Intelligent networked automobile electric control system state monitoring system based on edge calculation

Abstract

The invention discloses an intelligent networked automobile electric control system state monitoring system based on edge computing, and relates to the technical field of electric digital data processing. The intelligent networked automobile electric control system state monitoring system based on edge calculation comprises a steering preparation state monitoring module, a steering execution state monitoring module and a steering return state monitoring module. According to the method, acquisition delay optimization judgment is carried out through real-time analysis of the steering working condition information acquisition process, then synchronous error optimization judgment is carried out through accuracy analysis of the steering state recognition process, and finally load fluctuation optimization judgment is carried out through accuracy analysis of the steering return state recognition process. The effect of improving the monitoring accuracy of the state of the electric control system of the intelligent networked automobile in the steering process of the intelligent networked automobile is achieved, and the problem that in the prior art, the monitoring timeliness of the corresponding steering state in the steering process of the intelligent networked automobile is not high, and consequently the monitoring accuracy of the state of the electric control system of the intelligent networked automobile is not high is solved.

Description

Technical Field

[0001] This invention relates to the field of electronic digital data processing technology, and in particular to a status monitoring system for intelligent connected vehicle electronic control systems based on edge computing. Background Technology

[0002] The intelligent connected vehicle electronic control system is the core of vehicle electronic control, encompassing modules such as the engine control unit (ECU), battery management system (BMS), and autonomous driving domain controller. It is responsible for key functions such as power output, energy management, and intelligent driving. Its hardware is distributed across areas such as the engine compartment, chassis, and passenger compartment, achieving high-speed interconnection via in-vehicle Ethernet or CAN (Controller Area Network) bus. In daily driving, steering operations in parking scenarios are crucial for safety. Compared to normal driving, parking steering requires frequent large-angle turns within a confined space, posing a severe challenge to the stability and reliability of the steering system.

[0003] If a vehicle's electronic control system malfunctions, such as steering gear sticking, sensor drift, or motor overheating, it can easily lead to serious accidents like vehicle swerving or loss of control in confined parking spaces. The specific steps for monitoring vehicle steering status in existing technologies are as follows: First, data acquisition is performed using sensors distributed across key components of the steering system, such as steering angle sensors, torque sensors, and power steering motor current sensors, to collect real-time data on steering angle, steering torque, and power steering motor current. These sensors convert physical signals into electrical signals and transmit them to the data processing unit. Next, data analysis is conducted. The collected steering angle data is used to calculate the deviation between the commanded angle value and the actual value to determine steering accuracy. Steering torque fluctuations are analyzed to identify abnormal conditions such as increases or decreases in torque. Power steering motor current fluctuations are tracked to determine potential risks such as overheating. Finally, a response mechanism is implemented. When the system detects that the above parameters exceed limits, a tiered response mechanism is immediately triggered. First, an alarm is displayed on the instrument panel with sound and light to alert the driver to the steering system malfunction. If the fault continues to worsen, the system actively limits the steering range to prevent loss of control due to oversteering, or switches to a redundant steering mode to ensure the vehicle retains basic steering functionality when parked, reducing the risk of steering failure.

[0004] In existing technologies, both the acquisition of steering condition data and the execution control face significant real-time challenges throughout the entire steering cycle of a vehicle. During the steering condition information acquisition phase, redundancy in the sampling points of sensors (steering angle / torque sensors) during high-frequency steering (such as sudden lane changes) exacerbates the computational load of low-pass filtering, leading to signal phase lag. Conversely, excessively long sampling intervals during low-frequency steering (such as constant speed cruising) can easily result in the loss of transient characteristics, causing filtering convergence delay. At the same time, timing deviations occur when multi-source data (wheel speed, yaw rate) are transmitted via the CAN bus due to the arbitration mechanism. This, combined with the cumulative computational delay from edge computing unit data fusion, ultimately results in a spatiotemporal misalignment between the acquired state and the actual steering action. During the steering execution phase, when the load changes abruptly (such as a sudden increase in steering resistance on a low-friction surface), the lag in the existing algorithm causes a delay in the power assist motor response, resulting in a "sluggish" steering feel. During the return-to-center phase, the nonlinear characteristics of steering damping (such as the damping coefficient of the hydraulic power assist system changing with vehicle speed) coupled with mechanical friction, coupled with the complexity of dynamic decoupling calculations for multiple parameters such as vehicle speed and roll angle, lead to an increased deviation between the return-to-center status monitoring signal and the actual return-to-center angle. This results in the problem of low timeliness of steering status monitoring during the steering process of intelligent connected vehicles, leading to low accuracy of the status monitoring of the intelligent connected vehicle's electronic control system. Summary of the Invention

