Brake deceleration early warning system and method

Abstract

The application belongs to the field of brake deceleration early warning, and relates to data analysis technology, and is used for solving the problem that the prior art cannot dynamically optimize the early warning basis by combining the driving habits of drivers and the wear state of vehicles, in particular to a brake deceleration early warning system and method, comprising a deceleration early warning platform, the deceleration early warning platform is communicatively connected with a user portrait module, a wear evaluation module, a database and a plurality of terminal processors; the application obtains a primary conventional early warning threshold and a senior conventional early warning threshold as initial benchmarks from the database through an optimization processing module, wherein the numerical value of the senior conventional early warning threshold is set to be less than the primary conventional early warning threshold to clearly define the priority of early warning levels; the process realizes a dynamic scaling mechanism of early warning judgment basis, so that the threshold adjustment is both independent of the driving behavior characteristics of drivers and independent of the wear state of vehicles, thereby ensuring that the optimized early warning threshold can adapt to individual differences and vehicle performance changes simultaneously.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of brake deceleration warning, and relates to data analysis technology, in particular to a brake deceleration warning system and a method thereof. BACKGROUND

[0002] The brake warning system is an active safety technology that monitors obstacles or dangerous situations in front in real time through sensors and algorithms, and automatically alarms or brakes when necessary; obstacles in front are detected by radar or camera, and braking is automatically triggered when the distance is too close to reduce the risk of collision.

[0003] The invention patent with the publication number CN103303225B discloses an intelligent brake warning system, which starts from active defense, makes up for the deficiency of current social vehicle active safety configuration, has the advantages of low cost, high precision, flexible setting, good stability and the like; however, the warning system cannot dynamically optimize the warning basis in combination with the driving habits of the driver and the wear state of the vehicle, resulting in that the warning trigger result does not match the actual collision risk, and especially when the warning result is contrary to the user habits, it may affect the normal driving operation of the driver.

[0004] In view of the above technical problems, the present application provides a solution. SUMMARY

[0005] The application aims to provide a brake deceleration warning system and a method thereof, which can dynamically optimize the warning basis in combination with the driving habits of the driver and the wear state of the vehicle.

[0006] The technical problem to be solved by the application is how to provide a brake deceleration warning system and a method thereof that can dynamically optimize the warning basis in combination with the driving habits of the driver and the wear state of the vehicle.

[0007] The object of the application can be achieved by the following technical solutions.

[0008] A brake deceleration warning system comprises a deceleration warning platform, wherein the deceleration warning platform is communicatively connected with a user portrait module, a wear evaluation module, a database and a plurality of terminal processors.

[0009] The user portrait module is used for portrait analysis of the driver accessing the deceleration warning platform: the registered driver of the vehicle corresponding to the terminal processor is marked as an analysis object, an analysis period is generated, the following data and lane changing data of the analysis object in the analysis period are obtained, and the analysis object is marked as an aggressive object or a regular object through the following data and lane changing data.

[0010] The loss evaluation module is used for loss evaluation analysis of the vehicle accessing the deceleration early warning platform: the terminal processor marks the vehicle corresponding to the terminal processor as an evaluation object, and obtains the point brake data and tire temperature data of the evaluation object in an analysis period; the evaluation object is marked as a loss correction object or a loss difference object through the point brake data and the tire temperature data;

[0011] The terminal processor is in communication connection with a data acquisition module, an optimization processing module, an early warning analysis module and a controller.

[0012] The data acquisition module is used for driving data acquisition of the vehicle accessing the deceleration early warning platform.

[0013] The optimization processing module is used for optimization processing of the braking early warning judgment basis of the vehicle.

[0014] The early warning analysis module is used for real-time braking early warning analysis of the vehicle.

[0015] Further, the process of obtaining the following vehicle data includes: extracting and analyzing the license plate number of the front vehicle of the vehicle driven by the analysis object through the vehicle event data recorder and marking it as record information, marking a following period when the record information lasts for L1 seconds without switching and the average speed is not lower than L2 km / h as a following period, marking the shortest distance between the vehicle driven by the analysis object and the front vehicle in the following period as the following value of the following period, and obtaining the following data by summing and averaging the following values of all following periods in the analysis period; the process of obtaining the lane changing data includes: marking the process from starting to turning off the vehicle as a target process, marking the ratio of the actual lane changing times of the vehicle in the target process to the lane changing times in the navigation plan as the lane changing value of the target process, and obtaining the lane changing data by summing and averaging the lane changing values of all target processes in the analysis period.

[0016] Further, the specific process of marking the analysis object as an aggressive object or a regular object includes: obtaining the following threshold and the lane changing threshold through the database, comparing the following data and the lane changing data of the analysis object with the following threshold and the lane changing threshold respectively: if the following data is less than the following threshold or the lane changing data is greater than or equal to the lane changing threshold, the corresponding analysis object is marked as an aggressive object; otherwise, the corresponding analysis object is marked as a regular object.

