Vehicle-mounted network fault isolation and self-healing system and vehicle-mounted network fault self-healing method

Abstract

The invention provides a vehicle-mounted network fault isolation and self-healing system and a vehicle-mounted network fault self-healing method.The vehicle-mounted network fault isolation and self-healing system comprises a heterogeneous double-ring communication architecture which comprises a control ring and a data ring, the control ring adopts a main-standby redundant differential signal transmission path, and the data ring adopts a main-standby redundant differential signal transmission path; the data ring adopts a ring topology formed by aggregating Ethernet links; the lightweight cross-layer diagnosis engine is used for synchronously acquiring a physical layer signal quality parameter, a network layer data frame continuity parameter and an application layer verification parameter, and outputting node-level fault prediction information based on a parameter fusion result; the dynamic arbitration module is configured to divide communication time slot priorities according to function security levels; and the self-healing execution module is coupled with the differential signal transmission path and the prediction information, and executes fault node isolation and communication path reconstruction when detecting that the path is abnormal and the prediction information meets a preset condition.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle network communication technology, and in particular to a vehicle network fault isolation and self-healing system and a vehicle network fault self-healing method. Background Technology

[0002] Intelligent driving systems place stringent requirements on in-vehicle networks for real-time performance and multi-protocol compatibility. Existing technology employs an AUTBUS dual-ring redundant architecture, which achieves physical separation of environmental perception and operational control, but suffers from three bottlenecks: First, fault switching relies on domain controller decisions, with a switching latency greater than 20ms, failing to meet the real-time requirement of less than 10ms for critical commands such as steering control; second, the domain controller, as a common node in both rings, is at risk of single-point failure, and its failure will cause both rings to paralyze simultaneously; third, a custom AUTBUS interface chip is required, increasing the hardware cost per vehicle by more than $15.

[0003] Existing technology 2 proposes a redundant control method that coordinates Ethernet ring network and CAN broadcast, utilizing the high reliability of CAN to synchronize the status of the entire network links. However, this solution has fundamental flaws: the CAN bus bandwidth is only 1Mbps, and frequent broadcasts of abnormal link status can easily cause channel congestion; the fault judgment logic is simple, with a false switching rate of over 15%, and it cannot distinguish between link faults and ECU node faults, resulting in coarse isolation granularity and reduced system availability.

[0004] In summary, existing technologies have failed to simultaneously address core issues such as high switching latency, coarse fault isolation granularity, single-point dependency risk, high hardware cost, and poor multi-protocol compatibility. Summary of the Invention

[0005] This disclosure aims to solve at least one of the technical problems existing in the prior art, and proposes an in-vehicle network fault isolation and self-healing system and an in-vehicle network fault self-healing method.

[0006] In a first aspect, embodiments of this disclosure provide a vehicle network fault isolation and self-healing system, including:

[0007] The heterogeneous dual-ring communication architecture includes a control ring and a data ring. The control ring adopts a primary and backup redundant differential signal transmission path, while the data ring adopts a ring topology composed of Ethernet link aggregation.

[0008] A lightweight cross-layer diagnostic engine is used to simultaneously collect physical layer signal quality parameters, network layer data frame continuity parameters, and application layer verification parameters, and output node-level fault prediction information based on the parameter fusion results.

[0009] The dynamic arbitration module is configured to prioritize communication time slots according to functional safety levels.

[0010] The self-healing execution module is coupled with the differential signal transmission path and prediction information. When an abnormality is detected in the path and the prediction information meets the preset conditions, it performs fault node isolation and communication path reconstruction.

[0011] In some embodiments, the primary / backup redundant differential signal transmission path of the control loop includes:

[0012] The shielded twisted-pair physical media pairs carry the primary communication channel and the backup communication channel, which is in a listening state, respectively.

[0013] The differential comparator coupled to the twisted pair is configured to detect the voltage deviation between the primary and backup channels with an adaptive threshold and generate a hardware fault trigger signal.

