Machining Estimation Model Using Extended Experimental Plans

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional methods for device machining face challenges in estimating objective variables without in-line measurement data, requiring additional experimental designs and increasing the number of experiments needed, even when the input variables cannot generate experimental points as designed.

Innovation Solution

A generation method that acquires and extends plan information to derive relationships between different types of machining information, allowing for the estimation of machining results using a model generated from second and third type information obtained during machining, without necessitating new experiments as output variables.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional methods are used to estimate objective variables without in-line measurement data, then estimation can be performed, but the number of experiments required increases significantly

Engineering Contradiction:

Improveestimation accuracyVSAvoidnumber of experiments

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary experimental design and data collection to build a polynomial model before actual machining operations. By pre-establishing the relationship between input variables and objective variables through controlled experiments, the system avoids needing to perform additional experiments during production while maintaining accurate estimation capabilities.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent transforms the estimation problem by changing the mathematical representation from direct physical measurement to polynomial function approximation. By expressing objective variables as polynomial functions of input variables, the system can estimate outcomes without direct measurement, reducing the need for repeated experiments while maintaining accuracy.

Inventive Principle:

Principle #35Parameter changes

2Device complexity

If polynomial models are used with accumulated measurement data, then the number of measurement steps can be suppressed, but the model accuracy may be insufficient when physical models are difficult to configure

Engineering Contradiction:

Improvemeasurement stepsVSAvoidestimation accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent employs dynamic model selection and adaptive polynomial fitting that adjusts to the specific characteristics of the machining process. Rather than using a fixed model structure, the system adapts the polynomial degree and parameters based on the accumulated measurement data, allowing it to achieve high accuracy without requiring complex physical models or numerous measurement steps.

Inventive Principle:

Principle #15Dynamics

3Measurement precision

If experimental designs are extended to ensure uniformity between input and output variables, then estimation accuracy improves, but the complexity of experimental planning increases

Engineering Contradiction:

Improveuniformity of variablesVSAvoidexperimental planning

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent creates a universal polynomial modeling framework that can handle multiple input and output variables simultaneously. By establishing a general mathematical relationship that works across different variable types and machining conditions, the system achieves uniformity in variable relationships without requiring separate complex experimental designs for each variable combination.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20230070635A1Generation method, estimation method, generation device, and estimation device

Publication Date: 2023.03.09 PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO LTD

AI summary

Experimental device machining is performed according to plan information including first type information indicating a first type condition of the experimental device machining and second type information indicating a second type condition of the experimental device machining. Third type information indicating a third type result and fourth type information indicating a fourth type result are acquired. Extended plan information is acquired in which a uniformity of extended second type information and extended third type information is equal to or greater than a threshold value. Extended third type information indicating a third type result and extended fourth type information indicating a fourth type result are acquired by performing the experimental device machining according to the extended plan information. An extended first relationship is derived that is a relationship between extended first type information, the extended second type information, and the extended third type information. An extended second relationship is derived that is a relationship between the extended first type information, the extended second type information, and the extended fourth type information. A model for estimating fourth type information indicating a fourth type result of actual device machining by receiving the second type information measured during the actual device machining and the third type information measured during the actual device machining and using the extended first relationship and the extended second relationship is generated. The model is output.