Vehicle chassis collision identification method and device, electronic equipment, medium and product

Abstract

The invention discloses a vehicle chassis collision identification method and device, electronic equipment, a medium and a product. The method comprises the following steps: acquiring battery operation time sequence data corresponding to a vehicle battery of a to-be-tested vehicle; a battery fault detection unit is adopted to process the battery operation time sequence data to obtain a battery fault detection result corresponding to the vehicle battery; and according to the battery fault detection result, determining a chassis collision identification result corresponding to the to-be-detected vehicle. According to the technical scheme provided by the embodiment of the invention, the effect of accurately identifying the vehicle chassis collision event only according to the battery operation time sequence data of the vehicle battery without additionally deploying special hardware is realized.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a method, device, electronic equipment, medium, and product for identifying vehicle chassis collisions. Background Technology

[0002] With the continuous development of automotive technology, cars have gradually become a primary means of transportation. When vehicles are driven in adverse road conditions, such as on bumpy or uneven surfaces, the vehicle chassis is prone to collisions, which can even affect the vehicle's driving safety and lifespan.

[0003] In related technologies, reliance on user subjective perception is common. This approach can only detect severe chassis impacts, failing to detect minor ones, resulting in low accuracy in chassis impact recognition. Alternatively, external hardware installed on the vehicle can be used to detect chassis impacts. However, this method may require expensive hardware and has low real-time performance, affecting the vehicle's response time to impact events and compromising driving safety. Summary of the Invention

[0004] This invention provides a method, device, electronic device, medium, and product for identifying vehicle chassis collisions, so as to achieve the effect of accurately identifying vehicle chassis collision events based solely on the battery runtime sequence data of the vehicle battery without the need for additional dedicated hardware deployment.

[0005] According to one aspect of the present invention, a method for identifying vehicle chassis collisions is provided, the method comprising:

[0006] Obtain the battery runtime sequence data corresponding to the vehicle battery of the vehicle under test;

[0007] A battery fault detection unit is used to process the battery runtime sequence data to obtain the battery fault detection result corresponding to the vehicle battery.

[0008] Based on the battery fault detection results, the chassis collision identification results corresponding to the vehicle are determined.

[0009] According to another aspect of the present invention, a vehicle chassis collision detection device is provided, the device comprising:

[0010] The battery data acquisition module is used to acquire battery runtime sequence data corresponding to the vehicle battery of the vehicle under test.

[0011] The battery fault detection module is used to process the battery operation sequence data using the battery fault detection unit to obtain the battery fault detection result corresponding to the vehicle battery.

[0012] The chassis collision recognition module is used to determine the chassis collision recognition result corresponding to the vehicle based on the battery fault detection result.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the vehicle chassis collision recognition method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the vehicle chassis collision recognition method according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the vehicle chassis collision recognition method according to any embodiment of the present invention.

[0019] The technical solution of this invention provides core raw data support for subsequent fault detection by acquiring battery runtime sequence data corresponding to the vehicle battery of the vehicle under test. No additional dedicated detection hardware is required; reliable and timely judgment of chassis collision events can be achieved based solely on the battery runtime sequence data. Furthermore, by processing the battery runtime sequence data using a battery fault detection unit, battery fault detection results corresponding to the vehicle battery are obtained. Targeted analysis of the battery runtime sequence data accurately identifies battery fault characteristics caused by chassis collisions, providing reliable and accurate core evidence for subsequent chassis collision event judgment and avoiding false alarms and missed alarms. Moreover, by determining the chassis collision identification result corresponding to the vehicle under test based on the battery fault detection result, the effect of accurately identifying chassis collisions based on the battery fault detection result is achieved. Hidden chassis collisions can be accurately captured without additional dedicated hardware, providing timely and reliable judgment evidence for vehicle safety maintenance. The technical solution of this invention addresses the problems of high hardware costs, low real-time performance and accuracy of chassis collision recognition, which affect the vehicle's response speed to chassis collision events. It achieves accurate identification of chassis collision events based solely on the vehicle's battery runtime sequence data without requiring additional dedicated hardware. This reduces the cost of chassis collision recognition, improves its real-time performance and detection accuracy, effectively accelerates the vehicle's response speed to chassis collision events, and ensures battery safety and driving reliability.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a vehicle chassis collision recognition method according to Embodiment 1 of the present invention;

[0023] Figure 2 This is a flowchart of a vehicle chassis collision recognition method according to Embodiment 2 of the present invention;

[0024] Figure 3 This is a flowchart of a vehicle chassis collision recognition method according to Embodiment 3 of the present invention;

[0025] Figure 4 This is a flowchart of a vehicle chassis collision recognition method according to Embodiment 4 of the present invention;

[0026] Figure 5 This is a schematic diagram of the structure of a vehicle chassis collision recognition device according to Embodiment 5 of the present invention;

[0027] Figure 6 This is a schematic diagram of the structure of an electronic device that implements the vehicle chassis collision recognition method according to an embodiment of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Example 1

[0031] Figure 1 This is a flowchart of a vehicle chassis collision recognition method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations involving collisions to the vehicle chassis. The method can be executed by a vehicle chassis collision recognition device, which can be implemented in hardware and / or software and can be configured in a terminal and / or server. Figure 1 As shown, the method includes:

[0032] S110. Obtain the battery runtime sequence data corresponding to the vehicle battery of the vehicle under test.

[0033] Typically, the vehicle battery is housed in the chassis of an electric vehicle. A collision with the chassis can cause multi-dimensional damage to the battery (such as physical structural damage, electrical performance failure, and thermal runaway), leading to battery malfunction and ultimately affecting driving safety. Therefore, identifying chassis collision events can be done using the battery's operational timing data.

[0034] The vehicle under test can be an electric vehicle requiring chassis collision detection. The vehicle under test can be any type of electric vehicle. The vehicle battery can be the power battery pack on the vehicle under test, used to provide power. It can be understood that the vehicle battery includes core components such as cell packs, battery management system, liquid cooling / thermal management system, insulation structure, and connecting harnesses. A cell pack consists of multiple individual cells. The vehicle battery can be a core component that is easily damaged after a chassis collision and can output fault characteristic data. Battery runtime sequence data can be understood as the dynamic data related to the battery continuously collected and recorded chronologically by an onboard data acquisition system during vehicle operation (including vehicle driving, charging, and stationary parking). Battery runtime sequence data can be used to characterize the vehicle battery's operation over a period of time. It should be noted that battery runtime sequence data can carry timestamps to reflect changes in battery operation data over time. For example, battery runtime sequence data includes battery operation data at time A, battery operation data at the previous time A, and battery operation data at the next time A. Furthermore, the battery runtime timing data collection scenarios can cover all vehicle usage states (including driving, charging, and parking). That is, during vehicle operation, battery runtime data can be continuously collected, and the collected battery runtime data containing time-series characteristics is used as battery runtime timing data. Battery runtime timing data can include multiple data related to the battery's operating state, optionally including at least one of battery temperature timing data, battery resistance timing data, battery voltage timing data, and charging status data. Specifically, battery temperature timing data can refer to vehicle battery temperature data collected continuously in chronological order, including temperature data from at least one of the following: individual battery cells and key areas of the battery pack (such as liquid cooling inlets / outlets, and the casing). Optionally, battery temperature timing data can include temperature data of the vehicle battery at multiple consecutive time points, and the temperature data includes temperature parameter values ​​of multiple individual battery cells. When the temperature data includes temperature parameter values ​​of multiple individual cells, the temperature data can include at least one of the following: maximum temperature parameter value, minimum temperature parameter value, and average temperature parameter value.

[0035] The battery resistance time-series data can refer to the insulation resistance data of the vehicle battery collected continuously in chronological order. Changes in the battery resistance time-series data can directly reflect the battery's insulation performance or the internal structural state of the cells. Optionally, the battery resistance time-series data can include the resistance data of the vehicle battery at multiple consecutive time points. The battery voltage time-series data can refer to the vehicle battery voltage data collected continuously in chronological order, including voltage-related data such as the voltage data of each individual cell of the vehicle battery, the total voltage of the vehicle battery, and the module voltage. Optionally, the battery voltage time-series data can include the voltage data of the vehicle battery at multiple consecutive time points, and the voltage data includes the voltage parameter values ​​of multiple individual cells in the vehicle battery. When the voltage data includes the voltage parameter values ​​of multiple individual cells, the voltage data can include at least one of the following: the highest voltage of an individual cell, the lowest voltage of an individual cell, and the average voltage of an individual cell.

[0036] It should be noted that the entity that performs the identification of chassis collisions of the vehicle under test based on the battery runtime sequence data of the vehicle battery can be the vehicle's on-board terminal, the data platform of the battery supplier, or a cloud platform associated with the vehicle under test. This embodiment does not specifically limit this.

[0037] In one embodiment, during the operation of the vehicle under test, battery operation data can be collected according to a preset data acquisition step size, and the collected battery operation data can be transmitted to the data platform of the vehicle battery supplier according to a preset data transmission protocol. This allows the acquisition of battery operation sequence data of the vehicle under test.

[0038] S120. The battery fault detection unit processes the battery operation sequence data to obtain the battery fault detection result corresponding to the vehicle battery.