[0014] In some embodiments, the Ethernet link aggregation ring topology of the data ring includes:

[0015] Multiple vehicle-mounted switch nodes are connected in a ring via bidirectional links;

[0016] The frame duplication and elimination mechanism unit is configured to add a circular sequence identifier to the data frame and perform duplicate frame removal at the receiving end;

[0017] The link aggregation management unit is used to virtualize multiple physical links into a single logical channel.

[0018] In some embodiments, the lightweight cross-layer diagnostic engine is specifically configured as follows:

[0019] The physical layer acquires the received signal strength indication value and calculates the dual-ring difference.

[0020] The network layer counts the number of packet losses within a unit time window.

[0021] The application layer records the cyclic redundancy check error rate;

[0022] The dual-ring difference, the number of lost packets, and the cyclic redundancy check error rate are normalized and fused, and then input into the embedded machine learning model.

[0023] In some embodiments, the embedded machine learning model is a compressed neural network with the number of parameters limited by the storage capacity of the vehicle microcontroller. The input nodes of the compressed neural network include the temperature value of the electronic control unit, the power supply voltage fluctuation value, and the bit error rate statistics.

[0024] In some embodiments, the dynamic arbitration module divides the communication cycle into at least four priority time slots corresponding to functional safety levels.

[0025] The highest priority time slot is dedicated to transmitting active safety control commands, and the length of each time slot is dynamically adjustable according to the functional safety level.

[0026] In some embodiments, the self-healing execution module is configured as follows:

[0027] The granularity of fault isolation is reduced to a single electronic control unit node rather than the entire communication link;

[0028] After a fault is detected, the port status switch and path reconstruction are completed within a preset time.

[0029] Control messages carrying global link status are broadcast through the controller area network to synchronize the configuration of each node.

[0030] Secondly, this disclosure provides a self-healing method for in-vehicle network faults, comprising the following steps:

[0031] The physical link status of the control loop is detected in real time by comparing the hardware-level voltage of the primary and backup differential signal transmission paths.

[0032] In a ring topology of a data ring, the sequence labels of data frames are monitored to assess network layer continuity;

[0033] The physical layer signal quality parameters, network layer continuity parameters, and application layer verification parameters are collected simultaneously, and after parameter fusion processing, they are input into the lightweight prediction model deployed on the vehicle gateway.

[0034] Based on the node-level fault prediction information output by the model and the comparison results of the hardware-level voltage, cross-validation is used to locate the fault to the electronic control unit node.

[0035] The communication time slot allocation is dynamically adjusted according to the functional safety level, and fault node isolation and communication path reconstruction are triggered.

[0036] Thirdly, embodiments of this disclosure provide an electronic device, including:

[0037] One or more processors;

[0038] Memory, used to store one or more programs;

[0039] When one or more programs are executed by one or more processors, the one or more processors implement the in-vehicle network fault self-healing method provided in the second aspect.

[0040] Fourthly, embodiments of this disclosure provide a computer-readable medium storing a computer program, which, when executed by a processor, implements the vehicle network fault self-healing method provided in the second aspect.

[0041] The vehicle network fault isolation and self-healing system provided in this disclosure adopts a heterogeneous dual-ring architecture and cross-layer diagnostic collaborative design, which solves the industry pain points of single-point dependence and high switching latency, enabling the system to maintain basic control functions when the domain controller fails, and distributed diagnostics avoids the bottleneck of centralized decision-making. Attached Figure Description

[0042] Figure 1 This is a schematic diagram of the structure of an in-vehicle network fault isolation and self-healing system provided in an embodiment of the present disclosure;

[0043] Figure 2 A schematic diagram of another vehicle network fault isolation and self-healing system provided in this embodiment of the present disclosure;

[0044] Figure 3 A flowchart illustrating a self-healing method for vehicle network faults provided in an embodiment of this disclosure;

[0045] Figure 4 This is a structural block diagram of an electronic device provided in an embodiment of the present disclosure. Detailed Implementation

[0046] To enable those skilled in the art to better understand the technical solutions of this disclosure, exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments of this disclosure to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0047] Where there is no conflict, the various embodiments of this disclosure and the features thereof in the embodiments may be combined with each other.

