State recognition method and system for braking system in vehicle, vehicle and storage medium

Abstract

The embodiment of the invention provides a state recognition method and system for a braking system in a vehicle, the vehicle and a storage medium, and the method comprises the steps that operation state parameters of the braking system in the vehicle are obtained, and the operation state parameters are used for representing the operation state of the braking system; feature extraction is conducted on the operation state parameters, time domain features and frequency domain features of operation feature parameters are obtained, the time domain features are used for representing the abrasion state of the braking system, and the frequency domain features are used for representing the vibration and stress state of the braking system; performing fusion processing on the time domain feature and the frequency domain feature to obtain a fusion feature; and the fusion features are identified, an identification result is obtained, and the identification result is used for representing the health state of the braking system. The technical problem that the monitoring efficiency of the braking system is low is solved.

Description

Technical Field

[0001] This application relates to the field of vehicle safety technology, and more specifically, to a method, system, vehicle, and storage medium for identifying the state of a braking system in a vehicle. Background Technology

[0002] Currently, traditional braking systems rely on periodic manual inspections and cannot be monitored in real time. However, existing monitoring systems are limited in scope (e.g., only detecting brake pad thickness) and lack multi-dimensional data fusion and intelligent diagnostic capabilities, thus resulting in low monitoring efficiency for braking systems.

[0003] There is currently no good solution to the above problems. Summary of the Invention

[0004] This application provides a method, system, vehicle, and storage medium for identifying the state of a braking system in a vehicle, in order to at least solve the technical problem of low monitoring efficiency of the braking system.

[0005] According to one aspect of the embodiments of this application, a method for identifying the state of a braking system in a vehicle is provided. The method may include: acquiring operating state parameters of the braking system in the vehicle, wherein the operating state parameters are used to characterize the operating state of the braking system; extracting features from the operating state parameters to obtain time-domain features and frequency-domain features of the operating feature parameters, wherein the time-domain features are used to characterize the wear state of the braking system, and the frequency-domain features are used to characterize the vibration and stress state of the braking system; fusing the time-domain features and the frequency-domain features to obtain fused features; and identifying the fused features to obtain an identification result, wherein the identification result is used to characterize the health state of the braking system.

[0006] Furthermore, feature extraction is performed on the operating status parameters to obtain the time-domain and frequency-domain features of the operating feature parameters, including: filtering the operating status parameters to obtain filtered data; and extracting features from the filtered data to obtain time-domain and frequency-domain features.

[0007] Further, the identification results include a first identification result and / or a second identification result. The first identification result is used to characterize the fault status of the braking system, and the second identification result is used to characterize the remaining life of the braking system. Identifying the fused features to obtain the identification results includes: using a diagnostic model to identify the fused features to obtain the first identification result, wherein the diagnostic model is trained using historical fault operating state parameters of the braking system and the fault identification results corresponding to the historical fault operating state parameters; in response to the first identification result characterizing the existence of a fault in the braking system, using a prediction model to identify the fused features to obtain the second identification result, wherein the prediction model is trained using historical wear data of the braking system and the historical remaining life corresponding to the historical wear data.

[0008] Furthermore, the method may also include: responding to the identification result used to characterize a fault in the braking system, outputting a first prompt message, and determining the cause of the fault in the braking system based on the identification result, wherein the first prompt message is used to indicate that a fault exists in the braking system; and generating a maintenance work order using the cause of the fault.

[0009] Furthermore, the method may also include: acquiring a three-dimensional model of the braking system; and displaying the recognition results in the three-dimensional model.

[0010] Furthermore, obtaining a three-dimensional model of the braking system includes: obtaining vehicle identification information; determining the target type of the braking system based on the identification information; determining the structural parameters that match the target type; and constructing a three-dimensional model according to the structural parameters.

[0011] According to one aspect of the embodiments of this application, a state recognition system for a braking system in a vehicle is provided. The system may include: a data acquisition unit for acquiring operating state parameters of the braking system in the vehicle, wherein the operating state parameters are used to characterize the operating state of the braking system; an edge computing unit for extracting features from the operating state parameters to obtain time-domain features and frequency-domain features of the operating feature parameters, wherein the time-domain features are used to characterize the wear state of the braking system, and the frequency-domain features are used to characterize the vibration and stress state of the braking system; fusing the time-domain features and frequency-domain features to obtain fused features; and a data processing unit for recognizing the fused features to obtain a recognition result, wherein the recognition result is used to characterize the health state of the braking system.

[0012] Furthermore, the system may also include: an early warning unit, which outputs a first warning message in response to the identification result indicating that the health status of the braking system is abnormal, and outputs a second warning message in response to the identification result indicating that the health status of the braking system is normal.

[0013] According to another aspect of the embodiments of this application, a state recognition device for a braking system in a vehicle is also provided. The device may include: an acquisition unit for acquiring operating state parameters of the braking system in the vehicle, wherein the operating state parameters are used to characterize the operating state of the braking system; an extraction unit for extracting features from the operating state parameters to obtain time-domain features and frequency-domain features of the operating feature parameters, wherein the time-domain features are used to characterize the wear state of the braking system, and the frequency-domain features are used to characterize the vibration and stress state of the braking system; a processing unit for fusing the time-domain features and the frequency-domain features to obtain fused features; and an identification unit for identifying the fused features to obtain an identification result, wherein the identification result is used to characterize the health state of the braking system.

[0014] According to another aspect of the embodiments of this application, a vehicle is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of this application when it runs.

[0015] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of this application.

[0016] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of this application.

