A Digital Twin for Cyber-Physical Energy Systems

Pileggi, Paolo; Verriet, Jacques; Broekhuijsen, Jeroen; Leeuwen, C.J. van; Wijbrandi, Wilco; Konsman, Mente J.

doi:10.1109/mscpes.2019.8738792

Cited by 39 publications

(14 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several applications are presented in different areas of design, production, prognostic and health management. To the best of our knowledge, there are just few references in literature to the usage of Digital Twin in the context of anomaly detection [11]- [13] and all of those are more focused to present the Digital Twin system rather than a anomaly detection algorithm.…”

Section: Related Workmentioning

confidence: 99%

Real-World Anomaly Detection by Using Digital Twin Systems and Weakly Supervised Learning

Castellani

Schmitt

Squartini

2021

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

The continuously growing amount of monitored data in the Industry 4.0 context requires strong and reliable anomaly detection techniques. The advancement of Digital Twin technologies allows for realistic simulations of complex machinery, therefore, it is ideally suited to generate synthetic datasets for the use in anomaly detection approaches when compared to actual measurement data. In this paper, we present novel weakly-supervised approaches to anomaly detection for industrial settings. The approaches make use of a Digital Twin to generate a training dataset which simulates the normal operation of the machinery, along with a small set of labeled anomalous measurement from the real machinery. In particular, we introduce a clustering-based approach, called Cluster Centers (CC), and a neural architecture based on the Siamese Autoencoders (SAE), which are tailored for weakly-supervised settings with very few labeled data samples. The performance of the proposed methods is compared against various state-of-the-art anomaly detection algorithms on an application to a real-world dataset from a facility monitoring system, by using a multitude of performance measures. Also, the influence of hyper-parameters related to feature extraction and network architecture is investigated. We find that the proposed SAE based solutions outperform stateof-the-art anomaly detection approaches very robustly for many different hyper-parameter settings on all performance measures.

show abstract

Section: Related Workmentioning

confidence: 99%

Real-World Anomaly Detection by Using Digital Twin Systems and Weakly Supervised Learning

Castellani

Schmitt

Squartini

2021

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

show abstract

“…(1) Power industry equipment and systems [53]. DT can digitize all stages of the life cycle for power generation equipment [54] used in the power industry [55], such as wind turbine manufacturing, assembly, operation and maintenance, power network data transmission, and user services. (2) Aero-engine DT has been used to solve aircraft-related problems in the aerospace industry [56] from the beginning of DT applications.…”

Section: Digital Twin-based Turbomachinery Applicationsmentioning

confidence: 99%

Digital Twin Technologies for Turbomachinery in a Life Cycle Perspective: A Review

et al. 2021

View full text Add to dashboard Cite

Turbomachinery from a life cycle perspective involves sustainability-oriented development activities such as design, production, and operation. Digital Twin is a technology with great potential for improving turbomachinery, which has a high volume of investment and a long lifespan. This study presents a general framework with different digital twin enabling technologies for the turbomachinery life cycle, including the design phase, experimental phase, manufacturing and assembly phase, operation and maintenance phase, and recycle phase. The existing digital twin and turbomachinery are briefly reviewed. New digital twin technologies are discussed, including modelling, simulation, sensors, Industrial Internet of Things, big data, and AI technologies. Finally, the major challenges and opportunities of DT for turbomachinery are discussed.

show abstract

“…In the energy domain, sensor and context data from a Cyber-Physical Energy System (CPES) can be used to synchronize fit-for-purpose models with reasoning logic during the operational phase of the system, i.e., Digital Twins coordinated to support specific system goals. Previously, Pileggi et al used an actual flexible energy system deployment to demonstrate the applicability of the Digital Twin [1].…”

mentioning

confidence: 99%

“…These batteries provide flexibility to compensate for the energy imbalance in the ecosystem. They demonstrated an application of Digital Twin simulation to explore system battery behavior using an expert model [1]. The battery receives instructions from the controller and provides the controller with its flexibility information.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning for Digital Twins to Predict Responsiveness of Cyber-Physical Energy Systems

Snijders

Pileggi²,

Broekhuijsen

et al. 2020

2020 8th Workshop on Modeling and Simulation of Cyber-Physical Energy Systems

Self Cite

View full text Add to dashboard Cite

show abstract

A Digital Twin for Cyber-Physical Energy Systems

Cited by 39 publications

References 13 publications

Real-World Anomaly Detection by Using Digital Twin Systems and Weakly Supervised Learning

Real-World Anomaly Detection by Using Digital Twin Systems and Weakly Supervised Learning

Digital Twin Technologies for Turbomachinery in a Life Cycle Perspective: A Review

Machine Learning for Digital Twins to Predict Responsiveness of Cyber-Physical Energy Systems

Contact Info

Product

Resources

About