MR Device Digital Twin for Operating Behavior Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing MRI scanners have complex operating behaviors that are difficult to model accurately, necessitating improved methods for predicting and optimizing their performance during development and operation.
Innovation Solution
A computer-implemented method using neural networks, specifically LSTM networks, to simulate and predict the operating behavior of MRI scanners by analyzing event log data, enabling proactive fault monitoring and improved production planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional modeling methods are used for MR device operating behavior, then the model development is simpler, but the prediction accuracy and reliability are insufficient
Solution Approach 1:
The patent creates a digital twin (virtual copy) of the MR device that replicates its operating behavior. This digital twin is trained using historical operating data to accurately predict future states, replacing traditional simplified models while maintaining manageable complexity through data-driven approaches.
Solution Approach 2:
The patent replaces traditional mechanical/mathematical modeling approaches with machine learning algorithms (neural networks). This substitution enables the system to learn complex patterns from data without requiring explicit mathematical formulations of the underlying physical processes, thereby improving prediction accuracy while keeping the implementation feasible.
2Reliability
If actual measured operating data is used for training, then the prediction reliability improves, but the data processing complexity increases
Solution Approach 1:
The digital twin system automatically ingests and processes operating data from the MR device without requiring manual intervention. The neural network models self-train on historical data and continuously improve their predictions, enabling the system to serve itself by learning from its own operational history.
Solution Approach 2:
The system implements a feedback loop where predicted operating states are compared with actual measured data. This feedback is used to continuously retrain and refine the neural network models, improving prediction reliability over time while automating the data processing workflow.
3Reliability
If digital twins are used for proactive fault monitoring, then safety improves, but the computational resources required increase
Solution Approach 1:
The digital twin performs preliminary predictions of potential failures before they actually occur. By forecasting future operating states and identifying anomalies in advance, the system enables proactive maintenance actions, improving safety while allowing computational resources to be used during non-critical periods for training and prediction.
Data Source
AI summary
A method for computer-aided estimation of an operating behavior for an MR device having a set of device component. The method includes providing a memory with a set of digital models, wherein each digital model simulates the operating behavior of a respective component of the MR device, and wherein the digital models are interconnected in accordance with the structure and/or functionality of the MR device to form a higher-order model which simulates the operating behavior of the MR device, acquiring operating data of the MR device, and in an inference phase, accessing by a processor of the memory having the acquired operating data to estimate the operating behavior of the MR device in order to output a result.