Electric vehicle battery module operation safety real-time monitoring and early warning system based on internet of things

Abstract

The present application relates to the technical field of automobile battery safety monitoring, in particular to an electric vehicle battery module operation safety real-time monitoring and early warning system based on the Internet of Things, comprising a multi-dimensional sensing module, a data preprocessing module, an Internet of Things transmission module, an analysis and decision module, an early warning execution module, a safety protection module and a storage and traceability module; the multi-dimensional sensing module collects battery operation state data; the data preprocessing module is used to solve the problems of large noise, chaotic time sequence and insufficient precision of original sensing data; the analysis and decision module analyzes the battery operation state, identifies hidden troubles and determines the risk level; the early warning execution module executes differentiated and graded early warning operations; the safety protection module executes active safety protection operations; the storage and traceability module realizes full-time sequence data retention and fault traceability; the system relies on a multi-algorithm fusion artificial intelligence model to realize accurate estimation of the battery state, early prediction of thermal runaway and analysis of accumulated fault risks, and greatly reduces the false alarm rate and the missed alarm rate.

Description

Technical Field

[0001] This invention relates to the field of automotive battery safety monitoring technology, and in particular to an IoT-based real-time monitoring and early warning system for the operational safety of electric vehicle battery modules. Background Technology

[0002] The power battery module is the core energy storage and power component of electric vehicles, and its operational safety directly determines the driving safety of the vehicle and the personal and property safety of users. Currently, electric vehicle power batteries generally suffer from problems such as long-term charge-discharge cycles, operation in high and low temperature environments, vibration and shock, and uniform degradation of individual cells. These problems can easily lead to safety faults such as overheating of individual cells, internal short circuits, thermal runaway, bulging and leakage, which can then lead to serious safety accidents such as vehicle fires and explosions.

[0003] Existing electric vehicle battery monitoring systems mostly rely on onboard BMS to monitor basic voltage, current, and temperature, which has several technical shortcomings: First, the monitoring data dimensions are limited, failing to capture early latent faults such as gas generation, minor vibrations, and internal resistance decay within the battery; they can only identify visible faults, resulting in severe warning lag. Second, data processing capabilities are weak; the onboard unit does not effectively preprocess the raw sensor data, and noisy data easily leads to false alarms and missed alarms. Third, the warning response mode is simplistic, lacking a tiered warning and layered protection mechanism, resulting in excessive intervention for minor anomalies and untimely response to serious risks. Fourth, data traceability is lacking; it is impossible to retain full-time operational data, making it difficult to accurately pinpoint the cause after a fault occurs.

[0004] Therefore, there is an urgent need for an IoT-based real-time monitoring and early warning system for the operational safety of electric vehicle battery modules to address the aforementioned shortcomings and comprehensively improve the operational safety assurance capabilities of electric vehicle batteries. Summary of the Invention

[0005] The purpose of this invention is to provide an IoT-based real-time monitoring and early warning system for the operational safety of electric vehicle battery modules, aiming to predict hidden battery faults and aging risks in advance, prevent battery thermal runaway safety accidents, and improve the operational safety and reliability of electric vehicles.

[0006] To achieve the above objectives, this invention provides an IoT-based real-time monitoring and early warning system for the operational safety of electric vehicle battery modules. It includes a multi-dimensional sensing module, a data preprocessing module, an IoT transmission module, an analysis and decision-making module, an early warning execution module, a security protection module, and a storage and traceability module; The multi-dimensional sensing module is used to collect battery operating status data from all directions; The data preprocessing module is used to solve the problems of high noise, disordered timing, and insufficient accuracy in the raw sensor data; The IoT transmission module is used to enable two-way data interaction between the vehicle-mounted terminal and the cloud platform; The analysis and decision-making module is used to deeply analyze the battery's operating status, identify potential faults, and determine the risk level. The early warning execution module performs differentiated and graded early warning operations based on the three-level risk instructions issued from the cloud. The security protection module executes proactive security protection operations based on cloud-based control commands. The storage traceability module is used to achieve full-time data retention and fault traceability.

