Machining Diagnosis Using Cycle-Based Characteristic Modeling

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for diagnosing abnormalities in machining devices are limited in providing versatile evaluation, as they primarily display chatter estimation information and detected chatter spectra without comprehensive analysis.

Innovation Solution

A diagnosis system that includes a diagnosis apparatus connected to a machining device, which extracts characteristic information from detected physical quantities, generates models for normal operation, and determines abnormality by using context and detection information, enabling comprehensive evaluation and display of time-series data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If only chatter estimation information and detected chatter spectrum are displayed, then the display is simple, but the evaluation is not versatile

Engineering Contradiction:
Improveevaluation versatilityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The diagnosis apparatus performs multiple functions including detecting physical quantities, extracting characteristic information, generating models, determining abnormalities, and displaying results. This multi-functional approach enables versatile evaluation while integrating all functions into a unified system that manages complexity through functional integration

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Measurement precision

If comprehensive analysis and model generation are performed, then evaluation versatility is improved, but processing time increases

Engineering Contradiction:
Improvediagnosis precisionVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system generates models during normal operation based on detected physical quantities and characteristic information. This preliminary model generation enables rapid abnormality determination when needed, as the comparison framework is already established, reducing processing time during actual diagnosis while maintaining comprehensive analysis capabilities

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors physical quantities, compares them against generated models, and provides feedback on abnormality determinations. This feedback mechanism allows the system to learn and refine its models over time, improving diagnosis precision while optimizing processing efficiency through iterative refinement rather than repeated comprehensive analysis

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3540534B1Information processing apparatus, method and computer readable medium
Publication Date: 2024.01.17 RICOH CO LTD
  • EP3540534B1 patent drawingFigure 1
  • EP3540534B1 patent drawingFigure 2
  • EP3540534B1 patent drawingFigure 3

AI summary

An information processing apparatus (100) includes: a detected information receiver (112) configured to obtain physical quantity information indicating a physical quantity that occurs in a target device (200) and changes in accordance with operation of the target device; a characteristic information generator (102a) configured to generate characteristic information indicating a characteristic of the physical quantity information; a data manager (103) configured to classify the characteristic information into a plurality of stages contained in one cycle, so as to generate a plurality of pieces of characteristic information for each cycle, the cycle being a cycle including the plurality of stages and to be repeatedly executed by the target device; a storage unit (113) configured to store the plurality of pieces of characteristic information for each cycle; and an output control unit (104) configured to output one or more pieces of the plurality of pieces of characteristic information for a plurality of cycles that are different to an output unit (115).