Brake pad service life prediction and early warning system and method based on driving behaviors

Abstract

The invention discloses a brake pad life prediction and early warning system and method based on driving behaviors, and relates to the field of safety monitoring, and the method comprises the steps: S1, collecting multi-dimensional original data through a vehicle end burying point and a vehicle-mounted sensor; the multi-dimensional original data comprises driving behavior related data and environment data; s2, performing preprocessing and feature extraction on the multi-dimensional original data to generate a driving behavior feature vector; s3, establishing a driving behavior feature model based on the driving behavior feature vector, calculating a driving behavior score and generating a driving habit file; s4, based on a material mechanics principle and a statistical method, in combination with a driving behavior characteristic model output result, brake contact pressure, relative sliding speed, environment temperature and vehicle mass, establishing a wear prediction model, and calculating accumulated wear loss, wear rate and residual life; and S5, comparing the residual life with a preset threshold value, determining an early warning level in combination with the behavior tolerance, and generating early warning information.

Description

Technical Field

[0001] This application relates to the field of safety monitoring, and in particular to a brake pad life prediction and early warning system based on driving behavior, a brake pad life prediction and early warning method based on driving behavior, electronic equipment, storage media, and vehicle monitoring platform. Background Technology

[0002] With the rapid development of the automotive industry and the continuous advancement of intelligent connected vehicle technology, vehicle safety monitoring systems have become an important component of modern automobiles. In the vehicle braking system, brake pads, as a critical safety component, directly affect driving safety. Traditional brake pad maintenance methods mainly rely on periodic inspections or replacement strategies based on fixed mileage intervals.

[0003] Currently, the main brake pad monitoring solutions in existing technologies include the following:

[0004] Mechanical wear indicator: A metal plate is installed on the brake pads. When the brake pads wear down to a certain extent, the metal plate contacts the brake disc and produces an abnormal noise, reminding the user to replace the brake pads.

[0005] Electronic wear sensor: The electronic sensor installed on the brake pads monitors the brake pad thickness in real time and transmits the data to the vehicle system.

[0006] Mileage-based prediction method: reminds users to replace brake pads based on vehicle mileage and manufacturer-recommended replacement intervals.

[0007] Although existing technologies can monitor brake pad condition to some extent, the following significant problems still exist:

[0008] 1. Low prediction accuracy: Traditional prediction methods based on fixed mileage ignore individual differences in driving behavior. Different drivers' driving habits (such as frequency of emergency braking, braking intensity, etc.) have a significant impact on brake pad wear, and using a uniform standard can easily lead to over-maintenance or under-maintenance.

[0009] 2. Poor real-time performance: Mechanical indicators can only issue a warning when the brake pads are worn to their limit, lacking early warning function and unable to inform users of maintenance needs in advance.

[0010] 3. High cost: Electronic sensor solutions require the installation of a dedicated sensor on each brake pad, which increases system cost and complexity, and the sensors themselves may have reliability issues.

[0011] 4. Lack of personalization: The existing solution does not fully consider personalized factors such as vehicle usage environment and driving habits, and cannot provide customized maintenance suggestions for different users.

[0012] 5. Passive response: Existing technologies mostly adopt passive monitoring methods, which cannot actively predict the remaining life of brake pads, making it difficult for users to arrange maintenance plans in advance.

[0013] The root cause of the above problems is that existing technologies have failed to establish a quantitative relationship model between driving behavior and brake pad wear, and lack a systematic analysis of the combined effects of multiple factors. Summary of the Invention

[0014] The purpose of this invention is to provide a brake pad life prediction and early warning system based on driving behavior, which solves at least one of several technical problems.

[0015] The current technology suffers from several drawbacks. First, it lacks predictive accuracy. Traditional fixed-mileage-based solutions ignore individual differences in driving behavior, leading to over- or under-maintenance. Second, it has poor real-time performance. Mechanical indicators only alert when wear reaches its limit, lacking early warning capabilities. Third, it is costly. Electronic sensor solutions require additional specialized equipment, increasing system complexity and reliability risks. Fourth, it lacks personalization, failing to adequately consider driving habits and usage environments, thus unable to provide customized maintenance recommendations. Fifth, it is reactive, unable to proactively predict remaining lifespan, preventing users from planning maintenance in advance. The root cause is the absence of a quantitative model establishing the relationship between driving behavior and brake pad wear, and a lack of systematic analysis of the combined effects of multiple factors.

[0016] This invention provides the following solution:

[0017] According to a first aspect of the present invention, a brake pad life prediction and early warning system based on driving behavior is provided, comprising: a vehicle-side data acquisition unit, a cloud processing unit, and an early warning output unit;

[0018] The vehicle-mounted data acquisition unit is connected to the cloud processing unit, and the cloud processing unit is connected to the early warning output unit.

[0019] in,

[0020] The vehicle-mounted data acquisition unit includes a data acquisition module;

[0021] The data acquisition module is used to collect multi-dimensional data during vehicle operation based on vehicle-mounted points and onboard sensors.

[0022] Multidimensional data includes driving behavior data and environmental data;

[0023] The cloud processing unit includes a driving behavior analysis module and a wear prediction module;

[0024] The driving behavior analysis module is used to preprocess multi-dimensional data, extract features, and then build a driving behavior feature model and driving habit profile.

[0025] The wear prediction module is used to establish a brake pad wear prediction model based on the principles of materials mechanics and statistical methods, combined with the output results of the driving behavior characteristic model, to calculate the cumulative wear amount, wear rate and remaining life of the brake pads.

[0026] The early warning output unit includes an early warning module;

[0027] The warning module compares the remaining lifespan of the brake pads with a preset threshold for brake pad lifespan. When the remaining lifespan of the brake pads is lower than the preset threshold, a warning message is sent to the user.

[0028] Furthermore, including:

[0029] Driving behavior data includes at least one of the following: braking frequency, braking intensity, braking distance, vehicle speed change rate, emergency braking frequency, downhill time percentage, frequency of driving on serpentine roads, vehicle load factor, number of frequent starts and stops, and braking frequency on continuous downhill sections.

[0030] Furthermore, including:

[0031] Environmental data includes ambient temperature and the percentage of driving time at night / in rainy / foggy weather;

[0032] The percentage of driving time at night / in rainy / foggy weather was obtained by combining timestamps, weather API data, and vehicle light status.

[0033] Furthermore, including:

[0034] The vehicle-mounted sensors include at least one of the following: brake pedal position sensor, vehicle speed sensor, acceleration sensor, pressure sensor, vehicle load sensor, and GPS module.

[0035] Furthermore, including:

[0036] The feature extraction process of the driving behavior analysis module includes:

[0037] Define driving behavior feature vector ;

[0038] in, For average braking intensity, For emergency braking frequency, The average braking distance The average braking time The percentage of downhill high-speed driving time, Number of high-speed trips on serpentine road sections For vehicle load factor, For frequent start-stop times, For continuous downhill sections, the frequency of braking use, The percentage of driving at night / in rainy / foggy weather.

[0039] Furthermore, including:

[0040] The driving behavior analysis module is also used to calculate a driving behavior score (0~1 points) based on feature vectors, and to classify driving style types according to the driving behavior score, generating a driving habit profile.

