Automobile remote detection method

Abstract

The invention relates to the technical field of automobile remote detection, in particular to an automobile remote detection method. In a vehicle networking module, a power supply state monitoring unit captures a bus voltage fluctuation waveform of a vehicle-mounted power supply, a ripple coefficient of a power supply line of a sensor and a transient working current response curve of a key electronic component in real time, and a three-dimensional power supply quality evaluation model is established based on the data to generate a power supply stability index; when the vehicle operation data is transmitted, the index is synchronously packaged; after the cloud platform receives the data, the power supply perception data fusion module realizes data space-time alignment, dynamic denoising of the self-adaptive filtering module, parallel operation of the reference and the elastic fault tree by the dual-mode fault judgment module and confidence comparison, and early warning is triggered only when the two fault trees report the same fault code; the problems of data deviation and false fault misjudgment caused by the fact that dynamic power supply fluctuation is not considered in the prior art are effectively solved.

Description

Technical Field

[0001] This invention relates to the field of automotive remote testing technology, specifically to automotive remote testing methods. Background Technology

[0002] With the increasing electrification and intelligence of automobiles, remote vehicle diagnostics technology has become an important means to ensure safe vehicle operation and reduce maintenance costs. This technology primarily uses vehicle-to-everything (V2X) modules to collect real-time operating data from key components such as the engine, transmission, braking system, and electronic stability program, including metrics like engine speed, oil pressure, temperature, and fault codes. This data is then transmitted to a cloud management platform via a mobile network. After initial data processing, the cloud platform provides feedback to the vehicle owner or service provider, allowing relevant personnel to monitor the vehicle's operating status without needing to be physically present, proactively identify potential faults, and schedule repairs, thus preventing driving safety hazards or repair delays caused by sudden malfunctions.

[0003] Current remote vehicle diagnostic methods do not adequately consider the accuracy of data collected under dynamic power supply fluctuation scenarios when collecting operational data from critical components. When a vehicle experiences frequent starts and stops (e.g., in congested urban areas), simultaneous operation of air conditioning and lights, or instantaneous changes in generator load, the voltage of the vehicle's power supply system will experience short-term fluctuations, typically within the standard range of 12V-14.5V with a deviation of ±0.5V. These voltage fluctuations directly affect the signal output accuracy of electronic component sensors, leading to slight deviations in collected data such as engine speed and oil pressure. The cloud-based data processing algorithms of existing remote diagnostic methods lack real-time correction mechanisms for these power supply fluctuations. They analyze data based on calibration parameters under standard power supply conditions, easily misinterpreting "false data anomalies" caused by power supply fluctuations as component malfunctions. This results in incorrect fault warnings being sent to owners or service providers, increasing unnecessary troubleshooting workload and reducing user trust in the reliability of remote diagnostic technology. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a remote vehicle detection method that solves the problems of sensor data deviation and false fault misjudgment caused by dynamic power supply fluctuations, which are not considered when using existing technologies.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a remote vehicle detection method, comprising: In the vehicle's Internet of Vehicles module, the power supply status monitoring unit captures the voltage fluctuation waveform of the vehicle power bus, the ripple coefficient of each sensor power supply line, and the transient operating current response curve of key electronic components in real time. Based on the waveform, ripple coefficient, and transient response curve, a three-dimensional power supply quality evaluation model is established, and a power supply stability index is dynamically generated. The power supply stability index maps the potential impact of the current vehicle power supply environment on sensor data acquisition in a digital twin manner. When transmitting vehicle operation data, the vehicle networking module simultaneously encapsulates the power supply stability index; The cloud platform receives vehicle operation data and power supply stability index, and performs dynamic compensation processing on the vehicle operation data based on the power supply stability index. This dynamic compensation processing includes: The power supply stability index is spatiotemporally aligned with vehicle operation data through the power supply sensing data fusion module to identify the coupling relationship between power supply fluctuations and sensor data anomalies. The adaptive filtering module employs a variable parameter digital filter, which dynamically adjusts the filter cutoff frequency and bandwidth of the variable parameter digital filter according to the power supply stability index, thereby performing dynamic noise reduction on the fluctuation-sensitive parameters. The dual-mode fault identification module establishes a baseline fault tree under normal power supply conditions and an elastic fault tree under dynamic power supply conditions. The two diagnostic logics run in parallel. By comparing the confidence differences of the diagnostic results under the two modes, false fault signals caused by power supply fluctuations are eliminated. A warning message is triggered only if both modes report the same fault code.

[0006] Furthermore, the power supply status monitoring unit captures in real time the voltage fluctuation waveform of the vehicle power bus, the ripple coefficient of each sensor power supply line, and the transient operating current response curve of key electronic components, including: Multi-channel synchronous sampling technology is used to acquire real-time voltage change data of the vehicle power bus within a preset time period; Real-time acquisition of the periodic ripple voltage amplitude of each sensor's power supply line; Real-time acquisition of transient current response values ​​of key electronic components under different operating loads.

