An intelligent anti-lock braking control method, system, device and storage medium

Abstract

The application discloses an intelligent anti-lock braking control method, system, device and storage medium, and relates to the field of vehicle active safety technology.The method first acquires multi-source sensor data by using a multi-source sensor module, and estimates a slip rate according to the multi-source sensor data.Then, a fuzzy rule base is constructed to predict an environmental friction coefficient and a friction extreme value.Combined with the environmental friction coefficient, wheel speed, vehicle acceleration, suspension displacement and yaw angular velocity, the prediction result is corrected to obtain an actual friction coefficient.Then, threshold control is performed according to the environmental friction coefficient, the friction extreme value and the actual friction coefficient to determine a braking pressure control scheme.The application can improve the adaptability to a dynamic environment and realize preventive control.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of vehicle active safety technology, in particular to an intelligent anti-lock braking control method, system, device and storage medium. BACKGROUND

[0002] Traditional ABS systems mainly rely on wheel speed sensors and control brake pressure through fixed slip ratio thresholds, which have the following defects:

[0003] Poor environmental adaptability: unable to identify road friction coefficients (such as dry, wet, icy, etc.) and environmental parameters (temperature, humidity, etc.) in real time, leading to increased braking distance or increased risk of wheel lock under extreme conditions.

[0004] Control lag: relying only on slip ratio feedback, unable to predict friction coefficient extremes (μ Xmax ), making it difficult to adjust braking strategy in a timely manner.

[0005] Insufficient stability: under lateral force action or complex road conditions, traditional ABS is difficult to maintain the optimal contact state of tire-road, and is prone to vehicle instability.

[0006] In the prior art, fuzzy logic control has been partially applied to ABS, but is mostly limited to single sensor data (such as wheel speed) and lacks the ability to predict dynamic changes in road conditions. Therefore, there is an urgent need for a new intelligent ABS system. SUMMARY

[0007] The purpose of the present application is to provide an intelligent anti-lock braking control method, system, device and storage medium, aiming to solve or improve at least one of the above technical problems.

[0008] To achieve the above purpose, the present application provides the following solutions:

[0009] An intelligent anti-lock braking control method, comprising:

[0010] Obtaining multi-source sensor data using a multi-source sensor module; the multi-source sensor data includes wheel speed, vehicle acceleration, vehicle longitudinal speed, tire-related data, temperature, humidity, rain intensity data, suspension displacement, and yaw angular velocity;

[0011] Estimating slip ratio based on the vehicle longitudinal speed and the tire-related data, and constructing a fuzzy rule base, predicting based on the fuzzy rule base, the temperature, the humidity, the rain intensity data and the slip ratio to obtain the environmental friction coefficient and the friction extreme value;

[0012] Correcting according to the environmental friction coefficient, the wheel speed, the vehicle acceleration, the suspension displacement and the yaw angular velocity to obtain the actual friction coefficient;

[0013] determining a brake pressure control scheme according to the environmental friction coefficient, the friction limit value and the actual friction coefficient; the brake pressure control scheme is a high-pressure charging and discharging mode, a low-pressure charging and discharging mode or an emergency braking mode.

[0014] Optionally, the environmental friction coefficient and the friction limit value are predicted based on the fuzzy rule base and the multi-source sensor data, including:

[0015] The temperature, the humidity and the rain intensity data are input into the fuzzy rule base, and the environmental friction coefficient corresponding to the to-be-tested time is obtained through fuzzy logic processing.

[0016] A dynamic model of the friction coefficient limit value changing with the slip rate is established based on historical test data, and a friction coefficient limit value prediction curve is determined according to the dynamic model.

[0017] The friction limit value corresponding to the to-be-tested time is determined according to the friction coefficient limit value prediction curve and the slip rate.

[0018] Optionally, the historical test data are obtained through a tire bench test.

[0019] Optionally, the actual friction coefficient is obtained through correction according to the environmental friction coefficient, the wheel speed, the vehicle acceleration, the suspension displacement and the yaw rate, and specifically includes:

[0020] The vertical force fluctuation is calculated according to the suspension displacement.

[0021] The actual friction coefficient is obtained through correction according to the vertical force fluctuation, the environmental friction coefficient, the wheel speed, the vehicle acceleration and the yaw rate.