[0007] The IoT-based real-time monitoring and early warning system for the operation safety of electric vehicle battery modules also includes a battery health prediction module and a charging safety management module. The battery health prediction module, based on the battery's full life cycle time-series data, enables early prediction of the battery's long-term aging trend, lifespan decay, and failure probability. The charging safety management module is used for safety monitoring and protection of electric vehicles in all scenarios, including slow charging, fast charging, and emergency charging.

[0008] The IoT-based real-time monitoring and early warning system for the safe operation of electric vehicle battery modules also includes a diagnostic and repair module and a device self-test module. The diagnosis and repair module is used for automatic diagnosis and autonomous repair of minor battery faults; The device self-test module is used to monitor the operating status of all hardware, software and link devices in the system in real time.

[0009] The multidimensional sensing module includes an electrical parameter acquisition unit, a temperature acquisition unit, an environmental acquisition unit, and a position and attitude unit. The electrical parameter acquisition unit is used to acquire battery cell voltage, total battery pack voltage, charging and discharging current, and dynamic internal resistance parameters in real time, and to capture electrical fault characteristics. The temperature acquisition unit is used to collect multi-point temperature data and temperature difference in real time; The environmental acquisition unit is used to collect real-time data on the concentration of combustible gas inside the battery pack, the amplitude and frequency of operating vibration, and the ambient temperature and humidity, in order to detect hidden battery faults. The position and attitude unit is used to collect tilt and bump attitude data of the battery module.

[0010] The data preprocessing module includes a noise reduction unit, an outlier removal unit, a timing calibration unit, and a parameter compensation unit. The noise reduction processing unit is used to filter out high-frequency noise data generated by vehicle driving electromagnetic interference and sensor jitter. The outlier removal unit removes extreme abnormal data caused by sensor malfunctions and transient interference based on the threshold range of normal battery operation parameters. The timing calibration unit is used to perform time stamp alignment on the data collected by the multi-dimensional sensing module. The parameter compensation unit performs dynamic compensation and calibration on parameters that are susceptible to environmental influences, based on temperature and humidity environmental parameters.

[0011] The analysis and decision-making module includes a battery state estimation module, a fault identification module, a thermal runaway early warning module, and a fault assessment module. The battery state estimation module is used to assess the degree of battery aging and capacity decay trend in real time. The fault identification module, based on a dynamic adaptive threshold, dynamically adjusts the judgment criteria in conjunction with battery operating conditions, ambient temperature, and charge / discharge status to identify various faults such as single-cell overvoltage, undervoltage, overcurrent, overtemperature, excessive temperature difference, abnormal internal resistance, and excessive gas production. The thermal runaway early warning module constructs a multi-parameter fusion thermal runaway prediction algorithm based on the temperature change rate, gas concentration increment, and internal resistance abrupt change characteristics to identify early thermal runaway risks in advance. The fault assessment module analyzes the frequency and duration of battery anomalies based on time-series data to assess hidden risks in the battery and enable early fault prediction.

[0012] The storage traceability module includes a storage unit and a source module unit; The storage unit is used to cache raw sensor data, preprocessed data, early warning records, protection operation logs, analysis results, and operation and maintenance records in real time. The tracing unit retrieves corresponding data based on time, vehicle number, and fault type to locate the cause of the fault and the fault propagation process.

[0013] This invention relates to an IoT-based real-time monitoring and early warning system for the operational safety of electric vehicle battery modules. The system utilizes a multi-dimensional sensing module to collect battery operational status data from all angles. A data preprocessing module addresses the issues of high noise, inconsistent timing, and insufficient accuracy in the raw sensor data. An IoT transmission module enables bidirectional data interaction between the vehicle-mounted terminal and the cloud platform. An analysis and decision-making module deeply analyzes the battery's operational status, identifies potential faults, and determines the risk level. An early warning execution module executes differentiated, graded early warning operations based on three-level risk commands issued from the cloud. A safety protection module executes proactive safety protection operations based on cloud-based control commands. A storage and traceability module enables full-time data retention and fault tracing. The system relies on a multi-algorithm fusion artificial intelligence model to achieve accurate battery status estimation, early prediction of thermal runaway, and analysis of accumulated fault risks. It dynamically and adaptively determines thresholds, significantly reducing false alarm and missed alarm rates. By integrating multi-dimensional sensor data on electrical, temperature, gas, vibration, and attitude, it can accurately capture early latent and overt battery faults, completely solving the problems of missed alarms and delayed warnings in traditional systems. It constructs a three-level risk classification response mechanism, matching differentiated warnings and protective actions to avoid excessive intervention in minor anomalies that affect the user experience, while ensuring rapid emergency response to serious risks, forming a closed loop of monitoring-analysis-early warning-protection. Through full-time data retention, it supports accurate fault tracing and provides data support for the full life cycle management of batteries. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0015] Figure 1 This is a schematic diagram of the real-time monitoring and early warning system for the operational safety of electric vehicle battery modules based on the Internet of Things provided by this invention.