[0039] The battery fault detection unit can be understood as a hardware module or software algorithm module that implements the battery fault detection function. The battery fault detection unit can be used to process and analyze battery runtime timing data and output fault-related judgment results. Optionally, when the battery fault detection unit includes a software algorithm module, the software algorithm module includes at least one of the following: a battery fault detection model, a module integrating a battery fault detection algorithm, and an intelligent agent. In this embodiment, when performing fault detection on the vehicle battery, fault detection can be performed from at least one dimension. Furthermore, the battery fault detection unit can include at least one fault detection subunit, which includes at least one of a temperature difference fault detection subunit, an insulation fault detection subunit, and a pressure difference fault detection subunit. The temperature difference fault detection subunit can be a functional submodule within the battery fault detection unit used to detect abnormal battery temperature distribution faults caused by chassis impacts based on battery temperature timing data. That is, the temperature difference fault detection subunit can be used to perform temperature difference fault detection on the vehicle battery based on battery temperature timing data. It is understandable that the core detection logic of the temperature difference fault detection subunit is based on the fault mechanism that "chassis impacts may cause liquid cooling pipe compression and local cooling failure, leading to a significant and continuous increase in the temperature difference between battery cells." By analyzing the temperature difference characteristics (such as temperature difference value, temperature difference change rate, and abnormal proportion) of battery temperature time-series data, it outputs a detection result indicating whether a temperature difference fault exists. Optionally, the temperature difference fault detection subunit may include a hardware module or a software algorithm module capable of implementing temperature difference fault detection. If the temperature difference fault detection subunit includes a software algorithm module, the software algorithm module may include at least one of the following: a temperature difference fault detection model, a module integrating a temperature difference fault detection algorithm, and an intelligent agent. The insulation fault detection subunit may be a functional submodule within the battery fault detection unit used to detect battery insulation performance failure caused by chassis impacts based on battery resistance time-series data. That is, the insulation fault detection subunit can be used to detect insulation faults in vehicle batteries based on battery resistance time-series data. It is understandable that the core detection logic of the insulation fault detection subunit is based on the fault mechanism that "chassis impacts may cause damage to the battery pack casing and insulation layer, leading to a decrease in insulation resistance." By analyzing the numerical changes and rate of decrease in battery resistance time-series data, it outputs a detection result indicating whether an insulation fault exists. Optionally, the insulation fault detection subunit may include a hardware module or a software algorithm module capable of implementing insulation fault detection. If the insulation fault detection subunit includes a software algorithm module, the software algorithm module may include at least one of the following: an insulation fault detection model, a module integrating an insulation fault detection algorithm, and an intelligent agent. The differential voltage fault detection subunit may be a functional submodule within the battery fault detection unit used to detect battery voltage differential faults caused by chassis impacts based on battery voltage time-series data.The differential pressure fault detection subunit can be used to detect differential pressure faults in vehicle batteries based on battery voltage timing data and charging status data. The core detection logic of the differential pressure fault detection subunit is based on the fault mechanism that "chassis impacts may cause cell compression and loosening of connecting harnesses, leading to sudden changes in individual battery voltage and increased differential pressure." By analyzing the differential pressure characteristics of the battery voltage timing data, it outputs a detection result indicating whether a differential pressure fault exists. Optionally, the insulation fault detection subunit may include a hardware module or a software algorithm module capable of implementing insulation fault detection. If the insulation fault detection subunit includes a software algorithm module, the software algorithm module may include at least one of the following: an insulation fault detection model, a module integrating an insulation fault detection algorithm, and an intelligent agent.

[0040] It should be noted that a battery fault detection unit may include at least one fault detection subunit, i.e., it may include one or more fault detection subunits. When a battery fault detection unit includes multiple fault detection subunits, these subunits can be executed in parallel to obtain the battery fault detection result corresponding to each subunit. The advantage of using multiple fault detection subunits to execute in parallel for battery fault detection is that, based on key parameters such as battery system temperature distribution, insulation resistance, and individual cell voltage, a multi-dimensional fault characteristic model can be established. This model integrates continuous data segment analysis, statistical characteristics, distribution characteristics, and time series change detection, enabling accurate identification of liquid cooling / liquid heating anomalies, insulation anomalies, and voltage anomalies. This, in turn, improves the detection accuracy and reliability of chassis impacts.

[0041] The battery fault detection result refers to the judgment conclusion related to battery faults output by the battery fault detection unit after processing the battery runtime sequence data. The content of the battery fault detection result may include at least one of the following: whether a fault exists; fault type; fault severity; fault correlation characteristics. In this embodiment, when the battery fault detection unit includes at least one of a temperature difference fault detection subunit, an insulation fault detection subunit, and a pressure difference fault detection subunit, the battery fault detection result may include at least one of a temperature difference fault detection result, an insulation fault detection result, and a pressure difference fault detection result.

[0042] In this embodiment, when the battery operating timing data includes at least one of battery temperature timing data, battery resistance timing data, and battery voltage timing data, and the battery fault detection unit includes at least one of a temperature difference fault detection subunit, an insulation fault detection subunit, and a pressure difference fault detection subunit, the battery fault detection unit processes the battery operating timing data to obtain a battery fault detection result corresponding to the vehicle battery. This includes at least one of the following: processing the battery temperature timing data using the temperature difference fault detection subunit to obtain a temperature difference fault detection result corresponding to the vehicle battery; processing the battery resistance timing data using the insulation fault detection subunit to obtain an insulation fault detection result corresponding to the vehicle battery; and processing the battery voltage timing data using the pressure difference fault detection subunit to obtain a pressure difference fault detection result corresponding to the vehicle battery.

[0043] In one embodiment, when battery operating timing data corresponding to the vehicle battery of the vehicle under test is obtained, the obtained battery operating timing data may include battery temperature timing data, battery resistance timing data, and battery voltage timing data. Further, a temperature difference fault detection subunit can be used to process the battery temperature timing data to obtain a temperature difference fault detection result corresponding to the vehicle battery; an insulation fault detection subunit can be used to process the battery resistance timing data to obtain an insulation fault detection result corresponding to the vehicle battery; and a differential pressure fault detection subunit can be used to process the battery voltage timing data to obtain a differential pressure fault detection result corresponding to the vehicle battery. Further, the obtained temperature difference fault detection result, insulation fault detection result, and differential pressure fault detection result can be used as the battery fault detection result corresponding to the vehicle battery.

[0044] S130. Based on the battery fault detection results, determine the chassis collision identification results corresponding to the vehicle under test.

[0045] The chassis collision recognition result can refer to the final output conclusion regarding whether the tested vehicle has experienced a chassis collision. Optionally, the chassis collision recognition result includes whether a chassis collision event occurred or not.

[0046] In practical applications, the vehicle chassis houses critical components such as the engine, driveshaft, exhaust pipe, fuel lines, battery, and / or communication lines. When driving on roads with significant bumps or potholes, the chassis is prone to scraping against the ground due to the small distance between it and the road surface, leading to chassis wear and even component failure, thus affecting driving safety. For example, in electric vehicles, the battery is mounted on the chassis. In the event of an impact, the battery casing can be damaged due to compression, potentially causing short circuits and thermal runaway. Currently, the identification of chassis impacts typically relies on the user's subjective perception, judging the impact and severity based on driving experience or guesswork. Minor impacts may go unnoticed, yet even slight impacts can affect driving safety. Alternatively, external hardware installed on the vehicle could be used to inspect the chassis and determine if an impact has occurred. However, this method of identifying vehicle chassis collisions requires high hardware costs and can only provide early warnings, not "post-event fault diagnosis," meaning it cannot identify whether a chassis collision has occurred.

[0047] In response to the above situation, in this embodiment, since vehicle chassis impact is associated with vehicle battery failure, a battery fault detection unit can be used to perform battery fault detection on the vehicle battery based on the battery operation sequence data to obtain battery fault detection results. Furthermore, the battery fault detection results can be used to determine whether the vehicle under test has experienced a chassis impact event.

[0048] Optionally, based on the battery fault detection results, the chassis collision identification result corresponding to the vehicle under test is determined, including: if the battery fault detection result indicates the presence of a battery fault, the chassis collision identification result corresponding to the vehicle is determined to be a chassis collision event; if the battery fault detection result indicates no battery fault, the chassis collision identification result corresponding to the vehicle is determined to be no chassis collision event. The presence of a battery fault in the battery fault detection result may include at least one of the following: battery temperature difference fault, battery insulation fault, and battery voltage difference fault.

[0049] In this embodiment, the battery fault detection result may include at least one of the following: temperature difference fault detection result, insulation fault detection result, and pressure difference fault detection result. Furthermore, a battery fault detection result indicating the presence of a battery fault may include at least one of the following: a temperature difference fault detection result indicating a battery temperature difference fault; an insulation fault detection result indicating a battery insulation fault; or a pressure difference fault detection result indicating a battery pressure difference fault. Correspondingly, a battery fault detection result indicating the absence of a battery fault may be: a temperature difference fault detection result indicating the absence of a battery temperature difference fault; an insulation fault detection result indicating the absence of a battery insulation fault; and a pressure difference fault detection result indicating the absence of a battery pressure difference fault.

[0050] In one embodiment, after obtaining the battery fault detection results, the obtained battery fault detection results include temperature difference fault detection results, insulation fault detection results, and pressure difference fault detection results. Further, if the temperature difference fault detection result indicates the presence of a battery temperature difference fault, it can be determined that the chassis collision identification result corresponding to the vehicle indicates a chassis collision event has occurred. If the temperature difference fault detection result indicates no battery temperature difference fault, the insulation fault detection result indicates no battery insulation fault, and the pressure difference fault detection result indicates no battery pressure difference fault, it can be determined that the chassis collision identification result corresponding to the vehicle indicates no chassis collision event has occurred.

[0051] The technical solution of this invention provides core raw data support for subsequent fault detection by acquiring battery runtime sequence data corresponding to the vehicle battery of the vehicle under test. No additional dedicated detection hardware is required; reliable and timely judgment of chassis collision events can be achieved based solely on the battery runtime sequence data. Furthermore, by processing the battery runtime sequence data using a battery fault detection unit, battery fault detection results corresponding to the vehicle battery are obtained. Targeted analysis of the battery runtime sequence data accurately identifies battery fault characteristics caused by chassis collisions, providing reliable and accurate core evidence for subsequent chassis collision event judgment and avoiding false alarms and missed alarms. Moreover, by determining the chassis collision identification result corresponding to the vehicle under test based on the battery fault detection result, the effect of accurately identifying chassis collisions based on the battery fault detection result is achieved. Hidden chassis collisions can be accurately captured without additional dedicated hardware, providing timely and reliable judgment evidence for vehicle safety maintenance. The technical solution of this invention addresses the problems of high hardware costs, low real-time performance and accuracy of chassis collision recognition, which affect the vehicle's response speed to chassis collision events. It achieves accurate identification of chassis collision events based solely on the vehicle's battery runtime sequence data without requiring additional dedicated hardware. This reduces the cost of chassis collision recognition, improves its real-time performance and detection accuracy, effectively accelerates the vehicle's response speed to chassis collision events, and ensures battery safety and driving reliability.

