Fault prediction method, device, medium and product for steer-by-wire system
By collecting and processing multi-source heterogeneous data from the steer-by-wire system, a multi-dimensional feature vector of the reliability attribute is constructed. Combined with fault triggering conditions and severity scores, full-dimensional fault prediction of the steer-by-wire system is realized, improving the safety and reliability of the system and avoiding the risk of loss of control due to sudden failures.
Patent Information
- Application Number
- CN202611050145.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2026-07-15
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2046-07-15
AI Technical Summary
Existing technologies cannot predict all faults in steer-by-wire systems, resulting in some hidden faults not being detected in time, which affects the overall operational safety of the system.
By collecting multi-source heterogeneous data across electrical, mechanical, and transmission dimensions, a target multi-dimensional feature vector with credibility attributes is constructed. Combined with preset fault triggering conditions and independent severity scores, the vehicle-level health is calculated, and fault prediction results are generated, achieving accurate prediction and proactive protection of faults across all dimensions.
It improves the robustness and reliability of the data, filters out occasional data fluctuations, quantifies the degree of failure, and outputs accurate failure prediction results, minimizing the risk of loss of control of the steer-by-wire system due to sudden mechanical or electronic failures, and ensuring the safety of people and vehicles.
Smart Images

Figure CN122561038B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the automotive field, and more particularly to a method, device, medium, and product for predicting faults in a steer-by-wire system. Background Technology
[0002] Currently, steer-by-wire systems have eliminated the rigid requirement for a mechanical connection between the steering wheel and the steering wheels. However, this does not mean a relaxation of safety standards; rather, it imposes more stringent requirements on steering system safety. This shifts the focus of steering system reliability and safety from mechanical safety to the stability of the electronic and electrical systems and actuators. Therefore, accurate prediction and proactive protection against system failures are crucial.
[0003] The inventors discovered that existing technologies mostly detect single or dual faults, without involving prediction, and do not cover all dimensions of electrical, mechanical, and transmission faults. This results in the overall health status of the steer-by-wire system not being fully monitored, and some hidden faults not being detected in time, thus causing safety hazards. Because the components of the steer-by-wire system are closely interconnected, if a fault in one dimension is not detected, it may spread to other dimensions and affect the overall operation of the system. Summary of the Invention
[0004] One objective of this application is to provide a fault prediction method for a steer-by-wire system, which at least solves the technical problem that it is impossible to achieve full-dimensional fault prediction in related technologies.
[0005] To achieve the above objectives, some embodiments of this application provide the following aspects:
[0006] In a first aspect, some embodiments of this application provide a fault prediction method for a steer-by-wire system, comprising: determining a target multi-dimensional feature vector based on multi-source heterogeneous data; the target multi-dimensional feature vector having an attached credibility attribute; comparing the target multi-dimensional feature vector with preset fault triggering conditions to obtain a fault feature vector; calculating an independent severity score corresponding to the fault feature vector; the independent severity score being used to represent the degree of impact of the corresponding faulty component on the overall vehicle safety; determining a vehicle-level health status based on the independent severity score; the vehicle-level health status being used to represent the overall health status of the steer-by-wire system; and generating a fault prediction result based on the independent severity score and the vehicle-level health status.
[0007] Secondly, some embodiments of this application also provide an electronic device, a cloud training paradigm, in which all raw data is uploaded to the cloud for unified training, which facilitates centralized management. The electronic device includes: one or more processors; and a memory storing computer program instructions, which, when executed, cause the processor to perform the steps of the method described above.
[0008] Thirdly, some embodiments of this application also provide a computer-readable medium having computer program instructions stored thereon, which can be executed by a processor to implement the method described above.
[0009] Fourthly, some embodiments of this application also provide a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the method described above.
[0010] Compared with related technologies, the solution provided in this application collects multi-source heterogeneous data covering all dimensions of electrical, mechanical, and transmission systems. This multi-source heterogeneous data is then constructed into a target multi-dimensional feature vector with an attached credibility attribute, integrating the three dimensions of electrical, mechanical, and transmission faults in the steer-by-wire system to improve the robustness and credibility of the collected data. By comparing preset fault triggering conditions, occasional data fluctuations generated during vehicle operation are filtered out, ensuring that only components with a genuine deterioration trend enter the prediction process. An independent severity score is calculated, and the feature values are multiplied and bound to the credibility coefficient during the calculation, allowing the degree of fault in each component to be quantified. Subsequently, the vehicle-level health is calculated based on the independent severity score. Finally, a comprehensive evaluation is performed based on the independent severity score and the vehicle-level health, outputting the fault prediction result. This physically constructs a defense, minimizing the risk of loss of control due to sudden mechanical or electronic failures of the steer-by-wire system, thus ensuring the safety of people and vehicles. Attached Figure Description
[0011] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.
