Battery Fault Prediction Method, Device, Equipment, Storage Medium and Program Product

Abstract

The present application relates to a battery fault prediction method, device, equipment, storage medium and program product. The method comprises: obtaining vibration signal data of a battery collected by a sensor provided on the battery, determining a moving average of similarities and differences corresponding to the vibration signal data according to the vibration signal data, then determining a target time for a battery failure according to the moving average of similarities and differences, and finally determining a target threshold corresponding to the battery at the target time, and determining a fault prediction result of the battery to be tested according to the target threshold. In the embodiment of the present application, the target time for a battery failure is determined according to the moving average of similarities and differences, and the target threshold corresponding to the battery at the target time is determined, which improves the accuracy of the target threshold, thereby being able to improve the accuracy of the fault prediction result of the battery to be tested obtained based on the target threshold.

Description

Technical Field

[0001] The present application relates to the field of lithium battery technology, and in particular to a battery failure prediction method, device, equipment, storage medium and program product. Background Art

[0002] In energy storage systems, overcharge and over-discharge failures of lithium batteries are the most frequent types of failures. When a lithium battery overcharges or over-discharges, it will cause thermal runaway of the lithium battery, leading to major safety accidents such as fire and explosion. Therefore, it is necessary to detect whether a lithium battery overcharges or over-discharges in order to reduce the probability of overcharge or over-discharge failures.

[0003] At present, the target threshold for overcharge or over-discharge failure is usually determined by analyzing the voltage, current, temperature, gas characteristics, etc. of the lithium battery, and the fault prediction result of the lithium battery is determined based on the target threshold. However, since the target threshold determined based on the voltage, current, temperature, gas characteristics, etc. of the lithium battery has low accuracy, the fault prediction result of the lithium battery obtained based on the target threshold is low in accuracy. Summary of the invention

[0004] Based on this, it is necessary to provide a battery fault prediction method, device, equipment, storage medium and program product that can improve the accuracy of lithium battery fault prediction results in response to the above technical problems.

[0005] In a first aspect, the present application provides a battery failure prediction method. The method comprises:

[0006] Obtaining vibration signal data of the battery collected by a sensor disposed on the battery;

[0007] Determine, according to the vibration signal data, a similarity-difference moving average corresponding to the vibration signal data;

[0008] Determine the target time for the battery to fail based on the similarity-difference moving average;

[0009] A target threshold corresponding to the battery at the target time is determined, and a fault prediction result of the battery to be tested is determined according to the target threshold.

[0010] In one embodiment, determining the target time of the battery failure according to the similarity-difference moving average includes:

[0011] The target time is determined according to the time corresponding to the intersection of the deviation value curve and the deviation mean value curve in the similarity-difference moving average line.

[0012] In one embodiment, determining the similarity-difference moving average corresponding to the vibration signal data according to the vibration signal data includes:

[0013] Build time window;

[0014] For each time window, the similarity-difference moving average is determined according to the vibration signal data of the time window.

[0015] In one embodiment, determining the similarity-difference moving average according to the vibration signal data in the time window includes:

[0016] Determine an exponential moving average based on the vibration signal data in the time window;

[0017] Determine the deviation value corresponding to the sliding average of the index;

[0018] Determine a deviation mean value based on the deviation value;

[0019] The similarity-difference moving average is determined according to the deviation value and the deviation mean.

[0020] In one embodiment, determining the similarity-difference moving average according to the deviation value and the deviation mean value includes:

[0021] Determine the deviation value curve according to each deviation value;

[0022] Determine the deviation mean value curve according to each deviation mean value;

[0023] The similarity-difference moving average line is determined according to the deviation value curve and the deviation mean value curve.

[0024] In one embodiment, the method further comprises:

[0025] The warning information is generated according to the fault prediction result; the warning information is used to prompt that when the parameter of the battery to be tested reaches the target threshold value, the battery to be tested will have an overcharge fault or an over-discharge fault.

[0026] In a second aspect, the present application also provides a battery failure prediction device. The device comprises:

[0027] An acquisition module, used to acquire vibration signal data of the battery collected by a sensor provided on the battery;

[0028] A first determination module is used to determine a similarity and difference moving average corresponding to the vibration signal data according to the vibration signal data;

[0029] A second determination module is used to determine a target time when the battery fails according to the similarity-difference moving average;

[0030] The third determination module is used to determine a target threshold value corresponding to the battery at the target time, and determine a fault prediction result of the battery to be tested according to the target threshold value.

