this article introduces a 3D virtual factory simulator designed to revolutionize microcontroller programming education. the simulator employs real-world physics and immersive environments, allowing students to interac...
详细信息
this article introduces a 3D virtual factory simulator designed to revolutionize microcontroller programming education. the simulator employs real-world physics and immersive environments, allowing students to interact with virtual machinery and systems. Students have responded enthusiastically, finding the simulator engaging and effective. this innovative tool not only reinforces programming concepts but also promotes practical understanding. In summary, the 3D virtual factory simulator offers an exciting approach to microcontroller programming education, enhancing student motivation and learning outcomes. Copyright (c) 2024 the Authors.
this work is about building automation. It deals withthe implementation of the connection between KNX TP bus and ZigBee wireless technology. the connection focuses on the control of lighting end devices supporting th...
详细信息
this work is about building automation. It deals withthe implementation of the connection between KNX TP bus and ZigBee wireless technology. the connection focuses on the control of lighting end devices supporting the ZigBee protocol by KNX TP sensors. this approach leads to a reduction in the cost of home automation. Copyright (c) 2024 the Authors.
this paper focuses on the implementation of recognition and detection algorithms for programmable logic controllers (PLCs) based on artificial intelligence (AI). AI methods based on deep neural networks (DNN) are char...
详细信息
this paper focuses on the implementation of recognition and detection algorithms for programmable logic controllers (PLCs) based on artificial intelligence (AI). AI methods based on deep neural networks (DNN) are characterized by a large number of hidden layers and neurons in hidden layers, which increases the computational complexity of computing the outputs of artificial neural networks (ANNs). Popular convolutional neural networks (CNN) are among such ResNet, AlexNet, GoogLeNet and others. A remote cloud solution is proposed in this paper to compute CNN outputs. the CNN implementation was tested on object recognition and detection applications. Training and testing of the CNN and YOLO detector was carried out in the Python environment. Copyright (c) 2024 the Authors.
the proceedings contain 54 papers. the topics discussed include: fault detection algorithm for pneumatic measuring and sorting station;design and analyses of tendon-driven continuum robots for minimally invasive surge...
the proceedings contain 54 papers. the topics discussed include: fault detection algorithm for pneumatic measuring and sorting station;design and analyses of tendon-driven continuum robots for minimally invasive surgery;a method of tactile resistive sensor array calibration;computer vision approaches for automated bee counting application;open source embedded system approach for decreasing carbon footprint of Oldtimers;practice-oriented controller design of a simple nonlinear system;laboratory tester for relay contacts lifespan;a data-driven approach to reliability and fault analysis in industrial maintenance;comparison of split computing scenarios for object detection;the influence of recursive filtering methods on Bluetooth-based localization;event driven phase-locked loop with application to atomic force microscopy oscillation non-resonant modes;road pavement monitoring and analysis approaches using gyroscope and accelerometer data;a comparison of methods recovering signals from non-uniform samples;and experimental kit and digital model to support an agile design process of an industrial multihead weigher.
In this paper a perception system of a mobile robot is proposed and implemented combining a LiDAR sensor with a colour camera. Localisation of unknown objects in an a priori known environment and their classification ...
详细信息
In this paper a perception system of a mobile robot is proposed and implemented combining a LiDAR sensor with a colour camera. Localisation of unknown objects in an a priori known environment and their classification is required in order for the robot to safely and reliably navigate the working area. To this end, a pipeline is proposed to process and fuse the LiDAR 3D point-cloud data with a monocular colour camera image classifications yielding precisely localised 3D detections with class designations. the proposed pipeline is designed to run on limited computational power embedded platforms in the ROS 2 environment, and has been tested on a robotic testbench. Copyright (c) 2024 the Authors. this is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0/)
this article deals with implementing an IoT approach based on a case study with an emphasis on current data collection concepts and expanding automated workplaces' functionality. As part of this, the article descr...
