Unmanned dumper steering fault processing method, system, equipment and medium

Abstract

The invention provides an unmanned dumper steering fault processing method, system and device and a medium, and belongs to the technical field of unmanned vehicle electric control. The method comprises the steps that in an unmanned driving mode, the state of a steer-by-wire system is monitored in real time through a chassis domain controller, steering fault types are recognized, fault reasons are recorded, an expert experience knowledge base is formed, and unique fault codes are distributed for different fault reasons; constructing and training a support vector machine classification model; when a steering fault occurs, extracting a feature vector of a current fault code, and predicting by using the classification model to obtain a fault processing category label; and executing corresponding grading processing measures according to the predicted fault processing category labels. According to the method, the expert experience is digitalized, and the intelligent classification model is utilized to realize automatic identification and grading processing of the fault, so that the fault processing efficiency is improved, and the attendance rate and the overall operation benefit of the unmanned motorcade in the mining area are effectively improved.

Description

Technical Field

[0001] This invention belongs to the field of electronic control technology for unmanned vehicles, and more specifically relates to a method, system, equipment and medium for handling steering faults in unmanned dump trucks. Background Technology

[0002] In unmanned transportation operations in mining areas, the carrying capacity and attendance efficiency of wide-body dump trucks are key indicators affecting overall operational economic benefits. Among these, the ability to quickly diagnose and handle vehicle malfunctions is particularly important. The steering system, as the core actuator for precise trajectory control in unmanned driving, directly impacts driving safety and operational continuity. However, the steering system is extremely sensitive to abnormal conditions. In actual operation, non-hardware issues such as occasional frame drops or repetitions in communication messages often trigger fault alarms, leading to abnormal vehicle stoppages. These problems can often be quickly resolved by remotely or by restarting the controller in place, without the need for manual maintenance. However, existing systems generally lack intelligent identification of the nature of the fault, easily causing unnecessary maintenance response times and delays.

[0003] Currently, the industry has some monitoring and handling solutions for vehicle steering faults, mainly focusing on real-time diagnosis and basic safety assurance when a fault occurs. These technologies typically rely on fixed thresholds or single signal criteria, attempting to maintain basic controllability when the system fails, or recording fault codes for later analysis. However, such methods have relatively simple strategies, lacking the fusion analysis of multi-source information and historical data, and making it difficult to distinguish between intermittent soft faults and persistent hard faults. As a result, the system often applies the same stringent processing procedures to all steering alarms, failing to achieve differentiated rapid recovery mechanisms. This causes vehicles that could recover automatically to enter a state awaiting manual intervention, reducing the vehicle's effective operating time.

[0004] Furthermore, existing systems have significant shortcomings in the accumulation and reuse of fault knowledge. Fault cases and maintenance experience accumulated by mining vehicles during long-term operation, especially expert experience in handling different fault phenomena, fault code combinations, and environmental conditions, have not been effectively and structurally incorporated into the diagnostic system. When steering faults requiring on-site repair occur, maintenance personnel often rely on personal experience or rummaging through scattered records for troubleshooting, resulting in low fault location efficiency and prolonged repair processes. Existing technical solutions lack the ability to intelligently analyze multi-dimensional fault characteristics and provide experience-based recommendations, failing to offer targeted guidance for rapid on-site troubleshooting, thus affecting fault resolution speed and vehicle uptime.

[0005] In summary, while existing steering fault handling technologies possess basic diagnostic and safety maintenance capabilities, they still have significant limitations in areas such as precise fault type identification, automatic recovery from intermittent faults, and the systematic integration and application of expert experience. These shortcomings prevent vehicles from optimally balancing safety and operational efficiency when faced with steering system anomalies, leading to unnecessary increases in downtime and hindering the overall capacity improvement of unmanned vehicle fleets in mining areas. Summary of the Invention

[0006] To address the above problems, the present invention aims to provide a method, system, device, and medium for handling steering faults in unmanned dump trucks. By constructing a digital expert experience knowledge base and applying a support vector machine model for intelligent fault classification, and performing differentiated and graded handling accordingly, the invention achieves rapid and accurate diagnosis and automated recovery of steering faults, thereby significantly improving the uptime and operational efficiency of unmanned vehicles while ensuring safety.

[0007] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, embodiments of this application provide a method for handling steering malfunctions in an unmanned dump truck, including: In autonomous driving mode, the status of the steer-by-wire system is monitored in real time by the chassis domain controller, the type of steering fault is identified and the cause of the fault is recorded, an expert experience knowledge base is formed, and a unique fault code is assigned to different fault causes. Construct and train a support vector machine classification model; when a steering failure occurs, extract the feature vector of the current fault code and use the classification model to predict the fault handling category label; Based on the predicted fault handling category label, corresponding graded handling measures are executed. The graded handling measures include soft restart of the steering controller, vehicle restart, controlling the vehicle to pull over and issuing a warning, or directly requesting manual intervention.

[0008] In an optional implementation, in the autonomous driving mode, the chassis domain controller monitors the status of the steer-by-wire system in real time, identifies steering fault types and records fault causes, forms an expert experience knowledge base, and assigns unique fault codes to different fault causes, including: In autonomous driving mode, the chassis domain controller analyzes the status feedback signal of the redundant steering system, the difference in steering parameters between the steering wheel and the reference wheel, and the status feedback signal of the steering controller frame by frame to identify the type of steering fault. The steering fault types include redundant steering activation fault, abnormal steering reference wheel fault, and steering controller disconnection fault.

