Metal Material Quality Analysis Using Prediction Error Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting metal material quality do not provide techniques for identifying the cause of quality abnormalities in manufacturing processes.
Innovation Solution
A quality abnormality analysis method that uses a quality prediction model to calculate quality contribution degrees of manufacturing conditions, presenting candidates for causing quality abnormalities by analyzing prediction errors and contribution degrees, and visualizing temporal transitions to identify the root cause.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a quality prediction model is constructed using past observation data, then quality prediction for requested conditions is improved, but the ability to identify causes of quality abnormalities is insufficient
Solution Approach 1:
The patent implements feedback by calculating the difference between predicted quality values and actual measured quality values, then using this feedback to identify abnormal causes. The system continuously compares prediction results with actual measurements and traces back to identify which manufacturing conditions contributed to quality abnormalities, closing the loop between prediction and cause analysis.
Solution Approach 2:
The patent introduces an intermediary mechanism by calculating quality contribution degrees of individual manufacturing conditions. This intermediary metric bridges the gap between the prediction model and actual quality measurements, enabling the system to identify which specific conditions contributed to quality abnormalities without requiring direct causal analysis.
2Adaptability or versatility
If multiple manufacturing conditions are analyzed to predict quality, then prediction comprehensiveness is improved, but complexity of identifying abnormal causes increases
Solution Approach 1:
The patent transforms the complex multi-dimensional problem of identifying causes among multiple manufacturing conditions into a simpler parameter-based analysis. By calculating quality contribution degrees for each condition and comparing predicted versus actual quality values, the system changes the problem parameters from direct causal analysis to quantitative contribution assessment, reducing analytical complexity.
Data Source
AI summary
A quality abnormality analysis method for a product manufactured by a manufacturing process includes: predicting quality of the product by inputting manufacturing conditions to a quality prediction model generated by using a plurality of manufacturing conditions of the manufacturing process as input variables and using the quality of the product as an output variable; calculating a quality evaluation value of an actual product manufactured by the manufacturing process; calculating, as a quality prediction error, a difference between a quality prediction value obtained as an output and the quality evaluation value; a quality contribution calculation step of quality contribution degrees of the input manufacturing conditions when predicting the quality of the product using the quality prediction model; and presenting, based on the quality prediction error and the quality contribution degree, a manufacturing condition causing a quality abnormality of the product.