[0017] According to another aspect of the embodiments of this application, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the methods in various embodiments of this application.

[0018] According to another aspect of the embodiments of this application, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of this application.

[0019] In this embodiment, operating state parameters of the braking system in a vehicle are obtained, wherein the operating state parameters are used to characterize the operating state of the braking system; feature extraction is performed on the operating state parameters to obtain time-domain and frequency-domain features of the operating feature parameters, wherein the time-domain features are used to characterize the wear state of the braking system, and the frequency-domain features are used to characterize the vibration and stress state of the braking system; the time-domain and frequency-domain features are fused to obtain fused features; the fused features are identified to obtain an identification result, wherein the identification result is used to characterize the health state of the braking system. That is, in this application, operating state parameters of the braking system are obtained, and feature extraction is performed on the operating state parameters to obtain time-domain and frequency-domain features. The time-domain and frequency-domain features can be used to determine different performance parameters of the braking system. Furthermore, the time-domain and frequency-domain features are fused to obtain fused features, and the fused features are identified to obtain an identification result. This identification result can be used to determine the health level (i.e., wear level) of the braking system, thereby achieving the technical effect of improving the monitoring efficiency of the braking system and solving the technical problem of low monitoring efficiency of the braking system. Attached Figure Description

[0020] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0021] Figure 1 This is a flowchart of a method for identifying the state of a braking system in a vehicle according to an embodiment of this application;

[0022] Figure 2 This is a flowchart of a health monitoring method for a braking system according to an embodiment of this application;

[0023] Figure 3 This is a schematic diagram of a vehicle braking system state recognition system according to an embodiment of this application;

[0024] Figure 4 This is a schematic diagram of a vehicle braking system status recognition device according to an embodiment of this application. Detailed Implementation

[0025] 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 should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] According to an embodiment of this application, a method embodiment for identifying the state of a braking system in a vehicle is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0028] Currently, traditional braking systems rely on periodic manual inspections, making it impossible to monitor key parameters such as wear, temperature, and pressure in real time. Existing monitoring systems are limited in scope (e.g., only detecting brake pad thickness) and lack multi-dimensional data fusion and intelligent diagnostic capabilities. They also struggle to provide timely warnings of sudden braking failures (such as hydraulic leaks or material fatigue). Therefore, there is a technical problem of low monitoring efficiency in braking systems.

[0029] To address the aforementioned issues, this embodiment proposes a braking system health monitoring system based on multi-sensor fusion and intelligent analysis. This system is suitable for real-time status monitoring and fault early warning of braking systems in automobiles, rail transit, and aircraft. It integrates sensor networks, data analysis, and cloud collaboration for real-time status monitoring and fault early warning of braking systems.

[0030] In this embodiment, the operating state parameters of the braking system are acquired, and feature extraction is performed on the operating state parameters to obtain time-domain features and frequency-domain features. The time-domain features and frequency-domain features can be used to determine different performance parameters of the braking system. Furthermore, the time-domain features and frequency-domain features are fused to obtain fused features. By identifying the fused features, an identification result is obtained. This identification result can be used to determine the health status (i.e., wear level) of the braking system, thereby achieving the technical effect of improving the monitoring efficiency of the braking system and solving the technical problem of low monitoring efficiency of the braking system.

[0031] This embodiment provides a method for recognizing the state of a vehicle's braking system. Figure 1 This is a flowchart of a method for recognizing the state of a braking system in a vehicle according to an embodiment of this application. Figure 1 As shown, the method may include the following steps:

[0032] Step S102: Obtain the operating status parameters of the braking system in the vehicle, wherein the operating status parameters are used to characterize the operating status of the braking system.

[0033] In the technical solution provided in step S102 of this application, the aforementioned operating state parameters can be used to characterize the operating state of the braking system, and may include, but are not limited to, parameters such as brake disc thickness, temperature, pressure, vibration, and hydraulic oil condition. It should be noted that this is merely an example, and no specific limitations are placed on the types of operating state parameters.

[0034] Optionally, before determining the health status of the braking system, it is necessary to use sensor modules to collect various operating parameters of the braking system. These operating parameters include, but are not limited to, brake disc thickness, brake pad temperature, brake caliper vibration, hydraulic pressure, and hydraulic oil condition. For example, a laser thickness sensor will periodically measure the thickness of the brake disc in the braking system to track the wear degree of the brake disc; a thermocouple array can continuously monitor the surface temperature of the brake pads to understand the thermal load during braking.

[0035] Optionally, the sensor modules in the data acquisition layer can be used to collect operating status parameters such as brake disc thickness, temperature, pressure, vibration, and hydraulic oil status.

[0036] Optionally, the data acquisition layer may include a physical sensor module, which may include, but is not limited to, laser thickness sensors, thermocouple arrays, micro-electro-mechanical systems (MEMS) accelerometers, hydraulic pressure sensors, etc. It should be noted that this is only an example and there are no specific restrictions on the devices for acquiring operating status parameters.

[0037] Optionally, a laser thickness sensor can be installed at a radially symmetrical position on the brake disc. This laser thickness sensor can measure the thickness change of the brake disc using a non-contact laser reflection principle. The aforementioned thermocouple array can be embedded in the brake pad backplate to monitor the temperature distribution of the brake friction surface in real time (range -40℃~1000℃). The aforementioned MEMS accelerometer can be fixed to the brake caliper bracket to acquire three-dimensional vibration signals (frequency range 0-10kHz). The aforementioned hydraulic pressure sensor can be integrated into the brake fluid line to monitor hydraulic system pressure fluctuations (range 0-30MPa).

