Machining Route Simulation Using ML for Cycle Time Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The generation and adjustment of machining routes to shorten cycle time in machining processes are burdensome for operators, and it is difficult to determine optimal allowable errors, leading to inefficiencies and increased costs.
Innovation Solution
A simulation apparatus that uses a machine learning device to simulate and optimize machining routes by learning from changes in machining conditions and cycle times, eliminating the need for operator-set allowable errors and reducing the need for actual machining during the learning process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If an operator manually generates and adjusts machining routes to shorten cycle time, then machining efficiency may improve, but operator burden increases and the process becomes difficult to optimize within allowable error ranges
Solution Approach 1:
The machine learning device automatically generates and optimizes machining routes without requiring operator intervention. The system learns from simulation results and autonomously determines optimal machining parameters, allowing the system to serve itself rather than requiring continuous human input and adjustment.
Solution Approach 2:
The patent replaces the manual mechanical process of route generation with an automated computational system. The machine learning device uses algorithms to generate machining routes based on simulation data, substituting human cognitive and manual operations with automated computational processes.
2Manufacturing precision
If an operator sets allowable error ranges for machining routes, then machining precision can be maintained, but the setting process becomes a burden and optimal values are difficult to determine
Solution Approach 1:
The machine learning device automatically determines optimal allowable error ranges through learning from simulation results. Instead of requiring operators to manually set these parameters, the system self-adjusts the error ranges based on learned patterns from multiple simulations, eliminating the burden of manual setting while maintaining precision.
Solution Approach 2:
The system uses feedback from simulation results to continuously refine the allowable error ranges. The machine learning device analyzes simulation outcomes and adjusts the error ranges in subsequent iterations, creating a closed-loop system that automatically optimizes precision parameters based on actual performance data.
3Productivity
If multiple simulations are performed to optimize machining routes, then optimal routes can be found, but the learning process requires extensive actual machining time and resources
Solution Approach 1:
The patent uses virtual copies of the machining process through simulation rather than requiring multiple actual machining operations. The machine learning device learns from simulated machining results, creating a virtual training environment that eliminates the need for time-consuming physical trial and error while still achieving optimization.
Solution Approach 2:
The system performs preliminary simulations and learning before actual machining operations. By conducting the optimization process in advance using simulation data, the system prepares optimal machining routes beforehand, eliminating the need for time-consuming adjustments during actual production machining.
Data Source
AI summary
A simulation apparatus includes a machine learning device for learning a change in a machining route in machining of a workpiece. The machine learning device observes data indicating the changed machining route and data indicating a machining condition of the workpiece as a state variable, and also acquires determination data for determining whether or not a cycle time obtained by simulation using the changed machining route is appropriate, and learns by associating the machining condition of the workpiece with the change in the machining route, using the state variable and the determination data.