A real-time fault detection method for vehicle electronic brake system

Abstract

The present invention relates to the field of vehicle brake fault detection, and in particular to a real-time fault detection method for a vehicle electronic brake system, the method comprising: collecting vehicle driving status data through an on-board sensor network and an electronic control unit, calculating filtered residual data of a target wheel speed sensor, and establishing calibration reference parameters of a healthy state; obtaining a dynamic response adaptive adjustment factor of the vehicle by jointly analyzing vehicle acceleration data and residual fluctuation data; obtaining a small drift confirmation factor of the vehicle through candidate residuals under a low dynamic interference state of the vehicle; and performing continuous fault judgment by combining the vehicle's dynamic response adjustment factor and the small drift confirmation factor to obtain a fault judgment result of the wheel speed sensor, thereby improving the accuracy and sensitivity of fault detection when a small systematic deviation occurs in the wheel speed sensor.

Description

Technical Field

[0001] The present invention relates to the field of vehicle brake fault detection, and in particular to a real-time fault detection method for a vehicle electronic brake system. Background Art

[0002] Modern vehicles are commonly equipped with electronic braking systems, such as anti-lock braking systems (ABS), electronic stability control (ESC), and traction control systems. These systems significantly enhance braking performance, driving stability, and overall safety in complex driving conditions by precisely regulating the braking force of the braking system or the vehicle's driving force. Wheel speed sensors, as the core sensing components of electronic braking systems, accurately measure the rotational speed of each wheel in real time, providing the electronic control unit with the essential data for decision-making and control. Based on the signals from the wheel speed sensors, the ECU determines the wheel's immediate motion state, such as whether a wheel is locked, the drive wheel is spinning, or the vehicle is showing signs of instability, and rapidly adjusts brake pressure or engine torque accordingly. Therefore, the accuracy and stability of the wheel speed sensor signals are crucial to the electronic braking system's ability to effectively fulfill its safety-enhancing responsibilities. Currently, a common approach for wheel speed sensor fault diagnosis is model comparison. This approach constructs a reference model of the vehicle and uses information such as the speeds of other wheels and vehicle dynamic parameters to estimate the target wheel's expected speed. The actual speed output by the wheel speed sensor is then compared with the expected speed predicted by the model, generating a residual. In traditional fault judgment logic, when the amplitude of this residual data continues to exceed a pre-set fixed threshold for a period of time, the system determines that the corresponding wheel speed sensor has failed.

[0003] However, the conventional methods of using fixed thresholds to determine wheel speed sensor residual data for fault diagnosis suffer from significant deficiencies in identifying early, subtle wheel speed sensor faults. Specifically, when a wheel speed sensor's output data exhibits small, intermittent systematic deviations due to gradual performance changes or changes in the operating environment—that is, wheel speed readings are consistently slightly higher or lower than the vehicle's actual wheel speed—these minor systematic deviations, an early sign of potential sensor performance degradation, can gradually develop into more significant faults. These deviations are particularly likely to negatively impact the control accuracy and responsiveness of electronic braking systems, such as those for anti-lock braking or electronic stability control systems, at critical moments when these systems are engaged, thereby threatening vehicle safety and stability. A major limitation of conventional fixed-threshold methods is that, to avoid false alarms during normal vehicle dynamics, the thresholds are typically set relatively loosely. This loose threshold leads to insensitivity to these minor systematic deviations, causing the residual signals generated by these deviations to be too small to trigger an alarm or to be mistaken for normal signal noise, leading to missed fault detection. Therefore, how to accurately and sensitively detect the intermittent, small-amplitude but unidirectional continuous systematic deviation of the wheel speed sensor while effectively adapting to the normal dynamic changes of the vehicle and suppressing noise interference has become a key technical problem that needs to be urgently solved in the field of vehicle electronic brake system fault detection. Summary of the Invention

[0004] In view of this, an embodiment of the present invention provides a real-time fault detection method for a vehicle electronic brake system to solve the problems of low accuracy and poor sensitivity in fault detection when a wheel speed sensor has a slight systematic deviation.

[0005] An embodiment of the present invention provides a real-time fault detection method for a vehicle electronic brake system, the method comprising the following steps:

[0006] Step S1: collecting vehicle driving status data through the on-board sensor network and the electronic control unit, calculating the filtered residual data of the target wheel speed sensor, and obtaining the calibration reference parameters of the health state;

[0007] Step S2: obtaining a dynamic response adaptive adjustment factor of the vehicle by jointly analyzing the vehicle dynamic energy and residual signal volatility on the vehicle acceleration data and the residual fluctuation data;

[0008] Step S3: Obtaining the vehicle's slight drift confirmation factor by performing a significance analysis on the consistency and amplitude of candidate residuals under the vehicle's low dynamic disturbance state;

[0009] Step S4: performing a continuous fault judgment by combining the vehicle's dynamic response adjustment factor and the small drift confirmation factor to obtain a fault judgment result of a small systematic deviation of the wheel speed sensor;

[0010] Step S5: Complete the active maintenance response of the wheel speed sensor by performing signal reporting and status storage processing on the fault determination result.

[0011] Preferably, the vehicle driving state data is collected through the vehicle sensor network and the electronic control unit, the filtered residual data of the target wheel speed sensor is calculated, and the calibration reference parameters of the health state are established, including:

[0012] Set a data sampling period to collect vehicle driving status data through the on-board sensor network and electronic control unit. The collected data includes: vehicle longitudinal acceleration, vehicle lateral acceleration, vehicle reference speed, and raw wheel speed data output by the vehicle target wheel speed sensor;

[0013] Obtaining a desired wheel speed of a vehicle target wheel speed sensor by using a vehicle reference speed and a dynamic tire radius of a target wheel; using a difference between the original wheel speed data and the desired wheel speed as vehicle target wheel speed original residual data; and filtering the vehicle target wheel speed original residual data by using a second-order Butterworth low-pass filter to obtain vehicle target wheel speed residual data;

[0014] Through the vehicle's offline calibration process, baseline dynamic energy data of the vehicle's normal dynamic energy level, baseline residual fluctuation data of the residual signal's inherent fluctuation level when the wheel speed sensor is working normally, and baseline noise standard deviation data of the healthy state residual data under steady-speed driving conditions are obtained; the baseline dynamic energy data, the baseline residual fluctuation data, and the baseline noise standard deviation data are stored as baseline parameters in the vehicle's electronic control unit.

