Battery internal resistance fluctuation monitoring method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of batteries, in particular to a battery internal resistance fluctuation monitoring method and device, electronic equipment and a storage medium. Acquiring current internal resistance data corresponding to the current target battery pack; obtaining a reference statistical result corresponding to the current target battery pack and a historical statistical result of a previous target battery pack corresponding to the current target battery pack; performing statistical processing on the current internal resistance data corresponding to the current target battery pack to generate a current statistical result; comparing the current statistical result with a reference statistical result and a historical statistical result; and determining the internal resistance fluctuation result corresponding to the current target battery pack according to the comparison result, thereby ensuring the accuracy of the determined internal resistance fluctuation result corresponding to the current target battery pack, further realizing the macroscopic early warning of the current internal resistance data fluctuation and change, and identifying the internal resistance abnormal state.

Description

Technical Field

[0001] The present invention relates to the field of battery technology, and in particular to a method, device, electronic equipment and storage medium for monitoring battery internal resistance fluctuation. Background Art

[0002] At present, in the production process of square shell lithium batteries, an internal resistance test is generally added before formation and after liquid injection. Usually, the ACIR test is used to eliminate the influence of polarization and directly test the battery's ohmic internal resistance. The purpose is to identify and screen assembly anomalies such as cold welding, broken welding, fracture, and welding deviation of the tabs during battery assembly.

[0003] During the internal resistance test, abnormal internal resistance of the battery cell may occur due to factors such as replacement of the main material, adjustment of the additive ratio, change of ambient temperature and change of welding process. Although the internal resistance test of the production unit (such as a single pallet) can well identify abnormal single cells, it cannot identify the changing trend and abnormal fluctuation of the internal resistance of the entire production line. This will result in the process of the overall fluctuation of the internal resistance to exceed the specification batch NG not being well monitored and warned, and this time is not utilized. Due to the characteristics of battery cell production such as continuity and large output, production personnel are unable to monitor the fluctuations and changes of the internal resistance in real time. Therefore, how to provide early warning of fluctuations and changes in the internal resistance test data at a macro level and identify the abnormal state of internal resistance has become an urgent problem to be solved. Summary of the invention

[0004] In view of this, the present invention provides a battery internal resistance fluctuation monitoring method, device, electronic device and storage medium to solve the problem of how to provide early warning of internal resistance test data fluctuations and changes in a macro sense and identify abnormal internal resistance states.

[0005] In a first aspect, the present invention provides a method for monitoring battery internal resistance fluctuation, the method comprising:

[0006] Obtaining current internal resistance data corresponding to the current target battery pack; the current target battery pack is used to characterize each target battery produced by the current production line within the current preset time period;

[0007] Obtaining the benchmark statistical results corresponding to the current target battery group and the historical statistical results of the previous target battery group corresponding to the current target battery group;

[0008] Performing statistical processing on the current internal resistance data corresponding to the current target battery pack to generate current statistical results;

[0009] Compare the current statistical results with the benchmark statistical results and the historical statistical results;

[0010] According to the comparison result, the internal resistance fluctuation result corresponding to the current target battery pack is determined.

[0011] The battery internal resistance fluctuation monitoring method provided in the embodiment of the present application obtains the current internal resistance data corresponding to the current target battery group. Since the current target battery group is used to characterize each target battery produced by the current production line within the current preset time period, the current internal resistance data of the current target battery group is guaranteed to be representative. Then, the benchmark statistical results corresponding to the current target battery group and the historical statistical results of the previous target battery group corresponding to the current target battery group are obtained; the current internal resistance data corresponding to the current target battery group is statistically processed to generate the current statistical results, thereby ensuring the accuracy of the generated current statistical results. The current statistical results are compared with the benchmark statistical results and the historical statistical results respectively, so that the comparison results of the current internal resistance data relative to the benchmark statistical results and the historical statistical results can be determined, and finally, according to the comparison results, the internal resistance fluctuation results corresponding to the current target battery group are determined. By comparing the current statistical results with the benchmark statistical results and the historical statistical results at the same time, it is not only avoided that only the current internal resistance data is compared with the historical statistical results, but also that there may be no large deviation in the comparison of the current internal resistance data with the historical statistical results each time, and gradually, the overall data exceeds the problem of large deviation of the benchmark statistical results, and at the same time, it is avoided that only the benchmark statistical results are used as a reference to determine the change trend of the internal resistance data in different periods. Therefore, the above method realizes the early warning of the current internal resistance data fluctuation and change on a macro level, and identifies the abnormal state of the internal resistance.

[0012] In an optional implementation, obtaining a benchmark statistical result corresponding to the current target battery group includes:

[0013] Obtain the current production output and current environment information corresponding to the current production line;

[0014] Based on the current production output and current environmental information, determine the reference time range corresponding to the current target battery group;

[0015] Determine the target battery produced within the benchmark time range as the benchmark target battery pack;

[0016] Obtaining reference internal resistance data corresponding to a reference target battery pack;

[0017] The benchmark internal resistance data is statistically calculated to obtain benchmark statistical results.

[0018] The battery internal resistance fluctuation monitoring method provided in the embodiment of the present application obtains the current production output corresponding to the current production line and the current environmental information corresponding to the current production line; based on the current production output and the current environmental information, the reference time range corresponding to the current target battery group is determined, thereby ensuring the accuracy and rationality of the determined reference time range. The target battery produced within the reference time range is determined as the reference target battery group, thereby ensuring the accuracy and representativeness of the determined reference target battery group. Then, the reference internal resistance data corresponding to the reference target battery group is obtained, and the reference internal resistance data is statistically calculated to obtain the reference statistical results, thereby ensuring that the current internal resistance number is detected based on the reference statistical results to see if it fluctuates and changes.

[0019] In an optional implementation manner, obtaining current internal resistance data corresponding to the current target battery pack includes:

[0020] Get the current production output corresponding to the current production line;

[0021] Based on the current production output, determine the preset duration corresponding to the preset time period;

[0022] Based on the preset duration, determine the current preset time period;

[0023] Obtain each target battery produced by the current production line within the current preset time period to form a current target battery group;

[0024] The internal resistance of each target battery in the current target battery pack is detected to generate current internal resistance data.

[0025] The battery internal resistance fluctuation monitoring method provided in the embodiment of the present application obtains the current production output corresponding to the current production line; based on the current production output, the preset duration corresponding to the preset time period is determined, thereby ensuring the accuracy and rationality of the preset duration corresponding to the determined preset time period. Based on the preset duration, the current preset time period is determined, thereby ensuring the accuracy of the determined current preset time period. The target batteries produced by the current production line within the current preset time period are obtained to form the current target battery group, thereby ensuring that the number of the generated current target battery group is reasonable and representative. The internal resistance of each target battery in the current target battery group is detected to generate the current internal resistance data, thereby detecting whether the current internal resistance data corresponding to the current target battery group has fluctuated and changed.

[0026] In an optional implementation, the current statistical result includes the current mean, the current variance, the current skewness and the current kurtosis; the benchmark statistical result includes the benchmark mean, the benchmark variance, the benchmark skewness and the benchmark kurtosis; the historical statistical result includes the historical mean, the historical variance, the historical skewness and the historical kurtosis; and the current statistical result is compared with the benchmark statistical result and the historical statistical result, respectively, including:

[0027] Calculate the absolute value of the difference between the current average value and the reference average value to obtain a first absolute value;

[0028] Calculate the absolute value of the difference between the current variance and the benchmark variance to obtain a second absolute value;

[0029] Calculate the absolute value of the difference between the current skewness and the benchmark skewness to obtain a third absolute value;

[0030] Calculate the absolute value of the difference between the current kurtosis and the reference kurtosis to obtain a fourth absolute value;

[0031] Calculate the absolute value of the difference between the current average value and the historical average value to obtain the fifth absolute value;

[0032] Calculate the absolute value of the difference between the current variance and the historical variance to obtain the sixth absolute value;

[0033] Calculate the absolute value of the difference between the current skewness and the historical skewness to get the seventh absolute value;

[0034] Calculate the absolute value of the difference between the current kurtosis and the historical kurtosis to obtain the eighth absolute value;

[0035] It is respectively detected whether the first absolute value, the second absolute value, the third absolute value, the fourth absolute value, the fifth absolute value, the sixth absolute value, the seventh absolute value and the eighth absolute value are within the corresponding preset ranges.

[0036] The battery internal resistance fluctuation monitoring method provided in the embodiment of the present application calculates the absolute value of the difference between the current average value and the benchmark average value to obtain a first absolute value; calculates the absolute value of the difference between the current variance and the benchmark variance to obtain a second absolute value; calculates the absolute value of the difference between the current skewness and the benchmark skewness to obtain a third absolute value; calculates the absolute value of the difference between the current kurtosis and the benchmark kurtosis to obtain a fourth absolute value; calculates the absolute value of the difference between the current average value and the historical average value to obtain a fifth absolute value; calculates the absolute value of the difference between the current variance and the historical variance to obtain a sixth absolute value; calculates the absolute value of the difference between the current skewness and the historical skewness to obtain a seventh absolute value; calculates the absolute value of the difference between the current kurtosis and the historical kurtosis to obtain an eighth absolute value, thereby ensuring the accuracy of the first to eighth absolute values ​​obtained, and determining the change and fluctuation of the current internal resistance data relative to the benchmark statistical results and the historical statistical results based on the first to eighth absolute values. Then, the first absolute value, the second absolute value, the third absolute value, the fourth absolute value, the fifth absolute value, the sixth absolute value, the seventh absolute value and the eighth absolute value are respectively detected to see whether they are within the corresponding preset ranges, so that the internal resistance fluctuation result corresponding to the current target battery pack can be determined based on the detection results.

