Methods, systems and devices for detecting brake system malfunctions

Abstract

This application discloses a method, system, and apparatus for detecting brake system anomalies, belonging to the field of intelligent driving technology. The method includes: when a braking event is detected, acquiring audio data via an audio acquisition component; based on the audio data and a trained brake system anomaly recognition model, identifying a brake system anomaly in the vehicle to obtain a target brake system anomaly type; if the target brake system anomaly type is included in the correspondence between brake system anomaly types and warning information, determining a target warning information corresponding to the target brake system anomaly type based on the correspondence; and providing a brake system anomaly warning based on the target warning information. Using this application can effectively improve driving safety.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a method, system and apparatus for detecting abnormalities in a braking system. Background Technology

[0002] During safe driving, braking performance will decline. Under normal circumstances, there will be no obvious sound when braking. However, as the vehicle travels a distance, users often hear abnormal sounds when braking, but they cannot determine the extent of the brake performance decline. They often think that the braking system has not failed, so they do not immediately carry out vehicle repairs, thus ignoring the abnormal sounds when braking and ignoring the potential safety hazards of the braking system.

[0003] During the abnormal decline in braking performance, the inability to accurately identify brake malfunctions poses a significant risk of brake failure. This safety risk is even greater for vehicles equipped with autonomous driving technology. Summary of the Invention

[0004] This application provides a method, system, and apparatus for detecting abnormalities in a braking system, which can effectively improve driving safety.

[0005] Firstly, a method for detecting abnormalities in a braking system is provided, the method comprising:

[0006] When a braking event is detected, audio data is acquired via the audio acquisition component.

[0007] Based on the audio data and the trained brake system anomaly identification model, brake system anomalies of the vehicle are identified to obtain the target brake system anomaly type of the vehicle.

[0008] If the target brake system abnormality type is included in the correspondence between brake system abnormality types and warning information, then the target warning information corresponding to the target brake system abnormality type is determined based on the correspondence.

[0009] Based on the target prompt information, a brake system malfunction warning is issued.

[0010] In one possible implementation, the step of acquiring audio data via an audio acquisition component when a braking event is detected includes:

[0011] When it is detected that the brake pedal of the vehicle is pressed and the pressing time reaches the first duration, if the travel of the brake pedal, the driving speed of the vehicle and the engine water tank temperature of the vehicle meet the audio acquisition conditions, then audio data is acquired through the audio acquisition component.

[0012] In one possible implementation, if the brake pedal travel, the vehicle speed, and the vehicle's engine coolant temperature meet the audio acquisition conditions, then audio data is acquired through the audio acquisition component, including:

[0013] If the proportion of the brake pedal travel to the total travel is greater than 0 and less than the proportion threshold, the vehicle's speed is within a first speed range, and the vehicle's engine coolant temperature is greater than a temperature threshold; or, if the proportion of the brake pedal travel to the total travel is greater than 0 and less than the proportion threshold, the vehicle's speed is within a second speed range, and the vehicle's engine coolant temperature is less than the temperature threshold, then audio data is collected through the audio acquisition component, wherein the speed in the first speed range is greater than that in the second speed range.

[0014] In one possible implementation, the first duration is 500ms, the ratio threshold is 60%, the first speed range is 10km / h to 40km / h, the second speed range is 0km / h to 10km / h, and the temperature threshold is 45 degrees Celsius.

[0015] In one possible implementation, the acquisition of audio data via the audio acquisition component includes: acquiring audio data of a second duration via the audio acquisition component.

[0016] In one possible implementation, the target braking system malfunction type includes at least one of the following: loose brake pad accessories, worn brake pads or brake discs, and malfunctioning caliper reset.

[0017] In one possible implementation, the method further includes:

[0018] Acquire sample audio data collected during the braking process of a sample vehicle, wherein the sample vehicle is a vehicle with an abnormal braking system;

[0019] Obtain the braking system anomaly type of the sample vehicle as the benchmark braking system anomaly type for training;

[0020] The sample audio data is input into the brake system anomaly recognition model to be trained to obtain the predicted brake system anomaly type;

[0021] Based on the baseline braking system anomaly type and the predicted braking system anomaly type, the braking system anomaly identification model to be trained is trained and its parameters are adjusted to obtain the trained braking system anomaly identification model.

[0022] Secondly, a system for detecting abnormalities in a braking system is provided, the system comprising:

[0023] The vehicle-mounted terminal is used to collect audio data through an audio acquisition component and send the audio data to a server when a braking event is detected.

[0024] The server is used to identify brake system anomalies in the vehicle based on the audio data and the trained brake system anomaly identification model, obtain the target brake system anomaly type of the vehicle, and if the target brake system anomaly type is included in the correspondence between brake system anomaly types and prompt information, then based on the correspondence, determine the target prompt information corresponding to the target brake system anomaly type and send the target prompt information to the vehicle terminal.

[0025] The vehicle-mounted terminal is used to provide a braking system malfunction warning based on the target prompt information.

