Managing a manufacturing process based on heuristic determination of predicted damages
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manufacturing processes, such as textile weaving, face challenges in managing defects that occur during production, leading to classification issues and potential rejection of materials, as existing computational methods are inadequate for handling the non-linear scalability and variability of defect counts.
Innovation Solution
A heuristic approach is employed to dynamically compute damage mitigation ranges and adjust manufacturing processes in real-time using edge computing devices, allowing for higher quality output by identifying and correcting defects within specified constraints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional computational methods are used to manage defect counts, then the system can handle basic quality control, but it cannot effectively manage the non-linear scalability and variability of defect counts across different defect classes
Solution Approach 1:
The patent implements dynamic allocation of defect counts across different defect classes based on non-linear scalability factors. The system continuously adjusts the remaining defect count allowance for each class as defects are detected, rather than using static thresholds. This allows the quality control system to adapt to the varying impact of different defect types on overall product quality.
Solution Approach 2:
The system changes the parameters used for defect evaluation by introducing class-specific weighting factors and non-linear scaling relationships. Instead of treating all defects equally, the system assigns different importance weights to various defect classes and dynamically adjusts the remaining defect count thresholds based on accumulated defects, enabling more nuanced quality control.
2Manufacturing precision
If real-time defect detection and process adjustment is implemented, then product quality is improved, but computational complexity and processing time increase
Solution Approach 1:
The patent segments the defect management system into distinct defect classes, each with its own count tracker and allocation rules. By dividing the overall defect management into independent but coordinated class-specific modules, the system can process defect information in a structured manner without requiring complex global optimization calculations, thus reducing computational complexity while maintaining real-time capability.
Solution Approach 2:
The system performs partial defect management by focusing on tracking and allocating defect counts at the class level rather than attempting to optimize every possible quality parameter simultaneously. This selective approach to real-time defect management reduces computational burden while still achieving significant quality improvements through targeted process adjustments.
3Manufacturing precision
If strict quality specifications are enforced, then defect counts are reduced, but manufacturing velocity must be decreased to maintain quality
Solution Approach 1:
The patent implements preliminary allocation of defect count budgets across different defect classes before manufacturing begins. By pre-establishing the maximum allowable defect counts for each class and dynamically tracking remaining allowances, the system can operate at high velocity without constantly checking quality specifications, only intervening when class-specific thresholds are approached or exceeded.
Solution Approach 2:
The system dynamically adjusts the remaining defect count allowances for each class as manufacturing progresses and defects are detected. This dynamic recalculation allows the manufacturing process to maintain higher velocities by only applying quality control interventions when necessary, rather than enforcing continuous strict checks that would slow production.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
A method, system and computer program product for a heuristic determination of in-process damage class control to manage expected output product category. The heuristic technique determines the predicted damages and their ranges while keeping the initial expected defects, the respective classes and range of defect and mitigation. The method dynamically computes a damage mitigation range of operation while being within the overall constraints and completes the computation in smaller number of loops being run at the edge computers so that the manufacturing equipment can operate at a higher velocity for higher quality of the output. The method includes a step of reducing error of the co-efficient and damage counts. An Internet of Things (loT) based robot is used to mitigate the damages in the manufacturing steps to ensure that the output class of the product remains what was expected at the start despite damages and mitigation measures.