International Journal of Engineering and Technology Innovation

Using Deep Learning Technology to Realize the Automatic Control Program of Robot Arm Based on Hand Gesture Recognition

2021-10-08T08:18:16+00:00

In this study, the robot arm control, computer vision, and deep learning technologies are combined to realize an automatic control program. There are three functional modules in this program, i.e., the hand gesture recognition module, the robot arm control module, and the communication module. The hand gesture recognition module records the user’s hand gesture images to recognize the gestures’ features using the YOLOv4 algorithm. The recognition results are transmitted to the robot arm control module by the communication module. Finally, the received hand gesture commands are analyzed and executed by the robot arm control module. With the proposed program, engineers can interact with the robot arm through hand gestures, teach the robot arm to record the trajectory by simple hand movements, and call different scripts to satisfy robot motion requirements in the actual production environment.

A Review on Advances in Automated Plant Disease Detection

2021-10-08T08:29:08+00:00

Plant diseases cause major yield and economic losses. To detect plant disease at early stages, selecting appropriate techniques is imperative as it affects the cost, diagnosis time, and accuracy. This research gives a comprehensive review of various plant disease detection methods based on the images used and processing algorithms applied. It systematically analyzes various traditional machine learning and deep learning algorithms used for processing visible and spectral range images, and comparatively evaluates the work done in literature in terms of datasets used, various image processing techniques employed, models utilized, and efficiency achieved. The study discusses the benefits and restrictions of each method along with the challenges to be addressed for rapid and accurate plant disease detection. Results show that for plant disease detection, deep learning outperforms traditional machine learning algorithms while visible range images are more widely used compared to spectral images.

On the Pull-Out Behavior of Hooked-End Shape Memory Alloys Fibers Embedded in Ultra-High Performance Concrete

2021-10-08T08:15:02+00:00

This study presents a three-dimensional non-linear finite element investigation on the pull-out behavior of straight and hooked-end Shape Memory Alloys (SMA) and steel fibers embedded in Ultra-High Performance Concrete (UHPC) using a single fiber pull-out model. A bilinear cohesive zone model is used to characterize the interfacial traction separation relationships. The Concrete Damage Plasticity (CDP) model is used to simulate UHPC, and the mechanical behavior is obtained through experimental tests. Parametric studies are conducted to evaluate the effects of fiber materials, fiber diameters, and hook angles on the load-displacement behavior. A good agreement between the numerical and experimental results is obtained. It is found that the hooked-end fibers with a smaller diameter and a hook angle of 40° can be a better choice for structural application. Furthermore, it is observed that the use of SMA fibers significantly improves the pull-out performance between fibers and UHPC.

A Hybrid Simulation of Converter-Interfaced Generation as the Part of a Large-Scale Power System Model

2021-10-08T08:16:44+00:00

This study aims to propose an alternative hybrid approach to model renewable energy sources (RESs), which provide the most reliable results in comparison with the existing simulating tools. Within the framework of this approach, a specialized hybrid processor for modeling converter-interfaced generation (CIG) is developed. This study describes its structure and validation in the test system by comparing the results with commercial modeling tools, and also presents experimental studies of its operation as parts of the practical power system. The results obtained confirm the adequacy of the developed tools.

Planar EBG Loaded UWB Monopole Antenna with Triple Notch Characteristics

2021-10-08T08:27:35+00:00

A triple band-notched ultra-wideband (UWB) monopole antenna using a planar electromagnetic bandgap (EBG) design is proposed. The EBG unit cell composed by an Archimedean spiral and inter-digital capacitance demonstrates the notch frequencies. The antenna with EBG cells near the feed line occupies only 30 × 36 mm²with triple band-rejection characteristics. The three notched bands at 4.2 GHz, 5.2 GHz, and 9.1 GHz can be used in C-band satellite downlink, wireless local area network (WLAN), and X-band radio location for naval radar or military required applications. In addition, the proposed design is flexible to tune different notched bands by altering the EBG dimensions. The parametric analysis is studied in details after placing the EBG unit cells near the feed line to show the coupling effect. The input impedance and surface current distribution analysis are also analyzed to understand the effect of EBG at notch frequencies. The proposed design prototype is fabricated and characterized. A fairly considerable agreement is observed between simulated and measured results.

Cement-Based Mortar Panels Reinforced with Recycled Steel Fibers in Flexural Strengthening of Concrete Beams

2021-10-08T08:20:01+00:00

The effectiveness of a strengthening technique devised for the concrete beams subjected to bending is presented in this study, where recycled-steel fiber-reinforced mortar (RSFRM) panels are used as an eco-friendly replacement for ordinary steel fibers. Different mix designs for RSFRM are first investigated experimentally by testing 160 × 400 × 400 mm³ notched beam-like specimens in 3-point bending, while 100 × 100 × 100 mm³ cubes are tested in compression, to optimize the mix design. Finite element (FE) analyses are carried out on strengthened and non-strengthened beams to investigate the effectiveness of the proposed strengthening technique based on RSFRM panels. Starting from the tests on notched beams, an inverse FE analysis is used to optimize the RSFRM’s parameters to be implemented into the numerical model. The results show that applying RSFRM panels not only markedly increases the load-bearing capacity of the beams (up to 3.19 times with 3% of fibers by volume), but also changes their fracture mechanism from brittle to ductile fracture.