[0022] Optionally, the brake pressure control scheme is determined through threshold control according to the environmental friction coefficient, the friction limit value and the actual friction coefficient, and specifically includes:

[0023] The environmental friction coefficient is set as μ env The friction limit value is set as μ Xmax The actual friction coefficient is set as μ act ;

[0024] If μ and μ , the brake pressure control scheme is determined as the high-pressure charging and discharging mode; wherein, when μ Xmax > μ env , high-pressure exhaust is performed, and when μ Xmax < μ env , high-pressure charging is performed. is the actual friction coefficient at the current moment, is the actual friction coefficient of the last time;

[0025] If And When the actual friction coefficient is less than the minimum value of the environmental friction coefficient, the brake pressure control scheme is determined as the low-pressure charging and discharging mode.

[0026] If When the actual friction coefficient is greater than the maximum value of the environmental friction coefficient, the brake pressure control scheme is determined as the emergency braking mode; wherein, is the minimum value of the environmental friction coefficient, is the maximum value of the environmental friction coefficient.

[0027] The application also provides an intelligent anti-lock braking control system, comprising:

[0028] A multi-source data acquisition unit is configured to acquire multi-source sensor data by using a multi-source sensor module; the multi-source sensor data includes wheel speed, vehicle acceleration, vehicle longitudinal speed, tire-related data, temperature, humidity, rain intensity data, suspension displacement, and yaw angular velocity.

[0029] An environment analysis unit is configured to estimate a slip rate based on the vehicle longitudinal speed and the tire-related data, and to construct a fuzzy rule base, and to make a prediction based on the fuzzy rule base, the temperature, the humidity, the rain intensity data, and the slip rate to obtain an environmental friction coefficient and a friction extreme value.

[0030] An actual friction coefficient calculation unit is configured to correct the environmental friction coefficient, the wheel speed, the vehicle acceleration, the suspension displacement, and the yaw angular velocity to obtain an actual friction coefficient.

[0031] A brake control unit is configured to perform threshold control based on the environmental friction coefficient, the friction extreme value, and the actual friction coefficient to determine a brake pressure control scheme; the brake pressure control scheme is a high-pressure charging and discharging mode, a low-pressure charging and discharging mode, or an emergency braking mode.

[0032] The application also provides an electronic device comprising a memory and a processor, wherein the memory is configured to store a computer program, and the processor is configured to run the computer program to enable the electronic device to perform the intelligent anti-lock braking control method according to the above.

[0033] The application also provides a computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the intelligent anti-lock braking control method as described above.

[0034] According to the embodiments of the application, the following technical effects are achieved:

[0035] The application discloses an intelligent anti-lock braking control method, system, device and storage medium, the method comprises the following steps: acquiring multi-source sensor data by using a multi-source sensor module, and estimating a slip rate; a fuzzy rule base is constructed, and prediction is carried out based on the fuzzy rule base, temperature, humidity and rain intensity data to obtain an environmental friction coefficient and a friction extreme value; correction is carried out according to the environmental friction coefficient, wheel speed, vehicle acceleration, suspension displacement and yaw angular velocity to obtain an actual friction coefficient; threshold control is carried out according to the environmental friction coefficient, the friction extreme value and the actual friction coefficient to determine a brake pressure control scheme; and the brake pressure control scheme is a high-pressure charging and discharging mode, a low-pressure charging and discharging mode or an emergency braking mode. The application can fuse multi-source sensor data, solve the problems of low braking efficiency and poor stability of a traditional ABS under complex road conditions, improve the adaptability of the ABS to dynamic environments (such as sudden change of road friction coefficient and lateral interference), and realize preventive control. BRIEF DESCRIPTION OF DRAWINGS

[0036] 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 in the embodiments. Obviously, the drawings described below only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0037] Figure 1 The figure is a schematic diagram of an intelligent ABS system architecture in which vehicle-mounted and roadside sensors are fused in the embodiment.

[0038] Figure 2 The figure is a schematic diagram of a fuzzy controller structure and input / output variables in the embodiment.

[0039] Figure 3 The figure is a schematic diagram of data transmission from a roadside database and a vehicle-mounted system to a decision module in the embodiment.

[0040] Figure 4 The figure is a brake pressure control logic flowchart in the embodiment.

[0041] Figure 5 The figure is a schematic diagram of typical working condition simulation results in the embodiment.