[0007] Furthermore, the three-dimensional power supply quality evaluation model established based on waveform, ripple coefficient, and transient response curve dynamically generates a power supply stability index. This power supply stability index, in a digital twin format, maps the potential impact of the current vehicle power supply environment on sensor data acquisition, including: Voltage change data, ripple voltage amplitude, and transient current response values ​​are input into a pre-trained three-dimensional power quality evaluation model; The three-dimensional power quality evaluation model outputs a dynamic power stability index based on input data. The magnitude of the index indicates the degree of impact of the power supply environment on the accuracy of sensor data acquisition.

[0008] Furthermore, the step of aligning the power supply stability index with vehicle operation data in a spatiotemporal manner through the power supply sensing data fusion module to identify the coupling relationship between power supply fluctuations and sensor data anomalies includes: Acquire the timestamps for vehicle operation data collection and power supply stability index generation; Align the power supply stability index with vehicle operation data based on timestamps; Analyze the aligned data to determine whether the changes in the power supply stability index are related to abnormal fluctuations in vehicle operation data.

[0009] Furthermore, the adaptive filtering module employs a variable-parameter digital filter, dynamically adjusting the filter cutoff frequency and bandwidth of the variable-parameter digital filter according to the power supply stability index, to dynamically denoise the fluctuation-sensitive parameters, including: Based on the power supply stability index, the filter cutoff frequency and filter bandwidth of the variable parameter digital filter are calculated and updated in real time. The fluctuation-sensitive parameters are input to a variable-parameter digital filter for processing, so as to realize intelligent notch filtering in the power supply noise frequency band and eliminate noise components introduced by power supply fluctuations.

[0010] Furthermore, the dual-mode fault discrimination module establishes a baseline fault tree under normal power supply conditions and an elastic fault tree under dynamic power supply conditions, and runs the two diagnostic logics in parallel. By comparing the confidence differences of the diagnostic results under the two modes, false fault signals caused by power supply fluctuations are eliminated, including: Based on historical vehicle operating data and standard fault modes, a baseline fault tree is constructed under normal power supply conditions to diagnose faults under stable power supply conditions. Based on power supply fluctuation simulation data and dynamic calibration parameters, an elastic fault tree under dynamic power supply conditions is constructed to diagnose faults under fluctuating power supply conditions. The denoised vehicle operating data is simultaneously input into the baseline fault tree and the elastic fault tree for diagnosis, and the respective diagnostic results and confidence levels are obtained.

[0011] Furthermore, by comparing the confidence differences of the diagnostic results under the two modes, false fault signals caused by power supply fluctuations are eliminated; and a warning message is triggered only when both modes report the same fault code, including: If the diagnostic results of the baseline fault tree and the resilient fault tree are inconsistent, or if the diagnostic results of the two modes are consistent but the confidence difference exceeds the preset threshold, the diagnostic results will be identified as false fault signals and removed. If both the baseline fault tree and the resilient fault tree diagnose the same fault code, and the difference in confidence between the two diagnostic results is within a preset threshold range, then it is considered a real fault, triggering an early warning message push.

[0012] Furthermore, the vehicle operating data includes engine speed, oil pressure, transmission temperature, and braking system status parameters; fluctuation-sensitive parameters include engine speed data and oil pressure data.

[0013] Furthermore, when transmitting vehicle operation data, the vehicle networking module simultaneously encapsulates a power supply stability index, including: Package vehicle operation data and power supply stability index into a unified data frame format; Data frames are transmitted to the cloud platform via mobile networks.

[0014] Furthermore, the cloud platform receives vehicle operation data and power supply stability index, including: The cloud platform receives data frames from the vehicle networking module via a mobile network interface; The cloud platform decapsulates data frames to obtain vehicle operation data and power supply stability index.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention utilizes a power supply status monitoring unit within the vehicle's vehicle networking module to capture real-time waveforms of onboard power bus voltage fluctuations, sensor power supply line ripple coefficients, and transient operating current response curves of key electronic components. Based on this data, a three-dimensional power supply quality evaluation model is established to generate a power supply stability index, which is simultaneously encapsulated during vehicle operation data transmission. Upon receiving the data on the cloud platform, a power supply perception data fusion module aligns the data in time and space, an adaptive filtering module dynamically denoises the data, and a dual-mode fault discrimination module operates in parallel with a benchmark and an elastic fault tree, comparing their confidence levels. An early warning is triggered only when both fault trees report the same fault code. This effectively solves the problem of data deviation and false fault misjudgment caused by dynamic power supply fluctuations in existing technologies, effectively improving the accuracy of remote vehicle detection, reducing unnecessary maintenance and troubleshooting workload, enhancing user trust in remote detection technology, and ensuring the reliability and effectiveness of vehicle fault early warning. Attached Figure Description