[0052] Example 2

[0053] Figure 2 This is a flowchart of a vehicle chassis collision recognition method provided in Embodiment 2 of the present invention. Based on the foregoing embodiments, when the battery operating sequence data includes battery temperature time-series data, and the battery fault detection unit includes a temperature difference fault detection subunit, the temperature difference fault detection subunit can be used to process the battery temperature time-series data to obtain the battery fault detection result. Specific implementation methods can be found in the technical solution of this embodiment. Technical terms that are the same as or similar to those in the above embodiments will not be repeated here. Figure 2 As shown, the method includes:

[0054] S210. Obtain battery runtime timing data corresponding to the vehicle battery of the vehicle under test; wherein, the battery runtime timing data includes battery temperature timing data.

[0055] S220: The temperature difference fault detection subunit processes the battery temperature time series data to obtain the battery fault detection results corresponding to the vehicle battery.

[0056] In this embodiment, the temperature difference fault detection subunit is used to process the battery temperature timing data, which may include at least one of the following methods.

[0057] Optionally, the temperature difference fault detection subunit includes a temperature difference fault detection model; the temperature difference fault detection subunit processes the battery temperature time series data to obtain the battery fault detection result corresponding to the vehicle battery, including: inputting the battery temperature time series data into the temperature difference fault detection model, obtaining the output temperature difference fault detection result, and determining the battery fault detection result corresponding to the vehicle battery based on the temperature difference fault detection result.

[0058] The temperature difference fault detection model can be understood as a neural network model that can determine whether a vehicle battery has a temperature difference fault based on battery temperature time-series data. This model automatically extracts temperature difference features (such as temperature change rate, duration of continuous anomalies, and temperature distribution entropy) from the battery temperature time-series data, performs feature analysis on the extracted features, and outputs a judgment result indicating whether a temperature difference fault exists. Typically, historical battery temperature data (including temperature time-series data under normal operating conditions and temperature anomaly time-series data caused by chassis impacts) is used as training samples to train the model, enabling it to learn the differences between normal and faulty temperature difference patterns. The temperature difference fault detection model can employ a deep learning model of any structure; optionally, it can use at least one of the following: Long Short-Term Memory Networks and Random Forests.

[0059] In one embodiment, after acquiring battery temperature time-series data, this data can be input into a temperature difference fault detection model. Furthermore, the temperature difference feature of the battery temperature time-series data can be extracted using the temperature difference fault detection model, and this feature can be processed to obtain the output temperature difference fault detection result. Further, the temperature difference fault detection result can be used as the battery fault detection result corresponding to the vehicle battery.

[0060] Optionally, the temperature difference fault detection subunit includes a module integrating a temperature difference fault detection algorithm; the battery temperature time series data includes temperature data of the vehicle battery at multiple consecutive time points; the temperature difference fault detection subunit processes the battery temperature time series data to obtain a battery fault detection result corresponding to the vehicle battery, including: when the battery fault detection unit includes a temperature difference fault detection unit, determining a first time period to be detected for temperature difference fault based on the battery temperature time series data; for multiple first time points in the first time period, determining the battery temperature difference value at each first time point based on the temperature data corresponding to the first time point; determining the number of first target time points among the multiple battery temperature differences that are greater than a preset temperature difference threshold, and determining a temperature difference abnormality ratio based on the number of first target time points and the total number of time points in the first time period; determining the temperature difference fault detection result corresponding to the vehicle battery based on the temperature difference fault detection result, so as to determine the battery fault detection result corresponding to the vehicle battery based on the temperature difference fault detection result.

[0061] The first time period can refer to the time period selected from battery temperature time-series data that meets preset detection conditions. This time period can be a specific analysis interval for temperature difference fault detection. The first time period includes multiple consecutive first time points, and the time interval between two adjacent first time points is less than a first preset interval threshold. A first time point can refer to a specific time node within the first time period. Each first time point corresponds to a set of temperature data, which includes the temperature parameter values ​​of multiple individual battery cells. The first time point is the time point in the battery temperature time-series data where the corresponding temperature data meets the preset liquid cooling trigger condition. The preset liquid cooling trigger condition can refer to a pre-set temperature threshold condition used to determine whether the vehicle's liquid cooling system is activated. Preset liquid cooling trigger conditions are usually divided into two types: liquid cooling heating mode trigger condition and liquid cooling cooling mode trigger condition. The preset time interval can refer to the critical value for determining whether time points are continuous, used to filter out valid first time periods. If the interval between two adjacent time points exceeds the preset interval threshold, it is considered a data interruption and is not included in the same first time period. The first preset interval threshold can be any value, such as 150 seconds, 180 seconds, or 200 seconds.

[0062] It should be noted that in the field of vehicle technology, electric vehicle battery packs typically employ liquid cooling systems for thermal management. When a chassis impact causes compression and restricted flow in the cooling circuit, localized cooling failure can occur, leading to uneven temperature distribution within the battery pack. This temperature anomaly is primarily manifested as a significant increase in the difference between the highest and lowest temperatures of individual cells, and it exhibits a persistent characteristic. Temperature difference fault detection, based on the operating characteristics of the liquid cooling system, employs a dual judgment mechanism based on time continuity and statistical characteristics. First, the triggering conditions for both liquid cooling heating and liquid cooling operating modes are identified. Then, the temperature difference change characteristics are analyzed over a continuous time period, and statistical analysis is used to determine whether a temperature difference anomaly exists. Therefore, when performing temperature difference fault detection, it is generally ensured that temperature difference fault detection is only performed on the temperature data during the actual operation of the liquid cooling system. Furthermore, when selecting the time period for temperature difference fault detection, two conditions can be used: whether the temperature data at each time point in the battery temperature time series data meets the preset liquid cooling triggering conditions, and whether the time interval between the first time points that meet the preset liquid cooling triggering conditions is less than a first preset interval threshold.

[0063] Optionally, the method for determining the first time period to be detected for temperature difference faults includes: for multiple time points in the battery temperature time series data, if the time point meets the preset liquid cooling trigger condition based on the temperature data corresponding to the time point, the time point is taken as the first time point; if more than two first time points are determined, the time interval between two adjacent first time points is determined to obtain multiple time intervals; the multiple time intervals are compared with a preset interval threshold in chronological order, and if the first time interval is not less than the preset interval threshold, the time interval not less than the preset interval threshold is taken as the target time interval; the first time period to be detected for temperature difference faults is determined based on the target time point that is earlier in the time series among the two first time points associated with the target time interval and at least one first time point located before the target time point.

[0064] The vehicle battery comprises multiple individual cells, and the temperature data includes the temperature parameter values ​​of these individual cells. In other words, for multiple time points in the battery temperature time-series data, the temperature data for each time point includes the temperature parameter values ​​of multiple individual cells in the vehicle battery at that time point. Generally, when the temperature data includes multiple temperature parameter values, these multiple temperature parameter values ​​typically include a maximum temperature parameter value and a minimum temperature parameter value. Preset liquid cooling trigger conditions are generally divided into two types: liquid cooling heating mode trigger conditions and liquid cooling cooling mode trigger conditions. The liquid cooling heating mode trigger condition can be the specific basis for determining whether the vehicle's liquid cooling system should activate its heating function. Its core logic is to ensure timely improvement of battery activity in low-temperature environments by detecting battery temperature and related state parameters, while avoiding overheating or resource waste. The liquid cooling heating mode trigger condition can include at least one of the following: the minimum temperature parameter value is less than a first preset heating trigger threshold; the average temperature parameter value is less than a second preset heating trigger threshold. The liquid cooling cooling mode trigger condition can be the specific basis for determining whether the vehicle's liquid cooling system should activate its cooling function. Its core logic is to automatically activate the cooling cycle when the battery temperature exceeds the safe / optimal operating range, preventing the battery from overheating and affecting performance or causing safety risks. The triggering condition for liquid cooling heating mode can include: the maximum temperature parameter value exceeding a preset cooling trigger threshold. The time interval between two adjacent first time points can refer to the duration between two consecutive first time points. For example, if first time point A is 10:00:00 and the next first time point B is 10:00:02, the time interval is 2 seconds. The time interval can be used to determine whether the data is continuous. The target time point that is earlier in time among the two first time points associated with the time interval can be, when the time interval between two adjacent first time points exceeds a preset interval threshold, the first time point that is "earlier in time" is the target time point. This target time point can be used to segment time periods. At least one first time point preceding the target time point can refer to all consecutive first time points preceding the target time point, which, together with the target time point, form a continuous dataset without excessively long time intervals.

[0065] In this embodiment, a time point satisfying a preset liquid cooling trigger condition includes at least one of the following: the minimum temperature parameter value in the temperature data corresponding to the time point is less than a first preset heating trigger threshold; the average temperature parameter value in the temperature data corresponding to the time point is less than a second preset heating trigger threshold; or the maximum temperature parameter value in the temperature data corresponding to the time point is greater than a preset cooling trigger threshold. It should be noted that, based on the working principle of the vehicle liquid cooling system, once a liquid cooling heating mode or liquid cooling mode is determined to be triggered, the system remains in either liquid cooling heating mode or liquid cooling mode for a subsequent period of time, and switching between these modes is generally not observed. Therefore, if a certain time point in the battery temperature time series data satisfies the liquid cooling heating mode trigger condition (or liquid cooling mode trigger condition), then all time points within a subsequent period of time will also satisfy the liquid cooling heating mode trigger condition (or liquid cooling mode trigger condition).