[0041] Furthermore, including:

[0042] The input parameters for the wear prediction model include driving behavior feature vectors. Braking contact pressure Relative sliding speed Ambient temperature and vehicle quality ;

[0043] The output parameter is time. Cumulative wear and tear over time The cumulative wear amount is expressed by a continuous formula. calculate;

[0044] in This refers to any moment during the braking process.

[0045] Furthermore, including:

[0046] Introducing a dynamic wear coefficient into the wear prediction model ;

[0047] Dynamic wear coefficient ,in The basic wear coefficient under standard conditions (laboratory calibration). This is a temperature correction function (reflecting the material softening characteristics at high temperatures). This is the load correction function (which is linearly related to the vehicle mass).

[0048] Furthermore, including:

[0049] Wear prediction module calculates remaining lifespan The formula is ;

[0050] in,

[0051] Total brake pad thickness (design value, unit: mm). The current worn thickness (unit: mm). Current wear rate (unit: mm / h);

[0052] Wear rates include: ;

[0053] in, , , These are the weighting coefficients calibrated in the experiment. Scoring driving behavior Environmental factors (0~1). Use frequency factor (0~1).

[0054] Furthermore, including:

[0055] The wear prediction module is also used to predict wear based on remaining lifespan. Determine the tolerance level for the behavior;

[0056] Behavioral tolerance is the upper limit of specific driving behaviors that brake pads can withstand under the current wear condition;

[0057] Among them, the remaining lifespan is determined based on the wear and tear of the brake pads under braking conditions. Converted into the number of times of emergency braking can be tolerated, the duration of continuous downhill driving can be tolerated, and / or the risk value of failure during high-speed serpentine driving;

[0058] Based on historical data on failures during high-speed serpentine driving, a preset threshold for failure risk is set.

[0059] Furthermore, including:

[0060] The early warning module adopts a tiered early warning strategy, which includes:

[0061] Level 1: It can withstand ≤1 emergency braking incident;

[0062] Level 2: It can withstand continuous downhill driving for ≤3 minutes;

[0063] Level 3: Furthermore, the failure risk value of high-speed serpentine driving is greater than the preset failure risk threshold.

[0064] Furthermore, including:

[0065] The warning information includes the remaining lifespan percentage, behavior tolerance level alerts, and customized maintenance recommendations;

[0066] Customized maintenance recommendations are generated based on driving habit profiles.

[0067] Furthermore, including:

[0068] The architecture of the cloud processing unit includes a data processing layer, a behavior analysis layer, a prediction model layer, and an early warning service layer.

[0069] The data processing layer is used to clean, extract features, fuse data, and detect anomalies in the collected raw data.

[0070] The behavior analysis layer is used to build driving behavior models based on feature data.

[0071] The predictive model layer is used to calculate the wear rate and remaining life;

[0072] The early warning service layer is used to generate early warning information and send it to the early warning output unit.

[0073] According to a second aspect of the present invention, a method for predicting and warning brake pad life based on driving behavior is provided, comprising:

[0074] S1: Collect multi-dimensional raw data through vehicle-mounted points and vehicle sensors;

[0075] The multi-dimensional raw data includes driving behavior-related data and environmental data;

[0076] S2: Preprocess and extract features from the multi-dimensional raw data to generate driving behavior feature vectors. ;

[0077] S3: Establish a driving behavior feature model based on driving behavior feature vectors, calculate driving behavior scores and generate driving habit profiles;

[0078] S4: Based on the principles of materials mechanics and statistical methods, combined with the output results of the driving behavior characteristic model and brake contact pressure. Relative sliding speed Ambient temperature and vehicle quality Establish a wear prediction model and calculate the cumulative wear amount. Wear rate and remaining lifespan ;

[0079] S5: Remaining lifespan Compared with a preset threshold, the warning level is determined by combining the behavior tolerance, and a warning message including customized maintenance suggestions is generated and pushed to the user.

[0080] Furthermore, including:

[0081] The driving behavior-related data in step S1 is obtained through at least one of the following methods: brake pressure signal, mileage and speed signal, GPS + vehicle speed data, brake switch status + timestamp, map matching + vehicle speed trajectory analysis, and gear shifting + vehicle speed change judgment.

[0082] Furthermore, including:

[0083] In step S4, the cumulative wear amount is obtained through a discretization formula. calculate;

[0084] in, The dynamic wear coefficient, The average braking force during the first braking action (unit: N). The braking distance for the nth braking action (unit: m). The duration of the first braking action (in seconds). This represents the number of braking events within the statistical period.

[0085] Furthermore, including:

[0086] In step S4, the behavior tolerance is at least one of the following: the maximum number of emergency braking cycles that the brake pads can withstand under the current wear condition, the maximum duration of continuous downhill driving, and driving restrictions on specific road sections.

[0087] Among them, the remaining lifespan is determined based on the wear and tear of the brake pads under braking conditions. Converted into the number of times of emergency braking can be tolerated, the duration of continuous downhill driving can be tolerated, and / or the risk value of failure during high-speed serpentine driving;

[0088] Based on historical data on failures during high-speed serpentine driving, a preset threshold for failure risk is set.

[0089] Furthermore, including:

[0090] In step S5, the warning levels include three levels: Level_1, Level_2, and Level_3. Different levels correspond to different remaining lifespan thresholds and behavioral risk thresholds.

[0091] Furthermore, including:

[0092] The vehicle-mounted sensors include at least one of the following: brake pedal position sensor, vehicle speed sensor, acceleration sensor, pressure sensor, vehicle load sensor, and GPS module.

[0093] Furthermore, including:

[0094] Customized maintenance recommendations are generated based on driving habit profiles, which include driving style type, braking behavior preferences, and characteristics of frequently traveled road sections.

[0095] According to a third aspect of the present invention, an electronic device is provided, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0096] The memory stores a computer program that, when executed by a processor, causes the processor to perform steps such as a brake pad life prediction and warning method based on driving behavior.

[0097] According to a fourth aspect of the present invention, a computer-readable storage medium is provided storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform steps such as a brake pad life prediction and warning method based on driving behavior.

[0098] According to a fifth aspect of the present invention, a vehicle monitoring platform is provided, comprising:

[0099] Electronic devices for implementing steps such as brake pad life prediction and early warning methods based on driving behavior;

[0100] The processor runs programs, and when the programs are running, they execute steps such as brake pad life prediction and warning methods based on driving behavior, based on data output from electronic devices.

[0101] Storage medium for storing programs that, when running, perform steps such as a brake pad life prediction and warning method based on driving behavior, based on data output from electronic devices.

[0102] The above solution achieves the following beneficial technical effects:

[0103] This application collects multi-dimensional data such as driving behavior, environmental conditions, and vehicle status, and combines materials mechanics and statistics to construct a wear prediction model. It accurately captures individual driving differences and the influence of multiple factors, avoids prediction bias caused by uniform standards, and significantly improves prediction accuracy.

[0104] This application achieves real-time proactive warning by monitoring the condition of brake pads in real time and sending early warnings in advance through a graded warning strategy, thereby avoiding safety hazards when the wear limit is reached and overcoming the drawbacks of passive response in traditional technologies.