[0015] Preferably, the step of performing a joint analysis of vehicle dynamic energy and residual signal volatility on vehicle acceleration data and residual fluctuation data to obtain the vehicle dynamic response adaptive adjustment factor includes:

[0016] By performing vehicle dynamic energy analysis on the longitudinal acceleration and lateral acceleration of the vehicle, a first vehicle dynamic energy index at a target moment is obtained;

[0017] Set the time series window of the wheel speed sensor residual data and obtain the short-term wheel speed residual standard deviation of the wheel speed sensor residual data in the previous time series window at the target time;

[0018] The dynamic response adaptive adjustment factor of the vehicle is obtained by performing a fusion evaluation of the dynamic driving intensity and the wheel speed residual fluctuation level on the first vehicle dynamic energy index and the short-term wheel speed residual standard deviation.

[0019] Preferably, the obtaining of the first vehicle dynamic energy index at the target moment by performing vehicle dynamic energy analysis on the longitudinal acceleration and the lateral acceleration of the vehicle includes:

[0020] The method includes setting a sliding time window length for dynamic energy analysis; obtaining the sum of the squares of the vehicle's lateral acceleration and longitudinal acceleration for each timestamp in the sliding time window for dynamic energy analysis; and calculating the result of raising the square of the mean of the sum of the squares of the accelerations corresponding to all timestamps in the sliding time window to the power of one-half as the first vehicle dynamic energy indicator at the target moment.

[0021] Preferably, the step of obtaining the vehicle's dynamic response adaptive adjustment factor by performing a fusion evaluation of the dynamic driving intensity and the wheel speed residual fluctuation level on the first vehicle dynamic energy index and the short-term wheel speed residual standard deviation includes:

[0022] Obtain baseline dynamic energy data and baseline residual fluctuation data; use the ratio of the first vehicle dynamic energy index to the baseline dynamic energy data as a first adjustment factor; use the ratio of the short-term wheel speed residual standard deviation to the baseline residual fluctuation data as a second adjustment factor; and use the result of adding a constant 1, the first adjustment factor, and the second adjustment factor as the vehicle's dynamic response adaptive adjustment factor.

[0023] Preferably, the obtaining of the vehicle's slight drift confirmation factor by performing a significance analysis on the consistency and amplitude of candidate residuals under the vehicle's low dynamic interference state includes:

[0024] Setting a basic threshold value of the vehicle wheel speed residual data, and performing weighted optimization on the basic threshold value using a dynamic response adaptive adjustment factor of the vehicle to obtain a first dynamic threshold value of the vehicle wheel speed residual data;

[0025] Preliminarily screening the vehicle wheel speed residual data by using the first dynamic threshold of the vehicle wheel speed residual data to obtain candidate vehicle wheel speed residual data;

[0026] By performing consistency evaluation on candidate residual data, a conditional cumulative consistency score is obtained; by performing amplitude change analysis on candidate residual data, a relative degree score of the conditional amplitude of candidate residual data exceeding baseline noise is obtained;

[0027] The vehicle's slight drift confirmation factor is obtained by comprehensively evaluating the conditional cumulative consistency score and the relative degree score of the vehicle wheel speed residual data conditional amplitude exceeding the baseline noise.

[0028] Preferably, the step of performing consistency evaluation on the candidate residual data to obtain a conditional cumulative consistency score of the candidate residual data; and performing amplitude change analysis on the candidate residual data to obtain a relative degree score of the conditional amplitude of the candidate residual data exceeding the baseline noise comprises:

[0029] The length of a long observation time window for determining minor drift is set; the vehicle wheel speed residual data is windowed using the long observation time window length to obtain the first window of the vehicle wheel speed residual data; the driving state is evaluated using the vehicle's real-time driving speed, lateral acceleration, and longitudinal acceleration to obtain a vehicle steady speed condition evaluation result. If the vehicle is in a steady speed state, the vehicle steady speed condition evaluation result is 1; if the vehicle is not in a steady speed state, the vehicle steady speed condition evaluation result is 0;

[0030] The candidate residual data satisfying the vehicle steady speed driving condition evaluation result of 1 in the first window of the vehicle wheel speed residual data at the target moment is used as the second candidate wheel speed residual data at the target moment; the absolute value of the sum of all the second candidate wheel speed residual data in the first window at the target moment is used as the cumulative deviation direction evaluation at the target moment; the sum of the absolute values ​​of all the second candidate wheel speed residual data in the first window at the target moment is used as the total fluctuation magnitude evaluation at the target moment; the ratio of the cumulative deviation direction evaluation at the target moment to the total fluctuation magnitude evaluation at the target moment is used as the conditional cumulative consistency score of the candidate residual data at the target moment;

[0031] A significance factor for the candidate residual is set; a result obtained by multiplying the baseline noise standard deviation data by the significance factor is used as the significance standard deviation of the candidate residual; a first relative degree evaluation at the target moment is obtained by subtracting the mean of the absolute values ​​of the second candidate wheel speed residual data at the target moment from the significance standard deviation and dividing the result by the baseline noise standard deviation data; and the larger value between the first relative degree evaluation at the target moment and a constant of 0 is used as the relative degree score of the conditional amplitude of the candidate residual data exceeding the baseline noise.

