Mounting Error Cause Estimation Using Two-Factor Bias Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional methods for estimating the cause of mounting errors in component mounters often inaccurately identify individual devices or data as causative, failing to account for multiple factors, leading to unreliable error determination.

Innovation Solution

A device and method that select two types of factors potentially causing the error, performing determinations while replacing each factor to acquire multiple results, providing a more reliable estimation of the causative individual by assessing bias in error occurrence status across different combinations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional ranking methods are used to identify causative individuals, then the estimation process is simple, but the reliability of error cause identification deteriorates due to inability to account for multiple factors

Engineering Contradiction:
Improvereliability of error cause identificationVSAvoidcomplexity of estimation method
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The estimation method segments the analysis by separating the first factor (whose individual is being evaluated) from the second factor (whose individuals are being compared). This segmentation allows the system to evaluate whether error occurrence status is biased according to differences in the second factor, thereby improving reliability without requiring a completely complex new approach.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The invention introduces a new dimension of analysis by examining error occurrence status across combinations of multiple factors rather than simply ranking individual devices. By analyzing whether error rates vary according to differences in one factor while holding another factor constant, the method achieves more reliable causative individual identification through multi-dimensional analysis.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Measurement precision

If multiple factors are considered in error estimation, then the accuracy of causative individual identification improves, but the complexity of the estimation process increases

Engineering Contradiction:
Improveprecision of error cause estimationVSAvoidcomplexity of estimation process
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The method segments the estimation process into distinct steps: selecting two types of factors, obtaining error occurrence status for combinations of individuals, and determining bias according to differences in one factor. This segmentation makes the multi-factor analysis more manageable and less complex than a comprehensive simultaneous analysis of all factors.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The invention applies partial action by focusing on two specific factors at a time rather than analyzing all possible factors simultaneously. This partial approach achieves improved precision through multi-factor consideration while keeping the process complexity manageable by limiting the scope of each estimation cycle.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3944730B1Device for estimating cause of mounting error, and method for estimating cause of mounting error
Publication Date: 2024.07.10 FUJI CORP
  • EP3944730B1 patent drawingFigure 1~2
  • EP3944730B1 patent drawingFigure 3
  • EP3944730B1 patent drawingFigure 4~5

AI summary

A device for estimating a cause of a mounting error includes an error history storage section configured to aggregate and store an error occurrence status of a mounting error that mounting work of mounting a component on a board has failed in a component mounter by dividing the error occurrence status into individuals of devices and data, a factor setting section configured to select two types of factors from among the devices and the data and to respectively set the selected factors as a first factor and a second factor, a first determination section configured to perform a process of determining whether the error occurrence status is biased under a condition that an individual as the first factor is specified according to a difference in the second factor, on each of multiple individuals as the first factor, a second determination section configured to perform a process of determining whether the error occurrence status is biased under a condition that an individual as the second factor is specified according to a difference in the first factor, on each of multiple individuals as the second factor, and a cause estimation section configured to estimate a causative individual causing the mounting error based on determination results in the first determination section and the second determination section.