Pub Date : 2022-10-17DOI: 10.1109/IECON49645.2022.9968368
Ningyu Zhu, Wen-Fang Xie, Henghua Shen
In this paper, a novel adaptive sliding mode control scheme with RBF (radial basis function) neural network-based tuning method is proposed for the trajectory tracking of a 6-RSS (Revolute-Spherical-Spherical) parallel robot in Cartesian space. Parallel robot is a highly nonlinear system with closed-chain mechanisms, which poses the major challenges to the controller design. The robust sliding mode controller is developed to deal with system uncertainties such as modeling errors, frictions, and disturbances. With strong adaptation and learning ability, RBF neural network is adopted to identify the parallel robot dynamics, and then the adaptive self-tuning of the control gains in the controller is realized, which is more flexible than manual tuning method and can guarantee the desired results of the changing system. The stability of the controller has been validated using Lyapunov theorem. Simulation results demonstrate that the proposed controller can achieve better tracking performance than the sliding mode controller with fixed control gains.
{"title":"Adaptive Sliding Mode Control with RBF Neural Network-Based Tuning Method for Parallel Robot","authors":"Ningyu Zhu, Wen-Fang Xie, Henghua Shen","doi":"10.1109/IECON49645.2022.9968368","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9968368","url":null,"abstract":"In this paper, a novel adaptive sliding mode control scheme with RBF (radial basis function) neural network-based tuning method is proposed for the trajectory tracking of a 6-RSS (Revolute-Spherical-Spherical) parallel robot in Cartesian space. Parallel robot is a highly nonlinear system with closed-chain mechanisms, which poses the major challenges to the controller design. The robust sliding mode controller is developed to deal with system uncertainties such as modeling errors, frictions, and disturbances. With strong adaptation and learning ability, RBF neural network is adopted to identify the parallel robot dynamics, and then the adaptive self-tuning of the control gains in the controller is realized, which is more flexible than manual tuning method and can guarantee the desired results of the changing system. The stability of the controller has been validated using Lyapunov theorem. Simulation results demonstrate that the proposed controller can achieve better tracking performance than the sliding mode controller with fixed control gains.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125617202","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}
Pub Date : 2022-10-17DOI: 10.1109/IECON49645.2022.9968541
Jesus O. Santos-Sanchez, Mauricio A. Rojas-Casas, O. Sergiyenko, J. Rodríguez-Quiñonez, W. Flores-Fuentes, César A. Sepúlveda-Valdez, Ruben Alaniz-Plata, Vera V. Tyrsa, Paolo Mercorelli
The present work is dedicated to improvement of the energetic efficiency of the mobile robot performing its task of cross-terrain inspections. It was improved by optimization of charge/discharge dynamics in a pair "solar panel – battery". The irradiance intensity was enhanced by additional system design improvement, in order to extend the time of mission performance. The validity of proposed approach was proved in a computational experiment.
{"title":"Analysis of the construction of an autonomous robot to improve its energy efficiency when traveling through irregular terrain","authors":"Jesus O. Santos-Sanchez, Mauricio A. Rojas-Casas, O. Sergiyenko, J. Rodríguez-Quiñonez, W. Flores-Fuentes, César A. Sepúlveda-Valdez, Ruben Alaniz-Plata, Vera V. Tyrsa, Paolo Mercorelli","doi":"10.1109/IECON49645.2022.9968541","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9968541","url":null,"abstract":"The present work is dedicated to improvement of the energetic efficiency of the mobile robot performing its task of cross-terrain inspections. It was improved by optimization of charge/discharge dynamics in a pair \"solar panel – battery\". The irradiance intensity was enhanced by additional system design improvement, in order to extend the time of mission performance. The validity of proposed approach was proved in a computational experiment.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125716601","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}
Pub Date : 2022-10-17DOI: 10.1109/IECON49645.2022.9968711
J. Xiang, C. Jiang, Tianlu Ma, Xiaosheng Wang, Bo Luo, Li Fang
Wireless power transfer (WPT) is one of the global highlight techniques with the rapid development of electric vehicles (EV). Currently, inductive power transfer (IPT) for EV charging faces the efficiency problem caused by the low saturation flux in the ferrite core bars. The nanocrystalline ribbon core is an advisable choice for the features of a high saturation flux and low power loss. In this paper, a double-D pads coupler with nanocrystalline core enhanced and ferrite TDK PC40 core will be detailed analyzed and compared regarding the magnetic field flux density, the air flux leakage around the vehicle body, the power loss distribution, and the magnetic shielding for wireless EV charging.
