, the weight of the jam comparison result, the second number, and the weight of the burr comparison result; wherein the weight of the jam comparison result is greater than the weight of the burr comparison result;
[0133] The abnormality level of the battery cell entering the shell is determined according to the abnormality score corresponding to each of the curves to be detected.
[0134] In an embodiment of the present disclosure, the number of jamming values included in the curve to be detected may be one or more, and the number of glitch values included may also be one or more. For any curve to be detected, that is, the target curve to be detected, the electronic device can count the number of jamming values in the target curve to be detected that are greater than the jamming threshold value, that is, the first number, after determining the corresponding jamming comparison result based on the jamming value included in the target curve to be detected; similarly, for the target curve to be detected, the electronic device can count the number of glitch values in the target curve to be detected that are greater than the glitch threshold value, that is, the second number, after determining the corresponding glitch comparison result based on the glitch value included in the curve to be detected.
[0135] The electronic device can then calculate the anomaly score corresponding to the target curve to be tested based on the first number, the second number, the weight of the jam comparison result, and the weight of the glitch comparison result, and determine the abnormality level of the battery cell insertion based on the anomaly score corresponding to each curve to be tested. Since jamming is a more abnormal condition during the battery cell insertion process, the weight of the jam comparison result is greater than the weight of the glitch comparison result.
[0136] During specific implementation, the electronic device obtains from statistics that the first number of curves a to be detected is 1, and the second number is also 1, while the weight of the jam comparison result is 2, and the weight of the burr comparison result is 1. Therefore, the abnormality score corresponding to the curve a to be detected is 1*2+1*1=3. The electronic device obtains from statistics that the first number of curves b to be detected is 2, and the second number is also 2. Therefore, the abnormality score corresponding to the curve b to be detected is 2*2+2*1=7. Different abnormality levels correspond to different abnormality score intervals. The electronic device can determine the abnormality level of the battery cell entering the shell based on the interval where the abnormality score is 10.
[0137] By adopting the above embodiment, by assigning different weights to the jam comparison results and the burr comparison results, the abnormal level of the battery cell entering the shell is determined according to the number of jam comparison results and the number of burr comparison results in the battery cell entering the shell process. The abnormal degree of each battery cell entering the shell can be analyzed more effectively, thereby better improving the problems existing in the process, and further improving the intelligence level of the battery cell entering the shell abnormality detection process.
[0138] In one embodiment, please refer to FIG5 , which is a flow chart of another method for detecting abnormalities in battery cell insertion provided by an embodiment of the present disclosure. This method can be applied to the aforementioned electronic device 10. As shown in FIG5 , the method may include the following steps:
[0139] 510. Obtain detection data during the process of the battery cell being pushed into the battery casing.
[0140] 520. Generate one or more curves to be detected based on the detection data.
[0141] 530. According to the battery cell shelling process, each curve to be tested is divided into multiple sub-curves; the multiple sub-curves correspond one-to-one to the multiple shelling sub-processes of the battery cell shelling process.
[0142] 540. Detect each sub-curve of each curve to be detected based on historical detection data to obtain detection results corresponding to each sub-curve of each curve to be detected, and determine the detection result corresponding to each curve to be detected based on the detection results corresponding to each sub-curve. The historical detection data refers to detection data obtained when no abnormality occurred during the process of pushing the battery cell into the battery housing.
[0143] In an embodiment of the present disclosure, the electronic device divides each curve to be detected into multiple sub-curves according to the battery cell shell process flow, wherein the multiple sub-curves correspond one-to-one to the multiple shell sub-processes of the battery cell shell process flow. In a specific implementation, the shell sub-process of the battery cell shell process flow includes one or more of the initial position, the pole suction position, the shell preparation position, the shell mold opening position, and the shell completion position; if the multiple shell sub-processes of the battery cell shell process flow include all of the above shell sub-processes, then the electronic device can divide each curve to be detected into 6 sub-curves.