[0066] In one embodiment, for multiple time points in the battery temperature time-series data, the temperature data corresponding to each time point is obtained from the battery temperature time-series data, and the maximum and minimum temperature parameter values ​​corresponding to the time points are determined based on the obtained temperature data. Further, the maximum temperature parameter value can be compared with a preset cooling trigger threshold, and the minimum temperature parameter value can be compared with a first preset heating trigger threshold. Further, if the maximum temperature parameter value is greater than the preset cooling trigger threshold, it can be determined that the temperature data corresponding to the time point meets the liquid cooling mode trigger condition, and thus, the temperature data corresponding to that time point meets the preset liquid cooling trigger condition, and that time point is designated as the first time point; or, if the minimum temperature parameter value is less than the first preset heating trigger threshold, it can be determined that the temperature data corresponding to the time point meets the liquid cooling mode trigger condition, and thus, the temperature data corresponding to that time point meets the preset liquid cooling trigger condition, and that time point is designated as the first time point. Further, if two or more first time points are determined, the time interval between two adjacent first time points can be determined, resulting in multiple time intervals. Furthermore, multiple time intervals are compared sequentially with a preset interval threshold. If a time interval is not less than the preset interval threshold for the first time, that time interval can be used as the target time interval. Further, the earlier of the two first time points associated with the target time interval can be used as the target time point. Further, at least one first time point preceding the target time point can be obtained, and the time interval consisting of the target time point and this at least one first time point can be used as the first time period for temperature difference fault detection.

[0067] In this embodiment, after determining a first time period for temperature difference fault detection, for multiple first time points within the first time period, the battery temperature difference at each first time point can be determined based on the temperature data at that first time point. Further, the number of first target time points among the multiple battery temperature differences that exceed a preset temperature difference threshold is determined, and a temperature difference abnormality ratio is determined based on the number of first target time points and the total number of time points in the first time period. Based on the temperature difference abnormality ratio and the total number of time points, a temperature difference fault detection result corresponding to the vehicle battery is determined, thereby determining the battery fault detection result corresponding to the vehicle battery based on the temperature difference fault detection result.

[0068] The preset temperature difference threshold refers to the critical value used to determine whether the battery temperature difference at a single first time point is abnormal. The preset temperature difference threshold can be any temperature difference value, such as 3 degrees Celsius, 5 degrees Celsius, or 7 degrees Celsius. The preset temperature difference threshold can be determined based on statistical analysis of the vehicle battery temperature distribution under normal operating conditions, or it can be modified according to actual conditions. The first target time point refers to the first time point within a first time period where the battery temperature difference is greater than the preset temperature difference threshold (i.e., the specific time node where temperature abnormality exists). For example, if there are 600 first time points in the first time period, and the battery temperature difference at 250 of these first time points is greater than the preset temperature difference threshold, then these 250 first time points are all considered as first target time points. The number of first target time points refers to the total number of all first target time points within the first time period (i.e., the number of time points with temperature abnormality). The total number of time points refers to the total number of all first time points included in the first time period. The temperature abnormality ratio refers to the ratio of the number of first target time points to the total number of time points in the first time period.

[0069] Optionally, the battery temperature difference at the first time point is determined based on the temperature data corresponding to the first time point, including: determining the maximum and minimum temperature parameter values ​​from the temperature parameter values ​​of multiple individual cells, and using the difference between the maximum and minimum temperature parameter values ​​as the battery temperature difference at the first time point.

[0070] Optionally, the temperature difference fault detection result corresponding to the vehicle battery is determined based on the temperature difference abnormality ratio and the total number of time points, including: if the temperature difference abnormality ratio is greater than or equal to a preset temperature difference ratio threshold and the total number of time points is greater than or equal to a preset number of time points threshold, the temperature difference fault detection result corresponding to the vehicle battery is determined to be a temperature difference fault.

[0071] The preset temperature difference ratio threshold refers to a pre-set critical value used to determine whether temperature difference anomalies are sufficiently prevalent. This threshold can be used to distinguish between occasional anomalies at individual time points (such as momentary fluctuations in the sensor) and persistent anomalies (such as liquid cooling system malfunctions). The preset temperature difference ratio threshold can be any value, selectable from 0.4 (40%), 0.5 (50%), or 0.6 (60%), etc. For example, if only 10% of the time points have temperature differences, it may be interference; if more than 40% of the time points have temperature differences, it is more likely a temperature difference fault. The preset time point number threshold refers to a pre-set critical value used to determine whether the total number of time points is sufficient. This threshold can be used to ensure the reliability and accuracy of the detection results. The preset time point number threshold can be any value, selectable from 500, 600, or 700, etc.

[0072] In one embodiment, for multiple first time points within a first time period, temperature data corresponding to each first time point can be obtained from battery temperature time-series data, and the maximum and minimum temperature parameter values ​​corresponding to each first time point can be determined based on the obtained temperature data. Further, the difference between the maximum and minimum temperature parameter values ​​can be determined, and this determined difference can be used as the battery temperature difference for each first time point. Further, for multiple battery temperature differences, the battery temperature differences can be compared with a preset temperature difference threshold; if the battery temperature difference is greater than the preset temperature difference threshold, this first time point can be used as a first target time point. Further, the number of time points for the first target time point and the total number of time points included in the first time period can be determined, and the ratio between the number of time points for the first target time point and the total number of time points can be determined, using this ratio as a temperature difference abnormality ratio. Further, the temperature difference abnormality ratio can be compared with a preset temperature difference ratio threshold, and the total number of time points can be compared with a preset time point number threshold. Therefore, if the temperature difference anomaly ratio is greater than or equal to a preset temperature difference ratio threshold, and the total number of time points is greater than or equal to a preset time point number threshold, the temperature difference fault detection result corresponding to the vehicle battery can be determined to indicate the presence of a temperature difference fault. If the temperature difference anomaly ratio is less than the preset temperature difference ratio threshold, and / or the total number of time points is less than the preset time point number threshold, the temperature difference fault detection result corresponding to the vehicle battery can be determined to indicate the absence of a temperature difference fault. Furthermore, if the temperature difference fault detection result indicates the presence of a temperature difference fault, the battery fault detection result corresponding to the vehicle battery can be determined to indicate the presence of a battery fault.

[0073] For example, the temperature difference fault detection process can be represented by the following formula: First, determine the operating mode of the liquid cooling system based on the ambient temperature conditions. Let the minimum temperature parameter value of the individual battery cell in the temperature data be... The maximum temperature parameter value is Then: Liquid cooling heating mode trigger condition: Liquid cooling mode trigger conditions: ;in, The first preset heating trigger threshold can be set to 6 degrees Celsius; The preset cooling trigger threshold can be set to 45 degrees Celsius. The threshold can be adjusted according to actual conditions.

[0074] Next, the time-continuous data segments are divided. To ensure the reliability of the detection, time continuity analysis is performed on the data that meets the trigger conditions. A preset interval threshold is set; when the time interval between two adjacent time points exceeds this preset interval threshold, the continuity is considered interrupted, and the data is divided into different continuous segments for independent analysis. Let the time series be... Calculate the time interval between adjacent time points: ;in, This indicates the first time point at which the preset liquid cooling trigger condition is met. Indicates a time interval; This indicates the later time point in the time sequence among two first time points associated with a time interval; This represents the earlier time point in the time sequence among two first time points associated with a time interval. When the time interval exceeds a first preset interval threshold, the data is considered to have a jump and needs to be segmented into independent data segments: if > Then at the first time point The data segment is divided into sections; among them, The first preset interval threshold can be set to 180 seconds. This parameter value takes into account situations such as abnormal data transmission.

[0075] Next, the abnormal characteristics of temperature differences are calculated, and for each first time period, a temperature difference sequence is calculated. Let the... The battery temperature difference at each first time point is: ;in, Indicates the first time point The corresponding maximum temperature parameter value; Indicates the first time point The corresponding minimum temperature parameter value; Indicates the first time point The battery temperature difference.

[0076] Next, the number of time points at which the battery temperature difference exceeds the preset temperature difference threshold, representing the first target time point, is calculated: ;in, This indicates the number of time points in the battery temperature difference that exceed the preset temperature difference threshold, representing the first target time point. This indicates the preset temperature difference threshold, which can be set to 3 degrees Celsius. This preset temperature difference threshold is determined based on statistical analysis of the battery pack temperature distribution under normal operating conditions, and the threshold can also be modified according to the actual situation.

[0077] Then, calculate the temperature difference abnormality ratio: ;in, Indicates the ratio of temperature difference abnormalities; This indicates the total number of time points in the first time period.

[0078] Finally, fault diagnosis and confirmation. Determining a temperature difference fault requires both conditions to be met simultaneously: Condition 1: The abnormal temperature difference ratio exceeds a threshold. ;in, This indicates the preset temperature difference ratio threshold, which can be set to 0.4. This parameter setting can be modified based on actual conditions. Condition 2: The data segment length meets the minimum requirement. ;in, This indicates the preset threshold for the number of time points, which can be set to 600 data points. This parameter can be modified according to actual conditions. When both of the above conditions are met simultaneously, it is determined to be a battery temperature difference fault, and the output fault type is "liquid cooling system pipe compression". The recommended measure is "check the liquid cooling system and treat the whole vehicle".

[0079] S230. Based on the battery fault detection results, determine the chassis collision identification results corresponding to the vehicle under test.

[0080] The technical solution of this invention acquires battery runtime timing data corresponding to the vehicle battery of the vehicle under test; wherein, the battery runtime timing data includes battery temperature timing data; further, a temperature difference fault detection subunit is used to process the battery temperature timing data to obtain battery fault detection results corresponding to the vehicle battery, accurately capturing the abnormal fault characteristics of battery temperature difference caused by chassis collision, providing a reliable temperature dimension judgment basis for vehicle battery fault detection, without the need for additional dedicated hardware, and balancing detection accuracy and cost economy.

