Predictive Fault Scheduling for Service Terminals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Self-service and assisted service terminals often experience failures that go unnoticed until it's too late, leading to unavailability, missed sales, lower customer satisfaction, and lost customers due to the lack of predictive maintenance capabilities.
Innovation Solution
A system that predicts fatal faults in terminals by analyzing non-fatal event data, using predetermined fault patterns and life limit data to generate a fault prediction signal, allowing for proactive maintenance and increasing terminal availability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If terminals operate continuously without predictive maintenance, then operational simplicity is maintained, but terminal availability decreases due to unexpected failures
Solution Approach 1:
The system performs preliminary actions by analyzing event data and predicting faults before they occur. The predictive maintenance system continuously monitors terminal events, identifies patterns indicating impending failures, and schedules maintenance actions in advance, preventing unexpected outages and improving terminal availability.
Solution Approach 2:
The system implements feedback mechanisms by continuously collecting terminal event data, comparing it against predicted fault patterns, and adjusting maintenance schedules based on actual terminal behavior. This closed-loop approach refines prediction accuracy over time and adapts to changing operational conditions.
2Reliability
If reactive maintenance is used (fixing only after failure), then maintenance cost is reduced, but customer satisfaction decreases due to service unavailability
Solution Approach 1:
The system schedules maintenance actions before terminal failures occur by predicting faults from event data patterns. This preliminary maintenance approach prevents service outages, maintains terminal availability, and improves customer satisfaction while minimizing downtime through planned rather than reactive maintenance.
3Reliability
If predictive maintenance is implemented, then terminal availability increases, but data processing requirements increase
Solution Approach 1:
The system extracts and analyzes only the relevant event data necessary for fault prediction by filtering and selecting events that match predicted fault patterns. This selective data processing approach reduces computational requirements while maintaining effective predictive maintenance capabilities.
Solution Approach 2:
The system applies partial analysis by focusing on specific event types and patterns most indicative of terminal failures, rather than processing all possible event data. This targeted approach balances predictive accuracy with data processing efficiency.
Data Source
AI summary
Disclosed is a fault prediction system and method that uses non-fatal event data received from a terminal to make predictions concerning future fatal faults for the terminal and to schedule a predicted service call. A complex fault pattern associated with a fault is applied to the non-fatal event data to predict the fault. A corrective action is provided for each predicted fault and historical data is used to predict a time to the predicted fault to govern the type of service response to create to prevent the fault.