AI Root Cause Analysis Model for Defect Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current root cause analysis methods are inefficient in identifying and addressing defects, as they often require manual processing and subjective human intuition, leading to resource wastage and errors in defect classification, priorities, and rework estimates.
Innovation Solution
A method utilizing artificial intelligence to train a classification model with defect classifier training data, processing it with a Pareto analysis model to select classes, calculate defect scores, and generate root cause corrective action recommendations, which can be retrained based on effectiveness scores to improve accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual processing methods are used for root cause analysis, then human intuition and expertise can be applied, but resource wastage and errors in defect classification occur
Solution Approach 1:
The patent replaces manual mechanical processing with an automated classification model that uses machine learning algorithms to classify defects, determine priorities, and estimate rework efforts. This substitution eliminates human error in classification while reducing resource consumption through automation.
Solution Approach 2:
The classification model is trained on historical defect data and performs self-learning to improve its accuracy over time. The system automatically processes defect information without requiring continuous human intervention, making the root cause analysis process self-sufficient and efficient.
2Reliability
If manual root cause analysis is performed, then detailed human analysis can be conducted, but time consumption and productivity decrease
Solution Approach 1:
The patent replaces time-consuming manual analysis with an automated classification model that processes defects rapidly. The model maintains reliability by being trained on comprehensive historical data and continuously refined through retraining, while simultaneously increasing processing speed through automation.
Solution Approach 2:
The classification model is pre-trained on historical defect data before actual use, so that when new defects are analyzed, the system already has established patterns and knowledge to quickly and accurately classify them without requiring time-consuming manual analysis each time.
3Measurement precision
If comprehensive defect analysis is performed manually, then accurate prioritization can be achieved, but rework efforts increase
Solution Approach 1:
The patent replaces manual priority determination with an automated classification model that uses algorithms to accurately assess and prioritize defects based on their characteristics and historical data. This automation maintains determination accuracy while eliminating the time-consuming manual rework associated with repeated analysis.
Solution Approach 2:
The classification model incorporates feedback mechanisms where the effectiveness of predicted corrective actions is evaluated and used to retrain the model. This continuous improvement loop enhances priority determination accuracy over time while reducing the need for manual rework and time investment.
Data Source
AI summary
A device trains a classification model with defect classifier training data to generate a trained classification model and processes information indicating priorities and rework efforts for defects, with a Pareto analysis model, to select a set of classes for the defects. The device calculates defect scores for the set of the classes and selects a particular class, from the set of the classes, based on the defect scores. The device processes a historical data set for the particular class to identify a root cause corrective action (RCCA) recommendation and processes information indicating a defect associated with the particular class, with the trained classification model, to generate a predicted RCCA recommendation for the defect. The device processes the predicted RCCA recommendation and the RCCA recommendation, with a linear regression model, to determine an effectiveness score for the predicted RCCA recommendation and retrains the classification model based on the effectiveness score.