[0081] Example 3

[0082] Figure 3 This is a flowchart of a vehicle chassis collision recognition method provided in Embodiment 3 of the present invention. Based on the foregoing embodiments, when the battery running timing data includes battery resistance timing data and the battery fault detection unit includes an insulation fault detection subunit, the insulation fault detection subunit can be used to process the battery resistance timing data to obtain the battery fault detection result. Specific implementation methods can be found in the technical solution of this embodiment. Technical terms that are the same as or similar to those in the above embodiments will not be repeated here. Figure 3 As shown, the method includes:

[0083] S310. Obtain battery runtime timing data corresponding to the vehicle battery of the vehicle under test; wherein, the battery runtime timing data includes battery resistance timing data.

[0084] S320: An insulation fault detection subunit is used to process the battery resistance timing data to obtain the battery fault detection results corresponding to the vehicle battery.

[0085] In this embodiment, the insulation fault detection subunit is used to process the battery resistance timing data, which may include at least one of the following methods.

[0086] Optionally, the insulation fault detection subunit includes an insulation fault detection model; the insulation fault detection subunit processes battery resistance time-series data to obtain battery fault detection results corresponding to the vehicle battery, including: inputting battery resistance time-series data into the insulation fault detection model, obtaining the output insulation fault detection results, and determining the battery fault detection results corresponding to the vehicle battery based on the insulation fault detection results.

[0087] The insulation fault detection model can be understood as a neural network model that can determine whether a vehicle battery has an insulation fault based on battery resistance time-series data. The insulation fault detection model can automatically extract insulation resistance features (such as the magnitude of insulation resistance drops, the duration of low resistance, and fluctuation frequency) from the battery resistance time-series data, perform feature analysis on the extracted insulation resistance features, and output a judgment result indicating whether an insulation fault exists. Generally, historical battery resistance data (including normal insulation resistance time-series data and insulation abnormality time-series data caused by faults such as aluminum shavings) is used as training samples to train the insulation fault detection model, enabling it to learn the differences between normal insulation patterns and faulty insulation patterns. The insulation fault detection model can employ a deep learning model of any structure; optionally, it can use at least one of the following: Long Short-Term Memory Networks and Random Forests.

[0088] In one embodiment, after obtaining the battery resistance time-series data, the battery resistance time-series data can be input into the insulation fault detection model. Furthermore, the insulation resistance features of the battery resistance time-series data can be extracted through the insulation fault detection model, and these features can be processed to obtain the output insulation fault detection result. Further, the insulation fault detection result can be used as the battery fault detection result corresponding to the vehicle battery.

[0089] Optionally, the insulation fault detection subunit includes a module integrating an insulation fault detection algorithm; the battery resistance time-series data includes the insulation resistance values ​​of the vehicle battery at multiple consecutive time points; the battery fault detection unit processes the battery runtime time-series data to obtain a battery fault detection result corresponding to the vehicle battery, including: when the battery fault detection unit includes an insulation fault detection subunit, for multiple time points in the battery resistance time-series data, normalizing the insulation resistance values ​​corresponding to the time points to obtain target insulation resistance values ​​corresponding to the time points; determining a second time period to be tested for insulation faults based on the target insulation resistance values ​​corresponding to the multiple time points and a preset insulation resistance threshold; determining the insulation fault detection result corresponding to the vehicle battery based on the duration of the second time period and a preset duration threshold, so as to determine the battery fault detection result corresponding to the vehicle battery based on the insulation fault detection result.

[0090] Battery resistance time-series data refers to the vehicle battery insulation resistance data recorded continuously in chronological order, including the original insulation resistance values ​​at multiple time points, with a timestamp for each data point (reflecting the time sequence). Battery resistance time-series data can be used to reflect changes in battery insulation performance over time. Insulation resistance values ​​at multiple consecutive time points refer to the original insulation resistance readings corresponding to each specific time node in the battery resistance time-series data. Normalization processing refers to standardizing the insulation resistance value at each time point to eliminate differences in insulation resistance benchmarks caused by variations in total battery voltage across different vehicle models (e.g., high-voltage vehicle batteries have higher absolute values ​​of normal insulation resistance), making the insulation performance of different vehicle models comparable. The target insulation resistance value refers to the insulation resistance value at each time point after normalization processing. The preset insulation resistance threshold refers to a pre-set critical value used to distinguish between normal and abnormal insulation. The preset insulation resistance threshold is an insulation resistance safety threshold; that is, if the target insulation resistance value is less than the preset insulation resistance threshold, the vehicle battery's insulation performance can be considered to have decreased to a dangerous level (i.e., exhibiting low resistance characteristics indicative of insulation failure). Optionally, the preset insulation resistance threshold can be any value, such as 50 ohms / volt, 60 ohms / volt, or 70 ohms / volt. The second time period can refer to a continuous period of time, selected from the battery resistance time series data, where the target insulation resistance value is consistently lower than the preset insulation resistance threshold. The second time period includes multiple consecutive second time points, with the time interval between two adjacent second time points being less than a second preset interval threshold; each second time point is the time point where its corresponding target insulation resistance value is lower than the preset insulation resistance threshold. All target insulation resistance values ​​at all second time points within the second time period are lower than the preset insulation resistance threshold, and the time interval between adjacent second time points is less than the second preset interval threshold. The duration of the second time period can refer to the total duration of the second time period from start to end. The preset duration threshold can refer to the critical value for determining whether the duration of the second time period is long enough to be considered a true fault. Generally, insulation damage caused by faults such as aluminum shavings piercing the blue film is permanent, and the low resistance value will persist; while low resistance values ​​caused by transient interference (such as poor sensor contact) are usually short-lived. Therefore, a preset duration threshold can be used for judgment.

[0091] Typically, when a vehicle chassis experiences a collision, aluminum shavings (such as fragments of the vehicle battery casing) generated by the impact pierce the insulating blue film on the surface of the battery cell. This causes the high-voltage components inside the cell to become conductive with the casing, triggering a fault mode characterized by a rapid and continuous decline in insulation performance. Its core characteristic is a sudden drop in insulation resistance from a normal level to a low level (e.g., below a preset insulation resistance threshold), which does not recover on its own, exhibiting a "persistently low resistance" characteristic. Therefore, battery resistance time-series data can be used to determine whether the vehicle battery exhibits this "persistently low resistance" characteristic, thereby allowing for the assessment of battery fault detection results.

[0092] In this embodiment, the method for determining the target insulation resistance value includes: for multiple time points in the battery resistance time series data, determining the target insulation resistance value corresponding to the time point based on the insulation resistance value corresponding to the time point and the total battery voltage of the vehicle battery.

[0093] In this embodiment, the method for determining the second time period includes: for multiple time points in the battery resistance time series data, if the target insulation resistance value corresponding to the time point is less than a preset insulation resistance threshold, the time point is taken as the second time point; if more than two second time points are determined, the time interval between two adjacent second time points is determined to obtain multiple time intervals; the multiple time intervals are compared with a second preset interval threshold in chronological order, and if the time interval is not less than the second preset interval threshold for the first time, the time interval not less than the second preset interval threshold is taken as the target time interval; based on the target time point that is earlier in the time series among the two second time points associated with the target time interval and at least one second time point located before the target time point, the second time period to be detected for insulation fault is determined.

[0094] In one embodiment, when the battery fault detection unit includes an insulation fault detection subunit, for multiple time points in the battery resistance time-series data, the product between the insulation resistance value corresponding to each time point and a preset parameter can be determined to obtain a first value. Then, the ratio between the first value and the total battery voltage of the vehicle battery is determined, and this ratio is used as the target insulation resistance value corresponding to the time point. Further, for multiple time points in the battery resistance time-series data, if the target insulation resistance value corresponding to a time point is less than a preset insulation resistance threshold, the time point is designated as a second time point; if two or more second time points are determined, the time interval between two adjacent second time points is determined, resulting in multiple time intervals; these multiple time intervals are sequentially compared with a second preset interval threshold according to their chronological order; if the first occurrence of a time interval not less than the second preset interval threshold is found, the time interval not less than the second preset interval threshold is designated as the target time interval; based on the target time point that appears earlier in the time sequence among the two second time points associated with the target time interval, and at least one second time point preceding the target time point, a second time period for insulation fault detection is determined. Further, the length of the second time period can be determined and compared with a preset duration threshold. Furthermore, if the time length is greater than or equal to a preset time threshold, it can be determined that the insulation fault detection result corresponding to the vehicle battery indicates the presence of an insulation fault.

[0095] For example, the insulation fault detection process can be represented by the following formula:

[0096] First: Insulation resistance normalization: To eliminate the impact of differences in battery capacity between different vehicle models, the insulation resistance is normalized. ;in, Indicates the target insulation resistance value; Indicates the insulation resistance value; This indicates the total voltage of the vehicle's battery; This indicates the preset parameters.

[0097] Next, low resistance range identification: set a preset insulation resistance threshold. ;in, .

[0098] The logic for identifying all time points below the preset insulation resistance threshold is as follows:

[0099]

[0100] in, For the first Low resistance value at a specific time point. Specifically, this means: if the target insulation resistance value at a certain time point is ≤ If the target insulation resistance value at that time point is greater than a certain value, it indicates that the target insulation resistance value is low and is marked as "1"; if the target insulation resistance value at a certain time point is greater than a certain value, it indicates that the target insulation resistance value is low and is marked as "1"; If the value is 0, it indicates that the target insulation resistance value at that time point is not a low resistance value, and it is marked as "0". The time point marked as low resistance value is taken as the second time point.

[0101] Next, continuous low-resistance segments are extracted: Consecutive low-resistance time periods are identified and used as the second time period. Let the start position of the second time period be `start` and the end position be `end`, then the duration (time length) of the second time period is: Simultaneously, the continuity of the data is checked to ensure that the time interval between any two adjacent second time points within the second time period does not exceed a second preset interval threshold. ;in, This indicates that a second time point is included. The time interval; This indicates the second preset interval threshold, which can be set to 120 seconds (this threshold can be adjusted according to actual conditions).

[0102] Finally, the determination of aluminum shavings piercing the blue film of the battery cell: if the length of the second time period exceeds the preset time threshold, it is determined to be an aluminum casing puncture fault. If this is detected, it is determined that aluminum shavings have entered and punctured the blue film of the battery cell. This indicates the preset duration threshold, which can be set to 300 seconds (this threshold can be adjusted according to actual conditions).