[0017] Further, the point brake data is the number of point brake times of the evaluation object in the analysis period, and the process of obtaining the tire temperature data includes: collecting the tire temperature in real time through the built-in sensor when the evaluation object is driving, marking the driving time period when the tire temperature is not less than the preset temperature threshold as a temperature difference period, and marking the ratio of the sum of the lengths of all temperature difference periods in the analysis period to the total driving time as the tire temperature data.

[0018] Further, the specific process of marking the evaluation object as a normal loss object or an abnormal loss object includes: obtaining the brake threshold and the tire temperature threshold through the database, comparing the brake data and the tire temperature data of the evaluation object with the brake threshold and the tire temperature threshold respectively, and marking the corresponding evaluation object as an abnormal loss object if the brake data is greater than the brake threshold or the tire temperature data is greater than the tire temperature threshold, otherwise marking the corresponding evaluation object as a normal loss object.

[0019] Further, the specific process of the data acquisition module collecting driving data of the vehicle accessing the deceleration warning platform includes: acquiring the speed data and the obstacle data of the evaluation object in real time when the evaluation object is driving, and not performing brake warning analysis when the speed data is less than a preset speed threshold; sending the obstacle data to the optimization processing module when the speed data is not less than the preset speed threshold; the obstacle data is the straight-line distance between the evaluation object and the obstacle in front.

[0020] Further, the specific process of the optimization processing module optimizing the brake warning judgment basis of the vehicle includes: calling the primary conventional warning threshold and the senior conventional warning threshold through the database, the primary conventional warning threshold and the senior conventional warning threshold are both preset numerical constants, and the senior conventional warning threshold is less than the primary conventional warning threshold; multiplying the primary conventional warning threshold by the habit intervention coefficient t1 and the habit intervention coefficient t2 in turn to obtain the primary optimized warning threshold, and multiplying the senior conventional warning threshold by the habit intervention coefficient t1 and the habit intervention coefficient t2 in turn to obtain the senior optimized warning threshold, and sending the primary optimized warning threshold and the senior optimized warning threshold to the warning analysis module.

[0021] Further, the value determination process of t1 and t2 includes: if the analysis object is marked as an aggressive object, then 0.85≤t1≤0.95; if the analysis object is marked as a conventional object, then t1=1; if the evaluation object is marked as an abnormal loss object, then 1.05≤t2≤1.15; if the evaluation object is marked as a normal loss object, then t2=1.

[0022] A brake deceleration warning method, comprising the following steps:

[0023] Step one: portrait analysis is performed on the driver accessing the deceleration warning platform, and the analysis object is marked as an aggressive object or a conventional object;

[0024] Step two: loss evaluation analysis is performed on the vehicle accessing the deceleration warning platform, and the evaluation object is marked as a normal loss object or an abnormal loss object;

[0025] Step three: driving data of the vehicle accessing the deceleration warning platform is collected, and obstacle data is acquired in real time;

[0026] Step four: the braking warning judgment basis of the vehicle is optimized and the primary optimized warning threshold and the senior optimized warning threshold are generated;

[0027] Step five: the braking warning analysis is performed on the vehicle in real time.

[0028] The application has the following beneficial effects:

[0029] 1. The follow-up vehicle threshold and the lane changing threshold retrieved by the database are used as objective criteria, the follow-up data and the lane changing data of the analysis object are respectively input into the comparison logic unit for two-dimensional verification, when the system detects that the follow-up data is below the safety threshold or the lane changing data exceeds the reasonable frequency threshold, the aggressive object marking process is automatically triggered, which accurately corresponds to the impulsive tendency reflected by the close follow-up and the aggressive habit embodied by the frequent lane changing, if both data are within the safety threshold range, the regular object marking process is executed, and the bottom mechanism ensures that the normal driving behavior is not misjudged. The classification logic based on the two-dimensional threshold linkage makes the behavior type determination result traceable and verifiable, and provides reliable behavior characteristic input for subsequent warning optimization;

[0030] 2. The scheme of the application collects tire temperature data in real time during the driving process of the evaluation object through the built-in sensor, the system continuously compares the temperature value with the preset temperature threshold, when the temperature value reaches or exceeds the threshold, the system automatically marks the warm abnormal period during driving and records the duration, at the same time, the system accurately counts the brake-on events in the analysis period through the brake pedal sensor to form the brake-on data, finally, the system calculates the ratio of the total duration of all warm abnormal periods to the total driving duration as the tire temperature data. The process ensures that the brake-on data is directly related to the braking system operation frequency, the tire temperature data quantifies the overheat accumulation effect of the tire through normalization processing, and both of them jointly constitute objective indexes that can be repeated and compared, so that the wear evaluation module can accurately distinguish between the normal wear object and the abnormal wear object based on the actual operation data, thereby providing a reliable data basis for the dynamic optimization of the warning basis;