[0009] In an optional implementation, the step of analyzing the redundant steering system status feedback signal, the steering parameter difference between the steering wheel and the control wheel, and the steering controller status feedback signal frame by frame using the chassis domain controller to identify the steering fault type includes: The chassis domain controller processes the redundant steering system status feedback signal frame by frame. When the chassis domain controller receives the first frame of the redundant steering system activation signal, it starts counting. When the chassis domain controller receives five consecutive frames of the redundant steering system activation signal, it determines that the redundant steering system is activated. After the redundant steering system is activated, the chassis domain controller starts to feed back the redundant steering activation to the autonomous driving system from the sixth frame of the redundant steering system activation signal to determine that a redundant steering activation fault has occurred. The chassis domain controller processes the steering angle information fed back by the steering reference wheel frame by frame to obtain the steering parameters of the reference wheel; by calculating the difference between the steering parameters of the reference wheel and the preset steering wheel parameters, the steering parameter deviation is obtained; it is determined whether the steering parameter deviation is greater than the preset steering deviation threshold; if so, it is determined that an abnormal fault has occurred in the steering reference wheel. The chassis domain controller detects the steering controller status feedback information frame by frame. When the chassis domain controller does not receive the first frame of the steering controller status signal, it starts timing. When the chassis domain controller loses 3 frames of steering controller status signals, it is determined that a steering controller disconnection fault has occurred.

[0010] In an optional implementation, the construction and training of the support vector machine classification model includes: A training dataset D is constructed based on the expert experience knowledge base and the fault codes, where D = Where M is the total number of fault codes in the dataset. For the m-th fault code, Here is the 6-dimensional feature attribute vector corresponding to the m-th fault code: ∈R6, For the time of frame loss in steering controller messages; The probability of a controllable turn; This represents the probability of a soft reboot. Probability of enabling redundant steering; This represents the abnormal probability of the steering wheel control group. This represents the probability of hardware failure. The processing category label vector corresponding to the fault code: , A label used to indicate whether steering is controllable; Labels are used to identify fault handling categories; these categories include soft restart, steering controller disconnection, steering control group abnormality, and non-restart. The support vector machine algorithm is used, with radial basis functions. As a kernel function, the model is trained on the training dataset D to determine the model parameters; where u and v represent the 6-dimensional feature vector after fault code standardization, and γ is the kernel function bandwidth parameter; the model parameters include feature weight w, bias b, penalty coefficient C, and slack variable δ.

[0011] In an optional implementation, when a steering failure occurs, extracting the feature vector of the current fault code and using the classification model to predict the fault handling category label includes: When a steering fault is detected, the current fault code is generated; Based on the current fault code, extract the steering controller message frame loss time from the communication logs of the chassis domain controller that detected this fault; obtain the corresponding feature attribute vector by querying the preset fault feature knowledge base, based on the mapping relationship between the fault code and the probability of steering controllability, the probability of soft restart resolution, the probability of redundant steering activation, the probability of abnormality of the steering wheel control group, and the probability of hardware failure; generate a 6-dimensional feature attribute vector X corresponding to the current fault code based on the extracted data; The 6-dimensional feature attribute vector X is standardized and preprocessed, and then input into the trained support vector machine classification model; The predicted numerical labels are output by the support vector machine classification model, and then converted into specific processing category label vectors through a decoding operation to generate fault processing category labels.

[0012] In an optional implementation, the step of performing corresponding graded processing measures based on the predicted fault handling category label includes: When the predicted fault handling category label is uncontrollable steering or abnormal steering control group, the autonomous driving system feeds back the fault information to the dispatching platform and other vehicles in the formation, plans a parking path, controls the vehicle to complete the parking action, requests EPB to brake and turns on the warning lights. When the predicted fault handling category label is soft restart, a soft restart request is sent to the autonomous driving system. After receiving the soft restart request, the autonomous driving system issues a vehicle braking command to control the vehicle to complete the stopping action, requests the EPB to brake and turn on the warning lights, and at the same time issues a steering controller soft restart command to control the steering controller to restart. When the steering controller receives the restart message, it re-enters the autonomous driving mode and checks whether the steering system continues to report fault codes within 5 seconds through the chassis domain controller. If the fault is not eliminated, an alarm message is issued to request manual takeover.

[0013] In an optional implementation, when the predicted fault handling category label is steering controller disconnection, a 300ms steering controller disconnection request is sent to the autonomous driving system, and a vehicle braking command is issued to the EBS to control the vehicle to complete the parking action. The autonomous driving system is requested to remotely hibernate and wake up. After receiving the hibernation and wake-up command, the autonomous driving system requests the EPB to brake and turn on the warning lights, and at the same time issues a hibernation and wake-up command to control the vehicle to restart. After the vehicle restarts, the steering controller re-enters the autonomous driving mode and checks whether the steering system continues to report fault codes within 5 seconds through the chassis domain controller. If the fault is not eliminated, an alarm message is issued to request manual takeover. When the predicted fault handling category label is non-restart, a non-restart fault is reported to the autonomous driving system. At the same time, the autonomous driving system is requested to issue a vehicle braking command to control the vehicle to complete the parking action. The autonomous driving system is requested to apply EPB braking and turn on the warning lights. At the same time, the dispatch platform is requested to take over manually.