[0103] S330. Based on the battery fault detection results, determine the chassis collision identification result corresponding to the vehicle under test.

[0104] The technical solution of this invention acquires battery runtime timing data corresponding to the vehicle battery of the vehicle under test; wherein, the battery runtime timing data includes battery resistance timing data; further, an insulation fault detection subunit is used to process the battery resistance timing data to obtain battery fault detection results corresponding to the vehicle battery, accurately capturing the battery insulation abnormality fault characteristics caused by chassis collision, providing a reliable insulation dimension judgment basis for vehicle battery fault detection, without the need for additional dedicated hardware, and balancing detection effectiveness and cost economy.

[0105] Example 4

[0106] Figure 4 This is a flowchart of a vehicle chassis collision recognition method provided in Embodiment 4 of the present invention. Based on the foregoing embodiments, when the battery runtime timing data includes battery voltage timing data and the battery fault detection unit includes a differential pressure fault detection subunit, the differential pressure fault detection subunit can be used to process the battery voltage timing data to obtain the battery fault detection result. Specific implementation methods can be found in the technical solution of this embodiment. Technical terms that are the same as or similar to those in the above embodiments will not be repeated here. Figure 4 As shown, the method includes:

[0107] S410. Obtain battery runtime timing data corresponding to the vehicle battery of the vehicle under test; wherein, the battery runtime timing data includes battery voltage timing data.

[0108] S420: The differential pressure fault detection subunit processes the battery voltage timing data to obtain the battery fault detection results corresponding to the vehicle battery.

[0109] In this embodiment, the differential pressure fault detection subunit is used to process the battery voltage timing data, which may include at least one of the following methods.

[0110] Optionally, the differential pressure fault detection subunit includes a differential pressure fault detection model; the differential pressure fault detection subunit processes battery voltage time series data to obtain battery fault detection results corresponding to the vehicle battery, including: acquiring vehicle operating status data of the vehicle under test, inputting the vehicle operating status data and battery voltage time series data into the differential pressure fault detection model, obtaining the output differential pressure fault detection results, and determining the battery fault detection results corresponding to the vehicle battery based on the differential pressure fault detection results.

[0111] The differential pressure fault detection model can be understood as a neural network model that can determine whether a vehicle battery has a differential pressure fault based on battery voltage time-series data and vehicle operating status data. The differential pressure fault detection model can automatically extract key features (such as the peak differential pressure during charging, the rate of rise, and the correlation with self-discharge) from the battery voltage time-series data and vehicle operating status data, and perform feature analysis on the extracted key features to output a judgment result on whether a differential pressure fault exists. Generally, historical battery voltage data (including voltage time-series data during normal charging, abnormal voltage time-series data during cell compression faults, and the corresponding vehicle operating status) is used as training samples to train the differential pressure fault detection model, enabling it to learn the differences between normal and faulty differential pressure patterns. The differential pressure fault detection model can employ a deep learning model of any structure; optionally, it can use at least one of the following: temporal convolutional networks and gradient boosting trees.

[0112] In one embodiment, after acquiring battery voltage timing data and vehicle operating status data of the vehicle under test, the battery voltage timing data and vehicle operating status data can be input into the differential pressure fault detection model. Furthermore, the differential pressure fault detection model can extract key features from the battery voltage timing data and vehicle operating status data, and process these key features to obtain the output differential pressure fault detection result. Further, the differential pressure fault detection result can be used as the battery fault detection result corresponding to the vehicle battery.

[0113] Optionally, the temperature difference fault detection subunit includes a module integrating a temperature difference fault detection algorithm; the battery voltage time series data includes voltage data of the vehicle battery at multiple consecutive time points; the battery fault detection unit processes the battery operating time series data to obtain the battery fault detection result corresponding to the vehicle battery, including: when the battery fault detection unit includes a differential pressure fault detection subunit, acquiring the vehicle operating status time series data of the vehicle under test, determining the third time period for differential pressure fault detection based on the vehicle operating status time series data; and determining the voltage data corresponding to multiple third time points in the third time period. The differential pressure sequence corresponds to the third time period; wherein the differential pressure sequence includes battery voltage differences corresponding to multiple third time points respectively; the number of third target time points in the differential pressure sequence whose corresponding battery voltage differences are greater than a preset differential pressure threshold is determined, and the differential pressure abnormality ratio is determined based on the number of third target time points and the total number of time points in the third time period; the linear regression slope is determined based on the third time period, the time mean corresponding to the third time period, the differential pressure sequence, and the differential pressure mean corresponding to the differential pressure sequence; the differential pressure abnormality ratio and the linear regression slope are used to determine the differential pressure fault detection result corresponding to the vehicle battery.

[0114] Battery voltage time-series data refers to vehicle battery voltage information recorded continuously in chronological order, containing voltage data at multiple time points, including voltage parameter values ​​for multiple individual battery cells. Vehicle operating status time-series data refers to dynamic data reflecting the operating mode of the vehicle under test, recorded continuously in chronological order, including the vehicle operating status at each time point (such as "charging," "driving," "stationary," "charging complete," etc.) and the corresponding timestamp. Vehicle operating status time-series data can be used to filter out the corresponding time period under the vehicle's charging status (since differential pressure faults mainly manifest during vehicle charging). Generally, the determination of the vehicle's charging status is usually based on the vehicle operating status identifier in the vehicle operating status time-series data. For example, charging start identifier: if State_current (current charging status) = "charging" and State_previous (previous charging status) ≠ "charging," then it is marked as charging start; charging end identifier: if State_current ≠ "charging" and State_previous = "charging," then it is marked as charging end; or, if State_current = "charging complete," then it is marked as charging end. The third time period refers to the continuous time period during which the vehicle is in a charging state, selected from battery voltage time-series data. The third time period includes multiple consecutive third time points, with the time interval between two adjacent third time points being less than a third preset interval threshold. Each third time point corresponds to a point in time when the vehicle is in a charging state. The third preset interval threshold is a critical value used to determine whether the interval between adjacent third time points is too long, ensuring no significant interruption in the data within the third time period. The third preset interval threshold can be any value, such as 120 seconds, 150 seconds, or 180 seconds. If the time interval between two adjacent third time points is greater than the third preset interval threshold, it indicates a data break (e.g., sensor disconnection, brief vehicle power outage), and the time period needs to be divided into multiple third time periods (only the continuous portion with a time interval ≤ the third preset interval threshold is retained). The voltage difference sequence refers to the sequence of battery voltage differences at each third time point within the third time period, reflecting the dynamic changes in the voltage differences of individual battery cells during charging. The battery voltage difference can refer to the difference between the maximum and minimum voltage parameter values ​​of an individual battery cell at the third time point. The preset differential pressure threshold refers to the critical value used to determine whether the battery voltage difference at a single third time point is abnormal. It is determined by statistical analysis of differential pressure under normal charging conditions. If the battery voltage difference at a certain third time point is greater than the preset differential pressure threshold, it is considered that there is a differential pressure abnormality at that third time point. The time mean of the third time period refers to the average of the timestamps of all third time points within the third time period, which is the benchmark time point for linear regression calculation. The differential pressure mean corresponding to the differential pressure sequence refers to the average of all battery voltage differences in the differential pressure sequence, which is the benchmark differential pressure for linear regression calculation.The slope of linear regression can refer to a parameter calculated through linear regression that reflects the rate of change of pressure difference over time.

[0115] In this embodiment, the method for determining the voltage difference sequence includes: for multiple third time points in the third time period, determining the maximum voltage parameter value and the minimum voltage parameter value from the voltage data of the third time point, and taking the difference between the maximum voltage parameter value and the minimum voltage parameter value as the battery voltage difference value of the third time point; arranging the battery voltage differences of multiple third time points in chronological order to obtain the voltage difference sequence.

[0116] In this embodiment, the differential pressure fault detection result corresponding to the vehicle battery is determined based on the differential pressure anomaly ratio and the linear regression slope, including: determining the self-discharge anomaly detection result corresponding to the vehicle battery; and determining that the differential pressure fault detection result corresponding to the vehicle battery exists when the differential pressure anomaly ratio is greater than or equal to a preset differential pressure ratio threshold, the linear regression slope is greater than a preset slope threshold, and the self-discharge anomaly detection result is a pass.

[0117] In one embodiment, when the battery fault detection unit includes a differential pressure fault detection subunit, the vehicle operating status time-series data of the vehicle under test is acquired. Based on the vehicle operating status time-series data, multiple consecutive third time points in the charging state are determined, and a third time period is determined based on these multiple consecutive third time points. Further, for the multiple third time points within the third time period, voltage data corresponding to the third time points can be obtained from the battery voltage time-series data, and the maximum and minimum voltage parameter values ​​corresponding to the third time points are determined based on the acquired voltage data. Further, the difference between the maximum and minimum voltage parameter values ​​can be determined, and this determined difference is used as the battery voltage difference at the third time point. The battery voltage differences at multiple third time points are arranged in chronological order to obtain a differential pressure sequence. Further, for the multiple battery voltage differences in the differential pressure sequence, the battery voltage differences are compared with a preset differential pressure threshold. If it is determined that the battery voltage difference is greater than the preset differential pressure threshold, this third time point can be used as the third target time point. Furthermore, the number of time points at the third target time point and the total number of time points included in the third time period can be determined, and the ratio between the number of time points at the third target time point and the total number of time points can be determined. This ratio is used as the differential pressure anomaly ratio. Further, the time mean corresponding to the third time period and the differential pressure mean corresponding to the differential pressure sequence can be determined, and the linear regression slope can be determined based on the third time period, the time mean corresponding to the third time period, the differential pressure sequence, and the differential pressure mean corresponding to the differential pressure sequence. Further, a self-discharge anomaly detection algorithm can be used to determine the self-discharge anomaly detection result corresponding to the vehicle battery. If the differential pressure anomaly ratio is greater than or equal to a preset differential pressure ratio threshold, the linear regression slope is greater than a preset slope threshold, and the self-discharge anomaly detection result is a pass, then the differential pressure fault detection result corresponding to the vehicle battery is determined to be a differential pressure fault. Furthermore, if the differential pressure fault detection result is determined to be a differential pressure fault, then the battery fault detection result corresponding to the vehicle battery is determined to be a battery fault.