[0037] In an optional implementation, determining the internal resistance fluctuation result corresponding to the current target battery pack according to the comparison result includes:

[0038] If the first absolute value is not within the preset range corresponding to the first absolute value, it is determined that the current internal resistance data is abnormal relative to the reference internal resistance data, and the abnormal result is that the current internal resistance data increases or decreases;

[0039] If the second absolute value is not within the preset range corresponding to the second absolute value, it is determined that the current internal resistance data is abnormal relative to the reference internal resistance data, and the abnormal result is the current internal resistance data stratification;

[0040] If the third absolute value is not within the preset range corresponding to the third absolute value, it is determined that the current internal resistance data is abnormal relative to the reference internal resistance data, and the abnormal result is a deviation of the current internal resistance data;

[0041] If the fourth absolute value is not within the preset range corresponding to the fourth absolute value, it is determined that the current internal resistance data is abnormal relative to the reference internal resistance data, and the abnormal result is that the current internal resistance data is diffused;

[0042] If the fifth absolute value is not within the preset range corresponding to the fifth absolute value, it is determined that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is that the current internal resistance data increases or decreases;

[0043] If the sixth absolute value is not within the preset range corresponding to the sixth absolute value, it is determined that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is the current internal resistance data stratification;

[0044] If the seventh absolute value is not within the preset range corresponding to the seventh absolute value, it is determined that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is the current internal resistance data offset;

[0045] If the eighth absolute value is not within the preset range corresponding to the eighth absolute value, it is determined that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is that the current internal resistance data is diffuse.

[0046] Among them, the preset range corresponding to the first absolute value is greater than the preset range corresponding to the fifth absolute value, the preset range corresponding to the second absolute value is greater than the preset range corresponding to the sixth absolute value, the preset range corresponding to the third absolute value is greater than the preset range corresponding to the seventh absolute value, and the preset range corresponding to the fourth absolute value is greater than the preset range corresponding to the eighth absolute value.

[0047] The battery internal resistance fluctuation monitoring method provided in the embodiment of the present application determines the internal resistance fluctuation result corresponding to the current internal resistance number of the current target battery pack according to the detection results that the first absolute value, the second absolute value, the third absolute value, the fourth absolute value, the fifth absolute value, the sixth absolute value, the seventh absolute value and the eighth absolute value are not within the corresponding preset range, thereby ensuring the accuracy of the internal resistance fluctuation result corresponding to the current internal resistance number of the current target battery pack, and then early warning can be given based on the internal resistance fluctuation result to avoid the generated target battery being unqualified and causing serious problems.

[0048] In an optional embodiment, the method further includes:

[0049] If the internal resistance fluctuation result indicates that the current internal resistance data is abnormal, the duration of the abnormality of the current internal resistance data is recorded;

[0050] If the duration is longer than the preset duration threshold, the current operating parameters corresponding to the current production line are obtained;

[0051] The current operating parameters are input into the preset fault diagnosis model, the current fault type corresponding to the current production line is output, and prompt information is output based on the current fault type.

[0052] The battery internal resistance fluctuation monitoring method provided in the embodiment of the present application records the duration of the abnormality of the current internal resistance data if the internal resistance fluctuation result indicates that the current internal resistance data is abnormal. Then, if the duration is greater than the preset duration threshold, the current operating parameters corresponding to the current production line are obtained, so that the current operating parameters can be input into the preset fault diagnosis model, the current fault type corresponding to the current production line is output, and prompt information is output based on the current fault type. This realizes fault detection of the current production line, so that the user can repair the current production line based on the output prompt information, without the need for manual troubleshooting of the current production line, thereby improving work efficiency and saving time.

[0053] In an optional implementation, the training process of the preset fault diagnosis model includes:

[0054] Obtain a training data set; the training data set includes training operation parameters and training fault types corresponding to the training operation parameters;

[0055] Identify training run parameters and determine time series data in the training data set;

[0056] Extract time domain features from time series data and convert them into frequency domain features;

[0057] Extract the time-frequency domain features corresponding to the training operation parameters;

[0058] Calculate the time domain features and frequency domain features corresponding to the training data set, as well as the correlation between the time-frequency domain features and the fault types corresponding to the training data set;

[0059] Deleting time domain features, and / or frequency domain features, and / or time-frequency domain features whose correlation is less than a preset correlation threshold, to obtain target features;

[0060] Based on the target features, the initial fault diagnosis network is trained to generate a preset fault diagnosis model.

[0061] The battery internal resistance fluctuation monitoring method provided in the embodiment of the present application obtains a training data set; identifies the training operation parameters and determines the time series data in the training data set; extracts the time domain features in the time series data and converts the time domain features into frequency domain features; extracts the time-frequency domain features corresponding to the training operation parameters; calculates the correlation between the time domain features, frequency domain features corresponding to the training data set and the time-frequency domain features and the fault types corresponding to the training data set, so that the time domain features and / or frequency domain features and / or time-frequency domain features whose correlation is less than a preset correlation threshold can be deleted according to the correlation to obtain the target features, thereby ensuring that the correlation between the obtained target features and the fault types is strong. Then, the accuracy of the preset fault diagnosis model generated by training the initial fault diagnosis network based on the target features can be guaranteed, thereby improving the accuracy of the current fault type output by the preset fault diagnosis model.

[0062] In a second aspect, the present invention provides a battery internal resistance fluctuation monitoring device, the device comprising:

[0063] The first acquisition module is used to acquire the current internal resistance data corresponding to the current target battery pack; the current target battery pack is used to characterize each target battery produced by the current production line within the current preset time period;

[0064] A second acquisition module is used to acquire a benchmark statistical result corresponding to the current target battery group and a historical statistical result of a previous target battery group corresponding to the current target battery group;

[0065] A calculation module, used to perform statistical processing on the current internal resistance data corresponding to the current target battery pack to generate current statistical results;

[0066] A comparison module is used to compare the current statistical results with the benchmark statistical results and the historical statistical results;

[0067] The determination module is used to determine the internal resistance fluctuation result corresponding to the current target battery pack according to the comparison result.

[0068] The battery internal resistance fluctuation monitoring method provided in the embodiment of the present application obtains the current internal resistance data corresponding to the current target battery group. Since the current target battery group is used to characterize the various target batteries produced by the current production line within the current preset time period, the current internal resistance data of the current target battery group is guaranteed to be representative. Then, the benchmark statistical results corresponding to the current target battery group and the historical statistical results of the previous target battery group corresponding to the current target battery group are obtained; the current internal resistance data corresponding to the current target battery group is statistically processed to generate the current statistical results, thereby ensuring the accuracy of the generated current statistical results. The current statistical results are compared with the benchmark statistical results and the historical statistical results, respectively, so that the comparison results of the current internal resistance data relative to the benchmark statistical results and the historical statistical results can be determined. Then, based on the comparison results, the internal resistance fluctuation results corresponding to the current target battery group are determined, thereby ensuring the accuracy of the internal resistance fluctuation results corresponding to the determined current target battery group, thereby achieving a macroscopic early warning of the fluctuation and change of the current internal resistance data, and identifying the abnormal state of the internal resistance.

[0069] In a third aspect, the present invention provides an electronic device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the battery internal resistance fluctuation monitoring method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0070] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the battery internal resistance fluctuation monitoring method of the first aspect or any corresponding embodiment thereof.

[0071] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the battery internal resistance fluctuation monitoring method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0073] Figure 1 is a schematic diagram of a first type of internal resistance data according to an embodiment of the present invention;

[0074] Figure 2is a schematic diagram of a second type of internal resistance data according to an embodiment of the present invention;

[0075] Figure 3 is a schematic diagram of a third type of internal resistance data according to an embodiment of the present invention;

[0076] Figure 4 is a schematic diagram of a fourth type of internal resistance data according to an embodiment of the present invention;

[0077] Figure 5 is a schematic diagram of a fifth type of internal resistance data according to an embodiment of the present invention;

[0078] Figure 6 is a schematic diagram of a sixth type of internal resistance data according to an embodiment of the present invention;

[0079] Figure 7 is a flow chart of a method for monitoring battery internal resistance fluctuation according to an embodiment of the present invention;

[0080] Figure 8 is a flow chart of another method for monitoring battery internal resistance fluctuation according to an embodiment of the present invention;

[0081] Fig. 9 is a schematic diagram of a seventh type of internal resistance data according to an embodiment of the present invention;

[0082] Fig.10 is a structural block diagram of a battery internal resistance fluctuation monitoring device according to an embodiment of the present invention;

[0083] Fig.11 is a structural block diagram of a battery internal resistance fluctuation monitoring device according to an embodiment of the present invention;

[0084] Fig.12 It is a schematic diagram of the hardware structure of the electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0085] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0086] At present, in the production process of square shell lithium batteries, an internal resistance test is generally added before formation and after liquid injection. Usually, ACIR AC internal resistance test is used to eliminate the influence of polarization and directly test the battery's ohmic internal resistance. The purpose is to identify and screen assembly anomalies such as cold welding, broken welding, fracture, and welding deviation of the tabs during battery assembly.

[0087] During the internal resistance test, abnormal fluctuations and stratification of the internal resistance of the battery cell may occur due to factors such as the replacement of the main material, adjustment of the additive ratio, changes in ambient temperature, and changes in the welding process. Although the internal resistance test of the production unit (such as a single pallet) can well identify abnormal single cells, it cannot identify the changing trend and abnormal fluctuations of the internal resistance of the entire production line. In order to ensure smooth production, the internal resistance specifications are generally set in a relatively loose range, which will lead to the process of overall internal resistance fluctuations to exceeding the specification batch NG. This process is not well monitored and warned, and this time is not utilized. Due to the characteristics of battery cell production such as continuity and large output, production personnel cannot monitor the fluctuations and changes of internal resistance in real time. In addition, although the internal resistance test of the production unit (such as a single pallet) can well identify abnormal single cells, it cannot identify the changing trend and abnormal fluctuations of the internal resistance of the entire production line.

