Robot Controller Machine Learning Speed Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial robots face challenges in maintaining a consistent teaching speed for the tip end, requiring expensive pumps and extensive manual adjustments, which are time-consuming and costly, due to the complex interdependence of motor movements.
Innovation Solution
A controller with a machine learning device that learns and adjusts the movement speed of each motor to match a target speed, using state observation, determination data acquisition, and reinforcement learning to optimize the movement path and speed of the robot's tip end, allowing for constant film thickness without expensive pumps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If a pump with pressure control function is used to control rotation speed according to robot movement speed, then the amount of sealing agent per unit distance and film thickness are kept constant, but the system cost increases significantly
Solution Approach 1:
The patent replaces the mechanical pressure control system (expensive pump with pressure control) with a control system that adjusts robot movement speed based on learned parameters. The controller modifies motor speeds to maintain constant sealing agent application rate without requiring complex pressure control hardware, thereby reducing system cost while maintaining film thickness consistency.
Solution Approach 2:
The patent changes the control parameter from pump pressure control to robot movement speed control. By learning the relationship between motor speeds and tip end speed, the system adjusts movement speed parameters to achieve constant sealing agent application, eliminating the need for expensive pressure control while maintaining manufacturing precision.
2Device complexity
If the robot tip end moves at a predetermined constant speed using an inexpensive pump, then the system cost is reduced, but extensive manual adjustment by skilled workers is required and the process becomes time-consuming
Solution Approach 1:
The patent implements a self-learning control system where the controller automatically learns the relationship between motor speeds and tip end speed through observation and determination data. This eliminates the need for skilled workers to perform time-consuming manual adjustments by trial and error, as the system autonomously optimizes the movement parameters.
Solution Approach 2:
The patent introduces a feedback mechanism where the controller acquires determination data about the appropriateness of tip end speed and uses this information to adjust motor speeds. This closed-loop control enables automatic optimization without manual intervention, reducing both system cost and adjustment time.
3Ease of operation
If manual adjustment of robot tip end speed is performed by trial and error, then the movement speed can be adjusted, but enormous efforts are expended and the process becomes inefficient
Solution Approach 1:
The patent replaces manual trial-and-error adjustment with an automated machine learning system. The controller learns the complex relationship between multiple motor speeds and tip end speed through data acquisition and determination, automatically determining optimal speed settings without requiring skilled workers to expend enormous efforts.
Solution Approach 2:
The patent performs preliminary learning and parameter optimization before actual production. The controller acquires determination data and learns the optimal speed relationships in advance, so that during operation, the system can directly apply the learned parameters without time-consuming manual adjustments, thereby improving productivity.
Data Source
AI summary
A machine learning device of a controller observes data on a movement speed of each motor of a robot and an adjustment amount of the movement speed, a target speed of a tip end of the robot, and a movement path proximate to the tip end of the robot, as state variables expressing a current state of an environment, and acquires determination data indicating an appropriateness determination result of the movement speed of the tip end of the robot. Then, the machine learning device learns the target speed data, the movement speed data, and the movement path data in association with the adjustment amount of the movement speed of each of the motors of the robot by using the observed state variables and the acquired determination data.