Production Record Analysis for Sudden Defect Root Cause Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In manufacturing processes, identifying the cause of substandard product performance is challenging due to complex processes and large volumes of data, leading to timeliness and accuracy issues in defect diagnosis.
Innovation Solution
A data processing method that acquires production records, determines high-incidence time periods of defects, and calculates the influence degree of process information on sudden defects using statistical analysis and machine learning techniques, facilitating automatic diagnosis and quick decision-making.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual analysis of production records is used to identify defect causes, then analysis accuracy can be maintained, but detection efficiency and timeliness deteriorate due to large volumes of data
Solution Approach 1:
The patent replaces manual mechanical analysis with an automated computer-based system that collects production information, calculates defect indices, and identifies high-incidence time periods automatically. This substitution dramatically improves detection efficiency while reducing diagnosis time.
Solution Approach 2:
The system performs self-service by automatically collecting production data, calculating defect indices, identifying high-incidence periods, and determining process information influence degrees without requiring manual intervention at each step, thereby improving productivity and reducing time loss.
2Measurement precision
If comprehensive process information is analyzed to accurately identify defect causes, then diagnosis accuracy improves, but system complexity increases
Solution Approach 1:
The patent segments the complex analysis task into distinct modules: collecting production information, calculating defect indices, identifying high-incidence time periods, and determining process information influence. This segmentation maintains comprehensive analysis while organizing system complexity into manageable components.
Solution Approach 2:
The system transforms comprehensive process information into quantifiable parameters such as defect indices and influence degrees through standardized calculations. This parameter transformation enables accurate diagnosis while simplifying the handling of complex process data through consistent mathematical operations.
3Measurement precision
If detailed production records are collected for all samples, then defect analysis accuracy improves, but data processing complexity and time consumption increase
Solution Approach 1:
The patent extracts only the essential production information needed for defect analysis while discarding redundant data. By focusing on critical process parameters and their temporal relationships, the system maintains high analysis accuracy without being overwhelmed by excessive data volume.
Solution Approach 2:
The system applies partial action by selectively analyzing only the most relevant process information for each defect case rather than processing all available data uniformly. This approach maintains diagnostic accuracy while reducing unnecessary data processing overhead.
Data Source
AI summary
A data processing method, comprising: acquiring a production record corresponding to each sample of a plurality of samples, the production record including process information, a production time corresponding to the process information, and an index value; determining a high-incidence time period of defects according to index values and production times corresponding to the process information in acquired production records of a plurality of samples; determining an influence degree of the process information on sudden defect according to the high-incidence time period of defects and the acquired production records.