Machine Parameter Adjustment Using Health Metrics to Extend Lifetime
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods struggle to determine how to adjust machine parameter settings to extend the remaining useful life of machines, as it is difficult to assess the impact of parameter changes on equipment health and impending failures.
Innovation Solution
A system that periodically collects data from machines, calculates health metric values based on operational and health data, estimates unknown health metric values, and automatically adjusts parameter settings for the healthiest and least healthy machines to maximize equipment life.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Duration of action of stationary object
If machine parameter settings are manually adjusted to extend equipment life, then remaining useful equipment life is improved, but the complexity of determining optimal parameter adjustments increases
Solution Approach 1:
The system enables machines to automatically adjust their own parameter settings based on real-time health metrics and operational data. The machine self-monitors its condition, self-diagnoses potential issues, and self-adjusts parameters without external intervention, thereby extending equipment life while avoiding the complexity of manual determination processes
Solution Approach 2:
The system continuously monitors machine health metrics, operational parameters, and performance data, then feeds this information back to automatically adjust parameter settings. This closed-loop feedback mechanism enables dynamic optimization of equipment life by constantly adapting parameters based on actual machine condition, eliminating the need for complex manual analysis
2Duration of action of stationary object
If parameter settings are changed to extend equipment life, then machine lifetime is improved, but the risk of suboptimal adjustments causing failure increases
Solution Approach 1:
The system implements conservative parameter adjustments that make small, incremental changes rather than large, risky modifications. By applying partial adjustments based on gradual degradation patterns, the system extends equipment life while minimizing the risk of causing failure through excessive or inappropriate parameter changes
Solution Approach 2:
The system proactively adjusts parameters in advance of predicted failures or critical conditions. By monitoring trends and making preventive adjustments before problems escalate, the system cushions against potential failures and maintains reliable operation, reducing the risk associated with reactive parameter changes
3Duration of action of stationary object
If continuous monitoring and adjustment of machine parameters is implemented, then equipment life is extended, but the energy consumption and operational complexity increase
Solution Approach 1:
The system performs monitoring and parameter adjustments at periodic intervals rather than continuously. Health metrics are calculated and parameters are adjusted at predetermined time intervals, which extends equipment life through regular maintenance while significantly reducing energy consumption compared to continuous monitoring and adjustment operations
Data Source
AI summary
Parameter settings and operational data are received from machines for a current predefined time interval. For each machine, a corresponding health metric value is calculated based on the received operational data and machine health data, and stored in association with the received corresponding parameter settings. Associated unknown health metric values are estimated for machines associated with combinations of parameter settings different from the received parameter settings having at least one of the combinations of parameter settings with an associated previously determined health metric value, and at least one other of the combinations of parameter settings with the associated unknown health metric value, based on the corresponding calculated health metric value and the corresponding previously determined health metric value. Associated parameter settings for at least one healthiest machine and at least one least healthy machine are determined based on the stored health metric values and are automatically adjusted.