Battery state intelligent monitoring method and system

Abstract

The invention is suitable for the technical field of battery monitoring, and provides a battery state intelligent monitoring method and system. The method comprises the steps of determining a battery pack and dividing the battery pack into a plurality of battery areas; generating a plurality of optimization monitoring periods; synchronously selected monitoring planning is carried out on the plurality of battery areas; periodically selecting a plurality of target areas for monitoring and acquisition, and respectively performing data fusion processing to generate a plurality of area fusion values; and comparing the plurality of regional fusion values, and selecting an abnormal region to perform state early warning when an abnormal risk exists. The method can divide a plurality of battery areas, plan monitoring planning data, perform monitoring acquisition and data fusion processing on a plurality of target areas, generate a plurality of area fusion values, and perform comparison and judgment on abnormal risks, so as to capture subtle differences of different areas of the battery, and can determine the abnormal risks through comparison of the plurality of area fusion values. And timely risk judgment and early warning are carried out, so that the requirements of accurate, efficient and safe management of the battery can be met.

Description

Technical Field

[0001] The present invention belongs to the technical field of battery monitoring, and in particular relates to a battery status intelligent monitoring method and system. Background Art

[0002] Battery monitoring is the process of analyzing the battery status by measuring battery parameters such as voltage, current, internal resistance, temperature and / or pressure. It is of great significance to ensure the safe, reliable and efficient operation of the battery system, and can provide important data support for the optimal design and maintenance of the battery system.

[0003] Battery monitoring in existing technologies usually adopts an overall monitoring mode, which needs to focus on the entire battery for macro-level status monitoring. It is difficult to capture subtle differences in different areas of the battery, and the alarm mechanism can only be triggered when the battery has obvious abnormalities. It is impossible to achieve timely risk warnings and it is difficult to meet the needs of accurate, efficient and safe battery management. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a battery status intelligent monitoring method and system, aiming to solve the technical problems existing in the prior art mentioned in the background technology.

[0005] The embodiment of the present invention is implemented as follows: A battery status intelligent monitoring method, the method comprising the following steps: Obtaining a three-dimensional annotated model of a battery device, identifying the three-dimensional annotated model, determining a battery pack, and dividing the battery pack into a plurality of battery areas, each of which is composed of a plurality of battery blocks; Identify the current device state of the battery device, match the basic monitoring cycle, and perform targeted optimization of regional monitoring on multiple battery areas to generate multiple corresponding optimized monitoring cycles; According to the plurality of optimized monitoring cycles, a monitoring plan is performed for the plurality of battery areas to be synchronously selected, and monitoring plan data is generated; According to the monitoring planning data, multiple target areas are periodically selected from the multiple battery areas for monitoring and collection, and data fusion processing is performed on each area to generate multiple area fusion values; The fused values ​​of the multiple regions are compared to determine whether there is an abnormal risk, and when there is an abnormal risk, the abnormal region is selected for status warning.

[0006] As a further limitation of the technical solution of the embodiment of the present invention, the step of obtaining a three-dimensional annotation model of a battery device, identifying the three-dimensional annotation model, determining a battery pack, and dividing the battery pack into a plurality of battery areas, each of which is composed of a plurality of battery blocks, specifically includes the following steps: Obtain a 3D annotated model of the battery device; Performing structural recognition on the three-dimensional annotated model to determine the battery pack; Acquiring structural information of the battery pack; The battery pack is divided into a plurality of battery areas according to the structural information, and each battery area is composed of a plurality of battery blocks.

[0007] As a further limitation of the technical solution of the embodiment of the present invention, the identifying the current device state of the battery device, matching the basic monitoring cycle, and optimizing the regional monitoring of the multiple battery areas to generate multiple corresponding optimized monitoring cycles specifically includes the following steps: identifying a current device state of the battery device; According to the current device status, matching the basic monitoring cycle; Performing usage impact analysis on the multiple battery areas and planning multiple impact coefficients; According to the basic monitoring cycle and the multiple influence coefficients, targeted optimization of regional monitoring is performed on the multiple battery regions to generate multiple optimized monitoring cycles.