[0144] For each sub-curve, the electronic device can detect the sub-curve according to the stored historical detection data to obtain the detection result corresponding to each sub-curve. Then, the electronic device determines the detection result corresponding to each curve to be detected based on the detection result corresponding to each sub-curve. In a specific implementation, for a curve to be detected, the curve to be detected is divided into 6 sub-curves. The electronic device can draw six standard sub-curves according to the historical detection data, compare each standard sub-curve with the corresponding sub-curve to obtain the detection result corresponding to each sub-curve, and then the electronic device can determine the detection result corresponding to the curve to be detected based on the detection result corresponding to each sub-curve. For example, if the detection result corresponding to one sub-curve in the curve to be detected is abnormal, then the electronic device will judge the detection result corresponding to the curve to be detected as abnormal; or, if the detection results corresponding to a certain number of sub-curves in the curve to be detected are abnormal, then the electronic device will judge the detection result corresponding to the curve to be detected as abnormal; or, only when the detection results corresponding to all sub-curves in the curve to be detected are abnormal, will the electronic device judge the detection result corresponding to the curve to be detected as abnormal.
[0145] By adopting the above embodiment, by dividing the curve to be detected into multiple sub-curves for abnormality analysis, it is possible to effectively reflect the process in which abnormalities occur in the shell entry process flow, so as to determine the main abnormal problem; and abnormality analysis is performed based on the abnormality analysis results of the multiple sub-curves, further improving the accuracy of the abnormality detection process.
[0146] 550. Determine an abnormal result of the battery cell entering the shell based on the test result corresponding to each curve to be tested.
[0147] Please refer to Figure 6, which is a schematic diagram of a curve anomaly detection process provided by an embodiment of the present disclosure. In some embodiments, the electronic device performs a test on each sub-curve of each curve to be detected based on historical detection data, obtains a detection result corresponding to each sub-curve of each curve to be detected, and determines a detection result corresponding to each curve to be detected based on the detection result corresponding to each sub-curve. The process may include the following steps:
[0148] Generate a standard sub-curve corresponding to each sub-curve based on historical detection data, and determine a slope threshold based on each standard sub-curve;
[0149] Determine the slope of each sub-curve, and compare the slope of each sub-curve with a slope threshold to obtain a slope comparison result of each sub-curve;
[0150] Determine the similarity between each sub-curve and the corresponding standard sub-curve, and compare each similarity with a similarity threshold to obtain a similarity comparison result for each sub-curve;
[0151] According to the slope comparison result and similarity comparison result of each sub-curve, the detection result corresponding to each curve to be detected is obtained.
[0152] In an embodiment of the present disclosure, as shown in FIG6 , the electronic device can generate a standard curve based on historical detection data, and divide the standard curve into multiple standard sub-curves according to multiple shell-entry sub-processes of the battery cell shell-entry process, wherein each standard sub-curve corresponds one-to-one to a sub-curve in the curve to be detected.
[0153] The electronic device can determine the maximum slope of each standard sub-curve and determine a slope threshold based on each maximum slope. Optionally, a slope threshold can be determined using statistical methods, such as selecting the maximum value, selecting the minimum value, or calculating the average value. For each sub-curve, the electronic device can use the maximum slope or average slope of the sub-curve as the slope of the sub-curve and compare this slope with the slope threshold to obtain a slope comparison result for each sub-curve. In specific implementations, the electronic device can determine that the slope comparison result of a sub-curve with a slope greater than the slope threshold is abnormal.
[0154] The electronic device calculates the similarity between each sub-curve and its corresponding sub-curve and compares the obtained similarity with a similarity threshold to obtain a similarity comparison result for each sub-curve. The similarity threshold may be an empirical value. In specific implementations, the electronic device may determine that the similarity comparison result for a sub-curve whose similarity is less than the similarity threshold is abnormal.
