CVT Pulley Ratio Control Using Demand Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing continuously variable transmission systems experience a pulley ratio reverse control phenomenon and increased belt tension due to sudden changes in demand power, leading to inefficient power transfer and potential belt damage.
Innovation Solution
A deep learning model, specifically a variational auto-encoder-based system, predicts vehicle speed and accelerator position sensor values for future time points, allowing for controlled pulley ratio adjustments to prevent reverse control and maintain optimal belt tension by maintaining or adjusting the pulley ratio based on predicted values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If the pulley ratio is adjusted based on current demand power and accelerator position, then the transmission responds quickly to driver input, but pulley ratio reverse control occurs when future demand power exceeds current demand power
Solution Approach 1:
The system performs preliminary action by predicting future demand power and accelerator position using a deep learning model before actual changes occur. This allows the control system to anticipate upcoming changes and adjust the pulley ratio in advance, preventing reverse control phenomena by ensuring monotonic increase of the pulley ratio even when future conditions differ from current conditions.
2Power
If the pulley ratio is increased in advance to increase belt tension when demand power is increased, then future power delivery is improved, but belt tension becomes excessively high causing potential damage
Solution Approach 1:
The system implements feedback by continuously monitoring the predicted pulley ratio trajectory and comparing it with the current pulley ratio. When a reverse control condition is detected (where future pulley ratio would be lower than current), the feedback mechanism prevents the increase by maintaining the current pulley ratio, thereby avoiding excessive belt tension while still preparing for future power delivery needs through controlled adjustments.
3Adaptability or versatility
If the pulley ratio fluctuates up and down frequently, then the transmission adapts to changing driving conditions, but power transfer efficiency decreases due to reverse control phenomena
Solution Approach 1:
By using deep learning to predict future accelerator position and demand power, the system takes preliminary action to determine the optimal pulley ratio trajectory. This allows the transmission to adapt smoothly to changing driving conditions by following a pre-calculated monotonic path, eliminating frequent fluctuations and reverse control phenomena that would otherwise cause energy loss.
Data Source
AI summary
An apparatus of controlling a pulley of a continuously variable transmission and a method therefore is provided. The apparatus includes a non-transitory storage configured for storing a deep learning model, learning of which is completed and a controller that predicts a vehicle speed and an accelerator position sensor (APS) value for each future time point based on the deep learning model and controls the pulley of the continuously variable transmission based on a pulley ratio for each future time point, the pulley ratio corresponding to the predicted vehicle speed and the predicted APS value, thus preventing a reverse control phenomenon of the pulley ratio and increasing a tension of the belt in the continuously variable transmission.