Real-time Human-machine Interface Research Articles

A Novel Approach to Surface EMG-based Gesture Classification Using a Vision Transformer Integrated with Convolutive Blind Source Separation.

A robust pattern recognition framework is required for ideal real-time human-machine interface (HMI) applications. Convolutional neural networks and recurrent neural networks have been widely used for the classification of gestures based on electromyography (EMG), but few studies have demonstrated the effectiveness of using a vision transformer for this purpose. Additionally, the accuracy achieved is influenced by the efficacy of the preprocessing pipeline. This study assessed ViT with and without an attention mechanism for precise motor intent decoding by investigating various input features and integrating convolutive blind source separation (BSS) preprocessing. All investigations were carried out with two open-access high-density surface EMG datasets of 34 and 21 hand gestures recorded from 20 and 5 healthy subjects respectively. Integration of centering and optimal extension factors resulted in better performance with raw input. However, spatial whitening increased the model's sensitivity to noise. The best-performing BSS-integrated convolution vision transformer model (BSS-CViT) model yielded an accuracy of 96.61% and 91.98% on test datasets one and two. This is a promising result for future studies in real-time HMI applications. The code implementation results reported in this study are available on GitHub. https://github.com/deremustapha/BSS-ViT.

The Development of Dispatcher Training Simulator in a Thermal Energy Generation System

A dispatcher training simulator (DTS) is a real-time Human Machine Interface (HMI)-based control tool that is able to visualize industrial control system processes. The present study was aimed at developing a simulator tool for boilers in a thermal power station. The DTS prototype was designed using technical data of thermal power station boilers in Indonesia. It was then designed and implemented in Wonderware Intouch 10. The resulting simulator came with component drawing, animation, control display, alarm system, real-time trend, historical trend. This application used 26 tagnames and was equipped with a security system. The test showed that the principles of real-time control worked well. It is expected that this research could significantly contribute to the development of thermal power station, particularly in terms of its application as a training simulator for beginning dispatchers.

A Study of Cloud Computing Based Intelligent Scheduling System for Manufacturing Quality

In the paper, a cloud computing based intelligent scheduling system for manufacturing quality is proposed. Most of scheduling system is only considered producing time but manufacturing quality. It is very important to focus on manufacturing quality for the industry upgrade. The factors of manufacturing quality are product, equipment, material and human. It makes higher cost for scheduling the flexible manufacturing system. So we develop the cloud computing-based intelligent scheduling system by using artificial neural network and optimized layout method for manufacturing quality in the research. The architecture of the intelligent scheduling system contains: (1) Cloud database structure. (2) Intelligent scheduling engine. (3) Real-time human-machine interface. SQL Azure is used as the cloud database for scattering and storing data. And the intelligent scheduling engine contains the intelligent sequence score system of the products, the optimized layout system and the monitoring system of available resources. By using Visual C#, we can program a human-machine interface with real-time data updating. So that we can see real-time scheduling states of manufacturing by the human-machine interface at any time everywhere. We get good performance from the results of the experiment in the intelligent scheduling system considering manufacturing quality. It is important to develop a cloud computing-based intelligent scheduling system for manufacturing quality because of the advantages of production fluency, low cost, just good quality and flexible management.

Development of Cloud Computing Based Intelligent Integrated Manufacturing System

A cloud computing based intelligent integrated manufacturing system was proposed. In order to develop an intelligent integrated manufacturing system, it is necessary to build up many database servers, which makes the system very expensive. To overcome this problem, we developed a cloud computing based system for quality analysis of the intelligent integrated manufacturing system. The architecture of the system contains: i) Cloud database structure; ii) Quality analysis engine; iii) Real-time human-machine interface. We use Microsoft SQL Azure as the cloud database to scatter and store data on redundant disk arrays. The quality analysis engine contains 12 quality input factors and 16 prediction outputs. It is used to predict manufacturing quality using neural networks. ASP.NET was used to program a human-machine interface with real-time data updating, providing a real-time data display available anytime, anywhere through the interface. Through experiments we found that that by using many database servers, improvement in a general traditional manufacturing system can be realized. The proven advantages of low cost, performance scalability, mobile management and maintenance facilities, make it important to develop a cloud computing based intelligent integrated manufacturing system using the analysis engine to predict manufacturing quality.

A real time human–machine interface for an ultrahigh temperature MEMS sensor–igniter

Abstract The progress of numerous emerging technologies is currently hampered by a disconnect between material science and engineering applications. The potential of nano-scale engineering can not be fully exploited as long as basic material science and engineering are not integrated. This paper is concerned with the development of a novel computational methodology that unites fundamental materials science, mechanical design, reliability analysis, and system level performance assessment in an interactive environment called the human–machine interface (HMI). The HMI serves as a real time display of the performance and the status of the device, e.g. the remaining life, and provides a simulation platform for design and optimization. The architecture and performance of the HMI is demonstrated by the example of an ultrahigh temperature MEMS sensor–igniter. The device is fabricated from a novel polymer derived ceramic (PDC) called silicon carbonitride (SiCN). The HMI methodology is portable to health monitoring of other high temperature systems such as gas turbine engines, missile systems, and high temperature processing of advanced materials.