Machine Learning Control of Chuck Waiting Time in Workpiece Transfer
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing machine learning devices are unable to complete the transfer of a workpiece in a short time due to the need for low-speed closing operations to prevent scratching, which results in prolonged waiting times and inefficient transfer processes.
Innovation Solution
A machine learning device that learns the waiting times for grasping and releasing a workpiece using a state observing unit and feedback current from a drive mechanism, optimizing the transfer time by adjusting the grasp and release waiting times based on data sets created from observed state variables.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If the chuck performs closing operation at low speed to prevent workpiece scratching, then the workpiece surface quality is improved, but the transfer time is prolonged
Solution Approach 1:
The chuck closing speed is made dynamically adjustable rather than fixed at low speed. The control device varies the closing speed according to the operation phase: high speed during approach and release, low speed only during the critical grasping moment, and high speed again during positioning. This dynamic speed adjustment resolves the contradiction by maintaining surface quality during grasping while minimizing total transfer time through high-speed operations in other phases.
Solution Approach 2:
The closing operation is divided into periodic phases with different speed characteristics: approach phase (high speed), grasping phase (low speed), and positioning phase (high speed). This periodic variation in operating speed allows the system to achieve both objectives - preventing scratches during the critical low-speed grasping phase while maintaining overall efficiency through high-speed operations in other phases.
2Reliability
If the waiting time from chuck closing start to release start is prolonged to ensure reliable workpiece transfer, then the transfer reliability is improved, but the transfer efficiency deteriorates
Solution Approach 1:
The control device incorporates feedback mechanisms that monitor the actual grasping completion status and adjust the waiting time accordingly. By detecting when the workpiece is securely grasped (through current feedback from the drive mechanism), the system can minimize the waiting time while ensuring reliable transfer, rather than using fixed prolonged waiting periods. This resolves the contradiction by making the waiting time adaptive rather than static.
Solution Approach 2:
The chuck of the receiving machine tool begins closing operation in advance before the chuck of the sending machine tool completes its release. This preliminary action overlap allows the transfer process to be more tightly coordinated, reducing the total waiting time while maintaining reliability through proper sequencing of operations.
Data Source
AI summary
A machine learning device that learns a waiting time for at least one of grasping of a workpiece by a spindle chuck and releasing of the workpiece by a loader chuck during transfer of the workpiece between the spindle chuck—that grasps and sends the workpiece and the loader chuck that grasps and receives the workpiece. The machine learning device includes a state observing unit that observes the waiting time and a FB current from a drive unit that moves the loader chuck as state variables, and a learning unit that learns the waiting time with which a transfer time of the workpiece is shortened, in accordance with a data set created based on the state variables.