[0008] As a further limitation of the technical solution of the embodiment of the present invention, the monitoring plan for synchronously selecting the multiple battery areas according to the multiple optimized monitoring cycles and generating the monitoring plan data specifically include the following steps: Comparing a plurality of the optimized monitoring cycles and selecting a unit monitoring cycle; Determine the basic synchronization quantity; Performing a monitoring plan for synchronous selection of the plurality of battery areas according to the basic synchronization quantity, the unit monitoring cycle and the plurality of optimized monitoring cycles, and generating a plurality of synchronization sequence data; A plurality of the synchronous sequence data are comprehensively arranged to generate monitoring planning data.

[0009] As a further limitation of the technical solution of the embodiment of the present invention, the step of periodically selecting multiple target areas from multiple battery areas for monitoring and collection according to the monitoring planning data, and performing data fusion processing respectively to generate multiple area fusion values ​​specifically includes the following steps: According to the monitoring planning data, periodically selecting a plurality of target areas from the plurality of battery areas; Performing battery status monitoring on a plurality of target areas and collecting a plurality of battery status data; Optimizing the plurality of battery status data to generate a plurality of optimized status data; Data fusion processing is performed on the plurality of optimization state data respectively, and regional fusion values ​​corresponding to the plurality of target regions are calculated.

[0010] As a further limitation of the technical solution of the embodiment of the present invention, the calculation formula of the regional fusion value corresponding to the multiple target regions is: ; in, For the i The regional fusion value of the target area, For the i The optimization status data of the target area j state values, each optimization state data has a total of m Status value, For the i The state mean of the optimized state data of the target area.

[0011] As a further limitation of the technical solution of the embodiment of the present invention, the comparing of the fusion values ​​of the multiple regions to determine whether there is an abnormal risk, and when there is an abnormal risk, selecting the abnormal region for status warning specifically includes the following steps: Performing difference calculation on the fusion values ​​of the multiple regions to obtain multiple fusion difference values; Based on a preset standard difference value, comparing the plurality of fused difference values ​​to determine whether there is an abnormal risk; When there is an abnormal risk, selecting an abnormal area from the plurality of battery areas; generating a regional abnormality signal according to the abnormal region; Respond to abnormal signals in the area and issue status warnings.

[0012] A battery status intelligent monitoring system, the system includes a battery area division module, a cycle matching optimization module, a synchronous monitoring planning module, a data fusion processing module and an abnormal risk warning module, wherein: A battery area division module is used to obtain a three-dimensional annotation model of a battery device, identify the three-dimensional annotation model, determine the battery pack, and divide it into multiple battery areas, each of which is composed of multiple battery blocks; A cycle matching optimization module, used to identify the current device state of the battery device, match the basic monitoring cycle, and perform targeted optimization of regional monitoring on multiple battery areas to generate multiple corresponding optimized monitoring cycles; A synchronous monitoring planning module, used to perform synchronously selected monitoring planning for the plurality of battery areas according to the plurality of optimized monitoring cycles, and generate monitoring planning data; A data fusion processing module is used to periodically select multiple target areas from the multiple battery areas for monitoring and collection according to the monitoring planning data, and perform data fusion processing on each area to generate multiple area fusion values; The abnormal risk warning module is used to compare the fused values ​​of the multiple regions to determine whether there is an abnormal risk, and when there is an abnormal risk, select the abnormal region for status warning.

[0013] As a further limitation of the technical solution of the embodiment of the present invention, the data fusion processing module specifically includes: A target area selection unit, configured to periodically select a plurality of target areas from the plurality of battery areas according to the monitoring planning data; A battery status monitoring unit, used to monitor the battery status of the plurality of target areas and collect a plurality of battery status data; A state data optimization unit, used for optimizing the plurality of battery state data to generate a plurality of optimized state data; The data fusion processing unit is used to perform data fusion processing on the plurality of optimization state data respectively, and calculate the regional fusion values ​​corresponding to the plurality of target areas.

