AMT gearbox diagnosis method and system thereof

Abstract

The application relates to an AMT gearbox diagnosis method and system, which comprises the following steps: acquiring operation data of a vehicle, wherein the operation data comprises a gear shift displacement signal, a gear signal and a vehicle driving state signal; according to the gear signal and the vehicle driving state signal, target data meeting a preset stable working condition are screened out from the operation data; based on the gear signal and the gear shift displacement signal in the target data, a characteristic value of the gear shift displacement is calculated; and according to the change condition of the characteristic value, a diagnosis result of the AMT gearbox is determined. According to the application, the diagnosis result is determined according to the change condition of the characteristic value, the diagnosis basis is changed from a single fault threshold to a displacement trend change, data basis for identifying abnormal signs before a displacement deviation accumulates to trigger a fault code is provided, the early abnormal signal capturing capability in the operation data is improved, potential risks can be found through trend changes before the fault code appears, and the early warning capability of the AMT gearbox displacement fault is improved.

Description

Technical Field

[0001] This application relates to the field of transmissions, specifically to a diagnostic method and system for an AMT transmission. Background Technology

[0002] AMT (Automated Manual Transmission) is widely used in commercial vehicles and some passenger cars due to its advantages such as high transmission efficiency and relatively low cost. The shifting action of an AMT transmission mainly relies on an actuator driving the shift fork shaft to move, thereby achieving gear engagement and disengagement. During this process, a shift displacement sensor is used to monitor the position of the shift fork shaft in real time and feeds the signal back to the transmission controller (TCU), making it a key component ensuring shifting accuracy and smoothness.

[0003] During actual operation, due to mechanical wear, electrical interference, and environmental factors, some vehicles' AMT transmissions may experience abnormal shift position signals or gear position recognition deviations. Typical symptoms include shift position sensor signals exceeding the preset range, neutral jamming during shifting, and discrepancies between the displayed gear and the actual gear. If these faults are not addressed promptly, they may lead to the vehicle being unable to engage gears or experiencing power interruption while driving, severely impacting vehicle availability and driving safety.

[0004] In existing technologies, the diagnosis and maintenance of such faults mainly rely on on-site handling after the vehicle malfunctions. Typical repair procedures include reading fault codes (DTCs) and self-learning values ​​from the transmission control unit using a diagnostic tool, disassembling and inspecting the actuators based on repair experience, and in severe cases, even replacing the entire transmission assembly. This reactive repair approach has a significant lag; often, by the time the fault codes are triggered, mechanical components have already suffered severe wear or damage, increasing repair costs and reducing vehicle uptime. Summary of the Invention

[0005] This application provides an AMT transmission diagnostic method and system, which can solve the problem of delayed fault diagnosis of AMT transmissions in the prior art and the inability to achieve early anomaly identification based on operating data.

[0006] In a first aspect, embodiments of this application provide an AMT transmission diagnostic method, which includes: Acquire vehicle operating data, including shift displacement signal, gear signal, and vehicle driving status signal; Based on the gear position signal and the vehicle driving status signal, target data that meets the preset stable operating conditions is selected from the operating data; Based on the gear position signal and shift displacement signal in the target data, calculate the characteristic value of the shift displacement; The diagnostic results for the AMT transmission are determined based on the changes in the aforementioned characteristic values.

[0007] In conjunction with the first aspect, in one implementation method, satisfying the preset stable operating conditions includes: Vehicle speed is greater than zero; The actual gear position matches the target gear position. The error between the instrument's cumulative mileage and the mileage calculated based on vehicle speed integral is less than a preset error threshold.

[0008] In conjunction with the first aspect, in one implementation, based on the gear position signal and shift displacement signal in the target data, the characteristic value of the shift displacement is calculated, specifically including: Based on the gear position signal in the target data, the target data is divided into data subsets corresponding to different gear positions; For each subset of data, the shift displacement signal is extracted to construct a displacement sample sequence for the same gear. Statistical analysis was performed on the displacement sample sequence of the same gear to obtain the characteristic value of the shift displacement.

[0009] In conjunction with the first aspect, in one implementation, statistical analysis is performed on the same gear shift displacement sample sequence to obtain the characteristic values ​​of the shift displacement, specifically including: Within a preset time window or mileage window, calculate the rolling median of the displacement sample sequence of the same gear. The rolling median is determined as the center value of the stable displacement and used as the characteristic value of the shift displacement.

[0010] In conjunction with the first aspect, in one implementation, statistical analysis is performed on the same gear shift displacement sample sequence to obtain the characteristic values ​​of the shift displacement, specifically including: Within a preset time window or mileage window, calculate the mode of displacement of the displacement sample sequence of the same gear. The mode of the displacement is determined as the center value of the stable displacement and used as the characteristic value of the shift displacement.

[0011] In conjunction with the first aspect, in one implementation, determining the diagnostic result of the AMT transmission based on the changes in the characteristic values ​​specifically includes: The proportion of the mode of displacement within the preset time window or mileage window to the total number of samples in the window is calculated to obtain the window mode proportion. When the change in the mode of displacement exceeds a preset change threshold, the proportion of the mode of the window is lower than a preset proportion threshold, and the continuous mileage after the jump exceeds a preset mileage threshold, a feature value change point is determined to have occurred. The diagnostic results of the AMT transmission are determined based on the stable displacement center values ​​before and after the point of change of the characteristic value.

