E-bike Processor Optimizing Power via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Human-powered vehicles with electrically assisted components face inefficiencies in electric power management, leading to increased consumption and reduced travel duration, as existing systems do not effectively adjust components based on traveling state and power usage.
Innovation Solution
An output device equipped with a processor that acquires input information related to traveling state and trains a machine learning model to optimize electric power consumption by adjusting components such as assist mechanisms, transmissions, and electric motors, using reinforcement learning to improve efficiency and comfort.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Duration of action of moving object
If components are operated using electric power from a power supply device without considering power management, then components can function properly, but electric power consumption increases and travel duration decreases
Solution Approach 1:
The patent applies dynamics by making the control parameters of components (assist mechanism, transmission, brake device) adjustable and adaptive based on real-time traveling state. The processor dynamically changes control parameters according to detected conditions such as vehicle speed, acceleration, and power consumption, optimizing the balance between component performance and power usage to extend travel duration.
Solution Approach 2:
The patent implements feedback by using a processor to detect the traveling state of the human-powered vehicle and the power consumption of components, then using this information to adjust control parameters. This closed-loop control system continuously monitors power usage and traveling conditions, modifying component operation to maintain optimal efficiency and extend battery life.
2Use of energy by moving object
If machine learning model is used to optimize component control, then electric power consumption efficiency improves, but device complexity increases
Solution Approach 1:
The patent applies self-service by implementing a machine learning model that automatically learns and optimizes control parameters without requiring manual intervention or complex external control systems. The model trains itself using detected traveling state data and power consumption information, progressively improving its ability to optimize component operation while maintaining relatively simple system architecture.
Data Source
AI summary
Provided are an output device, a method for generating a machine learning model, and a computer-readable storage medium for properly controlling a human-powered vehicle so as to travel comfortably for a long time by using a machine learning model. The output device includes an acquisition unit that acquires input information related to traveling of a human-powered vehicle, and a processor configured to train a machine learning model in accordance with an index value indicating electric power consumption efficiency in a power supply device for supplying electric power to a component of the human-powered vehicle, and to output output information related to controlling the component when the input information is inputted.