[0014] As a further limitation of the technical solution of the embodiment of the present invention, the abnormal risk warning module specifically includes: A difference calculation unit, used for performing difference calculation on the plurality of regional fusion values ​​to obtain a plurality of fusion difference values; a difference comparison unit, configured to compare the plurality of fused difference values ​​based on a preset standard difference value to determine whether there is an abnormal risk; an abnormal region selection unit, configured to select an abnormal region from a plurality of battery regions when there is an abnormal risk; A signal generating unit, configured to generate a regional abnormality signal according to the abnormal region; The status warning unit is used to respond to the abnormal signal of the area and issue a status warning.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The embodiment of the present invention determines the battery pack and divides it into multiple battery areas; generates multiple optimized monitoring cycles; performs monitoring planning for multiple battery areas synchronously; periodically selects multiple target areas for monitoring and collection, and performs data fusion processing respectively to generate multiple regional fusion values; compares the multiple regional fusion values, and selects the abnormal area for status warning when there is an abnormal risk. It is able to divide multiple battery areas, plan monitoring planning data, perform monitoring and collection and data fusion processing on multiple target areas, generate multiple regional fusion values, and compare and judge abnormal risks, so as to capture the subtle differences between different battery areas, and can make timely risk judgments and warnings by comparing the fusion values ​​of multiple areas, which can meet the needs of accurate, efficient and safe management of batteries. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of a battery status intelligent monitoring method provided by an embodiment of the present invention is shown; Figure 2 A flowchart of dividing multiple battery areas in a method provided by an embodiment of the present invention is shown; Figure 3 A flowchart of generating multiple optimized monitoring cycles in the method provided by an embodiment of the present invention is shown; Figure 4 A flowchart of synchronous selection monitoring planning in the method provided by an embodiment of the present invention is shown; Figure 5 A flowchart of data fusion processing in the method provided by an embodiment of the present invention is shown; Figure 6 A flow chart showing abnormal risk judgment and abnormal risk status warning in the method provided by an embodiment of the present invention is shown; Figure 7 An application architecture diagram of a battery status intelligent monitoring system provided by an embodiment of the present invention is shown; Figure 8 It shows a structural block diagram of a data fusion processing module in a system provided by an embodiment of the present invention; Fig. 9 The structure block diagram of the abnormal risk warning module in the system provided by the embodiment of the present invention is shown. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] It is understandable that battery monitoring in the existing technology usually adopts an overall monitoring mode, which needs to focus on the entire battery for macro-level status monitoring. It is difficult to capture subtle differences in different areas of the battery, and the alarm mechanism can only be triggered when the battery has obvious abnormalities. It is impossible to achieve timely risk warnings and it is difficult to meet the needs of accurate, efficient and safe battery management.

[0019] To solve the above problems, an intelligent battery status monitoring method and system disclosed in an embodiment of the present invention obtains a three-dimensional annotation model of a battery device, identifies the three-dimensional annotation model, determines the battery pack, and divides multiple battery areas, each of which is composed of multiple battery blocks; identifies the current device state of the battery device, matches the basic monitoring cycle, and optimizes the regional monitoring of multiple battery areas to generate multiple corresponding optimized monitoring cycles; according to multiple optimized monitoring cycles, synchronously selects monitoring plans for multiple battery areas to generate monitoring planning data; according to the monitoring planning data, periodically selects multiple target areas from multiple battery areas for monitoring and collection, and performs data fusion processing respectively to generate multiple regional fusion values; compares the fusion values ​​of multiple areas to determine whether there is an abnormal risk, and when there is an abnormal risk, selects the abnormal area for status warning. It can divide multiple battery areas, plan monitoring planning data, monitor and collect multiple target areas and perform data fusion processing, generate multiple regional fusion values, and compare and judge abnormal risks, so as to capture the subtle differences between different battery areas, and can make timely risk judgment and warning by comparing the fusion values ​​of multiple areas, which can meet the needs of accurate, efficient and safe management of batteries.

[0020] Specifically, Figure 1 A flow chart of a battery status intelligent monitoring method provided by an embodiment of the present invention is shown.

[0021] In a preferred embodiment of the present invention, a method for intelligently monitoring battery status includes the following steps: Step S101, obtain a three-dimensional annotation model of a battery device, identify the three-dimensional annotation model, determine the battery pack, and divide it into multiple battery areas, each battery area is composed of multiple battery blocks.

[0022] In an embodiment of the present invention, before performing intelligent monitoring of the battery status, a three-dimensional annotation model of the battery equipment is obtained, and then the equipment structure is identified on the three-dimensional annotation model to determine the battery pack in the battery equipment and obtain the structural information of the battery pack. By identifying the structural information, the battery pack is divided into a plurality of battery areas according to factors such as the influencing position and sensor layout in the structural information, wherein each battery area is composed of a plurality of battery blocks.

[0023] It is understandable that battery equipment can be electric vehicles, energy storage devices, computers, mobile phones and other devices that can carry batteries.