[0031] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.

[0032] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above methods when executed by a processor.

[0033] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of any of the above methods when executed by a processor.

[0034] The above-mentioned battery fault prediction method, device, equipment, storage medium and program product obtain the vibration signal data of the battery collected by the sensor set on the battery, determine the similarities and differences corresponding to the vibration signal data according to the vibration signal data, and then determine the target time of battery failure according to the similarities and differences moving average, and finally determine the target threshold corresponding to the battery at the target time, and determine the fault prediction result of the battery to be tested according to the target threshold. In the embodiment of the present application, the target time of battery failure is determined according to the similarities and differences moving average, and the target threshold corresponding to the battery at the target time is determined, which improves the accuracy of the target threshold, thereby improving the accuracy of the fault prediction result of the battery to be tested obtained based on the target threshold. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 An application environment diagram of a battery failure prediction method provided in an embodiment of the present application;

[0036] Figure 2 It is a flowchart of a battery failure prediction method provided in an embodiment of the present application;

[0037] Figure 3 It is a flow chart of a method for determining a similarity-difference moving average provided in an embodiment of the present application;

[0038] Figure 4 It is a flow chart of another method for determining the similarity and difference moving average provided in an embodiment of the present application;

[0039] Figure 5 It is a flowchart of another method for determining the similarity and difference moving average provided in an embodiment of the present application;

[0040] Figure 6 It is a flow chart of a lithium battery fault prediction method provided in an embodiment of the present application;

[0041] Figure 7 It is a time domain diagram of a lithium battery vibration signal under an overcharge fault experiment provided in an embodiment of the present application;

[0042] Figure 8 It is the MACD graph of the vibration signal of a lithium battery under an overcharge fault experiment provided by an embodiment of the present application;

[0043] Figure 9 It is the time-domain graph of the vibration signal of a lithium battery under an overdischarge fault experiment provided by an embodiment of the present application;

[0044] Figure 10 It is the MACD graph of the vibration signal of a lithium battery under an overdischarge fault experiment provided by an embodiment of the present application;

[0045] Figure 11 It is the structural block diagram of a battery fault prediction device provided by an embodiment of the present application;

[0046] Figure 12 It is the internal structure diagram of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0047] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0048] The battery fault prediction method provided by the embodiment of the present application can be applied to, for example, Figure 1 the application environment shown. Among them, the vibration signal acquisition card 102 communicates with the computer device 103. The vibration signal acquisition card 102 is used to collect vibration signal data on the surface of the battery 101 through a sensor and send the collected vibration signal data to the computer device 103. The battery 101 can be placed in the explosion-proof box 105. The battery measurement system 104 can be used to set the overcharge fault parameters or overdischarge fault parameters of the battery 101. Among them, the computer device 103 can be, but is not limited to, various personal computers, laptop computers, smart phones, and tablet computers.

[0049] In one embodiment, as Figure 2 shown, Figure 2 It is the flowchart of a battery fault prediction method provided by an embodiment of the present application. This method can be applied to Figure 1 the computer device 103 in it. This method includes the following steps:

[0050] S201, obtain the vibration signal data of the battery collected by the sensor set on the battery.

[0051] For example, the sensor may be a vibration acceleration sensor, and the battery may be a lithium battery. The vibration acceleration sensor may be a vibration acceleration sensor with a resolution of 150 μg, a sensitivity of 100 mV / g, and a sampling rate of 51.2 kHz; and the sensor may be attached to the surface of the battery.

[0052] Specifically, the sensor disposed on the battery can collect vibration signal data of the battery, and send the collected vibration signal data to the computer device 103 through the vibration signal acquisition card 102. The computer device 103 can obtain the vibration signal data sent by the vibration signal acquisition card 102.

[0053] S202, determining a similarity-difference moving average corresponding to the vibration signal data according to the vibration signal data.

[0054] Specifically, the Moving Average Convergence Divergence (MACD) is composed of "two lines, two columns and one axis". The two lines are the Differential Value (DIF) curve and the Discrete Exponential Average (DEA) curve, the two columns are the MACD red column and the MACD green column, and the one axis is the 0 axis.