[0012] In conjunction with the first aspect, in one implementation, the diagnostic result of the AMT transmission is determined based on the stable displacement center values ​​before and after the point of change of the characteristic value, specifically including: Calculate the change in the stable displacement center value after the point of change of the characteristic value relative to the stable displacement center value before the change; If the change is greater than or equal to a preset positive change threshold, the diagnostic result of the AMT transmission is determined to be mechanical slider wear. If the change is less than or equal to a preset negative change threshold, the diagnostic result of the AMT transmission is determined to be displacement sensor drift.

[0013] In conjunction with the first aspect, in one implementation, the method further includes a re-identification step: Obtain the number of gear shifts of the main gearbox from the operating data; When the decrease in the number of gear shifts of the AMT transmission exceeds the preset backoff threshold, a count reset event is determined to have occurred. Based on the running data after the count reset event, the steps of calculating the characteristic value of the shift displacement and determining the diagnostic result are re-executed.

[0014] In conjunction with the first aspect, in one embodiment, after determining the diagnostic results of the AMT transmission, the method further includes: Generate a diagnostic report, which includes at least the vehicle number, fault type, first abnormal mileage, risk level, and recommended remedial measures.

[0015] Secondly, embodiments of this application provide an AMT transmission diagnostic system, comprising: a data acquisition module, a data filtering module, a feature calculation module, and a diagnostic determination module. The data acquisition module is used to acquire vehicle operating data, which includes at least shift displacement signals, gear signals, and vehicle driving status signals. The data filtering module is used to filter target data that meets preset stable operating conditions from the operating data based on the gear signals and the vehicle driving status signals. The feature calculation module is used to calculate feature values ​​of the shift displacement based on the gear signals and shift displacement signals in the target data. The diagnostic determination module is used to determine the diagnostic result of the AMT transmission based on the changes in the feature values.

[0016] The beneficial effects of the technical solutions provided in this application include: This application provides an AMT transmission diagnostic method and system. It filters target data that meets preset stable operating conditions based on gear position signals and vehicle driving status signals, eliminating signal fluctuation interference during gear shifting and unstable states, making the displacement data used for analysis more representative. Calculating characteristic values ​​of shift displacement based on the target data to characterize the position center reflects the statistical regularity of displacement rather than instantaneous states, thus enabling the capture of minute displacement deviation trends. Determining the diagnostic result based on changes in these characteristic values ​​shifts the diagnostic basis from a single fault threshold to changes in displacement trends. This provides a data foundation for identifying abnormal signs before displacement deviations accumulate to trigger fault codes, improving the ability to capture early abnormal signals in operating data. It allows for the detection of potential risks through trend changes before fault codes appear, enhancing the early warning capability for displacement-related faults in AMT transmissions. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the diagnostic method for the AMT transmission in this application; Figure 2 This is a schematic diagram of sensor drift. Figure 3 This is a schematic diagram of sensor drift. Figure 4 A diagram illustrating the diagnosis of the window's mode and its percentage. Figure 5 This is a schematic diagram of wear trend fitting and derivative detection; Figure 6 This is a diagram illustrating the batch statistics of vehicles. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0019] This application provides an AMT transmission diagnostic method and system, which can solve the problem of delayed fault diagnosis of AMT transmissions in the prior art and the inability to achieve early anomaly identification based on operating data.

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0021] In a first aspect, embodiments of this application provide an AMT transmission diagnostic method, which includes: 101: Acquire vehicle operating data, including shift displacement signal, gear signal, and vehicle driving status signal; 102: Based on the gear position signal and vehicle driving status signal, select target data that meets the preset stable operating conditions from the operating data; 103: Calculate the characteristic value of the shift displacement based on the gear position signal and shift displacement signal in the target data; 104: Determine the diagnostic results of the AMT transmission based on the changes in characteristic values.

[0022] In the specific implementation process, step 101 is executed first: acquiring vehicle operating data, including shift displacement signals, gear signals, and vehicle driving status signals. This data is typically collected by the onboard terminal and uploaded to the cloud platform. The gear signal encompasses the actual gear and the target gear; the vehicle driving status signal includes vehicle speed and cumulative mileage; and the shift displacement signal reflects the specific position information of the shift mechanism, providing basic data support for subsequent diagnostics. When acquiring vehicle operating data, the vehicle number, time, vehicle speed, actual gear (gear), target gear (selectgearda12), shift displacement (tdisplacementda12), number of gear shifts in the main gearbox, and cumulative mileage are read from the vehicle network platform. This process is completed through the communication link between the onboard terminal and the cloud, ensuring that the data timestamps are continuous and complete, forming a basic dataset for analysis. Specifically, the actual gear (gear) and the target gear (selectgearda12) constitute the gear signal, the shift displacement (tdisplacementda12) corresponds to the shift displacement signal, and vehicle speed and cumulative mileage belong to the vehicle driving status signals. The main gear shift count auxiliary identification system resets its status, and all fields work together to support subsequent diagnostic logic, ensuring that the data dimensions cover the key characteristics of gearbox operation.

[0023] By integrating the aforementioned multi-source data, a foundational input is provided for subsequent screening of stable operating conditions and calculation of feature values, ensuring that the diagnostic model accurately reflects the actual mechanical state of the AMT transmission. Data reading is based on a preset time period or event-triggered mechanism to ensure that the operating data covers the vehicle's state information under different operating conditions, avoiding diagnostic biases caused by a single data source.