[0155] By the above method, the electronic device can obtain the slope comparison result and similarity comparison result of each sub-curve, and jointly determine the detection result corresponding to the curve to be detected based on the slope comparison result and similarity comparison result of each sub-curve. In specific implementation, for a curve to be detected, it is divided into 6 sub-curves; if the slope comparison result or similarity comparison result of a sub-curve is abnormal, the detection result corresponding to the sub-curve is determined to be abnormal; or, if the slope comparison result and similarity comparison result of a sub-curve are both abnormal, the detection result corresponding to the sub-curve is determined to be abnormal. If the detection result corresponding to one sub-curve in the curve to be detected is abnormal, the electronic device will judge the detection result corresponding to the curve to be detected to be abnormal; or, if the detection results corresponding to a certain number (such as more than 3) of sub-curves in the curve to be detected are abnormal, the electronic device will judge the detection result corresponding to the curve to be detected to be abnormal; or, if the detection results corresponding to all sub-curves in the curve to be detected are abnormal, the electronic device will judge the detection result corresponding to the curve to be detected to be abnormal.
[0156] By adopting the above embodiment, by constructing a standard curve and comparing the slope and overall similarity between the curve to be detected and the corresponding standard curve, the accuracy of the analysis of the curve to be detected can be further improved, and the curve to be detected can be analyzed and detected more efficiently, thereby improving the efficiency of the entire anomaly detection process; and performing anomaly analysis based on the anomaly analysis results of multiple sub-curves also improves the accuracy of the anomaly detection process.
[0157] Please refer to Figure 7, which is a schematic diagram of the jamming and glitch detection process provided by an embodiment of the present disclosure. In some embodiments, the electronic device performs the steps of separately detecting each sub-curve of each curve to be detected based on historical detection data, obtaining a detection result corresponding to each sub-curve of each curve to be detected, and determining a detection result corresponding to each curve to be detected based on the detection result corresponding to each sub-curve, which may include the following steps:
[0158] According to the detection data, determine the jamming value and glitch value corresponding to each sub-curve;
[0159] Determine abnormal data thresholds based on historical detection data;
[0160] Compare the jamming value corresponding to each sub-curve with the jamming threshold value to obtain the jamming comparison result corresponding to each sub-curve;
[0161] Compare the glitch value corresponding to each sub-curve with the glitch threshold value to obtain the glitch comparison result corresponding to each sub-curve;
[0162] According to the jam comparison result corresponding to each sub-curve and the burr comparison result corresponding to each sub-curve, the detection result corresponding to each curve to be detected is obtained.
[0163] In an embodiment of the present disclosure, as shown in FIG7 , the electronic device determines the jam value and glitch value of each sub-curve based on the detection data, such as thrust value and displacement value, based on which each sub-curve is generated. In a specific implementation, the electronic device can detect the peak of the sub-curve to match the peak with the characteristic curve morphology of the glitch and jam. If the match is successful, the jam value and glitch value of the sub-curve are determined based on the detection data corresponding to the peak. Each sub-curve may include multiple jam values and glitch values.
[0164] The electronic device determines a glitch threshold and a jam threshold based on historical detection data. The electronic device may generate a standard curve based on the historical detection data and divide the standard curve into multiple standard sub-curves. The jam value and glitch value of the standard sub-curve are determined based on the above-described method for determining the jam value and glitch value of the sub-curve. The jam threshold is determined based on the jam value of each standard sub-curve, and the glitch threshold is determined based on the glitch value of each standard sub-curve. For example, the maximum jam value in the standard sub-curve is determined as the jam threshold, and the maximum glitch value in the standard sub-curve is determined as the glitch threshold.
[0165] The electronic device compares the jam value corresponding to each sub-curve with the jam threshold to obtain a jam comparison result for each sub-curve; and compares the glitch value corresponding to each sub-curve with the glitch threshold to obtain a glitch comparison result for each sub-curve. Based on the jam comparison result and the glitch comparison result corresponding to each sub-curve, the electronic device determines the detection result corresponding to the curve to be detected.