[0031] 3. The application obtains the speed data and the obstacle data of the evaluation object in real time, first, the speed data is dynamically compared with the preset threshold, when the speed data is below the threshold, the warning analysis process is actively terminated, thereby avoiding invalid calculation in the low-speed scene, when the speed data reaches or exceeds the threshold, only the obstacle data is transmitted to the optimization processing module, so that the system resources are concentrated on the processing of the high-risk scene, at the same time, the obstacle data provides objective distance parameters in the form of straight-line distance, laying an accurate input foundation for subsequent warning analysis, thereby forming a screening mechanism based on the speed condition, effectively coordinating the resource allocation of the data acquisition and analysis link;

[0032] 4、The application obtains the primary conventional early warning threshold and the senior conventional early warning threshold as initial reference from the database through the optimization processing module, wherein the value of the senior conventional early warning threshold is set to be less than the primary conventional early warning threshold to clarify the priority of early warning level; then, the value range of the habit intervention coefficient t1 is determined according to the driver marking result output by the user portrait module, and the value range of the habit intervention coefficient t2 is determined according to the vehicle marking result output by the loss evaluation module; on this basis, the primary conventional early warning threshold is multiplied by t1 and t2 in turn to generate the primary optimized early warning threshold, and the senior conventional early warning threshold is multiplied by t1 and t2 in turn to generate the senior optimized early warning threshold; finally, the optimized threshold is transmitted to the early warning analysis module for real-time obstacle data comparison; this process realizes the dynamic scaling mechanism of early warning judgment basis, so that the threshold adjustment is independent of both the driver behavior characteristics and the vehicle loss state, thereby ensuring that the optimized early warning threshold can adapt to individual differences and vehicle performance changes simultaneously, avoiding the early warning opportunity deviation caused by the fixed threshold. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0034] Figure 1 The system block diagram of the first embodiment of the present application;

[0035] Figure 2 The system block diagram of the second embodiment of the present application;

[0036] Figure 3 The method flow chart of the third embodiment of the present application. DETAILED DESCRIPTION

[0037] The technical solutions of the present application will be described clearly and completely in combination with the embodiments. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0038] Traditional braking warning systems often fail to dynamically adjust warning criteria based on driver habits and vehicle wear and tear, leading to a mismatch between warning triggers and actual collision risks. The root of this problem lies in the system's reliance on fixed thresholds for warning decisions, neglecting to incorporate driver behavior and vehicle physical condition as dynamic inputs. This disconnect between the warning logic and real-time driving scenarios results in the system failing to adaptively optimize its evaluation criteria when driver behavior patterns or vehicle health conditions change. Consequently, the system's stability in safety performance and operational smoothness are compromised, manifesting as a deviation between warning timing and the actual risk level.

[0039] For example, in following scenarios during peak hours on urban roads, the system monitors the distance to obstacles ahead using radar, triggering a braking warning when the distance closes to a preset threshold. However, for drivers who habitually maintain a short following distance, their operating style is misjudged as high-risk by the system, resulting in frequent warning signals. Simultaneously, if brake pad wear causes a delay in braking response, the system still calculates the warning timing based on a standard model, failing to consider the impact of increased tire temperature on the coefficient of friction. In this scenario, the warning signal conflicts with the driver's actual operating intentions, disrupting the normal following rhythm, and the vehicle's physical wear and tear is not included in the risk assessment, causing the warning results to deviate from the actual collision probability.

[0040] If these issues are not addressed, the system will continue to generate warning outputs that are inconsistent with driving behavior, leading to decreased driver trust in the warning signals and potential neglect of critical safety alerts. Furthermore, the lack of quantitative assessment of vehicle wear and tear results in a mismatch between braking response characteristics and warning logic, further increasing the risk of false or missed warnings. This technical deficiency not only weakens the effectiveness of active safety features but may also affect traffic flow stability due to unnecessary braking intervention, increasing potential accident hazards.

[0041] Example 1: As Figure 1 As shown, a braking deceleration warning system includes a deceleration warning platform, which is communicatively connected to a user profiling module, a wear assessment module, a database, and several terminal processors.

[0042] The user portrait module is used for portrait analysis of drivers accessing the access deceleration early warning platform: the registered driver of the terminal processor corresponding to the vehicle is marked as an analysis object, an analysis period is generated, and the following data and lane changing data of the analysis object in the analysis period are obtained. The process of obtaining the following data includes: extracting the license plate number of the front vehicle of the analysis object driving through the driving recorder and marking it as record information, marking the driving period when the record information lasts for L1 seconds without switching and the average speed is not lower than L2 km / h as the following period, marking the shortest distance between the analysis object driving vehicle and the front vehicle in the following period as the following value of the following period, and summing and averaging the following values of all following periods in the analysis period to obtain the following data. The process of obtaining the lane changing data includes: marking the process from starting the vehicle to turning off the vehicle as a target process, marking the ratio of the actual lane changing times in the target process to the lane changing times in the navigation plan as the lane changing value of the target process, summing and averaging the lane changing values of all target processes in the analysis period to obtain the lane changing data; the following threshold and the lane changing threshold are obtained through the database, and the following data and the lane changing data of the analysis object are compared with the following threshold and the lane changing threshold respectively: if the following data is less than the following threshold or the lane changing data is greater than or equal to the lane changing threshold, the corresponding analysis object is marked as an aggressive object; otherwise, the corresponding analysis object is marked as a regular object.