[0014] Secondly, embodiments of this application also provide a steering fault handling system for an unmanned dump truck, comprising: The fault monitoring and expert experience coding module is used to monitor the status of the steer-by-wire system in real time through the chassis domain controller in autonomous driving mode, identify the type of steering fault and record the cause of the fault, form an expert experience knowledge base, and assign a unique fault code to different fault causes. The fault handling category prediction module is used to build and train a support vector machine classification model; when a steering fault occurs, the feature vector of the current fault code is extracted, and the classification model is used to predict the fault handling category label. The graded fault handling execution module is used to execute corresponding graded handling measures according to the predicted fault handling category label. The graded handling measures include steering controller soft restart, vehicle restart, controlling the vehicle to pull over and issuing a warning, or directly requesting manual intervention.

[0015] Thirdly, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the unmanned dump truck steering fault handling method described in any of the above descriptions.

[0016] Fourthly, embodiments of this application also provide a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the unmanned dump truck steering fault handling method described in any of the above claims.

[0017] As can be seen from the above technical solutions, the present invention has the following advantages: The steering fault handling method for unmanned dump trucks provided in this application constructs a digital expert experience knowledge base and intelligently classifies and predicts fault codes based on a support vector machine model. Finally, it executes a matching hierarchical processing strategy, thereby achieving precise, rapid, and automated handling of steering faults. This method effectively overcomes the shortcomings of existing technologies, such as unintelligent fault identification, unsystematic application of experience, and single processing strategies. It can automatically distinguish and quickly recover from intermittent soft faults, while performing safe stopping and precise assistance requests for serious faults. This significantly shortens the average fault handling time and maximizes the uptime rate and overall operational efficiency of unmanned dump trucks in mining areas while ensuring driving safety.

[0018] This application introduces an intelligent classification model based on support vector machine (SVM), which can automatically analyze and recognize patterns in real-time monitored fault data, quickly and accurately predict the fault handling category, realize an automated closed loop from fault occurrence to handling decision, and greatly shorten the diagnosis and initial response time.

[0019] This application achieves the systematic accumulation and efficient reuse of expert experience. By building and continuously updating a digital expert experience knowledge base, this application not only provides high-quality training data for machine learning models, but also enables precise invocation of experience knowledge in real-time diagnosis, transforming implicit expert judgment logic into repeatable and scalable system capabilities, and reducing excessive reliance on individual experience in operation and maintenance.

[0020] Based on intelligent prediction results, this application can automatically match and execute the optimal handling process, such as automatically restarting and recovering from occasional soft failures, and guiding vehicles to safely pull over and issuing warnings for potential safety risks. This tiered strategy minimizes unnecessary operational interruptions while ensuring a safety baseline, optimizing the balance between safety and efficiency.

[0021] This application significantly optimizes the allocation of operation and maintenance resources by organically integrating expert experience, intelligent decision-making, and automated control. A large number of occasional faults are handled automatically, avoiding unnecessary vehicle downtime and personnel deployment; while for faults requiring repair, accurate pre-diagnostic information greatly shortens on-site troubleshooting time. This directly improves the availability of individual vehicles and the overall economic efficiency of the fleet operation.

[0022] This application possesses the capability for continuous optimization that evolves in sync with the operational cycle. As vehicle operation data accumulates, the expert knowledge base will continue to grow, and the accuracy of the classification model will improve accordingly. This characteristic enables the solution to adapt to complex factors such as vehicle wear and tear and environmental changes over the long term, providing a solid guarantee for the reliable operation of the autonomous driving system throughout its entire lifecycle. Attached Figure Description

[0023] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description 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.

[0024] Figure 1 This is a flowchart illustrating the method for handling steering malfunctions in unmanned dump trucks provided in this application.

[0025] Figure 2 A flowchart illustrating another method for handling steering malfunctions in an unmanned dump truck provided in this application.

[0026] Figure 3 A schematic diagram of the logic control architecture provided in this application.

[0027] Figure 4 This is a schematic diagram of the steering fault handling system for the unmanned dump truck provided in this application.

[0028] Figure 5 A schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0029] The various embodiments of this disclosure will be described more fully in the following detailed description of the specific steps of the method for handling steering failures in unmanned dump trucks. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0030] In the following, the terms “comprising” or “may include”, which may be used in various embodiments of this disclosure, indicate the presence of the disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a particular feature, number, step, operation, element, component, or combination of the foregoing, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or the possibility of adding one or more combinations of the foregoing.

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] Please see Figure 1 The diagram shows a flowchart of a method for handling steering malfunctions in an unmanned dump truck, according to a specific embodiment. The method includes: S1: In autonomous driving mode, the status of the steer-by-wire system is monitored in real time through the chassis domain controller, the type of steering fault is identified and the cause of the fault is recorded, an expert experience knowledge base is formed, and a unique fault code is assigned to different fault causes.