[0005] To address the technical problems in existing technologies, embodiments of the present invention provide a state monitoring system for intelligent connected vehicle electronic control systems based on edge computing. The technical solution is as follows: A state monitoring system for intelligent connected vehicle electronic control systems based on edge computing is provided, including: a steering preparation state monitoring module, a steering execution state monitoring module, and a steering return-to-center state monitoring module. The steering preparation state monitoring module performs real-time analysis of the steering condition information acquisition process of the intelligent connected vehicle electronic control system during the steering preparation phase to determine whether to optimize the acquisition latency. Acquisition latency optimization involves adjusting the edge node computing resource utilization and the inherent frequency of the steering angle sensor to reduce the acquisition latency of steering condition information. The steering execution state monitoring module performs accuracy analysis of the steering state recognition process of the intelligent connected vehicle electronic control system during the steering execution phase to determine whether to optimize the synchronization error. Synchronization error optimization involves adjusting the feature extraction amount of the edge nodes and the processor clock frequency to reduce the time synchronization error in the steering state recognition process. The steering return-to-center state monitoring module performs accuracy analysis of the steering return-to-center state recognition process of the intelligent connected vehicle electronic control system during the steering return-to-center phase to determine whether to optimize the load fluctuation. Load fluctuation optimization involves adjusting the processing workload of the edge nodes and the input torque of the steering torque sensor to reduce the load fluctuation in the steering return-to-center state recognition process.

[0006] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: 1. The system analyzes data acquisition real-time performance during the preparation phase to determine if data acquisition latency needs optimization; analyzes identification accuracy during the execution phase to determine if synchronization error needs optimization; and analyzes identification accuracy during the return-to-center phase to determine if load fluctuation needs optimization. This system provides targeted monitoring in stages. During steering preparation, it focuses on data acquisition latency, addressing it by adjusting resources and sensor sampling frequencies. During the execution phase, it focuses on synchronization errors, optimizing node characteristics and clock frequencies. During the return-to-center phase, it emphasizes load fluctuations, adjusting workload and sensor torque processing. Each stage is independent yet collaborative, enabling precise identification and resolution of different issues, improving the accuracy of steering status monitoring, and ensuring safe and stable driving. 2. By acquiring the acquisition delay data from the steering condition information collection of the intelligent connected vehicle's electronic control system, and simultaneously retrieving the maximum allowable acquisition delay data from the database, the acquisition delay correlation index is obtained by calculating the ratio and then averaging the results. Compared with existing technologies, this method quantifies and integrates multiple delay data by calculating the acquisition delay correlation index. This allows for a comprehensive and accurate quantification of the impact of acquisition delay on the real-time performance of steering condition information collection, providing a strong basis for optimizing the electronic control system, improving the real-time performance and reliability of steering condition information collection, and ensuring the safe and stable operation of intelligent connected vehicles. 3. First, the method compares the acquired acquisition latency correlation index with the database setting value. If the index is greater, the CPU frequency of the edge nodes is adjusted to optimize the acquisition latency. If this is still insufficient, the sampling frequency of the steering angle sensor is adjusted. If the adjustment meets the requirements, the steering execution phase begins; otherwise, a steering preparation status monitoring and warning is issued. Compared with existing technologies, this method optimizes in steps. It first adjusts the computing resources of the edge nodes to reduce the latency caused by their occupancy. If this is ineffective, the sampling frequency of the steering angle sensor is adjusted. This method specifically addresses the problem of untimely updates, reducing acquisition latency more accurately and efficiently, ensuring the real-time performance and accuracy of steering condition information acquisition, and making the steering operation of intelligent connected vehicles safer and more stable. 4. By comparing the time synchronization deviation of multi-source sensors in steering status recognition with set values ​​and maximum allowable values, if the deviation is not greater than the set value, the steering returns to center; if it is greater than the set value but not greater than the maximum allowable value, the synchronization error is optimized; if it is greater than the maximum allowable value, a warning is issued. Compared with existing technologies, this method accurately compares deviation values ​​and handles different cases. If the deviation is outside the reasonable range but does not exceed the maximum allowable value, it can optimize both the amount of feature extraction from edge nodes and the processor clock frequency, improving data time alignment and reducing accumulated errors. If the optimization meets the standards, the steering returns to center smoothly; if it does not meet the standards, a warning is issued in time, effectively ensuring the accuracy and reliability of steering status recognition in intelligent connected vehicles. Attached Figure Description

[0007] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0008] Figure 1 A schematic diagram of the structure of a state monitoring system for an intelligent connected vehicle electronic control system based on edge computing, provided in an embodiment of the present invention; Figure 2 The execution flowchart of the steering preparation status monitoring module provided in the embodiment of the present invention; Figure 3 The execution flowchart of the steering execution status monitoring module provided in this embodiment of the invention; Figure 4 The execution flowchart of the steering return status monitoring module provided in the embodiment of the present invention is shown. Detailed Implementation

[0009] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0010] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0011] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0012] This invention provides a status monitoring system for intelligent connected vehicle electronic control systems based on edge computing, such as... Figure 1 The diagram shows the structure of a state monitoring system for an intelligent connected vehicle electronic control system based on edge computing. This system may include the following modules: a steering preparation state monitoring module, a steering execution state monitoring module, and a steering return state monitoring module.

[0013] The steering preparation status monitoring module is used to perform real-time analysis of the steering condition information (including steering angle, steering torque, braking pressure, suspension stiffness, wheel speed, etc.) of the intelligent connected vehicle's electronic control system during the steering preparation phase. This analysis determines whether to optimize the acquisition delay. Acquisition delay optimization means reducing the acquisition delay of steering condition information by adjusting the resource utilization rate of edge nodes and the inherent frequency of the steering angle sensor. This helps ensure that the steering condition information is obtained in a timely and accurate manner, providing a reliable data foundation for subsequent steering operations.