[0055] In one possible implementation, the corresponding short-term EMA and long-term EMA can be determined based on the vibration signal data, and then the DIF curve can be determined based on the short-term EMA and the long-term EMA, and the corresponding DEA can be determined based on the DIF to determine the DEA curve, and the corresponding MACD chart can be determined based on the DIF curve, the DEA curve, the MACD column and the 0 axis.

[0056] In another possible implementation, a time window may be constructed, and for each time window, a corresponding short-term EMA and a long-term EMA may be determined based on the vibration signal data, and then a DIF curve may be determined based on the short-term EMA and the long-term EMA, and a corresponding DEA may be determined based on the DIF to determine a DEA curve, and a corresponding MACD chart may be determined based on the DIF curve, the DEA curve, the MACD column, and the 0 axis.

[0057] S203, determining a target time for battery failure according to the similarity-difference moving average.

[0058] Optionally, the intersection of the DIF curve and the DEA curve in the similarity-difference moving average line, i.e., the "death cross", can be determined, and the moment of the "death cross" is used as the target time of battery failure. Alternatively, the critical time when the MACD red column in the similarity-difference moving average line turns into the MACD green column can be used as the target time of battery failure.

[0059] S204, determining a target threshold corresponding to the battery at the target time, and determining a fault prediction result of the battery to be tested according to the target threshold.

[0060] The target threshold value may be, for example, any one of the parameters of the battery corresponding to the target time, such as voltage, current, temperature, internal resistance, etc.

[0061] Specifically, the parameters corresponding to the battery at the target time are used as the target threshold. If the parameters of the battery to be tested reach the target threshold, the fault prediction result of the battery to be tested is determined to be an overcharge fault or an over-discharge fault of the battery to be tested; if the parameters of the battery to be tested do not reach the target threshold, the fault prediction result of the battery to be tested is determined to be no fault of the battery to be tested.

[0062] Exemplarily, if the target threshold is the voltage value of 2.5V corresponding to the battery at the target time, if the voltage of the battery to be tested reaches 2.5V, the fault prediction result of the battery to be tested is determined to be an overcharge fault or an over-discharge fault in the battery to be tested; if the voltage of the battery to be tested does not reach 2.5V, the fault prediction result of the battery to be tested is determined to be that the battery to be tested has no fault.

[0063] In the embodiment of the present application, the vibration signal data of the battery collected by the sensor set on the battery is obtained, the moving average of the similarities and differences corresponding to the vibration signal data is determined according to the vibration signal data, and then the target time of the battery failure is determined according to the moving average of the similarities and differences, and finally the target threshold corresponding to the battery at the target time is determined, and the fault prediction result of the battery to be tested is determined according to the target threshold. In the embodiment of the present application, the target time of the battery failure is determined according to the moving average of the similarities and differences, and the target threshold corresponding to the battery at the target time is determined, which improves the accuracy of the target threshold, thereby improving the accuracy of the fault prediction result of the battery to be tested obtained based on the target threshold.

[0064] Based on the above embodiment, the above S203, determining the target time of battery failure according to the similarity-difference moving average, can be implemented in the following way:

[0065] Determine the target time based on the time corresponding to the intersection of the deviation value curve and the deviation mean curve in the similarity-difference moving average.

[0066] In a possible implementation, the time corresponding to the intersection of the deviation value curve and the deviation average value curve may be used as the target time.

[0067] In another possible implementation, the middle time corresponding to the intersection of the deviation value curve and the deviation mean value curve in the similarity-difference moving average line may be determined, and the middle time may be corrected, and the corrected middle time may be used as the target time.

[0068] In an embodiment of the present application, the target time is determined according to the time corresponding to the intersection of the deviation value curve and the deviation mean value curve in the similarity-difference moving average line, so that the target threshold can be determined according to the target time, and the fault prediction result of the battery to be tested is determined according to the target threshold, thereby improving the accuracy of the target threshold, and further improving the accuracy of the fault prediction result of the battery to be tested obtained based on the target threshold.