[0033] In a specific implementation, under autonomous driving mode, the chassis domain controller analyzes the redundant steering system status feedback signal, the steering parameter difference between the steering wheel and the control wheel, and the steering controller status feedback signal frame by frame to identify steering fault types. These fault types include redundant steering activation fault, steering control wheel abnormality fault, and steering controller disconnection fault. Then, the causes and handling measures for each of these three types of faults are used as expert experience, and faults caused by different reasons are coded into different fault codes. Whenever the fault cause is updated, the fault code is updated synchronously.

[0034] Specifically, the identification process for the three types of steering faults is as follows: 1. The chassis domain controller processes the redundant steering system status feedback signal frame by frame. When the chassis domain controller receives the first frame of the redundant steering system activation signal, it starts counting. When the chassis domain controller receives 5 consecutive frames of the redundant steering system activation signal, it determines that the redundant steering system is activated. Based on the activation of the redundant steering system, the chassis domain controller starts to feed back the activation of redundant steering to the autonomous driving system from the moment it receives the 6th frame redundant steering system activation signal. Based on the redundant steering activation, the reason for each activation is investigated and processed into expert experience, and the reason for activation is made into a fault code.

[0035] 2. The chassis domain controller processes the steering angle information fed back by the steering reference wheel frame by frame. The chassis domain controller takes the difference between the received steering parameters of the reference wheel and the steering wheel parameters to obtain the steering parameter deviation. The steering control group is judged to be abnormal by comparing the steering parameter deviation with the set steering deviation threshold. Based on the abnormalities in the steering control group, the causes of each abnormality were thoroughly investigated, processed using expert experience, and the causes of the abnormalities in the steering control group were recorded as fault codes.

[0036] 3. The chassis domain controller detects the steering controller status feedback information frame by frame. When the chassis domain controller does not receive the first frame of steering controller status information, it starts timing. When the chassis domain controller fails to receive three consecutive frames of steering controller status signals, it determines that the steering controller is disconnected. Based on the aforementioned steering controller disconnection, the cause of each disconnection was thoroughly investigated, processed as expert experience, and the cause of the steering controller disconnection was recorded as a fault code. S2: Construct and train a support vector machine classification model; when a steering failure occurs, extract the feature vector of the current fault code and use the classification model to predict the fault handling category label.

[0037] It should be noted that in the autonomous driving state, the chassis domain controller monitors the message signals fed back by the steer-by-wire system in real time, and determines whether the SPN and FMI signals, redundant steering system, and steering control group in the message are abnormal. If so, the chassis domain controller feeds back the current fault code to the autonomous driving system; and based on the steering fault code and the steering fault handling method, it trains a model using the support vector machine (SVM) algorithm to predict the corresponding handling measures category of the steering fault code.

[0038] In a specific implementation, the support vector machine classification model is first constructed and trained, specifically including: Establish a dataset D containing fault codes, fault handling measures, and fault types. The fault codes in the dataset include steering controller message frame loss time, soft restart probability, steering controllability probability, redundant steering activation probability, steering wheel control group abnormality probability, and hardware fault probability feature vector. Based on the dataset D, it is defined as D= Where M is the total number of fault codes in the dataset. For the m-th fault code, Here is the 6-dimensional feature attribute vector corresponding to the m-th fault code: ∈R6, For the time of frame loss in steering controller messages; The probability of a controllable turn; This represents the probability of a soft reboot. Probability of enabling redundant steering; This represents the abnormal probability of the steering wheel control group. This represents the probability of hardware failure. The processing category label vector corresponding to the fault code: , The label indicates whether the steering is controllable; The dataset includes labels for soft restart, steering controller disconnection, steering control group abnormality, and non-restart. After the dataset is established, SVM (RBF kernel) is used for model training, and the model classifies the fault codes into different fault handling categories. According to the SVM algorithm, it includes feature weights. ∈R6, bias Penalty coefficient slack variables RBF kernel function: u and v represent the 6-dimensional feature vectors after the fault code is standardized. This refers to the kernel function bandwidth parameter.

[0039] Then, real-time fault handling category prediction is performed, specifically including: When a steering fault is detected, the current fault code is generated; Based on the current fault code, extract the steering controller message frame loss time from the communication logs of the chassis domain controller that detected this fault; obtain the corresponding feature attribute vector by querying the preset fault feature knowledge base, based on the mapping relationship between the fault code and the probability of steering controllability, the probability of soft restart resolution, the probability of redundant steering activation, the probability of abnormality of the steering wheel control group, and the probability of hardware failure; generate a 6-dimensional feature attribute vector X corresponding to the current fault code based on the extracted data; The 6-dimensional feature attribute vector X is standardized and preprocessed, and then input into the trained support vector machine classification model; Using a trained SVM model, the system matches the 6-dimensional attributes of the input fault code, performs standardization, model prediction, and label decoding, and finally outputs the fault handling category corresponding to the turnaround fault code. .

[0040] According to the fault handling category, its first label To determine whether the steering system is controllable, the second label... This refers to the specific fault handling category.

[0041] Based on the fault handling category with two tags, the chassis domain controller determines... The faults are categorized into controllable and uncontrollable steering faults for handling and judgment. The faults are categorized into redundancy steering or reference steering anomaly handling, soft restart fault handling, steering controller disconnection handling, and non-restart fault handling.

