Implementation of MQTT protocol based network architecture for smart factory

Yeh, Chia-Shin; Chen, Shang-Liang; Li, I-Ching

doi:10.1177/09544054211014488

Cited by 9 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An evolutional optimisation algorithm was executed on the edge service to efficiently pursuit a balanced optimisation between the energy consumption and the workload of production equipment during scheduling/rescheduling. A convolutional neural network (CNN)-based system to classify defective products on an assembly line was developed [5]. The CNN-based system was distributed into an edge-cloud architecture for system optimisation.…”

Section: Literature Reviewmentioning

confidence: 99%

“…A convolutional neural network (CNN)-based system to classify defective products on an assembly line was developed. 5 The CNN-based system was distributed into an edge-cloud architecture for system optimisation. In Li et al, 6 the shallow layer of the CNN-based system was arranged on an edge device to pre-process product data in a more efficient means.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Distributed deep learning enabled prediction on cutting tool wear and remaining useful life

Zhang

Wang

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

To optimise the utilisation cost of cutting tools, it is imperative to develop an online system to efficiently and accurately predict tool wear conditions and remaining useful lives (RULs). With this aim, a novel system is proposed based on deep learning algorithms distributed over an edge-cloud computing architecture. The system is innovative in the following aspects: (i) a lightweight convolutional neural network-random forest (CNN-RF) model is designed to be executed on an edge device to assess tool wear conditions efficiently, which supports severe tool resilience and tool replacement when necessary; (ii) a convolutional neural network-long short-term memory (CNN-LSTM) model is designed to be executed on a cloud to process long-term signals to predict the RUL of the cutting tool, which supports fine-tuning tool parameters dynamically; (iii) a signal compression mechanism is developed to condense the signals of tooling conditions into 2D images so the signal volumes transferred over the network are minimised and signal security is improved. Experiments were performed in a real-world machining workshop for research methodology validation. It showed that the prediction accuracies for tool wear and RUL achieved 90.6% and 93.2%, respectively, and the volume of signals transferred over the network was reduced by 89.0%. The experiments and benchmarks with comparative algorithms demonstrated that the system and its methodology exhibited great potential to reinforce cutting tool optimisation for real-world applications.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Distributed deep learning enabled prediction on cutting tool wear and remaining useful life

Zhang

Wang

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

show abstract

“…The MQTT protocol used in this paper is a relatively easy communication protocol for message transmission, which is also a lightweight transmission with two types of message transmission modes: publisher mode and subscriber mode. The MQTT protocol is extremely suitable for IoT projects and APPs with low network traffic because of these features [6].…”

Section: Mqtt-based Remote Capturementioning

confidence: 99%

A Pose Intelligent Monitoring System Based on Message Queuing Telemetry Transport Protocol in the Classroom Background

Huang¹,

Zhou²

2023

Atlantis Highlights in Computer Sciences

View full text Add to dashboard Cite

The prosperity of education contributes to national prosperity and socioeconomic development. The expanding student population in compulsory education makes it technically difficult for teachers to assess students' behavior and learning attitudes. In order to regulate classroom teaching and prevent students from leaving early, missing classes, or cheating on exams, schools have purchased video surveillance equipment and thus made such products enter the education market. However, the current combination of cameras and video recorders has a limited effect due to the lack of intelligent factors. To address this problem, this study is dedicated to introducing an artificial intelligence solution in the education field to deepen education informatization, i.e., using a pose detection algorithm to achieve intelligent monitoring of students' poses in a classroom background through the subscribe and publish mechanism in the Message Queuing Telemetry Transport (MQTT) protocol. The system is able to reflect the students' classroom performance to the teacher, which plays an essential role in promoting the development of teaching programs and improving teaching quality.

show abstract

“…Once the perception layer is deployed in the FFP, the network layer then requires a real-time and reliable network technology for the heading process. 37 That edge computing coordinating with cloud computers helps the scale expansion and IIoT application. Because of the high-speed punching actions of the heading machine in the FFP, individual screws can not be measured directly to verify the acceptance of the dimension.…”

Section: Network Layer Technologiesmentioning

confidence: 99%

Industrial Internet of Things on integrated preventive maintenance and enterprise-resource-planning systems: A case study of fastener forming manufacturing processes

Hsu

Wang³

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

The Industrial Internet of Things (IIoT) has evolved industrial operations to be more efficient and reliable. The fastener forming process (FFP) used to rely on the judgments of in-process inspectors and experienced operators. Since no critical information was transmitted between machines, the machining status during production was unable to reveal. Now, with sensors installed in the machines of FFP, manufacturing data can be collected, analyzed, and responded to the machines. This IIoT-embedded FFP can not only carry out real-time data, pre-processing, and feature engineering but also enable optimally selecting classification algorithms for preventive maintenance. Consequently, the FFP establishes machine-health indicators for the production site and the heading process recognizes the abnormal situations between punches. The operator-delayed response leads to a great amount of loss that can be avoided. Besides, with the integration of enterprise resource planning (ERP) and manufacturing execution system (MES), this IIoT-embedded FFP converts receiving customer orders into work orders and coordinates operations and sales within enterprises. This system integration catches the status of various production indicators and further advances accurate materials preparation and inventory costs control. Overall, this IIoT-embedded FFP system becomes no necessity for increasing inventory and reserving backlog funds to cope with the impact of a vast number of scrap products. Finally, other types of machining processes or systems can adopt this systematic approach in the future.

show abstract

Implementation of MQTT protocol based network architecture for smart factory

Cited by 9 publications

References 6 publications

Distributed deep learning enabled prediction on cutting tool wear and remaining useful life

Distributed deep learning enabled prediction on cutting tool wear and remaining useful life

A Pose Intelligent Monitoring System Based on Message Queuing Telemetry Transport Protocol in the Classroom Background

Industrial Internet of Things on integrated preventive maintenance and enterprise-resource-planning systems: A case study of fastener forming manufacturing processes

Contact Info

Product

Resources

About