[0012] Figure 1 An exemplary flowchart of a fault prediction method for a steer-by-wire system provided for some embodiments of this application;
[0013] Figure 2 This is a schematic diagram of the structure of an electronic device provided in some embodiments of this application. Detailed Implementation
[0014] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0015] The first embodiment of this application relates to a fault prediction method for a steer-by-wire system. For example... Figure 1 As shown, the method may include the following steps:
[0016] Step S1: Determine the target multi-dimensional feature vector based on multi-source heterogeneous data; the target multi-dimensional feature vector is accompanied by a credibility attribute;
[0017] Step S2: Compare the target multi-dimensional feature vector with the preset fault triggering conditions to obtain the fault feature vector;
[0018] Step S3: Calculate the independent severity score corresponding to the fault feature vector; the independent severity score is used to represent the degree of impact of the corresponding faulty component on the overall vehicle safety;
[0019] Step S4: Determine the vehicle-level health score based on the independent severity score; the vehicle-level health score is used to represent the overall health status of the steer-by-wire system.
[0020] Step S5: Generate fault prediction results based on the independent severity score and the vehicle-level health score.
[0021] For step S1, the vehicle-side sensors collect electrical signals, mechanical signals, and transmission signals in real time as multi-source heterogeneous data. After normalization processing, dynamic reliability assessment, and physical consistency verification of the multi-source heterogeneous data, the target multi-dimensional feature vector is obtained.
[0022] In step S2, the target multi-dimensional feature vector is compared with preset fault triggering conditions. For example, the triggering condition for belt slippage is: the speed difference feature in the transmission dimension satisfies δ>0.08 for 2 seconds, and there is no sudden change in torque command. The triggering condition for abnormal wiring harness resistance is: the wiring harness resistance feature in the electrical dimension satisfies R>100mΩ for 10 seconds, and the current ripple increases by >20%. Only when the specific threshold and duration window in the preset fault triggering conditions are met will the component corresponding to the feature vector be determined to enter a potential fault state, thereby generating a fault feature vector.
[0023] For step S3, the independent severity score Si∈[0,1] corresponding to the fault feature vector is calculated by using a preset piecewise linear function or lookup table method, where 0 represents complete health and 1 represents complete failure.
[0024] For step S4, firstly, a safety priority base value is predefined for each type of fault. The safety priority base value reflects the degree of impact of the component on the safety of the whole vehicle. Then, the whole vehicle-level health is calculated by combining the predefined safety priority base value and the independent severity score.
[0025] For step S5, it is combined with the above steps to form an integrated decision-making system for prediction, early warning, and prevention, outputting fault prediction results and classifying early warning levels.
[0026] It is not difficult to see that, compared with related technologies, the solution provided in this application collects multi-source heterogeneous data covering all dimensions of electrical, mechanical, and transmission systems. This multi-source heterogeneous data is then constructed into a target multi-dimensional feature vector with a credibility attribute, integrating the three dimensions of electrical, mechanical, and transmission faults in the steer-by-wire system, thereby improving the robustness and credibility of the collected data. By comparing preset fault triggering conditions, occasional data fluctuations generated during vehicle operation are filtered out, ensuring that only components with a genuine deterioration trend enter the prediction process. By calculating an independent severity score and binding the feature value with its credibility coefficient during the calculation, the degree of fault in each component can be quantified. Then, based on the independent severity score, the vehicle-level health is calculated. Finally, a comprehensive evaluation is performed based on the independent severity score and the vehicle-level health, outputting the fault prediction result. This physically constructs a defense, minimizing the risk of loss of control due to sudden mechanical or electronic failures of the steer-by-wire system, thus ensuring the safety of people and vehicles.
[0027] In one embodiment, the step S1 of determining the target multi-dimensional feature vector based on the multi-source heterogeneous data may include:
[0028] The multi-source heterogeneous data is normalized to determine multi-dimensional feature vectors; the multi-source heterogeneous data includes electrical signal data, mechanical signal data, and transmission signal data.
[0029] Based on the multi-dimensional feature vector, the target multi-dimensional feature vector is obtained.
