An intelligent agent-based architecture for resilient digital twins in manufacturing

Vrabič, Rok; Erkoyuncu, John Ahmet; Farsi, Maryam; Ariansyah, Dedy

doi:10.1016/j.cirp.2021.04.049

Cited by 24 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simulation methods are fundamental to constructing a DT to predict, optimise, and make decisions or detect faults. Simulation methods may be based on agent-based simulation (Belfadel et al 2021;Meta et al 2021;Park et al 2020;Rodríguez-Aguilar and Marmolejo-Saucedo 2020;Vrabič et al 2021) or discrete event simulation (Eyre et al 2018;Rodríguez-Aguilar and Marmolejo-Saucedo 2020;Vrabič et al 2021;Karakra et al 2020;Negri et al 2019Negri et al , 2021Marmolejo-Saucedo 2021;Hyeong-su et al 2019). Agent-based simulation is used to model autonomous agents that fulfil their own decisions to satisfy a common goal, e.g., people in urban simulation (Belfadel et al 2021;Meta et al 2021;Christensen et al 2019), supply-chain agents (Park et al 2020;, and highly specialized units (Vaerbak et al 2019) and learning agents (Vrabič et al 2021).…”

Section: Methodologiesmentioning

confidence: 99%

“…Simulation methods may be based on agent-based simulation (Belfadel et al 2021;Meta et al 2021;Park et al 2020;Rodríguez-Aguilar and Marmolejo-Saucedo 2020;Vrabič et al 2021) or discrete event simulation (Eyre et al 2018;Rodríguez-Aguilar and Marmolejo-Saucedo 2020;Vrabič et al 2021;Karakra et al 2020;Negri et al 2019Negri et al , 2021Marmolejo-Saucedo 2021;Hyeong-su et al 2019). Agent-based simulation is used to model autonomous agents that fulfil their own decisions to satisfy a common goal, e.g., people in urban simulation (Belfadel et al 2021;Meta et al 2021;Christensen et al 2019), supply-chain agents (Park et al 2020;, and highly specialized units (Vaerbak et al 2019) and learning agents (Vrabič et al 2021). Discrete event simulation is a simulation method that simulates events with a chronological event queue, e.g., production processes (Christensen et al 2020a(Christensen et al , 2020b, arriving patients (Karakra et al 2020), drilling station (Negri et al 2019(Negri et al , 2021, periodic decisions in supply chains (Marmolejo-Saucedo 2021) and robot events (Eyre et al 2018).…”

Section: Methodologiesmentioning

confidence: 99%

See 1 more Smart Citation

Can we benefit from game engines to develop digital twins for planning the deployment of photovoltaics?

2022

View full text Add to dashboard Cite

Digital Twins (DTs) have attracted great attention in the energy sector. Game engines have been suggested to model DTs of their physical counterparts because they provide realistic graphics, lighting-, fluid- and physics engines that simulate the real world. However, the application of game engines to develop DTs for photovoltaics (PVs) has not yet been discussed in the literature. Therefore, this paper assesses the built-in game engine features' ability to support the DT development of PVs with Unreal Engine 5. This paper mainly focuses on visual representation because the surrounding environment significantly impacts PV deployment, and the existing software tools do not allow the study of the environmental factors at the early planning phase of a project’s lifecycle. Furthermore, this paper investigates the position of the sun, shadows and reflections from nearby objects that influence the PVs' power output, and if the built-in light engine can be used for planning the deployment of PVs. The result shows that in-game objects in the environment can be used to affect the simulated PV output estimate over a year. It also indicates that applying Unreal Engine 5 to model PV systems that rely on mirroring real-world behaviour is promising if accurate data is used in the modelling. Real data and mathematical PV models are necessary since Unreal Engine 5’s Lumen subsystem cannot provide realistic solar radiance on PVs for a given location on earth.

show abstract

Section: Methodologiesmentioning

confidence: 99%

Section: Methodologiesmentioning

confidence: 99%

Can we benefit from game engines to develop digital twins for planning the deployment of photovoltaics?