[0042] S3: Based on the predicted fault handling category label, execute the corresponding graded handling measures, which include steering controller soft restart, vehicle restart, controlling the vehicle to pull over and issuing a warning, or directly requesting manual intervention. In a specific implementation, in autonomous driving mode, the steering fault codes reported by the vehicle are predicted as specific fault handling categories by a support vector machine model. The chassis domain controller then determines the predicted fault handling categories as redundant steering system type, steering control group type, soft restart type, steering controller disconnection type, and non-restart type, and feeds back specific fault handling measures to the autonomous driving system. The autonomous driving system completes the handling of steering faults based on the handling measures fed back by the chassis. Each major fault category has corresponding fault handling measures and fault resolution failure measures.

[0043] As an example, the specific processing flow includes the following four scenarios: 1. When the predicted fault handling category label is uncontrollable steering or abnormal steering control group, the chassis domain controller feeds back to the autonomous driving system that the redundant steering system is enabled or the steering control group is abnormal. The autonomous driving system feeds back the fault information to the dispatching platform and other vehicles in the formation, and plans a parking path to the side of the road. It controls the vehicle to complete the parking action. When the vehicle speed is 0km / h, it requests EPB braking and turns on the warning lights.

[0044] Upon receiving feedback from the vehicle dispatching platform regarding a steering malfunction, the platform will synchronize the malfunction information and handling measures to the takeover operator information platform. The takeover operator will then board the vehicle and take over the malfunction as prompted.

[0045] 2. When the predicted fault handling category label is soft restart, the chassis domain controller feeds back the soft restart fault code and fault cause to the autonomous driving system, and at the same time requests the autonomous driving system to perform a soft restart of the steering controller. After receiving the soft restart request, the autonomous driving system issues a vehicle braking command to control the vehicle to complete the parking action. When the vehicle speed is 0km / h, it requests the EPB to brake and turn on the warning lights, and at the same time issues a steering controller soft restart command to control the steering controller to restart.

[0046] According to the restart of the steering controller, after receiving the restart message, the steering controller will re-enter the autonomous driving mode. The chassis domain controller will detect whether the steering system continues to provide fault codes within 5 seconds to determine whether the fault has been eliminated. If the fault has not been eliminated, manual intervention will be initiated.

[0047] 3. When the predicted fault handling category label is steering controller disconnection, the chassis domain controller reports the steering controller disconnection for 300ms and the reason for the disconnection to the autonomous driving system, and issues a vehicle braking command to the EBS to control the vehicle to complete the parking action. When the vehicle speed is 0km / h, it requests the autonomous driving system to perform remote hibernation and wake-up. After receiving the hibernation and wake-up command, the autonomous driving system requests the EPB to brake and turn on the warning lights, and at the same time issues a hibernation and wake-up command to control the vehicle to restart.

[0048] According to the vehicle restart, the steering controller will re-enter the autonomous driving mode. The chassis domain controller will detect whether the steering system continues to provide fault codes within 5 seconds to determine whether the fault has been eliminated. If the fault has not been eliminated, manual intervention will be initiated.

[0049] 4. When the predicted fault handling category label is non-restart, the chassis domain controller reports the non-restart fault and fault cause to the autonomous driving system, and at the same time requests the autonomous driving system to issue a vehicle braking command to control the vehicle to complete the parking action. When the vehicle speed is 0km / h, the autonomous driving system requests EPB braking and turns on the warning lights, and at the same time requests manual takeover from the dispatch platform.

[0050] In this embodiment, the chassis domain controller monitors and accurately identifies three types of faults frame by frame: redundant steering activation, control wheel anomaly, and controller disconnection, forming an iterative digital expert knowledge base. Furthermore, a support vector machine model based on six-dimensional feature vectors is constructed to intelligently classify faults, achieving accurate prediction of different types of faults such as soft restarts and controller disconnections. Finally, a matching hierarchical handling process is automatically triggered based on the predicted category. This method achieves second-level fault diagnosis and differentiated automatic handling, effectively solving the problem of rapid self-recovery from occasional faults while ensuring driving safety under severe faults. This significantly reduces ineffective vehicle downtime and greatly improves the attendance rate and overall operational efficiency of unmanned mining trucks.

[0051] Furthermore, as a refinement and extension of the specific implementation methods of the above embodiments, and to fully illustrate the specific implementation process in this embodiment, another method for handling steering faults in unmanned dump trucks is provided. This method is based on... Figure 3 The logical control architecture is shown below. Figure 2 As shown, the specific steps of this method are as follows: Step 1: The autonomous driving system enables the vehicle to enter autonomous driving mode through the chassis domain controller.

[0052] Step 2: The autonomous driving system sends a steering command. The chassis domain controller monitors the steering system fault feedback message. The feedback period is 100ms. It determines whether a steering fault has occurred. If so, proceed to step 3. Otherwise, execute the steering action of autonomous driving system command 1 normally. Step 3: Based on steering fault codes and steering fault handling experience, the chassis domain controller uses the SVM algorithm to predict the fault handling category of the current fault code and outputs the prediction result.

[0053] Step 4: The chassis domain controller monitors the steering fault handling type output in step 3 and determines whether the current fault type will cause the steering system to become uncontrollable. If so, continue to step 5; otherwise, proceed to step 7.