[0030] Specifically, the multi-source heterogeneous data is normalized to construct a multi-dimensional feature vector, which can be represented as Xt=[Ttemp,Vripple,Rwire,…,θdiff,avib,RHhum,…,ωdiff,Ttorque,Efft,…], where three features are extracted from the electrical dimension: Ttemp represents the main chip temperature, with an original value of 0~85°C and a normalized value of 0~0.85; Vripple represents the voltage ripple, with an original value of 0~0.3V and a normalized value of… 0~0.3; Rwire represents the wire harness resistance, with an original value of 0~0.15Ω and a normalized value of 0~0.45; three features are extracted from the mechanical dimension: θdiff represents the angle difference, with an original value of 0~2.5° and a normalized value of 0~0.60; aib represents the vibration acceleration, with an original value of 0~0.8m / s² and a normalized value of 0~0.30; RHhum represents the relative humidity, with an original value of 0~65% and a normalized value of 0~0.55; three features are extracted from the transmission dimension: ωdiff represents the speed difference, with an original value of 0~50 rpm and a normalized value of 0~0.20; Ttorque represents the torque fluctuation, with an original value of 0~1.2 N·m and a normalized value of 0~0.40; Efft represents the sideband energy, with an original value of 0~12 dB and a normalized value of 0~0.35.
[0031] Then, since there may be conflicts between signals collected by different sensors, the target multidimensional feature vector is obtained after dynamic credibility evaluation and physical consistency verification of the multidimensional feature vector.
[0032] In this implementation, instead of using a single-dimensional sensor, three specific physical meanings were precisely extracted from the electrical, mechanical, and transmission dimensions to construct a multi-dimensional feature vector. Each feature had an independent non-uniform normalization mapping interval. Then, dynamic credibility assessment and physical consistency verification based on conflict resolution rules were performed to obtain the target multi-dimensional feature vector. This eliminates the computational bias caused by different physical dimensions in subsequent fusion predictions and effectively removes spurious signal fluctuations caused by sensor malfunctions or environmental noise at the data source.
[0033] In one embodiment, obtaining the target multi-dimensional feature vector based on the multi-dimensional feature vector includes:
[0034] Based on the physical dynamics of the signal in the multi-dimensional feature vectors, a confidence coefficient is assigned to each feature vector; the confidence coefficient is used to quantify the reliability of the signal.
[0035] Multiply the confidence coefficient by the feature vector value to obtain the candidate multidimensional feature vector;
[0036] Based on the pre-established fault-feature vector association table and combined with logical judgment rules, abnormal feature vectors in the candidate multi-dimensional feature vectors are removed to obtain the target multi-dimensional feature vector.
[0037] Specifically, a confidence coefficient is dynamically assigned to each feature in the multidimensional feature vector, Ci∈[0,1], with an initial value of 1.0. The confidence coefficient is dynamically adjusted when an abnormal physical change in the signal is detected: when the signal jump exceeds the physical limit, the confidence coefficient is reduced to 0.2, and restored to its original value after 10 consecutive seconds of normal operation; when the signal freezes, the sensor hardware is deemed to have failed, and the confidence coefficient drops to 0, requiring a self-test before it can be restored; when the difference with a redundant sensor from the same source exceeds a set safety threshold, the confidence coefficient is directly multiplied by 0.5; when the deviation from the historical average exceeds a preset boundary, the confidence coefficient is multiplied by 0.7. Then, the confidence coefficient is multiplied by the feature vector value to obtain the candidate multidimensional feature vector. Through this mechanism, low-confidence features are significantly suppressed before entering subsequent judgments.
[0038] Finally, a fault-feature vector association table is built-in, which defines the combination of necessary and auxiliary features for each type of fault specific to the steer-by-wire system. If all the necessary features (logical AND conditions) of a certain fault are missing in the candidate feature vector, the feature will be removed or zeroed out even if its auxiliary feature jumps to alarm. If an abnormal vibration feature appears in the candidate feature vector and no auxiliary feature provides physical support, it is determined to be a false alarm by the vibration sensor or instantaneous environmental interference. The abnormal vibration feature is then directly removed, and the abnormal sensor status is only recorded in the background log.