[0026] In one possible implementation, the vehicle-mounted terminal is used for:

[0027] When it is detected that the brake pedal of the vehicle is pressed and the pressing time reaches the first duration, if the travel of the brake pedal, the driving speed of the vehicle and the engine water tank temperature of the vehicle meet the audio acquisition conditions, then audio data is acquired through the audio acquisition component.

[0028] In one possible implementation, the vehicle-mounted terminal is used for:

[0029] If the proportion of the brake pedal travel to the total travel is greater than 0 and less than the proportion threshold, the vehicle's speed is within a first speed range, and the vehicle's engine coolant temperature is greater than a temperature threshold; or, if the proportion of the brake pedal travel to the total travel is greater than 0 and less than the proportion threshold, the vehicle's speed is within a second speed range, and the vehicle's engine coolant temperature is less than the temperature threshold, then audio data is collected through the audio acquisition component, wherein the speed in the first speed range is greater than that in the second speed range.

[0030] In one possible implementation, the first duration is 500ms, the ratio threshold is 60%, the first speed range is 10km / h to 40km / h, the second speed range is 0km / h to 10km / h, and the temperature threshold is 45 degrees Celsius.

[0031] In one possible implementation, the vehicle terminal is configured to: acquire audio data of a second duration via an audio acquisition component.

[0032] In one possible implementation, the target braking system malfunction type includes at least one of the following: loose brake pad accessories, worn brake pads or brake discs, and malfunctioning caliper reset.

[0033] In one possible implementation, the server is further configured to:

[0034] Acquire sample audio data collected during the braking process of a sample vehicle, wherein the sample vehicle is a vehicle with an abnormal braking system;

[0035] Obtain the braking system anomaly type of the sample vehicle as the benchmark braking system anomaly type for training;

[0036] The sample audio data is input into the brake system anomaly recognition model to be trained to obtain the predicted brake system anomaly type;

[0037] Based on the baseline braking system anomaly type and the predicted braking system anomaly type, the braking system anomaly identification model to be trained is trained and its parameters are adjusted to obtain the trained braking system anomaly identification model.

[0038] Thirdly, a device for detecting abnormalities in a braking system is provided, the device comprising:

[0039] The acquisition module is used to acquire audio data through the audio acquisition component when a braking event is detected;

[0040] The identification module is used to identify brake system anomalies in the vehicle based on the audio data and the trained brake system anomaly identification model, and to obtain the target brake system anomaly type of the vehicle.

[0041] The determination module is used to determine the target prompt information corresponding to the target brake system abnormality type based on the correspondence between the target brake system abnormality type and the prompt information if the target brake system abnormality type is included in the correspondence between the brake system abnormality type and the prompt information.

[0042] The prompting module is used to provide a braking system malfunction prompt based on the target prompting information.

[0043] In one possible implementation, the acquisition module is used for:

[0044] When it is detected that the brake pedal of the vehicle is pressed and the pressing time reaches the first duration, if the travel of the brake pedal, the driving speed of the vehicle and the engine water tank temperature of the vehicle meet the audio acquisition conditions, then audio data is acquired through the audio acquisition component.

[0045] In one possible implementation, the acquisition module is used for:

[0046] If the proportion of the brake pedal travel to the total travel is greater than 0 and less than the proportion threshold, the vehicle's speed is within a first speed range, and the vehicle's engine coolant temperature is greater than a temperature threshold; or, if the proportion of the brake pedal travel to the total travel is greater than 0 and less than the proportion threshold, the vehicle's speed is within a second speed range, and the vehicle's engine coolant temperature is less than the temperature threshold, then audio data is collected through the audio acquisition component, wherein the speed in the first speed range is greater than that in the second speed range.

[0047] In one possible implementation, the first duration is 500ms, the ratio threshold is 60%, the first speed range is 10km / h to 40km / h, the second speed range is 0km / h to 10km / h, and the temperature threshold is 45 degrees Celsius.

[0048] In one possible implementation, the acquisition module is configured to: acquire audio data of a second duration via an audio acquisition component.

[0049] In one possible implementation, the target braking system malfunction type includes at least one of the following: loose brake pad accessories, worn brake pads or brake discs, and malfunctioning caliper reset.

[0050] In one possible implementation, the device further includes:

[0051] The training module is used to acquire sample audio data collected during the braking process of a sample vehicle, wherein the sample vehicle is a vehicle with an abnormal braking system; acquire the braking system abnormality type of the sample vehicle as a baseline braking system abnormality type for training; input the sample audio data into the braking system abnormality recognition model to be trained to obtain a predicted braking system abnormality type; and train and tune the braking system abnormality recognition model to be trained based on the baseline braking system abnormality type and the predicted braking system abnormality type to obtain a trained braking system abnormality recognition model.

[0052] Fourthly, a computer device is provided, the computer device including a processor and a memory, the memory for storing computer instructions, and the processor for executing the computer instructions stored in the memory to cause the computer device to perform the method of the first aspect and its possible implementations.

[0053] Fifthly, a computer-readable storage medium is provided, which stores computer program code, such that when the computer program code is executed by a computer device, the computer device performs the method of the first aspect and its possible implementations.

[0054] In a sixth aspect, a computer program product is provided, the computer program product including computer program code, and a method by which the computer device executes the first aspect and its possible implementations when the computer program code is executed by a computer device.