[0118] For example, the differential pressure fault detection process can be represented by the following formula:

[0119] First, charging segment identification and extraction: The charging process is identified based on the vehicle's operating status time-series data. The charging status is determined based on the vehicle's operating status identifiers: Charging start identifier: If State_current (current charging status) = "charging" and State_previous (previous charging status) ≠ "charging", then charging is marked as started; Charging end identifier: If State_current ≠ "charging" and State_previous = "charging", then charging is marked as ended; or, if State_current = "charging complete", then charging is marked as ended. Charging segment pairing: A nearest neighbor pairing strategy is used. For each charging start time, the nearest subsequent charging end time is found to form a complete charging segment, which is used as the third time period.

[0120] Next, voltage difference calculation and threshold verification: For each third time period, calculate the voltage difference sequence of the individual cell voltages. ;in, Indicates the first The battery voltage difference at a third time point; This represents the maximum voltage parameter value corresponding to the third time point; This represents the minimum voltage parameter value corresponding to the third time point.

[0121] Next, calculate the proportion of high pressure differential time points: ;in, This indicates the preset differential pressure threshold, which can be set to 30 millivolts; This indicates the total number of time points in the third time period; This indicates the number of time points at which the corresponding battery voltage difference is greater than the preset voltage difference threshold, representing the third target time point. This indicates the abnormal ratio of pressure difference.

[0122] Next, the high voltage differential ratio determination condition: if Then the pressure difference abnormality condition is satisfied; among which, This indicates the preset differential pressure ratio threshold, which can be set to 0.5 and adjusted according to actual conditions.

[0123] Next, the upward trend of the differential pressure was analyzed: linear regression was used to analyze the changing trend of the differential pressure. Let the time series of the third time period be... The corresponding pressure difference sequence is Calculate the slope of the linear regression: ;in, The slope of the linear regression; This represents the average time value corresponding to the third time period; Indicates the third time period A third point in time; This represents the average pressure difference corresponding to the pressure difference sequence; Indicates the pressure difference sequence with the first The battery voltage difference corresponding to the third time point. Criteria for determining an upward trend: If... Then, there is an upward trend in the pressure differential; among which, This indicates the preset slope threshold, which can be set to 0.1mV / s. The threshold can be adjusted according to the actual situation.

[0124] Next, self-discharge anomaly detection: various self-discharge anomaly detection algorithms can be used, such as collecting preset capacity data of charging and discharging segments, comparing differences and upward trends, etc., which will not be elaborated here.

[0125] Finally, the final determination of a differential pressure fault requires the following conditions to be met simultaneously: Condition 1: Abnormal differential pressure conditions are met; Condition 2: An upward trend in differential pressure exists; Condition 3: Self-discharge anomaly detection passes. When all three conditions are met simultaneously, it is determined to be a differential pressure fault, and the output fault type is "short circuit caused by internal cell compression deformation," with the recommended measure being "replace the battery pack."

[0126] S430. Based on the battery fault detection results, determine the chassis collision identification results corresponding to the vehicle under test.

[0127] The technical solution of this invention acquires battery runtime timing data corresponding to the vehicle battery of the vehicle under test; wherein, the battery runtime timing data includes battery voltage timing data; further, a differential pressure fault detection subunit is used to process the battery voltage timing data to obtain battery fault detection results corresponding to the vehicle battery, accurately capturing the abnormal fault characteristics of battery voltage difference caused by chassis collision, providing a reliable voltage dimension judgment basis for vehicle battery fault detection, without the need for additional dedicated hardware, and balancing detection accuracy and cost economy.

[0128] Example 5

[0129] Figure 5 This is a structural schematic diagram of a vehicle chassis collision recognition device provided in Embodiment 5 of the present invention. Figure 5 As shown, the device includes: a battery data acquisition module 510, a battery fault detection module 520, and a chassis collision recognition module 530. The battery data acquisition module 510 acquires battery runtime sequence data corresponding to the vehicle battery of the vehicle under test; the battery fault detection module 520 processes the battery runtime sequence data using a battery fault detection unit to obtain a battery fault detection result corresponding to the vehicle battery; and the chassis collision recognition module 530 determines the chassis collision recognition result corresponding to the vehicle under test based on the battery fault detection result.

[0130] The technical solution of this invention provides core raw data support for subsequent fault detection by acquiring battery runtime sequence data corresponding to the vehicle battery of the vehicle under test. No additional dedicated detection hardware is required; reliable and timely judgment of chassis collision events can be achieved based solely on the battery runtime sequence data. Furthermore, by processing the battery runtime sequence data using a battery fault detection unit, battery fault detection results corresponding to the vehicle battery are obtained. Targeted analysis of the battery runtime sequence data accurately identifies battery fault characteristics caused by chassis collisions, providing reliable and accurate core evidence for subsequent chassis collision event judgment and avoiding false alarms and missed alarms. Moreover, by determining the chassis collision identification result corresponding to the vehicle under test based on the battery fault detection result, the effect of accurately identifying chassis collisions based on the battery fault detection result is achieved. Hidden chassis collisions can be accurately captured without additional dedicated hardware, providing timely and reliable judgment evidence for vehicle safety maintenance. The technical solution of this invention addresses the problems of high hardware costs, low real-time performance and accuracy of chassis collision recognition, which affect the vehicle's response speed to chassis collision events. It achieves accurate identification of chassis collision events based solely on the vehicle's battery runtime sequence data without requiring additional dedicated hardware. This reduces the cost of chassis collision recognition, improves its real-time performance and detection accuracy, effectively accelerates the vehicle's response speed to chassis collision events, and ensures battery safety and driving reliability.

[0131] Optionally, the battery fault detection unit includes at least one of a temperature difference fault detection subunit, an insulation fault detection subunit, and a pressure difference fault detection subunit; the battery operating timing data includes at least one of battery temperature timing data, battery resistance timing data, and battery voltage timing data; the temperature difference fault detection subunit is used to perform temperature difference fault detection on the vehicle battery based on the battery temperature timing data; the insulation fault detection subunit is used to perform insulation fault detection on the vehicle battery based on the battery resistance timing data; and the pressure difference fault detection subunit is used to perform pressure difference fault detection on the vehicle battery based on the battery voltage timing data.

[0132] Optionally, the battery temperature time series data includes the temperature data of the vehicle battery at multiple consecutive time points; the battery fault detection module 520 includes: a first time period determination unit, a battery temperature difference determination unit, a temperature difference abnormality ratio determination unit, and a temperature difference fault detection result determination unit. The system includes a first time period determination unit, used when the battery fault detection unit includes a temperature difference fault detection unit, to determine a first time period for temperature difference fault detection based on battery temperature time series data; wherein the first time period includes multiple consecutive first time points, and the time interval between two adjacent first time points is less than a first preset interval threshold; the first time point is the time point in the battery temperature time series data where the corresponding temperature data meets a preset liquid cooling trigger condition; a battery temperature difference determination unit, used to determine the battery temperature difference at each of the multiple first time points in the first time period based on the temperature data corresponding to that first time point; a temperature difference anomaly ratio determination unit, used to determine the number of first target time points among the multiple battery temperature differences that are greater than a preset temperature difference threshold, and to determine the temperature difference anomaly ratio based on the number of first target time points and the total number of time points in the first time period; and a temperature difference fault detection result determination unit, used to determine the temperature difference fault detection result corresponding to the vehicle battery based on the temperature difference anomaly ratio and the total number of time points, so as to determine the battery fault detection result corresponding to the vehicle battery based on the temperature difference fault detection result.

[0133] Optionally, the vehicle battery includes multiple individual cells, and the temperature data includes temperature parameter values ​​of multiple individual cells. A first time period determination unit is specifically used to determine, for multiple time points in the battery temperature time series data, if a time point meets a preset liquid cooling trigger condition based on the temperature data corresponding to that time point, then that time point is designated as a first time point. If two or more first time points are determined, the time interval between two adjacent first time points is determined, resulting in multiple time intervals. These multiple time intervals are then compared sequentially with a first preset interval threshold. If the first occurrence of a time interval not less than the first preset interval threshold, the time interval not less than the preset interval threshold is designated as a target time interval. Based on the target time point that appears earlier in the time series among the two first time points associated with the target time interval, and at least one first time point preceding the target time point, a first time period for temperature difference fault detection is determined.

[0134] Optionally, the temperature difference fault detection result determination unit is specifically used to determine that the temperature difference fault detection result corresponding to the vehicle battery is a temperature difference fault when the temperature difference abnormality ratio is greater than or equal to a preset temperature difference ratio threshold and the total number of time points is greater than or equal to a preset time point number threshold.

[0135] Optionally, the battery resistance time-series data includes the insulation resistance values ​​of the vehicle battery at multiple consecutive time points. The battery fault detection module 520 includes: an insulation resistance normalization unit, a second time period determination unit, and an insulation fault detection result determination unit. The insulation resistance normalization unit, when the battery fault detection unit includes an insulation fault detection subunit, normalizes the insulation resistance values ​​corresponding to multiple time points in the battery resistance time-series data to obtain the target insulation resistance value corresponding to each time point. The second time period determination unit determines the second time period for insulation fault detection based on the target insulation resistance values ​​corresponding to multiple time points and a preset insulation resistance threshold. The second time period includes multiple consecutive second time points, and the time interval between two adjacent second time points is less than a second preset interval threshold. Each second time point is a time point where its corresponding target insulation resistance value is less than the preset insulation resistance threshold. The insulation fault detection result determination unit determines the insulation fault detection result corresponding to the vehicle battery based on the duration of the second time period and a preset duration threshold, thereby determining the battery fault detection result corresponding to the vehicle battery.