[0016] Figure 1 This is a flowchart of the power supply monitoring and index generation process of the present invention; Figure 2 This is a flowchart illustrating the data encapsulation and transmission process of the present invention. Figure 3 This is a flowchart of the cloud data processing of the present invention; Figure 4 This is a flowchart of the dual-mode fault detection process of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0018] Please see Figure 1-4 This invention provides a method for remote vehicle detection, comprising: In the vehicle's Internet of Vehicles module, the power supply status monitoring unit captures the voltage fluctuation waveform of the vehicle power bus, the ripple coefficient of each sensor power supply line, and the transient operating current response curve of key electronic components in real time. Based on the waveform, ripple coefficient, and transient response curve, a three-dimensional power supply quality evaluation model is established, and a power supply stability index is dynamically generated. The power supply stability index maps the potential impact of the current vehicle power supply environment on sensor data acquisition in a digital twin manner. When transmitting vehicle operation data, the vehicle networking module simultaneously encapsulates the power supply stability index; The cloud platform receives vehicle operation data and power supply stability index, and performs dynamic compensation processing on the vehicle operation data based on the power supply stability index. This dynamic compensation processing includes: The power supply stability index is spatiotemporally aligned with vehicle operation data through the power supply sensing data fusion module to identify the coupling relationship between power supply fluctuations and sensor data anomalies. The adaptive filtering module employs a variable parameter digital filter, which dynamically adjusts the filter cutoff frequency and bandwidth of the variable parameter digital filter according to the power supply stability index, thereby performing dynamic noise reduction on the fluctuation-sensitive parameters. The dual-mode fault identification module establishes a baseline fault tree under normal power supply conditions and an elastic fault tree under dynamic power supply conditions. The two diagnostic logics run in parallel. By comparing the confidence differences of the diagnostic results under the two modes, false fault signals caused by power supply fluctuations are eliminated. A warning message is triggered only if both modes report the same fault code.

[0019] Specifically, the vehicle's connected vehicle module is equipped with a power supply status monitoring unit, which operates continuously to capture three types of key data in real time. When the vehicle is in a dynamic power supply fluctuation scenario, such as frequent start-stop in congested urban areas or when the air conditioning and lights are on simultaneously, the on-board power bus voltage will deviate by ±0.5V within the standard range of 12V-14.5V. The monitoring unit captures this voltage fluctuation waveform in real time through multi-channel synchronous sampling technology (a mature technology widely used in scenarios with multiple signals in parallel acquisition). At the same time, it acquires the ripple coefficient of each sensor power supply line in real time, such as the periodic ripple voltage amplitude of the engine speed sensor power supply line. It also tracks the transient operating current response curves of key electronic components such as the ECU under different workloads.

[0020] Based on the captured waveforms, ripple coefficients, and transient response curves, a three-dimensional power quality evaluation model is constructed. This model is trained using a large amount of historical power supply data and sensor-collected accuracy data. The power supply stability index is dynamically generated using a formula, as follows: (1) in, This is the power supply stability index, with a value range of 0-10. The smaller the value, the less the power supply environment affects the sensor's acquisition accuracy; the larger the value, the greater the impact. , , These are the weighting coefficients for voltage fluctuation, ripple coefficient, and transient current response, respectively, with a sum of 1. This was set after multiple experimental calibrations. , , ; This is the normalized value of the voltage fluctuation waveform, calculated by comparing the actual voltage fluctuation amplitude with the deviation range of the standard voltage range, and its value ranges from 0 to 10. This is the normalized value of the ripple coefficient, calculated from the ratio of the actual ripple voltage amplitude to the sensor's allowable ripple threshold, and its value ranges from 0 to 10. This is the normalized value of the transient operating current response curve, determined based on the ratio of the current response fluctuation amplitude to the rated current fluctuation range of the electronic component, and ranges from 0 to 10.

[0021] This index uses a digital twin to intuitively map the potential impact of the current power supply environment on sensor data acquisition. For example, when the index rises to above 6, it means that power supply fluctuations may cause significant deviations in the speed and oil pressure data collected by the sensor.

[0022] When transmitting vehicle operating data such as engine speed and oil pressure, the vehicle networking module encapsulates the power supply stability index and operating data into a unified data frame, which is then synchronously sent to the cloud platform via the mobile network. Upon receiving the data, the cloud platform initiates dynamic compensation processing: First, the power supply sensing data fusion module aligns the power supply stability index with the operating data in time and space based on timestamps (timestamp matching is an existing data synchronization technology), accurately identifying the coupling relationship between power supply fluctuations and sensor data anomalies, such as determining whether a sudden drop in the power supply index during a certain period is synchronized with abnormal oil pressure data. Then, the adaptive filtering module dynamically adjusts the cutoff frequency and bandwidth of the variable-parameter digital filter based on the power supply stability index to denoise fluctuating parameters such as engine speed, eliminating noise introduced by power supply fluctuations. Finally, the dual-mode fault diagnosis module runs in parallel a baseline fault tree constructed based on normal power supply data and an elastic fault tree constructed based on power supply fluctuation data (the fault tree construction adopts the existing tree-like logic modeling method in the field of fault diagnosis), comparing the confidence levels of the two diagnostic results.