[0014] The steering execution status monitoring module is used to analyze the accuracy of the steering status recognition process of the intelligent connected vehicle's electronic control system during the steering execution phase, in order to determine whether to perform synchronization error optimization. Synchronization error optimization means reducing the time synchronization error in the steering status recognition process by adjusting the feature extraction amount of edge nodes and the processor clock frequency, which helps to ensure accurate judgment of the steering status and avoid misoperation.

[0015] The steering return-to-center status monitoring module is used to analyze the accuracy of the steering return-to-center status identification process of the intelligent connected vehicle's electronic control system during the steering return-to-center phase, in order to determine whether load fluctuation optimization should be performed. Load fluctuation optimization means reducing load fluctuations during the steering return-to-center status identification process and improving the return-to-center control effect by adjusting the processing workload of edge nodes and the input torque of the steering torque sensor.

[0016] In addition, a database is established before designing the edge computing-based intelligent connected vehicle electronic control system status monitoring system to store various set data. The database includes, but is not limited to, set acquisition delay correlation indicators, set time synchronization deviations, and set steering return time data. The set acquisition delay correlation indicators can be set based on the actual steering scenarios of the intelligent connected vehicle electronic control system. For example, the set acquisition delay correlation indicators can be represented by the sum and average of historical acquisition delay correlation indicators of the intelligent connected vehicle electronic control system in the historical steering condition information acquisition process in the database. In addition, various values ​​in the database can be set and fine-tuned by technicians according to actual debugging.

[0017] In this embodiment, the system is optimized in stages, which effectively solves the problem of low accuracy of state monitoring in intelligent connected vehicle electronic control systems caused by the low timeliness of steering state monitoring in the prior art, thereby improving driving safety and stability.

[0018] Furthermore, a real-time analysis is conducted on the steering condition information acquisition process of the intelligent connected vehicle electronic control system. Specifically, this involves acquiring acquisition delay data during the steering condition information acquisition process, simultaneously retrieving the maximum allowable acquisition delay data from the database, performing ratio calculations between the acquired acquisition delay data and the corresponding maximum allowable acquisition delay data, and summing and averaging the results of each ratio calculation to obtain an acquisition delay correlation index. This index quantifies the impact of acquisition delay data on the real-time performance of steering condition information acquisition. The acquisition delay data includes data interaction communication delay and steering command interaction delay, both of which are processed by the intelligent connected vehicle electronic control system. The system's built-in clock timing function is used to obtain the data interaction communication delay, which reflects the average response time of the communication link between various modules in the intelligent connected vehicle electronic control system. The steering command interaction delay reflects the average response time of the steering control command from being issued to the corresponding module in the intelligent connected vehicle electronic control system. The maximum allowable acquisition delay data includes the maximum allowable data interaction communication delay and the maximum allowable steering command interaction delay. The maximum allowable data interaction communication delay and the maximum allowable steering command interaction delay are respectively represented by the sum and average of the maximum values ​​of the historical data interaction communication delay and the historical steering command interaction delay in the historical steering condition information acquisition process of the intelligent connected vehicle electronic control system in the database.

[0019] In this embodiment, increased data interaction communication latency slows down the synchronization of information among modules in the intelligent connected vehicle's electronic control system, leading to increased steering command interaction latency, as commands need to wait for complete data before they can be effectively executed. Conversely, excessively long steering command interaction latency may trigger repeated data interactions or timeout retransmissions, further extending the data interaction communication latency. These two factors mutually constrain each other, jointly affecting the real-time performance of steering condition information acquisition.

[0020] By quantifying and collecting latency-related indicators, the root cause of latency can be accurately located, communication links or command processes can be optimized, and the impact of latency can be monitored and evaluated in real time. This can provide early warning of potential risks, ensure the accuracy and safety of steering control, and provide data support for the performance optimization of the electronic control system of intelligent connected vehicles, thereby improving the response speed and stability of intelligent connected vehicles under complex operating conditions.

[0021] like Figure 2The diagram shows the execution flowchart of the steering preparation status monitoring module provided in this embodiment of the invention. Its design logic is as follows: First, it enters the steering preparation stage and collects steering condition information. Then, it determines whether the collection delay correlation index exceeds the set value. If it exceeds the set value, it first adjusts the CPU frequency of the edge node and then checks the optimized index. If it still exceeds the set value, it optimizes the inherent frequency of the steering angle sensor and verifies whether its collection delay correlation index exceeds the set value. If the collection delay correlation index exceeds the set value, it issues a steering preparation status warning. If the collection delay correlation index does not exceed the set value or meets the standard after a series of optimizations, it enters the intelligent connected vehicle steering execution stage, thereby ensuring the stability and reliability of the steering system.

[0022] Further understanding is needed regarding the determination of whether to perform data acquisition delay optimization. Specifically, it involves determining whether the acquired data acquisition delay correlation index is greater than the data acquisition delay correlation index set in the database. If so, data acquisition delay optimization is performed; otherwise, the vehicle enters the intelligent connected vehicle steering execution phase.

