A trolleybus intelligent vehicle control method, system and medium

Abstract

The present application relates to the field of intelligent control, in particular to a trolleybus intelligent vehicle control method, system and medium, the method comprising collecting historical driving data of drivers and real-time driving data in driving process; setting an initial threshold of acceleration pedal opening degree change rate according to the historical driving data; dynamically updating the initial threshold through a real-time dynamic adjustment algorithm to obtain a dynamic threshold of the opening degree change rate; comparing the actual opening degree change rate with the dynamic threshold of the opening degree change rate; and performing hierarchical control of the trolleybus according to the comparison result. Whether it is a misoperation is determined according to the acceleration pedal opening degree change rate, effectively avoiding the problem that novice drivers and elderly drivers mispress the acceleration pedal to cause major traffic accidents when driving electric vehicles in the process of driving electric vehicles in the event of an emergency and improving the safety of vehicle driving.

Description

Technical Field

[0001] This invention relates to the field of intelligent control, specifically to an intelligent vehicle control method, system, and medium for electric vehicles. Background Technology

[0002] With the development of technology, electric vehicles are becoming more and more common in our lives. In daily driving, when encountering an emergency, drivers sometimes mistakenly step on the accelerator pedal instead of the brake pedal when they are nervous, which can lead to car accidents, especially for novice drivers or older drivers.

[0003] Chinese invention patent CN116811807A discloses a vehicle active braking method and system. The method includes the following steps: acquiring the current vehicle condition; acquiring the road conditions where the vehicle is currently traveling; acquiring the current weather; when the vehicle is traveling normally, acquiring the vehicle's safe braking distance based on the current weather and road conditions; and controlling the execution of different active braking strategies based on the acquired safe braking distance. The vehicle active braking method provided in this application comprehensively considers different vehicle conditions, road conditions, and weather to acquire the vehicle's safe braking distance and executes different active braking strategies accordingly to ensure vehicle driving safety.

[0004] It is evident that existing technologies generally determine whether active braking should be used based on factors such as road conditions and vehicle distance, but cannot determine whether the driver has accidentally pressed the accelerator pedal in an emergency, nor can they control the vehicle in the event of accidental pressing of the accelerator pedal. Summary of the Invention

[0005] To avoid the aforementioned problems in the prior art, the purpose of this invention is to provide an intelligent vehicle control method, system, and medium for electric vehicles.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for intelligent vehicle control of an electric vehicle, comprising the following steps:

[0007] S1: Collects historical driving data and real-time driving data during the driving process;

[0008] S2: Based on historical driving data, set an initial threshold for the rate of change of accelerator pedal opening;

[0009] S3: The initial threshold is dynamically updated by a real-time dynamic adjustment algorithm to obtain a dynamic threshold for the opening change rate;

[0010] S4: Compare the actual opening change rate with the dynamic threshold of the opening change rate;

[0011] S5: Implement graded control of trolleys based on the comparison results.

[0012] The present invention is further configured such that the historical driving data and real-time driving data include gradient, accelerator pedal opening, time and vehicle speed.

[0013] The present invention is further configured such that, in step S2, an initial threshold for the rate of change of accelerator pedal opening is set using a statistical learning algorithm, specifically including:

[0014] S21: Input the historical dataset of the accelerator pedal opening rate of change;

[0015] S22: Fitting is performed based on a Gaussian mixture model, and the parameters of each Gaussian distribution are estimated using the Expectation-Maximization (EM) algorithm:

[0016]

[0017] Let be the probability density function of a Gaussian distribution. The weights of the k-th Gaussian distribution are... Let be the mean of the k-th Gaussian distribution. Let $\frac{k}{k}$ be the standard deviation of the $k$-th Gaussian distribution.

[0018] S23: Identify abnormal clusters ;

[0019] S24: Initial threshold for calculating the rate of change of accelerator pedal opening:

[0020]

[0021] In the formula, As the initial threshold, This represents the mean of the abnormal cluster. denoted as the standard deviation of the abnormal cluster, and n is an adjustable parameter.

