Remote Fault Management for Medical Imaging Systems

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current fault management methods for electronic medical imaging apparatuses are inefficient and costly, often requiring guesswork and unnecessary part replacements, as they rely on user intervention and diagnostic routines only triggered by error codes, failing to identify issues before they become critical.

Innovation Solution

A method utilizing artificial intelligence, specifically a neural network, to analyze machine data in real-time from electronic medical imaging apparatuses, allowing for autonomous detection of anomalies and execution of diagnostic or corrective workflows remotely, thereby reducing downtime and unnecessary replacements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional fault management methods using error codes and manual diagnostics are used, then users can identify faults with some accuracy, but the process involves significant guesswork, unnecessary part replacements, and machine downtime

Engineering Contradiction:
Improvefault identification accuracyVSAvoidmachine downtime
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system continuously collects and analyzes machine data before faults manifest as error codes, performing preliminary detection of anomalies in machine parameters, sensor values, and operational patterns. This early detection enables proactive maintenance scheduling during planned downtime rather than unexpected breakdowns.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

An AI-based analysis server acts as an intermediary between the electronic apparatus and users/service technicians. The server receives machine data, performs sophisticated analysis to identify root causes, and provides precise diagnostic recommendations, eliminating the need for users to perform guesswork and multiple trial replacements.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of repair

If service technicians manually diagnose faults by replacing parts and running test sequences, then they can identify defective components, but the process is time-consuming and involves significant unnecessary part replacements

Engineering Contradiction:
Improvefault resolution effectivenessVSAvoidservice technician effort
Core Design Contradiction:
Ease of repairVSLoss of time

Solution Approach 1:

The system enables self-service diagnostics where the electronic apparatus automatically continues operation and collects diagnostic data while the AI server analyzes machine parameters, sensor outputs, and operational patterns to identify the root cause, eliminating the need for technicians to perform trial-and-error part replacements.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

Physical trial-and-error diagnostic methods (replacing parts and running test sequences) are replaced with automated AI-based analysis of machine data. The system substitutes mechanical diagnostic actions with intelligent software analysis that precisely identifies defective components through pattern recognition in operational data.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Reliability

If continuous monitoring and AI analysis of machine data are implemented, then faults can be detected earlier and more accurately, but the system complexity and data processing requirements increase

Engineering Contradiction:
Improvesystem availabilityVSAvoiddata processing system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The complex AI analysis and data processing functions are extracted from the electronic apparatus itself and relocated to a separate analysis server. The apparatus only needs to collect and transmit machine data, while the server performs sophisticated analysis using machine learning models trained on historical data, maintaining simplicity at the device level.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The AI analysis server provides universal diagnostic capabilities across multiple electronic apparatus units and different fault types. A single server can analyze data from numerous devices, performing pattern recognition, anomaly detection, and root cause identification for various system failures, eliminating the need for complex diagnostic systems in each individual apparatus.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP3534258B1Method of performing fault management in an electronic apparatus
Publication Date: 2021.05.26 SIEMENS HEALTHCARE GMBH
  • EP3534258B1 patent drawingFigure 1
  • EP3534258B1 patent drawingFigure 2
  • EP3534258B1 patent drawingFigure 3

AI summary

The invention describes a method of performing fault management in electronic apparatus (2), which method comprises the steps of transferring machine data (D) of electronic apparatus (2) to a remote support centre (3); analysing the machine data (D) of electronic apparatus (2) in the remote support centre (3); identifying a diagnostic and/or corrective workflow (WF) in response to an anomaly detected in machine data (D); and operating an electronic apparatus (2) from the remote support centre (3) to carry out the diagnostic or corrective workflow (WF). The invention further describes a fault management system (1) for electronic apparatus (2).