[0023] Specifically, the acquisition delay optimization involves mapping the acquired acquisition delay correlation index deviation to the database to obtain an adjustment value for the edge node's computing resource utilization rate. Based on this adjustment value, the CPU frequency of the current edge node is reduced to decrease the acquisition delay caused by the edge node's computing resource utilization rate. The acquisition delay correlation index deviation represents the difference between the acquired acquisition delay correlation index and the set acquisition delay correlation index. After adjusting the edge node's computing resource utilization rate, if the acquisition delay correlation index obtained from the re-acquisition of steering condition information is greater than the set acquisition delay correlation index in the database, it indicates that the effectiveness of the current edge node's computing resource utilization rate adjustment does not meet the expected requirements, and the inherent frequency of the steering angle sensor is optimized. Otherwise, the vehicle enters the intelligent connected vehicle steering execution stage.

[0024] It is important to understand that the optimization of the inherent frequency of the steering angle sensor is as follows: the deviation of the acquisition delay correlation index re-acquired after the edge node computing resource utilization rate is adjusted is mapped into the database to obtain the adjustment value of the inherent frequency of the steering angle sensor. Based on this adjustment value, the sampling frequency of the current steering angle sensor is increased to reduce the acquisition process delay caused by the untimely update of the inherent frequency of the steering angle sensor. After the inherent frequency of the steering angle sensor is adjusted, if the re-acquired acquisition delay correlation index is not greater than the acquisition delay correlation index set in the database, the acquisition delay optimization is completed and the vehicle enters the steering execution stage of the intelligent connected vehicle; otherwise, a steering preparation status monitoring and warning is issued.

[0025] In this embodiment, since the acquired acquisition delay correlation index is greater than the set acquisition delay correlation index, it indicates that the current acquisition process delay exceeds the expected delay. At this point, a pre-set multiple linear regression model in the database is used to train the model based on historical edge node computational resource utilization, steering angle sensor inherent frequency, and acquisition delay correlation index deviation. Simultaneously, based on the trained multiple linear regression model and combined with a linear regression algorithm, the edge node CPU frequency is reduced and the steering angle sensor sampling frequency is increased, thereby adjusting the edge node computational resource utilization and the steering angle sensor inherent frequency. This optimization mechanism precisely solves the acquisition delay problem through a hierarchical progressive strategy, improving the real-time performance and safety of intelligent connected vehicle steering conditions. Hierarchical optimization reduces resource waste caused by blind adjustments, while real-time monitoring and early warning mechanisms ensure the stable operation of the steering system, providing reliable data support for autonomous driving decisions.

[0026] like Figure 3 The diagram shows the execution flowchart of the steering execution status monitoring module provided in this embodiment of the invention. Its design logic is as follows: After steering execution begins, it first checks whether the time synchronization deviation is within a set value. If the deviation meets the requirements, it directly enters the steering return-to-center stage. If the deviation exceeds the set value, it adjusts the edge node feature extraction amount and the processor clock frequency, and then checks again whether the optimized deviation meets the requirements. If it does, it enters the steering return-to-center stage; if it still does not meet the requirements, it triggers a steering status recognition warning. This logic ensures the accuracy of time synchronization during steering execution, guaranteeing the stable operation and safety of the vehicle steering system.

[0027] Further understanding is needed regarding the determination of whether to perform synchronization error optimization. Specifically, based on the time synchronization deviation of the multi-source sensors corresponding to the intelligent connected vehicle electronic control system during the steering state recognition process, the time synchronization deviation and the maximum allowable time synchronization deviation set in the database are compared and analyzed. If the obtained time synchronization deviation is not greater than the set time synchronization deviation, the intelligent connected vehicle enters the steering return-to-center stage. If the obtained time synchronization deviation is greater than the set time synchronization deviation but not greater than the maximum allowable time synchronization deviation, synchronization error optimization is performed. If the obtained time synchronization deviation is greater than the maximum allowable time synchronization deviation, a warning is issued for the steering state recognition process. The time synchronization deviation is used to quantify the timestamp difference of the synchronous acquisition data from multi-source sensors (such as steering angle sensors, wheel speed sensors, accelerometers, etc.). The set time synchronization deviation is represented by the sum and average of the historical time synchronization deviations of the intelligent connected vehicle electronic control system in the historical steering state recognition process in the database. The maximum allowable time synchronization deviation is represented by the sum and average of the maximum values ​​of the historical time synchronization deviations of the intelligent connected vehicle electronic control system in each historical steering state recognition process in the database.

[0028] The synchronization error optimization specifically involves: mapping the acquired time synchronization deviation value to the database to obtain an adjustment value for the feature extraction amount of the edge node; increasing the sampling window length of the current edge node based on this adjustment value to improve the time alignment of multi-source sensor data; the time synchronization deviation value represents the difference between the acquired time synchronization deviation and the set time synchronization deviation, which represents the maximum value corresponding to the average acquisition time deviation during the multi-source sensor data acquisition process, obtained through the clock timing function built into the intelligent connected vehicle electronic control system; mapping the acquired time synchronization deviation value to the database to obtain an adjustment value for the processor clock frequency; increasing the current processor clock frequency based on this adjustment value to reduce accumulated errors; after synchronization error optimization, if the time synchronization deviation obtained from the re-entry of steering state recognition is not greater than the set time synchronization deviation, the synchronization error optimization is completed and the intelligent connected vehicle enters the steering return-to-center stage; otherwise, a warning is issued during the steering state recognition process; synchronization error optimization includes adjustment of the feature extraction amount of the edge node and adjustment of the processor clock frequency.