[0042] Figure 6 The figure is a schematic diagram of a potential tire grip force optimal area in the embodiment.

[0043] Figure 7 The figure is a schematic diagram of membership functions used to construct 27 rules in the embodiment; wherein, part (a) is a temperature schematic diagram, part (b) is a humidity schematic diagram, part (c) is a rain intensity schematic diagram, and part (d) is an environmental friction coefficient schematic diagram.

[0044] Figure 8 Fig. 1 is a schematic diagram of a fuzzy controller rule surface in the embodiment;

[0045] Figure 9 Fig. 2 is a schematic diagram of membership functions for constructing 59 fuzzy rules in the embodiment; wherein, (a) is a schematic diagram of a wheel slip rate, (b) is a schematic diagram of a deceleration factor, (c) is a schematic diagram of a vertical force fluctuation, and (d) is a schematic diagram of a yaw rate. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0047] The present application aims to provide an intelligent anti-lock braking control method, system, device and storage medium, aiming to solve or improve at least one of the above technical problems.

[0048] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0049] As shown in Figures 1-9 The present application provides an intelligent anti-lock braking control method, comprising:

[0050] obtaining multi-source sensor data by using a multi-source sensor module; the multi-source sensor data includes wheel speed, vehicle acceleration, vehicle longitudinal speed, tire-related data, temperature, humidity, rain intensity data, suspension displacement and yaw rate;

[0051] estimating a slip rate based on the vehicle longitudinal speed and the tire-related data, and constructing a fuzzy rule library, predicting based on the fuzzy rule library, the temperature, the humidity, the rain intensity data and the slip rate to obtain an environmental friction coefficient and a friction extreme value;

[0052] correcting according to the environmental friction coefficient, the wheel speed, the vehicle acceleration, the suspension displacement and the yaw rate to obtain an actual friction coefficient;

[0053] performing threshold control according to the environmental friction coefficient, the friction extreme value and the actual friction coefficient to determine a brake pressure control scheme; the brake pressure control scheme is a high-pressure charging and discharging mode, a low-pressure charging and discharging mode or an emergency braking mode.

[0054] The formula for calculating the slip ratio is as follows:

[0055]

[0056] Wherein: F x F y F z These are the tire longitudinal force, tire lateral force, and tire vertical force, respectively; V s ω is the wheel slip velocity, V is the vehicle longitudinal velocity, ω is the wheel rotation speed, and r is the effective tire radius. X It is the longitudinal friction coefficient of the tire; μ Y This is the tire lateral friction coefficient. The tire longitudinal friction coefficient and tire lateral friction coefficient are used to calculate the subsequent μ(s) curve.

[0057] like Figure 6 As shown in the figure, the gray area represents the potential optimal tire grip area (e.g., maximum tire friction coefficient). From the perspective of vehicle stability, the anti-lock braking system does not allow any wheel to roll in the region after the extreme conditions of the μ(s) curve.

[0058] As a specific implementation method, the system architecture of the application is built in the application, which includes a multi-source sensor module, an environmental analyzer, a preventive control module, and a decision and execution module.

[0059] The multi-source sensor module includes wheel speed sensors, vehicle acceleration sensors, temperature sensors, humidity sensors, rain intensity sensors, suspension displacement sensors, and yaw rate sensors, used to collect vehicle motion status and environmental parameters. The environmental analyzer processes sensor data based on a fuzzy logic controller, calculating the environmental friction coefficient in real time and predicting its extreme values. The preventative control module combines the onboard system database (storing μ(s) curves, brake parameters, and road surface properties) and roadside sensor data to generate pre-extreme and emergency thresholds, dynamically adjusting brake pressure. The decision-making and execution module, based on threshold comparison results, controls the brake pressure change rate (high-pressure charging / discharging, low-pressure charging / discharging, etc.) to ensure the wheel slip ratio (s) remains within the pre-extreme condition range (s≤0.25).

[0060] In the aforementioned system architecture, a fuzzy logic is constructed and used to drive environmental recognition: a fuzzy rule base (e.g., based on inputs from temperature, humidity, and rainfall intensity sensors) is built. Figures 7-8 The membership function shown can be fitted to obtain 27 commonly used rules in the industry, outputting the environmental friction coefficient, and combining wheel speed and acceleration data to correct the actual friction coefficient.