[0069] Reference Figure 3 , Figure 3 1 is a flow chart of a method for determining a moving average of similarities and differences provided in an embodiment of the present application. This embodiment relates to a possible implementation method of how to determine a moving average of similarities and differences corresponding to vibration signal data based on vibration signal data. Based on the above embodiment, the above S202 includes the following steps:

[0070] S301, constructing a time window.

[0071] S302, for each time window, determining a similarity-difference moving average according to the vibration signal data of the time window.

[0072] Specifically, a time window can be constructed, and for each time window, the corresponding short-term EMA and long-term EMA are determined according to the vibration signal data of the time window, and then the DIF curve is determined according to the short-term EMA and the long-term EMA, and the corresponding DEA is determined according to the DIF to determine the DEA curve, and the corresponding MACD chart is determined based on the DIF curve, the DEA curve, the MACD column and the 0 axis, and then the target time of battery failure is determined according to the "death cross" in the MACD chart. If the "death cross" does not appear in the corresponding MACD chart, the similarity and difference moving averages will be re-determined according to the vibration signal data of the next time window.

[0073] In an embodiment of the present application, a time window is constructed, and for each time window, a moving average of similarities and differences is determined based on the vibration signal data of the time window, so that the target time of battery failure can be determined based on the moving average of similarities and differences, thereby improving the accuracy of determining the target time, and further improving the accuracy of the target threshold determined based on the target time, thereby improving the accuracy of the fault prediction results of the battery to be tested.

[0074] Reference Figure 4 , Figure 4 1 is a flow chart of another method for determining a moving average of similarities and differences provided in an embodiment of the present application. This embodiment relates to a possible implementation method of how to determine a moving average of similarities and differences based on vibration signal data in a time window. Based on the above embodiment, the above S302 includes the following steps:

[0075] S401, determining an exponential sliding average according to vibration signal data in a time window.

[0076] Specifically, the short-term exponential moving average EMA and the long-term exponential moving average EMA can be determined according to the vibration signal data of the time window.

[0077] S402. Determine the deviation value corresponding to the exponential moving average.

[0078] Specifically, the difference obtained by subtracting the long-term EMA from the short-term EMA can be used as the deviation value DIF corresponding to the exponential moving average.

[0079] S403. Determine the average deviation value according to the deviation value.

[0080] Specifically, the average deviation value DEA can be determined according to the deviation values DIF of a preset number of time windows.

[0081] S404. Determine the moving average convergence divergence (MACD) according to the deviation value and the average deviation value.

[0082] Optionally, the deviation value curve can be determined according to the deviation value, the average deviation value curve can be determined according to the average deviation value, and the corresponding MACD chart can be determined according to the deviation value curve, the average deviation value curve, the MACD column, and the zero axis. Or, the deviation value can be multiplied by a first preset parameter to obtain a target deviation value, the average deviation value can be multiplied by a second preset parameter to obtain a target average deviation value, then the deviation value curve can be determined according to the target deviation value, the average deviation value curve can be determined according to the target average deviation value, and the corresponding MACD chart can be determined according to the deviation value curve, the average deviation value curve, the MACD column, and the zero axis.

[0083] In the embodiment of the present application, the exponential moving average is determined according to the vibration signal data of the time window, the deviation value corresponding to the exponential moving average is determined, the average deviation value is determined according to the deviation value, and the moving average convergence divergence is determined according to the deviation value and the average deviation value, so that the target time when the battery fails can be determined according to the moving average convergence divergence, the accuracy of determining the target time is improved, and further the accuracy of the target threshold determined according to the target time is improved, and the accuracy of the fault prediction result of the battery to be tested is improved.

[0084] Refer to Figure 5 , Figure 5 is a schematic flowchart of another method for determining the moving average convergence divergence provided by the embodiment of the present application. This embodiment relates to a possible implementation manner of how to determine the moving average convergence divergence according to the deviation value and the average deviation value. On the basis of the above embodiment, the above S404 includes the following steps:

[0085] S501. Determine the deviation value curve according to each deviation value.

[0086] Specifically, the points corresponding to each deviation value can be plotted in the coordinate axis, and the points corresponding to each deviation value are connected to form a deviation value curve.

[0087] S502, determining a deviation mean value curve according to each deviation mean value.