[0043] Among them, the driving recorder refers to a vehicle-mounted visual acquisition device, which can be realized by using a wide-angle lens in cooperation with an image recognition algorithm, for capturing real-time front vehicle images and extracting license plate information; the record information can be understood as the license plate data identifier obtained from the driving recorder, which can be stored in the temporary cache of the vehicle-mounted processor for continuous tracking; L1 seconds refer to a preset time threshold parameter, which can be dynamically adjusted according to the degree of road congestion, for ensuring the stability of the record information and excluding temporary interference; L2 km / h refers to a preset speed threshold parameter, which can be configured based on the road type, for screening effective driving scenarios to avoid the influence of low-speed working conditions; the following period refers to a continuous driving interval meeting the time threshold and the speed threshold, which can be identified by a time window detection algorithm; the following value refers to a minimum distance quantitative indicator in the following period, which can be obtained based on radar ranging or visual depth estimation technology; the target process refers to a complete driving session unit, which can be defined from the vehicle start signal trigger to the engine off signal end; the lane changing value refers to a ratio indicator of actual lane changing behavior and navigation plan lane changing, which can reflect the randomness degree of the driver's lane changing behavior.

[0044] Specifically, the scheme of the present application continuously captures the license plate information of the vehicle in front through the driving recorder. When the information remains stable within L1 seconds and the average vehicle speed is not lower than L2 km / h, both L1 and L2 are numerical constants, and the specific values of L1 and L2 are set by the management personnel. The system automatically marks this period as an effective following period and extracts the minimum vehicle distance in this period as the following value. At the same time, the system divides the target process into units from vehicle start to engine off, and calculates the ratio of the actual number of lane changes to the number of lane changes planned by the navigation system as the lane change value. By averaging all following values and lane change values in the analysis period, standardized following data and lane change data are formed, thereby providing an objective basis for driver behavior classification. This process focuses on stable driving scenarios through the dual constraints of time threshold and speed threshold, avoiding the interference of congestion or frequent lane changes. The minimum vehicle distance quantifies the closeness of following, highlighting the characteristics of risk moments. The navigation planning is used as a reference to calculate the lane change ratio, effectively distinguishing between planned lane changes and random lane changes. Finally, statistical averaging is used to eliminate the randomness of a single drive, ensuring the accuracy and consistency of data collection.

[0045] As a preferred embodiment, the scheme of the present application is implemented as follows: the driving recorder uses a standard vehicle camera module and is installed in the central position of the vehicle windshield to collect real-time images of the road ahead. During highway driving, the system detects that the license plate information of the vehicle in front does not switch within a reasonable period of time and the vehicle speed is within the normal driving range, automatically marks it as a following period, and records the minimum distance between vehicles in this period as the following value. For a daily commuting driving session, the system defines the vehicle start to engine off as the target process, counts the actual number of lane changes and compares it with the planned number of lane changes provided by the navigation system to generate a lane change value. After all following values and lane change values in the analysis period are calculated by the vehicle processor, standardized data are output for the user portrait module.

[0046] Among them, the following threshold refers to the critical parameter for quantitatively judging the safety boundary of the driver's following behavior, which can be realized by using statistical values determined based on historical driving behavior big data analysis or numerical value range recommended by industry safety specifications, the purpose is to objectively distinguish between safe following distance and dangerous following distance; the lane change threshold refers to the critical parameter for identifying whether the frequency of the driver's lane change behavior is abnormal, which can be realized by using the threshold calculated through vehicle dynamic model simulation or the lane change frequency benchmark value verified by real vehicle test, the purpose is to accurately capture the aggressive driving tendency reflected by excessive lane changes; the comparison process can be understood as a logical judgment operation on the quantified behavior data and the preset safety benchmark, the purpose is to establish a data-driven classification mechanism to avoid the bias introduced by subjective judgment.

[0047] Specifically, the scheme of the present application takes the following car threshold and lane changing threshold retrieved by the database as objective criteria, and inputs the following car data and lane changing data of the analysis object into the comparison logic unit for two-dimensional verification. When the system detects that the following car data is below the safety threshold or the lane changing data exceeds the reasonable frequency threshold, it automatically triggers the aggressive object marking process, which accurately corresponds to the impulsive tendency reflected by the close following and the aggressive habit embodied by the frequent lane changing. If both data are within the safety threshold range, the normal object marking process is executed, and this bottom mechanism ensures that normal driving behavior is not misjudged. This two-dimensional threshold linkage-based classification logic makes the behavior type determination result traceable and verifiable, providing reliable behavior feature input for subsequent warning optimization.