[0039] In this embodiment, because individual sensors are susceptible to instantaneous electromagnetic interference from road vibrations or window operation, leading to errors, dynamic reliability constraints and physical consistency checks are introduced to adaptively identify and eliminate single-feature anomalies. This improves the robustness of the steer-by-wire system's prediction capabilities and prevents driver panic due to frequent false alarms. The output target multi-dimensional feature vector has undergone rigorous physical consistency checks. Subsequent steps, whether performing independent severity scoring or health calculations, have highly deterministic input sources.
[0040] In one embodiment, the step of comparing the target multi-dimensional feature vector with preset fault triggering conditions to obtain a fault feature vector includes:
[0041] Extract the key feature values corresponding to the preset fault type from the target's multi-dimensional feature vector;
[0042] Based on a preset Boolean operation, the key feature values are compared with the corresponding thresholds in the preset fault triggering conditions to obtain a candidate fault feature vector.
[0043] The candidate fault feature vectors are weighted and determined based on the credibility coefficient attached to the target multidimensional feature vector, and the candidate fault feature vectors with credibility coefficients lower than a preset threshold are eliminated to obtain the fault feature vector.
[0044] Specifically, firstly, based on the preset fault type, a feature combination specifically targeting that fault is extracted from a vector containing nine normalized features. Then, the extracted key feature values are input into a preset Boolean logic gate for comparison. Taking abnormal wire harness resistance as an example, the comparison reveals that the wire harness resistance feature value is true, and the current ripple amplification is also present. Through an AND gate operation, both conditions are simultaneously satisfied, thus activating and generating a candidate fault feature vector. Finally, the confidence coefficient assigned to each feature vector in step S1 is retrieved, and the candidate fault feature vectors are weighted for judgment. For example, assuming worm gear tooth surface damage occurs, if the confidence coefficient obtained through Boolean comparison is higher than a preset threshold, then this candidate feature vector is retained and confirmed as a fault feature vector.
[0045] In this embodiment, Boolean operations (logical AND / OR) combining multiple features are first used as an initial screening threshold to filter false alarms caused by occasional fluctuations in a single feature. When determining candidate vectors, a weighted confidence coefficient and a low-threshold direct elimination mechanism are introduced. Therefore, the target multidimensional feature vector obtained in step S1 is transformed into a hard switch for trigger control, which can intelligently identify which candidate faults are caused by the degradation of vehicle-related components and which are caused by sensor problems or electromagnetic interference. Once the latter is determined, it continues to be intercepted and forcibly eliminated on the spot. This decoupling of the fault mechanism and the confidence level of the information source is achieved, enabling the steer-by-wire system to have extremely high anti-false alarm and self-healing identification capabilities when facing extremely complex real-vehicle electromagnetic interference, bumpy road conditions, and other long-tail extreme conditions.
[0046] Furthermore, in one embodiment, the preset fault triggering conditions include at least an electrical fault determination:
[0047] If the characteristic value of the wire harness resistance obtained by the resistance detection circuit sensor is greater than the preset resistance value and the duration is greater than the first preset time threshold, and at the same time it is determined that the increase in current ripple is greater than the first preset ratio threshold, the wire harness resistance is determined to be abnormal.
[0048] If the temperature characteristic value of the main chip obtained by the temperature sensor is greater than the first temperature threshold and the cumulative over-temperature time is greater than the first duration threshold, or if the temperature characteristic value of the main chip is instantaneously greater than the second dangerous temperature threshold, it is determined to be a solder joint thermal fatigue fault.
[0049] If the voltage ripple characteristic value obtained by the voltage sensor is greater than the first drop threshold and lasts for a second preset time, and the torque sensor determines that there is a torque mismatch, then the fault is identified as insufficient power supply to the motor.
[0050] Specifically, the preset resistance value can be 100mΩ, the first preset time threshold can be 10 seconds, and the first preset ratio threshold can be 20%. When the characteristic value of the harness resistance is greater than the preset resistance value, an alarm will not be triggered immediately. Instead, the state must be continuously greater than the first preset time threshold by a timer. At the same time, the increase in current ripple must also be greater than the first preset ratio threshold before the fault feature vector of abnormal harness resistance is activated.
[0051] Specifically, the first temperature threshold can be 105℃, the first duration threshold can be 500 hours, and the second danger temperature threshold can be 125℃. When the main chip temperature exceeds the first temperature threshold, the over-temperature operation time is accumulated using non-volatile memory. When the accumulated over-temperature time exceeds the first duration threshold, an alarm is triggered. Alternatively, if the measured main chip temperature characteristic value instantaneously exceeds the second danger temperature threshold, the alarm is triggered directly regardless of the accumulated time.