[0088] For example, in production, a large amount of internal resistance data normally presents a stable normal distribution, for example Figure 1 As shown. In simple terms, there is more data in the middle (normal or concentrated value) and less data on both sides (abnormal or edge value). According to the actual battery cell process and manufacturing conditions, this normal distribution is different, but their related data (such as overall mean μ, standard deviation δ, skewness βs, kurtosis βk) are relatively stable.

[0089] For example, the internal resistance data is exemplified as Figure 2 As shown in , as a data without obvious fluctuations, it presents a normal distribution within the specification, and its overall mean μ and standard deviation δ are relatively stable. However, once there is a sudden drop (or rise) in the data, the example Figure 3 As shown in the figure, although its standard deviation is the same, its overall average value has decreased significantly (from 0.22742 to 0.22589, a decrease of 0.00153, accounting for nearly 5% of the specification range). At this time, it can be predicted that the internal resistance is moving downward as a whole. For example, another internal resistance data is stratified, as shown in the example below: Figure 4 As shown, before mutation, the exemplary Figure 5 As shown, after stratification with mutations, the exemplary Figure 6 As shown, their overall means are not very different (the difference is only 0.00035, which is only about 1% of the specification range), but the standard deviations vary greatly, reflecting the stratification. Figure 5 The skewness in the data is actually already biased to the left, and the warning internal resistance data was initially concentrated on the high side, which requires attention and adjustment.

[0090] Therefore, how to provide early warning of fluctuations and changes in internal resistance test data and identify abnormal internal resistance has become an urgent problem to be solved.

[0091] It should be noted that the method for monitoring battery internal resistance fluctuations provided in the embodiment of the present application may be executed by a device for monitoring battery internal resistance fluctuations, and the device for monitoring battery internal resistance fluctuations may be implemented as part or all of an electronic device through software, hardware, or a combination of software and hardware, wherein the electronic device may be a server or a terminal, wherein the server in the embodiment of the present application may be a single server or a server cluster composed of multiple servers, and the terminal in the embodiment of the present application may be a smart phone, a personal computer, a tablet computer, a wearable device, an intelligent robot, or other intelligent hardware devices. In the following method embodiments, the execution subject is an electronic device as an example for explanation.

[0092] According to an embodiment of the present invention, an embodiment of a method for monitoring battery internal resistance fluctuations is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0093] In this embodiment, a battery internal resistance fluctuation monitoring method is provided, which can be used in the above-mentioned electronic device. Figure 7 is a flow chart of a method for monitoring battery internal resistance fluctuation according to an embodiment of the present invention. Figure 7 As shown, the process includes the following steps:

[0094] Step S101, obtaining current internal resistance data corresponding to the current target battery pack.

[0095] The current target battery group is used to characterize each target battery produced by the current production line within the current preset time period.

[0096] Specifically, the electronic device can determine that each target battery produced by the current production line within the current preset time period is the current target battery pack, and then measure the current internal resistance data corresponding to each target battery in the current target battery pack based on the internal resistance measuring device.

[0097] Among them, the internal resistance measuring device can be a multimeter, a professional internal resistance tester, etc., and the embodiment of the present application does not specifically limit the internal resistance measuring device.

[0098] This step will be described in detail below.

[0099] Step S102, obtaining a benchmark statistical result corresponding to the current target battery group and a historical statistical result of a previous target battery group corresponding to the current target battery group.

[0100] Specifically, the electronic device may first determine a reference target battery pack, and then obtain reference internal resistance data corresponding to the reference target battery pack; perform statistical calculations on the reference internal resistance data to obtain reference statistical results.

[0101] For example, a. if the pilot product parameters are available, the electronic device can directly use the pilot product as the reference target battery pack.

[0102] b. If there has been production in the past, the products produced in the past month can be determined as the benchmark target battery pack.

[0103] c. If there is no pilot product data, the first production product will be determined as the benchmark target battery pack based on the first day of production.

[0104] Specifically, the electronic device may determine a previous target battery group before the current target battery group according to a method for determining the current target battery group, and calculate a historical statistical result corresponding to the previous target battery group.

[0105] This step will be described in detail below.

[0106] Step S103, statistically processing the current internal resistance data corresponding to the current target battery pack to generate a current statistical result.

[0107] Specifically, the electronic device may perform Anderson-Darling normality calculation on the current internal resistance data corresponding to the current target battery pack to obtain the current mean value, current standard deviation, current skewness, and current kurtosis corresponding to the current internal resistance data.

[0108] Step S104, comparing the current statistical result with the benchmark statistical result and the historical statistical result respectively.

[0109] Specifically, the electronic device may compare the current statistical result with the benchmark statistical result and the historical statistical result respectively.

[0110] This step will be described in detail below.

[0111] Step S105 , determining the internal resistance fluctuation result corresponding to the current target battery pack according to the comparison result.

[0112] Specifically, the electronic device may determine the internal resistance fluctuation result corresponding to the current target battery pack according to the comparison result.

[0113] This step will be described in detail below.

[0114] The battery internal resistance fluctuation monitoring method provided in the embodiment of the present application obtains the current internal resistance data corresponding to the current target battery group. Since the current target battery group is used to characterize each target battery produced by the current production line within the current preset time period, the current internal resistance data of the current target battery group is guaranteed to be representative. Then, the benchmark statistical results corresponding to the current target battery group and the historical statistical results of the previous target battery group corresponding to the current target battery group are obtained; the current internal resistance data corresponding to the current target battery group is statistically processed to generate the current statistical results. The current statistical results are compared with the benchmark statistical results and the historical statistical results respectively, so that the comparison results of the current internal resistance data relative to the benchmark statistical results and the historical statistical results can be determined. Then, according to the comparison results, the internal resistance fluctuation results corresponding to the current target battery group are determined. By comparing the current statistical results with the benchmark statistical results and the historical statistical results at the same time, it not only avoids the problem that only the current internal resistance data is compared with the historical statistical results, but there may be no large deviation each time the current internal resistance data is compared with the historical statistical results, but the internal resistance data has gradually exceeded the large deviation of the benchmark statistical results as a whole, and at the same time avoids the problem that the change trend of the internal resistance data in different periods cannot be judged by only using the benchmark statistical results as a reference, resulting in the inability to make early warnings. Therefore, the above method, combined with the comparison of historical statistical results, can evaluate the battery status from multiple angles, reduce the possibility of misjudgment, and achieve early warning of current internal resistance data fluctuations and changes at a macro level, and identify abnormal internal resistance status.

[0115] In this embodiment, a battery internal resistance fluctuation monitoring method is provided, which can be used in the above-mentioned electronic device. Figure 8 is a flow chart of a method for monitoring battery internal resistance fluctuation according to an embodiment of the present invention. Figure 8 As shown, the process includes the following steps:

[0116] Step S201, obtaining current internal resistance data corresponding to the current target battery pack.

[0117] The current target battery group is used to characterize each target battery produced by the current production line within the current preset time period.

[0118] Specifically, the above step S201 may include the following steps:

[0119] Step S2011, obtaining the current production output corresponding to the current production line.

[0120] Specifically, the electronic device can receive the current production output corresponding to the current production line input by the user, or determine the current production output corresponding to the current production line by detecting the current production line. The electronic device can also receive the current production output corresponding to the current production line sent by other devices.

[0121] The embodiment of the present application does not specifically limit the manner in which the electronic device obtains the current production output corresponding to the current production line.

[0122] Step S2012: Determine the preset duration corresponding to the preset time period based on the current production output.

[0123] Specifically, the electronic device may calculate the number of samples corresponding to the current production output according to the current production output, and then determine the preset duration corresponding to the preset time period according to the number of samples.

[0124] Exemplarily, the electronic device can obtain the standard normal distribution corresponding to the current production output, and then determine the confidence level and the population standard deviation corresponding to the current production output under the standard normal distribution, and obtain the quantile of the standard normal distribution corresponding to the confidence level. In addition, the electronic device can also obtain the absolute error corresponding to the target battery based on the attribute information of the target battery and the required level corresponding to the target battery. The absolute error can represent the maximum allowable error between the sample statistic and the total number of N batteries. Then, the electronic device can calculate the number of samples corresponding to the current production output according to the following formula:

[0125] Among them, n is the sample size, that is, the number of samples to be drawn, and N is the total number, that is, the current production output. α / 2 is the quantile of the standard normal distribution corresponding to the confidence level. For example, at a confidence level of 99.7%, α = 1-99.7% = 0.003. Z α / 2 =2.75. σ is the population standard deviation, which is the standard deviation of N target batteries and indicates the degree of dispersion of the population data. d is the absolute error, which indicates the maximum allowable error between the sample statistic and the population quantity. Among them, this formula determines the sample size based on the given confidence level, population standard deviation and absolute error in the case of a finite population. Numerator: N(z α / 2 ) 2 σ 2 , taking into account the impact of the population size, confidence level and population standard deviation. Denominator: (N-1)d 2 +(z α / 2 ) 2 σ 2 , taking into account the impact of population size, absolute error and population standard deviation.

[0126] In practical applications, first determine the population size, population standard deviation, and absolute error. Determine the values ​​based on the desired confidence level. Substitute these values ​​into the formula to calculate the required sample size.

[0127] For example, if the 24-hour production volume N of a battery is 25,000, and the previous data shows that the population standard deviation σ is 0.00243, the absolute error d is 0.0005, and the internal resistance confidence level is 99.7%, then Zα / 2=2.75. According to the above formula, the number of samples that can be selected is n≈178. 178 / (25000 / 60 / 24)≈11min, so the preset duration can be set to 11min.

