Battery fault detection method and device, computer device, readable storage medium and program product

Abstract

The application relates to a battery fault detection method and device and a computer readable storage medium. The method comprises the following steps: obtaining relevant data of a battery module; calculating the impedance and impedance average of each single battery in the battery module in a preset frequency range according to the relevant data; calculating the correlation coefficient of each single battery in different preset frequency ranges; calculating the difference between the average value generated by the correlation coefficients of multiple single batteries in different preset frequency ranges and the correlation coefficient of each single battery, sorting the difference value, and obtaining the difference ranking value of each single battery in different preset frequency ranges; calculating the standard deviation and average value of the difference ranking value of each single battery in different preset frequency ranges, determining the preset threshold of the score of the single battery, scoring the single battery, and screening out the single battery with faults according to the score of each single battery. The method can quickly and accurately detect the single battery with faults in the battery module.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery detection, in particular to a battery fault detection method and device, computer equipment, computer readable storage medium and computer program product. BACKGROUND

[0002] With the rapid development of battery technology, renewable energy, electric vehicles and other fields have made continuous progress. However, battery abnormal problems still restrict the development of these technologies.

[0003] The existing technology is divided into battery internal parameter monitoring and data-driven abnormal diagnosis method. The former monitors and analyzes the internal parameters of lithium ion battery. The changes of these parameters can reflect the health status and performance degradation of the battery. The latter uses machine learning and data mining technology to realize automatic identification and prediction of battery abnormal state. However, these two methods are based on the abnormal diagnosis of single battery. When the battery module fails, only the single battery in the battery module can be detected one by one, and the single battery that fails in the battery module cannot be quickly and effectively detected, which is easy to cause waste of resources in the detection process. SUMMARY

[0004] Therefore, it is necessary to provide a battery fault detection method, device, computer equipment, computer readable storage medium and computer program product capable of quickly and accurately detecting the single battery that fails in the battery module.

[0005] In a first aspect, the present application provides a battery fault detection method, comprising:

[0006] Obtaining related data of a battery module; the related data includes the voltage and current of each single battery in the battery module;

[0007] According to the related data, the impedance and impedance average of each single battery in the battery module in a preset frequency range are calculated;

[0008] According to the impedance and the impedance average, the correlation coefficient of each single battery under different preset frequency ranges is calculated;

[0009] The difference between the correlation coefficient of each single battery and the average correlation coefficient of multiple single batteries under different preset frequency ranges is calculated, and the difference is sorted to obtain the difference ranking value of each single battery under the different preset frequency ranges;

[0010] The standard deviation and mean of the difference ranking value of each single battery under the different preset frequency ranges are calculated, and the score preset threshold of the single battery is determined according to the standard deviation and mean;

[0011] According to the difference ranking value of each single battery in the whole preset frequency range and the score preset threshold, the single battery is scored to obtain the score of the single battery.

[0012] According to the score of each single battery, a single battery with a fault is screened out.

[0013] In one embodiment, the impedance and impedance average of each single battery in the battery module in a preset frequency range are calculated according to the related data, including:

[0014] Based on wavelet transform, the voltage and current of each single battery are represented by waveforms in the time-frequency domain.

[0015] The time-frequency data of the voltage and current in the waveform state are compared to obtain the impedance of each single battery.

[0016] According to the impedance of each single battery, the impedance average of the single battery is obtained.

[0017] In one embodiment, the correlation coefficient of each single battery in different preset frequency ranges is calculated according to the impedance and the impedance average, including:

[0018] For each single battery and each preset frequency range, the impedance covariance between the single battery and each remaining single battery in the preset frequency range, and the impedance standard deviation of the single battery are calculated according to the impedance and the impedance average of the single battery.

[0019] According to the impedance standard deviation of the single battery and the impedance covariance corresponding to the single battery, the correlation coefficient of the single battery in the preset frequency range is calculated.

[0020] In one embodiment, the score preset threshold of the single battery is determined according to the standard deviation and the average, including:

[0021] The average plus a preset multiple of the standard deviation is taken as the upper limit of the score preset threshold.

[0022] The average minus a preset multiple of the standard deviation is taken as the lower limit of the score preset threshold.

[0023] In one embodiment, the single battery is scored according to the difference ranking value of the single battery in the whole preset frequency range and the score preset threshold to obtain the score of the single battery, including:

[0024] If the difference ranking value of the single battery in the whole preset frequency range exceeds the score preset threshold, a difference between the difference ranking value and an upper limit and a lower limit of the score preset threshold is calculated, and a minimum difference plus one is taken as the score of the single battery;

[0025] If the difference ranking value of the single battery in the whole preset frequency range does not exceed the score preset threshold, the score of the single battery is set to zero.

[0026] In one embodiment, the screening of the faulty single battery according to the score of each single battery comprises:

[0027] The score of each single battery is taken as a data point, and a radius and a reachable distance of each data point are determined;

[0028] For each data point, a local reachable density of the data point is calculated according to the reachable distances of the remaining data points in a range formed by the radius of the data point;

[0029] According to the local reachable density of the data point and the local reachable densities of the remaining data points in the range formed by the radius of the data point, a local outlier factor of each data point is calculated;

[0030] If the local outlier factor of the data point is greater than a preset value, the single battery represented by the data point is a faulty single battery.