[0088] Specifically, points corresponding to the mean values of the deviations may be plotted on the coordinate axis, and the points corresponding to the mean values of the deviations may be connected to form a mean value curve of the deviations.

[0089] S503, determining a similarity-difference moving average line according to the deviation value curve and the deviation mean value curve.

[0090] Specifically, the corresponding MACD chart can be determined based on the deviation value curve, the deviation mean curve, the MACD column and the 0 axis.

[0091] In an embodiment of the present application, a deviation value curve is determined based on each deviation value, a deviation mean value curve is determined based on each deviation mean value, and a similarity and difference moving average line is determined based on the deviation value curve and the deviation mean value curve, so that the target time of battery failure can be determined based on the similarity and difference moving average line, thereby improving the accuracy of determining the target time, thereby improving the accuracy of the target threshold determined according to the target time, and improving the accuracy of the fault prediction results of the battery to be tested.

[0092] Based on the above embodiment, the method further includes the following steps:

[0093] The warning information is generated according to the fault prediction result; the warning information is used to prompt that the battery to be tested will have an overcharge fault or an over-discharge fault when the parameter of the battery to be tested reaches the target threshold value.

[0094] Specifically, when the parameters of the battery to be tested reach the target threshold, the fault prediction result is determined to be that the battery to be tested will have an overcharge fault or an over-discharge fault, and an early warning message is generated based on the fault prediction result. The early warning message prompts the corresponding staff that the battery to be tested will have an overcharge fault or an over-discharge fault.

[0095] In an embodiment of the present application, warning information is generated based on the fault prediction result to indicate that when the parameters of the battery to be tested reach the target threshold, the battery to be tested will have an overcharge fault or an over-discharge fault, thereby reducing the probability of the battery to be tested having an overcharge fault or an over-discharge fault and improving the safety of the battery operation.

[0096] Reference Figure 6 , Figure 6 : is a flow chart of a lithium battery fault prediction method provided in an embodiment of the present application. The method comprises the following steps:

[0097] S601, obtaining vibration signal data of the battery collected by a sensor disposed on the battery.

[0098] S602, preprocess the vibration signal data of the battery to obtain the preprocessed vibration signal data.

[0099] S603, construct a time window.

[0100] S604, determine the MACD chart corresponding to the vibration signal data of the target time window.

[0101] S605, determine whether a "death cross" appears in the MACD chart.

[0102] If a "death cross" appears in the MACD chart, execute step S606; if a "death cross" does not appear in the MACD chart, use the next time window as the target time window and execute step S604.

[0103] S606, take the time when the "death cross" appears as the target time, determine the target threshold corresponding to the battery at the target time, and determine the fault prediction result of the battery to be tested according to the target threshold.

[0104] S607, generate a warning message according to the fault prediction result.

[0105] For a clearer introduction of the embodiments of the present application, the following is combined Figures 7 - 10 for exemplary illustration.

[0106] Exemplarily, a 50Ah square lithium iron phosphate battery cell (with a charging cut-off voltage of 3.65V and a discharging cut-off voltage of 2.5V) can be used as the above-mentioned battery. Place the square lithium iron phosphate battery cell in an explosion-proof box, and use a battery measurement system to set overcharge and over-discharge faults for the lithium battery cell respectively. The overcharge fault is set to charge at a constant current of 2C to 5V and then switch to constant voltage charging until the current drops to 0.2A. The over-discharge fault is set to discharge at a constant current of 2C to 0V. Use a vibration acceleration sensor (with a resolution and sensitivity of 150μg and 100mV / g respectively, and a sampling rate of 51.2kHz) as the above-mentioned sensor and paste it on the surface of the square lithium iron phosphate battery cell, and connect the vibration acceleration sensor to a data acquisition card to collect the vibration signal data on the surface of the square lithium iron phosphate battery cell.