[0128] In an optional implementation of the present application, the electronic device may also obtain current environmental information corresponding to the current production line. The current environmental information may include environmental parameters such as temperature, humidity, and air cleanliness, and the present embodiment of the application does not specifically limit the current environmental information. If at least one current environmental parameter exceeds the corresponding parameter threshold, the electronic device may shorten the preset duration corresponding to the preset time period.

[0129] For example, when the humidity in the workshop rises by more than 10% in a short period of time, the preset time will be shortened to half of the original time to ensure that the possible impact of environmental changes on the internal resistance of the product can be discovered in time.

[0130] Step S2013: determine the current preset time period based on the preset duration.

[0131] Specifically, the electronic device determines the current preset time period based on the preset duration. For example, starting from 9:00 in the morning, 9:00-9:11 is the first preset time period, 9:11-9:22 is the second preset time period, and so on.

[0132] Step S2014, obtaining each target battery produced by the current production line within the current preset time period to form a current target battery group.

[0133] Specifically, the electronic device may combine the target batteries produced by the current production line within the current preset time period into a current target battery group.

[0134] Step S2015, detecting the internal resistance of each target battery in the current target battery pack to generate current internal resistance data.

[0135] Specifically, the electronic device may use the internal resistance measuring device to detect the internal resistance of each target battery in the current target battery pack to generate current internal resistance data.

[0136] Among them, the internal resistance measuring device can be a multimeter, a professional internal resistance tester, etc., and the embodiment of the present application does not specifically limit the internal resistance measuring device.

[0137] Step S202 , obtaining a benchmark statistical result corresponding to the current target battery group and a historical statistical result of a previous target battery group corresponding to the current target battery group.

[0138] Specifically, the “obtaining the benchmark statistical results corresponding to the current target battery group” in the above step S202 may include the following steps:

[0139] Step S2021, obtaining the current production output corresponding to the current production line and the current environment information corresponding to the current production line.

[0140] Specifically, the electronic device can receive the current production output corresponding to the current production line input by the user, or determine the current production output corresponding to the current production line by detecting the current production line. The electronic device can also receive the current production output corresponding to the current production line sent by other devices.

[0141] The embodiment of the present application does not specifically limit the manner in which the electronic device obtains the current production output corresponding to the current production line.

[0142] In addition, the electronic device can monitor the current environmental information corresponding to the current production line based on the environmental sensor.

[0143] Among them, the current environmental information may include environmental parameters such as temperature, humidity, and air cleanliness. The embodiment of the present application does not specifically limit the current environmental information.

[0144] Step S2022: Determine a reference time range corresponding to the current target battery pack based on the current production output and current environmental information.

[0145] Specifically, the electronic device may input the current production output and the current environment information into the reference time range calculation model, and output the reference time range corresponding to the current target battery pack.

[0146] In an optional implementation of the present application, if at least one current environmental parameter exceeds a corresponding parameter threshold, the reference time range is shortened.

[0147] For example, when the humidity in the workshop rises by more than 10% in a short period of time, the benchmark time range is shortened to half of the original time range to ensure that the possible impact of environmental changes on the internal resistance of the product can be discovered in time.

[0148] In an optional implementation, the electronic device can also establish an environmental impact index based on the weights of the effects of different environmental parameters in the current environmental information on the internal resistance of the product. The most suitable data monitoring reference time range T is dynamically calculated through the index. For example, the environmental impact index EII = a×ΔT+b×ΔH+c×ΔC (where ΔT is the temperature change, ΔH is the humidity change, ΔC is the air cleanliness change, and a, b, and c are corresponding weight coefficients). When the corresponding parameter threshold is exceeded, the reference time range T is adjusted according to a specific formula.

[0149] Step S2023, determining the target batteries produced within the reference time range as the reference target battery pack.

[0150] Specifically, the electronic device may start timing from the current production line production, and determine the target batteries produced within the reference time range as the reference target battery pack.

[0151] Exemplarily, assuming that the reference time range is 1 day, the electronic device may determine the target batteries produced on the first day of production as the reference target battery pack.

[0152] In an optional embodiment of the present application, the electronic device may establish a system for regularly reviewing and updating the reference target battery set, and the electronic device may re-determine the reference target battery set after a certain period of time or after producing a preset number of target batteries. For example, after every 10,000 products are produced or after one month of production, the reference target battery set is re-determined based on the latest produced target batteries.

[0153] During the updating process, electronic equipment can adopt a weighted average method to give a higher weight to recent production data to reflect the latest situation in the production process.

[0154] Step S2024, obtaining reference internal resistance data corresponding to the reference target battery pack.

[0155] Specifically, the electronic device may measure reference internal resistance data corresponding to the reference target battery pack based on the internal resistance measuring device.

[0156] Step S2025, performing statistical calculations on the benchmark internal resistance data to obtain benchmark statistical results.

[0157] Specifically, the electronic device performs Anderson-Darling normality calculation on the reference internal resistance data to obtain a reference mean value, a reference standard deviation, a reference skewness, and a reference kurtosis corresponding to the reference internal resistance data.

[0158] Step S203, statistically processing the current internal resistance data corresponding to the current target battery pack to generate a current statistical result.

[0159] For details about this step, please refer to the above description of step S103, which will not be elaborated here.

[0160] Step S204, comparing the current statistical result with the benchmark statistical result and the historical statistical result respectively.

[0161] For details about this step, please refer to the above description of step S104, which will not be elaborated here.

[0162] Step S205 , determining the internal resistance fluctuation result corresponding to the current target battery pack according to the comparison result.

[0163] For details about this step, please refer to the above description of step S105, which will not be elaborated here.

[0164] The battery internal resistance fluctuation monitoring method provided in the embodiment of the present application obtains the current production output corresponding to the current production line; based on the current production output, the preset duration corresponding to the preset time period is determined, thereby ensuring the accuracy and rationality of the preset duration corresponding to the determined preset time period. Based on the preset duration, the current preset time period is determined, and each target battery produced by the current production line within the current preset time period is obtained to form the current target battery group, thereby ensuring that the number of the generated current target battery group is reasonable and representative. The internal resistance of each target battery in the current target battery group is detected to generate the current internal resistance data, thereby detecting whether the current internal resistance data corresponding to the current target battery group has fluctuated and changed.

[0165] In addition, the current production output corresponding to the current production line and the current environmental information corresponding to the current production line are obtained; based on the current production output and the current environmental information, the reference time range corresponding to the current target battery pack is determined, ensuring the accuracy and rationality of the determined reference time range. The target battery produced within the reference time range is determined as the reference target battery pack, ensuring the accuracy and representativeness of the determined reference target battery pack. Then, the reference internal resistance data corresponding to the reference target battery pack is obtained, and the reference internal resistance data is statistically calculated to obtain the reference statistical results, thereby ensuring that the current internal resistance number is detected based on the reference statistical results to see if it fluctuates and changes.

[0166] In this embodiment, a method for monitoring battery internal resistance fluctuation is provided, which can be used for the above-mentioned electronic device. The process includes the following steps:

[0167] Step S301, obtaining current internal resistance data corresponding to the current target battery pack.

[0168] The current target battery group is used to characterize each target battery produced by the current production line within the current preset time period.

[0169] For details about this step, please refer to the above description of step S201, which will not be elaborated here.

[0170] Step S302 , obtaining a benchmark statistical result corresponding to the current target battery group and a historical statistical result of a previous target battery group corresponding to the current target battery group.

[0171] For details about this step, please refer to the above description of step S202, which will not be elaborated here.

[0172] Step S303, statistically processing the current internal resistance data corresponding to the current target battery pack to generate a current statistical result.

[0173] For details about this step, please refer to the above description of step S203, which will not be elaborated here.

[0174] Step S304, comparing the current statistical result with the benchmark statistical result and the historical statistical result.

[0175] Specifically, the current statistical results include the current mean, the current variance, the current skewness and the current kurtosis; the benchmark statistical results include the benchmark mean, the benchmark variance, the benchmark skewness and the benchmark kurtosis; the historical statistical results include the historical mean, the historical variance, the historical skewness and the historical kurtosis; the above step S304 may include the following steps:

[0176] Step S3041, calculating the absolute value of the difference between the current average value and the reference average value to obtain a first absolute value.

[0177] Specifically, the electronic device may calculate the difference between the current average value and the reference average value, and then perform absolute value calculation on the difference between the current average value and the reference average value to obtain the first absolute value.

[0178] Step S3042, calculating the absolute value of the difference between the current variance and the reference variance to obtain a second absolute value.

[0179] Specifically, the electronic device may calculate the difference between the current variance and the reference variance, and then perform absolute value calculation on the difference between the current variance and the reference variance to obtain a second absolute value.

[0180] Step S3043, calculating the absolute value of the difference between the current skewness and the reference skewness to obtain a third absolute value.

[0181] Specifically, the electronic device may calculate the difference between the current skewness and the reference skewness, and then perform absolute value calculation on the difference between the current skewness and the reference skewness to obtain the third absolute value.

[0182] Step S3044, calculating the absolute value of the difference between the current kurtosis and the reference kurtosis to obtain a fourth absolute value.

[0183] Specifically, the electronic device may calculate the difference between the current kurtosis and the reference kurtosis, and then perform an absolute value calculation on the difference between the current kurtosis and the reference kurtosis to obtain a fourth absolute value.

[0184] Step S3045, calculating the absolute value of the difference between the current average value and the historical average value to obtain a fifth absolute value.

[0185] Specifically, the electronic device may calculate the difference between the current average value and the historical average value, and then perform absolute value calculation on the difference between the current average value and the historical average value to obtain the fifth absolute value.