[0031] In a second aspect, the application further provides a battery fault detection device, comprising:

[0032] An acquisition module is configured to acquire relevant data of a battery module; the relevant data comprises voltage and current of each single battery in the battery module;

[0033] A calculation module is configured to calculate impedance and impedance average of each single battery in the battery module in a preset frequency range according to the relevant data;

[0034] The calculation module is further configured to calculate correlation coefficients of each single battery in different preset frequency ranges according to the impedance and the impedance average;

[0035] The calculation module is further configured to calculate a difference between a mean value generated by the correlation coefficients of multiple single batteries in different preset frequency ranges and the correlation coefficient of each single battery, sort the difference, and obtain a difference ranking value of each single battery in the different preset frequency ranges;

[0036] The computing module is further configured to calculate a standard deviation and a mean value of the difference ranking values of each of the single batteries at the different preset frequency bands, and determine a preset threshold of the score of the single battery according to the standard deviation and the mean value;

[0037] The scoring module is configured to score the single battery according to the difference ranking values of the single battery at the entire preset frequency band and the preset threshold of the score, to obtain the score of the single battery.

[0038] The screening module is configured to screen out the single battery with faults according to the score of each of the single batteries.

[0039] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, the memory stores a computer program, and the processor realizes the following steps when executing the computer program:

[0040] Obtaining relevant data of a battery module; the relevant data comprises voltage and current of each single battery in the battery module;

[0041] According to the relevant data, calculating impedance and impedance mean value of each single battery in the battery module at a preset frequency band;

[0042] According to the impedance and the impedance mean value, calculating a correlation coefficient of each single battery at different preset frequency bands;

[0043] Calculating a difference value between a mean value generated by the correlation coefficients of multiple single batteries at different preset frequency bands and the correlation coefficient of each single battery, and sorting the difference value to obtain a difference ranking value of each single battery at the different preset frequency bands;

[0044] Calculating a standard deviation and a mean value of the difference ranking values of each of the single batteries at the different preset frequency bands, and determining a preset threshold of the score of the single battery according to the standard deviation and the mean value;

[0045] According to the difference ranking values of the single battery at the entire preset frequency band and the preset threshold of the score, scoring the single battery to obtain the score of the single battery;

[0046] According to the score of each of the single batteries, screening out the single battery with faults.

[0047] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the following steps:

[0048] Obtaining relevant data of a battery module; the relevant data comprises voltage and current of each single battery in the battery module;

[0049] According to the correlation data, impedance and impedance average of each single battery in the battery module in a preset frequency range are calculated;

[0050] According to the impedance and the impedance average, a correlation coefficient of each single battery in different preset frequency ranges is calculated;

[0051] A difference between the correlation coefficient of each single battery and the average of the correlation coefficients of multiple single batteries in different preset frequency ranges is calculated, and the difference is sorted to obtain a difference ranking value of each single battery in the different preset frequency ranges;

[0052] A standard deviation and an average of the difference ranking values of each single battery in the different preset frequency ranges are calculated, and a score preset threshold of the single battery is determined according to the standard deviation and the average;

[0053] According to the difference ranking value of the single battery in the entire preset frequency range and the score preset threshold, the single battery is scored to obtain a score of the single battery;

[0054] According to the score of each single battery, a single battery with a fault is screened out.

[0055] In a fifth aspect, the present application further provides a computer program product comprising a computer program which, when executed by a processor, implements the following steps:

[0056] Obtaining correlation data of a battery module; the correlation data comprises voltage and current of each single battery in the battery module;

[0057] According to the correlation data, impedance and impedance average of each single battery in the battery module in a preset frequency range are calculated;

[0058] According to the impedance and the impedance average, a correlation coefficient of each single battery in different preset frequency ranges is calculated;

[0059] A difference between the correlation coefficient of each single battery and the average of the correlation coefficients of multiple single batteries in different preset frequency ranges is calculated, and the difference is sorted to obtain a difference ranking value of each single battery in the different preset frequency ranges;

[0060] A standard deviation and an average of the difference ranking values of each single battery in the different preset frequency ranges are calculated, and a score preset threshold of the single battery is determined according to the standard deviation and the average;

[0061] According to the difference ranking value of the single battery in the whole preset frequency range and the score preset threshold, the single battery is scored to obtain the score of the single battery.

[0062] According to the score of each single battery, a single battery with a fault is screened out.

[0063] The above battery fault detection method, device, computer equipment, computer readable storage medium and computer program product, first, the voltage and current of each single battery in the battery module are obtained, and the impedance of each single battery is calculated according to the voltage and current of each single battery. The impedance mean value is calculated according to the impedance of each single battery. According to the impedance of the single battery and the impedance mean value, the correlation coefficient of each single battery in different preset frequency ranges is calculated. According to the correlation coefficient, the difference between the correlation coefficient of each single battery in different preset frequency ranges and the mean value of the correlation coefficient of all single batteries in the corresponding preset frequency range is calculated. The difference values of the single batteries in different preset frequency ranges are sorted to obtain the difference ranking values of the single batteries in different preset frequency ranges. According to the difference ranking value of the single battery, the standard deviation and mean value of the ranking value in different preset frequency ranges are calculated, and then the score preset threshold of the single battery is obtained according to the standard deviation and mean value of the ranking value. According to the difference ranking value of the single battery in the whole preset frequency range and the score preset threshold, the single battery is scored, and according to the score of each single battery, a single battery with a fault in the battery module is screened out. Therefore, the present application can process different single batteries in the battery module to obtain the score of each single battery, quickly and accurately find the single battery with a fault in the battery module which is different from the change trend of other single batteries, and effectively reduce the resource waste caused by checking each single battery one by one in the battery module fault detection process. BRIEF DESCRIPTION OF DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0065] Figure 1 A flowchart of a battery fault detection method in one embodiment;

[0066] Figure 2 A flowchart of a battery fault detection method in another embodiment;

[0067] Figure 3Impedance chart of a single battery in a battery module in an embodiment;

[0068] Figure 4 Local outlier factor distribution chart of a single battery in a battery module in an embodiment;

[0069] Figure 5 Structural block diagram of a battery fault detection device in an embodiment;

[0070] Figure 6 Internal structural diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0071] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0072] In an embodiment, as shown in Figure 1 A battery fault detection method is provided, and the embodiment is exemplified by the method applied to a terminal. It should be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and can be realized through the interaction of the terminal and the server. In the embodiment, the method includes the following steps 102 to 114.