[0022] The present invention is further configured such that, in step S23, by comparing the mean of the Gaussian distributions, the distribution with the larger mean is regarded as an abnormal operation cluster:

[0023]

[0024] To avoid the impact of a sudden increase in the opening change rate due to misoperation on the initial threshold setting.

[0025] The present invention is further configured such that step S3 specifically comprises:

[0026] S31: Record the pedal operation sequence in real time over the most recent M seconds (e.g., 5 seconds) using a sliding window, and calculate the statistics of the rate of change of opening within the window;

[0027] S32: Dynamic threshold is calculated according to the following formula. Update calculation:

[0028]

[0029] In the formula, This is the mean of the current window. denoted as the standard deviation of the current window, and 'a' as the sensitivity coefficient.

[0030] The present invention is further configured such that, in step S32, the sensitivity coefficient is adjusted according to the real-time vehicle speed and gradient, specifically by first setting a vehicle speed adjustment coefficient based on the vehicle speed and gradient. Slope adjustment coefficient ;

[0031] Determine the speed adjustment coefficient based on real-time vehicle speed and gradient. Slope adjustment coefficient The sensitivity coefficient α is calculated using the following formula:

[0032]

[0033] This is the preset base sensitivity coefficient.

[0034] The invention is further configured to: set a vehicle speed adjustment coefficient based on vehicle speed and gradient. Slope adjustment coefficient Specifically:

[0035] When the vehicle speed When the system is in a low-speed condition, typically in traffic jams or maneuvering in a parking lot, the driver may need to frequently press the accelerator pedal. To avoid false triggering, the sensitivity is reduced and the dynamic threshold is increased. ,Pick ;

[0036] When the vehicle speed When the condition is determined to be high-speed, the risk of accidentally pressing the accelerator is higher, requiring increased sensitivity and a reduced dynamic threshold. ,Pick ;

[0037] When the vehicle speed At that time, it was determined to be the basic working condition, with the vehicle traveling at a medium speed on a flat road. ;

[0038] When the slope It is determined to be a gentle uphill slope, and the slope adjustment coefficient is used. ;

[0039] When the slope It is determined to be a steep uphill slope, and the slope adjustment factor is used. ;

[0040] When the slope It is determined to be a gentle downhill slope, and the slope adjustment coefficient is used. ;

[0041] When the slope It is determined to be a steep downhill slope, and the slope adjustment factor is used. .

[0042] The present invention is further configured such that step S5 specifically comprises:

[0043] If the dynamic threshold of the opening change rate The dynamic threshold of actual opening change rate < 1.2 times the opening change rate If so, the vehicle will issue an audible and visual warning;

[0044] If the dynamic threshold of the opening change rate <Actual opening change rate < 1.2 Dynamic threshold for opening change rate The dynamic threshold is defined as a duration greater than 2 seconds, or a rate of change of 1.2 for opening degree. Dynamic threshold for actual opening change rate ≤ 1.5% of opening change rate The vehicle will then lose power and brake slowly.

[0045] If the actual opening change rate is greater than 1.5 times the dynamic threshold of the opening change rate If this happens, the vehicle will brake suddenly and the hazard lights will be activated.

[0046] An intelligent vehicle control system for electric vehicles, used in conjunction with the aforementioned intelligent vehicle control method for electric vehicles, includes:

[0047] Data monitoring module: Used to monitor vehicle driving data in real time and store historical driving data;

[0048] Data Analysis Module: Analyzes data from the data monitoring module, calculates the initial threshold of the accelerator pedal, and dynamically adjusts the initial threshold in real time;

[0049] Data comparison module; compares the actual opening change rate with the dynamic threshold of the opening change rate;

[0050] Vehicle control module: Performs hierarchical control of the trolley based on the comparison results from the data comparison module.

[0051] A storage medium storing an electric vehicle intelligent vehicle control method program, wherein the electric vehicle intelligent vehicle control method program, when executed by a processor, implements the aforementioned electric vehicle intelligent vehicle control method.

