Automated Reliability Range Determination for Machine Component Life Prediction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional methods for predicting the life consumption of machine components are inaccurate due to various variables, leading to inefficient and time-consuming manual evaluation of parameter values, which can result in unnecessary component replacement and potential operational failures.

Innovation Solution

A method is introduced to automatically determine a reliability range for parameter values from multiple load sessions, sorting out unrealistic values and iteratively adjusting the range to ensure only reliable values are used for life consumption predictions, thereby reducing manual workload and improving prediction accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual evaluation of parameter values is performed to ensure accuracy, then reliability of life consumption predictions is improved, but time consumption and workload increase significantly

Engineering Contradiction:

Improvereliability of life consumption predictionsVSAvoidtime consumption for manual evaluation

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs self-evaluation of parameter values through automated plausibility checks and consistency validations. The computer automatically identifies unrealistic parameter values and flags them for review, eliminating the need for manual evaluation of every parameter while maintaining reliability through systematic automated checking.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The manual mechanical evaluation process is replaced with an automated computer-based system that uses algorithms to assess parameter plausibility. The system substitutes human engineers' manual review with automated computational methods that can rapidly evaluate multiple parameters against predefined criteria and historical data.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If all parameter values are manually verified to ensure accuracy, then prediction reliability is improved, but productivity decreases due to time-consuming evaluation

Engineering Contradiction:

Improveprediction accuracyVSAvoidevaluation efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

Instead of verifying all parameter values manually, the system applies partial verification by automatically checking only those parameters that fail plausibility tests or consistency validations. This selective approach maintains prediction accuracy for critical parameters while dramatically improving overall evaluation efficiency by skipping obvious cases.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system implements feedback mechanisms where automated evaluation results are used to refine evaluation criteria and improve future assessments. The computer learns from identified unrealistic parameters and adjusts its plausibility checks, creating a continuous improvement cycle that enhances both reliability and productivity over time.

Inventive Principle:

Principle #23Feedback

3Duration of action of stationary object

If safety limits are reduced to improve accuracy, then operational lifetime is extended, but component replacement frequency increases if predictions are too optimistic

Engineering Contradiction:

Improveoperational lifetimeVSAvoidprediction accuracy

Core Design Contradiction:

Duration of action of stationary objectVSReliability

Solution Approach 1:

The system performs preliminary automated validation of parameter values before they are used in life consumption calculations. By pre-identifying and flagging unrealistic parameters through automated plausibility checks, the system ensures that only validated data enters the prediction model, improving accuracy and enabling more reliable extension of operational lifetimes without excessive safety margins.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS10073007B2Reliability limits of machines and components thereof

Publication Date: 2018.09.11 GKN AEROSPACE SWEDEN AB

AI summary

A reliability range is determined for a parameter of a component in a machine subjected to life reducing loads during operation, comprising the steps of: acquiring, for each of a plurality of load sessions, at least one parameter value for said component; generating a distribution pattern containing said parameter values for the plurality of load sessions; assigning a reliability range for the distribution pattern, wherein parameter values outside said reliability range are considered as being unrealistic; analyzing the parameter values outside the reliability range to determine which of said parameter values outside the reliability range are confirmed to be unrealistic; and adjusting the reliability range if a ratio between the confirmed unrealistic parameter values and the considered unrealistic parameter values is outside a further range being predetermined for the ratio.