Self-Correcting Knowledge Base for Medical Imaging Maintenance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Predictive maintenance for medical imaging devices is challenging due to the large volumes of log data generated, the time lag between log data and component failures, and the need for frequent updates by subject matter experts, making it difficult to identify useful log data for proactive maintenance and keeping knowledge engines current with device changes.
Innovation Solution
A monitoring method and device that automatically generates maintenance alerts by extracting component IDs and operating parameter ranges from medical imaging device manuals, formulating these into decision rules, and applying them to log data to detect out-of-range values, reducing the need for manual updates and expert input.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If subject matter experts manually update the knowledge engine with decision rules, then predictive maintenance accuracy is improved, but device complexity and time consumption increase
Solution Approach 1:
The system automatically extracts component IDs and operating parameter ranges from device manuals and generates decision rules without requiring manual intervention from subject matter experts. The knowledge engine self-updates by processing manual documentation, eliminating the need for continuous expert input while maintaining accurate predictive maintenance capabilities
Solution Approach 2:
The patent replaces the manual mechanical process of expert rule creation with an automated information extraction and processing system. Natural language processing and data mining techniques substitute for human expert analysis, converting manual documentation into structured decision rules automatically
2Adaptability or versatility
If subject matter experts manually update the knowledge engine frequently, then adaptability to new products is improved, but loss of time and productivity decrease
Solution Approach 1:
The system automatically processes new device manuals and extracts updated component information and parameter ranges, enabling the knowledge engine to adapt to new products without manual intervention. This self-updating mechanism ensures continuous adaptability while eliminating time loss associated with manual knowledge base maintenance
Solution Approach 2:
The system performs preliminary extraction and structuring of information from device manuals in advance, creating a ready-to-use knowledge base that automatically adapts when new manuals are introduced. This preliminary processing eliminates the need for reactive manual updates when new products are deployed
3Measurement precision
If manual extraction of component IDs and parameter ranges is performed, then measurement precision is improved, but loss of time and productivity increase
Solution Approach 1:
The patent employs natural language processing, pattern recognition, and data mining algorithms to automatically extract component IDs and operating parameter ranges from device manuals. This automated information extraction system maintains high precision by using structured processing methods while dramatically increasing productivity compared to manual extraction
Solution Approach 2:
The system creates structured data copies from unstructured manual documentation, extracting and replicating relevant information into standardized formats. This copying process preserves the precision of the original information while enabling rapid processing and knowledge base generation without manual intervention
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
In a monitoring method for generating maintenance alerts, component IDs are extracted which identify medical imaging device components in electronic medical imaging device manuals (25, 26, 27, 28). Operating parameters of the medical imaging device components and associated operating parameter ranges are also extracted from the manuals, based on numeric values, parameter terms identifying operating parameters, and linking terms or symbols indicative of equality or inequality that connect the numeric values and parameter terms. The operating parameter ranges are formulated into decision rules (36) which are applied to log data (40) generated by a monitored medical imaging device (2) to detect out-of-range log data generated by the monitored medical imaging device. Maintenance alerts (24) are displayed on a display (18) in response to the detected out-of-range log data. The maintenance alerts are generated from out-of-range log data and are associated with component IDs contained in the out-of-range log data.