[0166] In a specific implementation, a curve to be detected is divided into six sub-curves. Each sub-curve can have one or more stutter values. The electronic device can then determine the stutter comparison result for the sub-curve based on each stutter value of the sub-curve. In a specific implementation, if a stutter value in a sub-curve does not meet the stutter threshold, the stutter comparison result is abnormal, and the stutter comparison result for that sub-curve is also abnormal.
[0167] Similarly, each sub-curve can have one or more glitch values. The electronic device can then determine a glitch comparison result for the sub-curve based on each glitch value of the sub-curve. In a specific implementation, if a glitch value in a sub-curve does not meet the glitch threshold, the glitch comparison result is abnormal, and the glitch comparison result for the sub-curve is also abnormal.
[0168] The electronic device obtains the detection result corresponding to each curve to be detected based on the jam comparison result corresponding to each sub-curve and the glitch comparison result corresponding to each sub-curve. In specific implementation, for a curve to be detected, the curve to be detected is divided into 6 sub-curves. If the jam comparison result of at least one sub-curve is abnormal and / or the glitch comparison result is abnormal, then the detection result corresponding to the curve to be detected is also abnormal; if the jam comparison result and the glitch comparison result of each sub-curve are both normal, then the detection result corresponding to the curve to be detected is also normal. More specifically, if the jam comparison result of at least one sub-curve is abnormal and the glitch comparison result of each sub-curve is normal, then the detection result corresponding to the curve to be detected is jam; if the glitch comparison result of at least one sub-curve is abnormal and the jam comparison result of each sub-curve is normal, then the detection result corresponding to the curve to be detected is glitch.
[0169] By adopting the above embodiment, the abnormal situation of the battery cell is judged by comparing the jam value and the burr value, which can more accurately judge the abnormal state of the battery cell shell insertion process, thereby improving the accuracy of the abnormal judgment of the battery cell shell insertion; and the abnormal analysis results based on the multi-segment sub-curve are used to perform abnormal analysis, which also improves the accuracy of the abnormal detection process.
[0170] In some embodiments, the anomaly detection method may further include the following steps:
[0171] According to the jam comparison result corresponding to the target sub-curve, determine the number of jam values in the target sub-curve that are greater than the jam threshold; the target sub-curve is any sub-curve;
[0172] According to the glitch comparison result corresponding to the target sub-curve, the number of glitch values in the target sub-curve that are greater than the glitch threshold is determined;
[0173] Determine the anomaly score corresponding to the target sub-curve based on the number of jam values in the target sub-curve that are greater than the jam threshold, the weight of the jam comparison result, the number of glitch values in the target sub-curve that are greater than the glitch threshold, and the weight of the glitch comparison result. Determine the anomaly score corresponding to each curve to be detected based on the anomaly score corresponding to each sub-curve. The weight of the jam comparison result is greater than the weight of the glitch comparison result.
[0174] The abnormality level of the battery cell entering the shell is determined according to the abnormality score corresponding to each curve to be detected.
[0175] In an embodiment of the present disclosure, the curve to be detected can be divided into multiple sub-curves, and each sub-curve can contain one or more jam values and one or more glitch values. For any sub-curve, that is, a target sub-curve, the electronic device can count the number of jam values in the target sub-curve that are greater than a jam threshold after determining the corresponding jam comparison result based on the jam values contained in the target sub-curve; similarly, the electronic device can count the number of glitch values in the target sub-curve that are greater than the glitch threshold after determining the corresponding glitch comparison result based on the glitch values contained in the target sub-curve.
[0176] The electronic device can then calculate the anomaly score corresponding to the target sub-curve based on the number of jam values in the target sub-curve that exceed the jam threshold, the weight of the jam comparison result, the number of glitch values in the target sub-curve that exceed the glitch threshold, and the weight of the glitch comparison result. The electronic device then determines the abnormality level of the battery cell insertion process based on the anomaly score. Since jams are a more abnormal condition during the battery cell insertion process, the jam comparison result is weighted more heavily than the glitch comparison result.
