Failure Predictor Detection Using Environmental Change Mediation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional failure prediction methods incorrectly detect equipment deterioration due to environmental changes, leading to false alarms.

Innovation Solution

A failure predictor detection device that uses a learning model to calculate estimated values from acquired data, compares them with measured values, and detects deviations over time to distinguish between environmental changes and actual equipment failures.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the detection threshold is set to be sensitive to deviations, then failure detection accuracy is improved, but false alarms increase due to environmental changes

Engineering Contradiction:

Improvefailure detection accuracyVSAvoidfalse alarms

Core Design Contradiction:

Measurement precisionVSObject-generated harmful factors

Solution Approach 1:

The patent introduces environmental change data as an intermediary factor in the detection process. By incorporating measurements of environmental conditions (temperature, humidity, pressure, etc.) into the comparison process, the system can distinguish between deviations caused by environmental changes and those caused by actual equipment failures. This intermediary allows the system to maintain sensitive detection thresholds while filtering out false alarms caused by environmental variations.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12572624B1Failure predictor detection device, failure predictor detection method, training device, and trained learning model generation method

Publication Date: 2026.03.10 MITSUBISHI ELECTRIC CORP

AI summary

An object is to obtain a failure predictor detection device that is capable of more adequately detecting a failure predictor. A failure predictor detection device according to the present disclosure includes: an acquisition unit to acquire estimation data and comparison data of targeted equipment for failure predictor detection in a targeted time period for the failure predictor detection; an estimation unit to calculate an estimated value of the comparison data during a normal operation from the estimation data using a learning model; and a detection unit to detect a failure predictor of the equipment on the basis of comparison results at multiple times between the estimated values and measured values shown by the comparison data.