Adaptive Behavioral Modeling for Device Life Prediction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for predicting the behavior of physical devices, such as engines and electronic components, are inadequate as they fail to account for changing external influences over time, leading to imprecise decision-making and increased economic and safety risks, often resulting in unnecessary maintenance or replacement.

Innovation Solution

A procedure using an electronic computing device to record and adapt a behavioral model based on current behavior parameters, simulation parameters, and environmental conditions, employing a neuronal network for reinforcement learning to generate a reliable behavior forecast, which continuously updates and learns from actual device behavior.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional models are used to predict device behavior, then predictions are accurate at the beginning of service life, but prediction accuracy deteriorates as service life increases due to unaccounted external influences

Engineering Contradiction:
Improveprediction accuracyVSAvoidservice life duration
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system continuously acquires actual behavior parameters from the device during operation and feeds this information back to update and adapt the behavioral model. This feedback mechanism allows the model to learn from real device performance and adjust to external influences, maintaining prediction accuracy throughout the device's service life rather than degrading over time

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The behavioral model autonomously adapts to the device's actual behavior by continuously learning from acquired behavior parameters without requiring external retraining or manual adjustment. The model self-updates its predictions based on the device's evolving characteristics, enabling it to maintain accuracy independently as the device ages

Inventive Principle:
Principle #25Self-service

2Reliability

If safety margins are increased to limit risks, then reliability improves, but productivity deteriorates due to unnecessary maintenance and replacement

Engineering Contradiction:
ImprovesafetyVSAvoiddevice utilization
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system dynamically adjusts maintenance decisions based on the adapted behavioral model's predictions of actual device behavior. By continuously updating the model with real behavior parameters, the system can accurately assess device condition and predict failures, enabling maintenance to be performed only when truly necessary rather than following conservative fixed schedules, thus maintaining reliability while improving productivity

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If behavioral models continuously adapt to device behavior, then prediction accuracy improves, but computational complexity increases

Engineering Contradiction:
Improvebehavior prediction accuracyVSAvoidcomputational complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system creates a behavioral model that replicates the device's behavior patterns based on acquired behavior parameters. This virtual copy learns and adapts to the device's characteristics through continuous data acquisition, enabling accurate predictions without requiring complex real-time simulations of the physical device, thus achieving high accuracy while managing computational complexity

Inventive Principle:
Principle #26Copying

Data Source

PatentEP4498196A1Method for generating a behavior prediction of a device, computer program product, computer-readable storage medium and electronic computing device
Publication Date: 2025.01.29 SIEMENS AG
  • EP4498196A1 patent drawingFigure 1
  • EP4498196A1 patent drawingFigure 2
  • EP4498196A1 patent drawingFigure 3

AI summary

The invention relates to a method for generating a behavioral prediction (16) of a device (18) using an electronic computing device (10), comprising the steps of: - providing an initial model of the device (18) using the electronic computing device (10); - acquiring at least one behavioral parameter (24) currently characterizing the device (18) using an acquisition device (12) of the electronic computing device (10); - adapting the initial model to a behavioral model (28) of the device (18) depending on the acquired behavioral parameter (24) using the electronic computing device (10); - acquiring a simulation parameter (40, 42) for the device (18) using a further acquisition device (14) of the electronic computing device (10); - evaluating the behavioral model (28) depending on the simulation parameter (40, 42) using the electronic computing device (10);and - generating the behavioral prediction (16) depending on the evaluation using the electronic computing device (10). Furthermore, the invention relates to a computer program product, a computer-readable storage medium and an electronic computing device (10).