[0177] During specific implementation, the curve to be detected is divided into 6 sub-curves. The electronic device counts all sub-curves and finds that the number of jamming values greater than the jamming threshold is 2, and the number of glitch values greater than the glitch threshold is also 2. The weight of the jamming comparison result is 2, and the weight of the glitch comparison result is 1. Therefore, the anomaly score is 2*2+2*1=7. Therefore, the anomaly score corresponding to the curve to be detected is 2*2+2*1=7. Different anomaly levels correspond to different anomaly score intervals. The electronic device can determine the anomaly level of the battery cell entering the shell based on the interval where the anomaly score is 7.
[0178] By adopting the above embodiment, by assigning different weights to the jam comparison results and the burr comparison results, the abnormality of the battery cell shelling process is determined according to the number of jam comparison results and the number of burr comparison results in the battery cell shelling process, and the abnormality degree of each battery cell shelling process can be more effectively analyzed, thereby better improving the problems existing in the process, and further improving the intelligence level of the abnormality detection process of the battery cell shelling process; and performing abnormality analysis based on the abnormality analysis results of multiple sub-curves also improves the accuracy of the abnormality detection process.
[0179] Please refer to Figure 8, which is a schematic diagram of the structure of a battery cell shell anomaly detection device provided in an embodiment of the present disclosure. The anomaly detection device can be applied to electronic device 10. As shown in Figure 8, the anomaly detection device 800 may include: a data acquisition module 810, a curve construction module 820, a curve detection module 830, and an anomaly detection module 840.
[0180] The data acquisition module 810 is used to acquire detection data during the process of the battery cell being pushed into the battery housing;
[0181] A curve construction module 820 is used to generate one or more curves to be detected based on the detection data;
[0182] The curve detection module 830 is configured to detect one or more curves to be detected based on historical detection data to obtain a detection result corresponding to each curve to be detected; the historical detection data is the detection data when no abnormality occurs during the process of the battery cell being pushed into the battery housing;
[0183] The abnormality detection module 840 is used to determine the abnormality result of the battery cell entering the shell according to the detection result corresponding to each curve to be detected.
[0184] In some embodiments, the detection data includes a displacement value and / or a thrust value of the battery cell being pushed into the battery housing.
[0185] The curve construction module 820 is further configured to:
[0186] A curve to be detected corresponding to the thrust value is generated according to the thrust value, and / or a curve to be detected corresponding to the displacement value is generated according to the displacement value.
[0187] In some embodiments, the curve detection module 830 is further configured to:
[0188] Generate a standard curve corresponding to each curve to be tested based on historical test data, and determine the slope threshold corresponding to each standard curve based on each standard curve;
[0189] Determine the slope of each curve to be detected, and compare the slope of each curve to be detected with a corresponding slope threshold to obtain a slope comparison result of each curve to be detected;
[0190] Determine the similarity between each curve to be tested and the corresponding standard curve, and compare each similarity with a similarity threshold to obtain a similarity comparison result for each curve to be tested;
[0191] According to the slope comparison result and the similarity comparison result of each curve to be detected, the detection result corresponding to each curve to be detected is obtained.
[0192] In some embodiments, the anomaly detection device shown in FIG8 further includes:
[0193] The data detection module 850 is used to determine the abnormal data corresponding to each curve to be detected based on the detection data;
[0194] The curve detection module 830 is further configured to:
[0195] Determine abnormal data thresholds based on historical detection data;
[0196] The abnormal data corresponding to each curve to be detected is compared with the abnormal data threshold to obtain the detection result corresponding to each curve to be detected.
