Asset Maintenance Scheduling via Health Condition Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current maintenance policies, such as scheduled maintenance, do not consider the future health condition of assets and are often costly due to continuous monitoring, leading to inefficient resource allocation.
Innovation Solution
A system and method that uses asset aging prediction based on electrical models, asset data, and external data to compute optimal preventive maintenance intervals for each asset, minimizing deviation from these intervals while adhering to labor and budget constraints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If continuously monitoring the condition indicator is performed, then the health condition assessment accuracy is improved, but the operational cost increases
Solution Approach 1:
The patent implements periodic condition monitoring instead of continuous monitoring. The system performs condition assessments at discrete time intervals determined by optimizing the monitoring frequency to balance accuracy requirements with operational costs. This periodic approach reduces the total number of monitoring operations while maintaining sufficient health condition assessment accuracy.
Solution Approach 2:
The patent dynamically adjusts the monitoring frequency parameter based on asset-specific characteristics and operational requirements. By changing the monitoring interval parameter from a fixed continuous approach to a variable periodic approach, the system optimizes the balance between measurement precision and operational cost for different assets and conditions.
2Stability of the object's composition
If scheduled maintenance is performed, then the maintenance consistency is improved, but the resource allocation efficiency deteriorates
Solution Approach 1:
The patent transitions from static scheduled maintenance to dynamic condition-based maintenance. The maintenance timing is dynamically adjusted based on actual asset condition indicators, allowing the system to adapt maintenance activities to real-time asset state while optimizing resource allocation efficiency through data-driven decision making.
Solution Approach 2:
The system implements feedback mechanisms where condition monitoring data is continuously used to adjust maintenance scheduling. The feedback loop allows the system to learn from actual asset performance and refine future maintenance decisions, improving both consistency and resource allocation efficiency through iterative optimization.
3Reliability
If condition-based maintenance is performed, then the maintenance relevance is improved, but the computational complexity increases
Solution Approach 1:
The patent segments the maintenance optimization problem into independent asset-level optimization problems. Each asset's maintenance schedule is determined separately based on its specific condition indicators and failure characteristics, reducing the computational complexity of solving a system-wide optimization problem while maintaining high maintenance relevance through individualized approaches.
Solution Approach 2:
The system uses simplified predictive models that replicate key asset behavior patterns without requiring complex full-system simulations. By creating manageable copies of asset failure models that capture essential characteristics, the system achieves maintenance relevance while keeping computational requirements at practical levels.
Data Source
AI summary
There are provided a system, a method and a computer program product for generating an optimal preventive maintenance/replacement schedule for a set of assets. The method includes receiving data regarding an asset, said data including a failure rate function of said asset, a cost of preventative maintenance (PM) of said asset, a cost of an asset failure, and a cost of replacing an asset. An optimal number K of preventative maintenance time intervals tk and an indication of a possible replacement is computed and stored for each asset by minimizing a mean cost-rate value function with respect to an electrical age of the asset. A first PM schedule is formed without consideration of labor and budget resource constraints. The method further generates a second maintenance schedule for a system of assets by minimizing a deviation from the optimal PM time intervals subject to the labor and budget resource constraints.