[0032] Preferably, the step of comprehensively evaluating the cumulative consistency score of the conditions and the relative degree to which the conditional amplitude of the vehicle wheel speed residual data exceeds the baseline noise to obtain the vehicle's slight drift confirmation factor includes:

[0033] The result of multiplying the conditional cumulative consistency score of the candidate residual data at the target moment by the relative degree score of the conditional amplitude of the candidate residual data exceeding the baseline noise is used as the vehicle's slight drift confirmation factor.

[0034] Preferably, the method of performing continuous fault judgment by combining the vehicle's dynamic response adjustment factor and the small drift confirmation factor to obtain a fault judgment result of a small systematic deviation of the wheel speed sensor includes:

[0035] A fault judgment threshold and a fault confirmation duration period length are set, and a fault confirmation counter is initialized. During a data sampling period, if the vehicle's slight drift confirmation factor is greater than the fault judgment threshold, the fault confirmation counter is incremented; if the vehicle's slight drift confirmation factor is less than or equal to the fault judgment threshold, the fault confirmation counter is reset to 0; when the accumulated value of the fault confirmation counter reaches the duration period length, it is determined that a slight systematic deviation fault has occurred in the target wheel speed sensor.

[0036] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0037] This invention provides a real-time fault detection method for a vehicle electronic brake system. Compared to existing diagnostic methods that rely solely on fixed thresholds or instantaneous fluctuations, this invention first establishes a joint analysis mechanism based on the difference between the vehicle's dynamic state and wheel speed sensor responses. The system acquires the vehicle's longitudinal and lateral accelerations, reference driving speed, and raw wheel speed sensor signals in real time to construct a residual signal representing the degree of deviation between vehicle operation and desired wheel speed. Signal processing techniques are then used to suppress high-frequency noise and occasional disturbances, resulting in a more stable and discriminable signal signature. This process ensures a stable input foundation for subsequent diagnostic models based on raw signal quality. To fully account for the rationality of wheel speed signal fluctuations under different driving conditions and enhance the system's adaptability to complex dynamic behaviors, this invention incorporates a calibration mechanism in the healthy vehicle state during system initialization. By collecting and statistically modeling vehicle operating data and wheel speed response results under various typical driving conditions over a long period of time, the system obtains benchmark values ​​that reflect normal vehicle driving characteristics, including a dynamic behavior reference value, a signal fluctuation level reference value, and a noise floor under static driving conditions. Through the construction of this calibration model, the system can adaptively adjust the detection sensitivity under different vehicles and different road conditions, significantly improving the versatility and deployment efficiency of the algorithm. In terms of the discrimination mechanism, the present invention proposes for the first time a dual-factor diagnostic model in which a dynamic adjustment factor and a small drift confirmation factor work together. Among them, the design of the dynamic adjustment factor fully considers the impact of the actual operating state of the vehicle on the fluctuation of the wheel speed signal. When the vehicle is in high-speed driving, sudden acceleration, emergency braking or steering, the initial residual recognition threshold is automatically relaxed to effectively prevent the system from misjudging the dynamic disturbance generated by the vehicle itself as a sensor abnormality; when the vehicle is in a low-dynamic state such as stable cruising or constant speed driving, the recognition threshold is automatically tightened, thereby enhancing the system's perception of weak but persistent abnormal deviations, and achieving a dynamic balance between fault false alarm control in dynamic conditions and abnormality detection sensitivity in static conditions.

[0038] This invention also introduces a continuous confirmation mechanism. After the diagnostic system identifies a suspected deviation signal, it must undergo a continuous judgment cycle and maintain consistency before confirming the fault status. This mechanism significantly reduces the risk of misjudgment caused by non-structural events such as occasional vibration and short-term electrical interference, making the final diagnosis more stable and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a method flow chart of a real-time fault detection method for a vehicle electronic brake system provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0040] The embodiments of the present disclosure are described in detail below, and examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and intended to be used to explain the present disclosure, but should not be understood as limiting the present disclosure.

[0041] In order to illustrate the technical solution of the present invention, specific embodiments are provided below.

[0042] See also Figure 1 , is a method flow chart of a real-time fault detection method for a vehicle electronic brake system provided by the first embodiment of the present invention, such as Figure 1 As shown, the method may include:

[0043] Step S1 : collecting vehicle driving status data through the vehicle sensor network and the electronic control unit, calculating the filtered residual data of the target wheel speed sensor, and obtaining the calibration reference parameters of the health status.

[0044] First, during vehicle operation, the on-board sensor network and related electronic control units collect data related to the vehicle's driving status and wheel speed sensor operation in real time with a sampling period of 10 milliseconds, corresponding to a sampling frequency of 100 Hz. Specifically, the collected data includes the vehicle's longitudinal acceleration, the vehicle's lateral acceleration, the vehicle's reference speed, and the raw wheel speed data output by the vehicle's target wheel speed sensor.

[0045] On the basis of collecting the above data, the expected wheel speed of the target wheel speed sensor at the target moment is further calculated by the vehicle reference speed and the dynamic tire radius of the target wheel. Specifically, the expected wheel speed is calculated by dividing the vehicle reference speed by the dynamic tire radius of the target wheel.

[0046] After obtaining the desired wheel speed, the target wheel speed sensor's actual wheel speed is subtracted from the desired wheel speed to calculate the raw wheel speed residual data at the target moment. To eliminate the high-frequency noise and irregular fluctuations inherent in this raw wheel speed residual data and extract more stable and reliable fault signatures, the raw wheel speed residual data is filtered using a second-order Butterworth low-pass filter to obtain filtered residual data, which is then used as the residual data for the vehicle's target wheel speed.