[0023] A warning message is only triggered when both fault trees report the same fault code and the difference in confidence level is within a preset range. This implementation effectively solves the problems of data deviation and false fault misjudgment caused by dynamic power supply fluctuations in existing technologies, significantly improves the accuracy of remote detection, reduces unnecessary maintenance and troubleshooting work, and enhances users' trust in the detection technology.

[0024] In this embodiment, the power supply status monitoring unit captures in real time the voltage fluctuation waveform of the vehicle power bus, the ripple coefficient of each sensor power supply line, and the transient operating current response curve of key electronic components, including: Multi-channel synchronous sampling technology is used to acquire real-time voltage change data of the vehicle power bus within a preset time period; Real-time acquisition of the periodic ripple voltage amplitude of each sensor's power supply line; Real-time acquisition of transient current response values ​​of key electronic components under different operating loads.

[0025] Specifically, the power supply status monitoring unit employs multi-channel synchronous sampling technology (a mature technology widely used in industrial data acquisition) to capture data. For the voltage fluctuation waveform of the vehicle power bus, a preset time period of 100 milliseconds is set. The multi-channel synchronous sampling module simultaneously collects voltage change data of the power bus within this time period, ensuring complete capture of instantaneous voltage fluctuations under frequent start-stop scenarios and avoiding waveform information loss due to asynchronous sampling.

[0026] For the ripple coefficient of each sensor power supply line, the monitoring unit monitors the periodic ripple voltage amplitude of each sensor power supply line in real time through the built-in ripple detection circuit. Whether it is the engine speed sensor, the braking system sensor or the transmission temperature sensor, it can continuously acquire the ripple status of its line, without missing the power supply ripple data of any sensor, providing a comprehensive basis for subsequent judgment on whether the sensor data is affected by ripple.

[0027] In capturing the transient operating current response curves of key electronic components, the monitoring unit, in conjunction with a high-speed ADC module and a current sampling resistor, tracks the state of electronic components under different operating loads, such as when the ECU load increases during vehicle acceleration, decreases during deceleration, or changes in generator load when high-power electrical equipment is turned on. It collects the transient current response values ​​of the electronic components under the corresponding operating conditions in real time, thus forming a complete transient operating current response curve. Through this method, comprehensive and real-time power supply-related data can be obtained, providing accurate and comprehensive basic data for subsequently substituting into formula (1) to construct a power supply quality evaluation model, ensuring the reliability of subsequent index generation.

[0028] In this embodiment, a three-dimensional power supply quality evaluation model is established based on waveform, ripple coefficient, and transient response curve. A power supply stability index is dynamically generated, which maps the potential impact of the current vehicle power supply environment on sensor data acquisition using a digital twin approach. This includes: Voltage change data, ripple voltage amplitude, and transient current response values ​​are input into a pre-trained three-dimensional power quality evaluation model; The three-dimensional power quality evaluation model outputs a dynamic power stability index based on input data. The magnitude of the index indicates the degree of impact of the power supply environment on the accuracy of sensor data acquisition.

[0029] Specifically, the three-dimensional power quality evaluation model is trained on a large amount of historical power supply data (covering voltage, ripple, and current data under different power supply fluctuation scenarios) and sensor acquisition accuracy data under corresponding scenarios. The model parameters are iteratively optimized through machine learning algorithms, enabling it to accurately analyze the impact of power supply status on sensor acquisition.

[0030] The voltage change data, ripple voltage amplitude, and transient current response value captured by the power supply status monitoring unit are normalized respectively to obtain... , , Three parameters, then according to formula (1) Calculate and dynamically output power supply stability index For example, when a vehicle experiences increased voltage fluctuations due to the simultaneous operation of the air conditioning and lights, From 2 to 5, the increase in ripple voltage amplitude causes... From 1 to 3, the increased fluctuation in the current response of electronic components leads to... From 1 to 2, substituting into the formula yields... This indicates that the power supply environment has a certain impact on the sensor's data acquisition accuracy.

[0031] The index is presented in a numerical range of 0-10 and is also visually displayed in the vehicle digital model built on the cloud platform in the form of a digital twin. Through the digital model, staff can clearly know whether the current power supply status will interfere with sensor data, providing a clear basis for subsequent processing of vehicle operation data and improving the pertinence of data processing.

