Virtual Comissioning of Manufacturing System Intelligent Control

Xia, Kaishu; Sacco, Christopher; Kirkpatrick, Max; Harik, Ramy; Bayoumi, Abdel

doi:10.33599/nasampe/s.19.1403

Cited by 10 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All of these data transmission must be reported and administrated by control network hosted by OPC-UA server in PLC devices. Derived optimal action can be pushed to either the digital twin for virtual commissioning [ 27 ] or the physical cell for deployment. In fact, this high-fidelity simulation-based digital twin [ 12 ] adds another layer of expert knowledge and substantially increases the reliability of data-driven approaches adopted in the control loop.…”

Section: Resultsmentioning

confidence: 99%

“…In particular, enabling the integration of inspection data with more complete analysis has been studied in some advanced manufacturing processes, such as automated fiber placement [ 22 , 23 , 24 ]. Traditionally, direct process signals monitored via Programmable Logic Control (PLC) systems, including the control signals indicating the running states of field devices, can be reported over the standardized protocols, such as OPC-UA [ 25 ], and MTConnect [ 26 ], allowing for easy interconnections to other manufacturing systems [ 12 , 27 ]. The Machine-to-Machine (M2M) communications establish interconnections between machines and autonomous actions over Industrial Internet of Things (IIoT) networks [ 28 ].…”

Section: Literature Reviewmentioning

confidence: 99%

“…The automation signals are synchronized and exchanged between PLC and the cyber system via an OPC-UA server. Detailed implementation for this smart manufacturing system was introduced in our previous work [ 11 , 12 , 27 ]. The overview of this simulation-based digital twin is presented in Figure 1 .…”

Section: Vision System For Process Monitoringmentioning

confidence: 99%

See 2 more Smart Citations

Towards Semantic Integration of Machine Vision Systems to Aid Manufacturing Event Understanding

Xia

Saidy

Kirkpatrick

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

A manufacturing paradigm shift from conventional control pyramids to decentralized, service-oriented, and cyber-physical systems (CPSs) is taking place in today’s 4th industrial revolution. Generally accepted roles and implementation recipes of cyber systems are expected to be standardized in the future of manufacturing industry. The authors intend to develop a novel CPS-enabled control architecture that accommodates: (1) intelligent information systems involving domain knowledge, empirical model, and simulation; (2) fast and secured industrial communication networks; (3) cognitive automation by rapid signal analytics and machine learning (ML) based feature extraction; (4) interoperability between machine and human. Semantic integration of process indicators is fundamental to the success of such implementation. This work proposes an automated semantic integration of data-intensive process signals that is deployable to industrial signal-based control loops. The proposed system rapidly infers manufacturing events from image-based data feeds, and hence triggers process control signals. Two image inference approaches are implemented: cloud-based ML model query and edge-end object shape detection. Depending on use cases and task requirements, these two approaches can be designated with different event detection tasks to provide a comprehensive system self-awareness. Coupled with conventional industrial sensor signals, machine vision system can rapidly understand manufacturing scenes, and feed extracted semantic information to a manufacturing ontology developed by either expert or ML-enabled cyber systems. Moreover, extracted signals are interpreted by Programmable Logical Controllers (PLCs) and field devices for cognitive automation towards fully autonomous industrial systems.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Towards Semantic Integration of Machine Vision Systems to Aid Manufacturing Event Understanding

Xia

Saidy

Kirkpatrick

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Classical AI methods based on probabilistic approaches have been developed with known physics and pure data-driven based models too [70,[123][124][125][126][127][128][129][130][131][132][133][134][135][136][137][138]. The method of reinforcement learning has not yet been in practical use, but there are very few conceptual works on the inspection during the manufacturing process [139]. Fuzzy logic is used in combination with several models and deals with uncertainty [89,99,[140][141][142].…”

Section: Ai Paradigms In Compositesmentioning

confidence: 99%

Artificial intelligence in real-time diagnostics and prognostics of composite materials and its uncertainties—a review

Elenchezhian

Vadlamudi

Raihan

et al. 2021

Smart Mater. Struct.

View full text Add to dashboard Cite

In the era of the 4th industrial revolution of big data, artificial intelligence (AI) is widely used in each and every field of composite materials which includes design and analysis, material storage, manufacturing, non-destructive testing, structural health monitoring (SHM) and prognostics of its remaining useful life, material state (MS) and damage modes. While these AI models are rapidly developed and integrated into the industrial internet of things to keep track of the health of a composite material from its birth to death, these integrations remain uncertain for prognostics without the certainty of its previous MS. This article is a comprehensive review of the AI models being developed over the past few decades in the field of SHM and prognostics health management of polymer matrix composites. It further analyzes the real gaps between these developments and the nature of uncertainty of these methods. Finally, the pipeline for the real-time prognostics from birth to death, hybrid approaches, uncertainty quantification of data-driven and physics-based systems, and its reliability standards to such complex advanced composite materials are discussed. This paper will be focused as a basic guide for researchers implementing AI in composites for diagnosis, prognosis, and control.

show abstract

“…By creating an Industrial Internet-of-Things (IIoT) platform, this work presents data-driven science solutions to the current industrial applications while moving towards accelerated Smart Manufacturing Innovation. As a result of this work, the conceptual outline towards an AI-driven robotic manufacturing cell proposed by our preliminary proof of concept [18] is further enhanced by illustrating more detailed implementations and key technologies along with some preliminary results using our methodology. On this basis, the foundation of a dynamic scheduler agent, termed the Digital Engine (DE), is developed as a smart process optimization tool utilizing virtual platform data.…”

Section: Introductionmentioning

confidence: 99%

Building Future Factories: A Smart Robotic Assembly Platform Using Virtual Commissioning, Data Analytics, and Accelerated Computing

Kircaliali¹,

Sacco²,

Xia³

et al. 2020

SAMPE 2020 | Virtual Series

View full text Add to dashboard Cite

Modern manufacturing platforms are defined by the quest for increased automation throughout the production cycle. This continuing pressure towards automation dictates that emergent technologies are leveraged towards this goal. Unfortunately, this increasing automation brings additional complexity and production issues. To address these challenges, this paper discusses the methods developed and deployed by our team (USC neXt) to employ (1) large-scale simulation, (2) system health monitoring sensors, and (3) advanced computational technologies to establish a life-like digital manufacturing platform and to capture, represent, predict, and control the dynamics of a live manufacturing cell. A machine learning based Digital Engine will be used to dynamically control and schedule operations in the live manufacturing cell, based on simulation results and real time data. Sensors, such as load cells, accelerometers, robot monitors, and thermal cameras will connect to digital twin systems, collecting and sharing accurate real-time plant descriptions between stakeholders. By creating our future factory using an Industrial Internet of Things (IIoT) platform, we will present data-driven science and engineering solutions to our industrial partners, accelerating the Smart Manufacturing Innovation. Future work will focus on applying the proposed methodology on more diverse manufacturing tasks and material flow, including collaborative assembly jobs, visual inspection, and continuous movement tasks.

show abstract

Virtual Comissioning of Manufacturing System Intelligent Control

Cited by 10 publications

References 0 publications

Towards Semantic Integration of Machine Vision Systems to Aid Manufacturing Event Understanding

Towards Semantic Integration of Machine Vision Systems to Aid Manufacturing Event Understanding

Artificial intelligence in real-time diagnostics and prognostics of composite materials and its uncertainties—a review

Building Future Factories: A Smart Robotic Assembly Platform Using Virtual Commissioning, Data Analytics, and Accelerated Computing

Contact Info

Product

Resources

About