[0073] Step 102, obtaining related data of a battery module; the related data includes the voltage and current of each single battery in the battery module.

[0074] The battery module is a unit composed of a plurality of single batteries combined in series or in parallel.

[0075] Specifically, the terminal can collect the voltage and current data of each single battery in the battery module through a high-frequency acquisition instrument. The high-frequency acquisition instrument is an electronic measuring instrument mainly used for data acquisition.

[0076] Step 104, calculating the impedance and impedance average of each single battery in the battery module in a preset frequency range according to the related data.

[0077] The impedance plays a hindering role on the current in the circuit, and is a complex number composed of real and imaginary parts.

[0078] In some embodiments, the terminal processes the collected voltage and current data of the single battery by using wavelet transform to obtain the voltage and current waveforms of each single battery in time-frequency domain. The impedance of each single battery at the moment is obtained by dividing the time-frequency data of the voltage of each single battery by the time-frequency data of the current. The impedance average of the single battery in a preset frequency range is obtained by dividing the impedance collected at each frequency collection point in each frequency range by the number of collection points.

[0079] In step 106, the correlation coefficient of each single battery in different preset frequency ranges is calculated according to the impedance and the impedance average.

[0080] The correlation coefficient is Pearson correlation coefficient, which is a statistical index for measuring the degree of linear correlation between two variables.

[0081] In some embodiments, for each single battery and each preset frequency range, the terminal calculates the impedance standard deviation of each single battery in each preset frequency range, and calculates the impedance covariance between each single battery and each remaining single battery in each preset frequency range. According to the impedance standard deviation of the single battery and the impedance covariance corresponding to the single battery, the correlation coefficient of each single battery in each preset frequency range is calculated.

[0082] The correlation coefficient of a single battery in a preset frequency range is the average of all correlation coefficients calculated between the single battery and each remaining single battery in the preset frequency range.

[0083] In step 108, the difference between the average of the correlation coefficients of multiple single batteries in different preset frequency ranges and the correlation coefficient of each single battery is calculated, and the difference is sorted to obtain the difference ranking value of each single battery in different preset frequency ranges.

[0084] The difference between the average of the correlation coefficients of multiple single batteries and the correlation coefficient of each single battery is DTW (Dynamic Time Warping) distance, which is used to measure the similarity between the two.

[0085] In some embodiments, the terminal calculates the average of the correlation coefficients of each single battery in the battery module in each preset frequency range, and the specific calculation formula is shown in formula (1). Then, the DTW distance between the correlation coefficient of each single battery and the average of the correlation coefficients is calculated, and the specific calculation formula is shown in formula (2). The DTW distance of each single battery in each preset frequency range is sorted to obtain the difference ranking value of each single battery in different preset frequency ranges.

[0086]

[0087]

[0088] wherein, is the correlation coefficient of the i-th single battery under each preset frequency band, is the number of single batteries in the battery module, and t is a frequency collection point in the preset frequency band.

[0089] In step 110, the standard deviation and the mean of the difference ranking values of each single battery under different preset frequency bands are calculated, and the score preset threshold of the single battery is determined according to the standard deviation and the mean.

[0090] In some embodiments, the terminal calculates the standard deviation and the mean of the difference ranking values of the single batteries according to the difference ranking values of the single batteries under different preset frequency bands. Then, the score preset threshold of each single battery is determined according to the difference ranking value of each single battery.

[0091] In step 112, the single battery is scored according to the difference ranking value of the single battery under the entire preset frequency band and the score preset threshold, to obtain the score of the single battery.

[0092] The entire preset frequency band includes all preset frequency bands.

[0093] In some embodiments, the terminal re-calculates the difference between the mean of the correlation coefficients of the plurality of single batteries under the entire preset frequency band and the correlation coefficient of each single battery under the entire preset frequency band, and reorders the difference, to obtain a new difference ranking value of each single battery under the entire preset frequency band. The single battery is scored according to the new difference ranking value of each single battery and the score preset threshold corresponding to the single battery, to obtain the score of each single battery.

[0094] In step 114, the single battery with a fault is screened out according to the score of each single battery.

[0095] In some embodiments, the terminal determines the reachable distance of each data point by taking the score of each single battery as a data point. The local reachable density of each data point is calculated according to the reachable distance of the remaining data points in the range formed by the local reachable density of each data point. The local outlier factor of each data point is calculated according to the local reachable density of the remaining data points in the range formed by the local reachable density of each data point and the reachable distance of the data point.

[0096] Further, the terminal judges whether the local outlier factor of each data point is much larger than the preset value. If the local outlier factor of the data point is close to the preset value, the monomer battery represented by the data point is a normal battery; if the local outlier factor of the data point is much larger than the preset value, the monomer battery represented by the data point is a faulty monomer battery.