[0024] It is understandable that dividing the battery pack into multiple battery areas according to factors such as the impact position and sensor layout can ensure that the divided battery areas belong to different impact positions (for example, the impact of electric vehicle batteries close to the ground and far from the ground is different, and the battery area close to the ground is more susceptible to bumps), and each battery area has more than one monitoring sensor of the same type, providing a basis for the subsequent division and optimization of the monitoring cycle.

[0025] Specifically, Figure 2 A flow chart of dividing multiple battery areas in the method provided in an embodiment of the present invention is shown.

[0026] Among them, in another preferred embodiment provided by the present invention, the three-dimensional annotation model of the battery device is obtained, the three-dimensional annotation model is identified, the battery pack is determined, and a plurality of battery areas are divided, each battery area is composed of a plurality of battery blocks, and specifically includes the following steps: Step S1011, obtaining a three-dimensional annotated model of the battery device.

[0027] Step S1012: perform structural recognition on the three-dimensional annotated model to determine the battery pack.

[0028] Step S1013: Acquire structural information of the battery pack.

[0029] Step S1014: Divide the battery pack into a plurality of battery areas according to the structural information, each battery area being composed of a plurality of battery blocks.

[0030] Furthermore, the battery status intelligent monitoring method further comprises the following steps: Step S102: Identify the current device state of the battery device, match the basic monitoring cycle, and perform targeted optimization of regional monitoring on multiple battery areas to generate multiple corresponding optimized monitoring cycles.

[0031] In an embodiment of the present invention, by identifying the current device status of the battery device, matching the corresponding basic monitoring cycle according to the current device status, and then performing usage impact analysis on multiple battery areas, planning multiple impact coefficients, and then multiplying the basic monitoring cycle with the multiple impact coefficients, targeted optimization of regional monitoring of multiple battery areas is achieved, and multiple optimized monitoring cycles are generated.

[0032] It can be understood that the current device state can be divided into a working state and an idle state, wherein the basic monitoring period of the working state is shorter than the basic monitoring period of the idle state.

[0033] It is understandable that the influence coefficient is a value between 0 and 1.

[0034] It is understandable that the use of impact analysis is mainly determined by the factors affecting the location. For example, when the battery device is an electric vehicle, the impact coefficient is matched according to the impact location. The closer the battery pack is to the battery area on the ground, the smaller the impact coefficient.

[0035] Specifically, Figure 3 A flow chart of generating multiple optimized monitoring cycles in the method provided by an embodiment of the present invention is shown.

[0036] Among them, in another preferred embodiment provided by the present invention, the identifying the current device state of the battery device, matching the basic monitoring cycle, and optimizing the regional monitoring of the multiple battery areas to generate multiple corresponding optimized monitoring cycles specifically includes the following steps: Step S1021: Identify the current device state of the battery device.

[0037] Step S1022: Match the basic monitoring cycle according to the current device status.

[0038] Step S1023: performing usage impact analysis on the multiple battery areas and planning multiple impact coefficients.

[0039] Step S1024: Optimize the regional monitoring of the multiple battery areas according to the basic monitoring cycle and the multiple influence coefficients, and generate multiple optimized monitoring cycles.

[0040] Furthermore, the battery status intelligent monitoring method further comprises the following steps: Step S103: Perform monitoring planning for the multiple battery areas according to the multiple optimized monitoring cycles, and generate monitoring planning data.

[0041] In an embodiment of the present invention, multiple optimized monitoring cycles are compared, the smallest optimized monitoring cycle is selected, marked as a unit monitoring cycle, and the basic synchronization number is determined. Then, based on the basic synchronization number, the unit monitoring cycle and multiple optimized monitoring cycles, a monitoring plan for synchronous selection of multiple battery areas is performed to ensure that during each unit monitoring cycle, more than the basic synchronization number of battery areas are synchronously monitored, and the monitoring order of multiple battery areas is recorded to generate multiple corresponding synchronization order data. Then, a total monitoring sequence is generated according to the unit monitoring cycle, and multiple synchronization sequence data are comprehensively arranged on the total monitoring sequence to generate monitoring plan data.

[0042] Specifically, Figure 4 A flow chart of synchronous selection monitoring planning in the method provided by an embodiment of the present invention is shown.

[0043] Among them, in another preferred embodiment provided by the present invention, the monitoring plan for synchronously selecting multiple battery areas according to multiple optimized monitoring cycles and generating monitoring plan data specifically include the following steps: Step S1031: compare the multiple optimized monitoring periods and select a unit monitoring period.

[0044] Step S1032: Determine the basic synchronization quantity.