[0016] Figure 2 This is a schematic diagram of the sensing module of the IoT-based real-time monitoring and early warning system for the operation safety of electric vehicle battery modules provided by the present invention.

[0017] Figure 3 This is a schematic diagram of the data preprocessing module of the IoT-based real-time monitoring and early warning system for the operation safety of electric vehicle battery modules provided by the present invention.

[0018] Figure 4 This is a schematic diagram of the data preprocessing module of the IoT-based real-time monitoring and early warning system for the operation safety of electric vehicle battery modules provided by the present invention.

[0019] Figure 5 This is a schematic diagram of the storage and traceability module of the IoT-based real-time monitoring and early warning system for the operation safety of electric vehicle battery modules provided by the present invention.

[0020] In the diagram: 1-Multidimensional sensing module, 2-Data preprocessing module, 3-IoT transmission module, 4-Analysis and decision-making module, 5-Early warning execution module, 6-Safety protection module, 7-Storage traceability module, 8-Battery health prediction module, 9-Charging safety management and control module, 10-Diagnosis and repair module, 11-Equipment self-test module, 101-Electrical parameter acquisition unit, 102-Temperature acquisition unit, 103-Environmental acquisition unit, 104-Position and attitude unit, 201-Noise reduction processing unit, 202-Outlier removal unit, 203-Timing calibration unit, 204-Parameter compensation unit, 401-Battery state estimation module, 402-Fault identification module, 403-Thermal runaway early warning module, 404-Fault analysis module, 71-Storage unit, 72-Source module unit. Detailed Implementation

[0021] The embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, but should not be construed as limiting the present invention.

[0022] Please see Figures 1 to 5 This invention provides an IoT-based real-time monitoring and early warning system for the operational safety of electric vehicle battery modules, comprising a multi-dimensional sensing module 1, a data preprocessing module 2, an IoT transmission module 3, an analysis and decision-making module 4, an early warning execution module 5, a safety protection module 6, and a storage and traceability module 7. The multi-dimensional sensing module 1 is used to collect battery operating status data from all directions; The data preprocessing module 2 is used to solve the problems of high noise, disordered timing, and insufficient accuracy of the original sensor data; The IoT transmission module 3 is used to realize two-way data interaction between the vehicle terminal and the cloud platform; The analysis and decision module 4 is used to deeply analyze the battery operating status, identify potential faults, and determine the risk level. The early warning execution module 5 executes differentiated and graded early warning operations based on the three-level risk instructions issued by the cloud. The security protection module 6 executes proactive security protection operations based on cloud control commands. The storage traceability module 7 is used to realize full-time data retention and fault traceability.