[0052] Specifically, the first drop threshold can be 15%, and the second preset time can be 50ms; the voltage ripple characteristic value, i.e. the voltage drop rate, is calculated in real time. When the voltage drop is detected to be greater than the first drop threshold and lasts for the second preset time, combined with the current torque mismatch state, it is determined that the motor power supply is insufficient.
[0053] Furthermore, in one embodiment, the preset fault triggering condition includes at least a mechanical fault determination:
[0054] If the angle difference feature value obtained by the dual-angle sensor is greater than the first angle difference threshold or the response delay is greater than the third preset time threshold, it is determined to be a gap stroke.
[0055] If the relative humidity characteristic value obtained by the humidity sensor is greater than the first humidity threshold and the duration is greater than the fourth preset time threshold, it is determined to be water intrusion.
[0056] If the vibration acceleration characteristic value obtained from the accelerometer sensor is greater than the first vibration threshold and the kurtosis is greater than the first kurtosis threshold, and the duration is greater than the fifth time threshold, it is determined to be abnormal vibration.
[0057] Specifically, the first angle difference threshold can be 2.5°, and the third preset time threshold can be 80ms; the clearance stroke covers the mechanical clearance performance in two dimensions: static physical deviation (angle difference) and dynamic transmission lag (response delay).
[0058] The first humidity threshold can be 85%, the third preset time can be 10 minutes; the first vibration threshold can be 5 m / s², and the first kurtosis threshold can be 3.5.
[0059] Furthermore, in one embodiment, the preset fault triggering condition includes at least a transmission dimension fault determination:
[0060] If the speed difference feature value obtained by the dual speed sensors is greater than the first speed difference rate threshold and the duration is greater than the sixth time threshold, and at the same time it is determined that there is no sudden change in the torque command, it is determined that the belt is slipping.
[0061] The sideband energy characteristic value obtained from the torque sensor is greater than the normal sideband energy threshold, and the torque fluctuation is greater than the first fluctuation threshold, which is determined to be worm gear tooth surface damage.
[0062] If the torque fluctuation characteristic value obtained from the dual torque sensors is less than the steady-state steering threshold, it is determined that the transmission efficiency has decreased.
[0063] Specifically, the first speed difference threshold can be 0.08, the sixth time threshold can be 2 seconds, the first fluctuation threshold can be 20%, and the steady-state steering threshold can be 85%.
[0064] In one embodiment, determining the vehicle-level health status based on the independent severity score includes:
[0065] Based on the independent severity score and the predefined safety priority base value, the dynamic weight value corresponding to a single fault is calculated.
[0066] The instantaneous health status at the current moment is calculated based on the independent severity score and the dynamic weight value.
[0067] The instantaneous health status is weighted and filtered based on historical health status queue data to obtain the vehicle-level health status at the current moment.
[0068] Specifically, a safety priority base value is predefined for each fault type. This is used to characterize the inherent impact of the component on chassis driving safety. Among them, core safety components such as torque sensors are calibrated with high base values. General transmission or electrical components, such as wire harnesses, belts, and worm gears, are calibrated using low base values. Other components are calibrated between 0.3 and 0.7 according to the safety level. The formula for calculating the dynamic weight value is:
[0069]
[0070] in, Indicates the first Independent severity scores for each component Indicates the first Safety priority base value for each component Indicates the first The dynamic weight value of each component, with coefficient 2 being an empirical amplification factor. The empirical amplification factor can be actually calibrated to significantly increase the weight of high-risk faults, with an upper limit of 0.95 to prevent a single fault from completely dominating the evaluation results.
[0071] The formula for calculating instantaneous health is:
[0072]
[0073] in, For instantaneous health, the numerator in the formula is the weighted sum of the independent severity scores of all activated faults, and the denominator is the sum of dynamic weight values. When all components are fully healthy, i.e., the independent severity scores are all 0, the instantaneous health is 1; when the core component completely fails, i.e., the independent severity score is 1, the instantaneous health will approach 0.
[0074] Finally, to prevent frequent jumps in vehicle-level health due to transient impacts, road noise, or occasional signal jitter during driving, a circular queue consisting of the most recent M health values is maintained in memory. The instantaneous health value calculated at the current moment is weighted and filtered with the data in this historical health value queue to smooth out high-frequency noise, and finally the vehicle-level health value at the current moment is output.