[0038] Alternatively, the vehicle data interface can be used to obtain operating status parameters (also known as operating condition data) such as vehicle speed, brake pedal travel, and ABS trigger count via the On-Board Diagnostics II / Controller Area Network (OBD-II / CAN) bus.

[0039] In this embodiment, multi-source heterogeneous data are collected synchronously, covering key parameters such as mechanical wear, thermal load, and hydraulic status, providing comprehensive input for health assessment.

[0040] Step S104: Extract features from the operating state parameters to obtain the time-domain and frequency-domain features of the operating feature parameters. The time-domain features are used to characterize the wear state of the braking system, and the frequency-domain features are used to characterize the vibration and stress state of the braking system.

[0041] In the technical solution provided in step S104 of this application, the aforementioned time-domain features can be a description of the signal's performance and evolution on the time axis. They can be used to identify slowly changing trends or short-term events, such as the wear rate (μm / 100km), temperature rise slope (℃ / s), and hydraulic pressure fluctuations of the braking system. They can also be used to determine the wear rate of the brake disc, the thermal stability of the brake pad material, and leakage or blockage within the braking system. The aforementioned frequency-domain features can be characteristics obtained through spectral analysis of the signal. They can be used to identify specific frequency components in the vibration and to determine the vibration and stress state characterizing the braking system. These can include, but are not limited to, data such as the dominant frequency component, frequency band energy, and harmonic distribution. The aforementioned dominant frequency component can be the frequency component with the highest energy identified by analyzing the vibration signal of the brake caliper using Fast Fourier Transform. It can correspond to the natural frequency of the braking system, and an abnormal dominant frequency can indicate structural damage to the braking system. The aforementioned frequency band energy can be the vibration energy within a specific frequency range (e.g., 5-8kHz). If the energy in this frequency band increases relatively, it may indicate microcracks or material fatigue in the brake disc. The above harmonic distribution can represent the harmonic components in the vibration signal of the braking system. The appearance of higher harmonics is related to nonlinear effects or structural defects. It should be noted that this is only an illustrative example, and no specific limitations are made on the characterization of time-domain and frequency-domain features.

[0042] Optionally, to gain a more comprehensive and in-depth understanding and analysis of the intrinsic properties of the operating status parameters, this embodiment performs feature extraction on the operating status parameters to obtain their time-domain and frequency-domain features. In the processing and diagnosis of time series data, time-domain and frequency-domain features provide different perspectives, which are helpful for fault detection, condition monitoring, and predictive maintenance.

[0043] Optionally, time-domain characteristics can directly reflect the changes in operating state parameters over time, clearly showing the time-series patterns of these parameters, such as trends, periodicity, and abrupt changes. This is highly effective for monitoring slowly changing processes (such as wear rates) or sudden events (such as instantaneous impacts). Furthermore, transient events typically manifest as spikes or abrupt changes in the signal, and time-domain analysis can directly capture these characteristics. For example, detecting a sudden drop in pressure or increased vibration may indicate a fault or anomaly in the braking system.

[0044] Optionally, in the time domain, noise can be identified and removed by observing or processing the signal, such as by using smoothing filters or adaptive filters, which is crucial for the accuracy of subsequent analysis.

[0045] Optionally, frequency domain features can be used to focus on the frequency distribution of a signal. By converting the signal from the time domain to the frequency domain using techniques such as Fourier transform, it is possible to identify the components of different frequencies in the operating state parameters. For example, specific fault modes correspond to energy distributions at specific frequencies or within specific frequency ranges; bearing faults, for instance, typically exhibit additional energy peaks in the high-frequency region. Frequency domain analysis can help us identify these modes, thereby diagnosing faults.

[0046] Optionally, frequency domain feature analysis can be used to build machine learning models to assess system health. For example, by monitoring energy changes within a certain frequency range, the remaining lifespan of components can be predicted, allowing for advance maintenance planning. In the frequency domain, noise at specific frequencies can be filtered out more precisely while enhancing the frequency components of interest in the signal, resulting in a cleaner and clearer signal in the time domain.

[0047] Optionally, by combining time-domain and frequency-domain characteristics, a more comprehensive signal analysis framework can be constructed, which is particularly crucial for the monitoring and diagnosis of complex systems. In the application scenario of brake system health monitoring, time-domain characteristics such as wear rate and temperature rise slope can intuitively reflect the aging process of components; while frequency-domain characteristics such as the dominant frequency component in vibration signals can reveal potential problems inside the structure. The combination of the two greatly enhances the insight and predictive capabilities of the monitoring system.

[0048] For example, feature extraction of operating parameters can include time-domain feature extraction and frequency-domain feature extraction. For time-domain feature extraction, the rate of change of brake disc thickness (wear rate) can be calculated. This rate of change can reveal the wear trend of the brake disc over a period of time. Methods such as moving averages can be used to process brake pad temperature data to obtain the slope of temperature rise and understand the change of thermal stress over time. For frequency-domain feature extraction, Fourier transform can be used to convert the vibration signal from the time domain to the frequency domain to identify the dominant frequency component. For example, if the energy of the brake caliper vibration signal increases significantly in the 5-8 kHz frequency band, this may indicate the presence of microcracks or irregular wear inside the braking system, as such vibration modes are often associated with structural damage.

[0049] Step S106: The time-domain features and frequency-domain features are fused to obtain the fused features.

[0050] In the technical solution provided by step S106 of this application, time-domain features and frequency-domain features can be fused to obtain fused features.