[0105] This application simplifies the system structure and reduces hardware and maintenance costs by reusing existing vehicle-mounted sensors (such as brake pedal position sensors and vehicle speed sensors), eliminating the need for additional dedicated equipment and significantly reducing system costs.

[0106] This application establishes user habit profiles based on driving behavior characteristics, generates customized maintenance suggestions, adapts to different driving styles and driving scenarios, improves user experience, and provides personalized services.

[0107] This application helps users rationally plan maintenance by accurately predicting the remaining lifespan of brake pads (including time and behavior tolerance dimensions), reducing unnecessary downtime and maintenance costs, and supporting scientific and proactive maintenance. Attached Figure Description

[0108] Figure 1 This is a flowchart of a brake pad life prediction and early warning method based on driving behavior, provided by one or more embodiments of the present invention.

[0109] Figure 2 This is a structural diagram of a brake pad life prediction and early warning system based on driving behavior, provided by one or more embodiments of the present invention.

[0110] Figure 3 This is a schematic diagram of the overall architecture combining cloud services and vehicle-side applications provided in a specific embodiment of the present invention.

[0111] Figure 4 This is a schematic diagram of an algorithm for calculating brake life and providing early warning under an overall architecture that combines cloud services and vehicle-side applications, provided by a specific embodiment of the present invention.

[0112] Figure 5 This is a block diagram of an electronic device for predicting and warning the life of brake pads based on driving behavior, provided by one or more embodiments of the present invention. Detailed Implementation

[0113] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0114] Figure 2 This is a structural diagram of a brake pad life prediction and early warning system based on driving behavior, provided by one or more embodiments of the present invention.

[0115] like Figure 2 The brake pad life prediction and early warning system based on driving behavior shown includes: a vehicle-side data acquisition unit, a cloud processing unit, and an early warning output unit;

[0116] The vehicle-mounted data acquisition unit is connected to the cloud processing unit, and the cloud processing unit is connected to the early warning output unit.

[0117] in,

[0118] The vehicle-mounted data acquisition unit includes a data acquisition module;

[0119] The data acquisition module is used to collect multi-dimensional data during vehicle operation based on vehicle-mounted points and onboard sensors.

[0120] Multidimensional data includes driving behavior data and environmental data;

[0121] The cloud processing unit includes a driving behavior analysis module and a wear prediction module;

[0122] The driving behavior analysis module is used to preprocess multi-dimensional data, extract features, and then build a driving behavior feature model and driving habit profile.

[0123] The wear prediction module is used to establish a brake pad wear prediction model based on the principles of materials mechanics and statistical methods, combined with the output results of the driving behavior characteristic model, to calculate the cumulative wear amount, wear rate and remaining life of the brake pads.

[0124] The early warning output unit includes an early warning module;

[0125] The warning module compares the remaining lifespan of the brake pads with a preset threshold for brake pad lifespan. When the remaining lifespan of the brake pads is lower than the preset threshold, a warning message is sent to the user.

[0126] Specifically, this application employs a collaborative architecture of vehicle-side data collection, cloud-based processing, and early warning output, along with a predictive model that integrates multi-dimensional data collection, driving behavior analysis, materials mechanics, and statistics. The technical problems addressed include: existing solutions are mostly passive monitoring, unable to proactively predict brake pad lifespan, making it difficult for users to plan maintenance in advance; ignoring individual differences in driving behavior and using only a uniform standard for prediction results in low accuracy, easily leading to over-maintenance or under-maintenance; and lacking a personalized early warning mechanism, failing to adapt to the needs of different users. The resulting technical effects are: proactive prediction of brake pad lifespan, supporting users in planning maintenance in advance and avoiding unexpected safety hazards; significantly improving the accuracy of lifespan prediction by constructing a predictive model based on comprehensive multi-dimensional data, effectively avoiding over-maintenance or under-maintenance; and providing solid system architecture support for subsequent personalized early warning services, laying the foundation for customized services.

[0127] In this embodiment, it includes:

[0128] Driving behavior data includes at least one of the following: braking frequency, braking intensity, braking distance, vehicle speed change rate, emergency braking frequency, downhill time percentage, frequency of driving on serpentine roads, vehicle load factor, number of frequent starts and stops, and braking frequency on continuous downhill sections.

[0129] Specifically, the technical features in this embodiment address the following existing technical problems: Existing technologies do not sufficiently collect key driving behavior data affecting brake pad wear, resulting in a lack of effective input for prediction models and an inability to fully reflect the impact of driving habits on wear; they also ignore individual differences in driving habits, relying only on single or a few parameters for prediction, leading to low prediction accuracy. The resulting technical effects are: comprehensive coverage of various driving behavior factors affecting brake pad wear, providing a rich and comprehensive data foundation for driving behavior analysis and wear prediction models; and highlighting individual differences in driving behavior among different drivers, making the prediction model more targeted and further improving the accuracy of lifespan prediction.

[0130] In this embodiment, it includes:

[0131] Environmental data includes ambient temperature and the percentage of driving time at night / in rainy / foggy weather;

[0132] The percentage of driving time at night / in rainy / foggy weather was obtained by combining timestamps, weather API data, and vehicle light status.

[0133] Specifically, the technical features in this embodiment address the following existing technical problems: Existing technologies generally ignore the impact of environmental factors on brake pad wear, leading to deviations between predicted results and actual operating conditions, resulting in low accuracy; driving data under adverse weather conditions is difficult to collect accurately, resulting in poor generalization ability of the prediction model and its inability to adapt to complex climatic conditions. The corresponding technical effects are: incorporating environmental variables into the prediction system, correcting prediction results through environmental data, enabling the model to adapt to usage scenarios in different climatic zones; achieving accurate collection of driving data in adverse weather conditions, effectively improving the adaptability of the prediction model to complex operating conditions, and enhancing the model's generalization ability.

[0134] In this embodiment, it includes:

[0135] The vehicle-mounted sensors include at least one of the following: brake pedal position sensor, vehicle speed sensor, acceleration sensor, pressure sensor, vehicle load sensor, and GPS module.

[0136] Specifically, the technical features in this embodiment address the following existing technical problems: Existing technologies rely on dedicated sensors to monitor brake pad status, resulting in high system costs and structural complexity, which is unfavorable for large-scale applications; sensor selection lacks specificity, and some solutions use sensors with insufficient stability, leading to poor data acquisition reliability. The corresponding technical benefits are: reusing existing vehicle sensors eliminates the need for additional dedicated equipment, significantly reducing system hardware costs and deployment complexity; based on a mature vehicle-mounted sensor system, the stability and reliability of data acquisition are guaranteed, providing high-quality data support for subsequent analysis and prediction.

[0137] In this embodiment, it includes:

[0138] The feature extraction process of the driving behavior analysis module includes:

[0139] Define driving behavior feature vector ;

[0140] in, For average braking intensity, For emergency braking frequency, The average braking distance The average braking time The percentage of downhill high-speed driving time, Number of high-speed trips on serpentine road sections For vehicle load factor, For frequent start-stop times, For continuous downhill sections, the frequency of braking use, The percentage of driving at night / in rainy / foggy weather.

