Intelligent driving system domain controller time synchronization self-detection method and system

Abstract

The invention relates to an intelligent driving system domain controller time synchronization self-detection method and system, and the method comprises the steps: M1, enabling a vehicle to run on a road, enabling a domain controller to regularly send a synchronization message to each sensor, obtaining the data information of the time when each sensor receives the synchronization message, timestamp marking is carried out on data collected by each sensor during working to obtain data information of a timestamp of the data collected by each sensor, and an improved exponential smoothing algorithm based on a self-adaptive error factor is adopted to predict time deviation of each sensor; and the predicted data information of the time deviation of each sensor is obtained. According to the method, the time synchronization state of each sensor in the intelligent driving system can be monitored in real time, the problem of inconsistent timestamps can be found and corrected in time, and the timeliness and consistency of data are ensured, so that the decision and control precision of automatic driving is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a time synchronization self-detection method and system for a domain controller of an intelligent driving system. Background Art

[0002] Intelligent driving systems rely on information from a variety of sensors for decision-making and control, including integrated navigation, radar, and cameras. These sensors each have independent clock systems, and due to hardware differences, environmental factors, or network latency, their timestamps may be inconsistent. Inconsistent timestamps can affect data synchronization, leading to errors in data processing by the intelligent driving system, and thus compromising the safety and reliability of autonomous driving.

[0003] While existing time synchronization solutions exist, such as the GPS-based "PPS+NMEA" time synchronization mechanism and the Ethernet-based IEEE 1588 / 802.1AS (PTP / gPTP) clock synchronization protocol, these solutions still have some shortcomings in practical applications. For example, GPS signals may be blocked or interfered with, resulting in unstable time synchronization; and PTP / gPTP protocols may experience reduced synchronization accuracy in complex network environments. Furthermore, existing solutions lack an effective self-detection mechanism to monitor the time synchronization status in real time and take appropriate countermeasures. Summary of the Invention

[0004] In view of the above shortcomings of the existing technology, the present invention provides a time synchronization self-detection method and system for the domain controller of an intelligent driving system, which can not only monitor the time synchronization status of each sensor in the intelligent driving system in real time, promptly discover and correct the problem of inconsistent timestamps, but also ensure the timeliness and consistency of data, thereby improving the decision-making and control accuracy of autonomous driving.

[0005] In order to achieve the above-mentioned and other related purposes, the present invention provides the following technical solutions: A time synchronization self-detection method for a domain controller of an intelligent driving system, the method comprising: M1. When a vehicle is driving on the road, the domain controller regularly sends synchronization messages to each sensor and obtains data information about the time when each sensor receives the synchronization message. It also timestamps the data collected by each sensor during operation and obtains data information about the timestamp of the data collected by each sensor. M2. Based on the data information of the time when each sensor receives the synchronization message and the data information of the timestamp of the data collected by each sensor, the time deviation of each sensor is predicted using an improved exponential smoothing algorithm based on an adaptive error factor to obtain the predicted data information of the time deviation of each sensor; M3 based on the predicted time deviation of each sensor data information, the use of variance-based cumulative average algorithm for the time synchronization of each sensor detection value characterization, to obtain the time synchronization of each sensor detection value data information; M4. Based on the data information of the time-synchronized detection values ​​of the various sensors, a preset threshold is set. If the time-synchronized detection value of each sensor is less than the preset threshold, there is no abnormality. If the time-synchronized detection value of each sensor is greater than the preset threshold, an abnormality occurs and an early warning is triggered.

[0006] Furthermore, in step M2, the use of an improved exponential smoothing algorithm based on an adaptive error factor to predict the time deviation of each sensor includes: M21 based on the data information of the time each sensor receives the synchronization message and the data information of each sensor collecting data timestamp, data alignment processing is performed to obtain the alignment of each sensor receiving the synchronization message time and the data information of the timestamp of the collected data; M22. Based on the alignment of the time information of each sensor receiving the synchronization message and the timestamp of the collected data, establish a time deviation prediction function Q for each sensor, , Among them, y1 is the data information of the time when each sensor receives the synchronization message after the alignment processing, y2 is the data information of the timestamp of the data collected by each sensor after the alignment processing, α1, α2 and α3 are adaptive error factors; M23. Based on the time deviation prediction function Q of each sensor, predict the time deviation of each sensor to obtain data information of the predicted time deviation of each sensor.