[0097] In the above battery fault detection method, the voltage and current of each monomer battery in the battery module are obtained, and the impedance of each monomer battery is calculated according to the voltage and current of each monomer battery. The impedance average is calculated according to the impedance of each monomer battery. The correlation coefficient of each monomer battery under different preset frequency bands is calculated according to the impedance of the monomer battery and the impedance average. According to the correlation coefficient, the difference between the correlation coefficient of each monomer battery under different preset frequency bands and the average of the correlation coefficients of all monomer batteries under the corresponding frequency band is calculated. The difference values of the monomer batteries under different preset frequency bands are sorted to obtain the difference ranking values of the monomer batteries under different preset frequency bands. According to the difference ranking values of the monomer batteries, the standard deviation and the average of the ranking values under different preset frequency bands are calculated, and then the scoring preset threshold of the monomer battery is obtained according to the standard deviation and the average of the ranking values. According to the difference ranking values of the monomer battery in the whole preset frequency band and the scoring preset threshold, the monomer battery is scored, and according to the score of each monomer battery, the faulty monomer battery in the battery module is screened out. Therefore, the present application can process different monomer batteries in the battery module to obtain the score of each monomer battery, quickly and accurately find out the monomer battery in the battery module which is different from other monomer batteries in change trend, i.e. the faulty monomer battery, and can effectively reduce the resource waste caused by checking the monomer batteries one by one in the battery module fault detection process.

[0098] In some exemplary embodiments, according to the relevant data, the impedance and impedance average of each monomer battery in the battery module under the preset frequency band are calculated, including: based on wavelet transform, the voltage and current of each monomer battery are represented by waveforms in the time-frequency domain; the time-frequency data of the voltage and current in the waveform state are compared to obtain the impedance of each monomer battery; and the impedance average of the monomer battery is obtained according to the impedance of each monomer battery.

[0099] In actual implementation, the terminal provides excitation for the battery module through an Arbin (battery test device) device, and collects the voltage and current data of each monomer battery in the battery module by using a high-frequency data collector. The optimal frequency bandwidth and center frequency of the wavelet function are selected by using an optimization algorithm, and the specific expression of the wavelet function is shown in formula (3).

[0100]

[0101] wherein, is the frequency bandwidth, t is the center frequency, a is the frequency point, b is the terminal-defined scaling factor, and b is the wavelet transform point, i.e., the moment when the excitation signal is generated from nothing.

[0102] Specifically, the optimization algorithm is used to select the optimal bandwidth and center frequency of the wavelet function as follows: using sparsity evaluation, the sparsity of the wavelet coefficients can be measured by the Shannon entropy (information entropy) of these wavelet coefficients. The Shannon entropy is calculated under different bandwidths. When the Shannon entropy is the minimum, it indicates that the current parameters are most suitable. The specific expression of Shannon entropy is shown in formula (4).

[0103]

[0104] in, , It is Shannon entropy. It represents the probability of wavelet coefficients; represents the wavelet coefficients at the j-th scale; M represents the total number of wavelet coefficients.

[0105] Furthermore, the terminal via The preset frequency range to be analyzed is obtained. Wavelet transform is performed on the voltage and current data within the preset frequency range to obtain the waveforms of the voltage and current of a single cell. The impedance of a single cell is obtained by comparing the time-frequency data of the voltage with the time-frequency data of the current. The impedance of a single cell is obtained by dividing the impedance collected at each frequency sampling point in the preset frequency range by the number of sampling points. The average impedance of a single cell in the preset frequency range is obtained by dividing the impedance collected at each frequency sampling point in the preset frequency range by the number of sampling points. The specific calculation formula is shown in (5).

[0106]

[0107] in, It is the impedance of the i-th single cell at the j-th frequency sampling point, and n is the number of frequency sampling points in the preset frequency band.

[0108] In the above embodiments, by performing wavelet transformation on the voltage and current data of individual cells in the battery module and representing them in waveform form, the impedance of individual cells is easier to calculate and the changing trend is easier to observe.

[0109] In some example embodiments, the correlation coefficient of each single battery at different preset frequency bands is calculated according to the impedance and the impedance average value, including: for each single battery and each preset frequency band, the impedance covariance between the single battery and each remaining single battery at the preset frequency band and the impedance standard deviation of the single battery are calculated according to the impedance and the impedance average value of the single battery; and the correlation coefficient of the single battery at the preset frequency band is calculated according to the impedance standard deviation of the single battery and the impedance covariance corresponding to the single battery.

[0110] In some embodiments, the terminal calculates the impedance covariance between each single battery and each remaining single battery at each preset frequency band according to the impedance of each single battery at different frequency collection points at each preset frequency band and the impedance average value of each single battery at the preset frequency band, and the specific calculation formula is shown in formula (6).

[0111]

[0112] wherein, is the impedance of the i-th single battery at the j-th frequency collection point, is the impedance of the k-th single battery at the j-th frequency collection point, is the impedance average value of the i-th single battery at the preset frequency band, is the impedance average value of the k-th single battery at the preset frequency band, and n is the number of frequency collection points at the preset frequency band.

[0113] The terminal calculates the impedance standard deviation of each single battery at each preset frequency band according to the impedance of each single battery at different frequency collection points at each preset frequency band and the impedance average value of each single battery at the preset frequency band, and the specific calculation formula is shown in formula (7).

[0114]

[0115] wherein, is the impedance of the i-th single battery at the j-th frequency collection point, is the impedance average value of the i-th single battery at the preset frequency band, and n is the number of frequency collection points at the preset frequency band.