[0052] In summary, the beneficial effects of the above-mentioned technical solution of the present invention are as follows:

[0053] 1. This invention determines the accelerator pedal opening change rate based on the current accelerator pedal information, compares the accelerator pedal opening change rate with a preset opening change rate threshold, and determines whether it is a misoperation based on the accelerator pedal opening change rate. This effectively avoids the problem of novice drivers and elderly drivers accidentally stepping on the accelerator pedal when they need to brake suddenly in an emergency while driving an electric vehicle, which could lead to a serious traffic accident, thus improving the safety of vehicle driving.

[0054] 2. This invention sets an initial threshold for the rate of change of opening based on a Gaussian mixture model, and uses a sliding window statistical algorithm to dynamically adjust the initial threshold, resulting in higher control accuracy.

[0055] 3. By dynamically adjusting the sensitivity coefficient based on real-time vehicle speed and slope, and combining this with the driving scenario, dynamic thresholds can be achieved. The updates aim to avoid excessive intervention by the driver and reduce the probability of misjudgments by the intelligent control system. Attached Figure Description

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

[0057] Figure 1 This is a flowchart of an intelligent vehicle control method for electric vehicles. Detailed Implementation

[0058] To enable those skilled in the art to better understand the technical solutions of the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Based on the embodiments of the present invention, other similar embodiments obtained by those skilled in the art without creative effort should all fall within the scope of protection of the present invention.

[0059] Furthermore, the directional terms mentioned in the following embodiments, such as "up," "down," "left," and "right," are only for reference to the accompanying drawings. Therefore, the directional terms used are for illustrative purposes and not for limiting the invention.

[0060] The present invention will be further described below with reference to the accompanying drawings and preferred embodiments.

[0061] Example 1

[0062] like Figure 1 As shown in the preferred embodiment of the present invention, an intelligent vehicle control method for electric vehicles includes the following steps:

[0063] S1: Collect the driver's historical driving data and real-time driving data during the driving process; the historical driving data and real-time driving data include slope, accelerator pedal opening, time and vehicle speed.

[0064] S2: Based on historical driving data, set an initial threshold for the rate of change of accelerator pedal opening;

[0065] S21: Input the historical dataset of accelerator pedal opening change rate; standardize the data.

[0066] S22: Fitting is performed based on a Gaussian mixture model, and the parameters of each Gaussian distribution are estimated using the Expectation-Maximization (EM) algorithm:

[0067]

[0068] Let be the probability density function of a Gaussian distribution. The weights of the k-th Gaussian distribution are... Let be the mean of the k-th Gaussian distribution. is the standard deviation of the k-th Gaussian distribution; K represents the number of Gaussian distributions in the Gaussian mixture model, which is 2 in this embodiment, corresponding to normal operation and abnormal operation respectively.

[0069] S23: Identify abnormal clusters By comparing the means of Gaussian distributions, the distribution with the larger mean is considered as an anomalous operation cluster.

[0070]

[0071] To avoid the impact of a sudden increase in the opening change rate due to misoperation on the initial threshold setting.

[0072] S24: Initial threshold for calculating the rate of change of accelerator pedal opening:

[0073]

[0074] In the formula, As the initial threshold, This represents the mean of the abnormal cluster. denoted as the standard deviation of the abnormal cluster, and n is an adjustable parameter.

[0075] S3: The initial threshold is dynamically updated by a real-time dynamic adjustment algorithm to obtain a dynamic threshold for the opening change rate;

[0076] S31: Record the pedal operation sequence in real time over the most recent M seconds (e.g., 5 seconds) using a sliding window, and calculate the statistics of the rate of change of opening within the window;

[0077] S32: Dynamic threshold is calculated according to the following formula. Update calculation:

[0078]

[0079] In the formula, This is the mean of the current window. denoted as the standard deviation of the current window, and 'a' as the sensitivity coefficient.