[0029] In this embodiment, if the acquired time synchronization deviation is greater than the set time synchronization deviation, it indicates that the data acquisition from the multi-source sensors is lagging. At this point, a preset linear regression algorithm is used to increase the sampling window length of the edge nodes, extending the sampling window to capture more historical data and improve time alignment. Simultaneously, a preset software clock compensation algorithm is used to increase the processor clock frequency to accelerate synchronization signal updates, thereby suppressing the accumulated error caused by multi-source sensor clock drift. This dual-layer optimization mechanism avoids the limitations of a single adjustment, reduces the risk of misjudging the steering state due to sensor time asynchrony, ensures the system quickly converges to the allowable error range, provides accurate data support for the steering return phase, and improves driving safety and stability.

[0030] Furthermore, an accuracy analysis is conducted on the steering return-to-center state recognition process of the intelligent connected vehicle electronic control system. Specifically, this involves: acquiring steering return-to-center time data during the steering return-to-center state recognition process of the intelligent connected vehicle electronic control system; simultaneously retrieving the set steering return-to-center time data from the database; performing ratio calculations between the acquired steering return-to-center time data and the set steering return-to-center time data; and simultaneously correcting the ratio calculation results by combining the steering return-to-center time data correction values ​​from the database, and performing coupling processing to obtain the steering return-to-center state recognition impact index.

[0031] The steering return time data includes the dynamic planning time of the return path, the collaborative control time of the multi-domain controller, and the decision-making time of the multi-sensor fusion. All of these are obtained through the clock timing function built into the intelligent connected vehicle electronic control system. The set steering return time data includes the set dynamic planning time of the return path, the collaborative control time of the multi-domain controller, and the decision-making time of the multi-sensor fusion. The steering return time data correction value includes the correction value of the dynamic planning time of the return path, the correction value of the collaborative control time of the multi-domain controller, and the correction value of the decision-making time of the multi-sensor fusion. The steering return state recognition influence index is used to quantify the degree of influence of the steering return time data on the accuracy of steering return state recognition. The steering return state recognition influence index represents the result of the coupled processing of the dynamic planning time score of the return path, the collaborative control time score of the multi-domain controller, and the decision-making time score of the multi-sensor fusion.

[0032] Specifically, the specific constraint expression for the indicator Y affecting the steering return state identification is as follows: In the formula, Y represents the steering return state recognition impact index of the intelligent connected vehicle electronic control system in the steering return state recognition process, Y1 represents the dynamic planning time score of the return path in the steering return state recognition process of the intelligent connected vehicle electronic control system, Y2 represents the multi-domain controller collaborative control time score of the intelligent connected vehicle electronic control system in the steering return state recognition process, and Y3 represents the multi-sensor fusion decision time score of the intelligent connected vehicle electronic control system in the steering return state recognition process.

[0033] The specific constraint expression for the dynamic programming time score Y1 of the correct path is: The specific constraint expression for the multi-domain controller collaborative control duration fraction Y2 is as follows: The specific constraint expression for the multi-sensor fusion decision duration score Y3 is as follows: In the formula, This represents the adjustment value for the dynamic programming time of the return path. This indicates the time taken for the intelligent connected vehicle's electronic control system to dynamically plan the return-to-center path during the steering return-to-center state recognition process. This represents the set dynamic programming time for the return-to-center path, which is the sum and average of the historical dynamic programming times for the return-to-center path in the historical steering return-to-center state identification process of the intelligent connected vehicle electronic control system in the database. This indicates the correction value for the duration of multi-domain controller collaborative control. This indicates the duration of multi-domain controller collaborative control in the steering return-to-center state recognition process of the intelligent connected vehicle's electronic control system. This represents the set multi-domain controller collaborative control duration, which is the sum and average of the historical multi-domain controller collaborative control durations during the historical steering return state identification process of the intelligent connected vehicle electronic control system in the database. This represents the correction value for the decision-making time of multi-sensor fusion. This indicates the multi-sensor fusion decision-making time of the intelligent connected vehicle's electronic control system during the steering return-to-center state recognition process. The set multi-sensor fusion decision duration is represented by the summation and averaging of the historical multi-sensor fusion decision durations of the historical intelligent connected vehicle electronic control system in the historical steering return state recognition process in the database.

[0034] The database stores preset correction values ​​closely related to the steering return state identification impact index. These correction values ​​establish a predefined mapping relationship with the corresponding dynamic planning time score of the return path, the collaborative control time score of the multi-domain controller, and the decision-making time score of the multi-sensor fusion. It is worth noting that this mapping is not arbitrarily set; it can be a one-to-one correspondence or a many-to-one relationship. In practical applications, the real-time acquired dynamic planning time score of the return path, the collaborative control time score of the multi-domain controller, and the decision-making time score of the multi-sensor fusion can be directly input into this preset mapping relationship. This allows for the rapid and accurate extraction of the dynamic planning time correction value of the return path, the collaborative control time correction value of the multi-domain controller, and the decision-making time correction value of the multi-sensor fusion, which match the steering return state identification impact index.