[0032] In this embodiment, the power supply stability index is spatiotemporally aligned with vehicle operation data through a power supply sensing data fusion module to identify the coupling relationship between power supply fluctuations and sensor data anomalies, including: Acquire the timestamps for vehicle operation data collection and power supply stability index generation; Align the power supply stability index with vehicle operation data based on timestamps; Analyze the aligned data to determine whether the changes in the power supply stability index are related to abnormal fluctuations in vehicle operation data.

[0033] Specifically, the power supply sensing data fusion module first obtains the timestamp when the vehicle operation data is collected and the timestamp when the power supply stability index is generated. Both timestamps are accurate to the millisecond level to ensure the accuracy of time recording. This process is implemented using existing time synchronization protocols.

[0034] Subsequently, the module aligns the power supply stability index with the vehicle operation data based on the timestamp, ensuring a one-to-one correspondence between the power supply index and the operation data at the same time point. For example, the power supply stability index generated at 10:05:23.120 will be used to align the power supply stability index with the vehicle operation data. This data is correlated with engine speed (2500 rpm) and oil pressure (3.2 bar) collected at that moment. After alignment, the module analyzes the data, calculating the correlation between the trends of the two to determine whether the change in the power supply stability index is coupled with abnormal operating data. For example, if the power supply stability index suddenly rises from 3.0 to 7.5 at a certain moment, and the engine speed suddenly jumps from 2200 rpm to 2800 rpm, and the engine speed returns to normal when the power supply index subsequently falls back, then it can be determined that the power supply fluctuation is coupled with the abnormal engine speed data.

[0035] In this way, the impact of power supply fluctuations on sensor data anomalies can be accurately located, laying the foundation for subsequent targeted data processing and avoiding blind adjustments to the operating data.

[0036] In this embodiment, an adaptive filtering module employs a variable-parameter digital filter. The filter cutoff frequency and bandwidth of the variable-parameter digital filter are dynamically adjusted according to the power supply stability index to dynamically denoise the fluctuation-sensitive parameters, including: Based on the power supply stability index, the filter cutoff frequency and filter bandwidth of the variable parameter digital filter are calculated and updated in real time. The fluctuation-sensitive parameters are input to a variable-parameter digital filter for processing, so as to realize intelligent notch filtering in the power supply noise frequency band and eliminate noise components introduced by power supply fluctuations.

[0037] Specifically, the adaptive filtering module is equipped with a variable parameter digital filter. The filter's cutoff frequency and bandwidth can be adjusted in real time according to the power supply stability index. The cutoff frequency adjustment is achieved through a formula, as follows: (2) In the formula, This is the adjusted filter cutoff frequency; The reference cutoff frequency is set to 1kHz based on the effective signal frequency band of the vehicle sensor data. This is a frequency adjustment factor, experimentally calibrated to 50 Hz / unit SI; This represents the current power supply stability index. The baseline power supply stability index is set at 3.0, representing the critical value for a basically stable power supply environment.

[0038] When the power supply stability index (Higher than the reference value), indicating that power supply fluctuations have a significant impact on sensor data. Substituting this into formula (2) yields... At the same time, the filter bandwidth is adjusted to be in a fixed proportion to the cutoff frequency, that is ( (where 0.2 is the scaling factor, and the bandwidth is the filter bandwidth). At this point, the bandwidth becomes 220Hz. By increasing the cutoff frequency and narrowing the bandwidth, the filtering capability for high-frequency power supply noise is enhanced. When the power supply stability index... (Below the benchmark value), the power supply environment is relatively stable, substituting into the formula yields... The bandwidth is increased to 190Hz to avoid filtering out valid information in the running data.

[0039] During the filtering process, fluctuation-sensitive parameters such as engine speed and oil pressure data are input into a variable-parameter digital filter. Based on the adjusted cutoff frequency and bandwidth, the filter performs intelligent notch filtering within the power supply noise band, accurately eliminating noise components introduced by power supply fluctuations. After processing, the accuracy of the fluctuation-sensitive parameters is significantly improved, providing more reliable data support for subsequent fault diagnosis.

[0040] In this embodiment, a dual-mode fault discrimination module is used to establish a baseline fault tree under normal power supply conditions and an elastic fault tree under dynamic power supply conditions. The two diagnostic logics run in parallel. By comparing the confidence differences of the diagnostic results under the two modes, false fault signals caused by power supply fluctuations are eliminated, including: Based on historical vehicle operating data and standard fault modes, a baseline fault tree is constructed under normal power supply conditions to diagnose faults under stable power supply conditions. Based on power supply fluctuation simulation data and dynamic calibration parameters, an elastic fault tree under dynamic power supply conditions is constructed to diagnose faults under fluctuating power supply conditions. The denoised vehicle operating data is simultaneously input into the baseline fault tree and the elastic fault tree for diagnosis, and the respective diagnostic results and confidence levels are obtained.