[0186] Step S3046, calculating the absolute value of the difference between the current variance and the historical variance to obtain a sixth absolute value.

[0187] Specifically, the electronic device may calculate the difference between the current variance and the historical variance, and then perform an absolute value calculation on the difference between the current variance and the historical variance to obtain a sixth absolute value.

[0188] Step S3047, calculating the absolute value of the difference between the current skewness and the historical skewness to obtain the seventh absolute value.

[0189] Specifically, the electronic device may calculate the difference between the current skewness and the historical skewness, and then perform an absolute value calculation on the difference between the current skewness and the historical skewness to obtain the seventh absolute value.

[0190] Step S3048, calculate the absolute value of the difference between the current kurtosis and the historical kurtosis to obtain the eighth absolute value.

[0191] Specifically, the electronic device may calculate the difference between the current kurtosis and the historical kurtosis, and then perform an absolute value calculation on the difference between the current kurtosis and the historical kurtosis to obtain the eighth absolute value.

[0192] Step S3049, respectively detecting whether the first absolute value, the second absolute value, the third absolute value, the fourth absolute value, the fifth absolute value, the sixth absolute value, the seventh absolute value and the eighth absolute value are within corresponding preset ranges.

[0193] Specifically, the electronic device can respectively compare the first absolute value, the second absolute value, the third absolute value, the fourth absolute value, the fifth absolute value, the sixth absolute value, the seventh absolute value and the eighth absolute value with the corresponding preset ranges to detect whether the first absolute value, the second absolute value, the third absolute value, the fourth absolute value, the fifth absolute value, the sixth absolute value, the seventh absolute value and the eighth absolute value are within the corresponding preset ranges.

[0194] Among them, the electronic device can receive the preset ranges corresponding to the first absolute value, the second absolute value, the third absolute value, the fourth absolute value, the fifth absolute value, the sixth absolute value, the seventh absolute value and the eighth absolute value input by the user, and can also set the preset ranges corresponding to the first absolute value, the second absolute value, the third absolute value, the fourth absolute value, the fifth absolute value, the sixth absolute value, the seventh absolute value and the eighth absolute value according to actual conditions.

[0195] Step S305 , determining the internal resistance fluctuation result corresponding to the current target battery pack according to the comparison result.

[0196] Step S3051: if the first absolute value is not within the preset range corresponding to the first absolute value, it is determined that the current internal resistance data is abnormal relative to the reference internal resistance data, and the abnormal result is that the current internal resistance data increases or decreases.

[0197] Specifically, if the first absolute value is not within the preset range corresponding to the first absolute value, the electronic device determines that the current internal resistance data is abnormal relative to the reference internal resistance data, and the abnormal result is that the current internal resistance data increases or decreases.

[0198] Step S3052: if the second absolute value is not within the preset range corresponding to the second absolute value, it is determined that the current internal resistance data is abnormal relative to the reference internal resistance data, and the abnormal result is that the current internal resistance data is stratified.

[0199] Specifically, if the second absolute value is not within the preset range corresponding to the second absolute value, the electronic device determines that the current internal resistance data is abnormal relative to the reference internal resistance data, and the abnormal result is that the current internal resistance data is stratified.

[0200] Step S3053: if the third absolute value is not within the preset range corresponding to the third absolute value, it is determined that the current internal resistance data is abnormal relative to the reference internal resistance data, and the abnormal result is that the current internal resistance data is offset.

[0201] Specifically, if the third absolute value is not within the preset range corresponding to the third absolute value, the electronic device determines that the current internal resistance data is abnormal relative to the reference internal resistance data, and the abnormal result is that the current internal resistance data is offset.

[0202] Step S3054: if the fourth absolute value is not within the preset range corresponding to the fourth absolute value, it is determined that the current internal resistance data is abnormal relative to the reference internal resistance data, and the abnormal result is that the current internal resistance data is diffuse.

[0203] Specifically, if the fourth absolute value is not within the preset range corresponding to the fourth absolute value, the electronic device determines that the current internal resistance data is abnormal relative to the reference internal resistance data, and the abnormal result is that the current internal resistance data spreads. For example, Fig. 9 shown.

[0204] Step S3055: if the fifth absolute value is not within the preset range corresponding to the fifth absolute value, it is determined that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is that the current internal resistance data increases or decreases.

[0205] Specifically, if the fifth absolute value is not within the preset range corresponding to the fifth absolute value, the electronic device determines that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is that the current internal resistance data increases or decreases.

[0206] Step S3056: if the sixth absolute value is not within the preset range corresponding to the sixth absolute value, it is determined that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is that the current internal resistance data is stratified.

[0207] Specifically, if the sixth absolute value is not within the preset range corresponding to the sixth absolute value, the electronic device determines that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is that the current internal resistance data is stratified.

[0208] Step S3057: if the seventh absolute value is not within the preset range corresponding to the seventh absolute value, it is determined that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is that the current internal resistance data is offset.

[0209] Specifically, if the seventh absolute value is not within the preset range corresponding to the seventh absolute value, the electronic device determines that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is that the current internal resistance data is offset.

[0210] Step S3058: if the eighth absolute value is not within the preset range corresponding to the eighth absolute value, it is determined that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is that the current internal resistance data is diffuse.

[0211] Specifically, if the eighth absolute value is not within the preset range corresponding to the eighth absolute value, the electronic device determines that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is that the current internal resistance data is diffuse.

[0212] It should be noted that the preset range corresponding to the first absolute value is greater than the preset range corresponding to the fifth absolute value, the preset range corresponding to the second absolute value is greater than the preset range corresponding to the sixth absolute value, the preset range corresponding to the third absolute value is greater than the preset range corresponding to the seventh absolute value, and the preset range corresponding to the fourth absolute value is greater than the preset range corresponding to the eighth absolute value. In other words, the preset range corresponding to the difference between the current internal resistance data and the reference statistical result is greater than the preset range corresponding to the difference between the current internal resistance data and the historical statistical result.

[0213] Specifically, the benchmark statistical results are general rules based on a large amount of battery sample data. Batteries of different brands, models, and batches have individual differences due to factors such as materials and processes. Setting a larger preset range can accommodate these differences, avoid too many misjudgments due to individual characteristics not being completely consistent with the benchmark, and ensure that the system can reasonably monitor various batteries. In addition, the benchmark statistical results reflect the general performance change rules of the battery throughout its life cycle. The larger preset range can roughly evaluate the long-term performance of the battery at a macro level, providing a reference framework for the overall prediction of battery life.

[0214] By comparing the current internal resistance data with the historical statistical results and using a smaller preset range of differences, the system can be more sensitive to subtle changes in the battery's internal resistance. For example, during the use of the battery, if the internal resistance shows an abnormal trend of gradually rising or falling, this setting can enable the system to issue an early warning as soon as the trend emerges, reminding relevant personnel to pay attention to the battery status so that timely measures can be taken to avoid further deterioration of battery problems. In addition, the internal resistance of the target battery may fluctuate in the short term due to various factors during the charging and discharging process, such as temperature, current, etc. A smaller preset range of differences from historical statistical results can help capture these short-term fluctuations, thereby gaining a more comprehensive understanding of the real-time status of the battery in the current use stage, and providing data support for the refined management of the battery.

[0215] If the difference between the current internal resistance data and the benchmark statistical result exceeds the corresponding preset range, it may mean that the chemical structure or physical properties inside the battery have undergone major changes, such as loss of electrode materials, drying up or deterioration of the electrolyte, etc. This is the result of aging or damage of the target battery, abnormal working environment of the target battery, or improper use of the target battery.

[0216] If the difference between the current internal resistance data and the benchmark statistical results is within the corresponding preset range, but the difference between the current internal resistance data and the historical statistical results exceeds the corresponding preset range, this may be an early signal that the battery performance is beginning to change. This means that the battery's internal resistance is developing in an abnormal direction, and there may be some subtle changes happening inside the battery, such as slight polarization of the electrode surface, a small loss of active substances, etc. It is necessary to pay close attention to its subsequent development to determine whether it will deteriorate further.

[0217] Therefore, this application avoids the possibility of misjudgment due to individual differences in target batteries, changes in usage environment, etc. if only the benchmark statistical results are used as a reference. By comparing historical statistical results and using different preset ranges, the battery status can be evaluated from multiple angles, reducing the possibility of misjudgment.

[0218] It should be noted that the contents of the above steps S3051 - S3058 may be combined arbitrarily to generate the internal resistance fluctuation result corresponding to the current target battery pack.

[0219] Step S306: if the internal resistance fluctuation result indicates that the current internal resistance data is abnormal, then the duration of the abnormality of the current internal resistance data is recorded.

[0220] Specifically, if the internal resistance fluctuation result indicates that the current internal resistance data is abnormal, the electronic device may record the duration of the abnormality in the current internal resistance data.

[0221] The duration can be determined based on the internal resistance data corresponding to each target battery pack. The electronic device can determine the number of target battery packs corresponding to the abnormality, and then multiply the number of groups by the current preset time period to obtain the duration of the abnormality of the current internal resistance data.

[0222] Step S307: if the duration is greater than the preset duration threshold, the current operating parameters corresponding to the current production line are obtained.

[0223] Specifically, the electronic device may receive a preset duration threshold input by a user, or may set the preset duration threshold according to user needs. The embodiment of the present application does not specifically limit the manner in which the electronic device obtains the preset duration threshold.

[0224] Then, the electronic device may compare the duration with a preset duration threshold, and if the duration is greater than the preset duration threshold, obtain the current operating parameters corresponding to the current production line.

[0225] Among them, the current operating parameters may include the operating parameters of mechanical components, including the speed and torque of various motors in the production line, the running speed and tension of the conveyor belt, the joint angle and motion trajectory of the robot arm, etc. For example, a sudden change in the motor speed may indicate that there is a problem with the motor itself or the transmission components connected to it; excessive or insufficient tension of the conveyor belt may cause poor product transmission or damage to the product.