[0055] In this embodiment, when the vehicle's brake pedal is lightly pressed, the audio acquisition component collects the sound emitted by the vehicle. The collected audio data is then input into the brake system anomaly identification model for data analysis to determine the cause of the abnormal braking noise. Different causes of abnormal noise correspond to different brake system anomaly types. For each type of brake system anomaly, a corresponding target prompt message is determined and a brake system anomaly warning is issued. This method enables timely identification of brake system malfunctions, prompting personnel to address related issues promptly, thereby effectively reducing the likelihood of accidents and improving driving safety. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 This is a schematic diagram of the structure of a vehicle-mounted terminal provided in an embodiment of this application;

[0058] Figure 2 This is a flowchart of a method for detecting abnormalities in a braking system provided in an embodiment of this application;

[0059] Figure 3 This is a graph of the Mel frequency cepstral coefficients of a braking system anomaly type provided in an embodiment of this application;

[0060] Figure 4 This is a flowchart of a method for training a braking system recognition model provided in an embodiment of this application;

[0061] Figure 5 This is a flowchart of a method for detecting brake system anomalies provided in an embodiment of this application;

[0062] Figure 6 This is a schematic diagram of the structure of a system for detecting abnormalities in a braking system provided in an embodiment of this application;

[0063] Figure 7 This application provides a device for detecting abnormalities in a braking system.

[0064] Figure 8This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0065] 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.

[0066] The following explains the terms used in the embodiments:

[0067] Braking System Anomaly Detection Model: This is an algorithmic model that identifies the type of braking system anomaly by analyzing audio data generated during vehicle braking. It is a machine learning model. The braking system anomaly detection model can be divided into a feature extraction module and a classification module. The feature extraction module extracts audio features from the collected audio data, such as Mel-Frequency Cepstral Coefficients (MFCCs). The classification module determines the type of braking system anomaly based on the audio features. This module can be a Support Vector Machine (SVM). The audio features are input into the SVM, and the output can be either a no-anomaly label or an anomaly type label. The no-anomaly label indicates that the braking system is normal, while the anomaly type label indicates the type of braking system anomaly.

[0068] Brake system malfunctions can include loose brake pad accessories, worn brake pads or discs, and malfunctioning caliper reset. Loose brake pad accessories can be caused by problems with the brake caliper, worn moving pins, or detached springs; these all fall under the category of loose brake pad accessories and produce similar brake noises.

[0069] The first duration is the time elapsed from the moment the brake pedal is detected to the moment the brake pedal travel is detected. The brake pedal is not released during this duration. The first duration can be set by technicians based on experience.

[0070] The proportional threshold is the threshold value of the proportion of the brake pedal travel to the total travel during the brake pedal depressing process. This proportional threshold can be set by technicians based on experience.

[0071] The first speed range and the second speed range can be set by technicians based on experience.

[0072] Temperature thresholds are used to distinguish whether a vehicle is cold or hot. If the engine coolant temperature is above the threshold, it is considered a hot engine; conversely, if the engine coolant temperature is below the threshold, it is considered a cold engine. Temperature thresholds can be set by technicians based on experience.

[0073] The second duration is the time from when the audio acquisition component starts collecting audio data to when it stops collecting audio data. In other words, it's the time from when the audio acquisition component starts collecting audio data until the second duration has elapsed and then when audio data collection stops. This second duration can be set by technicians based on experience.

[0074] Sample audio data: This is audio data collected during braking of vehicles with abnormal braking systems. It can be used to train and tune the braking system abnormality identification model.

[0075] Baseline braking system anomaly type: This refers to the type of actual anomaly in the vehicle's braking system that was collected from the sample audio data. It is a reference value (or true value) used to compare with the predicted braking system anomaly type output by the model during the training of the braking system anomaly recognition model.

[0076] Predicting the type of brake system anomaly: This refers to the type of brake system anomaly directly output by the model after the audio data is input into the brake system anomaly identification model.

[0077] This application provides a method for detecting brake system anomalies, primarily applicable to vehicle driving scenarios. The method can be applied to vehicles, which may include an on-board terminal, a brake system, and many other components (not all of which are described here). The brake system includes a vacuum booster pump, brake calipers, brake pads, brake discs, and many other components (not all of which are described here). The method can be implemented by the on-board terminal, or by a combination of the on-board terminal and a server. The server can be a single server or a server group consisting of multiple servers.

[0078] Figure 1 This is a schematic diagram of the structure of a vehicle-mounted terminal provided in an embodiment of this application. From the perspective of hardware composition, the structure of the computer device 100 can be as follows: Figure 1 As shown, it includes a processor 101, a memory 102, a communication component 103, a display component 104, an audio acquisition component 105, and an audio output component 106.

[0079] The processor 101 can be a central processing unit (CPU) or a system-on-chip (SoC), etc. The processor 101 can be used to detect braking events, to identify braking system anomalies of the vehicle based on audio data and a trained braking system anomaly recognition model, to obtain the target braking system anomaly type of the vehicle, and to determine the target prompt information corresponding to the target braking system anomaly type based on the correspondence between the braking system anomaly type and the prompt information if the target braking system anomaly type is included in the correspondence between the braking system anomaly type and the prompt information.