[0197] In some embodiments, the abnormal data includes a jamming value and a glitch value, and the abnormal data threshold includes a jamming threshold and a glitch threshold;
[0198] The curve detection module 830 is further configured to:
[0199] Compare the jamming value corresponding to each curve to be detected with the jamming threshold to obtain the jamming comparison result corresponding to each curve to be detected;
[0200] Compare the glitch value corresponding to each curve to be detected with the glitch threshold to obtain the glitch comparison result corresponding to each curve to be detected;
[0201] According to the jam comparison result corresponding to each curve to be detected and the burr comparison result corresponding to each curve to be detected, the detection result corresponding to each curve to be detected is obtained.
[0202] In some embodiments, the anomaly detection module 840 is further configured to:
[0203] Determining, based on a jam comparison result corresponding to a target curve to be detected, a first number of the target curves to be detected whose jam values are greater than a jam threshold value; the target curve to be detected is any curve to be detected;
[0204] Determine, based on the burr comparison result corresponding to the target curve to be detected, a second number of burr values in the target curve to be detected that are greater than a burr threshold;
[0205] Determining an anomaly score corresponding to the target curve to be detected based on the first number, the weight of the jam comparison result, the second number, and the weight of the burr comparison result; wherein the weight of the jam comparison result is greater than the weight of the burr comparison result;
[0206] The abnormality level of the battery cell entering the shell is determined according to the abnormality score corresponding to each curve to be detected.
[0207] In some embodiments, the curve construction module 820 is further configured to:
[0208] After generating one or more curves to be tested based on the test data, each curve to be tested is divided into multiple sub-curves according to the battery cell shelling process flow. The multiple sub-curves correspond one-to-one to the multiple shelling sub-processes of the battery cell shelling process flow. The curve detection module 830 is further used to:
[0209] Each sub-curve of each curve to be detected is detected respectively according to historical detection data to obtain a detection result corresponding to each sub-curve of each curve to be detected, and a detection result corresponding to each curve to be detected is determined according to the detection result corresponding to each sub-curve.
[0210] Please refer to Figure 9, which is an architecture diagram of a battery cell shell anomaly detection system according to an embodiment of the present disclosure. As shown in Figure 9, the system includes a data acquisition layer, a data processing layer, and a data display layer.
[0211] The data acquisition layer uses encoders to capture displacement data from the battery cell being pushed into the battery housing, and uses pressure sensors to capture force data from the cell being pushed into the battery housing. The data acquisition layer also includes a data acquisition platform, which collects force and displacement data according to pre-set acquisition rules and variable settings.
[0212] The data acquisition layer transmits the displacement data and pressure data to the data processing layer via data transmission. The data processing layer includes a detection module, a historical data statistics engine, and a database. The data processing layer can first determine whether there are any abnormalities in the acquisition process, specifically whether the equipment such as the encoder and pressure sensor is faulty. If not, the data is transmitted to the detection module. The detection module can first generate the curve to be detected, and determine the jamming value and glitch value of the curve to be detected based on the detection data such as thrust value and displacement value used to generate the curve to be detected. Then the jamming detection engine in the detection module can compare the jamming value corresponding to each curve to be detected with the jamming threshold value to obtain the jamming comparison result corresponding to each curve to be detected; the glitch detection engine in the detection module can compare the glitch value corresponding to each curve to be detected with the glitch threshold value to obtain the glitch comparison result corresponding to each curve to be detected.
[0213] At the same time, the historical data statistics engine can obtain historical detection data from the database and generate one or more standard curves based on the historical detection data. The standard curves correspond to the curves to be detected one by one. The data processing layer can determine the slope of each curve to be detected, and compare the slope of each curve to be detected with the slope threshold of the corresponding standard curve to obtain the slope comparison result of each curve to be detected. The data processing layer can also determine the similarity between each curve to be detected and the corresponding standard curve, and compare each similarity with the similarity threshold to obtain the similarity comparison result of each curve to be detected. The data processing layer can also detect the maximum value trend of the abnormal pressure data, judge the changes in the process of battery cell shelling, and determine whether the battery cell shelling process is abnormal.