[0107] In the overcharge experiment, construct a 5s time window, and obtain 256,000 groups of vibration signal data on the surface of the square lithium iron phosphate battery cell, as Figure 7 shown, Figure 7It is a time-domain diagram of the vibration signal of a lithium battery under an overcharge fault experiment provided by an embodiment of the present application. It is known that at the 3rd second, the square lithium iron phosphate battery monomer reaches its charging cut-off voltage value, that is, the first 3 seconds is the normal state, and the state after 3 seconds is the overcharge fault state. By regarding the vibration signal data of 12,800 adjacent sampling points as a period, that is, each 0.25 seconds is a period. Two exponential moving averages (EMA) with different speeds are determined according to the vibration signal data, that is, the above-mentioned short-term EMA and long-term EMA. The positive and negative difference (Differential value, DIF) between the short-term EMA and the long-term EMA is calculated, that is, the above-mentioned deviation value. Then, the average deviation value (Discrete Exponential Average, DEA) is calculated according to the DIF. The deviation value and the average deviation value are plotted on a coordinate with time as the horizontal axis and MACD as the vertical axis, and an auxiliary indicator "MACD column" is introduced to obtain the corresponding MACD diagram, as Figure 8 shown Figure 8 It is a MACD diagram of the vibration signal of a lithium battery under an overcharge fault experiment provided by an embodiment of the present application. It is found according to the direction, absolute position and relative position relationship of the deviation value curve and the average deviation value curve that: under the overcharge fault setting, in the first 2.75002 seconds, the MACD column is positive, that is, the MACD column is red, and the DIF curve is higher than the DEA curve, indicating that the lithium battery is in a continuous normal state. At the moment of 2.75002 seconds, the DIF curve intersects with the DEA curve, that is, a "death cross" appears. After that, the MACD column changes from positive to negative, that is, the MACD column is green. At this time, the square lithium iron phosphate battery monomer has an overcharge fault.

[0108] In the overdischarge experiment, a 5-second time window is constructed, and 256,000 groups of vibration signal data on the surface of the square lithium iron phosphate battery monomer are obtained, as Figure 9 shown Figure 9It is a time-domain diagram of the vibration signal of a lithium battery under an over-discharge fault experiment provided by an embodiment of the present application. It is known that at the 3rd second, the square lithium iron phosphate battery monomer reaches its charging cut-off voltage value, that is, the first 3 seconds are in a normal state, and the state after 3 seconds is an over-discharge fault state. By regarding the vibration signal data of 12,800 adjacent sampling points as a period, that is, each 0.25 seconds is a period. According to the vibration signal data, two exponential moving averages (EMA) with different speeds are determined, that is, the above-mentioned short-term EMA and long-term EMA. According to the short-term EMA and long-term EMA, the positive and negative difference (Differential value, DIF) between the two is calculated, that is, the above-mentioned deviation value. Then, according to the DIF, the discrete exponential average (DEA) is calculated. The deviation value and the discrete exponential average are plotted on a coordinate with time as the horizontal axis and MACD as the vertical axis, and an auxiliary indicator "MACD column" is introduced to obtain the corresponding MACD diagram, as Figure 10 shown Figure 10 It is a MACD diagram of the vibration signal of a lithium battery under an over-discharge fault experiment provided by an embodiment of the present application. According to the direction, absolute position, and relative position relationship of the deviation value curve and the discrete exponential average curve, it is found that: under the over-discharge fault setting, in the first 2.50002 seconds, the MACD column is positive, that is, the MACD column is red, and the DIF curve is higher than the DEA curve, indicating that the lithium battery is in a continuous normal state. At the moment of 2.50002 seconds, the DIF curve intersects with the DEA curve, that is, a "death cross" appears. After that, the MACD column changes from positive to negative, that is, the MACD column is green. At this time, the square lithium iron phosphate battery monomer has an over-discharge fault.

[0109] It should be understood that although the steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps in other steps.

[0110] Based on the same inventive concept, the embodiment of the present application also provides a battery fault prediction device for implementing the battery fault prediction method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more battery fault prediction device embodiments provided below can refer to the limitations of the battery fault prediction method above, and will not be repeated here.

[0111] In one embodiment, Figure 11 As shown, Figure 11 11 is a structural block diagram of a battery fault prediction device provided in an embodiment of the present application. The device 1100 includes:

[0112] The acquisition module 1101 is used to acquire vibration signal data of the battery collected by a sensor provided on the battery.

[0113] The first determining module 1102 is used to determine the similarity-difference moving average corresponding to the vibration signal data according to the vibration signal data.

[0114] The second determination module 1103 is used to determine the target time when the battery fails according to the similarity-difference moving average.