[0041] Specifically, the dual-mode fault diagnosis module first constructs two types of fault trees. The baseline fault tree is constructed based on the historical operating data accumulated during long-term vehicle operation under normal power supply conditions. It combines standard fault modes commonly used in the automotive industry (such as engine oil pressure below 2.0 bar being judged as pressure abnormality) and uses existing fault tree analysis methods to clarify the characteristics and judgment logic of various faults under normal power supply conditions, which is used to carry out fault diagnosis under stable power supply conditions.

[0042] The resilient fault tree is built on power supply fluctuation simulation data obtained through simulation experiments (covering power supply fluctuation scenarios of different amplitudes and frequencies) and dynamic calibration parameters calibrated according to actual power supply fluctuation conditions (such as lowering the oil pressure fault judgment threshold by 0.1 bar for every 1.0 increase in the power supply index). It can adapt to the fault diagnosis needs under power supply fluctuation scenarios. Its construction method is also based on the existing fault tree modeling logic, only optimizing parameters for power supply fluctuation scenarios.

[0043] After acquiring the vehicle operating data processed by adaptive filtering, it is simultaneously input into both the baseline fault tree and the elastic fault tree. Each fault tree analyzes the data according to its own diagnostic logic, outputting its own diagnostic results and providing a confidence level for each result (the confidence level is calculated based on the degree of matching between fault features and data, ranging from 0 to 1, with values ​​closer to 1 indicating higher reliability). This provides crucial information for subsequent elimination of false fault signals.

[0044] In this embodiment, by comparing the confidence differences of the diagnostic results under the two modes, false fault signals caused by power supply fluctuations are eliminated; a warning message is triggered only when both modes report the same fault code, including: If the diagnostic results of the baseline fault tree and the resilient fault tree are inconsistent, or if the diagnostic results of the two modes are consistent but the confidence difference exceeds the preset threshold, the diagnostic results will be identified as false fault signals and removed. If both the baseline fault tree and the resilient fault tree diagnose the same fault code, and the difference in confidence between the two diagnostic results is within a preset threshold range, then it is considered a real fault, triggering an early warning message push.

[0045] Specifically, the dual-mode fault diagnosis module compares and analyzes the diagnostic results and confidence levels of the baseline fault tree and the flexible fault tree. If the baseline fault tree determines that there is a transmission overheating fault (above 120°C) with a confidence level of 0.9, while the flexible fault tree does not detect the fault with a confidence level of 0.1; or if both determine that the fault exists, but the baseline fault tree has a confidence level of 0.9 and the flexible fault tree has a confidence level of 0.6, and the difference exceeds the preset threshold of 0.2, then the diagnostic result is determined to be a false fault signal and is discarded to avoid misjudgment due to power supply fluctuations.

[0046] Only when both the baseline fault tree and the flexible fault tree diagnose the same fault code, such as both reporting an engine oil pressure too low (below 2.0 bar), and the baseline fault tree confidence is 0.85, the flexible fault tree confidence is 0.78, and the difference between the two is 0.07, which is within the preset threshold of 0.2, is it considered a real fault, and a warning message is triggered to send the fault information to the vehicle owner and the car service provider.

[0047] This method effectively eliminates false fault signals caused by power supply fluctuations, ensuring that the pushed early warning information is accurate and reliable, reducing unnecessary maintenance and scheduling, and improving service efficiency.

[0048] In this embodiment, vehicle operating data includes engine speed, oil pressure, transmission temperature, and braking system status parameters; fluctuation-sensitive parameters include engine speed data and oil pressure data.

[0049] Specifically, vehicle operating data includes key parameters such as engine speed, oil pressure, transmission temperature, and braking system status parameters (e.g., brake pad wear and brake fluid level). These data are collected in real time by sensors installed in various parts of the vehicle and can comprehensively reflect the operating status of the vehicle's core components: engine speed reflects the engine's workload, and abnormal speed may reflect problems with the ignition system or fuel supply; transmission temperature reflects the transmission's heat dissipation and operating status, and excessively high temperature may indicate poor lubrication; braking system status parameters are directly related to driving safety, and abnormalities must be addressed immediately.

[0050] Among these operational data, engine speed and oil pressure data are fluctuation-sensitive parameters. This is because the signal outputs of the engine speed sensor and oil pressure sensor are analog signals, which are easily affected by fluctuations in the power supply voltage. When the power supply voltage deviates by ±0.5V, the data collected by these two types of sensors will show slight deviations first. If no targeted processing is performed, it can easily lead to misdiagnosis of faults. Clearly defining the fluctuation-sensitive parameters can make subsequent adaptive filtering based on formula (2) more targeted, avoid over-filtering of data such as gearbox temperature that are less affected by the power supply, and improve data processing efficiency and accuracy.

[0051] In this embodiment, the vehicle networking module simultaneously encapsulates a power supply stability index when transmitting vehicle operation data, including: Package vehicle operation data and power supply stability index into a unified data frame format; Data frames are transmitted to the cloud platform via mobile networks.

