Engine Service Recommendations Using RUL-Based Maintenance Coordination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Engine systems, such as gensets and vehicles, face challenges in determining optimal maintenance schedules, leading to premature repair or delayed maintenance, resulting in inefficiencies and downtime due to the lack of a comprehensive approach to analyze remaining useful life (RUL) and integrate multiple factors for service recommendations.
Innovation Solution
A method and system that utilize processing circuits to analyze RUL values, duty cycle information, and cost data to generate coordinated service recommendations, including near-term and extended-term service intervals, dynamically populating fields with degradation values and downtime predictions, to optimize maintenance schedules and reduce downtime.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If routine maintenance is performed too frequently, then component reliability is maintained, but resource waste and operational downtime increase due to premature repair and replacement
Solution Approach 1:
The system dynamically changes maintenance parameters (service intervals) based on actual component condition and predicted RUL values. Instead of fixed periodic maintenance, the service interval is adjusted according to real-time monitoring data and degradation trends, allowing extension of service intervals when components are healthy and reduction when degradation is detected, thus optimizing the balance between reliability and downtime
Solution Approach 2:
The system performs preliminary assessment of component RUL and generates service recommendations before actual maintenance is needed. By predicting future component states and identifying components that will require service soon, the system enables proactive scheduling of maintenance during planned downtime rather than reactive repairs during unexpected failures
2Loss of time
If routine maintenance is performed too infrequently, then operational downtime and resource waste are reduced, but component reliability deteriorates leading to unexpected failures
Solution Approach 1:
The system continuously monitors component performance parameters and feeds this information back to update RUL predictions and service recommendations. Real-time feedback from sensors and diagnostic systems allows the system to detect actual degradation trends and adjust maintenance timing accordingly, ensuring components are serviced before failure while minimizing unnecessary maintenance
Solution Approach 2:
The patent replaces traditional mechanical/time-based maintenance systems with an intelligence-based predictive system. Instead of relying on fixed schedules or mechanical wear indicators, the system uses data analytics, machine learning models, and RUL prediction algorithms to determine optimal maintenance timing, substituting computational intelligence for conventional maintenance mechanics
3Reliability
If multiple separate service recommendations are generated for different components, then comprehensive maintenance coverage is achieved, but service coordination complexity and planning difficulty increase
Solution Approach 1:
The system merges multiple individual service recommendations into a single coordinated service plan. By aggregating recommendations for different components and analyzing their temporal relationships, the system combines overlapping service intervals and coordinates maintenance activities across multiple components, reducing the number of separate service events while maintaining comprehensive coverage
Solution Approach 2:
The service recommendation system performs multiple functions simultaneously: it monitors individual component RUL, generates component-specific recommendations, coordinates services across multiple components, and optimizes overall maintenance scheduling. This multi-functional approach consolidates what would otherwise require separate systems into a unified platform
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method includes: receiving system data corresponding to an engine system. The system data includes a plurality of remaining useful life (RUL) values with each RUL value associated with a component of the engine system. The method further includes: comparing a first RUL value to a service interval threshold; generating a near-term service recommendation including a first list of components that correspond to each RUL value that are less than or equal to the service interval threshold; generating an extended term service recommendation including a second list of components and a downtime prediction; generating a coordinated service recommendation by dynamically populating one or more fields of the coordinated service recommendation based on the near-term service recommendation and the extended term service recommendation; and providing the combined service recommendation to a user device.