[0115] The third determination module 1104 is used to determine a target threshold corresponding to the battery at a target time, and determine a fault prediction result of the battery to be tested according to the target threshold.

[0116] In one embodiment, the second determination module 1103 is specifically configured to determine the target time according to the time corresponding to the intersection of the deviation value curve and the deviation mean value curve in the similarity-difference moving average line.

[0117] In one embodiment, the second determining module 1103 includes:

[0118] Construction unit, used to construct time windows.

[0119] A determination unit is used to determine the similarity-difference moving average according to the vibration signal data of each time window.

[0120] Determine the similarity-divergence moving average based on the vibration signal data of the window duration.

[0121] In one embodiment, the determining unit includes:

[0122] The first determination subunit is used to determine an exponential sliding average according to the vibration signal data of the time window.

[0123] The second determination subunit is used to determine the deviation value corresponding to the exponential sliding average.

[0124] The third determining subunit is used to determine a deviation mean value according to the deviation value.

[0125] The fourth determining subunit is used to determine the similarity-difference moving average according to the deviation value and the deviation average.

[0126] In one embodiment, the fourth determining subunit is specifically configured to determine a deviation value curve according to each deviation value, determine a deviation mean value curve according to each deviation mean value, and determine a similarity-difference moving average line according to the deviation value curve and the deviation mean value curve.

[0127] In one embodiment, the apparatus 1100 further includes:

[0128] The generation module is used to generate warning information according to the fault prediction result; the warning information is used to prompt that when the parameters of the battery to be tested reach the target threshold, the battery to be tested will have an overcharge fault or an over-discharge fault.

[0129] In one embodiment, a computer device is provided, whose internal structure diagram can be as follows: Figure 12 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. The processor of the computer device is used 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, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. When the computer program is executed by the processor, a battery fault prediction method is implemented.

[0130] Those skilled in the art will understand that Figure 12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0131] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0132] Obtaining vibration signal data of the battery collected by a sensor arranged on the battery;

[0133] Determine the similarity and difference moving average corresponding to the vibration signal data according to the vibration signal data;

[0134] Determine the target time for battery failure based on the similarity-difference moving average;

[0135] Determine a target threshold value corresponding to the battery at the target time, and determine a fault prediction result of the battery to be tested according to the target threshold value.

[0136] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0137] Determine the target time based on the time corresponding to the intersection of the deviation value curve and the deviation mean curve in the similarity-difference moving average.

[0138] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0139] Build time window;

[0140] For each time window, a similarity-difference moving average is determined based on the vibration signal data of the time window.

[0141] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0142] Determine the exponential moving average based on the vibration signal data in the time window;

[0143] Determine the deviation value corresponding to the exponential moving average;

[0144] Determine the mean value of the deviation based on the deviation value;

[0145] Determine the similarity-divergence moving average based on the deviation value and the deviation mean.

[0146] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0147] Determine a deviation value curve according to each deviation value;

[0148] Determine a deviation mean curve according to each deviation mean;

[0149] Determine the similarity-difference moving average based on the deviation value curve and the deviation mean curve.

[0150] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0151] The warning information is generated according to the fault prediction result; the warning information is used to prompt that the battery to be tested will have an overcharge fault or an over-discharge fault when the parameter of the battery to be tested reaches the target threshold value.

[0152] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0153] Obtaining vibration signal data of the battery collected by a sensor arranged on the battery;

[0154] Determine the similarity and difference moving average corresponding to the vibration signal data according to the vibration signal data;

[0155] Determine the target time for battery failure based on the similarity-difference moving average;

[0156] Determine a target threshold value corresponding to the battery at the target time, and determine a fault prediction result of the battery to be tested according to the target threshold value.

[0157] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0158] Determine the target time based on the time corresponding to the intersection of the deviation value curve and the deviation mean curve in the similarity-difference moving average.

[0159] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0160] Build time window;

[0161] For each time window, a similarity-difference moving average is determined based on the vibration signal data of the time window.

[0162] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0163] Determine the exponential moving average based on the vibration signal data in the time window;

[0164] Determine the deviation value corresponding to the exponential moving average;

[0165] Determine the mean value of the deviation based on the deviation value;

[0166] Determine the similarity-divergence moving average based on the deviation value and the deviation mean.