[0061] Among them, 27 rules mainly reflect the specific rules of different environmental temperature T (low, medium, high), different humidity (low, medium, high) and different rain intensity r (low, medium, high) corresponding to different environmental friction coefficient μenv, similar to look-up table (data table determined by experimental data).

[0062] μ Xmax (s) curve prediction: based on historical test data (such as tire bench test) to establish a dynamic model of friction coefficient extreme value with slip ratio, used to set the brake pressure threshold in advance. Threshold control strategy: according to μ Xmax Dynamic adjustment of pre-extreme threshold value, realize preventive brake pressure control, and set emergency threshold value as redundant backup, when pre-extreme control fails, trigger emergency brake through μ env ±δμ. Among them, δμ is the probability deviation.

[0063] Adaptive adjustment algorithm: according to slip ratio (s), deceleration factor (ts), vertical force fluctuation (ΔFz) and other parameters, through 59 fuzzy rules to dynamically correct control logic, adapt to road sudden change (such as dry ground to ice surface). Among them, the 59 fuzzy rules reflect the actual friction coefficient μ act under different slip ratio (s), deceleration factor (ts), vertical force fluctuation (ΔFz). The specific membership function is shown in Figure 9 According to the function fitting, 59 fuzzy rules commonly used in the industry can be obtained.

[0064] Based on the above technical solutions, the specific embodiments are provided as shown below.

[0065] Sensor data fusion:

[0066] Wheel speed sensor collects angular velocity ω, combined with Kalman filter to estimate vehicle linear speed V, calculate real-time slip ratio s. And based on temperature, humidity, rain intensity sensor data through fuzzy processing, output μ env through rule base.

[0067] Friction coefficient prediction and correction:

[0068] According to μ Xmax (s) curve and current slip ratio s, retrieve μ Xmax prediction value from database. Combined with vertical force fluctuation ΔFz (calculated by suspension displacement sensor), yaw rate Ωz, correct actual friction coefficient μ act .

[0069] Brake pressure control:

[0070] Decision module compares μ env , μ Xmax , μ actand historical values ​​( and Determine the adjustment mode:

[0071] like and At that time, the braking pressure control scheme is determined to be a high-pressure charging and discharging mode; wherein, when μ Xmax >μ env When high-pressure exhaust is performed, when μ Xmax <μ env At that time, high-pressure inflation is performed; The actual coefficient of friction at the current moment. This represents the actual friction coefficient at the previous moment.

[0072] like and At that time, the braking pressure control scheme was determined to be the low-pressure charging and discharging mode.

[0073] like At that time, the braking pressure control scheme was determined to be emergency braking mode; among which, This represents the lowest value for the environmental friction coefficient. This represents the maximum value of the environmental friction coefficient.

[0074] Braking frequency is adaptively adjusted (4-8Hz) to match different road surface inertia.

[0075] Simulation verification:

[0076] Using a 10-ton city bus as an example, we simulated dry → wet / icy road conditions in MATLAB.

[0077] Results: Transient process time ≤ 2.3 seconds, steady-state slip ratio s_st ≤ 0.35, braking efficiency improved by ≥ 7%.

[0078] Therefore, it has the following technical effects:

[0079] Braking distance reduced: Simulation results show that compared with traditional slip ratio control, braking distance is reduced by 9.5% to 23.7% (e.g., braking distance on dry ground is reduced from 37m to 35m).

[0080] Enhanced stability: The average slip ratio is reduced to 0.08 (0.3 in the conventional system), ensuring the lateral force coefficient μ y Maintain a high level and improve anti-skid capability.

[0081] Environmental adaptability: Supports seamless switching from dry to wet / icy surfaces with a transient time of ≤2.3 seconds.

[0082] The various embodiments described in this specification are intended to be exemplary only. The various embodiments were chosen and described in order to best explain the principles of the application and its practical application, to thereby enable others skilled in the art to best utilize the application, various embodiments with various modifications as are suited to the particular use contemplated.