[0051] Optionally, the fusion processing stage aims to integrate time-domain and frequency-domain features to form a more comprehensive "fused feature," which combines multi-dimensional information on braking system wear and vibration stress. For example, wear rate, temperature rise slope, and vibration energy in a specific frequency band can be used as inputs, and a feature vector containing comprehensive state information of the braking system can be generated through feature vector fusion algorithms (such as PCA principal component analysis, feature concatenation, etc.). It should be noted that the fusion method described here is only illustrative and is not intended to impose specific limitations.

[0052] Step S108: Identify the fused features to obtain identification results, wherein the identification results are used to characterize the health status of the braking system.

[0053] In the technical solution provided by step S108 of this application, the identification result can be an assessment and prediction of the health status of the braking system given by the identification model after feature extraction and fusion processing. This can include, but is not limited to: the braking system fault code. If the edge computing unit or cloud model detects an abnormal combination of features (such as excessively high temperature or abnormally fast wear rate), it will generate a corresponding fault code (such as P001-P006) to indicate the specific fault type; the braking system matching health score, which can be based on a comprehensive evaluation of various features to give a health status score between 0 and 100, reflecting the current integrity of the braking system; and the remaining service life prediction, which uses a trained Long Short-Term Memory (LSTM) network, combined with historical wear data and current features, to predict the remaining service life (RUL) of the braking system, providing a confidence interval in kilometers or time range to help plan maintenance or replacement in advance.

[0054] In this embodiment, a health monitoring system is proposed. This system collects and analyzes the operating status parameters of the braking system in real time, extracts time-domain and frequency-domain features, and finally identifies the health status and possible faults of the braking system through an intelligent model, so as to achieve early warning and preventive maintenance and ensure the safe operation of the vehicle.

[0055] For example, a trained recognition model (such as Support Vector Machine (SVM) or Long Short-Term Memory (LSTM) network) can be used to analyze the fused feature vectors to obtain the health status recognition result of the braking system. For instance, an SVM model might determine whether the vehicle's braking system is currently in a normal, warning-required, or faulty state based on the fused features; while an LSTM neural network uses time series characteristics to predict the remaining service life (RUL) of the braking system over a future period, providing a specific numerical range, such as "the brake discs are expected to continue to be used for 1500 kilometers."

[0056] Optionally, when an accelerated brake disc wear rate, increased vibration frequency component energy, and abnormal temperature rise slope are detected, the identification model may determine that "the remaining life of the brake disc is below the safety standard and it is recommended to check it immediately" by integrating the above features, and send this identification result to the vehicle's warning module so as to notify the driver in a timely manner or automatically generate a repair work order.

[0057] Through the above steps, the braking system health monitoring system in this embodiment can effectively transform multi-source heterogeneous data into an accurate assessment of the braking system's health status, achieving the goals of fault warning and remaining life prediction, and improving the overall safety and reliability of the vehicle.

[0058] Through the aforementioned steps S102 to S108, operating state parameters of the braking system in the vehicle are obtained, wherein the operating state parameters are used to characterize the operating state of the braking system; feature extraction is performed on the operating state parameters to obtain time-domain and frequency-domain features of the operating feature parameters, wherein the time-domain features are used to characterize the wear state of the braking system, and the frequency-domain features are used to characterize the vibration and stress state of the braking system; the time-domain and frequency-domain features are fused to obtain fused features; the fused features are identified to obtain an identification result, wherein the identification result is used to characterize the health state of the braking system. That is, in this application, operating state parameters of the braking system are obtained, and feature extraction is performed on the operating state parameters to obtain time-domain and frequency-domain features. The time-domain and frequency-domain features can be used to determine different performance parameters of the braking system. Furthermore, the time-domain and frequency-domain features are fused to obtain fused features, and the fused features are identified to obtain an identification result. This identification result can be used to determine the health level (i.e., wear level) of the braking system, thereby achieving the technical effect of improving the monitoring efficiency of the braking system and solving the technical problem of low monitoring efficiency of the braking system.

[0059] The above-mentioned method of this application will be further described below.

[0060] As an optional implementation, step S104 involves extracting features from the operating status parameters to obtain the time-domain and frequency-domain features of the operating feature parameters, including: filtering the operating status parameters to obtain filtered data; and extracting features from the filtered data to obtain time-domain and frequency-domain features.

[0061] In this embodiment, after obtaining the operating status parameters, the operating status parameters can be preprocessed to obtain filtered data after filtering. Feature extraction can be performed on the filtered data to obtain time-domain features and frequency-domain features.

[0062] Optionally, after obtaining the operating status parameters, the operating status parameters can be processed in real time using the edge computing unit to obtain time domain features and frequency domain features. By utilizing the edge computing layer, the cloud transmission load can be effectively reduced, and millisecond-level local fault detection (such as sudden hydraulic leakage) can be achieved.

[0063] Optionally, the aforementioned edge computing unit, also known as the edge computing layer, may include an embedded processor running a real-time operating system (RTOS) and incorporating the following functional modules: a data preprocessing module and a feature extraction module. The data preprocessing module can use Kalman filtering to eliminate vibration signal noise and sliding window normalization to process temperature data. Controller Area Network (CAN) bus data is aligned with sensor timestamps (error <1ms). The feature extraction module can extract features from the filtered data to obtain time-domain and frequency-domain features.

[0064] Optionally, time-domain features may include: calculating the brake disc thickness wear rate (μm / 100km) and the temperature rise slope (℃ / s). Frequency-domain features may include the dominant frequency components (such as energy indicator cracks in the 5-8kHz frequency band) obtained by analyzing the vibration signal through Fast Fourier Transform (FFT).