[0023] In this implementation scheme, the multi-dimensional sensing module 1 collects battery operating status data from all directions; the data preprocessing module 2 is used to solve the problems of high noise, disordered timing, and insufficient accuracy of the raw sensing data; the IoT transmission module 3 realizes two-way data interaction between the vehicle terminal and the cloud platform; the analysis and decision module 4 is used to deeply analyze the battery operating status, identify potential faults, and determine the risk level; the early warning execution module 5 executes differentiated graded early warning operations based on the three-level risk instructions issued by the cloud, wherein, for the first level of minor anomaly: only the local background records data, the cloud pushes maintenance prompts, and no vehicle The system provides audible and visual warnings to alert users to monitor battery status. For Level 2 general faults, it triggers text prompts on the vehicle's instrument panel and low-frequency audible and visual warnings, while simultaneously pushing fault details, location, and maintenance suggestions to the owner's mobile phone and the vehicle manufacturer's maintenance backend. For Level 3 severe risks, it triggers high-frequency audible and visual alarms and an emergency warning pop-up on the instrument panel, simultaneously pushing an emergency risk alert to instruct the user to pull over immediately, and also activates emergency protection through the local safety protection module 6. The safety protection module 6 executes active safety protection operations based on cloud-based control commands. Specifically, for minor anomalies, it activates active balancing control of individual battery cells to correct individual cell imbalances. For voltage inconsistency issues, optimize battery operation. For general faults: limit battery charging and discharging power, reduce battery operating load, prevent fault aggravation, and record fault data for maintenance. For serious risks: immediately disconnect battery high-voltage output, stop charging and discharging operations, activate battery pack heat dissipation / cooling devices to suppress continuous temperature rise, and trigger passive fire suppression devices if necessary to prevent thermal runaway and fire accidents. The storage and traceability module 7 realizes full-time data retention and fault traceability. This system relies on a multi-algorithm fusion artificial intelligence model to achieve accurate battery status estimation, early prediction of thermal runaway, and fault accumulation. Risk analysis and dynamic adaptive threshold determination significantly reduce false alarm and false negative rates. Integrating multi-dimensional sensor data (electrical, temperature, gas, vibration, and attitude) allows for accurate detection of early-stage latent and overt battery faults, completely resolving the issues of missed detections and delayed warnings inherent in traditional systems. A three-tiered risk response mechanism is constructed, matching differentiated warnings and protective actions to avoid excessive intervention in minor anomalies that could negatively impact the user experience, while ensuring rapid emergency response to serious risks, forming a closed loop of monitoring, analysis, warning, and protection. Full-time data retention supports precise fault tracing, providing data support for the entire battery lifecycle management.

[0024] Furthermore, the IoT-based real-time monitoring and early warning system for the operation safety of electric vehicle battery modules also includes a battery health prediction module 8 and a charging safety management module 9; the IoT-based real-time monitoring and early warning system for the operation safety of electric vehicle battery modules also includes a diagnosis and repair module 10 and a device self-test module 11. The battery health prediction module 8, based on the battery's full life cycle time series data, enables early prediction of the battery's long-term aging trend, lifespan decay, and failure probability. The charging safety management module 9 is used for safety monitoring and protection of electric vehicles in all scenarios, including slow charging, fast charging, and emergency charging. The diagnosis and repair module 10 is used for automatic diagnosis and autonomous repair of minor battery faults. The device self-test module 11 is used to monitor the operating status of all hardware, software and link devices in the system in real time.

[0025] In this implementation scheme, the battery health prediction module 8, based on the battery's full life-cycle time-series data, enables early prediction of long-term battery aging trends, lifespan degradation, and failure probabilities, overcoming the shortcomings of traditional systems that only monitor in real time without predictive analysis. The charging safety management module 9 is used for safety monitoring and protection of electric vehicles in all scenarios of slow charging, fast charging, and emergency charging, filling the gap in charging scenario management in traditional systems. Specifically, it monitors voltage fluctuations, charging current stability, battery temperature rise rate, individual cell voltage difference, and charging pile grounding status in real time during the charging process, identifying charging-specific faults such as overcharging, fast charging overheating, charging short circuits, and abnormal power supply from the charging pile. For high-risk scenarios such as low-temperature charging, high-temperature exposure charging, and fast charging of old batteries, it automatically matches charging current limiting, segmented charging, and temperature-linked pause strategies to prevent charging thermal runaway and charging fire accidents. At the same time, it records the entire process data of each charging session, generating a charging safety log to make charging risks monitorable, protectable, and traceable. The diagnosis and repair module 10 is used for automatic diagnosis and autonomous repair of minor battery faults. Specifically, it can self-diagnose in real time minor imbalances in individual battery cells, minor drifts in sensor data, minor communication delays, and minor abnormalities in thermal management, among other self-healing faults. For inconsistent battery cell voltages, it automatically initiates passive and active balancing for collaborative repair. For minor deviations in sensor data, it automatically calibrates parameters to correct errors. For short-term communication fluctuations, it automatically restarts the communication link to complete repairs without manual intervention. The device self-test module 11 is used to monitor the operating status of all hardware, software, and link devices in the system in real time, avoiding monitoring failures, missed reports, and false alarms due to system malfunctions. Specifically, it periodically self-checks the operating status of various sensors, the MCU's operating status, the signal strength of the IoT communication module, the read / write status of the storage module, and the operating status of the early warning execution device. It identifies system problems such as sensor failures, communication disconnections, hardware failures, and program lag. Once a device abnormality is detected, it immediately generates a device fault log and provides local maintenance prompts, avoiding technical loopholes such as "battery faults not being monitored and system failures not being perceived," thus ensuring the reliability and stability of the monitoring system itself.