[0226] The current operating parameters can also include the operating parameters of electrical components, including measuring electrical characteristics such as voltage, current, resistance, capacitance, etc. For key electrical equipment, such as the power module in the control cabinet, real-time monitoring is performed to see whether its output voltage is stable within the rated value range and whether the current fluctuates abnormally. If the current of a circuit suddenly increases, it may indicate that the circuit is short-circuited or overloaded.

[0227] Current operating parameters can also include sensor data: production lines are usually equipped with a large number of sensors, such as temperature sensors, pressure sensors, humidity sensors, displacement sensors, etc. Temperature sensors can monitor the operating temperature of key parts of equipment. For example, if the temperature of the welding head of welding equipment on the production line is too high, it may lead to reduced welding quality or equipment damage; pressure sensors are used to measure pressure values ​​in hydraulic systems and pneumatic systems to ensure that these systems operate within the normal pressure range.

[0228] In addition, the current operating parameters can also include production process parameters, such as production beat: record the time required for each production link to complete the operation, as well as the production beat of the entire production line. If the production beat of a certain process suddenly becomes longer, it may be that the equipment of the process fails or the operator encounters an operating problem. Product processing parameters: For processing production lines, such as mechanical processing production lines, it is necessary to monitor the cutting parameters of the tool (cutting speed, feed rate, cutting depth), the opening and closing time of the mold, pressure, etc. In the injection molding production line, changes in parameters such as injection pressure, injection speed, and holding time directly affect product quality. Once these parameters are abnormal, product defects may occur. Material flow parameters: Track the flow of raw materials, semi-finished products and finished products on the production line, including material conveying speed, flow rate, storage capacity, etc. In the food processing production line, if the feed rate of raw materials is unstable, it may affect the formula ratio of the product, and thus affect the product quality.

[0229] In addition, the current operating parameters can also include environmental parameters. For example, temperature and humidity: the ambient temperature and humidity of the entire production workshop will affect the operation of the equipment and the production of products. For example, in the production line of electronic components, the requirements for environmental humidity are very strict. Excessive humidity may cause components to be damaged by moisture; in precision machining, changes in ambient temperature may affect the machining accuracy. Air quality: monitor the content of dust, particulate matter, harmful gases, etc. in the air. In semiconductor manufacturing workshops, tiny dust particles in the air may contaminate chips and affect product performance, so monitoring air quality is crucial.

[0230] Step S308, inputting the current operating parameters into a preset fault diagnosis model, outputting the current fault type corresponding to the current production line, and outputting prompt information based on the current fault type.

[0231] Specifically, the electronic device can input the current operating parameters into a preset fault diagnosis model, the preset fault diagnosis model extracts features from the current operating parameters, outputs the current fault type corresponding to the current production line, and outputs prompt information based on the current fault type.

[0232] Among them, the current fault type can be a rule-based model, a machine learning-based model, and a physical model-based model.

[0233] in,

[0234] The rule-based model is a series of rules established based on expert knowledge and experience. For example, if the current of the motor exceeds 120% of the rated current and lasts for more than 5 seconds, and the temperature of the motor rises by 30°C above the ambient temperature, the motor is judged to be overloaded. The rule base contains a large number of similar rules for different equipment and production conditions. When the operating parameters meet the conditions of a certain rule, the corresponding fault type can be diagnosed. The formulation of rules requires industry experts to have a deep understanding of the production line and long-term practical experience. With the upgrade of the production line and changes in production processes, the rule base needs to be continuously updated and improved.

[0235] Models based on machine learning can include:Supervised learning models: For example, using decision trees, support vector machines (SVM), neural networks and other algorithms. First, a large amount of operating parameter data with fault labels needs to be collected as a training set. During the training process, the model learns the mapping relationship between operating parameters and fault types. For example, for a neural network model for bearing fault diagnosis, the operating parameters such as vibration frequency, amplitude, temperature, etc. of the bearing are input, and the output is whether the bearing has a fault and the type of fault (such as wear, fatigue, corrosion, etc.). Unsupervised learning models: Such as clustering algorithms, which do not require fault label data. By clustering the operating parameters, similar operating states are clustered into one category. When new operating parameter data arrives, it is judged whether there is an abnormality based on the cluster to which it belongs. For example, if the new data point is far away from the cluster under normal operating conditions, it can be considered that the production line may have a fault, but further analysis is needed to determine the type of fault. Deep learning models: In particular, convolutional neural networks (CNN) and long short-term memory networks (LSTM) have good applications in processing time series data and image data. In production line monitoring, if the operating parameters can be converted into image form (such as using time-frequency analysis to convert vibration signals into time-frequency graphs), CNN can be used for fault diagnosis; for operating parameters with time series characteristics (such as the temperature change curve of equipment over a period of time), LSTM can capture its time dependency well, thereby accurately diagnosing faults.

[0236] The physical model-based model builds a fault diagnosis model based on the physical principles and mathematical models of the production line equipment. For example, for a mechanical vibration system, its dynamic equation can be established based on Newton's second law and vibration theory. By substituting the actual measured vibration parameters into the equation, the system's natural frequency, damping ratio and other characteristic parameters are calculated. If these parameters deviate significantly from the theoretical values, it can be inferred that there is a fault in the system, such as loose parts and wear. The advantage of this model is that it has a clear physical meaning, but the disadvantage is that the modeling process is usually complicated and requires a deep understanding of the physical mechanism of the equipment.

[0237] Among them, the fault types include mechanical fault types, electrical fault types, sensor fault types, production process faults, and environment-related faults.

[0238] Among them, the types of mechanical failures may include: such as wear, breakage, looseness of parts, etc. Taking the gears in the production line as an example, the wear of the gears will lead to an increase in the meshing clearance between the gears, which is manifested as increased vibration and noise during operation. At the same time, by measuring the gear tooth thickness, tooth shape and other parameters, the degree of wear can be judged, and then the type of failure can be determined.

[0239] Among them, electrical fault types may include: short circuit, open circuit, overload, undervoltage, etc. For example, in an electrical control cabinet, if a line is short-circuited, the fuse will blow, and the fault location and type can be quickly located by detecting the current and voltage changes in the line.

[0240] Among them, sensor failure may include: sensor failure, reduced accuracy, etc. For example, a temperature sensor may have a large deviation in measurement value due to long-term use. By comparing the data with other similar sensors or calibrating the sensor, it can be determined whether it is faulty.

[0241] Among them, production process failures may include: abnormal process parameters: such as incorrect processing parameter settings, missing process steps, etc. In metal processing production lines, if the feed rate of the cutting tool is set too large, the surface roughness of the processing will not meet the requirements. This failure can be discovered by testing the processing quality of the product and comparing the standard process parameters.

[0242] Material flow failure: For example, material blockage, material supply interruption caused by conveying equipment failure, etc. In an automated packaging production line, if the conveying device of the packaging material fails, the packaging material cannot be supplied in time. Such failures can be diagnosed by monitoring the flow status of the material and the operation of the equipment.

[0243] Among them, environmental-related faults may include: Environmental parameters exceeding the standard: such as too high or too low temperature, too high humidity, poor air quality, etc., which affect production. In pharmaceutical production lines, the requirements for environmental cleanliness are extremely high. If the content of microorganisms in the air exceeds the standard, it will cause drug contamination. Environmental monitoring equipment can detect such environmental faults in a timely manner.

[0244] In an optional implementation manner of the present application, the training process of the preset fault diagnosis model includes:

[0245] Step a1: Obtain a training data set.

[0246] The training data set includes training operation parameters and training fault types corresponding to the training operation parameters.

[0247] Specifically, electronic equipment can collect data covering various fault types from actual production lines. For example, for a machining production line, it is necessary to collect fault data such as tool wear, abnormal spindle vibration, and motor overload. For each fault type, it is necessary to ensure that the data is representative and can reflect the performance of the fault at different levels.

[0248] At the same time, the electronic equipment collects data when the production line is operating normally. The normal operation data serves as a comparison benchmark to help the model distinguish between normal and faulty states. The normal operation data should cover data from different production batches and different production environments (such as different temperature and humidity conditions).

[0249] Then, the electronic device accurately labels the collected fault data and clearly indicates the fault type corresponding to each data. For example, the data of motor overheating fault is labeled as "motor overheating", and the data of transmission belt slippage is labeled as "transmission belt slippage", etc., thereby generating a training data set.

[0250] Step a2, identifying the training operation parameters and determining the time series data in the training data set.

[0251] Specifically, the electronic device can identify the training operation parameters and determine the time series data in the training data set.

[0252] Among them, time series data may include equipment vibration data, current and voltage data and other data.

[0253] Step a3: extract time domain features from time series data and convert the time domain features into frequency domain features.

[0254] Specifically, the electronic device can extract time domain features from the time series data and convert the time domain features into frequency domain features.

[0255] Among them, the time domain features may include mean, variance, standard deviation, maximum value, minimum value, peak value, kurtosis, skewness, etc. For example, the mean of equipment vibration data can reflect the average level of vibration, and the kurtosis can reflect the impact characteristics in the vibration signal.

[0256] Then, the electronic device converts the time domain features into frequency domain features through Fourier transform or wavelet transform, such as main frequency, frequency band energy, frequency variance, etc. For example, in motor fault diagnosis, motor faults often lead to changes in its vibration frequency, and motor faults can be effectively detected by analyzing frequency domain features.

[0257] Step a4: extracting time-frequency domain features corresponding to the training operation parameters.