{"title":"A Comparison of Advanced IPT Systems with Nanocrystalline and Ferrite Cores for Wireless EV Charging","authors":"J. Xiang, C. Jiang, Tianlu Ma, Xiaosheng Wang, Bo Luo, Li Fang","doi":"10.1109/IECON49645.2022.9968711","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9968711","url":null,"abstract":"Wireless power transfer (WPT) is one of the global highlight techniques with the rapid development of electric vehicles (EV). Currently, inductive power transfer (IPT) for EV charging faces the efficiency problem caused by the low saturation flux in the ferrite core bars. The nanocrystalline ribbon core is an advisable choice for the features of a high saturation flux and low power loss. In this paper, a double-D pads coupler with nanocrystalline core enhanced and ferrite TDK PC40 core will be detailed analyzed and compared regarding the magnetic field flux density, the air flux leakage around the vehicle body, the power loss distribution, and the magnetic shielding for wireless EV charging.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122011524","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}
Pub Date : 2022-10-17DOI: 10.1109/IECON49645.2022.9969048
Muhammad S. Tolba, M. Fanni, G. Nasser, S. Umezu, A. F. El-Bab
Temperature control is vital in micro-heaters used in medical devices such as the polymerase chain reaction (PCR). The primary goal is to achieve tight control and a high rate of heating for a portable, low-cost medical device. Even though the fact that several designs for micro-heaters have been proposed, uniform temperature distribution and the high-speed heating rate remain challenging for micro-heaters. This high speed is achieved by the reduction of the thermal mass. The most common methods for reducing thermal mass or heating time in a device are to establish a highly desired structural design and to select a better heating mechanism with a robust controller. Increasing the thermal mass improves temperature distribution on the heater surface but slows heat transfer. On the other hand, removing the thermal mass makes the controller struggle to provide a high-temperature uniformity distribution on the micro-heater surface. In this study, we provide a design of a cost-effective, high-speed, thin-film micro-heater based on the Joule heating technique. The CoventorWare software tool is used to simulate the temperature distribution of the micro-heater. The heater provides a well-distributed temperature on the heated surface. When a DC voltage of 24 V was applied for 250 s, a maximum temperature of 272 °C was obtained. Besides, the heater’s average heating rate is 15 °C/s. The heater is then fabricated with the micro-electromechanical systems (MEMS) technology on a silicon substrate. The transfer function of the heating system is computed. Two controllers are designed to control the temperature of the micro-heater and improve its response. The classical proportional–integral–derivative (PID) controller produces rise time (Tr) of 21.9 s, settling time (Ts) of 73.3 s, and a maximum overshoot (Mp) of 4.8 %. Then by applying a fractional-order proportional-integral-derivative (FOPID) controller, a great enhancement in the system performance is observed, the controller is faster than the normal PID controller, the rise time (Tr) reaches 16.4 s and the settling time (Ts) reaches 23.6 s. It also reduces the maximum overshoot (Mp) to 0.32 %.