[0047] After obtaining the residual data of the vehicle's target wheel speed, the baseline parameters under the healthy state are obtained through an offline calibration process. Specifically, a calibration vehicle with a wheel speed sensor that is confirmed to be in normal working condition is selected. Under test conditions covering various typical driving conditions, a large amount of the above-defined healthy state data is collected, especially the vehicle acceleration data and the wheel speed residual data after filtering. Based on this healthy state data set, the following calibration baseline parameters are calculated and determined, including: baseline dynamic energy data of the vehicle's normal dynamic energy level, baseline residual fluctuation data of the inherent fluctuation level of the residual signal when the wheel speed sensor is working normally, and baseline noise standard deviation data of the healthy state residual data under steady-speed driving conditions; the baseline dynamic energy data, baseline residual fluctuation data and baseline noise standard deviation data are stored as baseline parameters in the vehicle's electronic control unit.

[0048] Step S2: obtaining a dynamic response adaptive adjustment factor of the vehicle by performing a joint analysis of the vehicle dynamic energy and the residual signal volatility on the vehicle acceleration data and the residual fluctuation data.

[0049] During actual vehicle operation, its driving conditions are complex and varied, including various dynamic conditions such as acceleration, deceleration, steering, and navigating uneven roads. Under these dynamic conditions, even if the wheel speed sensors are operating perfectly properly, the instantaneous rotational speed of each wheel will experience reasonable or even significant fluctuations due to physical phenomena such as the interaction between the wheel and the road, the transfer of vehicle load, and the elastic deformation of the tire. These normal wheel speed fluctuations will inevitably manifest as corresponding fluctuating components in the residual signal when compared with the vehicle reference model. Existing technologies use a fixed threshold to determine whether the residual signal is abnormal. To avoid a large number of false fault alarms during these normal vehicle dynamics, this fixed threshold must be set relatively high. However, a high fixed threshold directly results in insensitivity to small systematic deviations that indicate early sensor failure or gradual performance degradation, leading to missed detection of these true faults.

[0050] Therefore, to resolve the inherent conflict between fixed thresholds adapting to vehicle dynamics and detecting minor faults, the present invention first introduces a vehicle dynamic response adaptive adjustment factor. This factor dynamically adjusts the initial fault diagnosis benchmark based on the vehicle's current real-time dynamic driving intensity and the recent inherent fluctuation level of the wheel speed sensor residual signal. When the vehicle is experiencing intense dynamic conditions (such as sudden acceleration, braking, or rapid steering), large fluctuations in the wheel speed residual signal are normal. The vehicle's dynamic response adaptive adjustment factor should accordingly raise the judgment benchmark to tolerate these reasonable dynamic disturbances and prevent false alarms. Conversely, when the vehicle is in a stable driving state and the residual signal's inherent fluctuations are relatively small, any minor deviations from the normal baseline are more worthy of attention. In this case, the vehicle's dynamic response adaptive adjustment factor should make the judgment benchmark more stringent to increase sensitivity to weak abnormal signals. In this way, the vehicle's dynamic response adaptive adjustment factor enables the initial fault detection screening process to intelligently adapt to the vehicle's real-time operating conditions, providing a more reliable input for subsequent, more refined identification of minor systematic deviations.

[0051] For the vehicle's dynamic response adaptive adjustment factor, first, a vehicle dynamic energy analysis is performed on the vehicle's longitudinal acceleration and lateral acceleration to obtain a first vehicle dynamic energy index at the target moment. Then, a timing window of the wheel speed sensor residual data is set to obtain the short-term wheel speed residual standard deviation of the wheel speed sensor residual data in the previous timing window at the target moment. The vehicle's dynamic response adaptive adjustment factor is obtained by performing a fusion evaluation of the dynamic driving intensity and the wheel speed residual fluctuation level on the first vehicle dynamic energy index and the short-term wheel speed residual standard deviation.

[0052] Specifically, first, the length of the sliding time window for dynamic energy analysis is set. In this embodiment, the sliding time window length is set to 0.5 seconds of sampling points; the sum of the squares of the vehicle's lateral acceleration and longitudinal acceleration for each timestamp in the sliding time window for dynamic energy analysis is obtained; and the result of the calculation of the power of one-half of the mean of the sum of the squares of acceleration corresponding to all timestamps in the sliding time window is used as the first vehicle dynamic energy indicator at the target moment.

[0053] In one embodiment, it is assumed that the first The longitudinal acceleration of the vehicle at a historical moment is ; The first The lateral acceleration of the vehicle at a historical moment is ; The number of data points in the sliding window used for dynamic energy analysis is , then in The calculation formula of the first vehicle dynamic energy index at a moment is:

[0054]

[0055] in, Indicates the The first vehicle dynamic energy index at a moment; Indicates the The longitudinal acceleration of the vehicle at each historical moment; Indicates the The lateral acceleration of the vehicle at each historical moment; Indicates the number of data points in the sliding window used for dynamic energy analysis.

[0056] After obtaining the first vehicle dynamic energy index at the target time, a timing window for the wheel speed sensor residual data is set. In the embodiment of the present invention, the timing window length of the wheel speed sensor residual data is set to a sampling length corresponding to 3 seconds, and the short-term wheel speed residual standard deviation of the wheel speed sensor residual data in the previous timing window at the target time is obtained.

[0057] In one embodiment, assuming that The residual data of the vehicle target wheel speed at a historical moment is ;No. The mean of the residual data in the previous time series window of the wheel speed sensor residual data at the target moment is ; The number of data points in the time series window of the wheel speed sensor residual data is , then the wheel speed sensor residual data is The calculation formula for the standard deviation of the short-term wheel speed residual in the time series window before the target moment is:

[0058]

[0059] in, Indicates the residual data of the wheel speed sensor at the The standard deviation of the short-term wheel speed residual in the time series window before the target moment; The number of data points in the time series window representing the wheel speed sensor residual data; Indicates the The residual data of the vehicle target wheel speed at each historical moment; Indicates the The mean of the residual data in the previous time series window of the wheel speed sensor residual data at the target moment.

