An Electric and Electronic Circuit Remote Laboratory in a Control Course

Pavani, Ana M. M.; Barbosa, William S.

doi:10.1109/educon52537.2022.9766652

Cited by 3 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep expertise and experience are required for these developing technologies since they have significant effects on education processes and business structures as provided in the manuscript by Andriole [2]. The virtual laboratory is widely developed to interface many hardware laboratories curriculum like Embedded systems, analog systems, and electronic devices and circuits as shown in Pavani and Barbosa [16] and Villar-Martínez et al [21]. Currently, robotic laboratories for teaching and providing training to students are quite expensive.…”

Section: Introductionmentioning

confidence: 99%

Implementation of an Industrial Automation Remote Lab (IARL) and validation using a deep learning approach during the COVID pandemic

Sekaran,

Hildas

2023

Comp Applic In Engineering

View full text Add to dashboard Cite

The purpose of this study is to demonstrate a novel remote lab development for improving student psychomotor skills in the Industry 4.0 course. In this work, the vision and Internet of Things‐based lab setup for third‐year undergraduates is proposed as Industrial Automation Remote Lab (IARL). The major motivation of this novel approach is to replicate Industry 4.0 in the laboratory for learning purposes to undergraduate students during pandemic condition. In industries, it is essential to collect all the data from the machines to make optimal use of resources and increase the efficiency of the system. The stored data are interfaced through the user datagram protocol to control the speed of the hydraulic actuator. In the proposed experimental work, a vision sensor‐based anydesk remote control software technique is employed to conduct programmable logic circuit (PLC) experiments. To collect the various output image data sets, numerous PLC experiments were conducted. The collection of images is classified to investigate the student performance using deep learning algorithms like YOLOv4, VGG, and YOLOv5. Based on the simulation and validation results, the IARL‐based approach with YOLOv5 outperforms the other two algorithms with 98% accuracy. Additionally, the validated statistical internal and external results show that the remote laboratory Conceive, Design, Implement, and Operate (CDIO) batch performance is highly improved over virtual laboratory CDIO batch students.

show abstract

Section: Introductionmentioning

confidence: 99%