[0007] Furthermore, the adaptive error factors α1, α2 and α3 are, , , , Among them, y1 is the data information of the time when each sensor receives the synchronization message after the alignment processing, and y2 is the data information of the timestamp of the data collected by each sensor after the alignment processing.

[0008] Furthermore, the constraint function f of the adaptive error factor is, , , Among them, the value range of the constraint function f is (1,2).

[0009] Furthermore, in step M3, the characterization of the time-synchronized detection values ​​of each sensor using a variance-based cumulative average algorithm includes: M31. Based on the predicted time deviation data information of each sensor, normalization is performed to obtain the normalized time deviation data information of each sensor; M32. Based on the normalized data information of the time deviation of each sensor, establish the cumulative average function R of the sensor time synchronization deviation, , Among them, x i is the time deviation data information of the i-th sensor after normalization, E is the expectation, n is the sample size, β i is the weight coefficient; M33. Based on the cumulative average function R of the sensor time synchronization deviation, the time synchronization detection value of each sensor is characterized to obtain data information of the time synchronization detection value of each sensor.

[0010] Furthermore, the weight coefficient β i The constraints are, .

[0011] In order to achieve the above-mentioned and other related objectives, the present invention further provides a system for implementing any one of the above-mentioned methods for self-detecting time synchronization of a domain controller of an intelligent driving system, the system comprising: The data acquisition module is used to obtain the data information of the time when each sensor receives the synchronization message, and timestamp the data collected by each sensor when it is working, so as to obtain the data information of the timestamp of the data collected by each sensor; A sensor time deviation prediction module is connected to the data acquisition module and is used to predict the time deviation of each sensor using an improved exponential smoothing algorithm based on an adaptive error factor to obtain data information of the predicted time deviation of each sensor; A sensor time synchronization detection value module is connected to the sensor time deviation prediction module and is used to characterize the time synchronization detection value of each sensor using a variance-based cumulative average algorithm to obtain data information of the time synchronization detection value of each sensor; The early warning module is connected to the time synchronization detection value module of the sensor and is used to set a preset threshold. If the time synchronization detection value of each sensor is less than the preset threshold, there is no abnormality. If the time synchronization detection value of each sensor is greater than the preset threshold, an abnormality occurs and an early warning is triggered.

[0012] Furthermore, a unified clock source module is connected to the data acquisition module to provide a high-precision time reference to ensure time synchronization within the entire intelligent driving system; a time synchronization protocol module is connected to the data acquisition module to achieve time synchronization between the domain controller and each sensor.

[0013] Furthermore, the system also includes: a hardware synchronization trigger module, which is connected to the data acquisition module and is used to achieve global timestamp synchronization when the sensor supports hardware triggering, and ensure that each sensor starts data acquisition at the same time when receiving the trigger signal by controlling the hardware trigger signal.

[0014] The present invention has the following positive effects: 1. This invention uses an improved exponential smoothing algorithm based on an adaptive error factor to predict the time deviation of each sensor, and combines it with a variance-based cumulative average algorithm to characterize the time synchronization detection values ​​of each sensor. This not only monitors the time synchronization status of each sensor in the intelligent driving system in real time, promptly discovers and corrects timestamp inconsistencies, but also ensures the timeliness and consistency of data, thereby improving the decision-making and control accuracy of autonomous driving.

[0015] 2. This invention helps improve the safety and reliability of autonomous driving systems and reduce accident risks by improving time synchronization accuracy and enhancing system stability. It also adopts a high-precision time source and time synchronization protocol, as well as a hardware synchronization trigger mechanism, which can significantly improve the time synchronization accuracy between sensors in intelligent driving systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 Schematic diagram of the method flow of the present invention; Figure 2 Schematic diagram of the process of the improved exponential smoothing algorithm based on the adaptive error factor of the present invention; Figure 3 Schematic diagram of the flow of the variance-based cumulative average algorithm of the present invention. DETAILED DESCRIPTION