[0080] The memory 102 may include various volatile or non-volatile memories, such as solid-state disks (SSDs) and dynamic random access memory (DRAM). The memory 102 can be used to store pre-data, intermediate data, and result data during the processing of brake system anomaly detection, such as audio data acquired by the audio acquisition component, the target brake system anomaly type of the vehicle identified by the brake system anomaly recognition model, etc.

[0081] The communication component 103 can be a wired network connector, a wireless fidelity (WiFi) module, a Bluetooth module, a cellular network communication module, etc. The communication component 103 can be used to transmit data with other devices, such as servers or terminals. For example, the vehicle terminal can send collected audio data to the server, the server can receive audio data collected by the vehicle terminal, and the server can send target prompt information to the vehicle terminal.

[0082] The display component 104 can be a standalone screen or a screen integrated with the terminal body. The screen can be a touch screen or a non-touch screen. The display component 104 is used to display system interfaces, application interfaces, etc. For example, the display component 104 can be used to display target prompt information.

[0083] The audio acquisition component 105 can be a vehicle-mounted microphone. It can be used to acquire audio data.

[0084] The audio output component 106 can be a vehicle speaker. It can be used to play target prompt information.

[0085] Figure 2 This is a flowchart illustrating a method for detecting brake system anomalies according to an embodiment of this application. See also... Figure 2 The method may include the following steps:

[0086] 201. When the vehicle terminal detects that the vehicle's brake pedal has been pressed and the pressing time has reached the first duration, if the brake pedal travel, vehicle speed, and vehicle engine coolant temperature meet the audio acquisition conditions, then audio data is acquired through the audio acquisition component.

[0087] During driving, the driver will press the brake pedal based on real-time road conditions. When the braking system detects that the brake pedal has been pressed, it will send a braking notification and the percentage of the total travel of the brake pedal (referred to as the travel percentage) to the onboard terminal in real time. The braking system can subsequently periodically send the travel percentage to the onboard terminal. Upon receiving the travel percentage, the onboard terminal can start timing. During the timing process, if the onboard terminal continuously receives the travel percentage from the braking system periodically, the timing continues; if the braking system stops sending travel percentages to the onboard terminal, the timing stops.

[0088] When the timing reaches the first duration, the vehicle terminal begins to determine the audio acquisition conditions. These conditions may include requirements for three factors: brake pedal travel, vehicle speed, and engine coolant temperature. The specific details of the audio acquisition conditions are as follows:

[0089] If the proportion of the brake pedal travel to the total travel is greater than 0 and less than the proportional threshold, the vehicle speed is within the first speed range, and the vehicle's engine coolant temperature is greater than the temperature threshold, or if the proportion of the brake pedal travel to the total travel is greater than 0 and less than the proportional threshold, the vehicle speed is within the second speed range, and the vehicle's engine coolant temperature is less than the temperature threshold, then audio data is collected through the audio acquisition component, wherein the speed in the first speed range is greater than that in the second speed range.

[0090] For example, the first duration can be 500ms, the proportion threshold can be 60%, the first speed range is 10km / h to 40km / h, the second speed range is 0km / h to 10km / h, and the temperature threshold can be 45 degrees Celsius.

[0091] The following section demonstrates a method for acquiring audio data, taking into account specific audio acquisition conditions:

[0092] a. When the brake pedal is detected to be pressed, record the moment as t=0s. Keep the pedal pressed. When the pressing time reaches 500ms, detect the brake pedal travel and determine the proportion of the brake pedal travel to the total pedal travel. If the proportion of the brake pedal travel to the total pedal travel is greater than 60%, the audio acquisition component will not be activated to collect audio data.

[0093] b. If the brake pedal travel is greater than 0 and less than or equal to 60% of the total pedal travel, then the real-time speed is acquired and the speed is determined. If the speed is greater than 40 km / h, then the audio acquisition unit is not activated to collect audio data.

[0094] c. If the speed is between 10km / h and 40km / h, the real-time engine coolant temperature is obtained. If the engine coolant temperature is determined to be less than or equal to 45 degrees Celsius, the audio acquisition component is not activated to collect audio data. If the engine coolant temperature is determined to be greater than 45 degrees Celsius, the audio acquisition component is activated to collect audio data.

[0095] d. If the speed is between 0 km / h and 10 km / h, the real-time engine coolant temperature is obtained. If the engine coolant temperature is determined to be greater than or equal to 45 degrees Celsius, the audio acquisition component is not activated to collect audio data. If the engine coolant temperature is determined to be less than or equal to 45 degrees Celsius, the audio acquisition component is activated to collect audio data.

[0096] e. Start the audio acquisition component to acquire audio data. When the duration of audio data acquisition is equal to the second duration, stop acquiring audio data.

[0097] By using the above method, audio data can be collected only when abnormal noises occur in the braking system. This selective collection of vehicle audio data ensures that as much audio data as possible is collected during the braking process, saving a lot of resources.

[0098] 202. The vehicle terminal uses audio data and a trained braking system anomaly recognition model to identify braking system anomalies in the vehicle and obtain the target braking system anomaly type.