[0060] Finally, obtain the baseline dynamic energy data and the baseline residual fluctuation data; use the ratio of the first vehicle dynamic energy index to the baseline dynamic energy data as the first adjustment factor; use the ratio of the short-term wheel speed residual standard deviation to the baseline residual fluctuation data as the second adjustment factor; and use the result of adding the constant 1, the first adjustment factor, and the second adjustment factor as the vehicle's dynamic response adaptive adjustment factor. The calculation formula of the dynamic response adaptive adjustment factor at each target moment is:

[0061]

[0062] in, Indicates that the vehicle is Dynamic response adaptive adjustment factor at each target moment; Indicates the The first vehicle dynamic energy index at a moment; Baseline dynamic energy data representing a normal dynamic energy level of the vehicle obtained through an offline calibration process of the vehicle; Indicates the residual data of the wheel speed sensor at the The standard deviation of the short-term wheel speed residual in the time series window before the target moment; The baseline residual fluctuation data represents the inherent fluctuation level of the residual data when the wheel speed sensor is operating normally, obtained through the vehicle's offline calibration process.

[0063] It should be noted that the dynamic response adaptive adjustment factor proposed in the present invention is intended to overcome the inherent defect of poor adaptability of traditional fixed thresholds under complex vehicle dynamics. First, the constant 1 in the dynamic response adaptive adjustment factor calculation formula is the basic value set for the adjustment factor, indicating that in the extreme case where the ideal vehicle is completely stationary and the sensor data has no fluctuations, the value of the vehicle's dynamic response adaptive adjustment factor approaches 1. At this time, the dynamic effective threshold will be mainly determined by the preset basic threshold, thereby ensuring that even under static conditions, the system still retains the basic detection capability for minor anomalies. Secondly, the second term in the dynamic response adaptive adjustment factor calculation formula is It is a compensation for the macroscopic dynamic driving intensity of the vehicle. During the driving process of the vehicle, its longitudinal acceleration and lateral acceleration are the key physical quantities that characterize its dynamic behavior. By calculating the root mean square of the sum of squares of these accelerations, the vehicle's When the vehicle performs high-dynamic maneuvers such as emergency acceleration or obstacle avoidance steering, will increase significantly, at this time through Divided by the baseline dynamic energy obtained by calibration through a large amount of healthy working condition data The relative ratio is obtained to reflect the multiple of the current vehicle dynamic energy compared to the common dynamic level, so that when the vehicle dynamic energy changes drastically, the value of the vehicle's dynamic response adaptive adjustment factor increases accordingly, and then the dynamic effective threshold is proportionally increased through the dynamic response adaptive adjustment factor, thereby solving the problem that the traditional fixed threshold cannot adapt to the dynamic changes of the vehicle and is prone to false alarms under high dynamic conditions. This allows fault detection to allow the residual data to have a larger normal fluctuation space when the vehicle performs reasonable high dynamic operations. Finally, the third term in the dynamic response adaptive adjustment factor calculation formula It is an adaptive adjustment for the fluctuation characteristics of the residual data of the wheel speed sensor. The standard deviation of the residual data after filtering in the short term is It directly reflects the current noise level of the residual data. This fluctuation may come from the electrical noise of the sensor itself, small irregularities in the gear ring induction process, or subtle vibrations caused by uneven road surface. Compare and evaluate the cleanliness of the current data. If the volatility of the current residual data increases, the ratio will also increase, thereby improving the vehicle's dynamic response adaptive adjustment factor to increase the dynamic effective threshold. When the quality of the residual data deteriorates or is subject to minor external interference, the system can appropriately relax the judgment criteria to avoid misjudging normal noise fluctuations as faults, thereby enhancing the ability to initially screen the vehicle's wheel speed residual data.

[0064] Step S3: Obtaining a vehicle's slight drift confirmation factor by performing a significance analysis on the consistency and amplitude of the wheel speed residual data under the vehicle's low dynamic interference state.

[0065] After obtaining the vehicle's dynamic response adaptive adjustment factor in step S2, the basic threshold of the vehicle wheel speed residual data can be dynamically adjusted using the vehicle's dynamic response adaptive adjustment factor. Specifically, the result of multiplying the vehicle's dynamic response adaptive adjustment factor by the basic threshold of the vehicle wheel speed residual data is used as the first dynamic threshold of the vehicle wheel speed residual data at the target moment. The obtained first dynamic threshold can effectively filter out most large residuals caused by normal vehicle dynamic behavior or significant signal noise. However, when the wheel speed sensor experiences a small, intermittent systematic deviation, the residual signal generated is often insufficient in amplitude to exceed the first dynamic threshold, resulting in the inability to identify the small, intermittent systematic deviation.

[0066] Traditional fault detection methods, whether using fixed thresholds or dynamically adjusted thresholds, primarily rely on whether the instantaneous amplitude of the residual data exceeds a certain limit. This is because the harm of such deviations is more reflected in their persistent deviation from normal random noise in a specific direction rather than in their large amplitude at a single moment. Therefore, this method has limited ability to detect small but persistent systematic deviations, or small deviations that occur intermittently but have a clear bias when they occur.

[0067] Therefore, the present invention performs preliminary residual data screening through the first dynamic threshold, and takes the vehicle wheel speed residual data lower than the first dynamic threshold as candidate residual data, thereby obtaining the vehicle's micro-drift confirmation factor by performing a significance analysis on the consistency and amplitude of the candidate residuals under the vehicle's low dynamic interference state.