[0065] As an optional implementation, the identification result includes a first identification result and / or a second identification result. The first identification result is used to characterize the fault status of the braking system, and the second identification result is used to characterize the remaining life of the braking system. Step S108 involves identifying the fused features to obtain the identification result, including: using a diagnostic model to identify the fused features to obtain the first identification result, wherein the diagnostic model is trained using historical fault operating state parameters of the braking system and the fault identification results corresponding to the historical fault operating state parameters; in response to the first identification result characterizing the existence of a fault in the braking system, using a prediction model to identify the fused features to obtain the second identification result, wherein the prediction model is trained using historical wear data of the braking system and the historical remaining life corresponding to the historical wear data.

[0066] In this embodiment, the identification results may include a first identification result and a second identification result. The first identification result can be used to determine the immediate health status of the braking system and to characterize the fault conditions of the braking system. It may include, but is not limited to, information such as fault type identification and fault code generation. For example, the first identification result can be used to determine whether a fault exists and its specific type. It can be derived from the analysis of fused features based on a diagnostic model and can be used to immediately detect and notify the user at the initial stage of a fault or even when fault signs appear. The second identification result can be used to characterize the remaining lifespan of the braking system and to assess the time or mileage under current wear and usage conditions under which the braking system can continue to operate safely. It can also be a prediction of the long-term health status and remaining lifespan of the braking system. It should be noted that this is merely an illustrative example, and there are no specific limitations on the types of the first and second identification results.

[0067] Optionally, the first and second identification results provide health status information of the braking system from the perspectives of immediate fault diagnosis and long-term performance prediction, respectively. The combination of the two constitutes a comprehensive monitoring and early warning system, which significantly improves vehicle safety and maintenance efficiency.

[0068] Optionally, the diagnostic model described above can be a short-term diagnostic model. The prediction model described above can be a long-term prediction model.

[0069] In this embodiment, a cloud-based analytics platform can be constructed. This platform uses machine learning models (such as LSTM and random forest) to predict the remaining lifespan of the braking system and generate fault codes. This cloud-based analytics platform can be a cloud platform layer, and can consist of a digital twin model, machine learning modules, and a knowledge base.

[0070] Optionally, the aforementioned digital twin model constructs a 3D model of the braking system based on the Unity3D game development software engine, dynamically mapping real vehicle data (such as temperature field visualization). The aforementioned machine learning module can include a short-term diagnostic model and a long-term prediction model. The short-term diagnostic model can be a supervised learning model (Support Vector Machine, SVM), used to identify various common faults (fault codes P001-P006), such as uneven brake pad wear and hydraulic oil contamination. It can be trained using historical fault operating state parameters of the braking system and the corresponding fault identification results. The long-term prediction model can be an LSTM neural network, which can take historical wear data as input and output the remaining life (RUL) confidence interval (error <5%). That is, this prediction model can be trained using historical wear data of the braking system and the corresponding historical remaining life. The aforementioned knowledge base can be used to store multiple fault cases and supports similarity matching retrieval.

[0071] In this embodiment, a cloud platform layer is used to provide high-precision health status prediction and maintenance decision support, and supports over-the-air (OTA) model updates.

[0072] Optionally, the diagnostic model is primarily used to identify whether and what type of fault has occurred in the braking system. This model is trained using machine learning algorithms (such as Support Vector Machine (SVM), Random Forest, etc.), and the training dataset includes historical fault operation state parameters and their corresponding fault identification results. The historical fault operation state parameters cover data recorded by sensors before and after the fault occurred, such as brake disc thickness, brake pad temperature, brake caliper vibration, and hydraulic pressure; while the fault identification results are fault types verified by experts, such as brake pad wear, hydraulic oil leakage, and brake disc cracks.

[0073] Optionally, after obtaining the fused features, these features can be input into the diagnostic model for analysis. The diagnostic model can determine whether a fault exists in the current braking system and the type of fault based on the relationships and patterns between diagnostic models, and output a first identification result with a fault code. For example, if the diagnostic model detects an abnormal increase in vibration energy in a specific frequency band, combined with the characteristic of accelerated wear rate, it may identify "risk of brake disc cracking (fault code P003)".

[0074] Optionally, the predictive model focuses on predicting the remaining service life of the braking system, i.e., how long the braking system can continue to operate normally without intervention. The predictive model can employ time series analysis algorithms, such as Long Short-Term Memory (LSTM) networks, and the training dataset can be historical wear data and its corresponding historical remaining life. Historical wear data includes changes in brake disc and pad thickness and temperature records over time; historical remaining life is the time recorded in the past from a certain wear state to complete system failure.

[0075] Optionally, when the diagnostic model indicates a fault warning, or for the purpose of preventative maintenance planning, the predictive model can be further used to analyze and fuse features. Based on the current feature state and past wear data, the predictive model predicts the remaining life of the braking system and outputs a second identification result with a confidence interval. For example, the model might predict that "at the current wear and vibration levels, the brake discs are expected to be safely used for another 1500 kilometers (confidence interval 1300-1700 kilometers)."

[0076] Optionally, a strategy can be adopted to divide the identification results into a first identification result (fault diagnosis) and a second identification result (remaining life prediction). This allows for timely warnings when fault symptoms are detected, while providing remaining life predictions for systems that have not reached the fault threshold but show obvious wear trends. This helps users and maintenance personnel make more reasonable maintenance decisions, ensuring the safety and reliability of the vehicle's braking system. This dual-model identification mechanism takes into account both immediate fault response and long-term performance prediction.