[0052] Specifically, before transmitting vehicle operation data, the vehicle network module processes the data, packaging the vehicle operation data such as engine speed and oil pressure with the power supply stability index calculated by formula (1) into a unified data frame according to a preset format. This data frame includes data identifiers (used to distinguish different vehicle data), operation data fields (stored according to sensor type), and power supply stability index fields (storing SI values ​​separately), ensuring a clear data structure and facilitating parsing by the cloud platform. The data frame format follows the existing vehicle network data transmission protocol, with only the power supply stability index field being added.

[0053] After the data frames are packaged, the vehicle-to-everything (V2X) module transmits them to the cloud platform via the vehicle's mobile network (such as 4G or 5G). The network transmission utilizes existing wireless communication technologies to ensure the stability and real-time performance of data transmission. This synchronous encapsulation and transmission method avoids the problem of asynchronous transmission between operational data and power supply stability index, ensuring that the cloud platform can simultaneously acquire both types of data. This provides a guarantee for subsequent synchronous dynamic compensation processing and improves the continuity of data processing.

[0054] In this embodiment, the cloud platform receives vehicle operation data and power supply stability index, including: The cloud platform receives data frames from the vehicle networking module via a mobile network interface; The cloud platform decapsulates data frames to obtain vehicle operation data and power supply stability index.

[0055] Specifically, the cloud platform is pre-configured with an interface adapted to the vehicle's mobile network. This interface supports data reception from mainstream mobile networks such as 4G and 5G. The interface communication protocol adopts the existing common standard for vehicle networking, which can be compatible with the data transmission requirements of vehicle networking modules of different brands of vehicles, ensuring the stability and timeliness of data reception and avoiding data loss due to protocol incompatibility.

[0056] Upon receipt of data, the cloud platform initiates a data decapsulation process. Following a preset data frame format, it extracts vehicle operation data and the power supply stability index (SI value) from the data frame and stores them in their respective data processing units: the operation data is stored in a real-time database for fault diagnosis and analysis; the power supply stability index is stored in a correlation database and bound to the operation data for the corresponding time period. The decapsulation process is developed based on existing data parsing algorithms, optimizing the parsing logic only for custom data frame formats. This prepares the data for subsequent dynamic compensation processing steps such as power supply sensing data fusion, adaptive filtering, and dual-mode fault identification, ensuring the smooth progress of the entire remote detection process.

[0057] In summary, this invention, through a power supply status monitoring unit in the vehicle's vehicle networking module, captures in real-time the voltage fluctuation waveform of the vehicle's power bus, the ripple coefficient of the sensor power supply line, and the transient operating current response curve of key electronic components. Based on this data, a three-dimensional power supply quality evaluation model is established to generate a power supply stability index, which is simultaneously encapsulated when transmitting vehicle operation data. After receiving the data, the cloud platform performs spatiotemporal alignment through a power supply perception data fusion module, dynamic noise reduction through an adaptive filtering module, and parallel operation of a benchmark and an elastic fault tree through a dual-mode fault discrimination module, comparing confidence levels. An early warning is triggered only when the two fault trees report the same fault code. This effectively solves the problem of data deviation and false fault misjudgment caused by dynamic power supply fluctuations in existing technologies, effectively improves the accuracy of remote vehicle detection, reduces unnecessary maintenance and troubleshooting workload, enhances user trust in remote detection technology, and ensures the reliability and effectiveness of vehicle fault early warning.

[0058] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0059] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for remote vehicle inspection, characterized in that, include: In the vehicle's Internet of Vehicles module, the power supply status monitoring unit captures the voltage fluctuation waveform of the vehicle power bus, the ripple coefficient of each sensor power supply line, and the transient operating current response curve of key electronic components in real time. Based on the waveform, ripple coefficient, and transient response curve, a three-dimensional power supply quality evaluation model is established, and a power supply stability index is dynamically generated. The power supply stability index maps the potential impact of the current vehicle power supply environment on sensor data acquisition in a digital twin manner. When transmitting vehicle operation data, the vehicle networking module simultaneously encapsulates the power supply stability index; The cloud platform receives vehicle operation data and power supply stability index, and performs dynamic compensation processing on the vehicle operation data based on the power supply stability index. This dynamic compensation processing includes: The power supply stability index is spatiotemporally aligned with vehicle operation data through the power supply sensing data fusion module to identify the coupling relationship between power supply fluctuations and sensor data anomalies. The adaptive filtering module employs a variable parameter digital filter, which dynamically adjusts the filter cutoff frequency and bandwidth of the variable parameter digital filter according to the power supply stability index, thereby performing dynamic noise reduction on the fluctuation-sensitive parameters. The dual-mode fault identification module establishes a baseline fault tree under normal power supply conditions and an elastic fault tree under dynamic power supply conditions. The two diagnostic logics run in parallel. By comparing the confidence differences of the diagnostic results under the two modes, false fault signals caused by power supply fluctuations are eliminated. A warning message is triggered only if both modes report the same fault code.