[0035] Most importantly, to ensure the consistency and comparability of the evaluation, the values ​​of the dynamic programming time correction for the homing path, the collaborative control time correction for the multi-domain controller, and the decision-making time correction for the multi-sensor fusion in this example are strictly limited to between 0 and 1, and the sum of the three is 1.

[0036] In this embodiment, the impact index of steering return state recognition increases with the increase of the dynamic planning time of the return path, the collaborative control time of the multi-domain controller, and the decision-making time of the multi-sensor fusion. Specifically, the increased dynamic planning time of the return path prolongs the global task scheduling cycle, causing the multi-domain controller to wait for path data to become ready during collaborative control, indirectly lengthening the collaborative control time. Simultaneously, the multi-sensor fusion decision requires fusing path information over a longer time span, thus increasing the decision-making time. The increased collaborative control time of the multi-domain controller consumes more computing resources, forcing the path planning algorithm to simplify to reduce computational load, potentially lowering path accuracy. However, the fusion decision module may shorten the decision-making time due to improved data consistency. The increased multi-sensor fusion decision time leads to feedback delay, requiring the generation of more robust paths to reduce decision complexity. Simultaneously, the collaborative control module needs to adjust its control frequency to match the decision output rhythm. These three factors form a dynamic coupling relationship; optimization of a single parameter may cause fluctuations in other parameters.

[0037] By considering the aforementioned mutual influence mechanisms, it is helpful to achieve global optimization of the steering return state of the intelligent connected vehicle electronic control system. Traditional isolated adjustment of parameters can easily lead to local optima but overall performance degradation (e.g., excessively shortening the path planning time may cause cooperative control failure), while coupling analysis can identify key constraints (such as resource competition and data dependency chains) and balance the relationship among the three through multi-objective optimization algorithms (such as weighted summation or Pareto front). For example, when the cooperative control time becomes a bottleneck, the complexity of the path planning algorithm and the sensor sampling frequency can be optimized simultaneously to shorten the total time while ensuring decision accuracy.

[0038] like Figure 4 The diagram shows the execution flowchart of the steering return state monitoring module provided in this embodiment of the invention. Its design logic is as follows: After entering the steering return stage, it first determines whether the return state influencing indicator exceeds a set value. If it does, it first performs edge node load correction, then checks the corrected indicator. If it still exceeds the standard, it further performs steering torque sensor input torque correction. After correction, it checks whether the indicator is qualified again. If it is qualified, the electronic control system status monitoring is completed. If the return state influencing indicator is still unqualified after correction, a steering return state warning is triggered. This logic helps to promptly detect problems and take measures to ensure the stability and reliability of the steering return process.

[0039] Further understanding is needed regarding the determination of whether to perform load fluctuation optimization. Specifically, the difference between the acquired steering return state identification impact index and the steering return state identification impact index set in the database is compared. If the acquired steering return state identification impact index is greater than the set steering return state identification impact index, then load fluctuation optimization is performed; otherwise, the status monitoring of the intelligent connected vehicle electronic control system is completed. The status monitoring of the intelligent connected vehicle electronic control system includes monitoring of the steering condition information acquisition process, the steering state identification process, and the steering return state identification process.

[0040] The load fluctuation optimization specifically involves mapping the deviation of the acquired steering return state identification impact index in the database to obtain the edge node load correction value. Based on this correction value, the workload of the edge node's computing resource allocation is adjusted to reduce the load fluctuation of the edge node caused by the untimely update of the computing resource allocation workload. The deviation of the steering return state identification impact index represents the difference between the acquired steering return state identification impact index and the set steering return state identification impact index. The set steering return state identification impact index is represented by the summation and averaging of the historical steering return state identification impact indices of the intelligent connected vehicle electronic control system in the historical steering return state identification process in the database. After the edge node load is corrected, if the steering return state identification impact index obtained after re-identifying the steering return state is greater than the set steering return state identification impact index, it indicates that the effectiveness of the current edge node load correction does not meet the expected requirements, and the input torque of the steering torque sensor is optimized. Otherwise, the status monitoring of the intelligent connected vehicle electronic control system is completed.

[0041] The optimization of the steering torque sensor input torque is specifically as follows: the deviation of the steering return state identification influence index obtained after edge node load correction is mapped into the database to obtain the steering torque sensor input torque correction value. Based on this correction value, the zero-point offset of the steering torque sensor is corrected to reduce the input torque measurement distortion caused by the zero-point offset. After the steering torque sensor input torque is corrected, if the newly obtained steering return state identification influence index is not greater than the steering return state identification influence index set in the database, the load fluctuation optimization is completed and the state monitoring of the intelligent connected vehicle electronic control system is completed; otherwise, a warning is issued for the steering return state identification process.