[0075] In this embodiment, the traditional fixed-weighted health assessment method is abandoned. First, a nonlinear formula incorporating an empirical amplification factor and a cutoff upper limit is used to increase the weight of components with high safety baselines or severe degradation in the overall health model. Then, after calculating the instantaneous values, a weighted filtering and smoothing process is performed based on a historical health cyclic queue. This successfully addresses the problem of fatal faults in non-core components being masked by the high average scores of other normal components, highlighting high-risk areas. Furthermore, it filters out occasional dynamic interference noise under complex and harsh driving conditions in real vehicles. This improves the sensitivity, functional safety compliance, and signal stability of the vehicle-level health assessment.
[0076] Optionally, in one embodiment, the method further includes:
[0077] Calculate the decay slope of health based on the historical health cycle queue;
[0078] The remaining safe service life is obtained based on the attenuation slope and the set safety threshold; the remaining safe service life is used as a reference to generate the fault prediction result.
[0079] Specifically, the recursive least squares method is used to perform real-time linear fitting on the M historical health data points in the circular queue, calculating the decay slope of health over time. A decay slope > 0 indicates that the vehicle's current operating state is stable, and there is no decay trend in health; a decay slope < 0 indicates that some electrical, mechanical, or transmission components within the vehicle's steer-by-wire system are experiencing irreversible and continuous damage. Combining the current vehicle-level health, decay slope, and the set chassis safety threshold, the remaining safe service life is estimated. The safe service life serves as an optional reference for generating fault prediction results.
[0080] In one embodiment, generating a fault prediction result based on the independent severity score and the vehicle-level health score includes:
[0081] When the independent severity score is greater than the first threshold, or the vehicle-level health score is less than the first threshold, the warning level is determined to be the first warning, and the control terminal prompts the steer-by-wire system fault check information without interfering with the driver's normal driving operation.
[0082] When the independent severity score is greater than the second threshold, or the vehicle-level health score is less than the second threshold, the warning level is determined to be the second warning. The control terminal will then display the steer-by-wire system maintenance information and send a vehicle parameter adjustment command.
[0083] Specifically, the first threshold can be 0.4, the second threshold can be 0.7, and the first warning can be a yellow warning. At this time, the human-machine interface or control terminal only illuminates or prompts the information prompt that the steering system needs to be checked, and records the fault code in the background. At this time, it does not interfere with any normal driving operation of the driver, ensuring that the normal control of the vehicle does not change unnecessarily.
[0084] Optionally, if the remaining safe service life is within the first service life range, the warning level can also be determined as the first warning level.
[0085] Specifically, the third threshold can be 0.8, the fourth threshold can be 0.5, and the second warning can be a red warning. The control terminal prompts maintenance information for the steer-by-wire system and sends parameter adjustment commands to the vehicle's brake-steering linkage controller. For example, the intervention force coefficient of the left and right wheel differential braking is actively increased from the default value of 1.0 to 1.5, and the steering response speed coefficient is adjusted to 1.2 to establish braking redundancy. At the same time, the maximum output torque of the EPS motor is limited to prevent slippage from worsening, and the steering wheel feel is made heavier, forcing the driver to perceive the physical changes and drive cautiously.
[0086] In this embodiment, the traditional passive alarm mode for single-point faults is abandoned. Instead, a logical multi-dimensional parallel judgment architecture is adopted, using independent severity scores and vehicle-level health as triggering conditions. Furthermore, a graded fault-tolerant closed-loop system for first and second warnings is established for different damage-related qualitative change nodes. On the one hand, in the first warning stage, the system can accurately capture early latent degradation, issuing warnings without disturbing the driver or disrupting normal driving smoothness, thus avoiding unnecessary panic and wasted maintenance resources. On the other hand, in the second warning stage, the system can forcibly intervene in the chassis control domain in advance by sending vehicle parameter adjustment commands when the steer-by-wire system is in a critical fault state before a complete and sudden failure. This achieves an integrated closed-loop of "prediction-warning-prevention" at the chassis functional safety level. Even if the steer-by-wire system subsequently experiences a serious hardware power failure or mechanical jamming, the vehicle can still maintain directional control by using the adjusted braking parameters because the second warning has already physically adjusted the braking and steering redundancy and pre-reduced the risk domain for the entire vehicle.
[0087] The steps of the various methods described above are only for clarity. In practice, they can be combined into one step or some steps can be split into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this application. Adding insignificant modifications or introducing insignificant designs to the algorithm or process, but without changing the core design of the algorithm and process, are also within the scope of protection of this application.
