Graphical Model for Vehicle Maintenance Logistics Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Aircraft maintenance resource allocation is often inaccurate, leading to resource shortages or surpluses, which can delay maintenance or incur additional costs, and scheduling challenges arise due to time-limited scenarios and changing mission objectives during active missions.
Innovation Solution
A computing system generates a graphical model of locations, vehicles, and maintenance resources, computing a logistic plan that assigns resources to minimize or maximize a maintenance plan objective function while ensuring the assignment satisfies vulnerability assessment constraints, iteratively updating the plan to account for resource availability and potential disruptions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If maintenance resources are allocated to multiple locations, then vehicle operability is improved, but resource assignment complexity increases
Solution Approach 1:
The system segments the maintenance resource allocation problem into discrete graphical model components representing locations, vehicles, and resources. Each element is modeled as a separate node or entity in the graphical representation, allowing complex multi-location assignments to be broken down into manageable segments that can be optimized independently and then integrated.
Solution Approach 2:
The patent introduces a computational intermediary system that processes the complex resource assignment problem. This intermediary computes optimal assignments by evaluating multiple constraints and objectives, transforming the complex decision-making process into a systematic computation that resolves the contradiction between achieving high vehicle operability and managing resource assignment complexity.
2Reliability
If maintenance resources are oversupplied to ensure availability, then vehicle operability is improved, but resource allocation cost increases
Solution Approach 1:
The system performs preliminary computation of optimal resource assignments before maintenance operations begin. By pre-calculating the precise resource allocation needed based on vehicle schedules, maintenance requirements, and location demands, the system avoids both oversupply and undersupply, optimizing the quantity of resources allocated to achieve vehicle operability without unnecessary cost.
Solution Approach 2:
The patent dynamically adjusts resource allocation parameters based on changing conditions such as vehicle health status, maintenance urgency, and location-specific demands. This parameter optimization allows the system to allocate the minimum necessary resources to maintain vehicle operability, avoiding the cost of static oversupply while ensuring resources are available when needed.
3Reliability
If maintenance scheduling is optimized for mission objectives, then mission success probability is improved, but scheduling complexity increases
Solution Approach 1:
The maintenance scheduling system is designed to be dynamic rather than static. It continuously adapts to changing mission objectives, vehicle conditions, and resource availability by recomputing optimal schedules. This dynamic approach allows the system to optimize for mission success probability while managing scheduling complexity through systematic recomputation rather than complex manual planning.
Solution Approach 2:
The system incorporates feedback mechanisms that monitor vehicle health data, maintenance status, and mission requirements in real-time. This feedback informs the scheduling optimization process, allowing the system to adjust maintenance plans to maximize mission success probability while keeping scheduling complexity manageable through data-driven decision-making rather than complex heuristic rules.
4Reliability
If vulnerability assessment constraints are enforced, then resource assignment robustness is improved, but logistic plan flexibility decreases
Solution Approach 1:
The system applies vulnerability assessment constraints partially rather than universally to all resource assignments. By identifying and enforcing constraints only where critical vulnerabilities exist, the system achieves robustness in key areas while maintaining flexibility in less critical assignments. This selective application of constraints resolves the contradiction between robustness and flexibility.
Solution Approach 2:
The patent applies different levels of vulnerability assessment enforcement to different locations, vehicles, or resource types based on their specific risk profiles. Critical assets or locations receive stricter constraint enforcement for robustness, while less critical elements maintain greater flexibility. This localized quality approach allows the logistic plan to be both robust where needed and flexible where appropriate.
Data Source
AI summary
A computing system including one or more processing devices configured to generate a graphical model of locations, vehicles, and vehicle maintenance resources. The processing devices receive vehicle health signal data and maintenance event data. The processing devices compute a logistic plan based on the graphical model. The logistic plan includes an assignment of the vehicles and resources among the locations. Computing the logistic plan includes determining that the assignment satisfies a vulnerability assessment constraint. Over a plurality of maintenance plan generating iterations, the processing devices compute a maintenance plan for the vehicles that minimizes or maximizes a maintenance plan objective function. Each of the iterations includes computing the maintenance plan based on the vehicle health signal data, the maintenance event data, and the logistic plan, and modifying the logistic plan if performing the maintenance plan would violate the vulnerability assessment constraint. The processing devices output the logistic and maintenance plans.