{"title":"Experimental investigation of 1:25 scaled model of Pendulum Wave Energy Converter","authors":"Beatrice Fenu, F. Niosi, B. Paduano, S. Sirigu","doi":"10.1109/ICECCME55909.2022.9987910","DOIUrl":"https://doi.org/10.1109/ICECCME55909.2022.9987910","url":null,"abstract":"The experimental campaign of the 1:25 Pendulum Wave Energy Converter (PeWEC) scaled model is presented with the aim to understand the hydrodynamic behaviour of the device in operative and severe sea state conditions. The experimental setup is described and particular attention has been given to the mooring system scaling procedure and realization. Tests of system identification, irregular waves and extreme waves of the floating-moored model of the PeWEC device have been performed at the University of Naples Federico II. The results of the hydrodynamic analysis shows the influence of non-linearities depending on the sea condition. In addition the influence of the wavefront direction is evaluated through the loads acting on the mooring lines, resulting favorable for a wave front acting on the bow of the hull.","PeriodicalId":202568,"journal":{"name":"2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121603965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Anna Kusetogullari, H. Kusetogullari, Amir Yavariabdi, Martin Andersson, Johan Eklund
{"title":"Genetic Algorithm-based Variable Selection Approach for High-Growth Firm Prediction","authors":"Anna Kusetogullari, H. Kusetogullari, Amir Yavariabdi, Martin Andersson, Johan Eklund","doi":"10.1109/ICECCME55909.2022.9988729","DOIUrl":"https://doi.org/10.1109/ICECCME55909.2022.9988729","url":null,"abstract":"In this paper, we propose a novel method for high-growth firm prediction by minimizing a cost function using a Genetic Algorithm (GA). To achieve it, the GA is used to search to find a set of important variables which provide the best fit for machine learning models so that accurate predictions can be made for high-growth firm prediction. The GA is employed to optimize the mean square error (MSE) between the accurate results and the predicted results of the machine learning methods by evolving the initially generated binary solutions through iterations. The proposed method obtains the best fitting set of variables for the machine learning methods for high-growth firm prediction. Four different machine learning methods which are Support Vector Machines (SVM), Logistic Regression, Random Forest (RF) and K-Nearest Neighbor (K-NN) have been employed with the GA and experimental results show that using RF with the GA achieves the best accuracy results with 94.93%.","PeriodicalId":202568,"journal":{"name":"2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132298050","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Inverted Kinematics of a Redundant Manipulator with a MLP Neural Network","authors":"V. Hlavác","doi":"10.1109/ICECCME55909.2022.9987898","DOIUrl":"https://doi.org/10.1109/ICECCME55909.2022.9987898","url":null,"abstract":"The article describes the solution of the inverse kinematics of a serial redundant manipulator. Reachable endpoint positions are generated randomly based on forward kinematics, described by Denavit-Hartenberg notation. If the randomly generated position is part of the area in which the desired movement is to be solved, it is recorded in a special structure where each cell corresponds to a small range of the endpoint coordinates. Up to thousands of possible combinations can be recorded in each of the cells. Based on this data, inverse kinematics cannot be solved for a redundant manipulator because the same point can be reached by infinitely many combinations of arm settings. Therefore, the prepared angle settings for reaching an individual cell are first evaluated with a suitable additional fitness function. Additionally, solutions that do not represent continuous movement are filtered. After this process, described in this article, the few best solutions are then selected from each of the cells and used to train a simple MLP (multilayer perceptron) neural network. Based on data from forward kinematics, the network is trained to obtain an inverse kinematics solution. The result is a smooth motion whose accuracy is limited by the cell size used and the amount of samples generated.","PeriodicalId":202568,"journal":{"name":"2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132524483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"3D Matched Manifold Detection for Optimizing Point Cloud Registration","authors":"Amit Efraim, J. Francos","doi":"10.1109/ICECCME55909.2022.9988221","DOIUrl":"https://doi.org/10.1109/ICECCME55909.2022.9988221","url":null,"abstract":"Point cloud registration is usually performed by matching key points to obtain an approximate global alignment, followed by a local optimization algorithm such as the iterative closest point (I CP) and its variants, to refine the initial estimate. These refinement algorithms, however, converge in many cases to a false local extremum. We propose a new matched manifold detection approach over the group of rigid 3-D