[0024] Next, step 102 is executed: Based on the gear position signal and the vehicle driving status signal, target data that meets the preset stable operating conditions is filtered from the operating data; the preset stable operating conditions are specifically defined as the time period when the vehicle speed is greater than zero and the actual gear position is consistent with the target gear position. This filtering logic eliminates the fluctuating data generated during the gear shift transition, ensuring that subsequent analysis is based only on stable gear positions and avoiding transient interference from affecting diagnostic accuracy.

[0025] Then, step 103 is executed: based on the gear position signal and shift displacement signal in the target data, the characteristic value of the shift displacement is calculated; the characteristic value is calculated using the sliding window statistical method, including calculating the mode within the window to characterize the stable position center, and calculating the mode ratio to judge the stability of the center. At the same time, the rolling median is combined to suppress data noise, thereby extracting key statistics that can reflect changes in mechanical state.

[0026] Finally, step 104 is executed: Based on the changes in the characteristic values, the diagnostic results of the AMT transmission are determined; by monitoring the direction of the jump of the mode in the characteristic values ​​and the continuous mileage, if the displacement center increases and the continuous mileage meets the threshold, it is determined to be slider wear; if the displacement center decreases, it is determined to be sensor drift; if the continuous mileage is insufficient, it is marked as a risk state and included in the tracking, thereby realizing the differentiation and early warning of different fault types.

[0027] During data processing, the initial input fields for the operational data are defined, including `gpsdate`, `speed`, `gear`, and `selectgearda12`. These fields are used to determine the time sequence, effective driving state, and consistency between the actual and target gears. `gpsdate` provides a time-series reference, ensuring the continuity and traceability of data packets and supporting the reassembly of operational data by time sequence, thus resolving potential out-of-order issues in vehicle network data. `speed` and `gear` work together to filter vehicle operation segments, eliminating invalid signals from stationary states and ensuring the analysis is based on the dynamic driving process, avoiding interference from idling conditions on displacement signals. The comparison between `selectgearda12` and `gear` ensures proper gear engagement, forming valid operating condition samples. This avoids diagnostic biases caused by data fluctuations during gear shift transitions, providing a clean data foundation for subsequent feature calculations, meeting the prerequisite for stable operating condition screening, and ensuring that the operational data accurately reflects the gearbox engagement state.

[0028] Secondly, the raw input `tdisplacementda12`, as the core observation of the shift displacement sensor, directly reflects the physical position of the shift mechanism. Its numerical change corresponds to the actual displacement of the mechanical structure, serving as a direct basis for diagnosing slider wear and sensor drift. The raw inputs `mainbox3shifttimesda12` and other mainbox shift counts identify maintenance or count resets and are used to correlate wear levels. By monitoring the non-natural regression of this value, the system reset status is determined, preventing the misjudgment of a post-maintenance count as a sudden fault, ensuring the diagnostic logic is correctly initialized after maintenance events. The raw input `totalmileage` transforms the diagnosis from a time axis to a mileage axis, determining the persistence of abnormalities and ensuring fault determination is based on actual driving distance rather than simple time accumulation. This aligns with the physical law of a strong correlation between mechanical wear and mileage, improving the reliability of diagnostic results and the accuracy of maintenance recommendations, and supporting the mileage dimension calculation of feature values.

[0029] In the feature extraction stage, statistical features are constructed, including the rolling median, window mode, and window mode percentage. These features aim to suppress noise and determine whether the displacement center has stably migrated. Together, they constitute the characteristic value of the shift displacement. The rolling median eliminates spike interference, smooths short-term fluctuations, and adapts to the discrete characteristics of vehicle network data. The window mode locates stable positions, reflects the central tendency after sensor quantification, and characterizes the stable center of the mechanical structure. The window mode percentage quantifies the distribution concentration. All three factors jointly support the logic for determining state stability. When the percentage is below a threshold, it indicates that the center is migrating, thus distinguishing between normal fluctuations and abnormal jumps, enhancing the algorithm's adaptability to noisy environments, ensuring the robustness of feature value calculation, and providing a quantitative basis for diagnostic results.

[0030] Furthermore, trend features are generated, encompassing morphological closing operation curves, spline trends, and trend derivatives, to identify long-term wear trends, wear initiation points, and abrupt wear points, enriching the dimensions of feature values. Morphological closing operations smooth local pits, eliminating the influence of isolated outliers on trend lines and restoring the overall shape of the wear curve. Spline trends fit long-term trajectories, reconstructing the continuous process of wear development and supporting the quantification of wear rates. Trend derivatives capture slope changes, thereby achieving a refined description of the wear development process and accurate location of key nodes, supporting quantitative analysis of wear initiation points and abrupt wear points, providing accurate time and mileage references for predictive maintenance, and perfecting the complete technical chain from data acquisition to trend determination, ensuring that diagnostic methods can cover the entire lifecycle from transient anomalies to long-term wear.

[0031] This application filters target data that meets preset stable operating conditions based on gear position signals and vehicle driving status signals, eliminating signal fluctuation interference during gear shifting and unstable states, making the displacement data used for analysis more representative. Calculating characteristic values ​​of shifting displacement based on the target data to characterize the position center reflects the statistical regularity of displacement rather than instantaneous states, thus enabling the capture of minute displacement deviation trends. Determining diagnostic results based on changes in characteristic values ​​shifts the diagnostic basis from a single fault threshold to changes in displacement trends. This provides a data foundation for identifying abnormal signs before displacement deviations accumulate to trigger fault codes, improving the ability to capture early abnormal signals in operating data. It allows for the detection of potential risks through trend changes before fault codes appear, enhancing the early warning capability for displacement-related faults in AMT transmissions.