[0141] Specifically, the technical features in this embodiment address the following existing technical problems: Existing technologies lack a systematic analysis of multiple factors affecting brake pad wear and have not established a comprehensive driving behavior feature system, leading to one-sided considerations in prediction models; the feature dimensions are singular, failing to fully reflect the combined impact of driving behavior, road environment, and other factors on wear, resulting in insufficient scientific rigor in prediction. The corresponding technical effects are: a multi-dimensional, comprehensive driving behavior feature system is constructed, capable of comprehensively capturing key factors affecting brake pad wear and supporting personalized lifespan prediction; comprehensive and accurate input parameters are provided for the wear prediction model, making the prediction model more scientific and reasonable, and further improving prediction accuracy.

[0142] In this embodiment, it includes:

[0143] The driving behavior analysis module is also used to calculate a driving behavior score (0~1 points) based on feature vectors, and to classify driving style types according to the driving behavior score, generating a driving habit profile.

[0144] Specifically, the technical features in this embodiment address the following existing technical problems: Existing technologies do not quantify differences in driving behavior, making it impossible to accurately distinguish the impact of different drivers' driving habits on brake pad wear, thus hindering the provision of customized services; the lack of systematic recording of driving habits results in a lack of data basis for personalized warnings and maintenance suggestions. The corresponding technical effects are: by quantifying driving behavior characteristics through driving behavior scoring, the impact of different drivers' driving habits on brake pad wear is clarified, providing quantitative support for accurate prediction; the generated driving habit profile provides direct data basis for customized maintenance suggestions, enabling targeted satisfaction of different users' needs and improving user experience.

[0145] In this embodiment, it includes:

[0146] The input parameters for the wear prediction model include driving behavior feature vectors. Braking contact pressure Relative sliding speed Ambient temperature and vehicle quality ;

[0147] The output parameter is time. Cumulative wear and tear over time The cumulative wear amount is expressed by a continuous formula. calculate;

[0148] in This refers to any moment during the braking process.

[0149] Specifically, the technical features in this embodiment address the following existing technical problems: Existing technologies lack a quantitative relationship between driving behavior and brake pad wear, relying solely on experience or simple statistics for prediction, resulting in low accuracy; wear calculations lack support from materials mechanics theory, are insufficiently scientific, and cannot accurately reflect actual wear patterns. The resulting technical effects are: A quantitative prediction model is constructed based on the principles of materials mechanics, enabling precise calculation of wear amounts and making the prediction results more consistent with actual wear patterns; by integrating multi-dimensional input parameters, the influence of driving behavior, environment, and vehicle condition on wear is comprehensively considered, further improving the accuracy and reliability of the prediction results.

[0150] In this embodiment, it includes:

[0151] Introducing a dynamic wear coefficient into the wear prediction model ;

[0152] Dynamic wear coefficient ,in The basic wear coefficient under standard conditions (laboratory calibration). This is a temperature correction function (reflecting the material softening characteristics at high temperatures). This is the load correction function (which is linearly related to the vehicle mass).

[0153] Specifically, the technical features in this embodiment address the following existing technical problems: Existing technologies use a fixed wear coefficient to calculate brake pad wear, neglecting the influence of factors such as ambient temperature and vehicle weight on the wear coefficient, leading to significant prediction deviations; the model cannot adapt to different climate zones and vehicle types, exhibiting poor generalization ability. The resulting technical benefits are: by dynamically adjusting the wear coefficient through temperature and load correction functions, the model can adapt to different climatic conditions such as high altitudes and extreme cold, improving its adaptability to environmental changes; it is compatible with the load differences of different vehicle types such as heavy trucks and passenger cars, significantly improving the model's generalization ability and expanding the system's application scope.

[0154] In this embodiment, it includes:

[0155] Wear prediction module calculates remaining lifespan The formula is ;

[0156] in,

[0157] Total brake pad thickness (design value, unit: mm). The current worn thickness (unit: mm). Current wear rate (unit: mm / h);

[0158] Wear rates include: ;

[0159] in, , , These are the weighting coefficients calibrated in the experiment. Scoring driving behavior Environmental factors (0~1). Use frequency factor (0~1).

[0160] Specifically, the technical features in this embodiment address the following existing technical problems: Existing technologies cannot accurately predict the remaining lifespan of brake pads, relying solely on fixed mileage or wear limit alarms, thus failing to provide users with effective maintenance references; the wear rate calculation does not consider the combined effects of driving behavior, environment, and usage frequency, resulting in low accuracy in remaining lifespan prediction. The corresponding technical effects are: Accurate calculation of remaining lifespan through scientific formula derivation provides accurate data support for proactive maintenance, helping users to rationally plan maintenance schedules; dynamically adjusting the wear rate fully considers the combined effects of driving behavior, environment, usage frequency, and other factors, improving the real-time performance and accuracy of remaining lifespan prediction.

[0161] In this embodiment, it includes:

[0162] The wear prediction module is also used to predict wear based on remaining lifespan. Determine the tolerance level for the behavior;

[0163] Behavioral tolerance is the upper limit of specific driving behaviors that brake pads can withstand under the current wear condition;

[0164] Among them, the remaining lifespan is determined based on the wear and tear of the brake pads under braking conditions. Converted into the number of times of emergency braking can be tolerated, the duration of continuous downhill driving can be tolerated, and / or the risk value of failure during high-speed serpentine driving;

[0165] Based on historical data on failures during high-speed serpentine driving, a preset threshold for failure risk is set.

[0166] Specifically, the technical features in this embodiment address the following existing technical problems: Existing technologies only inform users of the remaining lifespan of brake pads, without specifying the usage boundaries under the current wear condition, leaving users without targeted usage guidance; users may continue high-load driving even when brake pads are nearing their wear limit, easily leading to safety hazards. The corresponding technical effects are: clearly defining the usage limitations of brake pads under the current wear condition, such as the number of emergency braking attempts and the duration of continuous downhill driving, providing users with clear driving behavior guidance; effectively reducing the safety risks caused by driving beyond the brake pad's capacity, further ensuring driving safety.

[0167] In this embodiment, it includes:

[0168] The early warning module adopts a tiered early warning strategy, which includes:

[0169] Level 1: It can withstand ≤1 emergency braking incident;

[0170] Level 2: It can withstand continuous downhill driving for ≤3 minutes;

[0171] Level 3: Furthermore, the failure risk value of high-speed serpentine driving is greater than the preset failure risk threshold.

[0172] Specifically, the technical features in this embodiment address the following existing technical problems: Existing warning methods are simplistic, only issuing alarms when brake pads are worn to their limit, resulting in poor real-time performance and an inability to proactively mitigate risks; the warnings lack a tiered design, making it difficult for users to assess the urgency of the risk and take appropriate countermeasures. The resulting technical benefits are: It enables tiered early warnings of remaining brake pad life, avoiding safety hazards caused by sudden wear and providing users with ample maintenance time; tiered warnings clearly define the urgency of the risk, facilitating users to take appropriate countermeasures based on the warning level, thus improving the practicality of the warning service.

[0173] In this embodiment, it includes:

[0174] The warning information includes the remaining lifespan percentage, behavior tolerance level alerts, and customized maintenance recommendations;

[0175] Customized maintenance recommendations are generated based on driving habit profiles.