[0214] The data processing layer can determine the detection result corresponding to the curve to be detected based on the above-obtained jam comparison results, burr comparison results, similarity detection results, slope detection results and maximum trend detection results.
[0215] The data display layer may include multiple terminal devices or display devices for displaying data trends, test results, and parameter settings during the shell entry process and anomaly detection process, so as to achieve real-time monitoring of anomaly detection results and ensure the efficiency of the shell entry process.
[0216] Please refer to Figure 10, which is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. As shown in Figure 10, the electronic device 1000 may include:
[0217] A memory 1010 storing executable program code;
[0218] a processor 1020 coupled to the memory 1010;
[0219] The processor 1020 calls the executable program code stored in the memory 1010 to execute any one of the anomaly detection methods provided in the embodiments of the present disclosure.
[0220] An embodiment of the present disclosure provides a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute any one of the anomaly detection methods provided by the embodiments of the present disclosure.
[0221] An embodiment of the present disclosure provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute any one of the anomaly detection methods provided by the embodiments of the present disclosure.
[0222] It should be understood that the references to "one embodiment" or "an embodiment" throughout the specification mean that the specific features, structures, or characteristics associated with the embodiment are included in at least one embodiment of the present disclosure. Therefore, the references to "in one embodiment" or "in an embodiment" throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. Those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required for the present disclosure.
[0223] In the various embodiments of the present disclosure, it should be understood that the size of the sequence numbers of the above-mentioned processes does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal strategy, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.
[0224] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of these units may be selected based on actual needs to achieve the objectives of this embodiment.
[0225] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.
[0226] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a memory and includes several requests for causing a computer device (which can be a personal computer, server, or network device, etc., specifically a processor in the computer device) to execute some or all of the steps of the above-mentioned method of each embodiment of the present disclosure.
[0227] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program. The program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.
[0228] The above is a detailed introduction to a battery shell abnormality detection method, device, electronic device, and storage medium provided by the embodiments of the present disclosure. Specific examples are used herein to illustrate the principles and implementation methods of the present disclosure. The description of the above embodiments is only used to help understand the method and core ideas of the present disclosure. At the same time, for those of ordinary skill in the art, based on the ideas of the present disclosure, there will be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present disclosure.
Claims
1. A method for detecting abnormality of battery cell entering the shell, It is characterized in that The method comprises: Obtain detection data during the process of the battery cell being pushed into the battery casing; Generate one or more curves to be detected according to the detection data; The one or more curves to be detected are detected respectively according to the historical detection data to obtain the detection result corresponding to each curve to be detected; the historical detection data is the detection data when no abnormality occurs during the process of the battery cell being pushed into the battery housing; The abnormal result of the battery cell entering the shell is determined according to the detection result corresponding to each of the curves to be detected.
2. The method according to claim 1, It is characterized in that The detection data includes a displacement value and / or a thrust value of the battery cell being pushed into the battery housing; The step of generating one or more curves to be detected according to the detection data comprises: A curve to be detected corresponding to the thrust value is generated according to the thrust value, and / or a curve to be detected corresponding to the displacement value is generated according to the displacement value.
3. The method according to claim 1, It is characterized in that The step of respectively detecting the one or more curves to be detected according to the historical detection data to obtain a detection result corresponding to each of the curves to be detected includes: Generating a standard curve corresponding to each of the curves to be detected according to the historical detection data, and determining a slope threshold corresponding to each of the standard curves according to each of the standard curves; Determine the slope of each of the curves to be detected, and compare the slope of each of the curves to be detected with a corresponding slope threshold to obtain a slope comparison result of each of the curves to be detected; Determine the similarity between each of the curves to be detected and the corresponding standard curve, and compare each of the similarities with a similarity threshold to obtain a similarity comparison result for each of the curves to be detected; According to the slope comparison result and the similarity comparison result of each of the curves to be detected, the detection result corresponding to each of the curves to be detected is obtained.