[0026] Furthermore, the multidimensional sensing module 1 includes an electrical parameter acquisition unit 101, a temperature acquisition unit 102, an environmental acquisition unit 103, and a position and attitude unit 104. The electrical parameter acquisition unit 101 is used to acquire battery cell voltage, total battery pack voltage, charging and discharging current, and dynamic internal resistance parameters in real time, and to capture electrical fault characteristics. The temperature acquisition unit 102 is used to collect multi-point temperature data and temperature difference in real time. The environmental acquisition unit 103 is used to collect data on the concentration of combustible gas inside the battery pack, the amplitude and frequency of operating vibration, and the ambient temperature and humidity in real time, so as to detect hidden battery faults. The position and attitude unit 104 is used to collect tilt and bump attitude data of the battery module.

[0027] In this implementation scheme, the electrical parameter acquisition unit 101 is used to acquire the individual battery cell voltage, total battery pack voltage, charging and discharging current, and dynamic internal resistance parameters in real time, accurately capturing electrical fault characteristics such as voltage fluctuations, current anomalies, and internal resistance decay. The temperature acquisition unit 102 acquires multi-point temperature data and temperature differences in real time, accurately identifying potential hazards such as local overheating and heat accumulation. The environmental acquisition unit 103 acquires combustible gas concentration, operating vibration amplitude and impact frequency, and ambient temperature and humidity data in real time, capturing latent faults such as battery micro-short circuit gas generation, loosening due to driving vibration, and leakage due to moisture. The position and attitude unit 104 acquires battery module tilt and bumpy attitude data to assist in assessing the structural stress risk of the battery under extreme road conditions.

[0028] Furthermore, the data preprocessing module 2 includes a noise reduction processing unit 201, an outlier removal unit 202, a timing calibration unit 203, and a parameter compensation unit 204; The noise reduction processing unit 201 is used to filter out high-frequency noise data generated by vehicle driving electromagnetic interference and sensor jitter. The outlier removal unit 202 removes extreme abnormal data caused by sensor malfunctions and transient interference based on the threshold range of normal battery operation parameters. The timing calibration unit 203 is used to perform timestamp-uniform alignment on the data collected by the multidimensional sensing module 1. The parameter compensation unit 204 performs dynamic compensation and calibration on parameters that are susceptible to environmental influences, based on temperature and humidity environmental parameters.

[0029] In this embodiment, the noise reduction processing unit 201 employs an adaptive Kalman filter algorithm to filter out high-frequency noise data generated by vehicle driving electromagnetic interference and sensor jitter, while retaining valid state characteristic data; the outlier removal unit 202, based on the normal operating parameter threshold range of the battery, removes extreme abnormal data generated by sensor malfunctions and transient interference; the timing calibration unit 203 performs time stamp unification alignment on the data collected by the multi-dimensional sensing module 1 to ensure the synchronization of electrical parameters, temperature, gas, and vibration data at the same time; and the parameter compensation unit 204 performs dynamic compensation calibration on parameters susceptible to environmental influences based on temperature and humidity environmental parameters to improve data monitoring accuracy.