[0176] Specifically, the technical features in this embodiment address the following existing technical problems: Existing technologies provide limited warning information, only including simple replacement reminders, lacking practical usage and maintenance guidance; maintenance suggestions are generic, not tailored to user driving habits, resulting in insufficient specificity and a poor user experience. The resulting technical effects are: providing users with comprehensive warning information covering lifespan status, usage limitations, and maintenance suggestions, making it more practical; generating customized maintenance suggestions based on driving habit profiles, aligning with actual user scenarios, improving the targeting and effectiveness of maintenance, and further optimizing the user experience.

[0177] In this embodiment, it includes:

[0178] The architecture of the cloud processing unit includes a data processing layer, a behavior analysis layer, a prediction model layer, and an early warning service layer.

[0179] The data processing layer is used to clean, extract features, fuse data, and detect anomalies in the collected raw data.

[0180] The behavior analysis layer is used to build driving behavior models based on feature data.

[0181] The predictive model layer is used to calculate the wear rate and remaining life;

[0182] The early warning service layer is used to generate early warning information and send it to the early warning output unit.

[0183] Specifically, the technical features in this embodiment address the following existing technical problems: existing data processing and analysis processes are disorganized, lacking clear functional divisions at each stage, resulting in low processing efficiency; the lack of a systematic architecture leads to insufficient continuity in data transmission, analysis, and early warning, making it difficult to guarantee real-time performance and reliability. The resulting technical effects are: by clarifying the functional positioning of each stage through a layered architecture, the data processing, analysis, and early warning processes are streamlined and standardized, significantly improving system operating efficiency; the systematic architecture design ensures the continuity of data transmission, analysis, and early warning, enhancing system stability and real-time performance, and supporting efficient processing of large-scale data.

[0184] Figure 1 This is a flowchart of a brake pad life prediction and early warning method based on driving behavior, provided by one or more embodiments of the present invention.

[0185] like Figure 1 The brake pad life prediction and early warning method based on driving behavior shown includes:

[0186] S1: Collect multi-dimensional raw data through vehicle-mounted points and vehicle sensors;

[0187] The multi-dimensional raw data includes driving behavior-related data and environmental data;

[0188] S2: Preprocess and extract features from the multi-dimensional raw data to generate driving behavior feature vectors. ;

[0189] S3: Establish a driving behavior feature model based on driving behavior feature vectors, calculate driving behavior scores and generate driving habit profiles;

[0190] S4: Based on the principles of materials mechanics and statistical methods, combined with the output results of the driving behavior characteristic model and brake contact pressure. Relative sliding speed Ambient temperature and vehicle quality Establish a wear prediction model and calculate the cumulative wear amount. Wear rate and remaining lifespan ;

[0191] S5: Remaining lifespan Compared with a preset threshold, the warning level is determined by combining the behavior tolerance, and a warning message including customized maintenance suggestions is generated and pushed to the user.

[0192] Specifically, the technical features in this embodiment address the following existing technical problems: Existing technologies lack a systematic prediction and early warning process, are cumbersome to operate, lack logical coherence, and have low engineering feasibility; the process design does not deeply integrate driving behavior analysis, resulting in low prediction accuracy and insufficient targeted early warning. The corresponding technical effects are: a standardized and implementable prediction and early warning process is constructed, with clear steps, rigorous logic, and good engineering feasibility, facilitating practical application and promotion; the deep integration of driving behavior analysis into the process makes wear prediction and early warning more targeted, further improving prediction accuracy and the practicality of the early warning service.

[0193] In this embodiment, it includes:

[0194] The driving behavior-related data in step S1 is obtained through at least one of the following methods: brake pressure signal, mileage and speed signal, GPS + vehicle speed data, brake switch status + timestamp, map matching + vehicle speed trajectory analysis, and gear shifting + vehicle speed change judgment.

[0195] Specifically, the technical features in this embodiment address the following existing technical problems: Existing technologies employ a single data collection method, making it difficult to accurately acquire some key driving behavior data, resulting in insufficient data reliability; the data collection methods lack specificity and cannot adapt to the collection needs of different types of driving behavior data, affecting the analysis results. The resulting technical effects are: adopting multi-channel and targeted collection methods ensures the accuracy and reliability of driving behavior data, providing high-quality data support for subsequent analysis and prediction; adapting to the collection needs of different types of driving behavior data improves the comprehensiveness and effectiveness of data collection, further enhancing the model's analytical capabilities.

[0196] In this embodiment, it includes:

[0197] In step S4, the cumulative wear amount is obtained through a discretization formula. calculate;

[0198] in, The dynamic wear coefficient, The average braking force during the first braking action (unit: N). The braking distance for the nth braking action (unit: m). The duration of the first braking action (in seconds). This represents the number of braking events within the statistical period.

[0199] Specifically, the technical features in this embodiment address the following existing technical problems: the continuous wear calculation formula is computationally complex and unsuitable for the real-time calculation requirements of the vehicle system, resulting in poor real-time performance; the vehicle system has limited computing power, making it difficult to support complex integral calculations, thus affecting the system's practicality. The corresponding technical effects are: the discretized formula simplifies the calculation logic, adapts to the computing power level of the vehicle system, and enables real-time calculation of wear; it ensures the timeliness of real-time warnings and improves the system's practicality and operability in real-world applications.

[0200] In this embodiment, it includes:

[0201] In step S4, the behavior tolerance is at least one of the following: the maximum number of emergency braking cycles that the brake pads can withstand under the current wear condition, the maximum duration of continuous downhill driving, and driving restrictions on specific road sections.

[0202] Among them, the remaining lifespan is determined based on the wear and tear of the brake pads under braking conditions. Converted into the number of times of emergency braking can be tolerated, the duration of continuous downhill driving can be tolerated, and / or the risk value of failure during high-speed serpentine driving;

[0203] Based on historical data on failures during high-speed serpentine driving, a preset threshold for failure risk is set.

[0204] Specifically, the technical features in this embodiment address the following existing technical problems: Existing technologies do not clearly define the usage boundaries of brake pads under different wear conditions, leading to potential overuse by users, accelerated wear, and even safety accidents; a lack of targeted driving advice means users cannot determine whether brake pads can withstand the corresponding load in complex road conditions. The resulting technical effects are: providing users with clear and specific guidance on driving limits, helping them to use brake pads appropriately under different road conditions and slowing down wear; further reducing the safety risks caused by driving beyond the brake pads' capacity, and comprehensively ensuring driving safety.

[0205] In this embodiment, it includes:

[0206] In step S5, the warning levels include three levels: Level_1, Level_2, and Level_3. Different levels correspond to different remaining lifespan thresholds and behavioral risk thresholds.

[0207] Specifically, the technical features in this embodiment address the following existing technical problems: Existing warning systems lack clear level classifications, making it difficult for users to assess the urgency of risks and respond quickly; warning threshold settings are singular, failing to adapt to the warning needs of different usage scenarios and exhibiting poor flexibility. The resulting technical effects are: by classifying warning levels by different thresholds, users can intuitively understand the urgency of risks and quickly take corresponding maintenance or driving adjustment measures; adapting to the warning needs of different usage scenarios improves the flexibility and accuracy of the warning mechanism and enhances the system's adaptability.