transformations, by employing a novel correlation operator between functions defined on sparsely and non-uniformly sampled point clouds. Correlation between point clouds is evaluated using a method-ology inspired by the definition of the Kernel Point Convolution (KPConv), but instead of performing convolution with a kernel, the inner-product of feature vectors evaluated on the points in the two point clouds are aggregated. The proposed approach is shown to outperform state of the art local registration methods in terms of accuracy on challenging data sets.","PeriodicalId":202568,"journal":{"name":"2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132536015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Filippo Sanfilippo, R. T. Thorstensen, A. Jha, Zhiyu Jiang, K. Robbersmyr
{"title":"A Perspective Review on Digital Twins for Roads, Bridges, and Civil Infrastructures","authors":"Filippo Sanfilippo, R. T. Thorstensen, A. Jha, Zhiyu Jiang, K. Robbersmyr","doi":"10.1109/ICECCME55909.2022.9988693","DOIUrl":"https://doi.org/10.1109/ICECCME55909.2022.9988693","url":null,"abstract":"A digital model that is the counterpart - or twin - of a physical asset is considered a digital twin. Digital twins are becoming one of the most important technology trends for transportation infrastructure because of their potential to increase asset reliability and performance. As they offer current information about the status of the road infrastructure and the risks connected to it, digital twins can be seen as the foundation of infrastructure decision-making. Digital twins provide civil engineers with the ability to visualise assets across their entire life cycle to track changes and to perform analysis that optimises asset performance. The aim of this paper is to present a novel perspective for designing, prototyping and testing digital twins of bridges and road infrastructure. The methodology used takes into account the potential for developing a digital twin for the road infrastructure, taking into account stratigraphic analysis, surface condition monitoring, and bridges structural analysis. We seek to stimulate global efforts towards the achievement of efficient maintenance and management of infrastructures and facilities.","PeriodicalId":202568,"journal":{"name":"2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130212982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A first e-scooter powertrain analysis for Fuel Cell integration","authors":"Ettore Bianco, M. Carello","doi":"10.1109/ICECCME55909.2022.9988297","DOIUrl":"https://doi.org/10.1109/ICECCME55909.2022.9988297","url":null,"abstract":"Micro-mobility is increasingly widespread in cities because of portability and low cost of the solutions. E-scooters are the emerging means of transport for short distances; however, some drawbacks are present such as the autonomy and the need of frequent recharges. The aim of this paper is to analyze an e-scooter commercial powertrain in order to evaluate the convenience of a Fuel Cell (FC) integration, obtaining an increase of autonomy. An electric model has been implemented in Matlab/Simulink, investigating the inverter control strategy behavior and the electrical waveforms flowing in the electric powertrain. Some experimental tests were performed to validate the electrical Brushless DC model and the control strategy. First, a test on a Maxon brushless DC motor was performed evaluating the inverter control strategy and battery pack coupling. Then a dynamic test was performed on a commercial e-scooter Ninebot E25E comparing the two motor behaviors and inverters control strategies. The final part of the paper presents a first evaluation of a fuel cell integration, comparing the commercial external Ninebot battery pack with a Horizon H-500 Fuel cell integration solution. The results have allowed the validation of the brushless DC model and the Fuel Cell integration feasibility.","PeriodicalId":202568,"journal":{"name":"2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133901339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Livia Maglić, Ana Grbčić, Lovro Maglić, Antonio Blažina
{"title":"Evaluation of ultrasonic berth sensors in the port environment: case study Port of Cristo","authors":"Livia Maglić, Ana Grbčić, Lovro Maglić, Antonio Blažina","doi":"10.1109/ICECCME55909.2022.9988615","DOIUrl":"https://doi.org/10.1109/ICECCME55909.2022.9988615","url":null,"abstract":"Berth occupancy sensors are used to monitor and determine the presence of vessels at a berth on a daily basis to improve port management and make a port more efficient and competitive. This paper presents an evaluation of wireless ultrasonic berth occupancy sensors by analyzing the accurate and inaccurate detection of berth occupancy and the efficiency of the sensors under different berth status conditions, highlighting the main causes of false detections. Results revealed that sensors' accuracy for berth status detection range from 35% to 92%. The most common causes of inaccurate berth occupancy detection are sea currents, inadequate sensor positioning, damage to the sensor, exceeding boat-to-sensor distance, ropes from adjoining berths, and surrounding vegetation.","PeriodicalId":202568,"journal":{"name":"2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133976298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Rinaldi, A. Flammini, M. Pasetti, A. Depari, Elia Mondini, E. Sisinni, P. Ferrari