[0045] Step S1033: Perform a monitoring plan for synchronous selection of the multiple battery areas according to the basic synchronization quantity, the unit monitoring cycle and the multiple optimized monitoring cycles, and generate multiple synchronization sequence data.

[0046] Step S1034: comprehensively arrange the plurality of synchronization sequence data to generate monitoring planning data.

[0047] Furthermore, the battery status intelligent monitoring method further comprises the following steps: Step S104: According to the monitoring planning data, multiple target areas are periodically selected from the multiple battery areas for monitoring and collection, and data fusion processing is performed on each area to generate multiple area fusion values.

[0048] In an embodiment of the present invention, according to the monitoring planning data, multiple target areas in the same monitoring time sequence are periodically selected from multiple battery areas, and multiple battery status data are collected by synchronously monitoring the battery status of the multiple target areas. Then, the multiple battery status data are optimized for invalid identification and elimination to generate multiple optimized status data, and then data fusion processing is performed on the multiple optimized status data respectively, and the regional fusion values ​​corresponding to the multiple target areas are calculated. Specifically, the calculation formula is: ; in, For the i The regional fusion value of the target area, For the i The optimization status data of the target area j state values, each optimization state data has a total of m Status value, For the i The state mean of the optimized state data of the target area.

[0049] It is understandable that the optimization process of performing invalid identification and elimination on multiple battery status data may be a process of identifying blank data, duplicate data, damaged data, etc. in the multiple battery status data and eliminating them.

[0050] It can be understood that battery status monitoring can be a process of monitoring the temperature, pressure, etc. of a relevant target area, and the corresponding status value can be a temperature value, a pressure value, etc.

[0051] Specifically, Figure 5 A flow chart of data fusion processing in the method provided by an embodiment of the present invention is shown.

[0052] Among them, in another preferred embodiment provided by the present invention, according to the monitoring planning data, multiple target areas are periodically selected from multiple battery areas for monitoring and collection, and data fusion processing is performed respectively to generate multiple regional fusion values, which specifically includes the following steps: Step S1041: periodically select multiple target areas from the multiple battery areas according to the monitoring planning data.

[0053] Step S1042: perform battery status monitoring on the plurality of target areas and collect a plurality of battery status data.

[0054] Step S1043: Optimize the plurality of battery status data to generate a plurality of optimized status data.

[0055] Step S1044: perform data fusion processing on the plurality of optimization state data respectively, and calculate the regional fusion values ​​corresponding to the plurality of target regions.

[0056] Furthermore, the battery status intelligent monitoring method further comprises the following steps: Step S105: compare the fusion values ​​of the multiple regions to determine whether there is an abnormal risk, and if there is an abnormal risk, select the abnormal region for status warning.

[0057] In an embodiment of the present invention, a plurality of fused difference values ​​are obtained by performing difference calculation on the fused values ​​of multiple regions by subtracting each other, and then the plurality of fused difference values ​​are compared with a preset standard difference value to determine whether there is an abnormal risk. Specifically: when multiple fused difference values ​​are all smaller than the standard difference value, it is determined that there is no abnormal risk; and when one or more fused difference values ​​are not smaller than the standard difference value, it is determined that there is an abnormal risk. At this time, an abnormal region is selected from multiple battery regions, and then a targeted regional abnormal signal is generated based on the abnormal region, and then a status warning is performed in response to the regional abnormal signal. Therefore, when the values ​​obtained by the status monitoring do not show obvious abnormalities, but the status monitoring between multiple target regions has obvious differences, a timely status warning can be performed to effectively avoid abnormal escalation.

[0058] It can be understood that if the fusion difference value between the target area A and the target area B is not less than the standard difference value, and the fusion difference value between the target area B and the target area C is less than the standard difference value, the target area A can be determined to be an abnormal area.

[0059] Specifically, Figure 6 A flow chart of abnormal risk judgment and abnormal risk status warning in the method provided by an embodiment of the present invention is shown.

[0060] Among them, in another preferred embodiment provided by the present invention, the comparison of the fusion values ​​of the multiple regions to determine whether there is an abnormal risk, and when there is an abnormal risk, selecting the abnormal region for status warning specifically includes the following steps: Step S1051, performing difference calculation on the fusion values ​​of the multiple regions to obtain multiple fusion difference values.

[0061] Step S1052: Based on a preset standard difference value, compare the multiple fusion difference values ​​to determine whether there is an abnormal risk.