[0068] First, the candidate residual data are evaluated for consistency to obtain the conditional cumulative consistency score; the long observation time window length for judging small drift is set; the vehicle wheel speed residual data is windowed by the long observation time window length to obtain the first window of the vehicle wheel speed residual data; the driving state is evaluated by the real-time driving speed, lateral acceleration and longitudinal acceleration of the vehicle to obtain the vehicle steady speed driving condition evaluation result. If the vehicle is in a steady speed driving state, the vehicle steady speed driving condition evaluation result is 1; if the vehicle is not in a steady speed driving state, the vehicle steady speed driving condition evaluation result is 0; the target time The candidate residual data that meets the vehicle steady speed driving condition evaluation result of the first window of the vehicle wheel speed residual data is 1 as the second candidate wheel speed residual data at the target moment; the absolute value of the sum of all the second candidate wheel speed residual data in the first window at the target moment is used as the cumulative deviation direction evaluation at the target moment; the sum calculation result of the absolute values ​​of all the second candidate wheel speed residual data in the first window at the target moment is used as the total fluctuation magnitude evaluation at the target moment; the ratio of the cumulative deviation direction evaluation at the target moment to the total fluctuation magnitude evaluation at the target moment is used as the conditional cumulative consistency score of the candidate residual data at the target moment.

[0069] Then, by performing amplitude change analysis on the candidate residual data, the relative degree score of the conditional amplitude of the candidate residual data exceeding the baseline noise is obtained, and the significance factor of the candidate residual is set; the result of multiplying the baseline noise standard deviation data by the significance factor is used as the significance standard deviation of the candidate residual; the mean of the absolute values ​​of the second candidate wheel speed residual data at the target moment is subtracted from the significance standard deviation and divided by the calculation result of the baseline noise standard deviation data as the first relative degree evaluation at the target moment; the larger value between the first relative degree evaluation at the target moment and the constant 0 is used as the relative degree score of the conditional amplitude of the candidate residual data exceeding the baseline noise.

[0070] Finally, the result of multiplying the conditional cumulative consistency score of the candidate residual data at the target moment by the relative degree score of the conditional amplitude of the candidate residual data exceeding the baseline noise is used as the vehicle's slight drift confirmation factor.

[0071] In one embodiment, assuming that The candidate residual data at time is ; The long observation time window used to judge small drift is ; The vehicle steady speed driving condition indicator function is ; In the long observation time window used to judge small drift, when the vehicle is in a steady-speed driving condition, the average of the absolute values ​​of all candidate residual data is ; The baseline noise standard deviation data of the residual data of the vehicle's health state under steady speed driving conditions is , then the vehicle is The calculation formula for the small drift confirmation factor at the moment is:

[0072]

[0073] in, Indicates that the vehicle is The small drift confirmation factor of the moment; Indicates the long observation time window used to judge small drifts; Represents the vehicle steady speed driving condition indicator function, which is used to judge the driving state of the vehicle. If the vehicle is in a predefined medium steady speed driving state, then ,otherwise ; It represents the average of the absolute values ​​of all candidate residual data in the long observation time window used to judge small drift when the vehicle is in a steady speed driving condition; Represents the significance factor. The present invention sets the significance factor , which is used to define how many times the average amplitude of the candidate residuals needs to exceed the baseline noise standard deviation to be considered a statistically significant deviation; Represents the baseline noise standard deviation data of the vehicle's health status residual data under steady speed conditions.

[0074] It should be noted that the core of the vehicle's micro-drift confirmation factor is to achieve accurate identification of the wheel speed sensor's micro-system deviation through a dual-criteria mechanism, thereby making up for the shortcomings of the traditional instantaneous amplitude judgment method. The first item in the vehicle's micro-drift confirmation factor is is the conditional cumulative consistency score, the numerator represents the absolute value of the algebraic sum of all candidate residuals when the vehicle is in a specific steady-speed driving condition within the long observation window, reflecting the intensity of the net deviation direction accumulated by these residual data, and the denominator represents the sum of the absolute values ​​of all candidate residuals under the same conditions, reflecting the total fluctuation magnitude of these residuals. The vehicle steady-speed driving condition indicator function is used to determine whether the vehicle is in a predefined medium steady-speed driving state at a historical moment. In this embodiment, when the real-time speed of the vehicle is between 30 km / h and 80 km / h, and the longitudinal acceleration and lateral acceleration of the vehicle are both less than The vehicle is judged to be in a medium steady speed driving state. The numerical range of the conditional cumulative consistency score is between 0 and 1. When all candidate residual data that meet the conditions have the same sign, that is, continuous positive or continuous negative deviation, the score approaches 1, indicating that the deviation has a high degree of unidirectional consistency; when the signs of the candidate residuals are randomly distributed, the score approaches 0. The main function of the conditional cumulative consistency score is to reveal at the statistical level whether the candidate residuals have continuous, unidirectional deviation characteristics under specific driving conditions. This part aims to distinguish between systematic small deviations with fixed bias and background noise with random direction, and provides a directional criterion for identifying potential fault signals. The second item in the vehicle's small drift confirmation factor The relative degree score of the conditional amplitude exceeding the baseline noise is used to further evaluate the actual abnormality of small deviations with unidirectional consistency. This design compares the average amplitude of the candidate residuals with pre-calibrated healthy baseline noise data under specific driving conditions and introduces a significance factor. This ensures that only when the deviation amplitude significantly exceeds the normal fluctuation range is it considered a statistically significant abnormality, thereby reducing the misjudgment of normal small noise by the sensor and improving detection accuracy. The vehicle's small drift confirmation factor multiplies the conditional cumulative consistency score with the assessment result of the relative degree score of the conditional amplitude exceeding the baseline noise, forming a collaborative judgment logic. Only when the candidate residual meets the two conditions of continuous unidirectional deviation and significant amplitude abnormality under specific driving conditions will the vehicle's small drift confirmation factor output a significant fault indication value.

[0075] Step S4 , performing a continuous fault judgment by combining the vehicle's dynamic response adjustment factor and the small drift confirmation factor, and obtaining a fault judgment result of a small systematic deviation of the wheel speed sensor.

[0076] After calculating the vehicle's dynamic response adaptive adjustment factor in step S2 and obtaining the first dynamic threshold based on it, and calculating the vehicle's slight drift confirmation factor in step S3, in this step, a final judgment is made on whether the target sensor has a slight systematic deviation fault based on the above calculation results.

