Sheet-Metal Production Scheduling for Scrap and Machine Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The complexity of production scheduling for sheet-metal parts, particularly due to varying geometries and production machine variables, has not been adequately addressed, leading to inefficiencies in resource utilization and production time optimization.
Innovation Solution
A method utilizing a neural network trained on a Monte Carlo tree search framework through supervised learning and self-play with reinforcement learning to create an optimized production schedule, minimizing scrap and production time by considering geometric data, production deadlines, and monetary values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of substance
If sheet-metal parts for different jobs are provided together on one metal sheet to save space, then scrap is reduced, but production scheduling complexity increases
Solution Approach 1:
The patent segments the production scheduling problem into multiple independent jobs, each with its own schedule. The system determines whether to schedule jobs separately or combine them on the same metal sheet by evaluating specific criteria, thereby managing complexity through structured decomposition while optimizing scrap reduction through selective combination.
Solution Approach 2:
The patent implements dynamic scheduling that adapts to changing production conditions. The system can respond to machine failures, urgent jobs, and capacity changes by recalculating schedules in real-time, allowing flexible adjustment of job combinations and machine assignments to maintain optimality under varying conditions.
2Productivity
If multiple identical or similar production machines are used, then productivity is increased, but production scheduling complexity increases
Solution Approach 1:
The patent treats multiple identical or similar machines as interchangeable resources that can perform the same functions. The scheduling system assigns jobs to any available machine of the required type, allowing flexible utilization of multiple machines while managing complexity through standardized machine categorization and assignment rules.
3Productivity
If production scheduling is optimized to minimize scrap and production time, then resource utilization is improved, but the complexity of solving the job shop scheduling problem increases
Solution Approach 1:
The patent incorporates feedback mechanisms where the system evaluates scheduling outcomes and uses this information to improve future scheduling decisions. By monitoring actual production results, scrap rates, and machine utilization, the system refines its scheduling algorithms to achieve better resource utilization while managing complexity through iterative improvement.
Solution Approach 2:
The patent performs preliminary scheduling calculations and optimizations before actual production begins. By pre-determining optimal job sequences, machine assignments, and sheet utilization plans, the system reduces real-time scheduling complexity while ensuring optimized resource utilization from the start of production.
Data Source
AI summary
A method for optimizing production of sheet-metal parts, the production comprising cutting out and singularizing the sheet-metal parts and bending the sheet-metal parts, wherein the method includes: (A) training a neural network, which is executed on a Monte Carlo tree search framework, by means of supervised learning and self-play with reinforcement learning; (B) recording constraints for the sheet-metal parts, the constraints comprising geometric data of the sheet-metal parts; (C) creating an optimized production schedule by way of the neural network; and (D) outputting the production schedule.