[0048] The wear evaluation module is used for wear evaluation analysis of vehicles accessing the deceleration warning platform: the vehicle corresponding to the terminal processor is marked as an evaluation object, the point brake data of the evaluation object in the analysis period and the tire temperature data are obtained, the point brake data of the evaluation object in the analysis period, and the tire temperature data acquisition process includes: collecting the tire temperature in real time through the built-in sensor when the evaluation object is driving, marking the driving time period when the tire temperature is not less than the preset temperature threshold as a warm abnormal period, marking the ratio of the sum of the lengths of all warm abnormal periods in the analysis period to the total driving time as the tire temperature data; the point brake threshold and the tire temperature threshold are obtained through the database, and the point brake data and the tire temperature data of the evaluation object are compared with the point brake threshold and the tire temperature threshold respectively: if the point brake data is greater than the point brake threshold or the tire temperature data is greater than the tire temperature threshold, the corresponding evaluation object is marked as a loss abnormal object; otherwise, the corresponding evaluation object is marked as a loss normal object.

[0049] Specifically, the point brake data refers to the number of point brake events of the evaluation object in the analysis period, which can be realized by monitoring the rapid brake events counted by the brake pedal sensor, and the purpose is to quantify the frequency of the driver's braking behavior to objectively evaluate the degree of mechanical wear of the braking system; wherein the built-in sensor can be understood as a temperature detection device integrated in the tire or hub, which can be realized by using a thermocouple or an infrared temperature sensor, and the purpose is to continuously obtain tire temperature data to support wear state analysis; in actual application, the temperature threshold is specifically a preset tire overheating critical point, which can be dynamically set based on tire material characteristics or environmental conditions, and the purpose is to accurately identify the tire high wear risk period; the warm abnormal period refers to the driving time period when the tire temperature is not less than the temperature threshold, which can be realized by comparing the time stamp record with the temperature threshold, and the purpose is to exclude the interference of normal temperature fluctuations; the tire temperature data can be understood as the ratio of the sum of the lengths of the warm abnormal periods to the total driving time, which can be realized by normalization calculation through the data processing unit, and the purpose is to eliminate the influence of different driving times to standardize the reflection of the tire overheating accumulation degree.

[0050] Specifically, the scheme of the present application collects tire temperature data in real time during the driving process of the evaluation object through the built-in sensor, and the system continuously compares the temperature value with the preset temperature threshold value; when the temperature value reaches or exceeds the threshold value, the system automatically marks the driving period as a warm abnormal period and records the duration; at the same time, the system accurately counts the point braking events in the analysis period through the brake pedal sensor to form point braking data; finally, the system calculates the ratio of the total duration of all warm abnormal periods to the total driving duration as the tire temperature data. This process ensures that the point braking data is directly related to the frequency of brake system operation, and the tire temperature data quantifies the cumulative effect of tire overheating through normalization processing, both of which together constitute objective indicators that can be repeated and compared, allowing the wear evaluation module to accurately distinguish between normal and abnormal objects based on actual operating data, thereby providing a reliable data foundation for dynamic optimization of early warning criteria.

[0051] As a specific implementation, the scheme of the present application is implemented as follows: a thermocouple sensor is embedded inside the vehicle tire as a built-in sensor for real-time collection of tire temperature; the data collection module transmits the temperature data to the wear evaluation module; when the temperature value reaches the preset temperature threshold value, the system records the period as a warm abnormal period; at the same time, the rapid braking events detected by the brake pedal sensor are counted as the number of point braking; at the end of the analysis period, the system calculates the ratio of the total duration of the warm abnormal period to the total driving duration as the tire temperature data. This implementation uses the original hardware of the vehicle to realize continuous monitoring, ensuring that the tire temperature data truly reflects the cumulative state of tire overheating.

[0052] Embodiment two: as shown in Figure 2 The terminal processor is communicatively connected with a data collection module, an optimization processing module, a warning analysis module, and a controller.

[0053] The data collection module is used for collecting driving data of vehicles connected to the deceleration warning platform: real-time acquisition of vehicle speed data and obstacle data of the evaluation object during the driving of the evaluation object, and no brake warning analysis is performed when the vehicle speed data is less than the preset vehicle speed threshold value; when the vehicle speed data is not less than the preset vehicle speed threshold value, the obstacle data is sent to the optimization processing module; the obstacle data is the straight-line distance between the evaluation object and the obstacle in front.