[0048] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0049] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Words such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0050] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this disclosure, and will not be interpreted as having an idealized or overly formal meaning, unless expressly so defined herein.

[0051] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information in this technical solution comply with relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution follows relevant national laws and regulations (e.g., the "Information Security Technology - Personal Information Security Specification"). For example, appropriate measures are taken for personal information access control; restrictions are imposed on the display of personal information; the purpose of using personal information does not exceed the scope of direct or reasonable association; and explicit identity targeting is eliminated when using personal information to avoid precisely identifying specific individuals.

[0052] With the rapid development of intelligent driving technology, in-vehicle networks need to meet two core requirements simultaneously: first, the transmission latency of critical control commands such as braking and steering must be less than 10ms; second, they need to be compatible with multi-protocol communication, including CAN / CANFD (control command transmission) and Ethernet (sensor data transmission). However, existing in-vehicle network fault handling solutions have three major bottlenecks, making it difficult to adapt to the stringent requirements of intelligent driving.

[0053] In existing technology one, patent CN202211101075.X proposes a dual-ring redundant communication architecture based on the AUTBUS bus, which achieves redundancy switching through a separate design of the environmental perception ring and the operation control ring. However, this solution relies on domain controller decisions, and the fault switching time exceeds 20ms, which cannot meet the real-time requirements of critical commands such as steering control; at the same time, as a common node, the domain controller is at risk of paralyzing both rings due to a single point of failure, and a customized AUTBUS interface chip would significantly increase the hardware cost per vehicle.

[0054] In the second prior art, patent CN202411213490.3 employs a redundant control method combining Ethernet link detection and CAN communication, which synchronizes link status and performs switching via CAN broadcast. This scheme suffers from the bottleneck of the 1Mbps bandwidth of the CAN bus, and frequent broadcasts can easily lead to network congestion; moreover, it cannot effectively distinguish between link faults and node faults, resulting in a false switching rate exceeding 15%, which affects the stable operation of the vehicle network.

[0055] To address the shortcomings of the existing technologies, this disclosure proposes a vehicle network fault isolation and self-healing system and method, aiming to achieve the technical goals of μs-level fault switching, node-level precise isolation, multi-protocol compatibility, and low-cost control.

[0056] Figure 1 This is a schematic diagram of the structure of an in-vehicle network fault isolation and self-healing system provided in an embodiment of this disclosure. Figure 2 This is a schematic diagram of another in-vehicle network fault isolation and self-healing system provided in an embodiment of this disclosure, as shown below. Figure 1 , Figure 2 As shown, the in-vehicle network fault isolation and self-healing system includes:

[0057] The heterogeneous dual-ring communication architecture 10 includes a control ring and a data ring. The control ring adopts a primary and backup redundant differential signal transmission path, while the data ring adopts a ring topology composed of Ethernet link aggregation.

[0058] The lightweight cross-layer diagnostic engine 20 is used to simultaneously collect physical layer signal quality parameters, network layer data frame continuity parameters, and application layer verification parameters, and output node-level fault prediction information based on the parameter fusion results.

[0059] The dynamic arbitration module 30 is configured to prioritize communication time slots according to functional safety levels.

[0060] The self-healing execution module 40 is coupled with the differential signal transmission path and prediction information. When an abnormality is detected in the path and the prediction information meets the preset conditions, it performs fault node isolation and communication path reconstruction.

[0061] The vehicle network fault isolation and self-healing system provided in this disclosure adopts a heterogeneous dual-ring architecture and cross-layer diagnostic collaborative design, which solves the industry pain points of single-point dependence and high switching latency, enabling the system to maintain basic control functions when the domain controller fails, and distributed diagnostics avoids the bottleneck of centralized decision-making.