[0167] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0168] Determine a deviation value curve according to each deviation value;

[0169] Determine a deviation mean curve according to each deviation mean;

[0170] Determine the similarity-difference moving average based on the deviation value curve and the deviation mean curve.

[0171] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0172] The warning information is generated according to the fault prediction result; the warning information is used to prompt that the battery to be tested will have an overcharge fault or an over-discharge fault when the parameter of the battery to be tested reaches the target threshold value.

[0173] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0174] Obtaining vibration signal data of the battery collected by a sensor arranged on the battery;

[0175] Determine the similarity and difference moving average corresponding to the vibration signal data according to the vibration signal data;

[0176] Determine the target time for battery failure based on the similarity-difference moving average;

[0177] Determine a target threshold value corresponding to the battery at the target time, and determine a fault prediction result of the battery to be tested according to the target threshold value.

[0178] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0179] Determine the target time based on the time corresponding to the intersection of the deviation value curve and the deviation mean curve in the similarity-difference moving average.

[0180] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0181] Build time window;

[0182] For each time window, a similarity-difference moving average is determined based on the vibration signal data of the time window.

[0183] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0184] Determine the exponential moving average based on the vibration signal data in the time window;

[0185] Determine the deviation value corresponding to the exponential moving average;

[0186] Determine the mean value of the deviation based on the deviation value;

[0187] Determine the similarity-divergence moving average based on the deviation value and the deviation mean.

[0188] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0189] Determine a deviation value curve according to each deviation value;

[0190] Determine a deviation mean curve according to each deviation mean;

[0191] Determine the similarity-difference moving average based on the deviation value curve and the deviation mean curve.

[0192] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0193] Generate a warning message according to the fault prediction result; the warning message is used to prompt that an overcharge fault or an over-discharge fault will occur in the battery under test when the parameters of the battery under test reach the target threshold.

[0194] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the various embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, 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. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the various embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the various embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0195] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0196] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A battery fault prediction method, characterized in that The method comprises: Acquiring vibration signal data of the battery collected by a sensor provided on the battery; Determine, according to the vibration signal data, a moving average of similarities and differences corresponding to the vibration signal data; Determining a target time for the battery to fail based on the similarity-difference moving averages; A target threshold corresponding to the battery at the target time is determined, and a fault prediction result of the battery to be tested is determined according to the target threshold.

2. The method according to claim 1, characterized in that, The step of determining the target time when the battery fails according to the similarity-difference moving average includes: The target time is determined according to the time corresponding to the intersection of the deviation value curve and the deviation mean value curve in the similarity-difference moving average line.

3. The method according to claim 2, wherein The determining, according to the vibration signal data, a similarity-difference moving average corresponding to the vibration signal data comprises: Build time window; For each of the time windows, the similarity-difference moving average is determined according to the vibration signal data of the time window.

4. The method according to claim 3, characterized in that, The determining the similarity-difference moving average according to the vibration signal data in the time window comprises: Determine an exponential sliding average based on the vibration signal data in the time window; Determine the deviation value corresponding to the exponential moving average; Determine a deviation mean value according to the deviation value; The similarity-difference moving average is determined according to the deviation value and the deviation mean value.

5. The method according to claim 4, wherein The determining the similarity-difference moving average according to the deviation value and the deviation mean value comprises: Determine the deviation value curve according to each of the deviation values; Determine the deviation mean value curve according to each of the deviation mean values; The similarity-difference moving average line is determined according to the deviation value curve and the deviation mean value curve.

6. The method according to claim 2, wherein The method further comprises: Generate warning information according to the fault prediction result; the warning information is used to prompt that when the parameter of the battery to be tested reaches the target threshold, the battery to be tested will have an overcharge fault or an over-discharge fault.

7. A battery fault prediction device, characterized in that, The device comprises: An acquisition module, used to acquire vibration signal data of the battery collected by a sensor provided on the battery; A first determination module, configured to determine a similarity-difference moving average corresponding to the vibration signal data according to the vibration signal data; A second determination module is used to determine a target time when the battery fails according to the similarity-difference moving average; The third determination module is used to determine a target threshold value corresponding to the battery at the target time, and determine a fault prediction result of the battery to be tested according to the target threshold value.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images