[0054] Specifically, vehicle speed data refers to the quantified information of the vehicle's current speed, which can be obtained using vehicle speed sensors or a global positioning system module, with the aim of monitoring the vehicle's dynamic status in real time; obstacle data refers to the spatial distance parameters between the assessed object and obstacles directly in front, which can be obtained using millimeter-wave radar or stereo vision cameras, with the aim of accurately perceiving the environment ahead; the preset vehicle speed threshold refers to a pre-set speed reference benchmark, which can be configured based on road type or vehicle model, with the aim of distinguishing between low-risk and high-risk driving scenarios; not performing brake warning analysis refers to suspending the warning calculation process, which can be achieved through software logic gating mechanisms, with the aim of avoiding redundant processing in low-speed scenarios; sending obstacle data to the optimization processing module refers to data transmission behavior, which can be achieved through the vehicle controller's local area network, with the aim of ensuring timely information flow in high-risk scenarios.

[0055] Specifically, the solution proposed in this application acquires vehicle speed data and obstacle data of the evaluation object in real time. First, the vehicle speed data is dynamically compared with a preset threshold. When the vehicle speed data is lower than the threshold, the early warning analysis process is actively terminated, thereby avoiding invalid calculations in low-speed scenarios. When the vehicle speed data reaches or exceeds the threshold, only the obstacle data is transmitted to the optimization processing module, so that system resources are concentrated on the processing of high-risk scenarios. At the same time, the obstacle data provides objective distance parameters in the form of straight-line distance, laying an accurate input foundation for subsequent early warning analysis. This forms a screening mechanism based on vehicle speed conditions, effectively coordinating the resource allocation of the data collection and analysis stages.

[0056] The optimization processing module optimizes the vehicle's braking warning judgment criteria: It retrieves the primary and advanced conventional warning thresholds from the database. Both thresholds are preset numerical constants, with the advanced threshold being smaller than the primary threshold. The primary conventional warning threshold is multiplied sequentially by the habitual intervention coefficient t1 and t2 to obtain the primary optimized warning threshold. Similarly, the advanced conventional warning threshold is multiplied sequentially by the habitual intervention coefficient t1 and t2 to obtain the advanced optimized warning threshold. The determination process for t1 and t2 includes: if the analyzed object is marked as an aggressive object, then 0.85 ≤ t1 ≤ 0.95; if the analyzed object is marked as a conventional object, then t1 = 1; if the evaluated object is marked as a damaged object, then 1.05 ≤ t2 ≤ 1.15; if the evaluated object is marked as a damaged positive object, then t2 = 1. The primary optimized warning threshold and the advanced optimized warning threshold are then sent to the warning analysis module.

[0057] The primary regular early warning threshold refers to a basic early warning trigger reference preset by the system, which can be implemented by using a fixed numerical constant stored in the database, and the purpose is to provide a standardized primary early warning reference point. The senior regular early warning threshold refers to an emergency early warning trigger reference preset by the system, which can be implemented by using a fixed numerical constant smaller than the primary regular early warning threshold, and the purpose is to define the trigger condition of the high-priority early warning scenario. The habit intervention coefficient t1 refers to a dynamic adjustment parameter reflecting the driving behavior characteristics, which can be implemented by using a numerical range determined based on the driver portrait analysis result, for example, mapped by the aggressive object or regular object label output by the user portrait module, and the purpose is to adapt to the following habits of different drivers. The habit intervention coefficient t2 refers to a dynamic adjustment parameter reflecting the state of the vehicle braking performance, which can be implemented by using a numerical range determined based on the vehicle wear evaluation result, for example, mapped by the abnormal object or normal object label output by the wear evaluation module, and the purpose is to compensate for the actual wear condition of the vehicle braking system. The primary optimized early warning threshold refers to the primary early warning reference adjusted by the habit intervention coefficient, which can be obtained by multiplying the primary regular early warning threshold by t1 and t2 in turn, and the purpose is to make the early warning based on individualization to match the real-time driving scenario. The senior optimized early warning threshold refers to the senior early warning reference adjusted by the habit intervention coefficient, which can be obtained by multiplying the senior regular early warning threshold by t1 and t2 in turn, and the purpose is to ensure that the trigger timing of the emergency early warning is synchronized with the vehicle state.

[0058] Specifically, the scheme of the present application obtains the primary regular early warning threshold and the senior regular early warning threshold as initial references from the database through the optimization processing module, wherein the numerical value of the senior regular early warning threshold is set to be smaller than the primary regular early warning threshold to clarify the priority of the early warning level; then, the value range of the habit intervention coefficient t1 is determined according to the driver label result output by the user portrait module, and the value range of the habit intervention coefficient t2 is determined according to the vehicle label result output by the wear evaluation module; on this basis, the primary regular early warning threshold is multiplied by t1 and t2 in turn to generate the primary optimized early warning threshold, and the senior regular early warning threshold is multiplied by t1 and t2 in turn to generate the senior optimized early warning threshold; finally, the optimized threshold is transmitted to the early warning analysis module for real-time obstacle data comparison. This process realizes a dynamic scaling mechanism for early warning judgment, so that the threshold adjustment is independent of both the driver behavior characteristics and the vehicle wear state, thereby ensuring that the optimized early warning threshold can adapt to individual differences and vehicle performance changes simultaneously, avoiding the deviation of the early warning timing caused by the fixed threshold.