[0032] Based on the above embodiments, in this embodiment, target data that meets preset stable operating conditions is selected from the operating data according to the gear position signal and the vehicle driving status signal. The preset stable operating conditions include: vehicle speed is greater than zero; the actual gear position is consistent with the target gear position; and the error between the instrument's cumulative mileage and the mileage calculated based on the vehicle speed integral is less than a preset error threshold.

[0033] The above conditions are set based on CAN bus data collected by the vehicle terminal. The vehicle driving status signal represents the vehicle's motion trajectory, and the gear signal represents the gearbox engagement status. The timestamps of each signal are synchronized to ensure accurate logical judgment and form a complete data record, providing a basis for subsequent diagnosis.

[0034] Specifically, data where the vehicle speed is greater than 0 and the actual gear matches the target gear (gear-selectgearda12=0) is retained, while data from gear shifting over-shifts, incorrect gear engagements, and failure to achieve the target gear are discarded. During gear shifting, the shift fork and slider are in motion, and the displacement signal changes drastically over time; including these changes in the analysis would distort the feature value calculation. By determining if the gear signal is consistent, it is ensured that the vehicle is in a stable driving phase after gear engagement. At this point, the shift displacement signal is only affected by mechanical wear or sensor zero-point, facilitating subsequent fault type identification. This method of extracting data in a gear-specific and steady-state manner avoids interference from natural displacement differences between different gears and solves the problem of misjudgment caused by fixed thresholds, ensuring that feature value calculations only consider the changing trend of the same mechanical structure under the same stable state.

[0035] Simultaneously, mileage is calculated by integrating the vehicle speed from the instrument panel. Comparing this to the instrument panel mileage, an error of less than 10% is considered valid data. Vehicle-to-everything (V2X) transmission links may experience packet loss or timing discrepancies, leading to non-physical jumps in accumulated mileage. Integrating the vehicle speed signal over time yields the theoretical driving distance, which is then cross-validated with the accumulated mileage reported by the instrument panel. This process identifies and eliminates samples with poor data quality. Only when the deviation between the two is within a preset error threshold is the time series of the operational data considered complete and the sensor readings reliable, providing a high-confidence data foundation for subsequent diagnostics. This cleaning process eliminates discrete points caused by communication noise or sudden changes in operating conditions, ensuring accurate convergence of the sliding window mode and proportion in subsequent calculations. This supports precise differentiation between slider wear and sensor drift.

[0036] Based on the above embodiments, in this embodiment, the characteristic value of the shift displacement is calculated based on the gear position signal and shift displacement signal in the target data, specifically including: Based on the gear position signals in the target data, the target data is divided into data subsets corresponding to different gears. For each data subset, the shift displacement signal is extracted to construct a shift displacement sample sequence for the same gear. Statistical analysis is then performed on the shift displacement sample sequence to obtain the feature values ​​of the shift displacement. This process first extracts displacement samples of the mechanism in fixed gears or neutral positions, such as 12th gear displacement samples, neutral gear displacement samples, and 10th gear displacement samples, to avoid misjudgments caused by the positional differences between different gears. Since the physical positions of the shift forks corresponding to different gears inside the AMT transmission naturally differ, mixing calculations would lead to a chaotic benchmark. Therefore, the operating data is isolated into independent data subsets using gear position signals to ensure that the shift displacement signal in each subset only reflects the mechanical state under that specific gear. Constructing the shift displacement sample sequence for the same gear aims to reorganize discrete time-series data into statistical samples classified by gear, providing a homogeneous data foundation for subsequent feature value calculations and eliminating interference from non-faulty displacement abrupt changes caused by gear switching.

[0037] In some possible embodiments, statistical analysis is performed on the displacement sample sequence of the same gear to obtain the characteristic value of the shift displacement. Specifically, this includes: calculating the rolling median of the displacement sample sequence of the same gear within a preset time window or mileage window; and determining the rolling median as the stable displacement center value, which is then used as the characteristic value of the shift displacement. In specific implementation, the rolling median is calculated for the displacement sequence of the same gear, and the window can take several sampling points to suppress instantaneous noise interference. The rolling median eliminates the influence of outliers by sorting and taking the median value, which is suitable for environments with high noise levels and ensures that the calculated stable displacement center value can truly reflect the mechanical geometric center under the current gear. This method prevents the characteristic value from deviating from the actual physical position due to short-term fluctuations in the sensor. By continuously monitoring the dynamic changes of the displacement center through a sliding window, it provides smoothed benchmark data for subsequent judgment of whether abrupt changes have occurred.

[0038] In other possible embodiments, statistical analysis is performed on the displacement sample sequence of the same gear to obtain the characteristic value of the shift displacement. Specifically, this includes: calculating the mode of the displacement sample sequence of the same gear within a preset time window or mileage window; determining the mode of displacement as the stable displacement center value, and using it as the characteristic value of the shift displacement. In specific implementation, a sliding window is set to contain several sampling points. The frequency of each displacement value is counted within the window range, and the displacement value with the highest frequency is determined as the mode of displacement. The mode is used to characterize the stable position center after sensor quantization. Since sensor signals have quantization errors, the mode can reflect the most frequent mechanical position state and is more resistant to outlier interference than the mean. It is suitable for scenarios with concentrated data distribution, ensuring that the characteristic value reflects the true mechanical center. The window size is set according to the sampling frequency to ensure coverage of sufficient driving cycles, thereby smoothing the impact of short-term fluctuations on the center value calculation.