{"title":"Design, Fabrication, and Control of Micro-Heater Based on Joule Effect for Low-Cost Medical Device","authors":"Muhammad S. Tolba, M. Fanni, G. Nasser, S. Umezu, A. F. El-Bab","doi":"10.1109/IECON49645.2022.9969048","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9969048","url":null,"abstract":"Temperature control is vital in micro-heaters used in medical devices such as the polymerase chain reaction (PCR). The primary goal is to achieve tight control and a high rate of heating for a portable, low-cost medical device. Even though the fact that several designs for micro-heaters have been proposed, uniform temperature distribution and the high-speed heating rate remain challenging for micro-heaters. This high speed is achieved by the reduction of the thermal mass. The most common methods for reducing thermal mass or heating time in a device are to establish a highly desired structural design and to select a better heating mechanism with a robust controller. Increasing the thermal mass improves temperature distribution on the heater surface but slows heat transfer. On the other hand, removing the thermal mass makes the controller struggle to provide a high-temperature uniformity distribution on the micro-heater surface. In this study, we provide a design of a cost-effective, high-speed, thin-film micro-heater based on the Joule heating technique. The CoventorWare software tool is used to simulate the temperature distribution of the micro-heater. The heater provides a well-distributed temperature on the heated surface. When a DC voltage of 24 V was applied for 250 s, a maximum temperature of 272 °C was obtained. Besides, the heater’s average heating rate is 15 °C/s. The heater is then fabricated with the micro-electromechanical systems (MEMS) technology on a silicon substrate. The transfer function of the heating system is computed. Two controllers are designed to control the temperature of the micro-heater and improve its response. The classical proportional–integral–derivative (PID) controller produces rise time (Tr) of 21.9 s, settling time (Ts) of 73.3 s, and a maximum overshoot (Mp) of 4.8 %. Then by applying a fractional-order proportional-integral-derivative (FOPID) controller, a great enhancement in the system performance is observed, the controller is faster than the normal PID controller, the rise time (Tr) reaches 16.4 s and the settling time (Ts) reaches 23.6 s. It also reduces the maximum overshoot (Mp) to 0.32 %.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122240524","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}
Pub Date : 2022-10-17DOI: 10.1109/IECON49645.2022.9968856
P. Priya, Annoy Kumar Das, S. Anand, B. G. Fernandes
Medium-frequency (MF) transformer is employed in several DC-DC converters, where its leakage inductance plays a crucial role in the converter operation, such as creating resonance in soft switching converter, limiting current in dual active bridge converter, etc. Therefore, it is paramount to accurately estimate the leakage inductance during the design stage. In the literature, leakage inductance calculation at medium frequency is analyzed considering the effects of eddy currents, winding arrangement, etc., but the effect of winding material remains unexplored. This is analyzed by calculating the magnetomotive force (MMF) distribution in the winding volume for different conductor materials. This helps deduce the energy stored in the winding and thereby formulate the effective leakage inductance analytically. Moreover, conductor materials with different resistivities exhibit different temperature coefficients. Therefore, this study also investigates the effect of temperature rise in the windings on the effective leakage inductance due to the change in the wire resistivity. Finally, a comparative analysis between Al and Cu foil designs of a 16 kVA, 1.5/20 kV, 20 kHz transformer is presented to summarize the relative benefits of using Al foils for high power MF transformer designs. The analytical model is verified using 2D FEM analysis. This study shows that higher resistivity material leads to higher leakage energy stored in the conductor volume; consequently this helps achieving higher leakage inductance. As the material resistivity increases with temperature, this also leads to higher leakage inductance.
{"title":"Effect of Material Resistivity and Temperature on Leakage Inductance of Medium Frequency Transformers Made of Al and Cu Foils","authors":"P. Priya, Annoy Kumar Das, S. Anand, B. G. Fernandes","doi":"10.1109/IECON49645.2022.9968856","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9968856","url":null,"abstract":"Medium-frequency (MF) transformer is employed in several DC-DC converters, where its leakage inductance plays a crucial role in the converter operation, such as creating resonance in soft switching converter, limiting current in dual active bridge converter, etc. Therefore, it is paramount to accurately estimate the leakage inductance during the design stage. In the literature, leakage inductance calculation at medium frequency is analyzed considering the effects of eddy currents, winding arrangement, etc., but the effect of winding material remains unexplored. This is analyzed by calculating the magnetomotive force (MMF) distribution in the winding volume for different conductor materials. This helps deduce the energy stored in the winding and thereby formulate the effective leakage inductance analytically. Moreover, conductor materials with different resistivities exhibit different temperature coefficients. Therefore, this study also investigates the effect of temperature rise in the windings on the effective leakage inductance due to the change in the wire resistivity. Finally, a comparative analysis between Al and Cu foil designs of a 16 kVA, 1.5/20 kV, 20 kHz transformer is presented to summarize the relative benefits of using Al foils for high power MF transformer designs. The analytical model is verified using 2D FEM analysis. This study shows that higher resistivity material leads to higher leakage energy stored in the conductor volume; consequently this helps achieving higher leakage inductance. As the material resistivity increases with temperature, this also leads to higher leakage inductance.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115830004","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}
Pub Date : 2022-10-17DOI: 10.1109/IECON49645.2022.9968357
Nga T. Dinh, Øystein Haugen
Wireless power transfer (WPT) to charge a wireless device (WD) using radio frequency (RF) has been a promising power supply solution in wireless networks. It should extend network lifetime and guarantee network sustainability and reliability. Charging from one energy source (ES) shared by several WDs makes the scheduling algorithm most important. This paper considers a directional ES that has significant scheduling impacts relative to the more commonly studied omnidirectional ES. The directional energy source overcomes the restrictions of broadcast energy by concentrating the power on the intended sectors and thus significantly improving energy efficiency. We propose a charging scheduling algorithm to maximize the network lifetime under several network conditions. The proposed algorithm first determines the charging duration for all WDs in a given sector. The algorithm then determines the transmit power from ES to each WD in the sector. The performance of the proposed algorithm is compared with that of a well-established benchmark scheme. The extensive simulation results demonstrate the effectiveness of our proposed algorithm.
