System Resilience through Health Monitoring and Reconfiguration
- URL: http://arxiv.org/abs/2208.14525v1
- Date: Tue, 30 Aug 2022 20:16:17 GMT
- Title: System Resilience through Health Monitoring and Reconfiguration
- Authors: Ion Matei, Wiktor Piotrowski, Alexandre Perez, Johan de Kleer, Jorge
Tierno, Wendy Mungovan and Vance Turnewitsch
- Abstract summary: We demonstrate an end-to-end framework to improve the resilience of man-made systems to unforeseen events.
The framework is based on a physics-based digital twin model and three modules tasked with real-time fault diagnosis, prognostics and reconfiguration.
- Score: 56.448036299746285
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: We demonstrate an end-to-end framework to improve the resilience of man-made
systems to unforeseen events. The framework is based on a physics-based digital
twin model and three modules tasked with real-time fault diagnosis, prognostics
and reconfiguration. The fault diagnosis module uses model-based diagnosis
algorithms to detect and isolate faults and generates interventions in the
system to disambiguate uncertain diagnosis solutions. We scale up the fault
diagnosis algorithm to the required real-time performance through the use of
parallelization and surrogate models of the physics-based digital twin. The
prognostics module tracks the fault progressions and trains the online
degradation models to compute remaining useful life of system components. In
addition, we use the degradation models to assess the impact of the fault
progression on the operational requirements. The reconfiguration module uses
PDDL-based planning endowed with semantic attachments to adjust the system
controls so that the fault impact on the system operation is minimized. We
define a resilience metric and use the example of a fuel system model to
demonstrate how the metric improves with our framework.
Related papers
- Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments [50.310636905746975]
Real-world machine learning systems often encounter model performance degradation due to distributional shifts in the underlying data generating process.
Existing approaches to addressing shifts, such as concept drift adaptation, are limited by their reason-agnostic nature.
We propose self-healing machine learning (SHML) to overcome these limitations.
arXiv Detail & Related papers (2024-10-31T20:05:51Z) - Causal Disentanglement Hidden Markov Model for Fault Diagnosis [55.90917958154425]
We propose a Causal Disentanglement Hidden Markov model (CDHM) to learn the causality in the bearing fault mechanism.
Specifically, we make full use of the time-series data and progressively disentangle the vibration signal into fault-relevant and fault-irrelevant factors.
To expand the scope of the application, we adopt unsupervised domain adaptation to transfer the learned disentangled representations to other working environments.
arXiv Detail & Related papers (2023-08-06T05:58:45Z) - Robustness and Generalization Performance of Deep Learning Models on
Cyber-Physical Systems: A Comparative Study [71.84852429039881]
Investigation focuses on the models' ability to handle a range of perturbations, such as sensor faults and noise.
We test the generalization and transfer learning capabilities of these models by exposing them to out-of-distribution (OOD) samples.
arXiv Detail & Related papers (2023-06-13T12:43:59Z) - Analysis of Numerical Integration in RNN-Based Residuals for Fault
Diagnosis of Dynamic Systems [0.6999740786886536]
The paper includes a case study of a heavy-duty truck's after-treatment system to highlight the potential of these techniques for improving fault diagnosis performance.
Data-driven modeling and machine learning are widely used to model the behavior of dynamic systems.
arXiv Detail & Related papers (2023-05-08T12:48:18Z) - Physics-Infused Fuzzy Generative Adversarial Network for Robust Failure
Prognosis [0.0]
FuzzyGAN based method embeds a physics-based model in the aggregation of the fuzzy implications.
Results on a bearing problem showcases the efficacy of adding a physics-based aggregation in a fuzzy logic model to improve GAN's ability to model health.
arXiv Detail & Related papers (2022-06-15T18:50:16Z) - Capturing Actionable Dynamics with Structured Latent Ordinary
Differential Equations [68.62843292346813]
We propose a structured latent ODE model that captures system input variations within its latent representation.
Building on a static variable specification, our model learns factors of variation for each input to the system, thus separating the effects of the system inputs in the latent space.
arXiv Detail & Related papers (2022-02-25T20:00:56Z) - On-board Fault Diagnosis of a Laboratory Mini SR-30 Gas Turbine Engine [54.650189434544146]
A data-driven fault diagnosis and isolation scheme is explicitly developed for failure in the fuel supply system and sensor measurements.
A model is trained using machine learning classifiers to detect a given set of fault scenarios in real-time on which it is trained.
Several simulation studies were carried out to demonstrate and illustrate the proposed fault diagnosis scheme's advantages, capabilities, and performance.
arXiv Detail & Related papers (2021-10-17T13:42:37Z) - Data-driven Residual Generation for Early Fault Detection with Limited
Data [4.129225533930966]
In many complex systems it is not feasible to develop highly accurate models for the systems.
Data-driven solutions have received an immense attention in the industries systems for several practical reasons.
Unlike the model-based methods it is straight forward to combine time series measurements such as pressure and voltage with other sources of information.
arXiv Detail & Related papers (2021-09-28T03:18:03Z) - Bayesian Structural Learning for an Improved Diagnosis of Cyber-Physical
Systems [0.8379286663107844]
This paper proposes a scalable algorithm for an automated learning of a structured diagnosis model.
It offers equal performance to comparable algorithms while giving better interpretability.
arXiv Detail & Related papers (2021-04-02T11:14:05Z) - Monitoring and Diagnosability of Perception Systems [21.25149064251918]
Perception is a critical component of high-integrity applications of robotics and autonomous systems, such as self-driving cars.
Despite the paramount importance of perception systems, there is no formal approach for system-level monitoring.
We propose a mathematical model for runtime monitoring and fault detection of perception systems.
arXiv Detail & Related papers (2020-05-24T18:09:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.