[0042] In this embodiment, since the obtained steering return state recognition impact index is greater than the set steering return state recognition impact index, it indicates that the steering return state recognition accuracy of the current intelligent connected vehicle electronic control system is not high. At this time, in response to the load fluctuation of the edge node, a dynamic resource allocation algorithm based on reinforcement learning is adopted: taking the deviation of the steering return state recognition impact index as input, learning historical correction data through the Q-learning model, and dynamically generating the edge node computing resource allocation task quantity correction value. The algorithm adjusts the resource weight according to the real-time load status (such as CPU utilization and task queue length), giving priority to ensuring the resource needs of high-priority tasks (such as path planning and control decision-making), and reducing the latency fluctuation caused by resource competition.

[0043] To address the zero-point offset of the steering torque sensor, a least squares fitting calibration algorithm is employed: by collecting multiple sets of sensor output values ​​under static torque, an input-output error model is constructed, and the optimal zero-point offset correction value is solved using the least squares method to eliminate the influence of environmental factors on measurement accuracy and ensure the authenticity of the input torque data.

[0044] It's important to understand that the correction in this example doesn't specify a concrete direction because a dynamic correction mechanism is used. On one hand, the operating environment of intelligent connected vehicles is complex and variable; different operating conditions have varying impacts on the load of edge nodes and the zero-point offset of the steering torque sensor, making it impossible to predetermine a fixed correction direction. On the other hand, the correction value obtained based on database mapping is dynamically generated according to real-time deviations in impact indicators. This allows for precise adaptation by combining historical data with the current state. This dynamic adjustment can more effectively address various uncertainties, ensuring optimal correction results in different scenarios, guaranteeing the accuracy of steering return-to-center status recognition, and ultimately ensuring the stable operation of the intelligent connected vehicle's electronic control system.

[0045] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. A computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

[0046] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0047] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0048] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0049] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0050] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A status monitoring system for intelligent connected vehicle electronic control systems based on edge computing, characterized in that, include: Steering preparation status monitoring module, steering execution status monitoring module, and steering return status monitoring module; The steering preparation status monitoring module is used to perform real-time analysis of the steering condition information collection process of the intelligent connected vehicle electronic control system during the steering preparation stage of the intelligent connected vehicle, so as to determine whether to optimize the collection delay. The collection delay optimization means reducing the collection delay of steering condition information by adjusting the edge node computing resource occupancy rate and the inherent frequency of the steering angle sensor. The steering execution status monitoring module is used to analyze the accuracy of the steering status recognition process of the intelligent connected vehicle electronic control system during the steering execution phase of the intelligent connected vehicle, so as to determine whether to optimize the synchronization error. The synchronization error optimization means reducing the time synchronization error in the steering status recognition process by adjusting the feature extraction amount of edge nodes and the processor clock frequency. The steering return state monitoring module is used to perform an accuracy analysis of the steering return state identification process of the intelligent connected vehicle's electronic control system during the steering return phase, in order to determine whether load fluctuation optimization should be performed. The load fluctuation optimization means reducing load fluctuations during the steering return state identification process by adjusting the processing workload of edge nodes and the input torque of the steering torque sensor.

2. The edge computing-based intelligent connected vehicle electronic control system status monitoring system as described in claim 1, characterized in that, The real-time analysis of the steering condition information collection process of the intelligent connected vehicle electronic control system specifically includes: Acquire the acquisition delay data of the intelligent connected vehicle electronic control system during the steering condition information acquisition process, and simultaneously obtain the maximum allowable acquisition delay data from the database. Calculate the ratio of the acquired acquisition delay data with the corresponding maximum allowable acquisition delay data, and process the results of each ratio calculation to obtain the acquisition delay correlation index to quantify the impact of acquisition delay data on the real-time performance of steering condition information acquisition. The collected delay data includes data interaction communication delay and steering command interaction delay. The data interaction communication delay is used to reflect the average response time of the communication link between modules in the intelligent connected vehicle electronic control system, and the steering command interaction delay is used to reflect the average response time of the steering control command from being issued to the corresponding module in the intelligent connected vehicle electronic control system.

3. The edge computing-based intelligent connected vehicle electronic control system status monitoring system as described in claim 2, characterized in that, The determination of whether to perform data acquisition delay optimization specifically involves: Determine whether the acquired acquisition delay correlation index is greater than the acquisition delay correlation index set in the database. If so, optimize the acquisition delay; otherwise, proceed to the intelligent connected vehicle steering execution stage. The optimization of the acquisition delay specifically includes: Based on the deviation of the acquired acquisition latency correlation index, the edge node computing resource utilization adjustment value is obtained by mapping it in the database. The CPU frequency of the edge node is then adjusted to reduce the acquisition process latency caused by the edge node computing resource utilization. If, after adjusting the computing resource utilization rate of the edge node, the acquisition delay correlation index obtained by re-collecting steering condition information is greater than the acquisition delay correlation index set in the database, it indicates that the effectiveness of the current adjustment of the computing resource utilization rate of the edge node does not meet the expected requirements, and the inherent frequency of the steering angle sensor is optimized; otherwise, the vehicle enters the steering execution stage of the intelligent connected vehicle.

