Maintenance Management System Using Predictive Failure Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current maintenance management methods focus primarily on reactive maintenance after machine failure, lacking preventive measures and efficient strategies for managing multiple maintenance contracts across various geographic sites, leading to inconsistent performance and increased downtime.

Innovation Solution

A method that identifies potential machine component failures, assigns criticality factors based on probability and consequence, and triggers maintenance tasks proactively, including predictive, preventive, and reactive maintenance, with a record-keeping system to optimize maintenance management and improve performance metrics.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If reactive maintenance is performed after machine failure, then repair can be carried out, but machine downtime increases and productivity decreases

Engineering Contradiction:
Improvemachine reliabilityVSAvoidmachine downtime
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary maintenance actions by monitoring machine components and predicting failures before they occur. When the predicted probability of failure exceeds a threshold, maintenance is scheduled in advance, allowing for planned downtime rather than unexpected breakdowns, thus reducing overall machine downtime and improving reliability.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If preventive maintenance is implemented to prevent failures, then machine reliability improves, but maintenance costs and operational complexity increase

Engineering Contradiction:
Improvemachine reliabilityVSAvoidmaintenance management complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system dynamically adjusts maintenance strategies by changing parameters such as the failure probability threshold. When the predicted probability of failure exceeds this threshold, predictive maintenance is triggered. This parameter-based approach allows the system to optimize between reliability and complexity by adjusting the threshold based on machine criticality and operational context.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system implements feedback loops where maintenance outcomes are recorded and used to refine future maintenance decisions. By analyzing whether predicted failures actually occurred and how maintenance performance, the system continuously improves its predictions and adjusts maintenance strategies, reducing unnecessary maintenance while maintaining reliability.

Inventive Principle:
Principle #23Feedback

3Ease of operation

If ad-hoc maintenance management is used relying on personnel experience, then flexibility is maintained, but performance consistency across multiple contracts deteriorates

Engineering Contradiction:
Improvemaintenance flexibilityVSAvoidservice contract performance consistency
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system enables self-service maintenance management by automatically monitoring machine parameters, predicting failures, and generating maintenance work orders without relying on human expertise. The system independently analyzes data from multiple machines across different locations and consistently applies the same predictive algorithms, ensuring uniform performance across all service contracts while eliminating variability introduced by human operators.

Inventive Principle:
Principle #25Self-service

4Reliability

If monitoring of machine operating conditions is implemented to identify imminent failures, then failure prevention capability improves, but system complexity and monitoring costs increase

Engineering Contradiction:
Improvefailure prediction capabilityVSAvoidmonitoring system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system replaces complex mechanical monitoring equipment with data-driven predictive analytics. Instead of using sophisticated sensors and mechanical monitoring systems, the invention analyzes existing operational data patterns to predict failures. This substitution of mechanical/physical monitoring with computational analysis reduces system complexity while maintaining or improving failure prediction capability.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS7496475B2Maintenance management of a machine
Publication Date: 2009.02.24 SOLAR TURBINES INC
  • US7496475B2 patent drawing
  • US7496475B2 patent drawing
  • US7496475B2 patent drawing

AI summary

Methods of providing maintenance management of a machine are disclosed. In one embodiment, the method involves identifying a machine component failure that, if not repaired, will result in a functional failure of the machine. A criticality factor is assigned to the machine component failure based on at least a probability of occurrence of the functional failure and a consequence of the functional failure to a machine user. A maintenance task is generated to repair the machine component failure, and a triggering condition that activates the maintenance task is defined. The method further involves conducting a machine repair in response to a detection of the triggering condition, and maintaining a record that includes information relating to the conducted machine repair. The method of providing maintenance management is also modified based on at least the record.