[0077] The first dynamic threshold, derived from the vehicle's dynamic response adaptive adjustment factor, is primarily used to preliminarily screen residual data to adapt to the vehicle's real-time dynamic operating conditions and identify candidate residual data requiring further analysis using the vehicle's micro-drift confirmation factor. The core fault of concern in this invention, namely, the micro-systematic deviation of the wheel speed sensor, is ultimately identified and confirmed based on the estimated value of the vehicle's micro-systematic deviation. To ensure the accuracy of fault determination and avoid misjudgments caused by transient disturbances or single peaks in the output sequence of the vehicle's micro-drift confirmation factor, this embodiment introduces continuous confirmation logic when performing threshold comparisons on the vehicle's micro-drift confirmation factor value. Specifically, a fault determination threshold, Threshold, is set. In this embodiment, it is set to 0.7. This threshold can be adjusted based on actual scenarios and is not a requirement. A fault confirmation duration period, M, is set. In this embodiment, the value of M is set to 1000. The vehicle's micro-drift confirmation factor value is calculated and updated in real time based on the system data sampling period. A fault confirmation counter is set within the vehicle. During each calculation cycle, if the vehicle's minor drift confirmation factor exceeds the fault judgment threshold, the internal fault confirmation counter increments. If the minor drift confirmation factor does not exceed the fault judgment threshold, the internal fault confirmation counter resets to 0. When the accumulated value of the fault confirmation counter reaches a number of continuous cycles, M, the system determines that a minor systematic deviation fault has occurred in the target wheel speed sensor. For example, if M equals 1000, the vehicle's minor drift confirmation factor must remain above the fault judgment threshold for 10 seconds for the fault to be confirmed.

[0078] Step S5: Active maintenance response of the wheel speed sensor is performed by performing signal reporting and status storage processing on the fault determination result.

[0079] After the determination of whether the target wheel speed sensor has a minor systematic deviation fault is completed in step S4, this step performs corresponding fault information processing and response according to the determination result.

[0080] If the determination indicates a minor systematic deviation fault in the target wheel speed sensor, the system generates and records a diagnostic trouble code (DTC) indicating this specific early-stage fault. This fault information is transmitted to the vehicle's central diagnostic management module via the vehicle's onboard communication network, triggering the illumination of a corresponding warning indicator on the instrument panel to alert the driver of a potential performance degradation risk in the vehicle's electronic braking system. The DTC, along with relevant contextual information such as the time of fault occurrence and vehicle operating status, is stored in the vehicle's non-volatile fault memory. This stored information provides crucial support for subsequent vehicle repair and maintenance, enabling technicians to accurately locate the potentially problematic wheel speed sensor and conduct targeted inspection, cleaning, calibration, tightening, or replacement. This enables proactive intervention and predictive maintenance for early sensor performance degradation, effectively preventing further development and escalation of the fault.

[0081] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A real-time fault detection method for a vehicle electronic brake system, characterized in that: The real-time fault detection method for a vehicle electronic brake system comprises the following steps: Step S1: collecting vehicle driving status data through the on-board sensor network and the electronic control unit, calculating the filtered residual data of the target wheel speed sensor, and obtaining the calibration reference parameters of the health state; Step S2: obtaining a dynamic response adaptive adjustment factor of the vehicle by jointly analyzing the vehicle dynamic energy and residual signal volatility on the vehicle acceleration data and the residual fluctuation data; Step S3: Obtaining the vehicle's slight drift confirmation factor by performing a significance analysis on the consistency and amplitude of the wheel speed residual data under the vehicle's low dynamic disturbance state; Step S4: performing a continuous fault judgment by combining the vehicle's dynamic response adjustment factor and the small drift confirmation factor to obtain a fault judgment result of a small systematic deviation of the wheel speed sensor; Step S5: Active maintenance response of the wheel speed sensor is performed by signal reporting and state storage processing of the fault determination result; The method of obtaining a vehicle dynamic response adaptive adjustment factor by jointly analyzing vehicle dynamic energy and residual signal fluctuations on vehicle acceleration data and residual fluctuation data includes: obtaining a first vehicle dynamic energy index at a target moment by performing vehicle dynamic energy analysis on the vehicle longitudinal acceleration and lateral acceleration; setting a time series window for wheel speed sensor residual data to obtain a short-term wheel speed residual standard deviation of the wheel speed sensor residual data in a time series window preceding the target moment; and obtaining a vehicle dynamic response adaptive adjustment factor by performing a fusion evaluation of dynamic driving intensity and wheel speed residual fluctuation level on the first vehicle dynamic energy index and the short-term wheel speed residual standard deviation. The method obtains the vehicle's micro-drift confirmation factor by performing a significance analysis on the consistency and amplitude of the wheel speed residual data under the vehicle's low dynamic interference state, including: setting a basic threshold of the vehicle wheel speed residual data, weightedly optimizing the basic threshold through the vehicle's dynamic response adaptive adjustment factor, and obtaining a first dynamic threshold of the vehicle wheel speed residual data; performing preliminary screening of the vehicle wheel speed residual data through the first dynamic threshold of the vehicle wheel speed residual data to obtain candidate residual data of the vehicle wheel speed; obtaining a conditional cumulative consistency score by performing a consistency evaluation on the candidate residual data; obtaining a relative degree score of the conditional amplitude of the candidate residual data exceeding the baseline noise by performing an amplitude change analysis on the candidate residual data; and obtaining the vehicle's micro-drift confirmation factor by performing a comprehensive evaluation of the conditional cumulative consistency score and the relative degree score of the conditional amplitude of the candidate residual data exceeding the baseline noise.