[0030] Furthermore, the analysis and decision-making module 4 includes a battery state estimation module 401, a fault identification module 402, a thermal runaway early warning module 403, and a fault judgment module 404. The battery state estimation module 401 is used to evaluate the battery aging degree and capacity decay trend in real time. The fault identification module 402, based on a dynamic adaptive threshold, dynamically adjusts the judgment criteria in conjunction with battery operating conditions, ambient temperature, and charge / discharge status to identify various faults such as single-cell overvoltage, undervoltage, overcurrent, overtemperature, excessive temperature difference, abnormal internal resistance, and excessive gas production. The thermal runaway early warning module 403 constructs a multi-parameter fusion thermal runaway prediction algorithm based on the temperature change rate, gas concentration increment, and internal resistance abrupt change characteristics to identify early thermal runaway potential hazards in advance. The fault assessment module 404 analyzes the battery's hidden risks based on time-series data to statistically determine the frequency and duration of battery anomalies, thereby enabling early fault prediction.

[0031] In this implementation scheme, the battery state estimation module 401 integrates an extended Kalman filter algorithm to accurately estimate the battery's SOC (State of Charge) and SOH (State of Health), and to assess the battery's aging degree and capacity decay trend in real time. The fault identification module 402, based on a dynamic adaptive threshold, dynamically adjusts the judgment criteria according to battery operating conditions, ambient temperature, and charge / discharge status to identify various faults such as single-cell overvoltage, undervoltage, overcurrent, overtemperature, excessive temperature difference, abnormal internal resistance, and excessive gas production. The thermal runaway early warning module 403 constructs a multi-parameter fusion thermal runaway prediction algorithm based on temperature change rate, gas concentration increment, and internal resistance abrupt change characteristics to identify early thermal runaway risks in advance, solving the problem of delayed early warning in traditional systems. The fault analysis module 404 analyzes the hidden risks of the battery based on time-series data statistics on the frequency and duration of battery anomalies, and achieves early fault prediction.

[0032] Furthermore, the storage traceability module 7 includes a storage unit 71 and a traceability unit 72; The storage unit 71 is used to cache raw sensor data, preprocessed data, early warning records, protection operation logs, analysis results, and maintenance records in real time. The tracing unit 72 retrieves corresponding data based on time, vehicle number, and fault type to locate the cause of the fault and the fault propagation process.

[0033] In this implementation scheme, the storage unit 71 has two storage methods: local storage and cloud storage. Local storage: The vehicle-mounted terminal is equipped with a high-speed storage chip to cache raw sensor data, preprocessed data, early warning records, and protection operation logs in real time, with a local retention time of ≥30 days. The cloud server permanently stores all uploaded data, analysis results, and operation and maintenance records to build a database for the entire battery life cycle. The traceability unit 72 has built-in data retrieval and traceability functions, which can quickly retrieve corresponding data according to time, vehicle number, and fault type to accurately locate the fault cause and fault propagation process, providing data support for battery operation and maintenance, accident analysis, and product optimization.

[0034] The above-disclosed embodiments are merely preferred embodiments of the IoT-based real-time monitoring and early warning system for the operation safety of electric vehicle battery modules, and should not be construed as limiting the scope of this application. Those skilled in the art can understand that implementing all or part of the above embodiments and making equivalent changes in accordance with the claims of this application still fall within the scope of this application.

Claims

1. A real-time monitoring and early warning system for the operational safety of electric vehicle battery modules based on the Internet of Things, characterized in that, It includes a multi-dimensional sensing module, a data preprocessing module, an IoT transmission module, an analysis and decision-making module, an early warning execution module, a security protection module, and a storage and traceability module; The multi-dimensional sensing module is used to collect battery operating status data from all directions; The data preprocessing module is used to solve the problems of high noise, disordered timing, and insufficient accuracy in the raw sensor data; The IoT transmission module is used to enable two-way data interaction between the vehicle-mounted terminal and the cloud platform; The analysis and decision-making module is used to deeply analyze the battery's operating status, identify potential faults, and determine the risk level. The early warning execution module performs differentiated and graded early warning operations based on the three-level risk instructions issued from the cloud. The security protection module executes proactive security protection operations based on cloud-based control commands. The storage traceability module is used to achieve full-time data retention and fault traceability.