{"title":"Using Bluetooth Mesh to Enable Coordinate Charge of Domestic Charging Station for Electric Vehicles: An Experimental Analysis","authors":"S. Rinaldi, A. Flammini, M. Pasetti, A. Depari, Elia Mondini, E. Sisinni, P. Ferrari","doi":"10.1109/ICECCME55909.2022.9988049","DOIUrl":"https://doi.org/10.1109/ICECCME55909.2022.9988049","url":null,"abstract":"Recent energy policies have favored the adoption of electric vehicles to replace internal combustion engines. However, the growing presence of electric vehicles causes Distribution System Operators (DSOs) to face ever-increasing challenges due to the ever-increasing demand for electricity for recharging electric vehicles. To address this issue, coordinated charging systems are becoming increasingly popular: a supervision system can control the amount of electricity supplied by a Charging Station (CS) for Electric Vehicle Supply (EV). Implementing this control scheme requires communication systems capable of allowing an appropriate exchange of information between all charging infrastructure's players. The goal of this research activity is to investigate the feasibility of using the recent Bluetooth Mesh protocol, which was developed for home automation applications, to allow information exchange between users, vehicles and supervisor with CS. When compared to traditional Bluetooth, the Mesh solution has the advantage of being infrastructure-less and optimized to reduce energy consumption (optimal for battery-powered systems). As a result, it represents a good compromise solution for allowing information exchange for the supervision of CS in domestic applications. The experimental characterization in laboratory revealed that the maximum end-to-end latency in a Bluetooth Mesh network (1 hop) is around 141 ms, which is completely compliant with application requirements.","PeriodicalId":202568,"journal":{"name":"2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134096424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Improved Performance for the DC-AC Converters Control System Based on Robust Controller and Reinforcement Learning Agent","authors":"M. Nicola, C. Nicola","doi":"10.1109/ICECCME55909.2022.9988458","DOIUrl":"https://doi.org/10.1109/ICECCME55909.2022.9988458","url":null,"abstract":"Analyzing the problem of connecting a microgrid to the main grid by means of a voltage source inverter while maintaining a steady voltage in case with variation of load in the form of balanced/unbalanced linear resistance or nonlinear resistance, this paper presents, based on robust systems theory, the synthesis of a robust controller that achieves the above-mentioned goal. A maj or role is played by the network filters, the weights associated with the extended robust system together with the chosen topology. A combined control system based on a robust controller and a Reinforcement Learning-Twin-Delayed-Deep-Deterministic-Policy-Gradient (RL- TD3) agent is presented to improve the control system performance of this DC-AC converter. The RL- TD3-type agent is trained, tested and validated, and after implementation in the control system it is able to provide correction signals for the robust control in order to achieve superior performance in terms of steady-state error, ripple and Total Harmonic Distortion (THD). The numerical simulations confirm the superiority of the DC-AC converter control system using the robust controller combined with RL- TD3 agent.","PeriodicalId":202568,"journal":{"name":"2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134382491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Measurement and Analysis of MPT Multipath Throughput in Wire Channels","authors":"N. A. Jabbar, G. Lencse","doi":"10.1109/ICECCME55909.2022.9987956","DOIUrl":"https://doi.org/10.1109/ICECCME55909.2022.9987956","url":null,"abstract":"There is a significant growth in the use of the current intelligent and portable devices such as smartphones, laptops, and tablets that result in several network interfaces and various potential paths for communication. However, the mechanism used today via the Internet uses only one path for a communication session. This paper presents multipath throughput tests for the MPT network layer multipath communication library, a novel and promising solution for real-time transmission based on GRE-in-UDP encapsulation that provides an IPv4 or IPv6 tunneling (logical interface). We investigate the efficiency of channel capacity aggregation of MPT in dealing with physical paths via wired channels and test the cases when the physical paths have the same speed or radically different speeds.","PeriodicalId":202568,"journal":{"name":"2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134393031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}