[0116] The terminal calculates the Pearson correlation coefficient between each single battery and each remaining single battery according to the impedance standard deviation of each single battery at the preset frequency band and the impedance covariance between the single battery and each remaining single battery, and the specific calculation formula is shown in formula (8). The average value of all Pearson correlation coefficients of the single battery at the preset frequency band is the Pearson correlation coefficient of the single battery.

[0117]

[0118] In the above embodiment, the terminal intuitively shows the correlation of each single battery in the battery module through the Pearson correlation coefficient, so that subsequent analysis is more convenient.

[0119] In some example embodiments, the preset threshold of the score of the single battery is determined according to the standard deviation and the mean value, including: adding the preset multiple of the standard deviation to the mean value as the upper limit of the preset threshold of the score; subtracting the preset multiple of the standard deviation from the mean value as the lower limit of the preset threshold of the score.

[0120] In actual implementation, the terminal adds the mean value of the difference ranking value of each single battery to the standard deviation of the single battery by a preset multiple as the upper limit of the preset threshold of the score of the single battery; subtracts the mean value of the difference ranking value of each single battery from the standard deviation of the single battery by a preset multiple as the lower limit of the preset threshold of the score of the single battery.

[0121] The calculation formula of the mean value is shown in (9), and the calculation formula of the standard deviation is shown in (10).

[0122]

[0123]

[0124] Wherein, is the difference ranking value of the i th single battery in the preset frequency range, and n is the number of single batteries in the battery module.

[0125] In the above embodiment, by setting the preset threshold of the score, it can be quickly identified which single battery deviates from the normal level.

[0126] In some example embodiments, the single battery is scored according to the difference ranking value of the single battery in the entire preset frequency range and the preset threshold of the score, to obtain the score of the single battery, including: if the difference ranking value of the single battery in the entire preset frequency range exceeds the preset threshold of the score, calculating the difference between the difference ranking value and the upper and lower limits of the preset threshold of the score, and adding one to the smallest difference as the score of the single battery; if the difference ranking value of the single battery in the entire preset frequency range does not exceed the preset threshold of the score, the score of the single battery is set to zero.

[0127] In actual implementation, the terminal will judge the relationship between the difference ranking value of each single battery in the entire preset frequency range and the preset threshold of the score of the battery, and score each single battery.

[0128] Specifically, if the difference ranking value of the single battery in the entire preset frequency band exceeds the score preset threshold, the difference between the difference ranking value and the upper and lower limits of the score preset threshold is calculated, and the minimum difference plus one is taken as the score of the single battery. The specific score calculation formula is shown in formula (11).

[0129]

[0130] wherein, is the upper limit of the score preset threshold, is the lower limit of the preset score threshold, is the mean value corresponding to the single battery, is the standard deviation corresponding to the single battery.

[0131] If the difference ranking value of the single battery in the entire preset frequency band does not exceed the score preset threshold, the score of the single battery is set to zero.

[0132] In the above embodiment, by scoring the deviation degree of each single battery, the specific situation of each single battery is quantified, so that the subsequent data processing is simpler.

[0133] In some exemplary embodiments, according to the score of each single battery, the single battery with fault is screened out, including: taking the score of each single battery as a data point, determining the radius and reachable distance of each data point; for each data point, according to the reachable distance of the remaining data points in the range formed by the radius of the data point, the local reachable density of the data point is calculated; according to the local reachable density of the data point and the local reachable density of the remaining data points in the range formed by the radius of the data point, the local outlier factor of each data point is calculated; if the local outlier factor of the data point is greater than a preset value, the single battery represented by the data point is a single battery with fault.

[0134] In actual implementation, the terminal will take the score of each single battery as a data point. Given a data point k, the distance from the data point to all other data points is calculated, and the P nearest data points to the data point are found. Let P be a parameter, representing the number of selected nearest neighbor data points. For each data point k, the radius of the data point is the distance of the Pth nearest neighbor data point.

[0135] For each data point q corresponding to the circular range with a radius R belonging to the data point k, the reachable distance of the data point k to the data point q is defined. The specific calculation formula is shown in formula (12).

[0136]

[0137] wherein, represents the Pth nearest neighbor data point of is the distance from data point k to data point q, is the distance from data point q to the Pth nearest neighbor data point of data point k.

[0138] For each data point k, the calculation formula of the local reachable density is shown as (13).

[0139]

[0140] wherein, is the set of all neighboring data points of data point k within its radius.

[0141] Further, by the local reachable density of data point k and the local reachable density of the neighboring data point of data point k, the local outlier factor of data point k is calculated, and the specific calculation formula is shown as (14).

[0142]

[0143] wherein, is the local reachable density of the neighboring data point q of data point k, is the local reachable density of data point k, is the set of all neighboring data points of data point k within its radius.

[0144] Further, if the local outlier factor of data point k is much larger than the preset value, indicating that its density is much lower than that of its neighboring data points, then the monomer battery represented by the data point k is a faulty monomer battery; if the local outlier factor of data point k is close to the preset value, then the monomer battery represented by the data point k is a normal monomer battery.

[0145] In the above embodiment, by calculating the local outlier factor of each monomer battery, the monomer battery that appears to be faulty can be directly determined, making the detection process more simple and accurate.

[0146] To further illustrate the battery fault detection method in the present application, an example is given below, and the specific flow chart is shown as 2. Illustratively, the present application is described by a specific lithium battery fault detection method.