[0077] As an optional implementation, the method may further include: responding to the identification result used to characterize a fault in the braking system, outputting a first prompt message, and determining the cause of the fault in the braking system based on the identification result, wherein the first prompt message is used to indicate that a fault exists in the braking system; and generating a maintenance work order using the cause of the fault.

[0078] In this embodiment, if the identification result indicates a fault in the braking system, a first prompt message can be output. Based on the identification result, the cause of the braking system fault can be determined, and a repair work order can be generated using this cause. The first prompt message can be used to indicate a fault in the braking system and can be user-interactive content, text, or image information. For example, it could be a warning message such as, "Brake disc remaining life: 1500 km, inspection recommended." It should be noted that this is merely an example, and the specific format of the first prompt message is not limited. The repair work order can include a fault code and processing suggestions.

[0079] Optionally, a warning module is also provided, which can push alarm information through an in-vehicle display or a mobile terminal.

[0080] Optionally, the user interaction layer may include, but is not limited to, an in-vehicle HMI, a mobile application (APP), and a maintenance center interface. The in-vehicle HMI can be a touchscreen, used to display the braking system's health score (0-100%) and a 3D twin model. The mobile APP can be used to push warning information. The maintenance center interface can be used to automatically generate standardized repair work orders (including fault codes and handling suggestions). Through this user interaction layer, closed-loop management of the vehicle-person-service chain can be achieved.

[0081] As an optional implementation, the method may further include: acquiring a three-dimensional model of the braking system; and displaying the recognition results in the three-dimensional model.

[0082] In this embodiment, a three-dimensional model of the braking system can be displayed on the in-vehicle HMI. This three-dimensional model can be a three-dimensional twin model. Simultaneously, the recognition results can be displayed within the three-dimensional model.

[0083] Optionally, a 3D model of the braking system can be built based on the Unity3D engine, and real vehicle data can be dynamically mapped (such as temperature field visualization).

[0084] As an optional implementation method, obtaining a three-dimensional model of the braking system includes: obtaining vehicle identification information; determining the target type of the braking system based on the identification information; determining structural parameters that match the target type; and constructing a three-dimensional model according to the structural parameters.

[0085] In this embodiment, vehicle identification information can be obtained, such as license plate number and identification code, which can be used to determine the vehicle model and thus the target type of the braking system. Structural parameters matching the target type can be determined, and these parameters can be used to determine the size, structure, and other aspects of the braking system. Based on these structural parameters, a three-dimensional model can be constructed. It should be noted that this is merely an illustrative example, and the specific content of the structural parameters is not limited.

[0086] Figure 2 This is a flowchart of a health monitoring method for a braking system according to an embodiment of this application, such as... Figure 2 As shown, the method may include the following steps:

[0087] Step S202: Obtain the running status parameters.

[0088] In this embodiment, operating status parameters can be acquired. These operating status parameters may include brake disc thickness data, brake pad temperature data, vibration spectrum of the vibratory caliper, pressure waveform, and vehicle speed / braking frequency.

[0089] Optionally, the thickness data of the brake disc is collected using a brake disc laser thickness sensor, the temperature data of the brake pads is collected using a brake pad temperature sensor, the vibration spectrum of the caliper is collected using a brake caliper vibration sensor, the pressure waveform is collected using a hydraulic pressure sensor, and the vehicle speed / braking frequency is obtained using the vehicle CAN bus.

[0090] Step S204: Data preprocessing, and feature extraction of the preprocessed data.

[0091] In this embodiment, the operating status parameters are filtered to obtain filtered data. Feature extraction is then performed on the filtered data to obtain time-domain and frequency-domain features.

[0092] For example, the wear rate is calculated to obtain the time-domain characteristics, and the dominant vibration frequency is analyzed to obtain the frequency-domain characteristics.

[0093] Step S206: Fuse feature vectors.

[0094] In this embodiment, the time-domain features and frequency-domain features are fused to obtain fused features. These fused features can be multi-dimensional feature vectors.

[0095] Step S208: Identify the fused features to obtain the identification results.

[0096] In this embodiment, SVM / LSTM decision is performed on the fused features to obtain the recognition result.

[0097] Optionally, an SVM classifier can be used for real-time diagnosis to obtain fault codes, and an LSTM neural network can be used for long-term prediction to obtain the remaining life of the braking system. Based on the fault codes and remaining life, a health score is calculated for the braking system to obtain the identification result. This identification result can be a score of 0-100%, and may also include information such as fault type.

[0098] Step S210: Based on the identification results, trigger an early warning.

[0099] In this embodiment, if the identification result is greater than or equal to 80%, green is displayed, indicating that the braking system is in a normal health condition. If the identification result is between 60% and 80%, yellow is displayed, indicating that the braking system is in an abnormal health condition and needs to be checked.

[0100] In this embodiment, the operating state parameters of the braking system are obtained, and feature extraction is performed on the operating state parameters to obtain time-domain features and frequency-domain features. The time-domain features and frequency-domain features can be used to determine different performance parameters of the braking system. Furthermore, the time-domain features and frequency-domain features are fused to obtain fused features. By identifying the fused features, an identification result is obtained. This identification result can be used to determine the health status (i.e., wear level) of the braking system, thereby achieving the technical effect of improving the monitoring efficiency of the braking system and solving the technical problem of low monitoring efficiency of the braking system.