[0039] In this embodiment, the diagnostic result of the AMT transmission is determined based on the changes in characteristic values, specifically including: First, we calculate the proportion of the mode of displacement within a preset time window or mileage window to the total number of samples in the window, and obtain the mode proportion of the window. Then, when the change in the mode of displacement exceeds the preset change threshold, the proportion of the mode in the window is lower than the preset proportion threshold, and the continuous mileage after the jump exceeds the preset mileage threshold, the feature value change point is determined. Finally, the diagnostic results of the AMT transmission are determined based on the stable displacement center values ​​before and after the characteristic value change point.

[0040] This step specifically calculates the proportion of the most frequent displacement value within the window to the total number of samples in the window, obtaining the window mode proportion P_mode, calculated using the following formula: P_mode=max(freq(v)) / N, v∈W; Where W is the set of displacement value samples in the current window, v is a certain displacement value in the window, freq(v) is the frequency of the displacement value in the window, and N is the total number of samples in the window.

[0041] When the proportion of the mode is lower than the set threshold θ, it indicates that the displacement center is migrating or there is abnormal dispersion. That is, if P_mode ≥ θ, it is judged as stable; if P_mode < θ, it is judged as center migration or abnormal dispersion. Furthermore, when the window mode jumps, the proportion of the window mode is lower than the threshold, and the mileage after the jump meets the confirmation condition, this point is considered a candidate fault change point. Only when the change in displacement mode, the proportion of the window mode, and the continuous mileage simultaneously meet the preset conditions is a characteristic value change point determined. This constitutes a multi-confirmation mechanism to avoid misjudgments caused by fluctuations in a single indicator. Based on the stable displacement center values ​​before and after the characteristic value change point, the direction and magnitude of the change are compared to determine the diagnostic result of the AMT transmission. For example, it distinguishes whether the increased displacement is caused by mechanical wear or the decreased displacement is caused by sensor drift. By combining the continuous mileage verification of the change point, it ensures that the diagnostic result is based on long-term trends rather than transient interference, thereby improving the accuracy and robustness of fault identification.

[0042] Based on the above embodiments, in this embodiment, the diagnostic result of the AMT transmission is determined according to the stable displacement center value before and after the feature value change point, specifically including: Calculating the change in the stable displacement center value after the characteristic value change point relative to the stable displacement center value before the change: This step quantifies the degree of positional offset before and after the fault, eliminating the influence of initial installation errors or individual differences, and focusing on the relative change trend during operation. Therefore, comparing the stable displacement center values ​​before and after the change point, and using the difference calculation to clarify the evolution direction of the displacement signal, provides a data foundation for subsequently distinguishing between mechanical and electrical faults. This ensures that the diagnostic logic is based on objective numerical changes rather than absolute position, thereby constructing a data-driven fault judgment model and avoiding misjudgments caused by data fluctuations at a single moment.

[0043] If the change is greater than or equal to the preset positive change threshold, the diagnostic result for the AMT transmission is determined to be mechanical slider wear: when the slider is worn, the gap between the slider and the sleeve increases, requiring a greater distance to move compared to the normal state, resulting in greater displacement. If the displacement center increases (≥0.25) when the mileage exceeds the confirmation threshold, it is determined to be slider wear. The preset positive change threshold is used to define the boundary between normal mechanical clearance fluctuations and substantial wear, ensuring that a wear alarm is triggered only when the increase in displacement reaches a certain level and continues for a certain mileage. Positive change corresponds to a decrease in the physical size of the actuator or an increase in clearance, manifested as a cumulative increase in the displacement required to reach the same gear, avoiding misjudging brief shift shocks as mechanical wear, improving the accuracy of wear identification, and ensuring that maintenance recommendations are based on actual mechanical wear, guiding the replacement of worn parts.

[0044] If the change is less than or equal to the preset negative change threshold, the diagnostic result for the AMT transmission is determined to be displacement sensor drift: when iron filings cover the surface of the displacement sensor, the magnetic field changes, and the overall displacement shifts towards a negative displacement. If the displacement center becomes smaller (≤-0.25), it is determined to be displacement sensor drift. If the continuous mileage only reaches the risk threshold, it is determined to be risky and continuously monitored. The preset negative change threshold is used to identify sensor zero-point drift or signal attenuation, and to distinguish between mechanical and electrical faults through the characteristics of negative displacement changes. For cases where the continuous mileage has not reached the confirmation threshold but characteristic value changes have occurred, the case is added to the risk tracking list, and data continues to be collected to observe trend development, preventing premature conclusions and incorrect repairs. Negative changes usually do not involve changes in mechanical physical dimensions, but rather deviations at the signal acquisition level. This logic enables precise location of the root cause of the fault, guides subsequent maintenance strategies, and distinguishes between hardware replacement or sensor calibration requirements.

[0045] Based on the above embodiments, in this embodiment, the method further includes a re-identification step: The system acquires the master gear shift count from the operational data. This count serves as a key indicator of the transmission's maintenance history, monotonically increasing with vehicle operation unless a specific intervention event occurs. By monitoring the trend of this count in real time, a logical basis for judgments related to maintenance behavior is established, ensuring that the diagnostic logic can perceive state changes throughout the vehicle's entire lifecycle and providing a basis for subsequently identifying non-faulty data abrupt changes. The master gear shift count is stored in the controller's non-volatile memory. As a core parameter reflecting the cumulative frequency of transmission mechanical actions, its data integrity directly affects the reliability of the diagnostic benchmark.