{"title":"Charging Scheduling Algorithm for Wireless-Powered Communication Networks","authors":"Nga T. Dinh, Øystein Haugen","doi":"10.1109/IECON49645.2022.9968357","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9968357","url":null,"abstract":"Wireless power transfer (WPT) to charge a wireless device (WD) using radio frequency (RF) has been a promising power supply solution in wireless networks. It should extend network lifetime and guarantee network sustainability and reliability. Charging from one energy source (ES) shared by several WDs makes the scheduling algorithm most important. This paper considers a directional ES that has significant scheduling impacts relative to the more commonly studied omnidirectional ES. The directional energy source overcomes the restrictions of broadcast energy by concentrating the power on the intended sectors and thus significantly improving energy efficiency. We propose a charging scheduling algorithm to maximize the network lifetime under several network conditions. The proposed algorithm first determines the charging duration for all WDs in a given sector. The algorithm then determines the transmit power from ES to each WD in the sector. The performance of the proposed algorithm is compared with that of a well-established benchmark scheme. The extensive simulation results demonstrate the effectiveness of our proposed algorithm.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"306 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115874090","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}
Pub Date : 2022-10-17DOI: 10.1109/IECON49645.2022.9968848
Shinji Tanimoto, S. Muramatsu, K. Inagaki, D. Chugo, S. Yokota, H. Hashimoto
In recent years, development of robots that can run independently in the same space as humans has been progressing. Most of the current navigation methods for autonomous robots use geometric information. While this method is easy to implement, it has some drawbacks, such as the need for accurate self-positioning and vulnerability to errors in sensor information. Humans do not have an exact self-position, but rather, they recognize an approximate location based on surrounding information and envision the path to the goal to reach the destination. Therefore, this study examines a navigation method that plans a route based on an abstract map, such as a hand-drawn map, and then travels independently to the destination.
{"title":"Mobile robot's navigation based on road segmentation and route evaluation.","authors":"Shinji Tanimoto, S. Muramatsu, K. Inagaki, D. Chugo, S. Yokota, H. Hashimoto","doi":"10.1109/IECON49645.2022.9968848","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9968848","url":null,"abstract":"In recent years, development of robots that can run independently in the same space as humans has been progressing. Most of the current navigation methods for autonomous robots use geometric information. While this method is easy to implement, it has some drawbacks, such as the need for accurate self-positioning and vulnerability to errors in sensor information. Humans do not have an exact self-position, but rather, they recognize an approximate location based on surrounding information and envision the path to the goal to reach the destination. Therefore, this study examines a navigation method that plans a route based on an abstract map, such as a hand-drawn map, and then travels independently to the destination.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"17 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131451377","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}
Pub Date : 2022-10-17DOI: 10.1109/IECON49645.2022.9968828
C. J. V. Filho, F. Scalcon, R. Vieira, B. Nahid-Mobarakeh
This paper presents a high frequency linear model for low-speed sensorless control of interior permanent magnet synchronous motor (IPMSM) drives. The proposed model uses a β-axis high frequency signal injection in order to model a new high frequency flux variable, which has similar properties to the standard electromotive force (EMF) used for high-speed sensorless control. Through the proposed model, the well established observer techniques from the literature can be used for rotor position and speed estimation. Thus, the low-speed sensorless scheme can be designed in similar form as the high-speed EMF based methods. Here, position and speed estimation are performed by an adaptive full-order observer, which is designed through a pole placement method and its stability constraints are investigated. Simulation results validate the proposed high frequency linear model and adaptive observer design method under sensorless vector control.
