A Model for Working Environment Monitoring in Smart Manufacturing

Dobrilovic, Dalibor; Brtka, Vladimir; Stojanov, Zeljko; Jotanović, Gordana; Peraković, Dragan; Jauševac, Goran

doi:10.3390/app11062850

Cited by 21 publications

(20 citation statements)

References 39 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several standards available to be applied in monitoring applications [21]. Some industrial applications developed with wireless technologies are described in [22,23]. Sometimes, the IEEE 802.11 standard is used at industrial communications, but in general, it does not ensure the QoS requirements.…”

Section: Related Workmentioning

confidence: 99%

“…Finally, some studies in the literature propose different architectures that allow the integration of process data acquired with ZigBee with cloud infrastructures using different technologies [17,23,52,53]. This approach allows the separation of the traffic generated from the processes to the cloud services improving the efficiency of the factories.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Design and Performance of a XBee 900 MHz Acquisition System Aimed at Industrial Applications

et al. 2021

View full text Add to dashboard Cite

Wireless technologies are being introduced in industrial applications since they provide certain benefits, such as the flexibility to modify the layout of the nodes, improving connectivity with monitoring and decision nodes, adapting to mobile devices and reducing or eliminating cabling. However, companies are still reluctant to use them in time-critical applications, and consequently, more research is needed in order to be massively deployed in industrial environments. This paper goes in this direction by presenting a novel wireless acquisition system aimed at industrial applications. This system embeds a low-cost technology, such as XBee, not frequently considered for deterministic applications, for deploying industrial applications that must fulfill certain QoS requirements. The use of XBee 900 MHz modules allows for the use of the 2.4 GHz band for other purposes, such as connecting to cloud services, without causing interferences with critical applications. The system implements a time-slotted media access (TDMA) approach with a timely transmission scheduling of the messages on top of the XBee 900 MHz technology. The paper discusses the details of the acquisition system, including the topology, the nodes involved, the so-called coordinator node and smart measuring nodes, and the design of the frames. Smart measuring nodes are implemented by an original PCB which were specifically designed and manufactured. This board eases the connection of the sensors to the acquisition system. Experimental tests were carried out to validate the presented wireless acquisition system. Its applicability is shown in an industrial scenario for monitoring the positioning of an aeronautical reconfigurable tooling prototype. Both wired and wireless technologies were used to compare the variables monitored. The results proved that the followed approach may be an alternative for monitoring big machinery in indoor industrial environments, becoming especially suitable for acquiring values from sensors located in mobile parts or difficult-to-reach places.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Design and Performance of a XBee 900 MHz Acquisition System Aimed at Industrial Applications

et al. 2021

View full text Add to dashboard Cite

show abstract

“…AlexNet also included a stack of convolutional layers instead of the previous approach, where a pooling layer [17] followed each convolutional layer. The calculations make it possible to use a large database with a large amount of images at a high learning speed.…”

Section: ) Alexnetmentioning

confidence: 99%

An Advanced Ontology based Deep Learning for Computer-aided Interpretation of Mammography Images

Rahli¹,

Benamrane²

2021

IJACSA

View full text Add to dashboard Cite

Computer assisted detection (CAD) are able to detect and characterize suspicious mammographic images, micro calcifications, masses or more difficult, architectural distortion. With the exploitation of these different characteristics, the system can specify and predict the severity of the tumor to assess the risk in terms of Malignity/Benignness. Our work involves the development of a new method for screening breast cancer, this is achieved by developing a whole strategy of knowledge extraction through deep learning and medical ontology appropriate for the classification of regions selected from digital mammograms, for each radiological sign considered, namely, masses and micro calcifications. First, we extracted the parameters characterizing the images used as input to a deep convolutional neuron network CNN. The learning is supervised because the images used are images from the MARATHON database of the University of Florida; they are already diagnosed by experts. The second phase aims to add a semantic level to our classification through a specialized ontology developed for this purpose based on the BIRADS characterization system. Based on the evaluation performed, the proposed approach provides better classification results than the usual methods for assisting in the computer aided detection of breast cancer.

show abstract

“…For this reason, an academic smart factory environment [ 38 ] was developed, which serves students and therefore future experts as a practical learning environment to deepen their knowledge in digitalization technologies. In comparison to similar learning factories [ 39 , 40 , 41 , 42 , 43 , 44 ], the framework discussed in this paper has the advantage of consideration of real physical processes and material parameters (e.g., the possibility of integrating numerical simulation, prediction of microstructure of examined specimens). Furthermore, it supports SMEs by demonstrating low-cost possibilities of digitization and digitalization approaches within the metal processing industry.…”

Section: Introductionmentioning

confidence: 99%

Implementation of a Six-Layer Smart Factory Architecture with Special Focus on Transdisciplinary Engineering Education

Ralph

Sorger

Schödinger

et al. 2021

Sensors

View full text Add to dashboard Cite

Smart factories are an integral element of the manufacturing infrastructure in the context of the fourth industrial revolution. Nevertheless, there is frequently a deficiency of adequate training facilities for future engineering experts in the academic environment. For this reason, this paper describes the development and implementation of two different layer architectures for the metal processing environment. The first architecture is based on low-cost but resilient devices, allowing interested parties to work with mostly open-source interfaces and standard back-end programming environments. Additionally, one proprietary and two open-source graphical user interfaces (GUIs) were developed. Those interfaces can be adapted front-end as well as back-end, ensuring a holistic comprehension of their capabilities and limits. As a result, a six-layer architecture, from digitization to an interactive project management tool, was designed and implemented in the practical workflow at the academic institution. To take the complexity of thermo-mechanical processing in the metal processing field into account, an alternative layer, connected with the thermo-mechanical treatment simulator Gleeble 3800, was designed. This framework is capable of transferring sensor data with high frequency, enabling data collection for the numerical simulation of complex material behavior under high temperature processing. Finally, the possibility of connecting both systems by using open-source software packages is demonstrated.

show abstract

A Model for Working Environment Monitoring in Smart Manufacturing

Cited by 21 publications

References 39 publications

Design and Performance of a XBee 900 MHz Acquisition System Aimed at Industrial Applications

Design and Performance of a XBee 900 MHz Acquisition System Aimed at Industrial Applications

An Advanced Ontology based Deep Learning for Computer-aided Interpretation of Mammography Images

Implementation of a Six-Layer Smart Factory Architecture with Special Focus on Transdisciplinary Engineering Education

Contact Info

Product

Resources

About