[0208] In this embodiment, it includes:

[0209] The vehicle-mounted sensors include at least one of the following: brake pedal position sensor, vehicle speed sensor, acceleration sensor, pressure sensor, vehicle load sensor, and GPS module.

[0210] Specifically, the technical features in this embodiment address the following existing technical problems: Existing monitoring methods rely on dedicated sensors, leading to high implementation costs and complex installation, hindering widespread application; sensor compatibility is poor, with some solutions using sensors incompatible with the vehicle's existing system, affecting data acquisition. The resulting technical benefits are: reusing existing vehicle sensors eliminates the need for additional purchase and installation of dedicated equipment, reducing implementation costs and complexity; and based on the vehicle's existing sensor system, ensuring sensor compatibility with the vehicle's onboard system and improving the stability and reliability of data acquisition.

[0211] In this embodiment, it includes:

[0212] Customized maintenance recommendations are generated based on driving habit profiles, which include driving style type, braking behavior preferences, and characteristics of frequently traveled road sections.

[0213] Specifically, the technical features in this embodiment address the following existing technical problems: Existing maintenance recommendations are too generalized, failing to consider users' actual driving habits and driving scenarios, resulting in insufficient specificity and poor maintenance effectiveness; a lack of systematic recording of user driving-related characteristics leads to a lack of data support and insufficient scientific rigor in the maintenance recommendations. The resulting technical effects are: the generated maintenance recommendations are tailored to users' driving habits and frequently traveled road characteristics, accurately meeting users' personalized maintenance needs and improving maintenance effectiveness; providing maintenance recommendations based on comprehensive driving habit profiles enhances the scientific rigor and rationality of the recommendations, helping users to rationally plan maintenance schedules and reduce maintenance costs and unnecessary downtime.

[0214] It is worth noting that although this system / device only discloses the above-mentioned modules / units, it does not mean that this system / device is limited to the above-mentioned basic functional modules. On the contrary, what this invention intends to express is that, based on the above-mentioned basic functional modules, those skilled in the art can add one or more functional modules in combination with the prior art to form an infinite number of embodiments or technical solutions. That is to say, this system is open rather than closed. It cannot be assumed that the scope of protection of the claims of this invention is limited to the above-disclosed basic functional modules just because this embodiment only discloses a few basic functional modules.

[0215] In one specific embodiment, the following is disclosed: Figure 3 The core modules of the overall architecture combining cloud services and vehicle applications are shown below:

[0216] Data acquisition layer: Collects raw data such as brake pedal position, vehicle speed, and acceleration through on-board sensors, and reports the data to the cloud based on the embedded data.

[0217] Data processing layer: performs preprocessing and feature extraction on the raw data;

[0218] Behavioral analysis layer: Analyzes driving behavior patterns based on driving behavior feature data, generates driving behavior models, and establishes driving habit profiles;

[0219] Prediction Model Layer: Based on materials mechanics and statistics, a wear prediction model is established to calculate the wear rate and assess the remaining life;

[0220] Early warning service layer: Generates early warning information based on the prediction results and sends it to the vehicle's infotainment system.

[0221] In another specific embodiment, the disclosure is as follows Figure 4 The algorithm shown here, which calculates brake life and provides early warnings, is based on an overall architecture that combines cloud services and vehicle-side applications.

[0222] 1. Driving behavior feature extraction:

[0223] Define driving behavior feature vectors, where each vector represents a feature parameter that influences driving behavior:

[0224] The definitions of each feature parameter are shown in Table 1:

[0225] Table 1

[0226] variable Physical definition Measurement method or source <![CDATA[f1: Average braking intensity (unit: g)]]> Average braking force (g) per unit time Brake pressure signal <![CDATA[f2: Hard braking frequency (unit: times per 100 km)]]> Number of emergency braking times per 100 kilometers Brake pressure signal, mileage / speed signal <![CDATA[f3: Average braking distance (unit: meter)]]> Travel distance during a single braking process GPS + vehicle speed data <![CDATA[f4: Average braking time (unit: seconds)]]> Duration of a single braking action Brake switch status + timestamp <![CDATA[f5: Proportion of time spent driving at high speed downhill (unit: %)]]> The proportion of the total journey during the high-speed downhill period Statistics on time periods with vehicle speed > 80km / h and gradient > 5%. <![CDATA[f6: Number of high-speed runs on the serpentine section (unit: times / day)]]> Frequency of high-speed passage through areas with many curves Map matching + vehicle speed trajectory analysis <![CDATA[f7: Vehicle load factor (actual load / rated load)]]> Actual load / rated load Weighing sensor or axial compression estimation <![CDATA[f8: Number of frequent start-stop cycles (unit: times / hour)]]> Number of start-stop cycles per hour Gear shifting + speed change judgment <![CDATA[f9: Brake usage frequency on continuous downhill sections (unit: times / km)]]> Number of consecutive downhill sections per kilometer Map matching + vehicle speed trajectory analysis <![CDATA[f 10 Percentage of drivers at night / in rainy / foggy weather (unit: %) Percentage of driving time at night and in inclement weather Timestamp + Weather API + Headlight Status

[0227] Technical effects:

[0228] All features can be acquired in real time through onboard sensors or external data sources, making them engineering feasible; at the same time, they cover three major dimensions: driving habits, road conditions, and vehicle status, supporting personalized lifespan prediction.

[0229] 2. Brake pad wear prediction model:

[0230] Based on the principles of mechanics of materials, a formula for calculating brake pad wear is established: ;

[0231] enter:

[0232] F: Driving behavior feature vector (see above);

[0233] P(t): Braking contact pressure (collected in real time by on-board sensors);

[0234] V(t): Relative sliding speed (calculated from the difference between wheel speed and vehicle speed);

[0235] T_env: Ambient temperature (affects material properties);

[0236] M_vehicle: Vehicle mass (including load capacity);

[0237] Output:

[0238] W(t): Cumulative wear at time t (unit: mm);

[0239] in:

[0240] The dynamic wear coefficient is determined by both ambient temperature and vehicle mass.

[0241] Physical meaning: Reflects the wear resistance characteristics of a material under different working conditions.

[0242] Definition method: ;

[0243] ;

[0244] ;

[0245] ;

[0246] P(τ): Braking pressure at time τ;

[0247] V(τ): the sliding velocity at time τ;

[0248] Technical effects:

[0249] By introducing T_env and M_vehicle, the model can adapt to the differences in braking system lifespan in different climate zones (such as plateaus and extreme cold) and different vehicle types (heavy trucks vs. cars), significantly improving the predictive generalization ability.

[0250] Discretized expression (suitable for real-time calculations in vehicle systems): ;

[0251] in:

[0252] K: Wear coefficient;

[0253] F_brake_i: The average braking force during the i-th braking action, in N;

[0254] D_brake_i: Braking distance of the i-th braking action, in meters;

[0255] T_brake_i: The duration of the i-th braking event, in seconds;

[0256] n: Number of braking events within the statistical period;

[0257] 3. Remaining lifetime prediction algorithm:

[0258] Output definition:

[0259] The remaining lifespan RL(t) includes not only the time dimension but also the capability redundancy dimension, which is the ability to withstand driving behavior under the current wear condition.

