Search

CN-122008881-A - Vehicle control method and vehicle

CN122008881ACN 122008881 ACN122008881 ACN 122008881ACN-122008881-A

Abstract

The invention relates to the technical field of intelligent driving of vehicles, and provides a vehicle control method and a vehicle, wherein the vehicle control method and the vehicle are used for responding to the fact that the vehicle is monitored to brake on a downhill road section, obtaining road information of a road where the vehicle is located and vehicle running information, and determining target heat-sensitive data according to the road information and the vehicle running information; the method comprises the steps of obtaining historical heat attenuation data of a vehicle braking system, determining a target state vector according to the target heat sensitivity data and the historical heat attenuation data, inputting the target state vector into an energy recovery intensity determination model which is obtained through training in advance, processing the energy recovery intensity determination model to obtain target energy recovery intensity, and controlling the vehicle to recover energy based on the target energy recovery intensity. The driving style and the driving working condition are comprehensively considered when the target energy recovery intensity is determined, the accuracy of the thermal attenuation response and the self-adaptive robustness of the system are improved, and therefore the thermal attenuation risk under the high-frequency braking downhill working condition is effectively reduced.

Inventors

  • LI MING

Assignees

  • 长城汽车股份有限公司

Dates

Publication Date
20260512
Application Date
20260213

Claims (10)

  1. 1. A vehicle control method characterized by comprising: in response to monitoring that the vehicle brakes on a downhill road section, road information of the road on which the vehicle is positioned and vehicle running information are obtained, and target heat-sensitive data are determined according to the road information and the vehicle running information; Acquiring historical thermal decay data of a vehicle braking system, and determining a target state vector according to the target thermal sensitivity data and the historical thermal decay data; And inputting the target state vector into an energy recovery intensity determination model which is obtained through training in advance, processing the energy recovery intensity determination model to obtain target energy recovery intensity, and controlling the vehicle to recover energy based on the target energy recovery intensity.
  2. 2. The method of claim 1, wherein the obtaining historical thermal decay data for a vehicle braking system, determining a target state vector from the target heat sensitivity data and the historical thermal decay data, comprises: Acquiring historical thermal decay data of a vehicle braking system, and determining a predicted temperature sequence according to the historical thermal decay data; and determining a target fusion weight, and carrying out fusion processing on the vehicle running information, the target heat sensitive data and the predicted temperature sequence based on the target fusion weight to obtain a target state vector.
  3. 3. The method of claim 2, wherein the fusing the vehicle operation information, the target heat sensitive data, and the predicted temperature sequence based on the target fusion weights to obtain a target state vector comprises: Mapping and aligning the vehicle operation information, the target heat sensitive data and the predicted temperature sequence to obtain an operation data embedded vector, a heat sensitive embedded vector and a temperature embedded vector; and inputting the target fusion weight, the operation data embedding vector, the heat sensitive embedding vector and the temperature embedding vector into a pre-trained vector fusion model, and outputting a target state vector through the vector fusion model processing.
  4. 4. The method of claim 1, wherein the controlling the vehicle for energy recovery based on the target energy recovery intensity comprises: inputting the target heat sensitivity data, the target state vector, the vehicle running information and the target energy recovery intensity into a predictive deviation model which is obtained through training in advance, and obtaining the target confidence coefficient at the current moment through processing the predictive deviation model; And controlling the vehicle to conduct energy recovery based on the target energy recovery intensity in response to the target confidence level being greater than or equal to a preset confidence threshold.
  5. 5. The method of claim 4, further comprising, after obtaining the target confidence level: Responding to the target confidence coefficient being smaller than a preset confidence coefficient threshold value, and acquiring historical target energy recovery intensity and historical actual energy recovery intensity in a first preset time period before the current moment; determining a target deviation value according to the historical target energy recovery intensity and the historical actual energy recovery intensity; and correcting the target energy recovery intensity according to the target deviation value to obtain updated energy recovery intensity, and controlling the vehicle to recover energy based on the updated energy recovery intensity.
  6. 6. The method of claim 5, wherein determining a target bias value based on the historical target energy recovery intensity and the historical actual energy recovery intensity comprises: Aiming at each pair of historical target energy recovery intensity and historical actual energy recovery intensity in a first preset time period before the current moment, carrying out difference processing on the historical target energy recovery intensity and the historical actual energy recovery intensity to obtain a first deviation value; and carrying out average processing on all the first deviation values to obtain a target deviation value.
  7. 7. The method of claim 5, wherein the obtaining the historical target energy recovery intensity and the historical actual energy recovery intensity for a predetermined period of time prior to the current time in response to the target confidence level being less than a predetermined confidence level threshold comprises: Responding to the target confidence coefficient being smaller than a preset confidence coefficient threshold value, and acquiring a historical confidence coefficient corresponding to each historical moment in a second preset time period before the current moment; Determining that all the historical confidence coefficients are smaller than a preset confidence coefficient threshold value, and determining a target deviation direction of each historical moment; In response to the same target deviation direction, acquiring the historical target energy recovery intensity and the historical actual energy recovery intensity in a preset time period before the current moment, or In response to a difference in all of the target bias directions, controlling the vehicle to conduct energy recovery based on the target energy recovery intensity.
  8. 8. The method of claim 7, wherein said determining the target bias direction for each historical time comprises: For each time in each historical time, taking each time as a target time, and acquiring a first target energy recovery intensity and a first actual energy recovery intensity of the target time; Determining a target direction of deviation as a first direction in response to the first target energy recovery intensity being greater than a first actual energy recovery intensity, or And determining the target deviation direction as a second direction in response to the first target energy recovery intensity being less than or equal to the first actual energy recovery intensity.
  9. 9. The method of claim 1, wherein the energy recovery intensity determination model determination process comprises: Acquiring a first training data set and an initial energy recovery intensity determination model, wherein the first training data set comprises a historical state vector and a historical energy recovery intensity; And inputting training data in the first training data set into the initial energy recovery intensity determination model for training, and determining that a first preset training ending condition is met to obtain the energy recovery intensity determination model.
  10. 10. A vehicle, characterized by comprising: A memory for storing an executable program; A processor; the method according to any of claims 1-9 being implemented when the executable program is executed by the processor.