[0017] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0018] Example 1: Figure 1As shown, a time synchronization self-detection method for a domain controller of an intelligent driving system includes: M1. When a vehicle is driving on the road, the domain controller regularly sends synchronization messages to each sensor and obtains data information about the time when each sensor receives the synchronization message. It also timestamps the data collected by each sensor during operation and obtains data information about the timestamp of the data collected by each sensor. M2. Based on the data information of the time when each sensor receives the synchronization message and the data information of the timestamp of the data collected by each sensor, the time deviation of each sensor is predicted using an improved exponential smoothing algorithm based on an adaptive error factor to obtain the predicted data information of the time deviation of each sensor; M3 based on the predicted time deviation of each sensor data information, the use of variance-based cumulative average algorithm for the time synchronization of each sensor detection value characterization, to obtain the time synchronization of each sensor detection value data information; M4. Based on the data information of the time-synchronized detection values ​​of the various sensors, a preset threshold is set. If the time-synchronized detection value of each sensor is less than the preset threshold, there is no abnormality. If the time-synchronized detection value of each sensor is greater than the preset threshold, an abnormality occurs and an early warning is triggered.

[0019] In this embodiment, if Figure 2 As shown, in step M2, the use of an improved exponential smoothing algorithm based on an adaptive error factor to predict the time deviation of each sensor includes: M21 based on the data information of the time each sensor receives the synchronization message and the data information of each sensor collecting data timestamp, data alignment processing is performed to obtain the alignment of each sensor receiving the synchronization message time and the data information of the timestamp of the collected data; M22. Based on the alignment of the time information of each sensor receiving the synchronization message and the timestamp of the collected data, establish a time deviation prediction function Q for each sensor, , Among them, y1 is the data information of the time when each sensor receives the synchronization message after the alignment processing, y2 is the data information of the timestamp of the data collected by each sensor after the alignment processing, α1, α2 and α3 are adaptive error factors; M23. Based on the time deviation prediction function Q of each sensor, predict the time deviation of each sensor to obtain data information of the predicted time deviation of each sensor.

[0020] Furthermore, the adaptive error factors α1, α2 and α3 are, , , , Among them, y1 is the data information of the time when each sensor receives the synchronization message after the alignment processing, and y2 is the data information of the timestamp of the data collected by each sensor after the alignment processing.

[0021] In this embodiment, the constraint function f of the adaptive error factor is, , , Among them, the value range of the constraint function f is (1,2).

[0022] Furthermore, in step M3, the characterization of the time-synchronized detection values ​​of each sensor using a variance-based cumulative average algorithm includes: M31. Based on the predicted time deviation data information of each sensor, normalization is performed to obtain the normalized time deviation data information of each sensor; M32. Based on the normalized data information of the time deviation of each sensor, establish the cumulative average function R of the sensor time synchronization deviation, , Among them, x i is the time deviation data information of the i-th sensor after normalization, E is the expectation, n is the sample size, β i is the weight coefficient; M33. Based on the cumulative average function R of the sensor time synchronization deviation, the time synchronization detection value of each sensor is characterized to obtain data information of the time synchronization detection value of each sensor.

[0023] In this embodiment, the weight coefficient β i The constraints are, .

[0024] Example 2: Based on the time synchronization self-detection method of the intelligent driving system domain controller in Example 1, the present invention is further illustrated and described below.

[0025] like Figure 1 As shown, a time synchronization self-detection method for a domain controller of an intelligent driving system includes: M1. When a vehicle is driving on the road, the domain controller regularly sends synchronization messages to each sensor and obtains data information about the time when each sensor receives the synchronization message. It also timestamps the data collected by each sensor during operation and obtains data information about the timestamp of the data collected by each sensor. M2. Based on the data information of the time when each sensor receives the synchronization message and the data information of the timestamp of the data collected by each sensor, the time deviation of each sensor is predicted using an improved exponential smoothing algorithm based on an adaptive error factor to obtain the predicted data information of the time deviation of each sensor; M3 based on the predicted time deviation of each sensor data information, the use of variance-based cumulative average algorithm for the time synchronization of each sensor detection value characterization, to obtain the time synchronization of each sensor detection value data information; M4. Based on the data information of the time-synchronized detection values ​​of the various sensors, a preset threshold is set. If the time-synchronized detection value of each sensor is less than the preset threshold, there is no abnormality. If the time-synchronized detection value of each sensor is greater than the preset threshold, an abnormality occurs and an early warning is triggered.