{"title":"A New β-axis Based High-Frequency Signal Injection Model for Low-Speed Sensorless IPMSM Drives","authors":"C. J. V. Filho, F. Scalcon, R. Vieira, B. Nahid-Mobarakeh","doi":"10.1109/IECON49645.2022.9968828","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9968828","url":null,"abstract":"This paper presents a high frequency linear model for low-speed sensorless control of interior permanent magnet synchronous motor (IPMSM) drives. The proposed model uses a β-axis high frequency signal injection in order to model a new high frequency flux variable, which has similar properties to the standard electromotive force (EMF) used for high-speed sensorless control. Through the proposed model, the well established observer techniques from the literature can be used for rotor position and speed estimation. Thus, the low-speed sensorless scheme can be designed in similar form as the high-speed EMF based methods. Here, position and speed estimation are performed by an adaptive full-order observer, which is designed through a pole placement method and its stability constraints are investigated. Simulation results validate the proposed high frequency linear model and adaptive observer design method under sensorless vector control.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132192591","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}
Pub Date : 2022-10-17DOI: 10.1109/IECON49645.2022.9968904
M. Bucolo, A. Buscarino, L. Fortuna, Gabriele Puglisi
Neural networks based on back-propagation learning algorithms and gradient descent algorithms are the first and the easiest tools developed for machine learning. They are still widespread nowadays, so much so by exploiting a huge number of different coding languages, between which MatLab, Python or Java, we have the possibility of using these training tools. But as highlighted in the past, these traditional neural networks suffer from their slow convergence rate. Aim of this paper is to revisit an algorithm to improve the speed of the learning phase, by exploiting the power of parallel computing to train a suitable number of auxiliary neural networks which work concurrently with the principal network. The implementation of the proposed algorithm in MatLab is shown in order to make evident the main difference with the traditional learning algorithms. Several examples, related to modeling of technological datasets from industrial environment, confirm the suitability of the proposed procedure.
{"title":"Learning-on-learning approach for modeling","authors":"M. Bucolo, A. Buscarino, L. Fortuna, Gabriele Puglisi","doi":"10.1109/IECON49645.2022.9968904","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9968904","url":null,"abstract":"Neural networks based on back-propagation learning algorithms and gradient descent algorithms are the first and the easiest tools developed for machine learning. They are still widespread nowadays, so much so by exploiting a huge number of different coding languages, between which MatLab, Python or Java, we have the possibility of using these training tools. But as highlighted in the past, these traditional neural networks suffer from their slow convergence rate. Aim of this paper is to revisit an algorithm to improve the speed of the learning phase, by exploiting the power of parallel computing to train a suitable number of auxiliary neural networks which work concurrently with the principal network. The implementation of the proposed algorithm in MatLab is shown in order to make evident the main difference with the traditional learning algorithms. Several examples, related to modeling of technological datasets from industrial environment, confirm the suitability of the proposed procedure.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130424806","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}
Pub Date : 2022-10-17DOI: 10.1109/IECON49645.2022.9969120
Fiorella Sibona, Pangcheng David Cen Cheng, M. Indri
Human-robot collaborative applications are generally based on some kind of co-working of the human operator and the robot in the execution of a given task. A disruptive change in the collaborative modalities would be given by the capability of the robot to anticipate how it could be of help for the operator. In case of an Autonomous Mobile Robot (AMR), this would imply not only a safe navigation in presence of a human operator, but the automatic adaptation of its motion to the specific operation carried out by the operator. This paper investigates the possibility of achieving operation recognition by monitoring the human motion on a 2D map and classifying his/her path on the map, taken as an image data sample. Deep learning state-of-the-art libraries and architectures are exploited with the aim of making the robotic system aware of the ongoing process. The reported results, relative to a small training dataset, are nonetheless promising.
{"title":"How to improve human-robot collaborative applications through operation recognition based on human 2D motion","authors":"Fiorella Sibona, Pangcheng David Cen Cheng, M. Indri","doi":"10.1109/IECON49645.2022.9969120","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9969120","url":null,"abstract":"Human-robot collaborative applications are generally based on some kind of co-working of the human operator and the robot in the execution of a given task. A disruptive change in the collaborative modalities would be given by the capability of the robot to anticipate how it could be of help for the operator. In case of an Autonomous Mobile Robot (AMR), this would imply not only a safe navigation in presence of a human operator, but the automatic adaptation of its motion to the specific operation carried out by the operator. This paper investigates the possibility of achieving operation recognition by monitoring the human motion on a 2D map and classifying his/her path on the map, taken as an image data sample. Deep learning state-of-the-art libraries and architectures are exploited with the aim of making the robotic system aware of the ongoing process. The reported results, relative to a small training dataset, are nonetheless promising.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130431697","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：