[0080] The sensitivity coefficient is adjusted based on real-time vehicle speed and gradient. Specifically, a speed adjustment coefficient is first set based on the vehicle speed and gradient. Slope adjustment coefficient ;

[0081] Determine the speed adjustment coefficient based on real-time vehicle speed and gradient. Slope adjustment coefficient The sensitivity coefficient α is calculated using the following formula:

[0082]

[0083] This is the preset base sensitivity coefficient.

[0084] When the vehicle speed When the system is in a low-speed condition, typically in traffic jams or maneuvering in a parking lot, the driver may need to frequently press the accelerator pedal. To avoid false triggering, the sensitivity is reduced and the dynamic threshold is increased. ,Pick ;

[0085] When the vehicle speed When the condition is determined to be high-speed, the risk of accidentally pressing the accelerator is higher, requiring increased sensitivity and a reduced dynamic threshold. ,Pick ;

[0086] When the vehicle speed At that time, it was determined to be the basic working condition, with the vehicle traveling at a medium speed on a flat road. ;

[0087] When the slope It is determined to be a gentle uphill slope, and the slope adjustment coefficient is used. ;

[0088] When the slope It is determined to be a steep uphill slope, and the slope adjustment factor is used. ;

[0089] When the slope It is determined to be a gentle downhill slope, and the slope adjustment coefficient is used. ;

[0090] When the slope It is determined to be a steep downhill slope, and the slope adjustment factor is used. .

[0091] This embodiment uses the scenario of an underground parking garage entrance as an example to calculate the sensitivity coefficient. Assume the vehicle speed at the underground parking garage entrance is 10 km / h, and the slope of the underground parking garage entrance is... Preset base sensitivity coefficient =2.

[0092]

[0093] That is, the sensitivity coefficient a = 1.9 in this scenario.

[0094] S4: Compare the actual opening change rate with the dynamic threshold of the opening change rate;

[0095] S5: Implement graded control of trolleys based on the comparison results.

[0096] If the dynamic threshold of the opening change rate The dynamic threshold of actual opening change rate < 1.2 times the opening change rate If so, the vehicle will issue an audible and visual warning;

[0097] If the dynamic threshold of the opening change rate <Actual opening change rate < 1.2 Dynamic threshold for opening change rate The dynamic threshold is defined as a duration greater than 2 seconds, or a rate of change of 1.2 for opening degree. Dynamic threshold for actual opening change rate ≤ 1.5% of opening change rate The vehicle will then lose power and brake slowly.

[0098] If the actual opening change rate is greater than 1.5 times the dynamic threshold of the opening change rate If this happens, the vehicle will brake suddenly and the hazard lights will be activated.

[0099] Example 2

[0100] An intelligent vehicle control system for electric vehicles, used in conjunction with the aforementioned intelligent vehicle control method for electric vehicles, includes:

[0101] Data monitoring module: Used to monitor vehicle driving data in real time and store historical driving data;

[0102] Data Analysis Module: Analyzes data from the data monitoring module, calculates the initial threshold of the accelerator pedal, and dynamically adjusts the initial threshold in real time;

[0103] Data comparison module; compares the actual opening change rate with the dynamic threshold of the opening change rate;

[0104] Vehicle control module: Performs hierarchical control of the trolley based on the comparison results from the data comparison module.

[0105] Example 3

[0106] A storage medium storing an electric vehicle intelligent vehicle control method program, wherein the electric vehicle intelligent vehicle control method program, when executed by a processor, implements the aforementioned electric vehicle intelligent vehicle control method.