[0026] Specifically, the problem of time synchronization accuracy: In intelligent driving systems, various sensors (such as integrated navigation, radar, cameras, etc.) need to be highly synchronized to ensure data accuracy. However, due to hardware differences, environmental factors or network delays, the timestamps of these sensors may be inconsistent. This inconsistency in timestamps will affect the synchronization of the data, causing errors when the intelligent driving system processes data, which in turn affects the safety and reliability of autonomous driving. The time synchronization self-detection method and system of the domain controller of the intelligent driving system can significantly improve the time synchronization accuracy between the sensors in the intelligent driving system by adopting a high-precision d-time source (such as GPS or GNSS) and time synchronization protocol (such as PTP / gPTP), as well as a hardware synchronization trigger mechanism.

[0027] System stability issues: Intelligent driving systems have extremely high requirements for time synchronization. Any deviation in time synchronization can cause system instability or failure. While some existing time synchronization solutions exist, these solutions may lack effective self-detection mechanisms, making it impossible to monitor the status of time synchronization in real time and take appropriate countermeasures. The intelligent driving system domain controller time synchronization self-detection method and system, through regular timestamp detection and calibration, as well as self-detection and alarm mechanisms, can promptly detect and correct anomalies in the time synchronization system, thereby enhancing system stability and reliability.

[0028] Fault recovery and alarm mechanisms: In intelligent driving systems, time synchronization failures can lead to serious consequences, such as inconsistent sensor data and system control failure. Therefore, an effective fault recovery and alarm mechanism is crucial. The intelligent driving system's domain controller time synchronization self-detection method and system utilizes a built-in self-detection module to regularly check the time synchronization system and trigger an alarm mechanism when an anomaly is detected. This mechanism quickly notifies drivers or maintenance personnel, allowing them to promptly identify and address issues, thereby avoiding potential safety risks.

[0029] Time synchronization issues in complex network environments: Intelligent driving systems are often deployed in complex network environments, including both wired and wireless networks. In such environments, time synchronization may face challenges such as network latency and packet loss. The intelligent driving system domain controller time synchronization self-detection method and system utilizes advanced network synchronization technologies (such as PTP / gPTP) and combines them with a hardware synchronization trigger mechanism to achieve high-precision time synchronization in complex network environments.

[0030] In this embodiment, a unified clock source is configured: a high-precision time source is selected as the unified clock source for the entire intelligent driving system. This time source is a GPS or high-precision GNSS vehicle receiver, which provides a precise time reference. The domain controller receives and processes the time signal from the time source to achieve internal system time synchronization.

[0031] Time Synchronization Protocol Implementation: The PTP / gPTP time synchronization protocol is implemented between the domain controller and each sensor. The domain controller, acting as the master, periodically sends synchronization messages to each sensor and records the time they are sent. Each sensor, acting as a slave, receives the synchronization messages and records the time they are received. By calculating the round-trip time of the synchronization message and the network transmission delay, the domain controller can calculate the clock offset between each sensor and the master and adjust the local clock of the slave device to align it with the master.

[0032] Hardware synchronization trigger mechanism: If the sensor supports hardware triggering, this mechanism is used to synchronize global timestamps. The domain controller controls the hardware trigger signal to ensure that all sensors simultaneously begin data collection upon receiving the trigger signal and marks the collected timestamp as the global timestamp. This method eliminates the impact of internal sensor clock differences on timestamps, improving time synchronization accuracy.

[0033] Timestamp detection and calibration: The domain controller regularly checks the timestamps of each sensor. By comparing the sensor timestamps with those of the unified clock source, it calculates the time offset and performs calibration. The domain controller also monitors data transmission delays between sensors to ensure data timeliness and consistency. During the detection process, the domain controller can employ various algorithms and techniques to improve the accuracy and reliability of timestamp detection.

[0034] Self-diagnosis and alarm mechanism: The domain controller has a built-in self-diagnosis module that regularly checks the time synchronization system. This module checks the stability of the time synchronization protocol, the accuracy of the hardware synchronization trigger, and the calibration of the timestamp. If an anomaly is detected, an alarm mechanism is immediately triggered, and appropriate recovery measures are implemented. This alarm mechanism can be implemented through fault codes, display screen prompts, or alarm signals, allowing drivers and maintenance personnel to promptly identify and address problems.