[0099] The brake system anomaly identification model can include a feature extraction module and a classification module.

[0100] The vehicle-mounted terminal extracts audio features from the collected audio data. These features can be derived from MFCC parameters, and the extraction process may include pre-emphasis, windowing and framing, Fourier transform, filter bank filtering, logarithmic operations, and discrete cosine transform. The audio features are then input into a classification module, which outputs an anomaly type identifier and a no-anomaly identifier. The anomaly type identifier corresponds to the brake system's anomaly type, while the no-anomaly identifier corresponds to the brake system being functioning normally. The reason for outputting a no-anomaly identifier could be that the brake system is not making any abnormal noises, or that the brake system is making abnormal noises, but the cause is not due to a malfunction requiring repair or maintenance. It could be due to metal particles inside the brake pads or slippage between the brake pads and the brake disc.

[0101] For example, the identifier output by the trained brake system anomaly recognition model can be 0, 1, 2, or 3. 0 represents no anomaly, while 1, 2, and 3 represent the anomaly type. The cause of the abnormal noise in the vehicle could be at least one of the following: loose brake pad accessories, worn brake pads or discs, or malfunctioning caliper reset. 1, 2, and 3 represent the target brake system anomaly types: loose brake pad accessories, worn brake pads or discs, and malfunctioning caliper reset, respectively.

[0102] Different types of abnormal noises in a vehicle's braking system can be caused by different reasons and produce different sounds. Figure 3 The curves of the Mel frequency cepstral coefficients of brake noise under three types of brake system anomalies are shown, where different brake system anomalies correspond to different Mel frequency cepstral coefficient curves.

[0103] In addition to outputting an "no anomaly" label and an "anomaly type" label, the brake system anomaly identification model can also output a hazard level. For example, the hazard level can range from low to high as 0, 1, 2, and 3. The brake system anomaly identification model outputs an "anomaly type" label of 2 and a hazard level of 3. Alternatively, the brake system anomaly identification model outputs an "no anomaly type" label of 0 and a hazard level of 0.

[0104] 203. If the correspondence between brake system abnormality types and prompt information includes the target brake system abnormality type, then based on the correspondence, the vehicle terminal determines the target prompt information corresponding to the target brake system abnormality type.

[0105] A pre-established table mapping brake system malfunction types to warning messages is provided, as shown in Table 1.

[0106] Table 1

[0107] Braking system fault type identifier Prompt message 1 Message 1 2 Message 2 3 Message 3

[0108] For example, if the trained brake system anomaly recognition model outputs 0, indicating no anomaly identifier and the target prompt information cannot be determined, then no brake system anomaly prompt will be issued. If the trained brake system anomaly recognition model outputs 1, based on the above correspondence table, the brake system anomaly type is determined to be loose brake pad accessories, and the target prompt information is determined to be "Prompt Information One". The brake system anomaly prompt content is "Prompt Information One".

[0109] For situations involving hazard levels, a table can be pre-established to correspond to the types of brake system malfunctions, hazard levels, and warning messages, as shown in Table 2:

[0110] Table 2

[0111]

[0112] Different causes of abnormal noises in the braking system correspond to different types of braking system anomalies, and the same cause of abnormal noise in the braking system is assigned different hazard levels. Depending on the type of braking system anomaly, the target warning information can be the same or different. For a given cause of abnormal noise corresponding to a specific type of braking system anomaly, the target warning information is determined based on the hazard level. For example, if a trained braking system anomaly recognition model outputs anomaly type identifier 1 and a hazard level of 3, based on the above correspondence table, the brake system anomaly type is determined to be brake pad or brake disc wear, and the target warning information is determined to be "Warning Information Three," and the brake system anomaly warning content is "Warning Information Three."

[0113] 204. The vehicle terminal provides a braking system malfunction warning based on the target prompt information.

[0114] Brake system malfunction warnings can take the form of text prompts on display components, voice prompts through vehicle speakers, prompts on terminals such as mobile phones and wearable device apps, or prompts on after-sales management platforms.

[0115] This application also provides a method for training a braking system recognition model. See [link to relevant documentation]. Figure 4 The processing flow of this method may include the following steps:

[0116] 401. Obtain sample audio data collected during the braking process of the sample vehicle, wherein the sample vehicle is a vehicle with an abnormal braking system.

[0117] To obtain more sample audio data, audio data can be collected from after-sales vehicles with malfunctioning braking systems. For vehicles with malfunctioning braking systems, relevant personnel can drive the vehicle and, during the drive, ensure that the vehicle's condition meets the aforementioned audio collection conditions. Under these conditions, audio data is collected using an audio acquisition component to obtain the audio data that meets the audio collection conditions for the vehicle, which serves as sample audio data.

[0118] 402. Obtain the brake system anomaly type of the sample vehicle as the baseline brake system anomaly type for training.

[0119] For vehicles with abnormal braking systems, technicians can determine the root cause of the abnormal braking noise by inspecting the vehicle. Different causes of abnormal noise correspond to different types of braking system abnormalities. By determining the type of abnormality in the vehicle's braking system, the type of abnormality in the actual braking system of the vehicle whose sample audio data was collected is obtained. The obtained type of abnormality in the braking system is then used as the baseline type of abnormality in the braking system for training.

