Correlation Feature Extraction for Manufacturing Parameter Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data analysis methods struggle to identify influencing parameters when there are few production batches or many parameters, leading to reduced analysis precision and inability to narrow down factors affecting indicator performance in manufacturing processes.
Innovation Solution
A data analysis system that includes a data acquisition unit, a correlation feature value extraction unit, and a parameter extraction unit, which calculates correlation feature values and uses machine learning to extract parameters influencing indicators, even with limited production batches or numerous parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional data analysis methods are used to narrow down parameters, then analysis can be performed when there are sufficient production batches, but analysis precision deteriorates when there are few production batches or many parameters
Solution Approach 1:
The patent transforms the analysis from examining individual parameters to examining correlation features between parameter pairs. By calculating correlation coefficients and extracting correlation feature values, the system adds a dimensional transformation that captures relationships between parameters, enabling effective analysis even with limited production batch data.
Solution Approach 2:
The patent extracts correlation features from the raw parameter data by calculating correlation coefficients between parameter pairs and deriving correlation feature values. This extraction process separates the essential relationship information from the raw data, allowing precise parameter identification without requiring large quantities of production batches.
2Device complexity
If conventional data analysis methods are used to narrow down parameters, then analysis can be performed with manageable complexity, but the ability to narrow down factors deteriorates when there are many parameters
Solution Approach 1:
The patent segments the analysis process into distinct stages: calculating correlation coefficients for each parameter pair, extracting correlation feature values from these coefficients, and then identifying parameters based on these extracted features. This segmentation transforms a complex multi-parameter analysis into a systematic sequence of simpler operations, maintaining manageability while improving identification precision.
Solution Approach 2:
By transitioning from analyzing individual parameters to analyzing correlation relationships between parameter pairs, the patent creates a new dimensional space for analysis. This dimensional transformation reduces the effective complexity by focusing on relationships rather than individual parameter variations, enabling precise factor identification even when many parameters are present.
3Reliability
If conventional data analysis methods are used, then traditional analysis procedures can be followed, but the ability to stabilize product performance deteriorates when key parameters cannot be identified
Solution Approach 1:
The patent employs a feedback mechanism where correlation feature values are calculated from production data, used to identify influential parameters, and then applied to stabilize product performance. This closed-loop feedback enables continuous improvement by systematically identifying and addressing key parameters that affect product quality, thereby enhancing reliability.
Solution Approach 2:
The patent performs preliminary analysis by calculating correlation coefficients and extracting correlation feature values before the actual parameter identification and performance stabilization. This preliminary processing of data relationships prepares the foundation for accurate parameter identification, ensuring that key factors are identified early to guide subsequent performance stabilization efforts.
Data Source
AI summary
A data analysis system includes: a memory; and a processor connected to the memory and that acquires data to be analyzed. The data to be analyzed includes parameters relating to a production element of a product produced in each of production batches; and an indicator for evaluating the product. The processor outputs, to the memory, the acquired data to be analyzed. The memory stores, in each of the production batches, the parameters and the indicator associated with the parameters. The processor calculates a correlation feature value for each of the production batches based on a correlation between the parameters and data of the correlation and the parameters. The processor causes a display to display the calculated feature value.