Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Analysis of Centrifugal Clutches in Two-Speed Automatic Transmissions with Deep Learning-Based Engagement Prediction

Bo-Yi Lin, Kai Chun Lin

TL;DR

This work addresses engine-driven centrifugal clutches in two-speed automatic transmissions by integrating dynamic numerical modeling with a Deep Neural Network to predict clutch engagement. A three-shoe centrifugal clutch is analyzed within a two-speed gearbox, with a torque model $T$ that accounts for centrifugal force, spring deformation, geometry, and friction, alongside a DNN trained on simulation data to pre-screen engagement. Two configurations are compared: Configuration A favors smooth upshifts, while Configuration B enhances downshift responsiveness through higher centrifugal torque. A sensitivity analysis shows how engagement speed depends on shoe mass and preload, enabling rapid, design-time optimization for improved transmission efficiency. The combined DL-numerical framework offers a practical path to accelerate clutch design and performance tuning in automotive applications.

Abstract

This paper presents a comprehensive numerical analysis of centrifugal clutch systems integrated with a two-speed automatic transmission, a key component in automotive torque transfer. Centrifugal clutches enable torque transmission based on rotational speed without external controls. The study systematically examines various clutch configurations effects on transmission dynamics, focusing on torque transfer, upshifting, and downshifting behaviors under different conditions. A Deep Neural Network (DNN) model predicts clutch engagement using parameters such as spring preload and shoe mass, offering an efficient alternative to complex simulations. The integration of deep learning and numerical modeling provides critical insights for optimizing clutch designs, enhancing transmission performance and efficiency.

Analysis of Centrifugal Clutches in Two-Speed Automatic Transmissions with Deep Learning-Based Engagement Prediction

TL;DR

This work addresses engine-driven centrifugal clutches in two-speed automatic transmissions by integrating dynamic numerical modeling with a Deep Neural Network to predict clutch engagement. A three-shoe centrifugal clutch is analyzed within a two-speed gearbox, with a torque model that accounts for centrifugal force, spring deformation, geometry, and friction, alongside a DNN trained on simulation data to pre-screen engagement. Two configurations are compared: Configuration A favors smooth upshifts, while Configuration B enhances downshift responsiveness through higher centrifugal torque. A sensitivity analysis shows how engagement speed depends on shoe mass and preload, enabling rapid, design-time optimization for improved transmission efficiency. The combined DL-numerical framework offers a practical path to accelerate clutch design and performance tuning in automotive applications.

Abstract

This paper presents a comprehensive numerical analysis of centrifugal clutch systems integrated with a two-speed automatic transmission, a key component in automotive torque transfer. Centrifugal clutches enable torque transmission based on rotational speed without external controls. The study systematically examines various clutch configurations effects on transmission dynamics, focusing on torque transfer, upshifting, and downshifting behaviors under different conditions. A Deep Neural Network (DNN) model predicts clutch engagement using parameters such as spring preload and shoe mass, offering an efficient alternative to complex simulations. The integration of deep learning and numerical modeling provides critical insights for optimizing clutch designs, enhancing transmission performance and efficiency.
Paper Structure (11 sections, 5 equations, 9 figures, 1 table)

This paper contains 11 sections, 5 equations, 9 figures, 1 table.

Table of Contents

  1. Introduction
  2. Background
  3. Methodology
  4. Centrifugal Clutch Transmitted Torque
  5. Numerical Model Simulation Parameters
  6. Deep Neural Network for Clutch Engagement Prediction
  7. Results
  8. Transmission Upshifting and Downshifting Performance
  9. Deep Learning-Based Clutch Engagement Prediction
  10. Clutch Full Engagement Rotating Speeds
  11. Conclusion

Figures (9)

  • Figure 1: Three-shoe Centrifugal Clutch
  • Figure 2: Mechanical diagrams of the friction lining: (a) prior to engagement with the clutch drum and (b) post full engagement.
  • Figure 3: Schematic diagrams of Automatic Two-speed Gearbox with Centrifugal Clutches in Various Configurations: (a) Configuration A: centrifugal clutch paired in forward configuration, and (b) Configuration B: centrifugal clutch paired in reverse configuration.
  • Figure 4: Deep Neural Network Diagram for Predicting Centrifugal Clutch Engagement within Operational Speed Range
  • Figure 5: Configuration A Upshifting and Downshifting Process: (a) input and driven shaft rotating speed, (b) centrifugal clutch transmitted torque, and (c) input and driven shaft rotating acceleration.
  • ...and 4 more figures