[0260] ;

[0261] in:

[0262] W_total: Total thickness of brake pads (design value), in mm;

[0263] W_current: Current worn thickness, in mm;

[0264] R(t): Current wear rate (unit: mm / hour);

[0265] Wear rate modeling: ;

[0266] in:

[0267] Behavior_score: Driving behavior score (0~1), calculated based on F-vector weighting;

[0268] Environment_factor: Environmental factor (0~1), (e.g., high temperature, high humidity, ice and snow, etc.);

[0269] Usage_frequency: Uses a frequency factor (0~1), (e.g., city congestion vs. highway cruising);

[0270] Note: The concept of behavioral tolerance is introduced—for example, when RL(t) < 40%, the system can determine: "The current braking system can still withstand ≤3 emergency brakings or ≤5 minutes of continuous downhill driving, but it cannot engage in serpentine high-speed driving."

[0271] 4. Early warning mechanism:

[0272] The tiered early warning strategy is designed not only based on the percentage of remaining life expectancy, but also on the level of behavioral risk.

[0273] Warning_level=

[0274] {

[0275] Level 1: RL(t) < 20% and can withstand ≤ 1 emergency braking cycle;

[0276] Level 2: RL(t) < 40% and can withstand continuous downhill for ≤ 3 minutes;

[0277] Level 3: RL(t) < 60% and risk of serpentine high-speed driving > threshold;

[0278] }

[0279] In another specific embodiment, the system workflow is disclosed using a certain vehicle model as an example:

[0280] Data acquisition phase: Data from brake pedal position sensor, vehicle speed sensor, acceleration sensor, etc. are collected through the vehicle CAN bus to collect user driving behavior characteristic data and upload the data to the cloud based on the embedded data.

[0281] Feature extraction stage: Calculate the required driving behavior feature data based on the collected data. The basic data includes parameters such as braking force, braking distance, braking time, downhill high-speed driving time, and vehicle load for each braking action.

[0282] Behavioral analysis phase: The cloud platform uses embedded data to collect user driving behavior characteristics data over a month and generates a driving behavior score;

[0283] Wear prediction stage: Calculate the current wear amount and remaining life of the brake pads based on the established prediction model;

[0284] Early warning push phase: When the remaining lifespan is lower than the early warning threshold, a maintenance reminder will be pushed to the user through the vehicle system.

[0285] Key innovations of this application:

[0286] Multi-dimensional driving behavior analysis algorithm: Establishes a driving behavior feature model by integrating multiple parameters such as braking frequency, braking intensity, driving habits, vehicle conditions, and environmental conditions;

[0287] Wear prediction model based on materials mechanics: combines materials wear theory with actual driving data to improve prediction accuracy;

[0288] Personalized warning mechanism: Provides differentiated warning services based on the driving habits of different drivers;

[0289] Sensorless cost optimization solution: Make full use of existing vehicle sensor data, eliminating the need to install additional dedicated sensors.

[0290] Alternatives to this application:

[0291] Machine learning algorithms (such as neural networks and support vector machines) can be used to replace material mechanics models for wear prediction; cloud-based big data analysis can replace real-time on-board calculations; prediction models can be further optimized by combining environmental factors such as weather and road conditions; and it can be extended to life prediction of other braking system components such as brake discs and brake fluid.

[0292] The technical solution to be protected in this application is:

[0293] Brake pad wear prediction method based on driving behavior analysis; multi-dimensional driving behavior feature extraction algorithm; wear prediction model combining materials mechanics and statistics; personalized early warning push mechanism; overall system architecture and implementation method.

[0294] Figure 5 This is a block diagram of an electronic device for predicting and warning the life of brake pads based on driving behavior, provided by one or more embodiments of the present invention.

[0295] like Figure 5 As shown, this application provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0296] The memory stores a computer program that, when executed by the processor, causes the processor to perform steps of a brake pad life prediction and warning method based on driving behavior.

[0297] This application also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a brake pad life prediction and warning method based on driving behavior.

[0298] This application also provides a vehicle inspection platform, including:

[0299] Electronic equipment for implementing a method for predicting and warning the life of brake pads based on driving behavior;

[0300] The processor runs a program that, when running, executes steps of a brake pad life prediction and warning method based on driving behavior by taking data output from the electronic device.

[0301] Storage medium for storing programs that, when running, execute steps of a brake pad life prediction and warning method based on driving behavior in response to data output from electronic devices.

[0302] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not indicate that there is only one bus or one type of bus.

[0303] The electronic device comprises a hardware layer, an operating system layer running on top of the hardware layer, and an application layer running on the operating system. The hardware layer includes hardware such as a central processing unit (CPU), a memory management unit (MMU), and memory. The operating system can be any one or more computer operating systems that control the electronic device through processes, such as Linux, Unix, Android, iOS, or Windows. Furthermore, in this embodiment of the invention, the electronic device can be a smartphone, tablet computer, or other handheld device, or a desktop computer, portable computer, or other electronic device; there is no particular limitation in this embodiment.

[0304] In this embodiment of the invention, the executing entity for electronic device control can be an electronic device itself, or a functional module within an electronic device capable of calling and executing a program. The electronic device can obtain the firmware corresponding to the storage medium. This firmware is provided by the supplier, and different storage media may have the same or different firmware; no limitation is made here. After obtaining the firmware corresponding to the storage medium, the electronic device can write this firmware into the storage medium; specifically, it burns the firmware corresponding to the storage medium into the storage medium. The process of burning the firmware into the storage medium can be implemented using existing technology, and will not be elaborated upon in this embodiment of the invention.

[0305] Electronic devices can also obtain reset commands corresponding to storage media. These reset commands are provided by the supplier, and the reset commands for different storage media can be the same or different, which is not limited here.

[0306] At this time, the storage medium of the electronic device is a storage medium on which the corresponding firmware has been written. The electronic device can respond to the reset command corresponding to the storage medium on which the corresponding firmware has been written, thereby resetting the storage medium on which the corresponding firmware has been written according to the reset command. The process of resetting the storage medium according to the reset command can be implemented by existing technology and will not be described in detail in this embodiment of the invention.

[0307] For ease of description, the above devices are described separately by function as various units and modules. Of course, in implementing this application, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0308] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the meaning consistent with their meaning in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined.

[0309] For the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0310] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0311] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A brake pad life prediction and early warning system based on driving behavior, characterized in that, The brake pad life prediction and early warning system based on driving behavior includes: a vehicle-side data acquisition unit, a cloud-based processing unit, and an early warning output unit; The vehicle-mounted data acquisition unit is connected to the cloud processing unit, and the cloud processing unit is connected to the early warning output unit. in, The vehicle-mounted data acquisition unit includes a data acquisition module; The data acquisition module is used to collect multi-dimensional data during vehicle operation based on vehicle-mounted points and onboard sensors. The multi-dimensional data includes driving behavior data and environmental data; The cloud processing unit includes a driving behavior analysis module and a wear prediction module; The driving behavior analysis module is used to preprocess the multi-dimensional data, extract features, and then establish a driving behavior feature model and driving habit profile. The wear prediction module is used to establish a brake pad wear prediction model based on the principles of materials mechanics and statistical methods, combined with the output results of the driving behavior characteristic model, and to calculate the cumulative wear amount, wear rate and remaining life of the brake pads. The early warning output unit includes an early warning module; The warning module compares the remaining lifespan of the brake pads with a preset threshold for brake pad lifespan. When the remaining lifespan of the brake pads is lower than the preset threshold, a warning message is sent to the user.

