Fleet Maintenance Scheduling via Graph Divergence Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Maintenance schedules for fleets of assets often need updating due to changes in asset health predictions, but frequent updates can disrupt material and worker schedules, and existing tools do not adequately address the need to balance reactivity with overall fleet efficiency.
Innovation Solution
A method that constructs a graph representing the current state of assets, scores divergence from a previous state, and adjusts the maintenance schedule only when the divergence exceeds a threshold, using asset health scores and criticality scores to determine node and edge weights, and employs linear optimization to minimize schedule deviations while maximizing system reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If maintenance schedules are updated frequently to reflect changes in asset health predictions, then fleet reliability is improved, but worker and material schedule disruption increases
Solution Approach 1:
The system changes the parameter of schedule update frequency by introducing a divergence threshold. Instead of updating schedules frequently or continuously, the system monitors asset health predictions and only triggers schedule updates when the divergence from the previous state exceeds a predefined threshold, thus balancing reliability improvement with schedule stability
Solution Approach 2:
The system implements feedback by continuously monitoring asset health predictions and comparing them against previous states. The divergence scoring mechanism provides feedback on how much asset conditions have changed, and this feedback loop enables the system to determine when schedule updates are necessary versus when to maintain the existing schedule to avoid disruption
2Stability of the object's composition
If maintenance schedules are updated less frequently to reduce disruption, then worker and material schedule stability is improved, but fleet reliability may deteriorate
Solution Approach 1:
The system adjusts the update frequency parameter dynamically based on the divergence score. When divergence is low, updates are suppressed to maintain schedule stability. When divergence exceeds the threshold, updates are triggered to maintain fleet reliability, thus adaptively balancing both objectives
Solution Approach 2:
The maintenance schedule update mechanism is made dynamic rather than static. The system continuously evaluates asset health predictions and adjusts the update decision in real-time based on the divergence from previous states, allowing the system to respond appropriately to changing conditions while maintaining overall stability
Data Source
AI summary
A graph representing a current state of a set of assets is constructed, a weighted node in the graph representing an asset in the set of assets, a weighted edge in the graph representing a connection between two assets in the set of assets, a weight of the weighted node determined using an asset health score of the asset, a weight of the weighted edge determined according to an importance of the connection. A divergence between the graph and a previous graph representing a previous state of the set of assets is scored, the scoring resulting in a divergence score. Responsive to the divergence score being above a threshold score, a current maintenance schedule of the set of assets is adjusted, the adjusting resulting in an adjusted maintenance schedule.