[0054] Step 5: The chassis domain controller determines whether the current fault type belongs to the activation of the redundant steering system or the abnormal angle of the steering control group. If so, continue to step 6; otherwise, proceed to step 3.

[0055] Step 6: The chassis domain controller feeds back status 1 "Redundant steering enabled or steering control group angle abnormal", the autonomous driving system plans and controls the parking path, the autonomous driving system issues command 2 EPB braking and command 3 warning light, and the autonomous driving system synchronizes the fault information to the operator to take over the vehicle.

[0056] Step 7: The chassis domain controller determines whether the fault type can be resolved by a soft reboot. If yes, proceed to step 8; otherwise, proceed to step 11.

[0057] Step 8: The chassis domain controller reports status 2 "Steering requires soft restart", the autonomous driving system issues command 4 EBS braking, the autonomous driving system issues command 2 EPB braking and command 3 warning light, and the autonomous driving system requests a soft restart of the steering gear.

[0058] Step 9: The chassis domain controller determines whether the steer-by-wire system continues to provide steering fault information within 5 seconds after the steering gear soft restart. If yes, continue to execute Step 1; otherwise, execute Step 10.

[0059] Step 10: The chassis domain controller reports the fault code from Step 3 and the soft restart process fails. The autonomous driving system reports the fault information to the dispatch platform and synchronizes the fault information to the takeover operator's information platform. The takeover operator then gets into the vehicle to take over.

[0060] Step 11: The chassis domain controller determines whether the fault type is a steering controller disconnection for 300ms. If so, proceed to step 12; otherwise, proceed to step 15.

[0061] Step 12: The chassis domain controller feedback status 3 "Steering controller disconnected", the autonomous driving system issues command 4 EBS braking, the autonomous driving system issues command 2 EPB braking and command 3 warning light, and the autonomous driving system issues command 5 remote sleep wake-up.

[0062] Step 13: The chassis domain controller determines whether the steer-by-wire system continues to provide steering fault information within 5 seconds after the vehicle restarts. If yes, continue with Step 1; otherwise, proceed to Step 14.

[0063] Step 14: The chassis domain controller reports the fault code from Step 3 and the vehicle restart processing failure. The autonomous driving system reports the fault information to the dispatch platform and synchronizes the fault information to the takeover operator's information platform. The takeover operator then gets into the vehicle to take over.

[0064] Step 15: The chassis domain controller determines whether the fault is a non-reboot type fault. If so, continue to step 3; otherwise, proceed to step 16.

[0065] Step 16: The chassis domain controller reports the fault code from Step 3, the autonomous driving system issues Command 4 (EBS braking), Command 2 (EPB braking) and Command 3 (warning light), the autonomous driving system reports the fault information to the dispatch platform, and simultaneously synchronizes the fault information to the operator's information platform, and the operator gets into the vehicle to take over.

[0066] like Figure 4 As shown, the following are embodiments of the unmanned dump truck steering fault handling system provided in this disclosure. This system and the unmanned dump truck steering fault handling methods in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the unmanned dump truck steering fault handling system, please refer to the embodiments of the above unmanned dump truck steering fault handling methods.

[0067] An unmanned dump truck steering fault handling system includes: a fault monitoring and expert experience coding module, a fault handling category prediction module based on a machine learning model, and a hierarchical fault handling execution module.

[0068] The fault monitoring and expert experience coding module is used to monitor the status of the steer-by-wire system in real time through the chassis domain controller in autonomous driving mode, identify the type of steering fault and record the cause of the fault, form an expert experience knowledge base, and assign a unique fault code to different fault causes.

[0069] The fault handling category prediction module is used to build and train a support vector machine classification model. When a steering fault occurs, the feature vector of the current fault code is extracted, and the fault handling category label is predicted using the classification model.

[0070] The graded fault handling execution module is used to execute corresponding graded handling measures according to the predicted fault handling category label. The graded handling measures include steering controller soft restart, vehicle restart, controlling the vehicle to pull over and issuing a warning, or directly requesting manual intervention.

[0071] The unmanned dump truck steering fault handling system provided in this embodiment digitizes historical faults and handling experience to build an expert knowledge base, and intelligently classifies and predicts real-time faults based on a support vector machine model. Ultimately, the system automatically executes a matching hierarchical handling strategy, achieving rapid, accurate, and automated handling of steering faults. This method effectively solves the problems of unintelligent fault identification, difficulty in reusing experience, and limited handling strategies in existing technologies. It can automatically distinguish and recover from intermittent soft faults, while implementing safe stopping and precise alarms for serious faults. While ensuring driving safety, it significantly reduces fault handling time and the need for manual intervention, ultimately greatly improving the attendance rate and overall operational efficiency of the unmanned vehicle fleet in the mining area.

[0072] Figure 5 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0073] The steering failure handling method for unmanned dump trucks provided in this application embodiment can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiments of this invention does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, the electronic device includes, but is not limited to, laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0074] Electronic devices may include processors, external memory interfaces, internal memory, universal serial bus (USB) interfaces, charging management modules, power management modules, batteries, wireless communication modules, audio modules, speakers, microphones, sensor modules, buttons, cameras, displays, and SIM card interfaces, etc.

[0075] A processor may include one or more processing units, such as: a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0076] The processor can serve as the nerve center and command center of an electronic device. The controller can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions.

