Machining Diagnosis Using Stable Cutting Section Extraction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing machining diagnosis techniques process unusable data, leading to inefficient data processing and inaccurate abnormality determination in machining tools, resulting in unnecessary component replacements.

Innovation Solution

A machining diagnosis device that acquires machining data, extracts stable machining sections, cleanses the data, calculates features, and diagnoses abnormalities, thereby eliminating the processing of unusable data and improving accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If machining data throughout the entire machining period is used to determine abnormality, then more data is available for analysis, but data processing efficiency decreases due to processing unusable data

Engineering Contradiction:

Improveabnormality determination accuracyVSAvoiddata processing efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The machining period is segmented into stable machining periods and unstable machining periods. Only data from stable machining periods is extracted and used for abnormality determination, while data from unstable periods is excluded. This segmentation resolves the contradiction by processing only relevant data segments, improving both efficiency and accuracy.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The cutting section extractor extracts and isolates machining data corresponding to stable machining periods from the entire machining data set. By taking out only the usable portion of data for further processing, the system eliminates waste of computational resources on unusable data while maintaining determination accuracy.

Inventive Principle:

Principle #2Taking out (Extraction)

2Quantity of substance

If machining data including unstable periods is used for diagnosis, then comprehensive data is obtained, but diagnosis accuracy decreases due to inclusion of unusable data

Engineering Contradiction:

Improvevolume of machining dataVSAvoiddiagnosis accuracy

Core Design Contradiction:

Quantity of substanceVSMeasurement precision

Solution Approach 1:

The machining data is divided into stable and unstable segments based on machining condition analysis. Only the stable segments are selected for diagnosis, ensuring that the quantity of data used is optimized for accuracy rather than simply maximizing volume.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Different quality standards are applied to different portions of machining data. Stable machining period data is deemed high quality and used for diagnosis, while unstable period data is deemed low quality and excluded. This local quality assessment resolves the contradiction between data quantity and diagnosis accuracy.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS20230120046A1Machining diagnosis device, learning device, inference device, machining diagnosis method and recording medium

Publication Date: 2023.04.20 MITSUBISHI ELECTRIC CORP

AI summary

A machining diagnosis device (100) includes a machining data acquirer (3) to acquire, from a machining tool (1), machining data including a result of machining performed based on a machining condition, a cutting section extractor (4) to extract, from the acquired machining data, a cutting section corresponding to a stable machining period and machining data for the cutting section, a cleansing unit (8) to acquire the machining condition for cutting and perform, in accordance with the acquired machining condition, cleansing of the machining data extracted by the cutting section extractor (4), a feature calculator (9) to calculate a feature based on the cleansed machining data, and a machining diagnoser (11) to diagnose machining based on the calculated feature.