[0147] Firstly, the terminal will provide excitation for the battery module through the Arbin (battery test test equipment) device, the excitation is a square wave with amplitude 0.1C, period 15s, duty cycle 1 / 3, and the voltage and current data of each single battery in the battery module are collected by a high-frequency data collector. The optimal frequency bandwidth and center frequency of the wavelet function are selected by an optimization algorithm. The specific optimization algorithm is: using sparsity evaluation, the sparsity of wavelet coefficients can be measured by the Shannon entropy (information entropy) of these wavelet coefficients, and when the Shannon entropy is the smallest, the current parameters are the most appropriate. The specific expression of Shannon entropy is shown in formula (4). The specific expression of wavelet function is shown in formula (3).

[0148] Further, the terminal will Get the preset frequency range that needs to be analyzed, that is, the preset frequency band. The voltage and current data in the preset frequency band are wavelet transformed to obtain the voltage and current waveform of the single battery. The voltage time-frequency data and current time-frequency data of each single battery are compared to obtain the impedance of the single battery, and the specific impedance is shown in formula (2). Figure 3 The impedance of each frequency collection point of each single battery in the preset frequency band is divided by the number of collection points to obtain the impedance mean value of the single battery in the preset frequency band, and the specific calculation formula is shown in formula (5).

[0149] The terminal will calculate the impedance covariance between each single battery and the remaining single battery in each preset frequency band according to the impedance of each single battery at different frequency collection points in each preset frequency band and the impedance mean value of each single battery in the preset frequency band, and the specific calculation formula is shown in formula (6). According to the impedance of each single battery at different frequency collection points in each preset frequency band and the impedance mean value of each single battery in the preset frequency band, the impedance standard deviation of each single battery in the preset frequency band is calculated, and the specific calculation formula is shown in formula (7).

[0150] According to the impedance standard deviation of each single battery in the preset frequency band and the impedance covariance between the single battery and the remaining single battery, the Pearson correlation coefficient between the single battery and the remaining single battery is calculated. The specific calculation formula is shown in formula (8). The average value of all Pearson correlation coefficients of the single battery in the preset frequency band is the Pearson correlation coefficient of the single battery.

[0151] The terminal calculates the average of the correlation coefficients of each single battery in the battery module under each preset frequency band, and the specific calculation formula is shown as (1). Then, the DTW distance between the correlation coefficient of each single battery and the average of the correlation coefficients is calculated, and the specific calculation formula is shown as (2). The DTW distances of each single battery under each preset frequency band are sorted to obtain the difference ranking value of each single battery under different preset frequency bands.

[0152] The terminal adds the standard deviation of the single battery by a preset multiple to the average of the difference ranking value of each single battery as the upper limit of the preset threshold of the score of the single battery, and subtracts the standard deviation of the single battery by a preset multiple from the average of the difference ranking value of each single battery as the lower limit of the preset threshold of the score of the single battery. The calculation formula of the average is shown as (9), and the calculation formula of the standard deviation is shown as (10).

[0153] The terminal judges the relationship between the difference ranking value of each single battery under the entire preset frequency band and the preset threshold of the score of the single battery, and scores each single battery.

[0154] Specifically, if the difference ranking value of the single battery under the entire preset frequency band exceeds the preset threshold of the score, the difference between the difference ranking value and the upper limit and the lower limit of the preset threshold of the score is calculated, and the minimum difference plus one is taken as the score of the single battery. The specific calculation formula of the score is shown as (11). If the difference ranking value of the single battery under the entire preset frequency band does not exceed the preset threshold of the score, the score of the single battery is set to zero.

[0155] The terminal takes the score of each single battery as a data point. Given a data point k, the distance from the data point to all other data points is calculated, and the P nearest data points to the data point are found. P is a parameter representing the number of selected nearest neighbor data points. For each data point k, the radius of the data point is the distance of the Pth nearest neighbor data point.

[0156] For each data point q within the circular range with a radius R corresponding to the data point k, the reachable distance of the data point k to the data point q is defined, and the specific calculation formula is shown as (12). For each data point k, the calculation formula of the local reachable density is shown as (13). Further, the local outlier factor of the data point k is calculated by the local reachable density of the data point k and the local reachable density of the neighbor data point of the data point k, and the specific calculation formula is shown as (14).

[0157] Further, if the local outlier factor of the data point k is much greater than 1, indicating that the density of the data point k is much lower than the density of its adjacent data points, the monomer battery represented by the data point k is a faulty monomer battery; if the local outlier factor of the data point k is close to 1, it means that the monomer battery represented by the data point k is a normal monomer battery, and the local outlier factor distribution diagram of the specific monomer battery is as shown in Figure 4 .

[0158] The application provides a battery fault detection method. By comparing the impedance changes of each monomer battery in the battery module during the charging process, the abnormality of the monomer battery can be diagnosed by monitoring the differences in the local outlier factors of the monomer batteries. Compared with the prior art, the data required by the fault detection technology of the application is relatively simple, and the detection is efficient, thereby reducing the consumption of resources in the detection process.

[0159] The application provides a battery fault detection method. The application is suitable for various battery types and different working conditions, and these advantages are particularly useful for electric vehicles, so that the faulty monomer battery in the battery module can be quickly and accurately detected.

[0160] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0161] Based on the same inventive concept, the application also provides a battery fault detection device for implementing the above-mentioned battery fault detection method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more battery fault detection device embodiments provided below can refer to the limitations of the battery fault detection method described above, and will not be repeated here.

[0162] In one exemplary embodiment, as shown in Figure 5 , a battery fault detection device is provided, comprising: an acquisition module 501, a calculation module 502, a scoring module 503 and a screening module 504, wherein:

[0163] An acquisition module is configured to acquire relevant data of a battery module, wherein the relevant data comprises voltage and current of each single battery in the battery module.

