Transmission Hydraulic Leakage Estimation for Shift Pressure Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Hydraulically driven transmission systems face challenges in accurately estimating oil leakage, which can lead to insufficient oil flow to the speed change mechanism despite adequate discharge flow rates from the oil pump, due to deterioration over time.
Innovation Solution
A transmission control device equipped with a neural network that measures and estimates oil leakage by inputting state quantities such as discharge flow rate, discharge pressure, oil viscosity, and component clearances, allowing for accurate estimation of leakage degree and adjusting shift control accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If the discharge flow rate of the oil pump is increased to ensure sufficient oil supply to the speed change mechanism, then the oil supply adequacy is improved, but the power consumption and mechanical stress on the oil pump increase
Solution Approach 1:
The oil pump discharge flow rate is dynamically adjusted based on real-time leakage degree estimation. The control device varies the pump output according to actual hydraulic circuit conditions, ensuring sufficient oil supply while minimizing unnecessary power consumption and mechanical stress.
Solution Approach 2:
The system implements feedback control by continuously estimating the leakage degree using neural network-based prediction models and adjusting the oil pump discharge flow rate accordingly. This closed-loop control ensures optimal balance between oil supply adequacy and energy efficiency.
2Reliability
If the discharge pressure of the oil pump is increased to compensate for oil leakage, then the oil supply reliability is improved, but the mechanical stress and energy loss increase
Solution Approach 1:
The oil pump discharge pressure is dynamically regulated based on real-time leakage degree estimation. The control device adjusts pressure levels according to actual hydraulic circuit conditions, maintaining reliable oil supply while minimizing excessive mechanical stress and energy loss.
Solution Approach 2:
The system uses feedback control by continuously monitoring estimated leakage degree and adjusting discharge pressure accordingly. This ensures the minimum necessary pressure is maintained for reliable operation without subjecting the pump to unnecessary stress.
3Measurement precision
If a neural network model is implemented to accurately estimate oil leakage, then the measurement precision of leakage degree is improved, but the device complexity increases
Solution Approach 1:
A neural network model serves as an intermediary computational layer that processes readily available sensor data (discharge flow rate, discharge pressure, oil viscosity, component clearances) to estimate leakage degree. This approach achieves high measurement precision without requiring direct physical sensors for leakage measurement, thereby limiting the increase in device complexity.
Solution Approach 2:
The patent replaces direct physical measurement of oil leakage with a computational model based on neural networks. This substitution uses software-based prediction rather than complex hardware sensors, achieving accurate leakage estimation while avoiding significant increases in mechanical or electronic device complexity.
Data Source
AI summary
An output is calculated using, as an input, a measured value of a pump discharge pressure in a neural network having the pump discharge pressure as the input and a pump rotational speed as the output. A leakage degree of oil of the hydraulic circuit of a transmission is estimated based on a difference obtained by subtracting a measured value of the pump rotational speed from the calculated value of the output. Learning of the neural network is performed using, as teacher data, the measured values of the pump discharge pressure and the pump rotational speed in the transmission in which the leakage degree of oil is within an allowable range.