[0083] The principles and implementations of the present application have been described above with the specific examples. The above description of the embodiments is only for the purpose of understanding the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation and application range will be changed. In summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. An intelligent anti-lock braking control method, characterized in that, include: Multi-source sensor data is acquired using a multi-source sensor module; the multi-source sensor data includes wheel speed, vehicle acceleration, vehicle longitudinal speed, tire-related data, temperature, humidity, rainfall intensity data, suspension displacement, and yaw rate; The slip ratio is estimated based on the vehicle's longitudinal speed and the tire-related data, and a fuzzy rule base is constructed. Based on the fuzzy rule base, the temperature, the humidity, the rainfall intensity data, and the slip ratio, predictions are made to obtain the environmental friction coefficient and friction extreme values. The actual friction coefficient is obtained by correcting the environmental friction coefficient, wheel speed, vehicle acceleration, suspension displacement, and yaw rate. The braking pressure control scheme is determined by threshold control based on the environmental friction coefficient, the friction extreme value, and the actual friction coefficient; the braking pressure control scheme is a high-pressure charging and discharging mode, a low-pressure charging and discharging mode, or an emergency braking mode.

2. The intelligent anti-lock braking control method according to claim 1, characterized in that, Predicting the environmental friction coefficient and friction extreme values ​​based on the fuzzy rule base and the multi-source sensor data includes: The temperature, humidity, and rainfall intensity data are input into the fuzzy rule base, and after fuzzy logic processing, the environmental friction coefficient corresponding to the time to be measured is obtained. A dynamic model of the extreme value of friction coefficient as a function of slip ratio is established based on historical test data, and the prediction curve of the extreme value of friction coefficient is determined according to the dynamic model. The friction extreme value corresponding to the test time is determined based on the friction coefficient extreme value prediction curve and the slip ratio.

3. The intelligent anti-lock braking control method according to claim 2, characterized in that, The historical test data was obtained from tire bench tests.

4. The intelligent anti-lock braking control method according to claim 1, characterized in that, The actual friction coefficient is obtained by correcting for the environmental friction coefficient, wheel speed, vehicle acceleration, suspension displacement, and yaw rate, specifically including: Calculate vertical force fluctuation based on suspension displacement; The actual friction coefficient is obtained by correcting for the vertical force fluctuation, the environmental friction coefficient, the wheel speed, the vehicle acceleration, and the yaw rate.

5. The intelligent anti-lock braking control method according to claim 1, characterized in that, Based on the environmental friction coefficient, the friction extreme value, and the actual friction coefficient, a threshold control is performed to determine the braking pressure control scheme, specifically including: Let the environmental friction coefficient be μ. env The friction extreme value is set as μ. Xmax Let the actual coefficient of friction be μ. act ; like and At that time, the braking pressure control scheme is determined to be a high-pressure charging and discharging mode; wherein, when μ Xmax >μ env When high-pressure exhaust is performed, when μ Xmax <μ env At that time, high-pressure inflation is performed; The actual coefficient of friction at the current moment. The actual coefficient of friction at the previous moment; like and At that time, the braking pressure control scheme was determined to be the low-pressure charging and discharging mode; like At that time, the braking pressure control scheme was determined to be emergency braking mode; among which, This represents the lowest value for the environmental friction coefficient. This represents the maximum value of the environmental friction coefficient.

6. An intelligent anti-lock braking system, characterized in that, include: A multi-source data acquisition unit is used to acquire multi-source sensor data using a multi-source sensor module; the multi-source sensor data includes wheel speed, vehicle acceleration, vehicle longitudinal speed, tire-related data, temperature, humidity, rainfall intensity data, suspension displacement, and yaw rate. An environmental analysis unit is used to estimate the slip ratio based on the vehicle's longitudinal speed and the tire-related data, and to construct a fuzzy rule base. Based on the fuzzy rule base, the temperature, the humidity, the rainfall intensity data, and the slip ratio, a prediction is made to obtain the environmental friction coefficient and friction extreme value. The actual friction coefficient calculation unit is used to correct the actual friction coefficient based on the environmental friction coefficient, the wheel speed, the vehicle acceleration, the suspension displacement, and the yaw rate. The braking control unit is used to perform threshold control based on the environmental friction coefficient, the friction extreme value, and the actual friction coefficient to determine the braking pressure control scheme; the braking pressure control scheme is a high-pressure charging and discharging mode, a low-pressure charging and discharging mode, or an emergency braking mode.

7. An electronic device, characterized in that, The device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to cause the electronic device to perform the intelligent anti-lock braking control method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by a processor, implements the intelligent anti-lock braking control method as described in any one of claims 1-5.

Images