[0046] When the decrease in the number of shifts in the AMT transmission exceeds a preset rollback threshold, a count reset event is identified. Specifically, when the number of shifts in the master transmission drops significantly, it is identified as a maintenance, rewriting, or controller count reset event. This non-natural decrease in value usually corresponds to a software rewriting, hardware replacement, or manual count reset operation of the transmission control unit. The system compares the difference in count values ​​between adjacent timestamps to determine whether a significant rollback condition is met, thereby distinguishing between normal count accumulation and abnormal reset behavior. This prevents historical data gaps caused by count logic restarts from being misinterpreted as sudden changes in mechanical state. This logic excludes interference from single data loss due to communication packet loss and only judges significant downward trends in values.

[0047] Based on the operational data following the count reset event, the steps of calculating the characteristic values ​​of shift displacement and determining the diagnostic results are re-executed. Subsequent diagnostic features are recalculated using the initial value of the number of shifts after the reset point to avoid misjudging maintenance resets as fault transitions. The reset event signifies an update to the vehicle's maintenance status; previous wear accumulation features are no longer applicable to the mechanical state after the reset. Therefore, the sliding window and statistical baseline need to be reconstructed using the reset point as a new starting point. By clearing the historical feature cache before the reset, it is ensured that the diagnostic results only reflect the true mechanical state within the current maintenance cycle, eliminating spurious changes in displacement features caused by the count returning to zero, and guaranteeing diagnostic continuity and accuracy.

[0048] Based on the above embodiments, in this embodiment, after determining the diagnostic result of the AMT transmission, the method further includes: Generate a diagnostic report, which should include at least the vehicle number, fault type, first abnormal mileage, risk level, and recommended remedial measures.

[0049] The vehicle number serves as a unique identifier associated with a specific vehicle file. The fault type is clearly distinguished as mechanical slider wear or displacement sensor drift. The cumulative mileage at which the first abnormal mileage marker characteristic value change point first meets the confirmation conditions is recorded. The risk level is classified into tracking or repair levels based on the continuously confirmed mileage. The recommended handling measures provide guidance such as checking the slider or calibrating the sensor, forming a closed-loop information flow from diagnosis to maintenance.

[0050] To meet the needs of refined analysis, detailed output includes vehicle number, fault type, first abnormality time, first abnormal mileage, abnormal gear, stable displacement before and after the change, mode percentage, continuous confirmation mileage, trend slope, risk level, and recommended remedial measures. The first abnormality time records the specific timestamp of the fault trigger; the abnormal gear position identifies the specific gear range where the displacement jump occurred; the difference in the center value of the stable displacement before and after the change quantifies the characteristic value of the stable displacement to confirm the amount of wear or drift; the mode percentage reflects the concentration of displacement distribution within the window to verify stability; the continuous confirmation mileage records the driving distance that meets the threshold requirements after the jump; and the trend slope characterizes the rate of long-term wear development. All fields together constitute a complete fault file, supporting subsequent maintenance decisions and historical data traceability, ensuring the interpretability and actionability of the diagnostic results.

[0051] Diagnostic rules can be set as follows, and specific thresholds can be adjusted according to sampling frequency, vehicle configuration, and test calibration:

[0052] In summary, this application can detect potential risks by observing trend changes before fault codes appear, improving the early warning capability for displacement-related faults in AMT transmissions. This method identifies the direction of displacement signal evolution by monitoring stable displacement center values ​​before and after characteristic value change points, recognizing abnormal signs before displacement deviations accumulate to trigger fault codes. Based on the proportion of the window's mode, the distribution concentration is quantified; when the proportion is below a threshold, it indicates that the center is migrating, thus distinguishing between normal fluctuations and abnormal jumps. This provides a data foundation for early detection of abnormal signals in operational data, ensuring that diagnostic logic is based on objective numerical changes rather than absolute positions, achieving a shift from reactive maintenance to predictive maintenance.

[0053] By using gear selection and statistical window extraction to extract stable center values, the impact of approximately 1mm of normal fluctuations, sampling noise, and short-term jitter on the judgment results can be significantly reduced. Specifically, data with a vehicle speed greater than 0 and the actual gear matching the target gear (i.e., gear-selectgearda12=0) are retained, while data from the gear shift transition period are discarded. The rolling median is calculated for the displacement sequence of the same gear to suppress instantaneous noise, and the mode of the window is calculated to represent the stable position center after sensor quantization. This method avoids interference from natural displacement differences between different gears, ensures that feature value calculation only considers the changing trend of the same mechanical structure under the same stable state, solves the problem of misjudgment due to fixed thresholds, and enhances the algorithm's adaptability to noisy environments.

[0054] It can automatically scan large numbers of vehicles, leveraging the computing power of a cloud platform for parallel processing. The reference material statistically analyzed 905 vehicles, identifying 82 vehicles with drift characteristics, 57% of which had less than 40,000 kilometers on the odometer, demonstrating the value of early batch identification. The system converts diagnosis from a time-based to a mileage-based approach based on cumulative mileage, determining the persistence of anomalies and ensuring fault determination is based on actual driving distance, consistent with the physical law that mechanical wear is strongly correlated with mileage. Automatic scanning can quickly locate high-risk vehicle groups, enabling efficient risk screening and key monitoring in large-scale fleet management, supporting batch traceability and early intervention for quality issues.