[0258] Specifically, the electronic device can also use time-frequency analysis methods (such as short-time Fourier transform, wavelet packet decomposition) to extract time-frequency domain features corresponding to the training operation parameters. These features can simultaneously reflect the distribution of the signal in time and frequency.

[0259] Step a5, calculating the time domain features and frequency domain features corresponding to the training data set, and the correlation between the time and frequency domain features and the fault types corresponding to the training data set.

[0260] Specifically, the electronic device may calculate the time domain features, the frequency domain features, and the correlation between the time and frequency domain features and the fault type.

[0261] Optionally, the electronic device may use the Pearson correlation coefficient to measure the time domain features, the frequency domain features, and the linear correlation between the time-frequency domain features and the fault type.

[0262] Step a6, deleting the time domain features, and / or frequency domain features, and / or time-frequency domain features whose correlation is less than a preset correlation threshold, to obtain the target features.

[0263] Specifically, the electronic device may compare the calculated correlations with a preset correlation threshold and, based on the comparison result, delete the time domain features, and / or frequency domain features, and / or time-frequency domain features whose correlations are less than the preset correlation threshold to obtain the target features.

[0264] In an optional implementation, the electronic device may also compare the calculated correlations with a preset correlation threshold. The electronic device may delete the time domain features, and / or frequency domain features, and / or time-frequency domain features whose correlations are less than the preset correlation threshold according to the comparison result to obtain spare features.

[0265] Then, the electronic device selects features using the feature importance evaluation function of a machine learning algorithm such as a random forest. In a random forest, by calculating the importance score of each backup feature in the process of building a decision tree, the backup features with importance scores greater than a preset score threshold are selected to obtain the target feature.

[0266] Step a7: Based on the target features, train the initial fault diagnosis network to generate a preset fault diagnosis model.

[0267] Specifically, the electronic device can select a suitable optimization algorithm to train the initial fault diagnosis network based on the target characteristics and generate a preset fault diagnosis model.

[0268] Among them, the optimization algorithm can be a gradient descent algorithm and its variants (stochastic gradient descent, Adagrad, Adadelta, Adam, etc.). These optimization algorithms minimize the loss function by continuously updating the parameters of the model. For example, in neural network training, the Adam optimization algorithm is widely used because of its adaptive learning rate characteristics and can converge quickly during the training process.

[0269] In addition, electronic devices can also select appropriate loss functions according to the nature of the fault diagnosis problem. For classification problems, the commonly used loss functions are cross entropy loss functions; for regression problems, the mean square error (MSE) loss function is commonly used. For example, in multi-classification fault diagnosis problems, the cross entropy loss function is used to measure the difference between the model prediction results and the actual fault type.

[0270] The electronic device can use the validation set in the training data set to adjust the hyperparameters of the preset fault diagnosis model. The optimal hyperparameters are selected by evaluating the performance of the model under different hyperparameter combinations on the validation set. For example, when training the preset fault diagnosis model, by trying different maximum depth values ​​on the validation set, the maximum depth that makes the model most accurate on the validation set is selected as the final hyperparameter.

[0271] The battery internal resistance fluctuation monitoring method provided in the embodiment of the present application calculates the absolute value of the difference between the current average value and the benchmark average value to obtain a first absolute value; calculates the absolute value of the difference between the current variance and the benchmark variance to obtain a second absolute value; calculates the absolute value of the difference between the current skewness and the benchmark skewness to obtain a third absolute value; calculates the absolute value of the difference between the current kurtosis and the benchmark kurtosis to obtain a fourth absolute value; calculates the absolute value of the difference between the current average value and the historical average value to obtain a fifth absolute value; calculates the absolute value of the difference between the current variance and the historical variance to obtain a sixth absolute value; calculates the absolute value of the difference between the current skewness and the historical skewness to obtain a seventh absolute value; calculates the absolute value of the difference between the current kurtosis and the historical kurtosis to obtain an eighth absolute value, thereby ensuring the accuracy of the first to eighth absolute values ​​obtained, and determining the change and fluctuation of the current internal resistance data relative to the benchmark statistical results and the historical statistical results based on the first to eighth absolute values. Then, the first absolute value, the second absolute value, the third absolute value, the fourth absolute value, the fifth absolute value, the sixth absolute value, the seventh absolute value and the eighth absolute value are respectively detected to see whether they are within the corresponding preset ranges, so that the internal resistance fluctuation result corresponding to the current target battery pack can be determined based on the detection results.

[0272] Then, based on the detection results that the first absolute value, the second absolute value, the third absolute value, the fourth absolute value, the fifth absolute value, the sixth absolute value, the seventh absolute value and the eighth absolute value are not within the corresponding preset range, the internal resistance fluctuation result corresponding to the current internal resistance number corresponding to the current target battery pack is determined, thereby ensuring the accuracy of the internal resistance fluctuation result corresponding to the current internal resistance number corresponding to the current target battery pack, and then early warning can be given based on the internal resistance fluctuation result to avoid the generated target battery being unqualified and causing serious problems.

[0273] In addition, if the internal resistance fluctuation result indicates that the current internal resistance data is abnormal, the duration of the abnormality of the current internal resistance data is recorded. Then, if the duration is greater than the preset duration threshold, the current operating parameters corresponding to the current production line are obtained, so that the current operating parameters can be input into the preset fault diagnosis model, the current fault type corresponding to the current production line is output, and prompt information is output based on the current fault type. In this way, fault detection of the current production line is realized, so that the user can repair the current production line based on the output prompt information, without the need for manual troubleshooting of the current production line, which improves work efficiency and saves time.

[0274] Among them, the training process of the preset fault diagnosis model includes: obtaining a training data set; identifying the training operation parameters and determining the time series data in the training data set; extracting the time domain features in the time series data and converting the time domain features into frequency domain features; extracting the time-frequency domain features corresponding to the training operation parameters; calculating the correlation between the time domain features, frequency domain features corresponding to the training data set and the time-frequency domain features and the fault types corresponding to the training data set, so that the time domain features and / or frequency domain features and / or time-frequency domain features with correlations less than the preset correlation threshold can be deleted according to the correlation to obtain the target features, thereby ensuring that the correlation between the obtained target features and the fault types is strong. Then, the accuracy of the preset fault diagnosis model generated by training the initial fault diagnosis network based on the target features can be guaranteed, thereby improving the accuracy of the current fault type output by the preset fault diagnosis model.

[0275] In this embodiment, a battery internal resistance fluctuation monitoring device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated here. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0276] This embodiment provides a battery internal resistance fluctuation monitoring device, such as Fig.10 As shown, including:

[0277] The first acquisition module 401 is used to acquire the current internal resistance data corresponding to the current target battery group; the current target battery group is used to characterize each target battery produced by the current production line within the current preset time period;

[0278] The second acquisition module 402 is used to acquire the benchmark statistical result corresponding to the current target battery group and the historical statistical result of the previous target battery group corresponding to the current target battery group;

[0279] The calculation module 403 is used to perform statistical processing on the current internal resistance data corresponding to the current target battery pack to generate a current statistical result;

[0280] A comparison module 404 is used to compare the current statistical result with the benchmark statistical result and the historical statistical result;

[0281] The determination module 405 is used to determine the internal resistance fluctuation result corresponding to the current target battery pack according to the comparison result.

[0282] In some optional embodiments, the second acquisition module 402 is specifically used to obtain the current production output corresponding to the current production line and the current environmental information corresponding to the current production line; based on the current production output and the current environmental information, determine the reference time range corresponding to the current target battery pack; determine the target battery produced within the reference time range as the reference target battery pack; obtain the reference internal resistance data corresponding to the reference target battery pack; perform statistical calculations on the reference internal resistance data to obtain reference statistical results.

[0283] In some optional embodiments, the first acquisition module 401 is specifically used to obtain the current production output corresponding to the current production line; based on the current production output, determine the preset duration corresponding to the preset time period; based on the preset duration, determine the current preset time period; obtain each target battery produced by the current production line within the current preset time period to form a current target battery group; detect the internal resistance of each target battery in the current target battery group to generate current internal resistance data.

[0284] In some optional implementations, the current statistical results include the current mean, the current variance, the current skewness, and the current kurtosis; the benchmark statistical results include the benchmark mean, the benchmark variance, the benchmark skewness, and the benchmark kurtosis; the historical statistical results include the historical mean, the historical variance, the historical skewness, and the historical kurtosis; the comparison module 404 is specifically used to calculate the absolute value of the difference between the current mean and the benchmark mean to obtain a first absolute value; calculate the absolute value of the difference between the current variance and the benchmark variance to obtain a second absolute value; calculate the absolute value of the difference between the current skewness and the benchmark skewness to obtain a third absolute value; calculate the current The fourth absolute value is obtained by calculating the absolute value of the difference between the previous kurtosis and the benchmark kurtosis; the fifth absolute value is obtained by calculating the absolute value of the difference between the current average and the historical average; the sixth absolute value is obtained by calculating the absolute value of the difference between the current variance and the historical variance; the seventh absolute value is obtained by calculating the absolute value of the difference between the current skewness and the historical skewness; the eighth absolute value is obtained by calculating the absolute value of the difference between the current kurtosis and the historical kurtosis; and the first absolute value, the second absolute value, the third absolute value, the fourth absolute value, the fifth absolute value, the sixth absolute value, the seventh absolute value and the eighth absolute value are respectively detected to see whether they are within the corresponding preset ranges.