2022

View full text Add to dashboard Cite

show abstract

“…In the following period, 2020-2022, several models were implemented, such as the behaviour model [40]. Additionally, the focus was on model improvement and expert knowledge incorporation [27,[43][44][45][46].…”

Section: Data Analyticsmentioning

confidence: 99%

“…Simulation of physical process on ad hoc or continuous basis process simulation [63], automated simulation model generation, [64] Digital model richness Robustness, resilience, self-adaption, fidelity of virtual model Robustness, resilience, self-adaption, fidelity [44], DT fidelity [53], fidelity [61], DT behaviour model [37], high-fidelity of DTs [64] Human interaction Bridging human and machine Human-machine collaboration [5], bridges a human user and robot [25] Product life-cycle Product design, manufacturing and service Service stage: service, data analytics [38], Full product life-cycle management [37,63,65], Manufacturing stage: fault prediction [3], predicting energy efficiency [37], predictive maintenance, feature extraction [30] Figure 16 shows contribution of ML-based DT in manufacturing PLM. ML-based DT is marginally used in full product life-cycle management [37,63,65].…”

Section: Simulation Capabilitiesmentioning

confidence: 99%

Machine-Learning-Based Digital Twin in Manufacturing: A Bibliometric Analysis and Evolutionary Overview

2022

View full text Add to dashboard Cite

The Digital Twin (DT) concept in the manufacturing industry has received considerable attention from researchers because of its versatile application potential. Machine Learning (ML) adds a new dimension to DT by enhancing its functionality. Many studies on DT in the manufacturing industry have recently been published. However, there is still a lack of a systematic literature review on different aspects of ML-based DT in the manufacturing industry from a bibliometric and evolutionary perspective. Therefore, the proposed study is mainly aimed at reviewing DT in the manufacturing industry to identify the contribution of ML, current methods, and future research directions. According to the findings, the contribution of ML to this domain is significant. Additionally, the results show that the latest ML technologies are being used in the DT domain; neural networks have evolved based on application-specific requirements. The total number of papers and citations per paper on ML-based DT is increasing. The relevance of ML in DT has increased over time. The current trend is to use ML-based DT for data analytics. Additionally, there are many unfilled gaps; certain gaps include industrial applications of DT, synchronisation with real-time data through sensors, heterogeneous data management, and benchmarking.

show abstract

“…Interaction and communication processes play a major role in intelligence applications that provide the necessary set of information for the analysis process. Intelligent application is also used for the CNC machine diagnosis process [12]. CNC machines perform AI and provide necessary features and functionalities for intelligent applications to perform certain tasks for users.…”

Section: Introductionmentioning

confidence: 99%

Remote Diagnosis and Detection Technology for Electrical Control of Intelligent Manufacturing CNC Machine Tools

Yang

2022

Scientific Programming

View full text Add to dashboard Cite

An intelligent manufacturing environment employs internet-based communication and monitoring technologies for fault detection, diagnosis, and monitoring of industrial machines. The monitoring and fault detection are performed remotely without human intervention that predicts faults and ensures specific operational control. This article introduces a rational fault diagnosis process (RFDP) best suited for remote fault detection and diagnosis of CNC machine tools. The proposed process monitors different operational segments of the machine and extracts related data to validate its performance. The interconnection between the segments and fault impact are identified using the transfer learning process. The previously identified faults are used in the state training process to improve detection and diagnosis accuracy. Depending on the operational control continuity, the performance is assessed post the fault diagnosis. The learning paradigm is trained using the machine’s efficiency and rational data processing to predict the transfer states’ faults. The transfer states are modulated based on the efficiency and minimum-maximum control recommended for the CNC machine. This process’s performance is validated using detection accuracy, diagnosis recommendation, downtime, data processing rate, and processing time. From the experimental analysis, it is seen that for the varying data extraction rates, the proposed process improves detection accuracy by 10.14%, diagnosis recommendation by 8.58% and data processing rate by 7.95%, reducing the downtime by 8.85%, and processing by 11.24%.

show abstract

An intelligent agent-based architecture for resilient digital twins in manufacturing

Cited by 24 publications

References 13 publications

Can we benefit from game engines to develop digital twins for planning the deployment of photovoltaics?

Can we benefit from game engines to develop digital twins for planning the deployment of photovoltaics?

Machine-Learning-Based Digital Twin in Manufacturing: A Bibliometric Analysis and Evolutionary Overview

Remote Diagnosis and Detection Technology for Electrical Control of Intelligent Manufacturing CNC Machine Tools

Contact Info

Product

Resources

About