[0055] It can output fault type, fault mileage, and risk level, providing a basis for service station spare parts preparation, maintenance prioritization, and quality issue closure. The generated diagnostic report includes at least the vehicle number, fault type, first abnormal mileage, risk level, and recommended remedial measures, providing detailed output of stable displacement before and after the change, mode percentage, and trend slope. The fault type clearly distinguishes between mechanical slider wear and displacement sensor drift, and the risk level is divided into tracking or repair levels based on continuously confirmed mileage, forming a closed-loop information flow from diagnosis to maintenance. This ensures the interpretability and actionability of diagnostic results, guiding the replacement of worn parts or sensor calibration needs.

[0056] The method primarily relies on existing vehicle-to-everything (V2X) data and software algorithms, requiring no additional hardware sensors, resulting in low implementation costs and suitability for deployment on cloud platforms or after-sales diagnostic systems. Operational data includes shift displacement signals, gear position signals, and vehicle driving status signals, which are typically collected by the onboard terminal and uploaded to the cloud platform. The software algorithm, deployed on a cloud server, processes data through preset time periods or event-triggered mechanisms. This allows for the upgrading and iteration of diagnostic functions without modifying the vehicle's hardware structure, reducing the economic costs and technical barriers to large-scale applications and meeting the cost control requirements for commercialization.

[0057] See Figures 2-6 The following example illustrates the issue of an unreliable displacement sensor in the DA12 transmission. This embodiment extracts displacement, actual gear, target gear, vehicle speed, and cumulative mileage data from vehicles such as R8025698 and R8022107, based on vehicle operation data. Background fault information includes out-of-range shift position sensor signal, out-of-range front auxiliary gearbox position sensor signal, and stuck neutral gear shift.

[0058]

[0059] This table displays specific data examples of the vehicle's operational data acquired in step 101, corresponding to the original input fields read by the vehicle networking platform. The table lists fields such as gpsdate, gear, mainbox3shifttimesda12, rotation, selectgearda12, speed, tdisplacementda12, and totalmileage, comprehensively covering the time sequence, effective driving status, and consistency information between the actual and target gears required for the diagnostic method. Among these, gpsdate provides a time-series benchmark, ensuring the continuity and traceability of data packets and supporting the reassembly of operational data by time sequence. For example, the table shows the timestamps of continuous data acquisition at the second level from 2025-05-02 07:40:55.0 to 07:40:56.0, providing a time dimension basis for subsequent screening of stable operating conditions.

[0060] In the table, `gear` and `selectgearda12` correspond to the actual gear and target gear, respectively. The table data shows that both `gear` and `selectgearda12` are 12, indicating that the actual gear and target gear are consistent, meeting the condition for gear signal consistency in the preset stable operating conditions, and belonging to the sample under effective driving conditions. The `speed` field corresponds to vehicle speed; the values ​​of 67.16 and 67.23 in the table are greater than zero, meeting the screening condition of vehicle speed greater than zero, excluding invalid signals in a stationary state. `tdisplacementda12` is the core observation of the shift displacement sensor; the values ​​of 38.25 and 38 in the table directly reflect the physical position of the shift mechanism and are the direct basis for subsequent calculation of shift displacement characteristic values. Its small changes can be used to monitor the migration trend of the displacement center.

[0061] In addition, the mainbox3shifttimesda12 and other mainbox shift counts are used to identify maintenance or count resets. The value of 8330 in the table increases monotonically with vehicle operation. Unless a specific intervention event occurs, the non-natural decline of this value is used to determine the system reset status. Totalmileage converts the diagnosis from a time axis to a mileage axis. The cumulative mileage data of 113067810 in the table is used to determine the persistence of abnormalities, ensuring that fault determination is based on actual driving distance. The rotation field reflects the engine or input shaft speed, helping to determine the vehicle load status. This table as a whole reflects the multidimensional characteristics of the operating data, providing basic data support for subsequent selection of target data, calculation of feature values, and determination of diagnostic results, ensuring that the diagnostic logic can perceive state changes throughout the vehicle's entire life cycle.

[0062] Secondly, embodiments of this application provide an AMT transmission diagnostic system, comprising: a data acquisition module, a data filtering module, a feature calculation module, and a diagnostic determination module. The data acquisition module is used to acquire vehicle operating data, which includes at least shift displacement signals, gear signals, and vehicle driving status signals. The data filtering module is used to filter target data that meets preset stable operating conditions from the operating data based on the gear signals and the vehicle driving status signals. The feature calculation module is used to calculate feature values ​​of the shift displacement based on the gear signals and shift displacement signals in the target data. The diagnostic determination module is used to determine the diagnostic result of the AMT transmission based on the changes in the feature values.

[0063] The functions of each module in the AMT transmission diagnostic system correspond to the steps in the AMT transmission diagnostic method embodiment, and their functions and implementation processes will not be described in detail here.

[0064] Thirdly, this application provides an AMT transmission diagnostic device, which can be a personal computer (PC), laptop computer, server or other device with data processing capabilities.

[0065] In this embodiment, the AMT transmission diagnostic device may include a processor, a memory, a communication interface, and a communication bus.

[0066] The communication bus can be of any type and is used to interconnect the processor, memory, and communication interface.