[0101] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0102] According to an embodiment of this application, an embodiment of a state recognition system for a braking system in a vehicle is also provided. It should be noted that this system can be used to execute the above-described state recognition method for a braking system in a vehicle.

[0103] Figure 3 This is a schematic diagram of a vehicle braking system state recognition system according to an embodiment of this application. Figure 3 As shown, the braking system status recognition system in the vehicle may include: a data acquisition unit 302, an edge computing unit 304, and a data processing unit 306.

[0104] The data acquisition unit 302 is used to acquire the operating status parameters of the braking system in the vehicle, wherein the operating status parameters are used to characterize the operating status of the braking system.

[0105] In this embodiment, the data acquisition unit can be a sensor module, which may include different types of sensors and can be used to acquire operating status parameters of different positions of the braking system.

[0106] Edge computing unit 304 is used to extract features from operating state parameters to obtain time-domain and frequency-domain features of operating characteristic parameters. The time-domain features are used to characterize the wear state of the braking system, and the frequency-domain features are used to characterize the vibration and stress state of the braking system. The time-domain features and frequency-domain features are fused to obtain fused features.

[0107] The data processing unit 306 is used to identify the fused features and obtain the identification results, wherein the identification results are used to characterize the health status of the braking system.

[0108] In this embodiment, the data processing unit can be a cloud-based analysis platform, which can be equipped with diagnostic and predictive models, and can be used to identify fused features using the diagnostic and predictive models to obtain identification results.

[0109] As an optional implementation, the system may further include: an early warning unit, configured to output a first warning message in response to the identification result indicating that the health status of the braking system is abnormal, and to output a second warning message in response to the identification result indicating that the health status of the braking system is normal.

[0110] In this embodiment, an SVM classifier is used for real-time diagnosis to obtain fault codes, and an LSTM neural network is used for long-term prediction to obtain the remaining life of the braking system. Based on the fault codes and remaining life, a health score is calculated for the braking system to obtain an identification result. This identification result can be a score from 0-100%, and may also include information such as fault type. If the identification result is greater than or equal to 80%, it can be displayed in green, indicating that the braking system is in a normal health state. If the identification result is between 60% and 80%, it can be displayed in yellow, indicating that the braking system is in an abnormal health state and needs to be inspected.

[0111] Optionally, the first notification message can be used to indicate that the braking system is in an abnormal state and requires inspection or repair. The second notification message can be used to indicate that the braking system is in a normal state.

[0112] In this embodiment, a braking system health monitoring system is proposed, which may include: a sensor module for collecting parameters such as brake disc thickness, temperature, pressure, vibration, and hydraulic oil status; an edge computing unit for real-time data processing and feature extraction (such as wear rate and temperature gradient); a cloud analysis platform for predicting remaining life and generating fault codes through machine learning models (such as LSTM and random forest); and an early warning module for pushing alarm information through an in-vehicle display or mobile terminal.

[0113] Optionally, it enables full lifecycle monitoring of the braking system, reduces the risk of sudden failures, reduces manual maintenance costs, improves vehicle safety, and is compatible with multiple braking types (disc, drum, and electromagnetic brakes).

[0114] In this embodiment, the operating status parameters of the braking system in the vehicle are acquired by a data acquisition unit, wherein the operating status parameters are used to characterize the operating status of the braking system; the operating status parameters are feature extracted by an edge computing unit to obtain the time-domain features and frequency-domain features of the operating feature parameters, wherein the time-domain features are used to characterize the wear state of the braking system, and the frequency-domain features are used to characterize the vibration and stress state of the braking system; the time-domain features and frequency-domain features are fused to obtain fused features; the fused features are identified by a data processing unit to obtain identification results, wherein the identification results are used to characterize the health state of the braking system, thereby achieving the technical effect of improving the monitoring efficiency of the braking system and solving the technical problem of low monitoring efficiency of the braking system.

[0115] According to an embodiment of this application, a state recognition device for a braking system in a vehicle is also provided. It should be noted that this device can be used to execute the above-described state recognition method for a braking system in a vehicle.

[0116] Figure 4 This is a schematic diagram of a vehicle braking system status recognition device according to an embodiment of this application. Figure 4 As shown, the braking system status recognition device in the vehicle may include: an acquisition unit 402, an extraction unit 404, a processing unit 406, and an identification unit 408.

[0117] The acquisition unit 402 is used to acquire the operating status parameters of the braking system in the vehicle, wherein the operating status parameters are used to characterize the operating status of the braking system.

[0118] Extraction unit 404 is used to extract features from operating state parameters to obtain time-domain and frequency-domain features of operating feature parameters. The time-domain features are used to characterize the wear state of the braking system, and the frequency-domain features are used to characterize the vibration and stress state of the braking system.

[0119] The processing unit 406 is used to perform fusion processing on the time domain features and frequency domain features to obtain fused features.

[0120] The identification unit 408 is used to identify the fused features and obtain the identification result, wherein the identification result is used to characterize the health status of the braking system.

[0121] Furthermore, the extraction unit 402 includes: a processing module for filtering the operating status parameters to obtain filtered data; and an extraction module for extracting features from the filtered data to obtain time-domain features and frequency-domain features.

[0122] Further, the identification unit 408 includes: a first identification module, used to identify the fused features using a diagnostic model to obtain a first identification result, wherein the diagnostic model is trained using historical fault operating state parameters of the braking system and the fault identification results corresponding to the historical fault operating state parameters; and a second identification module, used to identify the fused features using a prediction model in response to the first identification result used to characterize the existence of a fault in the braking system to obtain a second identification result, wherein the prediction model is trained using historical wear data of the braking system and the historical remaining life corresponding to the historical wear data.