[0062] In some embodiments, the primary and backup redundant differential signal transmission paths of the control loop include:

[0063] The shielded twisted-pair physical media pairs carry the primary communication channel and the backup communication channel in monitoring mode, respectively; the differential comparator coupled to the twisted-pair pair is configured to detect the voltage deviation between the primary and backup channels with an adaptive threshold and generate a hardware fault trigger signal.

[0064] Specifically, the primary and backup redundant differential signal transmission paths of the control loop include shielded twisted-pair physical media pairs, which respectively carry the primary communication channel and the backup communication channel in a listening state. The primary and backup twisted-pair cables are laid in parallel. The backup channel is normally in a low-power listening mode, only receiving and not transmitting, and switches instantaneously when the primary channel fails. A differential comparator coupled to the twisted-pair pair uses an adaptive threshold to detect the voltage deviation between the primary and backup channels and generates a hardware fault trigger signal.

[0065] In one example, the control loop could use the FlexRay bus as an alternative, which can provide 10 Mbps bandwidth and deterministic transmission characteristics.

[0066] In some embodiments, the adaptive threshold of the differential comparator is dynamically calibrated based on historical signal deviation statistics and ambient temperature. Specifically, during normal operation, the system continuously records the voltage difference between the primary and backup channels, calculates their mean and standard deviation as a baseline, and compensates for the threshold offset by combining the ambient temperature data collected in real time by the vehicle temperature sensor. When the voltage deviation between the primary and backup channels exceeds ±0.1V, an edge-triggered signal is generated at the comparator output, which directly drives the interrupt input of the self-healing execution module, achieving a hardware-level microsecond-level response.

[0067] Furthermore, the Ethernet link aggregation ring topology of the data ring includes multiple vehicle-mounted switch nodes, which are connected to form a physical closed loop through bidirectional links.

[0068] In some embodiments, the Ethernet link aggregation ring topology of the data ring includes:

[0069] Multiple vehicle-mounted switch nodes are connected in a ring via bidirectional links; the frame duplication and elimination mechanism unit is configured to add a ring sequence identifier to the data frame and perform duplicate frame removal at the receiving end; the link aggregation management unit is used to virtualize multiple physical links into a single logical channel.

[0070] In some embodiments, the link aggregation management unit is configured to allocate non-real-time data to links with sufficient bandwidth when the utilization of a link reaches a preset threshold.

[0071] By configuring the data ring with an Ethernet link aggregation ring topology, bandwidth utilization can be significantly improved, and latency jitter caused by congestion can be avoided. In fault scenarios, the Ethernet ring network protection switching protocol can complete path switching in a short time, ensuring the continuity of the data ring. Compared with existing technologies that use a single Ethernet link or simple redundancy schemes, the link aggregation and ring network combined design of this invention achieves the optimal balance between link-level reliability and bandwidth efficiency.

[0072] Furthermore, the lightweight cross-layer diagnostic engine is specifically configured to simultaneously acquire physical layer signal quality parameters, network layer data frame continuity parameters, and application layer verification parameters.

[0073] In some embodiments, the lightweight cross-layer diagnostic engine is specifically configured as follows:

[0074] The physical layer collects the received signal strength indication value and calculates the dual-ring difference; the network layer counts the number of packets lost within a unit time window; the application layer records the cyclic redundancy check error rate; after normalizing and fusing the dual-ring difference, the number of packets lost, and the cyclic redundancy check error rate, the data is input into the embedded machine learning model.

[0075] In some embodiments, the embedded machine learning model is a compressed neural network with the number of parameters limited by the storage capacity of the on-board microcontroller. The input nodes of the compressed neural network include the temperature value of the electronic control unit, the power supply voltage fluctuation value, and the bit error rate statistics.