[0067] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces used for interconnecting internal components of the AMT transmission diagnostic equipment, as well as interfaces used for interconnecting the AMT transmission diagnostic equipment with other devices (such as other computing devices or user equipment). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user equipment can be displays, keyboards, etc.

[0068] Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0069] The processor can be a general-purpose processor, which can call the AMT transmission diagnostic program stored in the memory and execute the AMT transmission diagnostic method provided in the embodiments of this application. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the AMT transmission diagnostic program is called can be referred to in the various embodiments of the AMT transmission diagnostic method of this application, and will not be repeated here.

[0070] Fourthly, embodiments of this application also provide a computer-readable storage medium.

[0071] The present application provides a computer-readable storage medium storing an AMT transmission diagnostic program, wherein when the AMT transmission diagnostic program is executed by a processor, it implements the steps of the AMT transmission diagnostic method described above.

[0072] The method implemented when the AMT transmission diagnostic program is executed can be referred to in various embodiments of the AMT transmission diagnostic method of this application, and will not be repeated here.

[0073] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0074] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0075] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.

[0076] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0077] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0078] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0079] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A diagnostic method for an AMT (Automated Manual Transmission), characterized in that, It includes: Acquire vehicle operating data, including shift displacement signal, gear signal, and vehicle driving status signal; Based on the gear position signal and the vehicle driving status signal, target data that meets the preset stable operating conditions is selected from the operating data; Based on the gear position signal and shift displacement signal in the target data, calculate the characteristic value of the shift displacement; The diagnostic results for the AMT transmission are determined based on the changes in the aforementioned characteristic values.

2. The AMT transmission diagnostic method as described in claim 1, characterized in that, Meeting the preset stable operating conditions includes: Vehicle speed is greater than zero; The actual gear position matches the target gear position. The error between the instrument's cumulative mileage and the mileage calculated based on vehicle speed integral is less than a preset error threshold.

3. The AMT transmission diagnostic method as described in claim 1, characterized in that, Based on the gear position signal and shift displacement signal in the target data, the characteristic value of the shift displacement is calculated, specifically including: Based on the gear position signal in the target data, the target data is divided into data subsets corresponding to different gear positions; For each subset of data, the shift displacement signal is extracted to construct a displacement sample sequence for the same gear. Statistical analysis was performed on the displacement sample sequence of the same gear to obtain the characteristic value of the shift displacement.

4. The AMT transmission diagnostic method as described in claim 3, characterized in that, Statistical analysis is performed on the displacement sample sequence of the same gear to obtain the characteristic values ​​of the shift displacement, specifically including: Within a preset time window or mileage window, calculate the rolling median of the displacement sample sequence of the same gear. The rolling median is determined as the center value of the stable displacement and used as the characteristic value of the shift displacement.

5. The AMT transmission diagnostic method as described in claim 3, characterized in that, Statistical analysis is performed on the displacement sample sequence of the same gear to obtain the characteristic values ​​of the shift displacement, specifically including: Within a preset time window or mileage window, calculate the mode of displacement of the displacement sample sequence of the same gear. The mode of the displacement is determined as the center value of the stable displacement and used as the characteristic value of the shift displacement.

6. The AMT transmission diagnostic method as described in claim 5, characterized in that, Based on the changes in the aforementioned characteristic values, the diagnostic result of the AMT transmission is determined, specifically including: The proportion of the mode of displacement within the preset time window or mileage window to the total number of samples in the window is calculated to obtain the window mode proportion. When the change in the mode of displacement exceeds a preset change threshold, the proportion of the mode of the window is lower than a preset proportion threshold, and the continuous mileage after the jump exceeds a preset mileage threshold, a feature value change point is determined to have occurred. The diagnostic results of the AMT transmission are determined based on the stable displacement center values ​​before and after the point of change of the characteristic value.

7. The AMT transmission diagnostic method as described in claim 6, characterized in that, Based on the stable displacement center values ​​before and after the point of change of the characteristic value, the diagnostic results of the AMT transmission are determined, specifically including: Calculate the change in the stable displacement center value after the point of change of the characteristic value relative to the stable displacement center value before the change; If the change is greater than or equal to a preset positive change threshold, the diagnostic result of the AMT transmission is determined to be mechanical slider wear. If the change is less than or equal to a preset negative change threshold, the diagnostic result of the AMT transmission is determined to be displacement sensor drift.

8. The AMT transmission diagnostic method as described in claim 1, characterized in that, The method also includes a re-identification step: Obtain the number of gear shifts of the main gearbox from the operating data; When the decrease in the number of gear shifts of the AMT transmission exceeds the preset backoff threshold, a count reset event is determined to have occurred. Based on the running data after the count reset event, the steps of calculating the characteristic value of the shift displacement and determining the diagnostic result are re-executed.

9. The AMT transmission diagnostic method as described in claim 1, characterized in that, After determining the diagnostic results of the AMT transmission, the method further includes: Generate a diagnostic report, which includes at least the vehicle number, fault type, first abnormal mileage, risk level, and recommended remedial measures.

10. An AMT transmission diagnostic system, characterized in that, It includes: The data acquisition module is used to acquire vehicle operating data, which includes at least shift displacement signal, gear signal and vehicle driving status signal; The data filtering module is used to filter target data that meets preset stable operating conditions from the operating data based on the gear signal and the vehicle driving status signal. The feature calculation module is used to calculate the feature value of the shift displacement based on the gear position signal and shift displacement signal in the target data; The diagnostic determination module is used to determine the diagnostic result of the AMT transmission based on the changes in the characteristic values.

Images