2. The vehicle remote detection method according to claim 1, characterized in that, The power supply status monitoring unit captures in real time the voltage fluctuation waveform of the vehicle power bus, the ripple coefficient of each sensor power supply line, and the transient operating current response curve of key electronic components, including: Multi-channel synchronous sampling technology is used to acquire real-time voltage change data of the vehicle power bus within a preset time period; Real-time acquisition of the periodic ripple voltage amplitude of each sensor's power supply line; Real-time acquisition of transient current response values ​​of key electronic components under different operating loads.

3. The vehicle remote detection method according to claim 2, characterized in that, The three-dimensional power supply quality evaluation model, based on waveform, ripple coefficient, and transient response curve, dynamically generates a power supply stability index. This index, presented as a digital twin, maps the potential impact of the current vehicle power supply environment on sensor data acquisition, including: Voltage change data, ripple voltage amplitude, and transient current response values ​​are input into a pre-trained three-dimensional power quality evaluation model; The three-dimensional power quality evaluation model outputs a dynamic power stability index based on input data. The magnitude of the index indicates the degree of impact of the power supply environment on the accuracy of sensor data acquisition.

4. The vehicle remote detection method according to claim 1, characterized in that, The step of aligning the power supply stability index with vehicle operation data in a spatiotemporal manner through the power supply sensing data fusion module to identify the coupling relationship between power supply fluctuations and sensor data anomalies includes: Acquire the timestamps for vehicle operation data collection and power supply stability index generation; Align the power supply stability index with vehicle operation data based on timestamps; Analyze the aligned data to determine whether the changes in the power supply stability index are related to abnormal fluctuations in vehicle operation data.

5. The remote vehicle detection method according to claim 1, characterized in that, The adaptive filtering module employs a variable-parameter digital filter, dynamically adjusting the filter cutoff frequency and bandwidth of the variable-parameter digital filter according to the power supply stability index, to dynamically denoise fluctuation-sensitive parameters, including: Based on the power supply stability index, the filter cutoff frequency and filter bandwidth of the variable parameter digital filter are calculated and updated in real time. The fluctuation-sensitive parameters are input to a variable-parameter digital filter for processing, so as to realize intelligent notch filtering in the power supply noise frequency band and eliminate noise components introduced by power supply fluctuations.

6. The vehicle remote detection method according to claim 1, characterized in that, The dual-mode fault discrimination module establishes a baseline fault tree under normal power supply conditions and a resilient fault tree under dynamic power supply conditions, and runs the two diagnostic logics in parallel. By comparing the confidence differences of the diagnostic results under the two modes, false fault signals caused by power supply fluctuations are eliminated, including: Based on historical vehicle operating data and standard fault modes, a baseline fault tree is constructed under normal power supply conditions to diagnose faults under stable power supply conditions. Based on power supply fluctuation simulation data and dynamic calibration parameters, an elastic fault tree under dynamic power supply conditions is constructed to diagnose faults under fluctuating power supply conditions. The denoised vehicle operating data is simultaneously input into the baseline fault tree and the elastic fault tree for diagnosis, and the respective diagnostic results and confidence levels are obtained.

7. The vehicle remote detection method according to claim 6, characterized in that, The method involves comparing the confidence differences of diagnostic results under two modes to eliminate false fault signals caused by power supply fluctuations; a warning message is triggered only when both modes report the same fault code, including: If the diagnostic results of the baseline fault tree and the resilient fault tree are inconsistent, or if the diagnostic results of the two modes are consistent but the confidence difference exceeds the preset threshold, the diagnostic results will be identified as false fault signals and removed. If both the baseline fault tree and the resilient fault tree diagnose the same fault code, and the difference in confidence between the two diagnostic results is within a preset threshold range, then it is considered a real fault, triggering an early warning message push.

8. The vehicle remote detection method according to claim 1, characterized in that, The vehicle operating data includes engine speed, oil pressure, transmission temperature, and braking system status parameters; fluctuation-sensitive parameters include engine speed data and oil pressure data.

9. The vehicle remote detection method according to claim 1, characterized in that, When transmitting vehicle operation data, the vehicle networking module simultaneously encapsulates a power supply stability index, including: Package vehicle operation data and power supply stability index into a unified data frame format; Data frames are transmitted to the cloud platform via mobile networks.

10. The vehicle remote detection method according to claim 1, characterized in that, The cloud platform receives vehicle operation data and power supply stability index, including: The cloud platform receives data frames from the vehicle networking module via a mobile network interface; The cloud platform decapsulates data frames to obtain vehicle operation data and power supply stability index.

Images