Description

Vehicle control method and vehicle Technical Field The disclosure relates to the technical field of intelligent driving of vehicles, in particular to a vehicle control method and a vehicle. Background Currently, off-road vehicles are generally faced with the problem of rapid increases in brake system temperature caused by frequent braking during long-term, high-intensity downhill travel. The traditional vehicle thermal management system generally adopts a control logic based on a fixed temperature threshold value, and is difficult to accurately estimate the thermal load in a complex downhill scene, so that the system is easy to be triggered by mistake or has response lag, unnecessary energy loss is caused, the braking efficiency is reduced, and potential safety hazards exist. Disclosure of Invention In view of the above, the present disclosure is directed to a vehicle control method and a vehicle, which are used for solving the problems that the current vehicle thermal management system adopts a control logic based on a fixed temperature threshold, and is difficult to accurately estimate the thermal load in a complex downhill scene, resulting in a decrease in braking efficiency and potential safety hazard. In view of the above object, a first aspect of the present disclosure provides a vehicle control method including: in response to monitoring that the vehicle brakes on a downhill road section, road information of the road on which the vehicle is positioned and vehicle running information are obtained, and target heat-sensitive data are determined according to the road information and the vehicle running information; Acquiring historical thermal decay data of a vehicle braking system, and determining a target state vector according to the target thermal sensitivity data and the historical thermal decay data; And inputting the target state vector into an energy recovery intensity determination model which is obtained through training in advance, processing the energy recovery intensity determination model to obtain target energy recovery intensity, and controlling the vehicle to recover energy based on the target energy recovery intensity. Based on the same inventive concept, a second aspect of the present disclosure proposes a vehicle control apparatus including: The data acquisition module is configured to respond to the detection that the vehicle brakes on a downhill road section, acquire road information of the road on which the vehicle is positioned and vehicle running information, and determine target heat-sensitive data according to the road information and the vehicle running information; The state vector determining module is configured to acquire historical thermal decay data of a vehicle braking system and determine a target state vector according to the target thermal sensitivity data and the historical thermal decay data; And the vehicle control module is configured to input the target state vector into a pre-trained energy recovery intensity determination model, obtain target energy recovery intensity through the energy recovery intensity determination model, and control the vehicle to perform energy recovery based on the target energy recovery intensity. Based on the same inventive concept, a third aspect of the present disclosure proposes an electronic device comprising a memory, a processor and a computer program stored on the memory and executable by the processor, the processor implementing the vehicle control method as described above when executing the computer program. Based on the same inventive concept, a fourth aspect of the present disclosure proposes a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the vehicle control method as described above. Based on the same inventive concept, a fifth aspect of the present disclosure provides a vehicle including the vehicle control apparatus of the second aspect or the electronic device of the third aspect or the storage medium of the fourth aspect. From the foregoing, it can be seen that the present disclosure provides a vehicle control method and a vehicle, in response to monitoring that a vehicle brakes on a downhill road section, road information of a road on which the vehicle is located, and vehicle operation information are obtained, and target heat-sensitive data is determined according to the road information and the vehicle operation information. And acquiring historical thermal attenuation data of the vehicle braking system, and determining a target state vector according to the target thermal sensitivity data and the historical thermal attenuation data, namely, comprehensively considering road conditions of the vehicle, actual running conditions of the vehicle and temperature change conditions of the vehicle braking system when determining the target state vector, wherein the obtained target state vector is more accurate. And inputting the target state vector into an e