[0164] A calculation module is configured to calculate impedance and impedance average of each single battery in the battery module in a preset frequency range according to the relevant data.

[0165] The calculation module is further configured to calculate a correlation coefficient of each single battery in different preset frequency ranges according to the impedance and the impedance average.

[0166] The calculation module is further configured to calculate a difference between the correlation coefficient of each single battery and an average of correlation coefficients of multiple single batteries in different preset frequency ranges, and sort the difference to obtain a difference ranking value of each single battery in the different preset frequency ranges.

[0167] The calculation module is further configured to calculate a standard deviation and an average of the difference ranking value of each single battery in the different preset frequency ranges, and determine a score preset threshold of the single battery according to the standard deviation and the average.

[0168] A scoring module is configured to score the single battery according to the difference ranking value of the single battery in the entire preset frequency range and the score preset threshold, to obtain a score of the single battery.

[0169] A screening module is configured to screen out a single battery with a fault according to the score of each single battery.

[0170] In some embodiments, the calculation module is further configured to represent voltage and current of each single battery in a time-frequency domain using a waveform based on wavelet transform; compare time-frequency data of the voltage and the current in the waveform state to obtain impedance of each single battery; and obtain an impedance average of the single battery according to the impedance of each single battery.

[0171] In some embodiments, the calculation module is further configured to, for each single battery and each preset frequency range, calculate impedance covariance between the single battery and each remaining single battery in the preset frequency range and an impedance standard deviation of the single battery according to the impedance of the single battery and the impedance average; and calculate a correlation coefficient of the single battery in the preset frequency range according to the impedance standard deviation of the single battery and the impedance covariance corresponding to the single battery.

[0172] In some embodiments, the device further comprises a determination module configured to add a preset multiple of the standard deviation to the average as an upper limit of the score preset threshold, and subtract a preset multiple of the standard deviation from the average as a lower limit of the score preset threshold.

[0173] In some embodiments, the scoring module is further configured to, if the difference value ranking of the single battery in the entire preset frequency range exceeds a preset threshold value, calculate a gap between the difference value ranking and an upper limit and a lower limit of the preset threshold value, and add one to the smallest gap to obtain a score of the single battery; and if the difference value ranking of the single battery in the entire preset frequency range does not exceed the preset threshold value, set the score of the single battery to zero.

[0174] In some embodiments, the screening module is further configured to determine a radius and a reachable distance of each data point; calculate a local reachable density of each data point according to the reachable distances of the remaining data points in a range formed by the radius of the data point; calculate a local outlier factor of each data point according to the local reachable density of the data point and the local reachable densities of the remaining data points in the range formed by the radius of the data point; and if the local outlier factor of the data point is greater than a preset value, the single battery represented by the data point is a faulty single battery.

[0175] The modules in the battery fault detection device can be implemented by software, hardware, or a combination thereof. The modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in the computer device in software form, so as to be called and executed by the processor.

[0176] In an exemplary embodiment, a computer device is provided, which can be a terminal. An internal structure diagram of the computer device can be as shown in FIG. 1. Figure 6The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus. The communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to perform wired or wireless communication with external terminals. The wireless communication can be achieved through WIFI, mobile cellular network, near field communication (NFC) or other technologies. The computer program is executed by the processor to implement a battery fault detection method. The display unit of the computer device is configured to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0177] Those skilled in the art can understand that Figure 6 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0178] In one exemplary embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the following steps:

[0179] Obtaining related data of the battery module; the related data includes voltage and current of each single battery in the battery module;

[0180] According to the related data, calculating impedance and impedance average of each single battery in the battery module in a preset frequency range;

[0181] According to the impedance and the impedance average, calculating a correlation coefficient of each single battery in different preset frequency ranges;

[0182] calculating a difference between a mean value of the correlation coefficients of the plurality of single batteries at different preset frequency bands and the correlation coefficient of each single battery, and ranking the difference to obtain a difference ranking value of each single battery at the different preset frequency bands;

[0183] calculating a standard deviation and a mean value of the difference ranking values of each single battery at the different preset frequency bands, and determining a score preset threshold of the single battery according to the standard deviation and the mean value;

[0184] scoring the single battery according to the difference ranking value of the single battery at the entire preset frequency band and the score preset threshold, to obtain a score of the single battery;

[0185] screening a single battery with a fault according to the score of each single battery.

[0186] In one embodiment, a computer readable storage medium is provided, and a computer program is stored on the computer readable storage medium. The computer program is executed by a processor to implement the following steps:

[0187] obtaining correlation data of a battery module; the correlation data includes voltage and current of each single battery in the battery module;

[0188] calculating impedance and impedance mean value of each single battery in the battery module at a preset frequency band according to the correlation data;

[0189] calculating a correlation coefficient of each single battery at different preset frequency bands according to the impedance and the impedance mean value;

[0190] calculating a difference between a mean value of the correlation coefficients of the plurality of single batteries at different preset frequency bands and the correlation coefficient of each single battery, and ranking the difference to obtain a difference ranking value of each single battery at the different preset frequency bands;

[0191] calculating a standard deviation and a mean value of the difference ranking values of each single battery at the different preset frequency bands, and determining a score preset threshold of the single battery according to the standard deviation and the mean value;

[0192] scoring the single battery according to the difference ranking value of the single battery at the entire preset frequency band and the score preset threshold, to obtain a score of the single battery;

[0193] screening a single battery with a fault according to the score of each single battery.