详细信息
this article deals with implementing an IoT approach based on a case study with an emphasis on current data collection concepts and expanding automated workplaces' functionality. As part of this, the article describes the issues and advantages of IO-Link technology as part of the introduction of the emerging digitization all around us. Part of the presented solution is the direct configuration and diagnostic functions of IO-Link sensors and IO-Link master, which are applied to the FMS 500 modular laboratory system. the proposed case study proves the complexity and compatibility of individual modules, and its goal is to demonstrate the feasibility of practical requirements, research, and teaching in Industry 4.0 standards. Additionally, test experiments have shown the suitability of deploying such concepts in global diagnostics and predictive maintenance environments. Copyright (c) 2024 the Authors.
the circuitry modelling of the standalone photovoltaic (PV) maximum power point tracking (MPPT) lithium-ion battery charge controller is presented in this study using the MATLAB/Simulink environment. For the charge co...
详细信息
the circuitry modelling of the standalone photovoltaic (PV) maximum power point tracking (MPPT) lithium-ion battery charge controller is presented in this study using the MATLAB/Simulink environment. For the charge controller implementation, a DC-DC converter called a buck topology is used. the Perturb and Observe (P&O) MPPT algorithm monitors the solar panel's peak power. the lithium-ion battery is charged in three stages by the battery charge controller. the model's performance is analysed in terms of MPPT tracking performance, battery charging performance, and overall charge controller efficiency performance. With an MPPT efficiency of up to 99.9%, the performance result demonstrates that the MPPT is capable of tracking to the PV panel maximum point at any variation in solar irradiation. For small and medium standalone PV systems, this verified model aids in improved sizing of PV panels and battery energy storage. Techno-economic analysis refers to the assessment of the economic viability and profitability of using this type of lighting compared to other forms of lighting. the maintenance costs and efficiency of these systems can be improved even more by adding a programmable logic controller (PLC). Copyright (c) 2024 the Authors. this is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0/)
the addition of a 16-bit unsigned divider to Xilinx's Kintex and Virtex FPGA devices improves digital design and computational performance. Developers may divide nonnegative 16-bit integers withthe 16-bit unsigne...
详细信息
In the ever-evolving landscape of automotive engineering, the importance of efficient and adaptable engine control is paramount. Open-source Engine Control Unit (OS-ECU) emerges as an innovative, presenting a blend of...
详细信息
In the ever-evolving landscape of automotive engineering, the importance of efficient and adaptable engine control is paramount. Open-source Engine Control Unit (OS-ECU) emerges as an innovative, presenting a blend of intricate electronic design and adaptability. this study delves deep into the very heart of OS-ECU, unraveling its printed circuit board (PCB) layout withthrough Hole Technology (thT), electronic components, and the harmonious interplay between them. By meticulously exploring these aspects, we aim to understand not only the electronic foundation of OS-ECU but also its practical implications when integrated into a vehicle. Subsequently, the research touches upon the synergy between the electronics Engine Control Unit (ECU) and the accompanying software, shedding light on how they cohesively drive engine performance. Our findings emphasize the transformative potential of open-source electronic solutions like OS-ECU in reshaping and enhancing traditional automotive systems. Copyright (c) 2024 the Authors.
In recent years, the topic of embedded machine learning has become very popular in AI research. Withthe help of various compression techniques such as pruning, quantization and others compression techniques, it becam...
详细信息
In recent years, the topic of embedded machine learning has become very popular in AI research. Withthe help of various compression techniques such as pruning, quantization and others compression techniques, it became possible to run neural networks on embeddeddevices. these techniques have opened up a whole new application area for machine learning. they range from smart products such as voice assistants to smart sensors that are needed in robotics. Despite the achievements in embedded machine learning, efficient algorithms for training neural networks in constrained domains are still lacking. Training on embeddeddevices will open up further fields of applications. Efficient training algorithms would enable federated learning on embeddeddevices, in which the data remains where it was collected, or retraining of neural networks in different domains. In this paper, we summarize techniques that make training on embeddeddevices possible. We first describe the need and requirements for such algorithms. then we examine existing techniques that address training in resource-constrained environments as well as techniques that are also suitable for training on embeddeddevices, such as incremental learning. At the end, we also discuss which problems and open questions still need to be solved in these areas.
暂无评论