2. The IoT-based real-time monitoring and early warning system for the operational safety of electric vehicle battery modules as described in claim 1, characterized in that, The IoT-based real-time monitoring and early warning system for the operation safety of electric vehicle battery modules also includes a battery health prediction module and a charging safety management module. The battery health prediction module, based on the battery's full life cycle time-series data, enables early prediction of the battery's long-term aging trend, lifespan decay, and failure probability. The charging safety management module is used for safety monitoring and protection of electric vehicles in all scenarios, including slow charging, fast charging, and emergency charging.

3. The IoT-based real-time monitoring and early warning system for the operational safety of electric vehicle battery modules as described in claim 1, characterized in that, The IoT-based real-time monitoring and early warning system for the operation safety of electric vehicle battery modules also includes a diagnostic and repair module and a device self-test module. The diagnosis and repair module is used for automatic diagnosis and autonomous repair of minor battery faults; The device self-test module is used to monitor the operating status of all hardware, software and link devices in the system in real time.

4. The IoT-based real-time monitoring and early warning system for the operational safety of electric vehicle battery modules as described in claim 1, characterized in that, The multidimensional sensing module includes an electrical parameter acquisition unit, a temperature acquisition unit, an environmental acquisition unit, and a position and attitude unit. The electrical parameter acquisition unit is used to acquire battery cell voltage, total battery pack voltage, charging and discharging current, and dynamic internal resistance parameters in real time, and to capture electrical fault characteristics. The temperature acquisition unit is used to collect multi-point temperature data and temperature difference in real time; The environmental acquisition unit is used to collect real-time data on the concentration of combustible gas inside the battery pack, the amplitude and frequency of operating vibration, and the ambient temperature and humidity, in order to detect hidden battery faults. The position and attitude unit is used to collect tilt and bump attitude data of the battery module.

5. The IoT-based real-time monitoring and early warning system for the operational safety of electric vehicle battery modules as described in claim 1, characterized in that, The data preprocessing module includes a noise reduction unit, an outlier removal unit, a timing calibration unit, and a parameter compensation unit. The noise reduction processing unit is used to filter out high-frequency noise data generated by vehicle driving electromagnetic interference and sensor jitter. The outlier removal unit removes extreme abnormal data caused by sensor malfunctions and transient interference based on the threshold range of normal battery operation parameters. The timing calibration unit is used to perform time stamp alignment on the data collected by the multi-dimensional sensing module. The parameter compensation unit performs dynamic compensation and calibration on parameters that are susceptible to environmental influences, based on temperature and humidity environmental parameters.

6. The IoT-based real-time monitoring and early warning system for the operational safety of electric vehicle battery modules as described in claim 1, characterized in that, The analysis and decision-making module includes a battery status estimation module, a fault identification module, a thermal runaway early warning module, and a fault assessment module. The battery state estimation module is used to assess the degree of battery aging and capacity decay trend in real time. The fault identification module, based on a dynamic adaptive threshold, dynamically adjusts the judgment criteria in conjunction with battery operating conditions, ambient temperature, and charge / discharge status to identify various faults such as single-cell overvoltage, undervoltage, overcurrent, overtemperature, excessive temperature difference, abnormal internal resistance, and excessive gas production. The thermal runaway early warning module constructs a multi-parameter fusion thermal runaway prediction algorithm based on the temperature change rate, gas concentration increment, and internal resistance abrupt change characteristics to identify early thermal runaway risks in advance. The fault assessment module analyzes the frequency and duration of battery anomalies based on time-series data to assess hidden risks in the battery and enable early fault prediction.

7. The IoT-based real-time monitoring and early warning system for the operational safety of electric vehicle battery modules as described in claim 1, characterized in that, The storage traceability module includes a storage unit and a source module unit; The storage unit is used to cache raw sensor data, preprocessed data, early warning records, protection operation logs, analysis results, and operation and maintenance records in real time. The tracing unit retrieves corresponding data based on time, vehicle number, and fault type to locate the cause of the fault and the fault propagation process.

Images