2. The brake pad life prediction and early warning system based on driving behavior according to claim 1, characterized in that, include: The driving behavior data includes at least one of the following: braking frequency, braking intensity, braking distance, vehicle speed change rate, emergency braking frequency, downhill time percentage, frequency of driving on serpentine road sections, vehicle load factor, number of frequent starts and stops, and braking frequency on continuous downhill road sections. The environmental data includes ambient temperature and the percentage of driving time at night / in rainy / foggy weather; The percentage of driving time at night / in rainy / foggy weather was obtained by combining timestamps, weather API, and vehicle light status. The vehicle-mounted sensors include at least one of the following: brake pedal position sensor, vehicle speed sensor, acceleration sensor, pressure sensor, vehicle load sensor, and GPS module.

3. The brake pad life prediction and early warning system based on driving behavior according to claim 1, characterized in that, include: The feature extraction process of the driving behavior analysis module includes: Define driving behavior feature vector ; in, For average braking intensity, For emergency braking frequency, The average braking distance The average braking time The percentage of downhill high-speed driving time, Number of high-speed trips on serpentine road sections For vehicle load factor, For frequent start-stop times, For continuous downhill sections, the frequency of braking use, The proportion of driving at night / in rainy / foggy weather; The driving behavior analysis module is also used to calculate a driving behavior score based on the feature vector, and to classify driving style types according to the driving behavior score to generate a driving habit profile.

4. The brake pad life prediction and early warning system based on driving behavior according to claim 1, characterized in that, include: The input parameters of the wear prediction model include driving behavior feature vectors. Braking contact pressure Relative sliding speed Ambient temperature and vehicle quality ; The output parameter is time. Cumulative wear and tear over time The cumulative wear amount is expressed by a continuous formula. calculate; in This refers to any moment during the braking process; The wear prediction model incorporates a dynamic wear coefficient. ; The dynamic wear coefficient ,in The basic wear coefficient under standard conditions. This is a temperature correction function. This is the load correction function.

5. The brake pad life prediction and early warning system based on driving behavior according to claim 1, characterized in that, include: The wear prediction module calculates the remaining lifespan. The formula is ; in, Total brake pad thickness (design value, unit: mm). The current worn thickness (unit: mm). Current wear rate (unit: mm / h); The wear rate includes: ; in, , , These are the weighting coefficients calibrated in the experiment. Scoring driving behavior As environmental factors, To use frequency factors; The wear prediction module is also used to predict wear based on remaining lifespan. Determine the tolerance level for the behavior; The behavior tolerance is the upper limit of specific driving behaviors that the brake pads can withstand under the current wear condition; Among them, the remaining lifespan is determined based on the wear and tear of the brake pads under braking conditions. Converted into the number of times of emergency braking can be tolerated, the duration of continuous downhill driving can be tolerated, and / or the risk value of failure during high-speed serpentine driving; Based on historical data on failures during high-speed serpentine driving, a preset threshold for failure risk is set. in, The early warning module adopts a tiered early warning strategy, which includes: Level 1: It can withstand ≤1 emergency braking incident; Level 2: It can withstand continuous downhill driving for ≤3 minutes; Level 3: Furthermore, the failure risk value of high-speed serpentine driving is greater than the preset failure risk threshold; in, The early warning information includes the remaining lifespan percentage, behavior tolerance alerts, and customized maintenance suggestions; The customized maintenance recommendations are generated based on driving habit profiles.

6. The brake pad life prediction and early warning system based on driving behavior according to claim 1, characterized in that, include: The architecture of the cloud processing unit includes a data processing layer, a behavior analysis layer, a prediction model layer, and an early warning service layer. The data processing layer is used to clean, extract features, fuse data, and detect anomalies in the collected raw data. The behavior analysis layer is used to build a driving behavior model based on feature data; The prediction model layer is used to calculate the wear rate and remaining life; The early warning service layer is used to generate early warning information and send it to the early warning output unit.

7. A method for predicting and warning the lifespan of brake pads based on driving behavior, characterized in that, The brake pad life prediction and early warning method based on driving behavior includes: S1: Collect multi-dimensional raw data through vehicle-mounted points and vehicle sensors; The multi-dimensional raw data includes driving behavior-related data and environmental data; S2: Preprocess and extract features from the multi-dimensional raw data to generate a driving behavior feature vector. ; S3: Based on the driving behavior feature vector, establish a driving behavior feature model, calculate the driving behavior score, and generate a driving habit profile; S4: Based on the principles of materials mechanics and statistical methods, combined with the output results of the driving behavior characteristic model and brake contact pressure. Relative sliding speed Ambient temperature and vehicle quality Establish a wear prediction model and calculate the cumulative wear amount. Wear rate and remaining lifespan ; S5: The remaining lifespan Compared with a preset threshold, the warning level is determined by combining the behavior tolerance, and a warning message including customized maintenance suggestions is generated and pushed to the user; The driving behavior-related data mentioned in step S1 is obtained through at least one of the following methods: brake pressure signal, mileage speed signal, GPS + vehicle speed data, brake switch status + timestamp, map matching + vehicle speed trajectory analysis, and gear shifting + vehicle speed change judgment. In step S4, the cumulative wear amount is obtained through a discretization formula. Calculate; where, The dynamic wear coefficient, The average braking force during the first braking action (unit: N). The braking distance for the nth braking action (unit: m). The duration of the first braking action (in seconds). The number of braking operations within the statistical period; The behavior tolerance mentioned in step S4 is at least one of the following: the maximum number of emergency brakings that the brake pads can withstand under the current wear condition, the maximum duration of continuous downhill driving, and driving restrictions on specific road sections. Among them, the remaining lifespan is determined based on the wear and tear of the brake pads under braking conditions. Converted into the number of times of emergency braking can be tolerated, the duration of continuous downhill driving can be tolerated, and / or the risk value of failure during high-speed serpentine driving; Based on historical data on failures during high-speed serpentine driving, a preset threshold for failure risk is set. The warning levels mentioned in step S5 include three levels: Level_1, Level_2, and Level_3. Different levels correspond to different remaining lifespan thresholds and behavioral risk thresholds.

8. An electronic device, characterized in that, include: The processor, communication interface, memory, and communication bus are connected, with the processor, communication interface, and memory communicating with each other via the communication bus. The memory stores a computer program that, when executed by a processor, causes the processor to perform the steps of the brake pad life prediction and warning method based on driving behavior as described in claim 7.

9. A computer-readable storage medium, characterized in that, The device stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the brake pad life prediction and warning method based on driving behavior as described in claim 7.

10. A vehicle inspection platform, characterized in that, include: An electronic device for implementing the steps of the brake pad life prediction and early warning method based on driving behavior as described in claim 7; The processor runs a program that, when running, executes the steps of the brake pad life prediction and early warning method based on driving behavior as described in claim 7 from data output by the electronic device. A storage medium for storing a program that, when running, performs the steps of the brake pad life prediction and warning method based on driving behavior as described in claim 7 on data output from an electronic device.

Images