[0062] Step S1053: When there is an abnormal risk, select an abnormal area from the multiple battery areas.

[0063] Step S1054: Generate a regional abnormality signal according to the abnormal region.

[0064] Step S1055: respond to the regional abnormality signal and issue a status warning.

[0065] Furthermore, Figure 7 The application architecture diagram of the battery status intelligent monitoring system provided by an embodiment of the present invention is shown.

[0066] Specifically, in another preferred embodiment provided by the present invention, a battery status intelligent monitoring system includes: The battery area division module 101 is used to obtain a three-dimensional annotation model of a battery device, identify the three-dimensional annotation model, determine the battery pack, and divide it into multiple battery areas, each of which is composed of multiple battery blocks.

[0067] In an embodiment of the present invention, before performing intelligent monitoring of the battery status, the battery area division module 101 obtains a three-dimensional annotation model of the battery equipment, then performs equipment structure identification on the three-dimensional annotation model, determines the battery pack in the battery equipment, and obtains the structural information of the battery pack. By identifying the structural information, the battery pack is divided into a plurality of battery areas according to factors such as the influencing position and sensor layout in the structural information, wherein each battery area is composed of a plurality of battery blocks.

[0068] The cycle matching optimization module 102 is used to identify the current device state of the battery device, match the basic monitoring cycle, and perform targeted optimization of regional monitoring on multiple battery areas to generate multiple corresponding optimized monitoring cycles.

[0069] In an embodiment of the present invention, the cycle matching optimization module 102 identifies the current device status of the battery device, matches the corresponding basic monitoring cycle according to the current device status, performs usage impact analysis on multiple battery areas, plans multiple impact coefficients, and then multiplies the basic monitoring cycle with the multiple impact coefficients to achieve targeted optimization of regional monitoring of multiple battery areas and generate multiple optimized monitoring cycles.

[0070] The synchronous monitoring planning module 103 is used to perform synchronously selected monitoring planning for the multiple battery areas according to the multiple optimized monitoring cycles, and generate monitoring planning data.

[0071] In an embodiment of the present invention, the synchronous monitoring planning module 103 compares multiple optimized monitoring cycles, selects the smallest optimized monitoring cycle, marks it as a unit monitoring cycle, and determines the basic synchronization number. Then, based on the basic synchronization number, the unit monitoring cycle and multiple optimized monitoring cycles, a monitoring plan for synchronous selection is performed for multiple battery areas to ensure that during each unit monitoring cycle, more than the basic synchronization number of battery areas are synchronously monitored, and the monitoring order of multiple battery areas is recorded to generate multiple corresponding synchronization order data. Then, a total monitoring sequence is generated according to the unit monitoring cycle, and multiple synchronization sequence data are comprehensively arranged on the total monitoring sequence to generate monitoring planning data.

[0072] The data fusion processing module 104 is used to periodically select multiple target areas from the multiple battery areas for monitoring and collection according to the monitoring planning data, and perform data fusion processing on each area to generate multiple area fusion values.

[0073] In the embodiment of the present invention, the data fusion processing module 104 periodically selects multiple target areas in the same monitoring time sequence from multiple battery areas according to the monitoring planning data, collects multiple battery status data by synchronously monitoring the battery status of the multiple target areas, and then performs optimization processing of invalid identification and elimination on the multiple battery status data to generate multiple optimized status data, and then performs data fusion processing on the multiple optimized status data respectively, and calculates the regional fusion values ​​corresponding to the multiple target areas. Specifically, the calculation formula is: ; in, For the i The regional fusion value of the target area, For the iThe optimization status data of the target area j state values, each optimization state data has a total of m Status value, For the i The state mean of the optimized state data of the target area.

[0074] Specifically, Figure 8 It shows a structural block diagram of the data fusion processing module 104 in the system provided by the embodiment of the present invention.

[0075] In another preferred embodiment of the present invention, the data fusion processing module 104 specifically includes: The target area selection unit 1041 is used to periodically select multiple target areas from the multiple battery areas according to the monitoring planning data.

[0076] The battery status monitoring unit 1042 is used to perform battery status monitoring on the multiple target areas and collect multiple battery status data.

[0077] The state data optimization unit 1043 is used to optimize the plurality of battery state data to generate a plurality of optimized state data.

[0078] The data fusion processing unit 1044 is used to perform data fusion processing on the plurality of optimization state data respectively, and calculate the regional fusion values ​​corresponding to the plurality of target regions.

