Vehicle Drive Control Using Acceleration Prediction Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control systems face challenges in reducing vehicle front-rear vibration while maintaining kinetic performance, often requiring numerous adaptive parameters for drive torque control.
Innovation Solution
A control device and method using a machine learning-based vehicle front-rear acceleration prediction model to calculate command torque, minimizing deviation from target acceleration and torque, thereby reducing vibration and adaptive parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If multiple adaptive parameters are used for drive torque control to reduce vehicle front-rear vibration, then vibration reduction performance is improved, but device complexity and control difficulty increase
Solution Approach 1:
The invention changes the control parameter from multiple adaptive parameters to a single prediction horizon parameter (N seconds). The drive torque is controlled by predicting future vehicle speed N seconds ahead and calculating the optimal torque to minimize speed deviation, rather than using multiple adaptive parameters for vibration suppression. This reduces complexity while maintaining control effectiveness.
Solution Approach 2:
The invention replaces the mechanical control approach (using multiple adaptive parameters and complex control algorithms) with a model-based predictive control approach. By using a vehicle speed prediction model and optimization algorithm, the system achieves vibration reduction through mathematical optimization rather than mechanical parameter adjustments, simplifying the control system.
2Speed
If aggressive torque control is applied to improve vehicle acceleration and deceleration performance, then kinetic performance is improved, but vehicle front-rear vibration increases
Solution Approach 1:
The invention performs preliminary action by predicting the vehicle speed N seconds in the future before actually reaching that state. The optimization algorithm calculates the optimal drive torque in advance to minimize speed deviation at the future time point, allowing the system to prepare for acceleration or deceleration events while avoiding sudden torque changes that cause vibration.
Solution Approach 2:
The invention introduces dynamic adaptability through the prediction horizon parameter N and the optimization process. The control system dynamically adjusts the drive torque based on real-time vehicle conditions and the predicted future state, allowing aggressive torque application when appropriate while automatically smoothing transitions to prevent vibration, thus achieving both performance and comfort.
Data Source
AI summary
A control device for a vehicle drive unit is configured to control, based on an operating state of a vehicle, a vehicle drive unit having one or more power sources. The control device includes a processor and a storage device. The storage device is configured to store a vehicle front-rear acceleration prediction model being a machine learning model that receives as an input a command torque and outputs predicted acceleration. The processor is configured to: execute a predicted acceleration calculation process using the vehicle front-rear acceleration prediction model; and execute a command torque calculation process to calculate the command torque that minimizes an evaluation function. The evaluation function minimizes a deviation of the predicted acceleration with respect to a target vehicle front-rear acceleration according to a target torque based on the operating state while reducing a deviation of the command torque with respect to the target torque.