Brake Torque Learning Model for Stable Vehicle Deceleration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle braking systems face challenges in accurately controlling brake torque, leading to undesired dynamic responses such as oscillations and jerky behavior due to insufficient or inaccurate application of brake torque by service and auxiliary brakes.
Innovation Solution
A learning model trained using machine learning to determine target brake torque data by associating braking conditions with penalties for undesired vehicle dynamic responses, using operating condition data, brake torque data, and vehicle dynamic response data to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If brake torque is increased to improve deceleration performance, then deceleration capability is improved, but vehicle dynamic stability deteriorates due to oscillations and jerky behavior
Solution Approach 1:
The patent implements a feedback mechanism where vehicle dynamic response data is continuously monitored during braking. When oscillations or jerky behavior are detected, the system adjusts brake torque in real-time to maintain stability while preserving deceleration capability. This closed-loop control resolves the contradiction by dynamically balancing performance and stability based on actual vehicle response.
Solution Approach 2:
The braking system transitions from static brake torque application to dynamic adjustment based on real-time vehicle conditions. The system adapts brake torque levels according to detected dynamic responses, allowing optimal deceleration performance while preventing instability. This dynamic approach enables the system to maintain both high deceleration capability and vehicle stability simultaneously.
2Speed
If auxiliary brake torque is increased to compensate for insufficient service brake performance, then deceleration capability is improved, but control accuracy deteriorates leading to oscillating behavior
Solution Approach 1:
The patent introduces a control system that acts as an intermediary between the service brake and auxiliary brake. This intermediary system coordinates torque distribution between the two braking systems, optimizing the use of auxiliary brake while maintaining control accuracy through continuous monitoring and adjustment. The intermediary control prevents oscillating behavior by balancing torque application across both brake systems.
Solution Approach 2:
The system dynamically changes operating parameters including brake torque distribution, service brake torque, and auxiliary brake torque based on real-time vehicle conditions. By adjusting these parameters adaptively, the system maintains precise control accuracy even when utilizing auxiliary brake to enhance deceleration capability, thereby resolving the contradiction between performance and control precision.
3Speed
If brake torque application is optimized for specific braking conditions, then deceleration performance is improved, but system complexity increases due to multiple braking conditions and penalties
Solution Approach 1:
The patent employs parameter changes by assigning different penalty values to various vehicle dynamic responses based on braking conditions. The system adjusts control parameters dynamically according to the specific braking scenario, optimizing deceleration performance for each condition. This parameter-based approach manages system complexity by using adaptive parameter adjustment rather than requiring completely separate control systems for each braking condition.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A computer system (30) comprising a learning model (34) and processing circuitry (36) configured to train the learning model (34) for use in determination of target brake torque data, indicative of a target brake torque for at least each one of a service brake (24) and an auxiliary brake (26; 28) of a vehicle (10), the processing circuitry (36) being configured to: - receive braking condition information (38) comprising the following for each braking condition of a plurality of different braking conditions of the vehicle (10): ∘ operating condition data indicative of a current or predicted operating condition of the vehicle (10) during the braking condition; ∘ brake torque data, indicative of an applied brake torque for at least each one of the service brake (24) and the auxiliary brake (26; 28) during the braking condition, and ∘ vehicle dynamic response data indicative of a vehicle dynamic response of the vehicle (10) during the braking condition, - for each braking condition of the plurality of different braking conditions of the vehicle (10), associate the braking condition with a penalty in response to determining that the vehicle dynamic response data is indicative of a vehicle dynamic response of the vehicle (10) during the braking condition being outside an allowable vehicle dynamic response range, - input training data (40) to the learning model (34) to train the learning model (34) through machine learning, wherein the training data (40) comprises at least the operating condition data and the brake torque data for at least each braking condition of the plurality of different braking conditions not being associated with a penalty.