4. The edge computing-based intelligent connected vehicle electronic control system status monitoring system as described in claim 3, characterized in that, The optimization of the inherent frequency of the steering angle sensor is specifically as follows: The deviation of the acquisition delay correlation index re-acquired after the edge node computing resource occupancy rate is adjusted is mapped in the database to obtain the inherent frequency adjustment value of the steering angle sensor. The sampling frequency of the steering angle sensor is then adjusted to reduce the acquisition delay caused by the untimely update of the inherent frequency of the steering angle sensor. After the inherent frequency of the steering angle sensor is adjusted, if the newly acquired acquisition delay correlation index is not greater than the acquisition delay correlation index set in the database, the acquisition delay optimization is completed and the vehicle enters the steering execution stage of the intelligent connected vehicle; otherwise, a steering preparation status monitoring and warning is issued.

5. The edge computing-based intelligent connected vehicle electronic control system status monitoring system as described in claim 1, characterized in that, The determination of whether to perform synchronization error optimization is specifically as follows: Based on the time synchronization deviation of multiple source sensors corresponding to the steering state recognition process of the intelligent connected vehicle electronic control system, a comparative analysis was performed with the time synchronization deviation and the maximum allowable time synchronization deviation set in the database. If the obtained time synchronization deviation is not greater than the set time synchronization deviation, the vehicle will enter the steering return phase of the intelligent connected vehicle. If the obtained time synchronization deviation is greater than the set time synchronization deviation but not greater than the maximum allowable time synchronization deviation, then synchronization error optimization is performed. If the obtained time synchronization deviation is greater than the maximum allowable time synchronization deviation, an early warning will be issued during the steering status identification process. The time synchronization deviation is used to quantify the timestamp differences in data acquired synchronously by multiple source sensors.

6. The edge computing-based intelligent connected vehicle electronic control system status monitoring system as described in claim 5, characterized in that, The synchronization error optimization specifically includes: Based on the obtained time synchronization deviation values, the feature extraction amount adjustment value of the edge nodes is obtained by mapping them to the database, and the sampling window length of the edge nodes is adjusted to improve the time alignment of multi-source sensor data. Based on the acquired time synchronization deviation values, the processor clock frequency adjustment value is mapped into the database to compensate for the clock drift generated by the multi-source sensors, thereby reducing the cumulative error. After the synchronization error is optimized, if the time synchronization deviation obtained by re-identifying the steering status is not greater than the set time synchronization deviation, the synchronization error optimization is completed and the vehicle enters the steering return-to-center stage of the intelligent connected vehicle; otherwise, a warning is issued for the steering status identification process. The synchronization error optimization includes adjusting the feature extraction amount of edge nodes and adjusting the processor clock frequency.

7. The edge computing-based intelligent connected vehicle electronic control system status monitoring system as described in claim 1, characterized in that, The accuracy analysis of the steering return-to-center state recognition process of the intelligent connected vehicle electronic control system is as follows: The system acquires steering return time data during the steering return state recognition process of the intelligent connected vehicle electronic control system, and simultaneously retrieves the set steering return time data from the database. The acquired steering return time data is then compared with the set steering return time data. At the same time, the results of each ratio calculation are corrected by combining the steering return time data correction value in the database and coupled to obtain the steering return state recognition impact index, which is used to quantify the degree of influence of steering return time data on the accuracy of steering return state recognition. The steering return time data includes the dynamic planning time of the return path, the collaborative control time of the multi-domain controller, and the decision-making time of the multi-sensor fusion.

8. The edge computing-based intelligent connected vehicle electronic control system status monitoring system as described in claim 7, characterized in that, The determination of whether to perform load fluctuation optimization specifically involves: If the obtained steering return state identification impact index is greater than the set steering return state identification impact index, then load fluctuation optimization is performed; otherwise, the state monitoring of the intelligent connected vehicle electronic control system is completed. The status monitoring of the intelligent connected vehicle electronic control system includes monitoring the steering condition information acquisition process, the steering status recognition process, and the steering return-to-center status recognition process.

9. The edge computing-based intelligent connected vehicle electronic control system status monitoring system as described in claim 8, characterized in that, The load fluctuation optimization specifically includes: Based on the deviation of the identified turning and returning status, the edge node load correction value is obtained by mapping it to the database. The computing resource allocation task of the edge node is corrected to reduce the load fluctuation of the edge node caused by the untimely update of the computing resource allocation task. After the load correction at the edge node, if the steering return state recognition impact index obtained by re-identifying the steering return state is greater than the set steering return state recognition impact index, then the input torque of the steering torque sensor will be optimized; otherwise, the status monitoring of the intelligent connected vehicle electronic control system will be completed.

10. The edge computing-based intelligent connected vehicle electronic control system status monitoring system as described in claim 9, characterized in that, The optimization of the steering torque sensor input torque is specifically as follows: Based on the deviation of the steering return state identification index obtained after edge node load correction, the steering torque sensor input torque correction value is mapped in the database to calibrate the zero point offset of the steering torque sensor to reduce the input torque measurement distortion caused by the zero point offset. After the steering torque sensor input torque is corrected, if the steering return state identification impact index is not greater than the steering return state identification impact index set in the database, then the load fluctuation optimization is completed and the state monitoring of the intelligent connected vehicle electronic control system is completed; otherwise, a warning is issued for the steering return state identification process.

Images