Manufacturing Instruction Evaluation System Using Multiple Regression

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional manufacturing instruction evaluation systems lack the ability to calculate the correlation between manufacturing instruction parameters and manufacturing performance, relying on human judgment and resulting in ineffective utilization of performance data.

Innovation Solution

A manufacturing instruction evaluation support system that employs multiple regression analysis to calculate risk rates, correlation coefficients, and regression equations, identifying optimal parameters and generating new instruction parameters based on performance data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If multiple regression analysis is implemented to calculate correlation between manufacturing instruction parameters and manufacturing performance, then manufacturing performance data utilization is improved, but system complexity increases

Engineering Contradiction:

Improvemanufacturing performance data utilizationVSAvoidsystem complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The patent introduces a data processing intermediary layer that includes a data reading component, parameter sorting component, and regression equation calculating component. This intermediary layer processes manufacturing performance data and instruction parameters through multiple regression analysis, converting raw data into meaningful correlation insights without requiring the entire system to handle the complexity directly.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces manual human judgment and evaluation mechanisms with automated statistical analysis systems. Instead of relying on operators to manually assess manufacturing performance and adjust parameters, the system uses multiple regression analysis algorithms to automatically calculate correlations, risk rates, and optimal parameter settings, substituting mechanical human decision-making with computational analysis.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Manufacturing precision

If multiple regression analysis is used to identify optimal parameters, then manufacturing instruction accuracy is improved, but calculation time and processing resources increase

Engineering Contradiction:

Improvemanufacturing instruction accuracyVSAvoidcalculation time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary data processing and parameter sorting before executing the full multiple regression analysis. The system pre-processes manufacturing performance data, organizes instruction parameters, and prepares datasets in advance, which reduces the computational burden during the actual regression analysis and speeds up the overall process.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements a staged analysis approach where the system first calculates risk rates for individual parameters, then progressively builds regression models. This partial action approach allows the system to identify obviously suboptimal parameters early and focus computational resources on the most influential parameters, reducing overall calculation time while maintaining accuracy.

Inventive Principle:

Principle #16Partial or excessive action

3Reliability

If risk rate calculation is performed for each manufacturing instruction parameter, then parameter evaluation reliability is improved, but processing complexity increases

Engineering Contradiction:

Improveparameter evaluation reliabilityVSAvoidprocessing complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the parameter evaluation process into distinct components: a data reading component that collects raw data, a parameter sorting component that calculates risk rates for individual parameters, and a regression equation calculating component that synthesizes these into overall evaluations. This segmentation allows each component to handle specific tasks with high reliability while reducing the complexity burden on any single part of the system.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS8000819B2Manufacturing instruction evaluation support system, manufacturing instruction evaluation support method, and manufacturing instruction evaluation support program

Publication Date: 2011.08.16 HITACHI LTD

AI summary

A manufacturing instruction evaluation support system includes a data reading part that reads a manufacturing instruction parameter group and manufacturing performance data corresponding thereto, a parameter sorting part that calculates a risk rate for each manufacturing instruction parameter configuring the manufacturing instruction parameter group and an average value of risk rates among the manufacturing instruction parameters to identify as available choices the manufacturing instruction parameters having the risk rates no greater than the average value, a parameter identifying part that calculates an explanatory variable selection reference value for the manufacturing instruction parameter group and the manufacturing instruction parameters of the available choices with the multiple regression analysis program to identify the manufacturing instruction parameter group or the manufacturing instruction parameters of the available choices having the greater calculated explanatory variable selection reference value as optimum parameters, and a regression equation calculating part that calculates and displays a regression equation when employing the optimum parameters with the multiple regression analysis program.