[0076] In the above embodiments, the three-layer parameters are normalized and then input into an embedded machine learning model. This model is a compressed neural network with parameter size limited by the storage capacity of the on-board microcontroller, specifically a compressed LSTM model with fewer than 10KB of parameters. The model input nodes include the electronic control unit temperature value, power supply voltage fluctuation value, and bit error rate statistics, which are acquired in real time through the on-board sensor network. The model outputs a fault probability prediction value for the next 5 seconds, with an accuracy of 92.7% verified in a real vehicle. This cross-layer fusion diagnostic mechanism overcomes the limitations of single-level monitoring. Existing technologies can only monitor single indicators at the physical or network layers and cannot identify hidden faults at the application layer. This invention achieves a leap from passive response to proactive prediction through the complementarity of three-layer parameters and AI model inference.

[0077] In one example, the embedded machine learning model in a lightweight cross-layer diagnostic engine can also be a random forest algorithm. Random forest is 30% faster than LSTM inference, but its accuracy drops to 89%, making it suitable for cost-sensitive and computationally limited scenarios.

[0078] In some embodiments, the dynamic arbitration module divides the communication cycle into at least four priority time slots corresponding to the functional safety level, wherein the highest priority time slot is dedicated to transmitting active safety control commands, and the length of each time slot is dynamically adjustable according to the functional safety level.

[0079] Specifically, the four priority time slots of the dynamic arbitration module are allocated as follows: time slot 0 is dedicated to transmitting active safety control commands (such as AEB automatic emergency braking), time slot 1 is used for chassis dynamic control, time slot 2 is used for powertrain management, and time slot 3 is used for infotainment and diagnostics.

[0080] The length of each time slot is dynamically adjustable according to the functional safety level. For example, in high-speed driving scenarios, the proportion of time slot 0 can be expanded from 20% to 40%, ensuring that more bandwidth is allocated to safety-critical tasks. Time slot allocation is uniformly scheduled by the gateway, and each ECU node has a built-in time slot timer, achieving network-wide synchronization by receiving time slot configuration messages broadcast by the gateway. This dynamic time-division arbitration method solves the inefficiency problem of traditional fixed-priority arbitration on the CAN bus, ensuring that the latency of critical instructions is less than 100 microseconds even when the bus load exceeds 70%.

[0081] Furthermore, the self-healing execution module is configured to isolate faults precisely at the level of a single ECU node rather than the entire communication link.

[0082] In some embodiments, the self-healing execution module is configured as follows:

[0083] The fault isolation granularity is precise down to a single electronic control unit node rather than the entire communication link; after a fault is identified, port status switching and path reconstruction are completed within a preset time; control messages carrying the global link status are broadcast through the controller area network to synchronize the configuration of each node.

[0084] This node-level isolation mechanism avoids the problem of existing technologies mistakenly isolating the entire link due to their inability to distinguish between link failures and node failures, thus significantly improving system availability.

[0085] In summary, the vehicle network fault isolation and self-healing system provided in this embodiment adopts a heterogeneous dual-ring communication architecture as the underlying physical carrier. This architecture includes two logically independent communication planes: a control ring and a data ring. The control ring uses a primary / backup redundant differential signal transmission path, specifically for carrying real-time control commands such as braking and steering. The data ring uses a ring topology composed of Ethernet link aggregation, responsible for transmitting high-bandwidth sensor data such as cameras and radar. This heterogeneous division of labor design fundamentally avoids bandwidth contention between control flow and data flow, while the physical isolation of the dual rings eliminates the risk of single-point common-cause failure. The control ring and data ring achieve time synchronization and state coordination through the vehicle gateway. The lightweight cross-layer diagnostic engine built into the gateway collects the operating parameters of the two rings in real time, and outputs node-level fault prediction information after fusion processing. The dynamic arbitration module divides the communication cycle into at least four priority time slots according to the ISO 26262 functional safety level. The highest priority time slot is dedicated to transmitting active safety control commands, and the length of each time slot can be dynamically adjusted according to the functional safety level to ensure that critical commands always obtain the lowest latency channel. The self-healing execution module is coupled with the differential signal transmission path and prediction information. When a path anomaly is detected and the prediction information meets preset conditions, it performs fault node isolation and communication path reconstruction. The isolation granularity is precise to a single ECU node rather than the entire communication link. After identifying the fault, it completes port state switching and path reconstruction within a preset time and broadcasts control messages carrying the global link status via CAN to synchronize the configuration of each node. This architecture design solves the core defects of single-point dependence and high switching latency in existing domain controllers.