[0088] Furthermore, some embodiments of this application also provide an electronic device. The electronic device can be various forms of digital computer, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, etc. The electronic device can also be various forms of mobile devices, such as cellular phones, smartphones, wearable devices, and other similar computing devices.
[0089] The electronic device includes: one or more processors; and a memory storing computer program instructions that, when executed, cause the processor to perform the steps of the methods provided in any one or more of the above embodiments. Figure 2An exemplary structural diagram of the electronic device is disclosed. The electronic device includes one or more processors 1101, a memory 1102, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components are interconnected via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some other embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple electronic devices can be connected, each providing some of the necessary operations. The components, their connections and relationships, and their functions shown herein are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.
[0090] The electronic device may further include an input device 1103 and an output device 1104. The processor 1101, memory 1102, input device 1103 and output device 1104 may be connected by a bus or other means, as shown in the figure, which is connected by a bus.
[0091] Input device 1103 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the electronic device, such as a touch screen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 1104 may include a display device, auxiliary lighting device (e.g., LED), and haptic feedback device (e.g., vibration motor). The display device may include, but is not limited to, a liquid crystal display, a light-emitting diode display, and a plasma display. In some embodiments, the display device may be a touch screen.
[0092] To provide interaction with the user, the electronic device can be a computer. The computer has: a display device (e.g., a cathode ray tube or LCD monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback); and input from the user can be received in any form (e.g., voice input or tactile input).
[0093] In this embodiment, a computer-readable medium stores a computer program / instructions that, when executed by a processor, implement the steps of the methods provided in any one or more of the above embodiments. This computer-readable medium may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into that device. The aforementioned computer-readable medium carries one or more computer-readable instructions.
[0094] The memory 1102 can serve as a non-transitory computer-readable storage medium, used to store non-transitory software programs, non-transitory computer-executable programs, and modules. The processor 1101 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions, and modules stored in the memory 1102, thereby implementing the program instructions / modules corresponding to the methods provided in any one or more of the embodiments described above in this application.
[0095] The memory 1102 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device. Furthermore, the memory 1102 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 1102 may optionally include memory remotely located relative to the processor 1101, and these remote memories can be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
[0096] It should be noted that the computer-readable medium described in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. Computer-readable media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
[0097] Computer-readable media include permanent and non-permanent, removable and non-removable media, which can store information by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory, static random access memory, dynamic random access memory, other types of random access memory, read-only memory, electrically erasable programmable read-only memory, flash memory or other memory technologies, read-only optical discs, digital versatile optical discs or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.
[0098] Computer program code for performing the operations of this application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, and conventional procedural programming languages such as C or similar languages. The program code can be executed 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 remote computers, the remote computer can be connected to the user's computer via any type of network—including local area networks (LANs) or wide area networks (WANs), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0099] In the above embodiments, all or part of the implementation can be achieved through software, hardware, firmware, or any combination thereof. For example, it can be implemented using an application-specific integrated circuit (ASIC), a general-purpose computer, or any other similar hardware device. In some embodiments, the software program of this application can be executed by a processor to implement the above steps or functions. Similarly, the software program of this application (including related data structures) can be stored in a computer-readable recording medium, such as RAM memory, magnetic or optical drives, floppy disks, and similar devices. In addition, some steps or functions of this application can be implemented in hardware, for example, as circuitry that cooperates with a processor to perform the various steps or functions.
[0100] The computer program product provided in this application includes one or more computer programs / instructions. When executed by a processor, these computer programs / instructions generate, in whole or in part, the processes or functions described in this application. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive), etc.
[0101] The flowcharts or block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of devices, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated 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-specific system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0102] The scope of this application is defined by the appended claims rather than the foregoing description, and is therefore intended to encompass all variations falling within the meaning and scope of equivalents of the claims. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. Terms such as "first," "second," etc., are used only to distinguish descriptions and do not indicate any particular order, nor should they be construed as indicating or implying relative importance.
[0103] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily made by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims, and the above embodiments should be regarded as exemplary and non-limiting.