[0120] A training dataset can include a sample audio data point and a baseline braking system anomaly type. In this way, after acquiring a large amount of training data, these data points can be combined to form a training dataset.

[0121] 403. Input the sample audio data into the brake system anomaly recognition model to be trained to obtain the predicted brake system anomaly type.

[0122] The braking system anomaly recognition model to be trained can be divided into a feature extraction module and a classification module. Sample audio data is input into the feature extraction module to obtain sample audio features, and then these features are input into the classification module to obtain the predicted braking system anomaly type corresponding to the sample audio data.

[0123] 404. Based on the baseline brake system anomaly type and the predicted brake system anomaly type, the brake system anomaly identification model to be trained is trained and its parameters are adjusted to obtain the trained brake system anomaly identification model.

[0124] The training process can be iterative. The sample audio data from the first training dataset is input into the brake system anomaly recognition model to be trained to obtain the predicted brake system anomaly type. The predicted brake system anomaly type and the baseline brake system anomaly type are input into the loss function to obtain the loss value. The parameters in the brake system anomaly recognition model to be trained are adjusted according to the loss value.

[0125] Then, the model is trained again using the second training data, and the above training process is repeated until the training termination condition is met. The training termination condition can be reaching a specified number of training iterations, or the loss value in N consecutive training iterations being less than a loss value threshold, or the verification model accuracy exceeding an accuracy threshold, etc. The braking system anomaly recognition model obtained at this point is determined as the trained braking system anomaly recognition model.

[0126] For example, 100,000 training data points can be selected from the training dataset and sequentially input into the brake system anomaly detection model to be trained, resulting in a trained brake system anomaly detection model. Then, 20 new training data points are selected from the training dataset and input into this model. These 20 new training data points are not the same as the previously used training data. If the predicted brake system anomaly type identified by these 20 training data points matches the baseline brake system anomaly type, the model is considered reliable. If at least one training data point corresponds to a different predicted brake system anomaly type than the baseline, the model is considered unreliable. In this case, another 100,000 training data points are selected from the training dataset to train the model, and then another 20 training data points are selected to assess its reliability. This process is repeated until all 20 selected training data points correspond to the same predicted brake system anomaly type as the baseline, at which point the model is considered reliable.

[0127] This application also provides a detection method for detecting brake system anomalies using a system for brake system anomaly detection. See [link to relevant documentation]. Figure 5 The method may include the following steps:

[0128] 501. When a braking event is detected, the vehicle terminal collects audio data through the audio acquisition component.

[0129] For the corresponding processing, please refer to the relevant instructions in step 201.

[0130] 502, The vehicle terminal sends audio data to the server.

[0131] 503. The server uses audio data and a trained brake system anomaly recognition model to identify brake system anomalies in the vehicle and obtain the target brake system anomaly type. If the target brake system anomaly type is included in the correspondence between brake system anomaly types and prompt information, the target prompt information corresponding to the target brake system anomaly type is determined based on the correspondence.

[0132] The processing of the server is similar to that of the vehicle terminal; please refer to the relevant instructions for steps 202 and 203.

[0133] 504, the server sends a target prompt message to the vehicle terminal.

[0134] 505, the vehicle terminal issues a braking system malfunction warning based on the target prompt information.

[0135] For the corresponding processing, please refer to the relevant instructions in steps 202 and 204.

[0136] Figure 6 This application provides a schematic diagram of a system for detecting abnormalities in a braking system, the system comprising:

[0137] The vehicle terminal 601 is used to collect audio data through an audio acquisition component and send the audio data to a server when a braking event is detected.

[0138] Server 602 is used to identify brake system anomalies in a vehicle based on the audio data and a trained brake system anomaly identification model, obtain the target brake system anomaly type of the vehicle, and if the target brake system anomaly type is included in the correspondence between brake system anomaly types and prompt information, then based on the correspondence, determine the target prompt information corresponding to the target brake system anomaly type and send the target prompt information to the vehicle terminal.

[0139] The vehicle-mounted terminal 601 is used to provide a braking system malfunction warning based on the target prompt information.

[0140] In one possible implementation, the vehicle terminal 601 is used for:

[0141] When it is detected that the brake pedal of the vehicle is pressed and the pressing time reaches the first duration, if the travel of the brake pedal, the driving speed of the vehicle and the engine water tank temperature of the vehicle meet the audio acquisition conditions, then audio data is acquired through the audio acquisition component.

[0142] In one possible implementation, the vehicle terminal 601 is used for:

[0143] If the proportion of the brake pedal travel to the total travel is greater than 0 and less than the proportion threshold, the vehicle's speed is within a first speed range, and the vehicle's engine coolant temperature is greater than a temperature threshold; or, if the proportion of the brake pedal travel to the total travel is greater than 0 and less than the proportion threshold, the vehicle's speed is within a second speed range, and the vehicle's engine coolant temperature is less than the temperature threshold, then audio data is collected through the audio acquisition component, wherein the speed in the first speed range is greater than that in the second speed range.