4. The method according to claim 1, It is characterized in that The method further comprises: Determine, according to the detection data, abnormal data corresponding to each of the curves to be detected; The step of respectively detecting the one or more curves to be detected according to the historical detection data to obtain a detection result corresponding to each of the curves to be detected includes: Determine abnormal data thresholds based on historical detection data; The abnormal data corresponding to each of the to-be-detected curves is compared with the abnormal data threshold to obtain a detection result corresponding to each of the to-be-detected curves.
5. The method according to claim 4, It is characterized in that The abnormal data includes a jamming value and a glitch value, and the abnormal data threshold includes a jamming threshold and a glitch threshold; The step of comparing the abnormal data corresponding to each of the to-be-detected curves with the abnormal data threshold to obtain the detection result corresponding to each of the to-be-detected curves includes: Compare the jamming value corresponding to each of the to-be-detected curves with the jamming threshold value to obtain a jamming comparison result corresponding to each of the to-be-detected curves; Compare the burr value corresponding to each of the to-be-detected curves with the burr threshold value to obtain a burr comparison result corresponding to each of the to-be-detected curves; According to the jam comparison result corresponding to each of the to-be-detected curves and the burr comparison result corresponding to each of the to-be-detected curves, a detection result corresponding to each of the to-be-detected curves is obtained.
6. The method according to claim 5, It is characterized in that The method further comprises: According to the jam comparison result corresponding to the target curve to be detected, determining a first number of the jam values in the target curve to be detected that are greater than the jam threshold; the target curve to be detected is any of the curves to be detected; Determine, according to the burr comparison result corresponding to the target to-be-detected curve, a second number of burr values in the target to-be-detected curve that are greater than the burr threshold; Determine the abnormality score corresponding to the target curve to be detected according to the first number, the weight of the jam comparison result, the second number, and the weight of the burr comparison result; wherein the weight of the jam comparison result is greater than the weight of the burr comparison result; The abnormality level of the battery cell entering the shell is determined according to the abnormality score corresponding to each of the curves to be detected.
7. The method according to any one of claims 1 to 6, It is characterized in that After generating one or more curves to be detected according to the detection data, the method further includes: According to the battery cell shelling process flow, each of the curves to be detected is divided into multiple sub-curves; the multiple sub-curves correspond one-to-one to multiple shelling sub-processes of the battery cell shelling process flow; The step of respectively detecting the one or more curves to be detected according to the historical detection data to obtain a detection result corresponding to each of the curves to be detected includes: Each sub-curve of each of the curves to be detected is detected respectively according to the historical detection data to obtain the detection result corresponding to each sub-curve of each of the curves to be detected, and the detection result corresponding to each of the curves to be detected is determined according to the detection result corresponding to each sub-curve.
8. An abnormality detection device for battery cell shell entry, It is characterized in that The device comprises: A data acquisition module, used to acquire detection data during the process of the battery cell being pushed into the battery housing; A curve construction module, used to generate one or more curves to be detected according to the detection data; A curve detection module, used to detect the one or more curves to be detected respectively according to historical detection data, and obtain a detection result corresponding to each of the curves to be detected; the historical detection data is the detection data when no abnormality occurs during the process of the battery cell being pushed into the battery housing; The abnormality detection module is used to determine the abnormality result of the battery cell entering the shell according to the detection result corresponding to each of the curves to be detected.
9. An electronic device, It is characterized in that The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor implements the method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Method for producing a vehicle traction battery
CN112272888A
Method for determining a quality condition of a component used during a monitoring process and control device for monitoring a
CN114976379A
Method and device for detecting abnormity of battery cell entering shell, electronic equipment and storage medium
CN116448185A
Shell entering device and battery assembly equipment
CN216015464U
Traction battery for an electrically powered vehicle
DE102019130730A1