[0079] Furthermore, the battery status intelligent monitoring system also includes: The abnormal risk warning module 105 is used to compare the fused values ​​of the multiple regions to determine whether there is an abnormal risk, and if there is an abnormal risk, select the abnormal region for status warning.

[0080] In an embodiment of the present invention, the abnormal risk warning module 105 obtains multiple fusion difference values ​​by performing difference calculation on multiple area fusion values ​​by subtracting each other, and then compares the multiple fusion difference values ​​with the preset standard difference value to determine whether there is an abnormal risk. Specifically: when multiple fusion difference values ​​are all smaller than the standard difference value, it is determined that there is no abnormal risk; and when one or more fusion difference values ​​are not smaller than the standard difference value, it is determined that there is an abnormal risk. At this time, an abnormal area is selected from multiple battery areas, and then a targeted regional abnormal signal is generated based on the abnormal area, and then a status warning is performed in response to the regional abnormal signal. Therefore, when the values ​​obtained by the status monitoring do not show obvious abnormalities, but the status monitoring between multiple target areas has obvious differences, a timely status warning can be performed to effectively avoid abnormal escalation.

[0081] Specifically, Fig. 9It shows a structural block diagram of the abnormal risk warning module 105 in the system provided by an embodiment of the present invention.

[0082] Among them, in another preferred embodiment provided by the present invention, the abnormal risk warning module 105 specifically includes: The difference calculation unit 1051 is used to perform difference calculation on the multiple regional fusion values ​​to obtain multiple fusion difference values.

[0083] The difference comparison unit 1052 is used to compare the multiple fused difference values ​​based on a preset standard difference value to determine whether there is an abnormal risk.

[0084] The abnormal region selection unit 1053 is used to select an abnormal region from the multiple battery regions when there is an abnormal risk.

[0085] The signal generating unit 1054 is configured to generate a regional abnormality signal according to the abnormal region.

[0086] The status warning unit 1055 is used to respond to the regional abnormality signal and issue a status warning.

[0087] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0088] 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, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0089] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A battery status intelligent monitoring method, characterized in that: The method comprises the following steps: Obtaining a three-dimensional annotated model of a battery device, identifying the three-dimensional annotated model, determining a battery pack, and dividing the battery pack into a plurality of battery areas, each of which is composed of a plurality of battery blocks; Identify the current device state of the battery device, match the basic monitoring cycle, and perform targeted optimization of regional monitoring on multiple battery areas to generate multiple corresponding optimized monitoring cycles; According to the plurality of optimized monitoring cycles, a monitoring plan is performed for the plurality of battery areas to be synchronously selected, and monitoring plan data is generated; According to the monitoring planning data, multiple target areas are periodically selected from the multiple battery areas for monitoring and collection, and data fusion processing is performed on each area to generate multiple area fusion values; The fused values ​​of the multiple regions are compared to determine whether there is an abnormal risk, and when there is an abnormal risk, the abnormal region is selected for status warning.

2. The battery status intelligent monitoring method according to claim 1, characterized in that: The step of obtaining a three-dimensional annotation model of a battery device, identifying the three-dimensional annotation model, determining a battery pack, and dividing the battery pack into a plurality of battery areas, each of which is composed of a plurality of battery blocks, specifically includes the following steps: Obtain a 3D annotated model of the battery device; Performing structural recognition on the three-dimensional annotated model to determine the battery pack; Acquiring structural information of the battery pack; The battery pack is divided into a plurality of battery areas according to the structural information, and each battery area is composed of a plurality of battery blocks.

3. The battery status intelligent monitoring method according to claim 1, characterized in that: The identifying the current device state of the battery device, matching the basic monitoring cycle, and optimizing the regional monitoring of the multiple battery regions to generate multiple corresponding optimized monitoring cycles specifically includes the following steps: identifying a current device state of the battery device; According to the current device status, matching the basic monitoring cycle; Performing usage impact analysis on the multiple battery areas and planning multiple impact coefficients; According to the basic monitoring cycle and the multiple influence coefficients, targeted optimization of regional monitoring is performed on the multiple battery regions to generate multiple optimized monitoring cycles.