2. The real-time fault detection method for a vehicle electronic brake system according to claim 1, characterized in that: The vehicle driving state data is collected through the vehicle sensor network and the electronic control unit, the filtered residual data of the target wheel speed sensor is calculated, and the calibration reference parameters of the health state are established, including: Set a data sampling period to collect vehicle driving status data through the on-board sensor network and electronic control unit. The collected data includes: vehicle longitudinal acceleration, vehicle lateral acceleration, vehicle reference speed, and raw wheel speed data output by the vehicle target wheel speed sensor; Obtaining a desired wheel speed of a vehicle target wheel speed sensor by using a vehicle reference speed and a dynamic tire radius of a target wheel; using a difference between the original wheel speed data and the desired wheel speed as vehicle target wheel speed original residual data; and filtering the vehicle target wheel speed original residual data by using a second-order Butterworth low-pass filter to obtain vehicle target wheel speed residual data; Through the vehicle's offline calibration process, baseline dynamic energy data of the vehicle's normal dynamic energy level, baseline residual fluctuation data of the residual signal's inherent fluctuation level when the wheel speed sensor is working normally, and baseline noise standard deviation data of the healthy state residual data under steady-speed driving conditions are obtained; the baseline dynamic energy data, the baseline residual fluctuation data, and the baseline noise standard deviation data are stored as baseline parameters in the vehicle's electronic control unit.

3. The real-time fault detection method for a vehicle electronic brake system according to claim 1, characterized in that: The obtaining of a first vehicle dynamic energy index at a target moment by performing vehicle dynamic energy analysis on the vehicle longitudinal acceleration and lateral acceleration includes: The method includes setting a sliding time window length for dynamic energy analysis; obtaining the sum of the squares of the vehicle's lateral acceleration and longitudinal acceleration for each timestamp in the sliding time window for dynamic energy analysis; and calculating the result of raising the square of the mean of the sum of the squares of the accelerations corresponding to all timestamps in the sliding time window to the power of one-half as the first vehicle dynamic energy indicator at the target moment.

4. The real-time fault detection method for a vehicle electronic brake system according to claim 1, characterized in that: The step of obtaining the vehicle's dynamic response adaptive adjustment factor by performing a fusion evaluation of the dynamic driving intensity and the wheel speed residual fluctuation level on the first vehicle dynamic energy index and the short-term wheel speed residual standard deviation includes: Obtain baseline dynamic energy data and baseline residual fluctuation data; use the ratio of the first vehicle dynamic energy index to the baseline dynamic energy data as a first adjustment factor; use the ratio of the short-term wheel speed residual standard deviation to the baseline residual fluctuation data as a second adjustment factor; and use the result of adding a constant 1, the first adjustment factor, and the second adjustment factor as the vehicle's dynamic response adaptive adjustment factor.

5. The real-time fault detection method for a vehicle electronic brake system according to claim 2, characterized in that: The method of performing consistency evaluation on the candidate residual data to obtain a conditional cumulative consistency score of the candidate residual data; and performing amplitude change analysis on the candidate residual data to obtain a relative degree score of the conditional amplitude of the candidate residual data exceeding the baseline noise includes: The length of a long observation time window for determining minor drift is set; the vehicle wheel speed residual data is windowed using the long observation time window length to obtain the first window of the vehicle wheel speed residual data; the driving state is evaluated using the vehicle's real-time driving speed, lateral acceleration, and longitudinal acceleration to obtain a vehicle steady speed condition evaluation result. If the vehicle is in a steady speed state, the vehicle steady speed condition evaluation result is 1; if the vehicle is not in a steady speed state, the vehicle steady speed condition evaluation result is 0; The candidate residual data satisfying the vehicle steady speed driving condition evaluation result of 1 in the first window of the vehicle wheel speed residual data at the target moment is used as the second candidate wheel speed residual data at the target moment; the absolute value of the sum of all the second candidate wheel speed residual data in the first window at the target moment is used as the cumulative deviation direction evaluation at the target moment; the sum of the absolute values ​​of all the second candidate wheel speed residual data in the first window at the target moment is used as the total fluctuation magnitude evaluation at the target moment; the ratio of the cumulative deviation direction evaluation at the target moment to the total fluctuation magnitude evaluation at the target moment is used as the conditional cumulative consistency score of the candidate residual data at the target moment; A significance factor is set for the candidate residual; the result of multiplying the baseline noise standard deviation data by the significance factor is used as the significance standard deviation of the candidate residual; the mean of the absolute values ​​of the second candidate wheel speed residual data at the target moment is subtracted from the significance standard deviation and divided by the baseline noise standard deviation data as the first relative degree evaluation at the target moment; the larger value between the first relative degree evaluation at the target moment and the constant 0 is used as the relative degree score of the conditional amplitude of the candidate residual data exceeding the baseline noise.

6. The real-time fault detection method for a vehicle electronic brake system according to claim 1, characterized in that: The method of comprehensively evaluating the cumulative consistency score of the condition and the relative degree to which the conditional amplitude of the candidate residual data exceeds the baseline noise to obtain the vehicle's slight drift confirmation factor includes: The result of multiplying the conditional cumulative consistency score of the candidate residual data at the target moment by the relative degree score of the conditional amplitude of the candidate residual data exceeding the baseline noise is used as the vehicle's small drift confirmation factor.

7. The real-time fault detection method for a vehicle electronic brake system according to claim 1, characterized in that: The method of performing continuous fault judgment by combining the vehicle's dynamic response adjustment factor and the small drift confirmation factor to obtain a fault judgment result of a small systematic deviation of the wheel speed sensor includes: A fault judgment threshold and a fault confirmation duration period length are set, and a fault confirmation counter is initialized. During a data sampling period, if the vehicle's slight drift confirmation factor is greater than the fault judgment threshold, the fault confirmation counter is incremented; if the vehicle's slight drift confirmation factor is less than or equal to the fault judgment threshold, the fault confirmation counter is reset to 0; when the accumulated value of the fault confirmation counter reaches the duration period length, it is determined that a slight systematic deviation fault has occurred in the target wheel speed sensor.

Images