[0123] Furthermore, the device may also include: a determining unit, configured to output a first prompt message in response to the identification result characterizing a fault in the braking system, and to determine the cause of the fault in the braking system based on the identification result, wherein the first prompt message is used to indicate that a fault exists in the braking system; and a generating unit, configured to generate a maintenance work order using the cause of the fault.

[0124] Furthermore, the device can also be used to acquire a three-dimensional model of the braking system and display the recognition results in the three-dimensional model.

[0125] Furthermore, the device can also be used to acquire vehicle identification information; determine the target type of the braking system based on the identification information; determine the structural parameters that match the target type; and construct a three-dimensional model according to the structural parameters.

[0126] In the vehicle braking system state recognition device of this embodiment, the acquisition unit acquires the operating state parameters of the vehicle braking system, wherein the operating state parameters are used to characterize the operating state of the braking system; the extraction unit extracts features from the operating state parameters to obtain the time-domain features and frequency-domain features of the operating feature parameters, wherein the time-domain features are used to characterize the wear state of the braking system, and the frequency-domain features are used to characterize the vibration and stress state of the braking system; the processing unit fuses the time-domain features and frequency-domain features to obtain fused features; and the recognition unit recognizes the fused features to obtain recognition results, wherein the recognition results are used to characterize the health state of the braking system, thereby achieving the technical effect of improving the monitoring efficiency of the braking system and solving the technical problem of low monitoring efficiency of the braking system.

[0127] Embodiments of this application also provide a vehicle, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods described in various embodiments of this application when it runs.

[0128] Embodiments of this application also provide a computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of this application.

[0129] Embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements the methods of various embodiments of this application.

[0130] Embodiments of this application also provide a computer program product, including a non-volatile computer-readable storage medium for storing a computer program that, when executed by a processor, implements the methods in various embodiments of this application.

[0131] Embodiments of this application also provide a computer program that, when executed by a processor, implements the methods described in the various embodiments of this application.

[0132] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0133] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection of units or modules may be electrical or other forms.

[0134] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0135] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0136] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0137] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method of identifying a state of a brake system in a vehicle, characterized by, The method comprises: obtaining an operation state parameter of a braking system in the vehicle, wherein the operation state parameter is used to represent an operation state of the braking system; performing feature extraction on the operation state parameter to obtain a time domain feature and a frequency domain feature of the operation feature parameter, wherein the time domain feature is used to represent a wear state of the braking system, and the frequency domain feature is used to represent a vibration and stress state of the braking system; performing fusion processing on the time domain feature and the frequency domain feature to obtain a fusion feature; performing identification on the fusion feature to obtain an identification result, wherein the identification result is used to represent a health state of the braking system.

2. The method of claim 1, wherein, The operation state parameter is filtered to obtain filtered data, and the filtered data is subjected to feature extraction to obtain the time domain feature and the frequency domain feature. The identification result comprises a first identification result and / or a second identification result, the first identification result is used to represent a fault condition of the braking system, and the second identification result is used to represent a remaining life of the braking system. The fusion feature is identified by using a diagnosis model to obtain the first identification result, wherein the diagnosis model is trained by using historical fault operation state parameters of the braking system and fault identification results corresponding to the historical fault operation state parameters.

3. The method of claim 1, wherein, In response to the first identification result representing that the braking system has a fault, the fusion feature is identified by using a prediction model to obtain the second identification result, wherein the prediction model is trained by using historical wear data of the braking system and historical remaining life corresponding to the historical wear data. The method further comprises: in response to the identification result representing that the braking system has a fault, outputting first prompt information, and determining a fault cause of the braking system based on the identification result, wherein the first prompt information is used to prompt that the braking system has a fault; 4. The method of claim 3, wherein, generating a repair work order by using the fault cause. The method further comprises: obtaining a three-dimensional model of the braking system; 5. The method of claim 1, wherein, displaying the identification result in the three-dimensional model. The three-dimensional model of the braking system is obtained by: obtaining identification information of the vehicle; 6. The method of claim 5, wherein, determining a target type of the braking system based on the identification information; determining a structure parameter matched with the target type; constructing the three-dimensional model according to the structure parameter. The method comprises: a data acquisition unit configured to obtain an operation state parameter of a braking system in a vehicle, wherein the operation state parameter is used to represent an operation state of the braking system; 7. A system for identifying the degree of wear of a brake system in a vehicle, characterized by ​ ​ An edge computing unit is configured to perform feature extraction on the operation state parameter to obtain time domain features and frequency domain features of the operation feature parameter, wherein the time domain features are used to represent a wear state of the brake system, and the frequency domain features are used to represent a vibration and stress state of the brake system; and the time domain features and the frequency domain features are fused to obtain fused features. A data processing unit is configured to perform identification on the fused features to obtain an identification result, wherein the identification result is used to represent a health state of the brake system.

8. The system of claim 7, wherein, The system further includes: An early warning unit is configured to output first prompt information in response to the identification result representing that the health state of the brake system is an abnormal state, and output second prompt information in response to the identification result representing that the health state of the brake system is a normal state.

9. A vehicle characterized by comprising: It includes: A memory storing an executable program; A processor configured to run the program, wherein the program performs the method of any one of claims 1 to 6 when running.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium includes a stored executable program, wherein the executable program controls the device where the storage medium is located to perform the method of any one of claims 1 to 6 when running.

Images