[0077] The processor may also include memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or that are used repeatedly. If the processor needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0078] An external storage interface (ESI) can be used to connect external memory cards, such as microSD cards, to expand the storage capacity of electronic devices. The external memory card communicates with the processor through the ESI to perform data storage functions, such as saving music and video files on the external memory card.

[0079] Internal memory can be used to store computer executable program code, which includes instructions. The processor executes various functional applications and data processing of electronic devices by running the instructions stored in internal memory. Internal memory can include a program storage area and a data storage area. Internal memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0080] Wireless communication functionality in electronic devices can be achieved through antennas, wireless communication modules, modem processors, and baseband processors.

[0081] Wireless communication modules can provide solutions for wireless communication applications in electronic devices, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies.

[0082] Electronic devices can implement audio functions through audio modules, speakers, receivers, microphones, headphone jacks, and application processors.

[0083] Electronic devices can achieve shooting functions through ISPs, cameras, video codecs, GPUs, displays, and application processors.

[0084] Electronic devices can achieve display functions through GPUs, displays, and application processors.

[0085] A GPU is a microprocessor for image processing, connected to the display screen and application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. A processor may include one or more GPUs, which execute program instructions to generate or modify display information.

[0086] A display screen is used to display images, videos, etc. A display screen includes a display panel.

[0087] The aforementioned electronic equipment realizes the steering fault handling method of the unmanned dump truck of this application by digitizing expert experience into an iterative knowledge base, and realizing hierarchical automated handling of fault intelligent classification and matching based on the support vector machine model. This achieves the beneficial effects of significantly shortening fault handling time, improving vehicle uptime and overall operational efficiency while ensuring safety.

[0088] The storage medium provided in this application stores a program product capable of implementing a steering fault handling method for unmanned dump trucks.

[0089] Methods for handling steering malfunctions in driverless dump trucks include: In autonomous driving mode, the status of the steer-by-wire system is monitored in real time by the chassis domain controller, the type of steering fault is identified and the cause of the fault is recorded, an expert experience knowledge base is formed, and a unique fault code is assigned to different fault causes. Construct and train a support vector machine classification model; when a steering failure occurs, extract the feature vector of the current fault code and use the classification model to predict the fault handling category label; Based on the predicted fault handling category label, corresponding graded handling measures are executed. The graded handling measures include soft restart of the steering controller, vehicle restart, controlling the vehicle to pull over and issuing a warning, or directly requesting manual intervention. In some possible implementations, the unmanned dump truck steering failure handling method of this disclosure can be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0090] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0091] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for handling steering malfunctions in an unmanned dump truck, characterized in that, include: In autonomous driving mode, the status of the steer-by-wire system is monitored in real time by the chassis domain controller, the type of steering fault is identified and the cause of the fault is recorded, an expert experience knowledge base is formed, and a unique fault code is assigned to different fault causes. Construct and train a support vector machine classification model; when a steering failure occurs, extract the feature vector of the current fault code and use the classification model to predict the fault handling category label; Based on the predicted fault handling category label, corresponding graded handling measures are executed. The graded handling measures include soft restart of the steering controller, vehicle restart, controlling the vehicle to pull over and issuing a warning, or directly requesting manual intervention.

2. The method for handling steering malfunctions in an unmanned dump truck according to claim 1, characterized in that, In autonomous driving mode, the chassis domain controller monitors the status of the steer-by-wire system in real time, identifies steering fault types and records fault causes, forms an expert experience knowledge base, and assigns unique fault codes to different fault causes, including: In autonomous driving mode, the chassis domain controller analyzes the status feedback signal of the redundant steering system, the difference in steering parameters between the steering wheel and the reference wheel, and the status feedback signal of the steering controller frame by frame to identify the type of steering fault. The steering fault types include redundant steering activation fault, abnormal steering reference wheel fault, and steering controller disconnection fault.

3. The method for handling steering malfunctions in an unmanned dump truck according to claim 2, characterized in that, The method of analyzing the redundant steering system status feedback signal, the steering parameter difference between the steering wheel and the control wheel, and the steering controller status feedback signal frame by frame using the chassis domain controller to identify the steering fault type includes: The chassis domain controller processes the redundant steering system status feedback signal frame by frame. When the chassis domain controller receives the first frame of the redundant steering system activation signal, it starts counting. When the chassis domain controller receives five consecutive frames of the redundant steering system activation signal, it determines that the redundant steering system is activated. After the redundant steering system is activated, the chassis domain controller starts to feed back the redundant steering activation to the autonomous driving system from the sixth frame of the redundant steering system activation signal to determine that a redundant steering activation fault has occurred. The chassis domain controller processes the steering angle information fed back by the steering reference wheel frame by frame to obtain the steering parameters of the reference wheel; by calculating the difference between the steering parameters of the reference wheel and the preset steering wheel parameters, the steering parameter deviation is obtained; it is determined whether the steering parameter deviation is greater than the preset steering deviation threshold; if so, it is determined that an abnormal fault has occurred in the steering reference wheel. The chassis domain controller detects the steering controller status feedback information frame by frame. When the chassis domain controller does not receive the first frame of the steering controller status signal, it starts timing. When the chassis domain controller loses 3 frames of steering controller status signals, it is determined that a steering controller disconnection fault has occurred.

