Predictive Maintenance for Self-Service Terminals Using Statistical Correlations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Maintenance and support of Self-Service Terminals (SSTs) such as ATMs are inefficient, leading to frequent downtime and revenue loss due to the need for regular physical attendance and large support staffs, as existing methods lack proactive predictive maintenance capabilities.
Innovation Solution
A system and method that utilizes statistical correlations and machine learning to analyze historical data from service tickets, including tallies, events, and signal/vibration data, to predict maintenance issues and provide proactive guidance for service engineers, enabling predictive maintenance and reducing downtime.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If physical attendance and large support staff are used for SST maintenance, then reliability of service coverage is improved, but productivity and operational efficiency deteriorate due to frequent downtime and high costs
Solution Approach 1:
The system enables self-service through automated monitoring where the SST system automatically detects and reports its own maintenance needs without requiring manual inspection. The monitoring system continuously tracks operational parameters and autonomously generates service requests when thresholds are exceeded, eliminating the need for proactive physical attendance by support staff.
Solution Approach 2:
The patent replaces the mechanical system of physical inspection and manual monitoring with an automated electronic monitoring system. Sensors and software continuously track operational data, replacing the need for human engineers to physically attend to machines for routine checks, thereby maintaining reliability while improving productivity.
2Duration of action of stationary object
If physical attendance is increased for regular maintenance, then SST uptime is improved, but loss of time and operational costs worsen due to frequent service interventions
Solution Approach 1:
The monitoring system performs preliminary detection of maintenance needs by continuously tracking operational parameters and identifying trends that indicate future failures. By detecting issues before they cause downtime, the system enables planned maintenance during non-critical periods, maximizing SST uptime while minimizing disruptive service interventions.
Solution Approach 2:
The system implements continuous feedback loops where operational data is constantly monitored, analyzed, and used to adjust maintenance schedules. The feedback mechanism alerts engineers only when actual maintenance is needed, eliminating unnecessary service interventions and optimizing the timing of maintenance activities to minimize impact on SST availability.
3Reliability
If large support staff is deployed for ATM maintenance, then service coverage is improved, but organizational expenses worsen due to high labor costs
Solution Approach 1:
The automated monitoring system provides universal coverage across all SST locations simultaneously, replacing the need for multiple specialized engineers. A single centralized monitoring system can track and manage maintenance needs for numerous machines across different locations, eliminating the requirement for large distributed support staff while maintaining comprehensive service coverage.
Data Source
AI summary
Data is collected for Self-Service Terminals (SSTs) including tallies, events, and outcomes associated with servicing the SSTs. Statistical correlations are derived from the tallies and events with respect to the outcomes. Subsequent collected data is processed with the statistical correlations and a probability for a failure of a component or a part of the component associated with a particular SST is reported for servicing the component or part before the failure.