[0144] In one possible implementation, the first duration is 500ms, the ratio threshold is 60%, the first speed range is 10km / h to 40km / h, the second speed range is 0km / h to 10km / h, and the temperature threshold is 45 degrees Celsius.

[0145] In one possible implementation, the vehicle terminal 601 is used to: acquire audio data of a second duration via an audio acquisition component.

[0146] In one possible implementation, the target braking system malfunction type includes at least one of the following: loose brake pad accessories, worn brake pads or brake discs, and malfunctioning caliper reset.

[0147] In one possible implementation, the server 602 is further configured to:

[0148] Acquire sample audio data collected during the braking process of a sample vehicle, wherein the sample vehicle is a vehicle with an abnormal braking system;

[0149] Obtain the braking system anomaly type of the sample vehicle as the benchmark braking system anomaly type for training;

[0150] The sample audio data is input into the brake system anomaly recognition model to be trained to obtain the predicted brake system anomaly type;

[0151] Based on the baseline braking system anomaly type and the predicted braking system anomaly type, the braking system anomaly identification model to be trained is trained and its parameters are adjusted to obtain the trained braking system anomaly identification model.

[0152] Figure 7 This application provides a device for detecting brake system anomalies. This device can be the vehicle-mounted terminal described in the above embodiments. The device includes:

[0153] Acquisition module 701 is used to acquire audio data through audio acquisition component when a braking event is detected;

[0154] The identification module 702 is used to identify brake system anomalies in the vehicle based on the audio data and the trained brake system anomaly identification model, and to obtain the target brake system anomaly type of the vehicle.

[0155] The determining module 703 is used to determine the target prompt information corresponding to the target brake system abnormality type based on the correspondence if the target brake system abnormality type is included in the correspondence between brake system abnormality types and prompt information.

[0156] The prompting module 704 is used to provide a brake system malfunction prompt based on the target prompting information.

[0157] In one possible implementation, the acquisition module 701 is used for:

[0158] When it is detected that the brake pedal of the vehicle is pressed and the pressing time reaches the first duration, if the travel of the brake pedal, the driving speed of the vehicle and the engine water tank temperature of the vehicle meet the audio acquisition conditions, then audio data is acquired through the audio acquisition component.

[0159] In one possible implementation, the acquisition module 701 is used for:

[0160] If the proportion of the brake pedal travel to the total travel is greater than 0 and less than the proportion threshold, the vehicle's speed is within a first speed range, and the vehicle's engine coolant temperature is greater than a temperature threshold; or, if the proportion of the brake pedal travel to the total travel is greater than 0 and less than the proportion threshold, the vehicle's speed is within a second speed range, and the vehicle's engine coolant temperature is less than the temperature threshold, then audio data is collected through the audio acquisition component, wherein the speed in the first speed range is greater than that in the second speed range.

[0161] In one possible implementation, the first duration is 500ms, the ratio threshold is 60%, the first speed range is 10km / h to 40km / h, the second speed range is 0km / h to 10km / h, and the temperature threshold is 45 degrees Celsius.

[0162] In one possible implementation, the acquisition module 701 is used to: acquire audio data of a second duration via an audio acquisition component.

[0163] In one possible implementation, the target braking system malfunction type includes at least one of the following: loose brake pad accessories, worn brake pads or brake discs, and malfunctioning caliper reset.

[0164] In one possible implementation, the device further includes:

[0165] Training module 705 is used to acquire sample audio data collected during the braking process of a sample vehicle, wherein the sample vehicle is a vehicle with an abnormal braking system; acquire the braking system abnormality type of the sample vehicle as a baseline braking system abnormality type for training; input the sample audio data into the braking system abnormality recognition model to be trained to obtain a predicted braking system abnormality type; and train and tune the braking system abnormality recognition model to be trained based on the baseline braking system abnormality type and the predicted braking system abnormality type to obtain a trained braking system abnormality recognition model.

[0166] In this embodiment, when the vehicle's brake pedal is lightly pressed, the audio acquisition component collects the sound emitted by the vehicle. The collected audio data is then input into the brake system anomaly identification model for data analysis to determine the cause of the abnormal braking noise. Different causes of abnormal noise correspond to different brake system anomaly types. For each type of brake system anomaly, a corresponding target prompt message is determined and a brake system anomaly warning is issued. This method enables timely identification of brake system malfunctions, prompting personnel to address related issues promptly, thereby effectively reducing the likelihood of accidents and improving driving safety.

[0167] It should be noted that the brake system anomaly detection device provided in the above embodiments is only illustrated by the division of the above functional modules when performing brake system anomaly detection. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the brake system anomaly detection device and the brake system anomaly detection method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0168] Figure 8 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. The computer device can be the vehicle-mounted terminal described in the above embodiments. The computer device 800 can vary significantly due to differences in configuration or performance, and may include one or more central processing units (CPUs) 801 and one or more memories 802. The memory 802 stores at least one instruction, which is loaded and executed by the processor 801 to implement the methods provided in the various method embodiments described above. Of course, the computer device may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The computer device may also include other components for implementing device functions, which will not be elaborated upon here.