[0136] Optionally, the battery voltage time-series data includes voltage data of the vehicle battery at multiple consecutive time points; the battery fault detection module 520 includes: a third time period determination unit, a differential pressure sequence determination unit, a differential pressure abnormality ratio determination unit, a linear regression slope determination unit, and a differential pressure fault detection result determination unit. The third time period determination unit, when the battery fault detection unit includes a differential pressure fault detection subunit, acquires the vehicle operating status time-series data of the vehicle under test, and determines the third time period for differential pressure fault detection based on the vehicle operating status time-series data; wherein the third time period includes multiple consecutive third time points, and the time interval between two adjacent third time points is less than a third preset interval threshold; the third time point is the time point when the vehicle's operating status is charging; the differential pressure sequence determination unit is used to determine the differential pressure sequence corresponding to the third time period based on the voltage data corresponding to the multiple third time points in the third time period; wherein the differential pressure sequence includes... The system includes: a battery voltage difference corresponding to multiple third time points; a voltage difference anomaly ratio determination unit, used to determine the number of third target time points in the voltage difference sequence whose corresponding battery voltage difference is greater than a preset voltage difference threshold, and to determine the voltage difference anomaly ratio based on the number of third target time points and the total number of time points in the third time period; a linear regression slope determination unit, used to determine the linear regression slope based on the third time period, the time mean corresponding to the third time period, the voltage difference sequence, and the voltage difference mean corresponding to the voltage difference sequence; and a voltage difference fault detection result determination unit, used to determine the voltage difference fault detection result corresponding to the vehicle battery based on the voltage difference anomaly ratio and the linear regression slope.

[0137] Optionally, the chassis collision recognition module 530 is specifically used to determine that a chassis collision event has occurred if the battery fault detection result indicates that a battery fault exists; and to determine that no chassis collision event has occurred if the battery fault detection result indicates that no battery fault exists.

[0138] The vehicle chassis collision recognition device provided in this embodiment of the invention can execute the vehicle chassis collision recognition method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0139] Example 6

[0140] Figure 6 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0141] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0142] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0143] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as vehicle chassis collision recognition methods.

[0144] In some embodiments, the vehicle chassis collision identification method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the vehicle chassis collision identification method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the vehicle chassis collision identification method by any other suitable means (e.g., by means of firmware).

[0145] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device. Computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a dedicated computer, or other programmable data processing apparatus such that, when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. Computer programs can be executed entirely on a machine, partially on a machine, or as standalone software packages, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0146] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0147] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input). The systems and techniques described herein can be implemented in computing systems including back-end components (e.g., as a data server), or computing systems including middleware components (e.g., an application server), or computing systems including front-end components (e.g., a user computer with a graphical user interface or web browser through which the user interacts with embodiments of the systems and techniques described herein), or computing systems including any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), target blockchain networks, and the Internet.

[0148] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0149] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0150] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0151] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for identifying a vehicle chassis impact, characterized in that The method comprises: obtaining battery operation time sequence data corresponding to a vehicle battery of a vehicle to be tested; processing the battery operation time sequence data by using a battery fault detection unit to obtain a battery fault detection result corresponding to the vehicle battery; determining a chassis collision recognition result corresponding to the vehicle to be tested according to the battery fault detection result.

2. The vehicle chassis bump detection method according to claim 1, characterized by, The battery fault detection unit comprises at least one of a temperature difference fault detection subunit, an insulation fault detection subunit and a pressure difference fault detection subunit; the battery operation time sequence data comprises at least one of battery temperature time sequence data, battery resistance time sequence data and battery voltage time sequence data; The temperature difference fault detection subunit is configured to perform temperature difference fault detection on the vehicle battery according to the battery temperature time sequence data; The insulation fault detection subunit is configured to perform insulation fault detection on the vehicle battery according to the battery resistance time sequence data; The pressure difference fault detection subunit is configured to perform pressure difference fault detection on the vehicle battery according to the battery voltage time sequence data.

3. The vehicle underbody impact detection method according to claim 2, characterized by, The battery temperature time sequence data comprises temperature data of the vehicle battery at a plurality of consecutive time points; the processing of the battery operation time sequence data by using the battery fault detection unit to obtain the battery fault detection result corresponding to the vehicle battery comprises: in the case where the battery fault detection unit comprises a temperature difference fault detection unit, determining a first time period to be subjected to temperature difference fault detection according to the battery temperature time sequence data; wherein the first time period comprises a plurality of consecutive first time points, and the time interval between adjacent two first time points is less than a first preset interval threshold; the first time point is a time point in the battery temperature time sequence data, and the temperature data corresponding to the time point satisfies a preset liquid cooling trigger condition; for a plurality of first time points in the first time period, determining a battery temperature difference value of the first time point according to the temperature data corresponding to the first time point; determining the number of time points of a first target time point in a plurality of battery temperature difference values greater than a preset temperature difference threshold, and determining a temperature difference abnormality ratio value according to the number of time points of the first target time point and the total number of time points of the first time period; determining a temperature difference fault detection result corresponding to the vehicle battery according to the temperature difference abnormality ratio value and the total number of time points, and determining a battery fault detection result corresponding to the vehicle battery based on the temperature difference fault detection result.

4. The vehicle underbody impact detection method according to claim 3, characterized by, The vehicle battery comprises a plurality of single cells, and the temperature data comprises temperature parameter values of a plurality of single cells; the determination of the first time period to be subjected to temperature difference fault detection according to the battery temperature time sequence data comprises: for a plurality of time points in the battery temperature time sequence data, if it is determined that the time point satisfies a preset liquid cooling trigger condition according to the temperature data corresponding to the time point, the time point is taken as a first time point; in the case where two or more first time points are determined, determining the time interval between adjacent two first time points to obtain a plurality of time intervals; The plurality of time intervals are sequentially compared with a first preset interval threshold value according to time sequence, and in a case where the time interval is not less than the first preset interval threshold value for the first time, the time interval not less than the preset interval threshold value is taken as a target time interval; A first time period to be subjected to temperature difference fault detection is determined according to a target time point in time sequence earlier among the two first time points associated with the target time interval and at least one first time point before the target time point.

5. The vehicle chassis fender detection method of claim 3, wherein, The determination of the temperature difference fault detection result corresponding to the vehicle battery according to the temperature difference abnormality ratio and the total number of time points comprises: In a case where the temperature difference abnormality ratio is greater than or equal to a preset temperature difference proportion threshold value and the total number of time points is greater than or equal to a preset number of time point threshold value, it is determined that the temperature difference fault detection result corresponding to the vehicle battery is that there is a temperature difference fault.

6. The vehicle chassis fender detection method of claim 2, wherein, The battery resistance time sequence data comprises insulation resistance values of the vehicle battery at a plurality of continuous time points; The processing of the battery operation time sequence data by the battery fault detection unit to obtain the battery fault detection result corresponding to the vehicle battery comprises: In a case where the battery fault detection unit comprises an insulation fault detection subunit, the insulation resistance values corresponding to the time points are normalized to obtain target insulation resistance values corresponding to the time points for the plurality of time points in the battery resistance time sequence data; A second time period to be subjected to insulation fault detection is determined according to the target insulation resistance values corresponding to the plurality of time points and a preset insulation resistance threshold value; the second time period comprises a plurality of continuous second time points, and a time interval between adjacent two second time points is less than a second preset interval threshold value; the second time point is a time point whose corresponding target insulation resistance value is less than the preset insulation resistance threshold value; A determination of an insulation fault detection result corresponding to the vehicle battery is performed according to a time length of the second time period and a preset time length threshold value, so as to determine the battery fault detection result corresponding to the vehicle battery based on the insulation fault detection result.

7. The vehicle chassis bump identification method of claim 2, the battery voltage time series data comprising voltage data of the vehicle battery at a plurality of consecutive time points. The processing of the battery operation time sequence data by the battery fault detection unit to obtain the battery fault detection result corresponding to the vehicle battery comprises: In a case where the battery fault detection unit comprises a pressure difference fault detection subunit, vehicle operation state time sequence data of the vehicle to be tested is acquired, and a third time period to be subjected to pressure difference fault detection is determined according to the vehicle operation state time sequence data; the third time period comprises a plurality of continuous third time points, and a time interval between adjacent two third time points is less than a third preset interval threshold value; the third time point is a time point whose corresponding vehicle operation state is a charging state; A pressure difference sequence corresponding to the third time period is determined according to voltage data corresponding to the plurality of third time points in the third time period; the pressure difference sequence comprises battery voltage difference values corresponding to the plurality of third time points respectively. determining a pressure difference abnormality ratio value according to the third target time point quantity and a total time point quantity of the third time period; determining a linear regression slope according to the third time period, a time mean value corresponding to the third time period, the pressure difference sequence, and a pressure difference mean value corresponding to the pressure difference sequence; determining a pressure difference fault detection result corresponding to the vehicle battery according to the pressure difference abnormality ratio value and the linear regression slope, to determine a battery fault detection result corresponding to the vehicle battery based on the pressure difference fault detection result.

8. The vehicle chassis fender detection method of claim 1, wherein, The determining of the chassis collision identification result corresponding to the vehicle to be tested according to the battery fault detection result comprises: in a case where the battery fault detection result is that there is a battery fault, determining that the chassis collision identification result corresponding to the vehicle is that a chassis collision event occurs; in a case where the battery fault detection result is that there is no battery fault, determining that the chassis collision identification result corresponding to the vehicle is that no chassis collision event occurs.

9. A vehicle underbody knock detection device characterized by comprising: comprise: a battery data acquisition module configured to acquire battery operation time sequence data corresponding to a vehicle battery of a vehicle to be tested; a battery fault detection module configured to process the battery operation time sequence data by using a battery fault detection unit to obtain a battery fault detection result corresponding to the vehicle battery; a chassis collision identification module configured to determine a chassis collision identification result corresponding to the vehicle to be tested according to the battery fault detection result.

10. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the vehicle chassis collision identification method in any one of claims 1-8.

Images