[0059] The early warning analysis module is used for real-time braking early warning analysis of the vehicle; wherein, the early warning analysis module refers to a logic unit for performing braking early warning analysis, which can be realized by an embedded processor or an application specific integrated circuit, aiming to process obstacle data in real time and generate corresponding processing signals; the obstacle data refers to the straight-line distance between the evaluation object and the front obstacle, which can be obtained by millimeter wave radar or camera sensor collection, aiming to quantify the proximity between the vehicle and the front obstacle; the primary optimization early warning threshold and the senior optimization early warning threshold refer to the dynamically optimized early warning distance threshold, which can be calculated based on the optimization parameters stored in the database, aiming to adjust the early warning sensitivity according to the driver habit and the vehicle wear state; the determination logic refers to the rule of determining the early warning level based on the comparison result of the obstacle data and the threshold, which can be realized by conditional judgment statement, aiming to realize the grading determination of early warning; the controller refers to the unit receiving the processing signal and performing braking or warning operation, which can be realized by vehicle electronic control unit, aiming to ensure that the early warning result is converted into actual safety measures.

[0060] Embodiment three: as shown in the figure, a brake deceleration early warning method, comprising the following steps: Figure 3

[0061] Step one: portrait analysis is performed on the driver accessing the deceleration early warning platform, and the analysis object is marked as an aggressive object or a regular object;

[0062] Step two: wear evaluation analysis is performed on the vehicle accessing the deceleration early warning platform, and the evaluation object is marked as a loss-right object or a loss-different object;

[0063] Step three: driving data of the vehicle accessing the deceleration early warning platform is collected, and obstacle data is obtained in real time;

[0064] Step four: braking early warning judgment basis of the vehicle is optimized and primary optimization early warning threshold and senior optimization early warning threshold are generated;

[0065] Step five: real-time braking early warning analysis is performed on the vehicle.

[0066] ​A brake deceleration early warning system and method thereof, in operation, the deceleration early warning platform coordinates the data flow of each module, ensures that the analysis results of the user portrait module and the wear evaluation module are timely delivered to the terminal processor. For example, in the implementation process of the user portrait module, the relative distance change between the vehicle and the preceding vehicle can be monitored in real time through the cooperation of the driving recorder and the vehicle-mounted radar, the average following distance and the lane changing frequency ratio in the analysis period are calculated and analyzed in combination with the lane changing operation frequency recorded by the navigation system, so that the style type of the driver is objectively determined; similarly, the wear evaluation module uses the tire built-in temperature sensor and the brake pedal pressure detection device to continuously record the number of brake actions and the tire temperature abnormal period, and quantifies the wear state of the vehicle; thus, the optimization processing module adjusts the preset early warning threshold value according to the style classification of the analysis object and the wear state classification of the evaluation object, for example, when the analysis object is identified as an aggressive object, the system automatically adjusts the early warning trigger threshold value to adapt to the short safety distance habit, and when the evaluation object is marked as a wear abnormal object, the threshold value is correspondingly increased to compensate for the decline in brake performance caused by tire wear.

[0067] The above is only an example and description of the structure of the present application, and those skilled in the art can make various modifications or supplements to the described specific embodiments or use similar ways to replace them, as long as they do not deviate from the structure of the present application or exceed the scope defined by the present claims.

[0068] In the description of the present application, the description of the terms "one embodiment", "example", "specific example" and the like means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In the present description, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0069] The preferred embodiments of the application disclosed above are only used to help explain the application. The preferred embodiments do not describe all the details and limit the application to the specific embodiments. Obviously, many modifications and changes can be made according to the content of the present application. The present application selects and describes these embodiments in order to better explain the principles and practical application of the present application, so that those skilled in the art can well understand and utilize the present application. The present application is limited by the claims and their entire scope and equivalents.