[0035] In this embodiment, the present invention provides a system for implementing any one of the above-mentioned methods for self-detecting time synchronization of a domain controller in an intelligent driving system, the system comprising: The data acquisition module is used to obtain the data information of the time when each sensor receives the synchronization message, and timestamp the data collected by each sensor when it is working, so as to obtain the data information of the timestamp of the data collected by each sensor; A sensor time deviation prediction module is connected to the data acquisition module and is used to predict the time deviation of each sensor using an improved exponential smoothing algorithm based on an adaptive error factor to obtain data information of the predicted time deviation of each sensor; A sensor time synchronization detection value module is connected to the sensor time deviation prediction module and is used to characterize the time synchronization detection value of each sensor using a variance-based cumulative average algorithm to obtain data information of the time synchronization detection value of each sensor; The early warning module is connected to the time synchronization detection value module of the sensor and is used to set a preset threshold. If the time synchronization detection value of each sensor is less than the preset threshold, there is no abnormality. If the time synchronization detection value of each sensor is greater than the preset threshold, an abnormality occurs and an early warning is triggered.

[0036] In this embodiment, a unified clock source module is connected to the data acquisition module to provide a high-precision time reference to ensure time synchronization within the entire intelligent driving system; a time synchronization protocol module is connected to the data acquisition module to achieve time synchronization between the domain controller and each sensor.

[0037] In this embodiment, the system also includes: a hardware synchronization trigger module, which is connected to the data acquisition module and is used to achieve global timestamp synchronization when the sensor supports hardware triggering, and to ensure that each sensor starts data acquisition at the same time when receiving the trigger signal by controlling the hardware trigger signal.

[0038] Timestamp Detection and Calibration Module: This module detects and calibrates the timestamps of each sensor. By comparing sensor timestamps with those from a unified clock source, it calculates time deviations and makes adjustments. It also monitors data transmission delays between sensors to ensure data timeliness and consistency.

[0039] The self-test and alarm module performs self-tests on the time synchronization system and triggers alarms when anomalies are detected. This module includes functions such as checking the stability of the time synchronization protocol, the accuracy of the hardware synchronization trigger, and timestamp calibration. If an anomaly is detected, an alarm is immediately triggered and appropriate recovery measures are implemented.

[0040] The present invention also provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the intelligent driving system domain controller time synchronization self-detection methods.

[0041] Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0042] In summary, the present invention can not only monitor the time synchronization status of each sensor in the intelligent driving system in real time, promptly discover and correct the problem of inconsistent timestamps, but also ensure the timeliness and consistency of data, thereby improving the decision-making and control accuracy of autonomous driving.

[0043] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A time synchronization self-detection method for a domain controller of an intelligent driving system, characterized in that: The method comprises: M1. When a vehicle is driving on the road, the domain controller regularly sends synchronization messages to each sensor and obtains data information about the time when each sensor receives the synchronization message. It also timestamps the data collected by each sensor during operation and obtains data information about the timestamp of the data collected by each sensor. M2. Based on the data information of the time when each sensor receives the synchronization message and the data information of the timestamp of the data collected by each sensor, the time deviation of each sensor is predicted using an improved exponential smoothing algorithm based on an adaptive error factor to obtain the predicted data information of the time deviation of each sensor; M3 based on the predicted time deviation of each sensor data information, the use of variance-based cumulative average algorithm for the time synchronization of each sensor detection value characterization, to obtain the time synchronization of each sensor detection value data information; M4. Based on the data information of the time-synchronized detection values ​​of the various sensors, a preset threshold is set. If the time-synchronized detection value of each sensor is less than the preset threshold, there is no abnormality. If the time-synchronized detection value of each sensor is greater than the preset threshold, an abnormality occurs and an early warning is triggered.