[0086] Based on the same inventive concept, this disclosure also provides a method for self-healing of vehicle network faults. Figure 3 This is a flowchart illustrating a self-healing method for in-vehicle network faults provided in an embodiment of this disclosure, as shown below. Figure 3 As shown, the method includes steps S1-S5:

[0087] Step S1: Real-time detection of the physical link status of the control loop is achieved through hardware-level voltage comparison of the primary and backup differential signal transmission paths.

[0088] Step S2: Monitor the sequence labels of data frames in the ring topology of the data ring to evaluate network layer continuity.

[0089] Step S3: Simultaneously collect physical layer signal quality parameters, network layer continuity parameters, and application layer verification parameters, and input them into the lightweight prediction model deployed on the vehicle gateway after parameter fusion processing.

[0090] Step S4: Based on the node-level fault prediction information output by the model and the hardware-level voltage comparison results, cross-validate to locate the fault to the electronic control unit node.

[0091] Step S5: Dynamically adjust the communication time slot allocation according to the functional safety level, and trigger fault node isolation and communication path reconstruction.

[0092] The vehicle network fault self-healing method provided in this embodiment firstly detects the physical link status of the control loop in real time by comparing the hardware-level voltage of the primary and backup differential signal transmission paths. The differential comparator continuously monitors the voltage difference between the primary and backup channels, and immediately generates an edge trigger signal once it exceeds a ±0.1V threshold. In the ring topology of the data ring, the sequence label of the data frame is monitored to evaluate network layer continuity. The frame duplication and elimination mechanism unit performs a monotonicity check on the ring sequence number of each received frame. If a sequence number jump or duplication is detected, a network layer packet loss event is recorded. Physical layer signal quality parameters, network layer continuity parameters, and application layer verification parameters are simultaneously collected and input into a lightweight prediction model deployed on the vehicle gateway after parameter fusion processing. The fusion process uses z-score normalization to eliminate dimensional differences, and then the normalized vector is input into the compressed LSTM model. Based on the node-level fault prediction information output by the model and the hardware-level voltage comparison results, cross-validation is performed to locate the fault to the electronic control unit node. The cross-validation logic requires that the hardware trigger signal and the model prediction probability simultaneously meet the threshold condition to avoid false alarms caused by a single information source. The communication time slot allocation is dynamically adjusted according to the functional safety level. The gateway updates the time slot configuration in real time based on the current vehicle operating status (vehicle speed, driving mode) and broadcasts it to the entire network. Finally, the fault node isolation and communication path reconstruction are triggered. After receiving cross-validation confirmation, the self-healing execution module completes port blocking and path switching within 100 microseconds and synchronizes the configuration of each node via CAN broadcast.

[0093] Based on the same inventive concept, this disclosure also provides an electronic device. Figure 4 This is a structural block diagram of an electronic device provided in an embodiment of this disclosure. Figure 4 As shown, this disclosure provides an electronic device including: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement any of the vehicle network fault self-healing methods described in the above embodiments; the one or more I / O interfaces 103 are connected between the processor and the memory, configured to enable information interaction between the processor and the memory.

[0094] The processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read / write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus).

[0095] In some embodiments, the processor 101, memory 102, and I / O interface 103 are interconnected via bus 104, and thus connected to other components of the computing device.

[0096] In some embodiments, the one or more processors 101 include a field-programmable gate array.

[0097] This disclosure also provides a computer-readable medium. The computer-readable medium stores a computer program, which, when executed by a processor, implements the steps of any of the in-vehicle network fault self-healing methods described above. The computer-readable storage medium may be volatile or non-volatile.

[0098] This disclosure also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code. When the computer-readable code is run in the processor of an electronic device, the processor in the electronic device executes the above-described vehicle network fault self-healing method.

