Reliable Deep Learning and IoT-Based Monitoring System for Secure Computer Numerical Control Machines Against Cyber-Attacks With Experimental Verification

Tran, Minh-Quang; Elsisi, Mahmoud; Liu, Mengkun; Vu, Viet Q.; Mahmoud, Karar; Darwish, Mohamed M. F.; Abdelaziz, Almoataz Y.; Lehtonen, Matti

doi:10.1109/access.2022.3153471

Cited by 71 publications

(32 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This emulator integrates the PAE described in section IV-A-1), the PECE shown in Fig. 11, and the load model presented in (13). This system is executed on the FPGA every 14 μs.…”

Section: ) Emulators Integrationmentioning

confidence: 99%

“…The neural network determines the kind of fault based on gas concentration in the insolating oil with an accuracy of 94.36 % under normal conditions and 92.58 % considering cyberattacks. Finally, in [13] an IoT and deep learning neural network integration for online CNC machines monitoring is presented. The proposed platform classifies the machine operation into stable, unstable, and attacked, the latter in the case of an cyberattack, depending on the workpiece forces exerted by the machine.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Control Hardware in the Loop and IoT Integration: A Testbed for Residential Photovoltaic System Evaluation

et al. 2022

View full text Add to dashboard Cite

This article presents the development of a platform for the validation of controllers applied to photovoltaic systems (PVS) interconnected with the main grid (MG), integrating simulation real-time Hardware in the Loop (HIL) and Internet of Things (IoT). The proposed platform is made up of 5 parts: 1) a control HIL emulator (CHILE) that reproduces the behavior of a photovoltaic array, a power electronic converter for interconnection with the MG, and AC loads, 2) a cloud database implemented in ThingSpeak, 3) a smart sensor (SS) that monitors the behavior of AC loads, 4) a residential PVS with internet connection, and 5) an Android application for remote monitoring. The data generated by the residential system and the SS are stored in the database and from this information the CHILE reproduces its behavior in real time. The CHILE generates the variables related to the behavior of the PVS and transfers this information to the database. The mobile application allows users to view the behavior of the platform remotely. The usefulness of the platform is verified with a controller for the maximum power point tracking and the interconnection of the system with the MG in a 24-hour experiment, during which the behavior of the residential PVS and the AC loads are reproduced in the CHILE. The platform successfully emulates the behavior of the installed PVS with a mean relative error of 0.42 % and the AC load with a mean absolute error of 10 mA. Regarding data transfer in the IoT network, a mean time response of the server of 441.9 ms was observed without data loss during the 24-hours experiment.INDEX TERMS Control Hardware in the Loop, IoT, Photovoltaic System.

show abstract

“…This emulator integrates the PAE described in section IV-A-1), the PECE shown in Fig. 11, and the load model presented in (13). This system is executed on the FPGA every 14 μs.…”

Section: ) Emulators Integrationmentioning

confidence: 99%

mentioning

confidence: 99%

Control Hardware in the Loop and IoT Integration: A Testbed for Residential Photovoltaic System Evaluation

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In this work, we identify the effects of multiple factors as well as utilize DL tools in evaluating an optimal transmission strategy to decrease transmission loss and intelligent consumption of sensor power [27]. Using the DL method, the exploration of environmental conditions impacts on wireless connectivity in underground surroundings, such as transmission pathway loss, energy consumption, and system bandwidth balancing [32]. As a result, the development of a dependable and powerful data collection transmission is structured as a Cooperative and multi-constrained communication-based limitation.…”

Section: Proposed Deep Learning Based Cooperative Communication Chann...mentioning

confidence: 99%

A Novel Deep Learning-Based Cooperative Communication Channel Model for Wireless Underground Sensor Networks

Kanthavel

Dhaya

Khalaf

et al. 2022

Sensors

View full text Add to dashboard Cite

Wireless Underground Sensor Networks (WUSNs) have been showing prospective supervising application domains in the underground region of the earth through sensing, computation, and communication. This paper presents a novel Deep Learning (DL)-based Cooperative communication channel model for Wireless Underground Sensor Networks for accurate and reliable monitoring in hostile underground locations. Furthermore, the proposed communication model aims at the effective utilization of cluster-based Cooperative models through the relay nodes. However, by keeping the cost effectiveness, reliability, and user-friendliness of wireless underground sensor networks through inter-cluster Cooperative transmission between two cluster heads, the determination of the overall energy performance is also measured. The energy co-operative channel allocation routing (ECCAR), Energy Hierarchical Optimistic Routing (EHOR), Non-Cooperative, and Dynamic Energy Routing (DER) methods were used to figure out how well the proposed WUSN works. The Quality of Service (QoS) parameters such as transmission time, throughput, packet loss, and efficiency were used in order to evaluate the performance of the proposed WUSNs. From the simulation results, it is apparently seen that the proposed system demonstrates some superiority over other methods in terms of its better energy utilization of 89.71%, Packet Delivery ratio of 78.2%, Average Packet Delay of 82.3%, Average Network overhead of 77.4%, data packet throughput of 83.5% and an average system packet loss of 91%.

show abstract

“…The results of the research from various computer science topics are used to improve the overall experience in the industrial domain and improve the Industry 4.0 agenda [21]. It is not only the improvement of the product quality management system as described in [22] but also the usage of artificial intelligence (AI) and deep learning algorithms that could improve the segments of system security monitoring [23,24] and general fault diagnostics [25,26].…”

Section: Background and Significancementioning

confidence: 99%

Hybrid Software Deployment Strategy for Complex Industrial Systems

et al. 2022

View full text Add to dashboard Cite

Complex industrial systems run the different pieces of software in several interconnected physical layers. The software update in such an environment must be performed in the shortest possible period with the lowest possible resource usage. Namely, it is critical to minimize the data traffic, decrease software downtime, and reduce the impact of the transitional stage during the update process. To meet these requirements and to unify the update process, the common software node structure along with a hybrid software deployment strategy is proposed. The hybrid strategy is defined as a combination of the existing and well-tested techniques—blue/green, canary, and feature flags. The main aim was to utilize their positive sides and to obtain a better overall effect. The approach was tested in the simulation environment, based on the realistic factory layout, and running the software related to the enterprise resource planning (ERP) level. For successful updates, the proposed hybrid deployment method reduced downtime on server nodes to less than 5% and on client nodes to a half compared with the standard approach. The volume of data traffic reduction in a configuration with sentinel nodes is reduced by one-third. The presented results look promising, especially in cases of erroneous updates when a roll back is needed, where the downtime on the server nodes is reduced to the level of 3%. Achieved results are used to define the set of recommendations that could be extended for the other software layers, followed by a discussion about further potential problems and strategy variations.

show abstract

Reliable Deep Learning and IoT-Based Monitoring System for Secure Computer Numerical Control Machines Against Cyber-Attacks With Experimental Verification

Abstract: Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000.

Cited by 71 publications

References 56 publications

Control Hardware in the Loop and IoT Integration: A Testbed for Residential Photovoltaic System Evaluation

Control Hardware in the Loop and IoT Integration: A Testbed for Residential Photovoltaic System Evaluation

A Novel Deep Learning-Based Cooperative Communication Channel Model for Wireless Underground Sensor Networks

Hybrid Software Deployment Strategy for Complex Industrial Systems

Contact Info

Product

Resources

About