2. The time synchronization self-detection method of the intelligent driving system domain controller according to claim 1 is characterized in that: In step M2, the use of an improved exponential smoothing algorithm based on an adaptive error factor to predict the time deviation of each sensor includes: M21 based on the data information of the time each sensor receives the synchronization message and the data information of each sensor collecting data timestamp, data alignment processing is performed to obtain the alignment of each sensor receiving the synchronization message time and the data information of the timestamp of the collected data; M22. Based on the alignment of the time information of each sensor receiving the synchronization message and the timestamp of the collected data, establish a time deviation prediction function Q for each sensor, ， Among them, y1 is the data information of the time when each sensor receives the synchronization message after the alignment processing, y2 is the data information of the timestamp of the data collected by each sensor after the alignment processing, α1, α2 and α3 are adaptive error factors; M23. Based on the time deviation prediction function Q of each sensor, predict the time deviation of each sensor to obtain data information of the predicted time deviation of each sensor.

3. The method for self-detecting time synchronization of a domain controller in an intelligent driving system according to claim 2, characterized in that: The adaptive error factors α1, α2 and α3 are, ， ， ， Among them, y1 is the data information of the time when each sensor receives the synchronization message after the alignment processing, and y2 is the data information of the timestamp of the data collected by each sensor after the alignment processing.

4. The method for self-detecting time synchronization of a domain controller in an intelligent driving system according to claim 3, characterized in that: The constraint function f of the adaptive error factor is, ， ， Among them, the value range of the constraint function f is (1,2).

5. The time synchronization self-detection method of the intelligent driving system domain controller according to claim 1, characterized in that: In step M3, characterizing the time-synchronized detection values ​​of each sensor using a variance-based cumulative average algorithm includes: M31. Based on the predicted time deviation data information of each sensor, normalization is performed to obtain the normalized time deviation data information of each sensor; M32. Based on the normalized data information of the time deviation of each sensor, establish the cumulative average function R of the sensor time synchronization deviation, ， Among them, x i is the time deviation data information of the i-th sensor after normalization, E is the expectation, n is the sample size, β i is the weight coefficient; M33. Based on the cumulative average function R of the sensor time synchronization deviation, the time synchronization detection value of each sensor is characterized to obtain data information of the time synchronization detection value of each sensor.

6. The method for self-detecting time synchronization of a domain controller in an intelligent driving system according to claim 5, characterized in that: The weight coefficient β i The constraints are, 。 7. The method for self-detecting time synchronization of a domain controller in an intelligent driving system according to claim 1, characterized in that: The domain controller implements the PTP / gPTP time synchronization protocol with each sensor, regularly sends synchronization messages to each sensor, and records the sending time of the synchronization messages. Each sensor acts as a slave device, receives the synchronization messages and records the receiving time.

8. A system for implementing the time synchronization self-detection method of the intelligent driving system domain controller according to any one of claims 1 to 7, characterized in that: The system comprises: The data acquisition module is used to obtain the data information of the time when each sensor receives the synchronization message, and timestamp the data collected by each sensor when it is working, so as to obtain the data information of the timestamp of the data collected by each sensor; A sensor time deviation prediction module is connected to the data acquisition module and is used to predict the time deviation of each sensor using an improved exponential smoothing algorithm based on an adaptive error factor to obtain data information of the predicted time deviation of each sensor; A sensor time synchronization detection value module is connected to the sensor time deviation prediction module and is used to characterize the time synchronization detection value of each sensor using a variance-based cumulative average algorithm to obtain data information of the time synchronization detection value of each sensor; The early warning module is connected to the time synchronization detection value module of the sensor and is used to set a preset threshold. If the time synchronization detection value of each sensor is less than the preset threshold, there is no abnormality. If the time synchronization detection value of each sensor is greater than the preset threshold, an abnormality occurs and an early warning is triggered.

9. The system according to claim 8, characterized in that The system further comprises: A unified clock source module is connected to the data acquisition module to provide a high-precision time reference to ensure time synchronization within the entire intelligent driving system; a time synchronization protocol module is connected to the data acquisition module to achieve time synchronization between the domain controller and each sensor.

10. The system according to claim 8, wherein: The system also includes: a hardware synchronization trigger module, which is connected to the data acquisition module and is used to synchronize global timestamps when the sensor supports hardware triggering. By controlling the hardware trigger signal, it ensures that each sensor starts data acquisition at the same time when receiving the trigger signal.

Images