4. The battery status intelligent monitoring method according to claim 1, characterized in that: The monitoring plan for synchronously selecting the multiple battery areas according to the multiple optimized monitoring cycles and generating monitoring plan data specifically comprises the following steps: Comparing a plurality of the optimized monitoring cycles and selecting a unit monitoring cycle; Determine the basic synchronization quantity; Performing a monitoring plan for synchronous selection of the plurality of battery areas according to the basic synchronization quantity, the unit monitoring cycle and the plurality of optimized monitoring cycles, and generating a plurality of synchronization sequence data; A plurality of the synchronous sequence data are comprehensively arranged to generate monitoring planning data.

5. The battery status intelligent monitoring method according to claim 1, characterized in that: The step of periodically selecting multiple target areas for monitoring and collection from multiple battery areas according to the monitoring planning data, and performing data fusion processing respectively to generate multiple area fusion values ​​specifically includes the following steps: According to the monitoring planning data, periodically selecting a plurality of target areas from the plurality of battery areas; Performing battery status monitoring on a plurality of target areas and collecting a plurality of battery status data; Optimizing the plurality of battery status data to generate a plurality of optimized status data; Data fusion processing is performed on the plurality of optimization state data respectively, and regional fusion values ​​corresponding to the plurality of target regions are calculated.

6. The battery status intelligent monitoring method according to claim 4, characterized in that: The calculation formula of the regional fusion values ​​corresponding to the multiple target regions is: ； in, For the i The regional fusion value of the target area, For the i The optimization status data of the target area j state values, each optimization state data has a total of m Status value, For the i The state mean of the optimized state data of the target area.

7. The battery status intelligent monitoring method according to claim 1, characterized in that: The step of comparing the fusion values ​​of the multiple regions to determine whether there is an abnormal risk, and selecting the abnormal region for status warning when there is an abnormal risk specifically includes the following steps: Performing difference calculation on the fusion values ​​of the multiple regions to obtain multiple fusion difference values; Based on a preset standard difference value, comparing the plurality of fused difference values ​​to determine whether there is an abnormal risk; When there is an abnormal risk, selecting an abnormal area from the plurality of battery areas; generating a regional abnormality signal according to the abnormal region; Respond to abnormal signals in the area and issue status warnings.

8. A battery status intelligent monitoring system, characterized in that: The system includes a battery area division module, a cycle matching optimization module, a synchronous monitoring planning module, a data fusion processing module and an abnormal risk warning module, wherein: A battery area division module is used to obtain a three-dimensional annotation model of a battery device, identify the three-dimensional annotation model, determine the battery pack, and divide it into multiple battery areas, each of which is composed of multiple battery blocks; A cycle matching optimization module, used to identify the current device state of the battery device, match the basic monitoring cycle, and perform targeted optimization of regional monitoring on multiple battery areas to generate multiple corresponding optimized monitoring cycles; A synchronous monitoring planning module, used to perform synchronously selected monitoring planning for the plurality of battery areas according to the plurality of optimized monitoring cycles, and generate monitoring planning data; A data fusion processing module is used to periodically select multiple target areas from the multiple battery areas for monitoring and collection according to the monitoring planning data, and perform data fusion processing on each area to generate multiple area fusion values; The abnormal risk warning module is used to compare the fused values ​​of the multiple regions to determine whether there is an abnormal risk, and when there is an abnormal risk, select the abnormal region for status warning.

9. The battery status intelligent monitoring system according to claim 8, characterized in that: The data fusion processing module specifically includes: A target area selection unit, configured to periodically select a plurality of target areas from the plurality of battery areas according to the monitoring planning data; A battery status monitoring unit, used to monitor the battery status of the plurality of target areas and collect a plurality of battery status data; A state data optimization unit, used for optimizing the plurality of battery state data to generate a plurality of optimized state data; The data fusion processing unit is used to perform data fusion processing on the plurality of optimization state data respectively, and calculate the regional fusion values ​​corresponding to the plurality of target areas.

10. The battery status intelligent monitoring system according to claim 8, characterized in that: The abnormal risk warning module specifically includes: A difference calculation unit, used for performing difference calculation on the plurality of regional fusion values ​​to obtain a plurality of fusion difference values; a difference comparison unit, configured to compare the plurality of fused difference values ​​based on a preset standard difference value to determine whether there is an abnormal risk; an abnormal region selection unit, configured to select an abnormal region from a plurality of battery regions when there is an abnormal risk; A signal generating unit, configured to generate a regional abnormality signal according to the abnormal region; The status warning unit is used to respond to the abnormal signal of the area and issue a status warning.

Images