Learning Model for Human-Powered Vehicle Gear Shifting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automatic gear shifting control systems for human-powered vehicles rely on threshold determinations, which are insufficient for achieving comfortable and optimal gear shifts, leading to rider discomfort.
Innovation Solution
A control data creation device utilizing a learning algorithm to create and update a learning model based on input information from various sensors, optimizing component control by evaluating output information and adjusting the model to improve shifting performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If threshold determination is used for automatic gear shifting control, then the control system is simple to implement, but the control precision and rider comfort are insufficient
Solution Approach 1:
The patent transforms the control approach from simple threshold determination to a learning-based system that processes multiple sensor parameters (speed, cadence, torque, chain tension) simultaneously. The learning model dynamically adjusts control decisions based on trained relationships between these parameters, achieving higher precision without proportionally increasing system complexity.
Solution Approach 2:
The patent replaces the mechanical/threshold-based control logic with an information-processing system using learning algorithms. Instead of fixed threshold comparisons, the system uses trained models to interpret sensor data and determine optimal gear shifting timing, substituting computational intelligence for traditional control mechanics.
2Measurement precision
If multiple sensors and learning algorithms are used to improve control precision, then rider comfort increases, but device complexity increases
Solution Approach 1:
The learning model serves multiple functions simultaneously: it processes data from multiple sensors, determines gear shifting timing, and adapts to different riding conditions and rider preferences. This multi-functionality consolidates what would otherwise require separate control systems into a single intelligent controller.
Solution Approach 2:
The system performs self-learning and self-optimization through the learning algorithm that automatically adjusts control parameters based on training data. The model continuously improves its performance without requiring manual recalibration or complex adjustment mechanisms, reducing the need for external intervention and simplifying long-term system management.
Data Source
AI summary
A control data creation device is provided that has an acquisition part, a creation part and an evaluation part. The acquisition part acquires input information concerning traveling of a human-powered vehicle. The creation part creates by a learning algorithm a learning model that outputs output information concerning control of a component of the human-powered vehicle based on input information acquired by the acquisition part. The evaluation part evaluates output information output from the learning model. The creation part updates the learning model based on training data including an evaluation by the evaluation part, input information corresponding to an output of the output information and the output information.