Claims

1. A brake deceleration warning system, characterized in that, This includes a deceleration warning platform, which is communicatively connected to a user profiling module, a loss assessment module, a database, and several terminal processors. The user profiling module is used to perform profiling analysis on drivers connected to the deceleration warning platform: the registered drivers of the vehicles corresponding to the terminal processor are marked as analysis objects, an analysis period is generated, the following data and lane-changing data of the analysis objects within the analysis period are obtained, the analysis objects are marked as aggressive objects or normal objects through the following data and lane-changing data, and the marking results of the analysis objects are sent to the corresponding terminal processor. The loss assessment module is used to perform loss assessment analysis on vehicles connected to the deceleration warning platform: the vehicle corresponding to the terminal processor is marked as the assessment object, and the point braking data and tire temperature data of the assessment object are obtained within the analysis period. The assessment object is marked as a damaged object or a damaged object by using the braking data and tire temperature data, and the marking result of the assessment object is sent to the corresponding terminal processor. The terminal processor is communicatively connected to a data acquisition module, an optimization processing module, an early warning analysis module, and a controller; The data acquisition module is used to collect driving data from vehicles connected to the deceleration warning platform; The optimization processing module is used to optimize the vehicle's braking warning judgment criteria by combining the labeling results of the analysis object corresponding to the terminal processor and the labeling results of the evaluation object, and to obtain the primary optimized warning threshold and the advanced optimized warning threshold. The early warning analysis module is used to perform real-time braking early warning analysis on the vehicle based on the primary optimized early warning threshold and the advanced optimized early warning threshold.

2. The brake deceleration warning system according to claim 1, characterized in that, The process of acquiring following data includes: extracting the license plate number of the vehicle in front of the analysis subject using a dashcam and marking it as recorded information; marking the driving period during which the recorded information does not change for L1 seconds and the average vehicle speed is not less than L2 km / h as the following period; marking the shortest distance between the analysis subject's vehicle and the vehicle in front during the following period as the following value of the following period; and summing and averaging the following values ​​of all following periods within the analysis period to obtain the following data. The process of acquiring lane-changing data includes: marking the process from vehicle start-up to engine shutdown as the target process; marking the ratio of the actual number of lane changes during the target process to the number of lane changes planned in the navigation as the lane-changing value of the target process; and summing and averaging the lane-changing values ​​of all target processes within the analysis period to obtain the lane-changing data.

3. The brake deceleration warning system according to claim 2, characterized in that, The specific process of marking an analysis object as an aggressive object or a regular object includes: obtaining the following threshold and lane-changing threshold from the database, and comparing the following data and lane-changing data of the analysis object with the following threshold and lane-changing threshold respectively: if the following data is less than the following threshold or the lane-changing data is greater than or equal to the lane-changing threshold, the corresponding analysis object is marked as an aggressive object; otherwise, the corresponding analysis object is marked as a regular object.

4. A brake deceleration warning system according to claim 3, characterized in that, The braking point data refers to the number of braking points of the evaluation object within the analysis period. The process of obtaining tire temperature data includes: collecting tire temperature in real time through built-in sensors while the evaluation object is driving, marking the driving time period when the tire temperature is not lower than the preset temperature threshold as the temperature difference period, and marking the ratio of the sum of the duration of all temperature difference periods within the analysis period to the total driving time as the tire temperature data.

5. A brake deceleration warning system according to claim 4, characterized in that, The specific process of marking the assessment object as a damage-corrected object or a damage-abnormal object includes: obtaining the braking threshold and tire temperature threshold from the database, and comparing the braking data and tire temperature data of the assessment object with the braking threshold and tire temperature threshold respectively; if the braking data is greater than the braking threshold or the tire temperature data is greater than the tire temperature threshold, the corresponding assessment object is marked as a damage-abnormal object; otherwise, the corresponding assessment object is marked as a damage-corrected object.

6. A brake deceleration warning system according to claim 5, characterized in that, The specific process of the data acquisition module collecting driving data of vehicles connected to the deceleration warning platform includes: acquiring the vehicle speed data and obstacle data of the evaluation object in real time while the evaluation object is driving; not performing braking warning analysis when the vehicle speed data is less than the preset vehicle speed threshold; and sending obstacle data to the optimization processing module when the vehicle speed data is not less than the preset vehicle speed threshold. The obstacle data is the straight-line distance between the evaluation object and the obstacle directly in front.

7. A brake deceleration warning system according to claim 6, characterized in that, The specific process of optimizing the vehicle's braking warning judgment criteria by the optimization processing module includes: retrieving the primary conventional warning threshold and the advanced conventional warning threshold from the database. Both the primary conventional warning threshold and the advanced conventional warning threshold are preset numerical constants, and the advanced conventional warning threshold is less than the primary conventional warning threshold; multiplying the primary conventional warning threshold by the habitual intervention coefficient t1 and the habitual intervention coefficient t2 in sequence to obtain the primary optimized warning threshold; multiplying the advanced conventional warning threshold by the habitual intervention coefficient t1 and the habitual intervention coefficient t2 in sequence to obtain the advanced optimized warning threshold; and sending the primary optimized warning threshold and the advanced optimized warning threshold to the warning analysis module.

8. A brake deceleration warning system according to claim 7, characterized in that, The process for determining the values ​​of t1 and t2 includes: if the object being analyzed is marked as an aggressive object, then 0.85≤t1≤0.95; if the object being analyzed is marked as a normal object, then t1=1; if the object being evaluated is marked as a damaged object, then 1.05≤t2≤1.15; if the object being evaluated is marked as a damaged object, then t2=1.

Images