4. The method for handling steering malfunctions in an unmanned dump truck according to claim 3, characterized in that, The construction and training of the support vector machine classification model includes: A training dataset D is constructed based on the expert experience knowledge base and the fault codes, where D = Where M is the total number of fault codes in the dataset. For the m-th fault code, Here is the 6-dimensional feature attribute vector corresponding to the m-th fault code: ∈R6, For the time of frame loss in steering controller messages; The probability of a controllable turn; This represents the probability of a soft reboot. Probability of enabling redundant steering; This represents the abnormal probability of the steering wheel control group. This represents the probability of hardware failure. The processing category label vector corresponding to the fault code: , A label used to indicate whether steering is controllable; Labels are used to identify fault handling categories; these categories include soft restart, steering controller disconnection, steering control group abnormality, and non-restart. The support vector machine algorithm is used, with radial basis functions. As a kernel function, the model is trained on the training dataset D to determine the model parameters; where u and v represent the 6-dimensional feature vector after fault code standardization, and γ is the kernel function bandwidth parameter; the model parameters include feature weight w, bias b, penalty coefficient C, and slack variable δ.

5. The method for handling steering malfunctions in an unmanned dump truck according to claim 4, characterized in that, When a steering failure occurs, the feature vector of the current fault code is extracted, and the fault handling category label is predicted using the classification model, including: When a steering fault is detected, the current fault code is generated; Based on the current fault code, extract the steering controller message frame loss time from the communication logs of the chassis domain controller that detected this fault; obtain the corresponding feature attribute vector by querying the preset fault feature knowledge base, based on the mapping relationship between the fault code and the probability of steering controllability, the probability of soft restart resolution, the probability of redundant steering activation, the probability of abnormality of the steering wheel control group, and the probability of hardware failure; generate a 6-dimensional feature attribute vector X corresponding to the current fault code based on the extracted data; The 6-dimensional feature attribute vector X is standardized and preprocessed, and then input into the trained support vector machine classification model; The predicted numerical labels are output by the support vector machine classification model, and then converted into specific processing category label vectors through a decoding operation to generate fault processing category labels.

6. The method for handling steering malfunctions in an unmanned dump truck according to claim 5, characterized in that, The step of executing corresponding graded processing measures based on the predicted fault handling category label includes: When the predicted fault handling category label is uncontrollable steering or abnormal steering control group, the autonomous driving system feeds back the fault information to the dispatching platform and other vehicles in the formation, plans a parking path, controls the vehicle to complete the parking action, requests EPB to brake and turns on the warning lights. When the predicted fault handling category label is soft restart, a soft restart request is sent to the autonomous driving system. After receiving the soft restart request, the autonomous driving system issues a vehicle braking command to control the vehicle to complete the stopping action, requests the EPB to brake and turn on the warning lights, and at the same time issues a steering controller soft restart command to control the steering controller to restart. When the steering controller receives the restart message, it re-enters the autonomous driving mode and checks whether the steering system continues to report fault codes within 5 seconds through the chassis domain controller. If the fault is not eliminated, an alarm message is issued to request manual takeover.

7. The method for handling steering malfunctions in an unmanned dump truck according to claim 5, characterized in that, The step of executing corresponding graded processing measures based on the predicted fault handling category label includes: When the predicted fault handling category label is steering controller disconnection, a 300ms steering controller disconnection request is sent to the autonomous driving system, and a vehicle braking command is issued to the EBS to control the vehicle to complete the parking action. The autonomous driving system is requested to remotely hibernate and wake up. After receiving the hibernation and wake-up command, the autonomous driving system requests the EPB to brake and turn on the warning lights, and at the same time issues a hibernation and wake-up command to control the vehicle to restart. After the vehicle restarts, the steering controller re-enters the autonomous driving mode and checks whether the steering system continues to report fault codes within 5 seconds through the chassis domain controller. If the fault is not eliminated, an alarm message is issued to request manual takeover. When the predicted fault handling category label is non-restart, a non-restart fault is reported to the autonomous driving system. At the same time, the autonomous driving system is requested to issue a vehicle braking command to control the vehicle to complete the parking action. The autonomous driving system is requested to apply EPB braking and turn on the warning lights. At the same time, the dispatch platform is requested to take over manually.

8. A steering fault handling system for an unmanned dump truck, characterized in that, The system employs the steering fault handling method for unmanned dump trucks as described in any one of claims 1 to 7; The system includes: The fault monitoring and expert experience coding module is used to monitor the status of the steer-by-wire system in real time through the chassis domain controller in autonomous driving mode, identify the type of steering fault and record the cause of the fault, form an expert experience knowledge base, and assign a unique fault code to different fault causes. The fault handling category prediction module is used to build and train a support vector machine classification model; when a steering fault occurs, the feature vector of the current fault code is extracted, and the classification model is used to predict the fault handling category label. The graded fault handling execution module is used to execute corresponding graded handling measures according to the predicted fault handling category label. The graded handling measures include steering controller soft restart, vehicle restart, controlling the vehicle to pull over and issuing a warning, or directly requesting manual intervention.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the unmanned dump truck steering failure handling method as described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the steering fault handling method for unmanned dump trucks as described in any one of claims 1 to 7.

Images