[0285] In some optional embodiments, the determination module 405 is specifically used to determine that if the first absolute value is not within the preset range corresponding to the first absolute value, the current internal resistance data is determined to be abnormal relative to the benchmark internal resistance data, and the abnormal result is that the current internal resistance data rises or falls; if the second absolute value is not within the preset range corresponding to the second absolute value, the current internal resistance data is determined to be abnormal relative to the benchmark internal resistance data, and the abnormal result is the stratification of the current internal resistance data; if the third absolute value is not within the preset range corresponding to the third absolute value, the current internal resistance data is determined to be abnormal relative to the benchmark internal resistance data, and the abnormal result is the offset of the current internal resistance data; if the fourth absolute value is not within the preset range corresponding to the fourth absolute value, the current internal resistance data is determined to be abnormal relative to the benchmark internal resistance data, and the abnormal result is the offset of the current internal resistance data. The result is the diffusion of the current internal resistance data; if the fifth absolute value is not within the preset range corresponding to the fifth absolute value, it is determined that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is that the current internal resistance data rises or falls; if the sixth absolute value is not within the preset range corresponding to the sixth absolute value, it is determined that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is the stratification of the current internal resistance data; if the seventh absolute value is not within the preset range corresponding to the seventh absolute value, it is determined that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is the offset of the current internal resistance data; if the eighth absolute value is not within the preset range corresponding to the eighth absolute value, it is determined that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is the diffusion of the current internal resistance data.

[0286] In some optional embodiments, the battery internal resistance fluctuation monitoring device is as follows: Fig.11 As shown, it also includes:

[0287] The recording module 406 is used to record the duration of the abnormality of the current internal resistance data if the internal resistance fluctuation result indicates that the current internal resistance data is abnormal;

[0288] The third acquisition module 407 is used to acquire the current operating parameters corresponding to the current production line if the duration is greater than a preset duration threshold;

[0289] The output module 408 is used to input the current operating parameters into the preset fault diagnosis model, output the current fault type corresponding to the current production line, and output prompt information based on the current fault type.

[0290] In some optional embodiments, the output module 408 is specifically used to obtain a training data set; the training data set includes training operation parameters and training fault types corresponding to the training operation parameters; the training operation parameters are identified to determine the time series data in the training data set; the time domain features in the time series data are extracted, and the time domain features are converted into frequency domain features; the time-frequency domain features corresponding to the training operation parameters are extracted; the correlation between the time domain features, frequency domain features and the time-frequency domain features corresponding to the training data set and the fault types corresponding to the training data set is calculated; the time domain features, and / or frequency domain features, and / or time-frequency domain features whose correlation is less than a preset correlation threshold are deleted to obtain the target features; based on the target features, the initial fault diagnosis network is trained to generate a preset fault diagnosis model.

[0291] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0292] The battery internal resistance fluctuation monitoring device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0293] The embodiment of the present invention also provides an electronic device having the above Fig.10 and Fig.11 The battery internal resistance fluctuation monitoring device shown.

[0294] See also Fig.12 , Fig.12 is a schematic diagram of the structure of an electronic device provided by an optional embodiment of the present invention, such as Fig.12 As shown, the electronic device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig.12 A processor 10 is taken as an example.

[0295] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0296] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0297] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0298] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0299] The electronic device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Fig.12 The example of connecting through bus is taken in the following.

[0300] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0301] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0302] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0303] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for monitoring battery internal resistance fluctuation, characterized in that: The method comprises: Obtaining current internal resistance data corresponding to a current target battery pack; the current target battery pack is used to characterize each target battery produced by the current production line within a current preset time period; Obtaining a benchmark statistical result corresponding to the current target battery group and a historical statistical result of a previous target battery group corresponding to the current target battery group; Performing statistical processing on the current internal resistance data corresponding to the current target battery pack to generate a current statistical result; Comparing the current statistical result with the benchmark statistical result and the historical statistical result respectively; According to the comparison result, the internal resistance fluctuation result corresponding to the current target battery pack is determined.

2. The method according to claim 1, characterized in that: The obtaining of the benchmark statistical result corresponding to the current target battery group includes: Acquire the current production output corresponding to the current production line and the current environment information corresponding to the current production line; Determining a reference time range corresponding to the current target battery group based on the current production output and the current environmental information; Determine the target battery produced within the reference time range as the reference target battery pack; Acquiring reference internal resistance data corresponding to the reference target battery pack; Statistical calculation is performed on the benchmark internal resistance data to obtain the benchmark statistical result.

3. The method according to claim 1, characterized in that The obtaining of current internal resistance data corresponding to the current target battery pack includes: Obtaining the current production output corresponding to the current production line; Based on the current production output, determining a preset duration corresponding to a preset time period; Based on the preset duration, determining the current preset time period; Acquire each target battery produced by the current production line within the current preset time period to form the current target battery group; The internal resistance of each of the target batteries in the current target battery group is detected to generate the current internal resistance data.

4. The method according to claim 1, characterized in that: The current statistical result includes the current mean, current variance, current skewness and current kurtosis; the benchmark statistical result includes the benchmark mean, benchmark variance, benchmark skewness and benchmark kurtosis; the historical statistical result includes the historical mean, historical variance, historical skewness and historical kurtosis; the current statistical result is compared with the benchmark statistical result and the historical statistical result, respectively, including: Calculating an absolute value of a difference between the current average value and the reference average value to obtain a first absolute value; Calculating an absolute value of a difference between the current variance and the reference variance to obtain a second absolute value; calculating an absolute value of a difference between the current skewness and the reference skewness to obtain a third absolute value; Calculating an absolute value of a difference between the current kurtosis and the reference kurtosis to obtain a fourth absolute value; Calculating an absolute value of a difference between the current average value and the historical average value to obtain a fifth absolute value; Calculating an absolute value of a difference between the current variance and the historical variance to obtain a sixth absolute value; calculating an absolute value of a difference between the current skewness and the historical skewness to obtain a seventh absolute value; Calculating the absolute value of the difference between the current kurtosis and the historical kurtosis to obtain an eighth absolute value; It is respectively detected whether the first absolute value, the second absolute value, the third absolute value, the fourth absolute value, the fifth absolute value, the sixth absolute value, the seventh absolute value and the eighth absolute value are within corresponding preset ranges.

5. The method according to claim 4, characterized in that Determining the internal resistance fluctuation result corresponding to the current target battery pack according to the comparison result includes: If the first absolute value is not within the preset range corresponding to the first absolute value, it is determined that the current internal resistance data is abnormal relative to the reference internal resistance data, and the abnormal result is that the current internal resistance data increases or decreases; If the second absolute value is not within the preset range corresponding to the second absolute value, it is determined that the current internal resistance data is abnormal relative to the reference internal resistance data, and the abnormal result is that the current internal resistance data is layered; If the third absolute value is not within the preset range corresponding to the third absolute value, it is determined that the current internal resistance data is abnormal relative to the reference internal resistance data, and the abnormal result is a deviation of the current internal resistance data; If the fourth absolute value is not within the preset range corresponding to the fourth absolute value, it is determined that the current internal resistance data is abnormal relative to the reference internal resistance data, and the abnormal result is that the current internal resistance data is diffused; If the fifth absolute value is not within the preset range corresponding to the fifth absolute value, it is determined that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is that the current internal resistance data increases or decreases; If the sixth absolute value is not within the preset range corresponding to the sixth absolute value, it is determined that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is the stratification of the current internal resistance data; If the seventh absolute value is not within the preset range corresponding to the seventh absolute value, it is determined that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is a deviation of the current internal resistance data; If the eighth absolute value is not within the preset range corresponding to the eighth absolute value, it is determined that the current internal resistance data is abnormal relative to the historical internal resistance data, and the abnormal result is that the current internal resistance data is diffused; Among them, the preset range corresponding to the first absolute value is larger than the preset range corresponding to the fifth absolute value, the preset range corresponding to the second absolute value is larger than the preset range corresponding to the sixth absolute value, the preset range corresponding to the third absolute value is larger than the preset range corresponding to the seventh absolute value, and the preset range corresponding to the fourth absolute value is larger than the preset range corresponding to the eighth absolute value.

6. The method according to claim 1, characterized in that The method further comprises: If the internal resistance fluctuation result indicates that the current internal resistance data is abnormal, then the duration of the abnormality of the current internal resistance data is recorded; If the duration is greater than a preset duration threshold, obtaining current operating parameters corresponding to the current production line; The current operating parameters are input into a preset fault diagnosis model, the current fault type corresponding to the current production line is output, and prompt information is output based on the current fault type.

7. The method according to claim 6, characterized in that The training process of the preset fault diagnosis model includes: Acquire a training data set; the training data set includes training operation parameters and training fault types corresponding to the training operation parameters; Identifying the training operation parameters and determining the time series data in the training data set; Extracting time domain features from the time series data and converting the time domain features into frequency domain features; Extracting time-frequency domain features corresponding to the training operation parameters; Calculating the time domain features, the frequency domain features corresponding to the training data set, and the correlation between the time-frequency domain features and the fault type corresponding to the training data set; Deleting the time domain features, and / or the frequency domain features, and / or the time-frequency domain features whose correlation is less than a preset correlation threshold, to obtain target features; Based on the target features, an initial fault diagnosis network is trained to generate the preset fault diagnosis model.

8. A battery internal resistance fluctuation monitoring device, characterized in that: The device comprises: A first acquisition module is used to acquire current internal resistance data corresponding to a current target battery pack; the current target battery pack is used to characterize each target battery produced by the current production line within a current preset time period; A second acquisition module, used to acquire a benchmark statistical result corresponding to the current target battery group and a historical statistical result of a previous target battery group corresponding to the current target battery group; A calculation module, used for performing statistical processing on the current internal resistance data corresponding to the current target battery pack to generate a current statistical result; A comparison module, used to compare the current statistical result with the benchmark statistical result and the historical statistical result respectively; The determination module is used to determine the internal resistance fluctuation result corresponding to the current target battery pack according to the comparison result.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the battery internal resistance fluctuation monitoring method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the battery internal resistance fluctuation monitoring method according to any one of claims 1 to 7.

Images