[0194] In one embodiment, a computer program product is provided, and the computer program product includes a computer program. The computer program is executed by a processor to implement the following steps:

[0195] acquiring relevant data of the battery module; the relevant data includes voltage and current of each single battery in the battery module;

[0196] calculating impedance and impedance average of each single battery in the battery module in a preset frequency range according to the relevant data;

[0197] calculating correlation coefficient of each single battery in different preset frequency ranges according to the impedance and the impedance average;

[0198] calculating difference between correlation coefficient of each single battery and average value of correlation coefficients of multiple single batteries in different preset frequency ranges, and sorting the difference to obtain difference ranking value of each single battery in the different preset frequency ranges;

[0199] calculating standard deviation and average value of difference ranking value of each single battery in the different preset frequency ranges, and determining score preset threshold of the single battery according to the standard deviation and the average value;

[0200] scoring the single battery according to the difference ranking value of the single battery in the entire preset frequency range and the score preset threshold, to obtain score of the single battery;

[0201] screening out single battery with fault according to the score of each single battery.

[0202] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant regulations.

[0203] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0204] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist, they should be considered as the scope of the present application.

[0205] The above-described embodiments are merely illustrative of several embodiments of the present application, which are described in more detail and in a specific manner, but should not be construed as limiting the scope of the patent of the present application. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A battery fault detection method, characterized in that, The method includes: Obtain relevant data about the battery module; the relevant data includes the voltage and current of each individual battery cell in the battery module; Based on the relevant data, calculate the impedance and average impedance of each individual cell in the battery module at a preset frequency range; For each individual cell and each preset frequency band, based on the impedance and average impedance of the individual cell, calculate the impedance covariance between the individual cell and each of the remaining individual cells in the preset frequency band, as well as the impedance standard deviation of the individual cell. The correlation coefficient of the individual battery is calculated in the preset frequency range based on the impedance standard deviation and the impedance covariance of the individual battery. The difference between the mean of the correlation coefficients of multiple individual cells under different preset frequency bands and the correlation coefficient of each individual cell is calculated, and the difference is sorted to obtain the ranking value of the difference of each individual cell under the different preset frequency bands. Calculate the standard deviation and mean of the difference ranking values ​​of each individual battery cell under different preset frequency bands, and determine the preset scoring threshold of the individual battery cell based on the standard deviation and mean. If the difference ranking value of the single battery cell in the entire preset frequency range exceeds the preset scoring threshold, then the difference between the difference ranking value and the upper and lower limits of the preset scoring threshold are calculated, and the smallest difference is added by one as the score of the single battery cell. If the difference ranking value of the individual battery does not exceed the preset scoring threshold throughout the preset frequency range, then the score of the individual battery is set to zero. Based on the rating of each individual cell, faulty individual cells are identified.

2. The method according to claim 1, characterized in that, The step of calculating the impedance and average impedance of each individual cell in the battery module at a preset frequency range based on the relevant data includes: Based on wavelet transform, the voltage and current of each individual battery cell are represented by waveforms in the time-frequency domain; The impedance of each individual cell is obtained by comparing the time-frequency data of the voltage and current in the waveform state. The average impedance of each individual cell is obtained based on its impedance.

3. The method according to claim 1, characterized in that, The step of determining the preset scoring threshold for the individual battery cell based on the standard deviation and mean includes: The standard deviation, which is the mean plus a preset multiple, is used as the upper limit of the preset scoring threshold; The standard deviation, which is the mean minus a preset multiple, is used as the lower limit of the preset scoring threshold.

4. The method according to claim 1, characterized in that, The step of filtering out faulty individual cells based on the score of each individual cell includes: The score of each individual battery cell is used as a data point to determine the radius and reachability of each data point; For each data point, the local reachability density of the data point is calculated based on the reachability distance of the remaining data points within the range formed by the radius of the data point. Calculate the local outlier factor for each data point based on the local reachability density of the data point and the local reachability density of the remaining data points within the range formed by the radius of the data point. If the local outlier factor of the data point is greater than a preset value, then the single cell represented by the data point is a faulty single cell.

5. A battery fault detection device, characterized in that, The device includes: The acquisition module is used to acquire relevant data of the battery module; the relevant data includes the voltage and current of each individual cell in the battery module; The calculation module is used to calculate the impedance and average impedance of each individual cell in the battery module at a preset frequency range based on the relevant data. The calculation module is also used to calculate, for each individual cell and each preset frequency band, the impedance covariance between the individual cell and each remaining individual cell in the preset frequency band, and the impedance standard deviation of the individual cell, based on the impedance and the impedance mean of the individual cell; and to calculate the correlation coefficient of the individual cell in the preset frequency band based on the impedance standard deviation of the individual cell and the impedance covariance corresponding to the individual cell. The calculation module is also used to calculate the difference between the mean value of the correlation coefficients of multiple individual batteries under different preset frequency bands and the correlation coefficient of each individual battery, and to sort the difference values ​​to obtain the ranking value of the difference values ​​of each individual battery under the different preset frequency bands. The calculation module is also used to calculate the standard deviation and mean of the difference ranking values ​​of each individual battery cell under different preset frequency bands, and to determine the preset scoring threshold of the individual battery cell based on the standard deviation and mean. The scoring module is used to calculate the difference between the difference ranking value of the individual battery and the upper and lower limits of the preset scoring threshold respectively if the difference ranking value of the individual battery in the entire preset frequency range exceeds the preset scoring threshold, and add one to the smallest difference as the score of the individual battery; if the difference ranking value of the individual battery in the entire preset frequency range does not exceed the preset scoring threshold, the score of the individual battery is set to zero. The filtering module is used to filter out faulty individual cells based on the score of each individual cell.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images