Claims
1. A fault prediction method for a steer-by-wire system, characterized in that, include: Based on multi-source heterogeneous data, determine the target's multi-dimensional feature vector; The target multi-dimensional feature vector is accompanied by a credibility attribute; By comparing the target's multi-dimensional feature vector with the preset fault triggering conditions, a fault feature vector is obtained; Calculate the independent severity score corresponding to the fault feature vector; The independent severity score is used to indicate the degree of impact of the corresponding faulty component on the overall vehicle safety. The vehicle-level health status is determined based on the independent severity score, including: calculating the dynamic weight value corresponding to a single fault based on the independent severity score and a predefined safety priority base value; calculating the instantaneous health status at the current moment based on the independent severity score and the dynamic weight value; and performing weighted filtering on the instantaneous health status based on historical health status queue data in the historical health status circular queue to obtain the vehicle-level health status at the current moment; wherein, the vehicle-level health status is used to represent the overall health status of the steer-by-wire system; Based on the historical health status cyclic queue, the health status decay slope is calculated; based on the decay slope and the set safety threshold, the remaining safe service life is obtained; the remaining safe service life is used as a reference to generate the fault prediction result. Based on the independent severity score, the vehicle-level health score, and the remaining safe service life, a fault prediction result is generated.
2. The method according to claim 1, characterized in that, The step of determining the target multi-dimensional feature vector based on the multi-source heterogeneous data includes: The multi-source heterogeneous data is normalized to determine multi-dimensional feature vectors; the multi-source heterogeneous data includes electrical signal data, mechanical signal data, and transmission signal data. Based on the multi-dimensional feature vector, the target multi-dimensional feature vector is obtained.
3. The method according to claim 2, characterized in that, The step of obtaining the target multi-dimensional feature vector based on the multi-dimensional feature vector includes: Based on the physical dynamics of the signal in the multi-dimensional feature vectors, a confidence coefficient is assigned to each feature vector; the confidence coefficient is used to quantify the reliability of the signal. Multiply the confidence coefficient by the feature vector value to obtain the candidate multi-dimensional feature vector; Based on the pre-established fault-feature vector association table and combined with logical judgment rules, abnormal feature vectors in the candidate multi-dimensional feature vectors are removed to obtain the target multi-dimensional feature vector.
4. The method according to claim 3, characterized in that, The comparison of the target's multi-dimensional feature vector with preset fault triggering conditions yields a fault feature vector, including: Extract the key feature values corresponding to the preset fault type from the target's multi-dimensional feature vector; Based on a preset Boolean operation, the key feature values are compared with the corresponding thresholds in the preset fault triggering conditions to obtain a candidate fault feature vector. The candidate fault feature vectors are weighted and determined based on the credibility coefficient attached to the target multi-dimensional feature vector, and the candidate fault feature vectors with credibility coefficients lower than a preset threshold are eliminated to obtain the fault feature vector.
5. The method according to claim 4, characterized in that, The preset fault triggering conditions include at least electrical fault judgment: If the wire harness resistance obtained by the resistance detection circuit sensor is greater than the preset resistance value and the duration is greater than the first preset time threshold, and at the same time the current ripple increase is greater than the first preset ratio threshold, the wire harness resistance is determined to be abnormal. If the junction temperature obtained by the temperature sensor is greater than the first temperature threshold and the cumulative over-temperature time is greater than the first duration threshold, or if the junction temperature characteristic value is instantaneously greater than the second dangerous temperature threshold, it is determined to be a thermal fatigue failure of the solder joint. If the voltage drop rate characteristic value obtained by the voltage sensor is greater than the first drop threshold and lasts for a second preset time, and the torque sensor determines that there is a torque mismatch, then the fault is identified as insufficient power supply to the motor.
6. The method according to claim 1, characterized in that, The process of generating fault prediction results based on the independent severity score and the vehicle-level health score includes: When the independent severity score is greater than the first threshold, or the vehicle-level health score is less than the second threshold, the warning level is determined to be the first warning, and the control terminal prompts the steer-by-wire system fault check information without interfering with the driver's normal driving operation. When the independent severity score is greater than the third threshold, or the vehicle-level health score is less than the fourth threshold, the warning level is determined to be the second warning. The control terminal will then display the steer-by-wire system maintenance information and send a vehicle parameter adjustment command.
7. An electronic device, characterized in that, The electronic device includes: One or more processors; and A memory storing computer program instructions, which, when executed, cause the processor to perform the steps of the method as described in any one of claims 1 to 6.
8. A computer-readable medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 6.
9. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 6.
Citation Information
Patent Citations
Method and system for fault isolation in an electric power steering system
CN107154084A
Vehicle fault diagnosis method and related equipment
CN122085964A