[0169] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including instructions that can be executed by a processor in a terminal to complete the method for detecting brake system anomalies in the above embodiments. This computer-readable storage medium can be non-transitory. For example, the computer-readable storage medium can be ROM (read-only memory), RAM (random access memory), CD-ROM, magnetic tape, floppy disk, and optical data storage devices, etc.

[0170] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware, or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0171] The above are merely optional embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for detecting abnormalities in a braking system, characterized in that, The method includes: When it is detected that the vehicle's brake pedal is pressed and the pressing time reaches a first duration, if the proportion of the brake pedal travel to the total travel is greater than 0 and less than a proportional threshold, the vehicle's speed is within a first speed range, and the vehicle's engine coolant temperature is greater than a temperature threshold, or if the proportion of the brake pedal travel to the total travel is greater than 0 and less than a proportional threshold, the vehicle's speed is within a second speed range, and the vehicle's engine coolant temperature is less than the temperature threshold, then audio data is collected through the audio acquisition component, wherein the speed in the first speed range is greater than that in the second speed range. Based on the audio data and the trained brake system anomaly identification model, brake system anomalies of the vehicle are identified to obtain the target brake system anomaly type of the vehicle. If the target brake system abnormality type is included in the correspondence between brake system abnormality types and warning information, then based on the correspondence, the target warning information corresponding to the target brake system abnormality type is determined. The brake system abnormality type is at least one of the following: loose brake pad accessories, worn brake pads or brake discs, or faulty caliper reset. Based on the target prompt information, a brake system malfunction warning is issued.

2. The method according to claim 1, characterized in that, The first duration is 500ms, the ratio threshold is 60%, the first speed range is 10km / h to 40km / h, the second speed range is 0km / h to 10km / h, and the temperature threshold is 45 degrees Celsius.

3. The method according to any one of claims 1-2, characterized in that, The acquisition of audio data via the audio acquisition component includes: The second duration of audio data is acquired through an audio acquisition component.

4. The method according to any one of claims 1-2, characterized in that, The method further includes: Acquire sample audio data collected during the braking process of a sample vehicle, wherein the sample vehicle is a vehicle with an abnormal braking system; Obtain the braking system anomaly type of the sample vehicle as the benchmark braking system anomaly type for training; The sample audio data is input into the brake system anomaly recognition model to be trained to obtain the predicted brake system anomaly type; Based on the baseline braking system anomaly type and the predicted braking system anomaly type, the braking system anomaly identification model to be trained is trained and its parameters are adjusted to obtain the trained braking system anomaly identification model.

5. A system for detecting abnormalities in a braking system, characterized in that, The system includes: The vehicle terminal is configured to collect audio data via an audio acquisition component when it detects that the brake pedal of a vehicle has been pressed for a duration of a first duration, and if the proportion of the brake pedal travel to the total travel is greater than 0 and less than a proportional threshold, the vehicle's speed is within a first speed range, and the vehicle's engine coolant temperature is greater than a temperature threshold; or, the proportion of the brake pedal travel to the total travel is greater than 0 and less than a proportional threshold, the vehicle's speed is within a second speed range, and the vehicle's engine coolant temperature is less than the temperature threshold. The server is used to identify brake system anomalies in the vehicle based on the audio data and a trained brake system anomaly identification model, to obtain the target brake system anomaly type of the vehicle, and if the target brake system anomaly type is included in the correspondence between brake system anomaly types and prompt information, then based on the correspondence, the server determines the target prompt information corresponding to the target brake system anomaly type and sends the target prompt information to the vehicle terminal. The brake system anomaly type is at least one of the following: loose brake pad accessories, worn brake pads or brake discs, and poor caliper reset. The vehicle-mounted terminal is used to provide a braking system malfunction warning based on the target prompt information.

6. A device for detecting abnormalities in a braking system, characterized in that, The device includes: The acquisition module is used to acquire audio data through an audio acquisition component when it detects that the brake pedal of a vehicle has been pressed and the pressing time has reached a first duration. If the proportion of the brake pedal travel to the total travel is greater than 0 and less than a proportional threshold, the vehicle's speed is within a first speed range, and the vehicle's engine coolant temperature is greater than a temperature threshold, or the proportion of the brake pedal travel to the total travel is greater than 0 and less than a proportional threshold, the vehicle's speed is within a second speed range, and the vehicle's engine coolant temperature is less than the temperature threshold, the speed in the first speed range is greater than that in the second speed range. The identification module is used to identify brake system anomalies in the vehicle based on the audio data and the trained brake system anomaly identification model, and to obtain the target brake system anomaly type of the vehicle. The determination module is used to determine the target prompt information corresponding to the target brake system abnormality type based on the correspondence between the target brake system abnormality type and the prompt information if the target brake system abnormality type is included in the correspondence between the brake system abnormality type and the prompt information. The brake system abnormality type is at least one of the following: loose brake pad accessories, worn brake pads or brake discs, and poor caliper reset. The prompting module is used to provide a braking system malfunction prompt based on the target prompting information.

7. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing at least one instruction, which is loaded and executed by the processor to perform the operation of the method for detecting brake system anomalies as described in any one of claims 1 to 2.

Images