Machine Component State Forecasting for Predictive Maintenance

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for predicting the future states of machine components, such as imminent damage or maintenance requirements, rely heavily on operator experience and empirical values, leading to inconsistent and potentially inaccurate interpretations of measured parameters, which can result in unplanned failures and inefficient maintenance schedules.

Innovation Solution

A computer-assisted method that selects representative parameters for machine components, records measured values, and uses a database-driven process to interpret these values based on influence quantities and interactions, generating actionable recommendations through a self-learning system that improves over time, allowing for precise forecasting of machine component states and optimized maintenance planning.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If parameter interpretation is based on operator experience and empirical values, then maintenance decisions can be made using simple methods, but the reliability and consistency of predictions deteriorate due to subjective variability

Engineering Contradiction:

Improvesimplicity of maintenance decision methodVSAvoidconsistency of damage prediction

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The patent replaces the mechanical system of human operator interpretation with an automated computer-based evaluation system. The control device automatically compares measured operating parameters against stored reference values and predetermined criteria, eliminating subjective human judgment while maintaining operational simplicity through automated decision support.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an intermediary computer system that acts as a mediator between raw measured parameters and maintenance decisions. This intermediary automatically processes and evaluates the data, providing objective recommendations that bridge the gap between simple measurement and reliable prediction without requiring operator expertise.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If regular maintenance is performed based on maintenance plans, then the risk of spontaneous failure is reduced, but productivity deteriorates due to unplanned downtime and inefficient maintenance scheduling

Engineering Contradiction:

Improvereduction of spontaneous failure riskVSAvoidmaintenance efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent enables preliminary action by predicting future operating states and damage risks before they materialize. The system continuously evaluates current parameters against historical data and failure patterns, allowing maintenance to be scheduled in advance based on actual component condition rather than reactive or purely time-based approaches.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent transforms static maintenance schedules into dynamic, adaptive maintenance planning. The system adjusts maintenance recommendations based on real-time operating conditions, actual component degradation rates, and predicted future states, allowing optimization of maintenance timing to balance reliability with productivity.

Inventive Principle:

Principle #15Dynamics

3Reliability

If monitored parameters are used to trigger maintenance actions, then component failures can be prevented, but measurement precision deteriorates when limit values are based on empirical rather than objective criteria

Engineering Contradiction:

Improvefailure prevention capabilityVSAvoidaccuracy of limit value determination

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent implements feedback by continuously comparing measured parameters against dynamically updated reference values derived from actual failure data and operational history. The system learns from accumulated data to refine its evaluation criteria, improving the precision of limit values over time while maintaining reliable failure prevention through automated monitoring and alerting.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11016480B2Method for computer-assisted forecasting of future operating states of machine components

Publication Date: 2021.05.25 WALTHER FLENDER

AI summary

Provided is a method for forecasting future operating states of machine components, which includes the respective machine component considered, a parameter that is selected that is representative of the state of the machine component, the parameter is recorded as a measured value during ongoing use of the machine component and, taking into account the use case for which the machine component is used, the measured value recorded is fed into an automatically running process for finding a recommendation for action. A system is also disclosed.