[0107] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principle of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A method for intelligent vehicle control of an electric vehicle, characterized in that The method comprises the following steps: S1: collecting historical driving data of a driver and real-time driving data during driving; S2: setting an initial threshold of the acceleration pedal opening degree change rate according to the historical driving data; The historical driving data and real-time driving data include slope, acceleration pedal opening degree, time and vehicle speed; specifically including: S21: inputting a historical data set of the acceleration pedal opening degree change rate; S22: fitting based on Gaussian mixture model fitting, using an expectation maximization (EM) algorithm to estimate the parameters of each Gaussian distribution: is a probability density function of a Gaussian distribution, is a weight of the kth Gaussian distribution, is a mean of the kth Gaussian distribution, is a standard deviation of the kth Gaussian distribution; S23: Determine abnormal cluster ; S24: calculating the initial threshold of the acceleration pedal opening degree change rate: wherein, is the initial threshold value, is the mean of the abnormal cluster, is the standard deviation of the abnormal cluster, n is a tunable parameter S3: dynamically updating the initial threshold by a real-time dynamic adjustment algorithm to obtain a dynamic threshold of the opening degree change rate; S4: comparing the actual opening degree change rate with the dynamic threshold of the opening degree change rate; S5: performing hierarchical control of the electric vehicle according to the comparison result.

2. The intelligent vehicle control method of claim 1, wherein, In step S23, by comparing the means of the Gaussian distributions, the distribution with a larger mean is regarded as an abnormal operation cluster: Avoiding the influence of sudden increase of the opening degree change rate caused by misoperation on the setting of the initial threshold.

3. The intelligent vehicle control method of claim 1, wherein, Step S3 specifically comprises: S31: calculating the statistical quantity of the opening degree change rate in the window by statistically recording the pedal operation sequence in the last M seconds through a sliding window; S32: Dynamic thresholding according to the formula Update computation: wherein is the current window mean, is the current window standard deviation, and a is a sensitivity coefficient.

4. The intelligent vehicle control method of claim 3, wherein, In step S32, the sensitivity coefficient is adjusted according to the real-time vehicle speed and slope. Specifically, a vehicle speed adjustment coefficient is first set according to the vehicle speed and slope slope adjustment coefficient ; The vehicle speed adjustment coefficient is confirmed in real time from the vehicle speed and the gradient The gradient adjustment coefficient The sensitivity coefficient a is calculated by the following equation: wherein, is a preset base sensitivity coefficient.

5. The intelligent vehicle control method of claim 4, wherein, Adjusting the vehicle speed according to the vehicle speed and the slope Slope adjustment coefficient Specifically: When the vehicle speed is determined to be a low-speed operating condition, take ; When the vehicle speed is high, it is determined that the high-speed working condition is present, and the value of is taken. When the vehicle speed is equal to or less than 30 km / h, it is determined that the basic working condition is established, and the value of the target engine torque T is taken as ; When the slope , the gentle uphill is determined, and the slope adjustment coefficient ; When the slope , determine as steep uphill, take the slope adjustment coefficient ; When the slope , the gentle slope is determined, and the slope adjustment coefficient ; When the slope , it is determined that the slope is steep, and the slope adjustment coefficient is taken.

6. The intelligent vehicle control method of claim 3, wherein, Step S5 specifically comprises, If the dynamic threshold value of the opening degree change rate If the dynamic threshold value of the opening degree change rate The vehicle carries out sound and light early warning; If the actual opening rate is greater than the dynamic threshold value of the opening rate If the actual opening rate is greater than the dynamic threshold value of the opening rate for a duration greater than 2s; or If the actual opening rate is greater than the dynamic threshold value of the opening rate the vehicle cuts power and brakes slowly. If the actual opening rate of change > 1.5 times the dynamic threshold of opening rate of change Then the vehicle emergency brake, and open double flash.

7. A trolleybus intelligent vehicle control system, used in cooperation with the trolleybus intelligent vehicle control method of any one of claims 1-6, characterized in that, Including: A data monitoring module for monitoring the driving data of the vehicle in real time and storing historical driving data; A data analysis module for analyzing the data in the data monitoring module, calculating the initial threshold of the acceleration pedal, and dynamically adjusting the initial threshold in real time; A data comparison module; Comparing the actual opening degree change rate with the dynamic threshold of the opening degree change rate; A vehicle control module for performing hierarchical control of the electric vehicle according to the comparison result of the data comparison module.

8. A storage medium, characterized by The storage medium has a computer program stored thereon, and the computer program is executed by the processor to implement the electric vehicle intelligent whole vehicle control method of any one of claims 1-6.

Images