[0099] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0100] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0101] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0102] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0103] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0104] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0105] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0106] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0107] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0108] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for illustrative purposes only and should be construed as such, and is not intended to be limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in connection with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in connection with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of this disclosure as set forth by the appended claims.

Claims

1. A vehicle-mounted network fault isolation and self-healing system, characterized in that, include: The heterogeneous dual-ring communication architecture includes a control ring and a data ring. The control ring adopts a primary and backup redundant differential signal transmission path, while the data ring adopts a ring topology composed of Ethernet link aggregation. A lightweight cross-layer diagnostic engine is used to simultaneously collect physical layer signal quality parameters, network layer data frame continuity parameters, and application layer verification parameters, and output node-level fault prediction information based on the parameter fusion results. The dynamic arbitration module is configured to prioritize communication time slots according to functional safety levels. The self-healing execution module is coupled with the differential signal transmission path and prediction information. When an abnormality is detected in the path and the prediction information meets the preset conditions, it performs fault node isolation and communication path reconstruction.

2. The system according to claim 1, characterized in that, The primary and backup redundant differential signal transmission paths of the control loop include: The shielded twisted-pair physical media pairs carry the primary communication channel and the backup communication channel, which is in a listening state, respectively. The differential comparator coupled to the twisted pair is configured to detect the voltage deviation between the primary and backup channels with an adaptive threshold and generate a hardware fault trigger signal.

3. The system according to claim 1, characterized in that, The Ethernet link aggregation ring topology of the data ring includes: Multiple vehicle-mounted switch nodes are connected in a ring via bidirectional links; The frame duplication and elimination mechanism unit is configured to add a circular sequence identifier to the data frame and perform duplicate frame removal at the receiving end; The link aggregation management unit is used to virtualize multiple physical links into a single logical channel.

4. The system according to claim 1, characterized in that, The lightweight cross-layer diagnostic engine is specifically configured as follows: The physical layer acquires the received signal strength indication value and calculates the dual-ring difference. The network layer counts the number of packet losses within a unit time window. The application layer records the cyclic redundancy check error rate; The dual-ring difference, the number of lost packets, and the cyclic redundancy check error rate are normalized and fused, and then input into the embedded machine learning model.

5. The system according to claim 1, characterized in that, The embedded machine learning model is a compressed neural network with the number of parameters limited by the storage capacity of the vehicle microcontroller. The input nodes of the compressed neural network include the temperature value of the electronic control unit, the power supply voltage fluctuation value, and the bit error rate statistics.

6. The system according to claim 1, characterized in that, The dynamic arbitration module divides the communication cycle into at least four priority time slots corresponding to functional safety levels. The highest priority time slot is dedicated to transmitting active safety control commands, and the length of each time slot is dynamically adjustable according to the functional safety level.

7. The system according to claim 1 or 6, characterized in that, The self-healing execution module is configured as follows: The granularity of fault isolation is reduced to a single electronic control unit node rather than the entire communication link; After a fault is detected, the port status switch and path reconstruction are completed within a preset time. Control messages carrying global link status are broadcast through the controller area network to synchronize the configuration of each node.

8. A self-healing method for vehicle network faults, characterized in that, Includes the following steps: The physical link status of the control loop is detected in real time by comparing the hardware-level voltage of the primary and backup differential signal transmission paths. In a ring topology of a data ring, the sequence labels of data frames are monitored to assess network layer continuity; The physical layer signal quality parameters, network layer continuity parameters, and application layer verification parameters are collected simultaneously, and after parameter fusion processing, they are input into the lightweight prediction model deployed on the vehicle gateway. Based on the node-level fault prediction information output by the model and the comparison results of the hardware-level voltage, cross-validation is used to locate the fault to the electronic control unit node. The communication time slot allocation is dynamically adjusted according to the functional safety level, and fault node isolation and communication path reconstruction are triggered.

9. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the in-vehicle network fault self-healing method as described in claim 8.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps in the in-vehicle network fault self-healing method as described in claim 8.

Images