Digital twin-enabled automated anomaly detection and bottleneck identification in complex manufacturing systems using a multi-agent approach

Latsou, Christina; Farsi, Maryam; Erkoyuncu, John Ahmet

doi:10.1016/j.jmsy.2023.02.008

Cited by 25 publications

(11 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…-Monitoring and control: DTs mainly focus on monitoring assets to gain knowledge about decisive factors that can impact them. This asset understanding can be applied for different usages, such as anomaly detection, as for Calvo-Bascones et al or Latsou et al [16,17], or evaluating the status, history, or need for maintenance during the industrial process, especially in the supply chain, as with Dietz et al [18]. -Quality: Research related to quality in its distinct aspects, such as inspections, verification, or defect classification, are often areas where DT applications can be involved.…”

Section: Dt Concept and Its Adoptionmentioning

confidence: 99%

See 1 more Smart Citation

Digital Twins in Software Engineering—A Systematic Literature Review and Vision

Guinea-Cabrera,

Holgado-Terriza

2024

Applied Sciences

View full text Add to dashboard Cite

Digital twins are a powerful consequence of digital transformation. In fact, they have been applied to many industries to enhance operations, predict needs, improve decision making, or optimize performance, even though the definition of digital twins is still evolving. However, their impact on the software industry is still limited. Thus, this work aims to analyze the current adoption of digital twins in the software industry as a potential path to integrate them into application lifecycle management. To achieve this objective, first, the significant characteristics of current digital twins are analyzed in their application to manufacturing to understand how the knowledge and the lessons learned can be transferred to the software industry. Second, a systematic literature review was conducted on Scopus, the Web of Science, and the ScienceDirect database. The literature review revealed 93 documents after data screening and cleaning 251 initial documents. Our main findings are that digital twins are already influencing and will significantly affect the software industry, revolutionizing various aspects of the software development lifecycle. This study tackles what identifies a digital twin in the software industry, the specific domains and areas where they can be applied in the software lifecycle, and the proposed approaches explored to build digital twins for developing, deploying, and maintaining software systems. Finally, this study proposes some guidelines for building digital twins in the context of application lifecycle management. Determining an appropriate roadmap shortly is essential to achieve a widespread applicability to building suitable digital twins and preparing organizations for the software industry.

show abstract

Section: Dt Concept and Its Adoptionmentioning

confidence: 99%

“…-Join efforts into a network of DTs to have an SuS DT, as with Autiosalo et al [144]; -Cooperate with multi-agent systems to achieve a broader capacity, as with Latsou et al [17]; -A capacity to add AI and machine learning to DTs, as with Ricci et al [206].…”

Section: Rq1: Which Assets Can Dts Cover In Software Development?mentioning

confidence: 99%

Digital Twins in Software Engineering—A Systematic Literature Review and Vision

Guinea-Cabrera,

Holgado-Terriza

2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Experimental results on public testbeds demonstrate the effectiveness of such decoupled DT structures. Latsou et al [23] extended the concept of DT and proposed a multi-agent DT architecture for anomaly detection and bottleneck identification in complex manufacturing systems. In addition to DT construction for a specific CPS, Xu et al [37] and Lu et al [26] introduced transfer learning for DT evolution to synchronize with the changes in CPSs and software systems, respectively.…”

Section: Related Workmentioning

confidence: 99%

KDDT: Knowledge Distillation-Empowered Digital Twin for Anomaly Detection

Xu,

Ali,

Yue

et al. 2023

Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Enginee

View full text Add to dashboard Cite

Cyber-physical systems (CPSs), like train control and management systems (TCMS), are becoming ubiquitous in critical infrastructures. As safety-critical systems, ensuring their dependability during operation is crucial. Digital twins (DTs) have been increasingly studied for this purpose owing to their capability of runtime monitoring and warning, prediction and detection of anomalies, etc. However, constructing a DT for anomaly detection in TCMS necessitates sufficient training data and extracting both chronological and context features with high quality. Hence, in this paper, we propose a novel method named KDDT for TCMS anomaly detection. KDDT harnesses a language model (LM) and a long short-term memory (LSTM) network to extract contexts and chronological features, respectively. To enrich data volume, KDDT benefits from out-ofdomain data with knowledge distillation (KD). We evaluated KDDT with two datasets from our industry partner Alstom and obtained the F1 scores of 0.931 and 0.915, respectively, demonstrating the effectiveness of KDDT. We also explored individual contributions of the DT model, LM, and KD to the overall performance of KDDT, via a comprehensive empirical study, and observed average F1 score improvements of 12.4%, 3%, and 6.05%, respectively. CCS CONCEPTS• Software and its engineering → Maintaining software; • Security and privacy → Intrusion detection systems; • Computer systems organization → Embedded systems; Sensors and actuators; Embedded and cyber-physical systems; • Computing methodologies → Neural networks.

show abstract

“…aerospace [6][7][8], precision instruments [9], etc. It is also widely used for manufacturing workshops, such as intelligent machine tools [10][11][12], intelligent workshops [13][14][15], equipment health management [16][17][18], and human-computer interaction [19,20].…”

Section: Introductionmentioning

confidence: 99%

Fusion method for digital twin model of a production line

Liu,

Wang,

Huang

et al. 2024

Preprint

View full text Add to dashboard Cite

Digital twins have attracted more and more attention in the past few years. To put digital twins into practice, a large number of modeling approaches have been proposed, vast amounts of data have been collected, and their accuracy has been improving. However, current research has paid insufficient attention to the multi-scale features of the shop floor, which hinders the effective application of the digital twin shop floor. To address the problem of how to achieve effective multi-level and multi-dimensional fusion of digital twin models with production process data, this paper first proposes a structured data modeling framework for sorting out all the production process data collected in real-time; and then proposes a multi-level fusion framework for supporting the fusion of real-time data and twin models from the unit level to the system level. The method judges the parsed received data streams through the full-factor semanticization framework, and at the same time fuses the parsed data streams with the constructed full-factor twin model from multiple dimensions and layers, forming a twin model fusion method with real-time data streams as the blood and twin model as the skeleton. Finally, the micro-assembly-based production shop environment is selected as a case study to verify the correctness and feasibility of the proposed data grooming framework, data, and model fusion method.

show abstract

Digital twin-enabled automated anomaly detection and bottleneck identification in complex manufacturing systems using a multi-agent approach

Cited by 25 publications

References 60 publications

Digital Twins in Software Engineering—A Systematic Literature Review and Vision

Digital Twins in Software Engineering—A Systematic Literature Review and Vision

KDDT: Knowledge Distillation-Empowered Digital Twin for Anomaly Detection

Fusion method for digital twin model of a production line

Contact Info

Product

Resources

About