Pub Date : 2021-03-10DOI: 10.1109/ICIT46573.2021.9453474
Jessica Breitegger, Christian Raffelsberger, Siddhartha S. Borkotoky, Ingomar Rogler, C. Bettstetter
We report on multi-month experiments of a LoRa network deployed in a chemical plant. Using measurement data of nodes distributed (i) inside a building and (ii) over multiple buildings, all sending to a gateway, we estimate the path loss and fading characteristics of the links. Although we operate the system in a harsh environment according to these measurements—with a path loss exponent up to 5.1 and Nakagami fading with m as low as 0.7—the packet loss rate is low for in-building links (2.5% on the average), demonstrating LoRa’s suitability for certain industrial applications.
{"title":"Long-Term LoRa Experiments in a Chemical Plant","authors":"Jessica Breitegger, Christian Raffelsberger, Siddhartha S. Borkotoky, Ingomar Rogler, C. Bettstetter","doi":"10.1109/ICIT46573.2021.9453474","DOIUrl":"https://doi.org/10.1109/ICIT46573.2021.9453474","url":null,"abstract":"We report on multi-month experiments of a LoRa network deployed in a chemical plant. Using measurement data of nodes distributed (i) inside a building and (ii) over multiple buildings, all sending to a gateway, we estimate the path loss and fading characteristics of the links. Although we operate the system in a harsh environment according to these measurements—with a path loss exponent up to 5.1 and Nakagami fading with m as low as 0.7—the packet loss rate is low for in-building links (2.5% on the average), demonstrating LoRa’s suitability for certain industrial applications.","PeriodicalId":193338,"journal":{"name":"2021 22nd IEEE International Conference on Industrial Technology (ICIT)","volume":"367 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125625194","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 : 2021-03-10DOI: 10.1109/ICIT46573.2021.9453693
Shima Khoshzaman, I. Hahn
Introducing the excellent advantages of using wide bandgap semiconductors such as gallium nitride (GaN) in the construction of the power devices has set a starting point for a new era in the history of power electronics. Replacing the silicon-based with GaN-based power devices promises a number of benefits. Higher power densities, switching speeds and temperature stabilities with lower on-state resistance, reduced conduction and switching losses and a reduction in the die size are some of the performance improvements that the GaN transistors offer. To show both the advantages and challenges regarding this new technology, the methodology for an eligible comparison between Si-based and GaN-based transistors has been explained. Experimental comparison has been performed between a 100 V commercially available enhancement mode GaN FET and two silicon-based MOSFETs, and the results are discussed in detail.
{"title":"A Performance Comparison of GaN FET and Silicon MOSFET","authors":"Shima Khoshzaman, I. Hahn","doi":"10.1109/ICIT46573.2021.9453693","DOIUrl":"https://doi.org/10.1109/ICIT46573.2021.9453693","url":null,"abstract":"Introducing the excellent advantages of using wide bandgap semiconductors such as gallium nitride (GaN) in the construction of the power devices has set a starting point for a new era in the history of power electronics. Replacing the silicon-based with GaN-based power devices promises a number of benefits. Higher power densities, switching speeds and temperature stabilities with lower on-state resistance, reduced conduction and switching losses and a reduction in the die size are some of the performance improvements that the GaN transistors offer. To show both the advantages and challenges regarding this new technology, the methodology for an eligible comparison between Si-based and GaN-based transistors has been explained. Experimental comparison has been performed between a 100 V commercially available enhancement mode GaN FET and two silicon-based MOSFETs, and the results are discussed in detail.","PeriodicalId":193338,"journal":{"name":"2021 22nd IEEE International Conference on Industrial Technology (ICIT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120854194","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 : 2021-03-10DOI: 10.1109/ICIT46573.2021.9453660
M. Babaie, M. Mehrasa, K. Al-haddad
This paper is dealing with designing an advanced Direct Power Control (DPC) technique for a grid-connected nine-level Packed E-Cell (PEC9) inverter through Finite Control Set Model Predictive Control (FCSMPC) and Single-phase Direct-Quadrature (s-d-q) frame. Generating a nine-level voltage waveform using minimum active and passive components count makes PEC9 a cost-effective compact multilevel converter in single-phase applications. FSMPC symmetrically stabilizes the nine-level voltage waveform and accurately synchronizes the inverter current with the grid voltage by applying direct control to the switching operation of PEC9 inverter. The phase and the amplitude of the reference current in the proposed DPC are adjusted regarding the desired level of active and reactive power through s-d-q frame. In order to address the FCSMPC weighting factors tuning difficulty, some new adaptive functions using the error value of the capacitors voltages and the inverter current are also proposed. The experiments and simulations approve that PEC9 accurately generates the desired amounts of active and reactive power with standard level of THD and dc voltage ripple.
{"title":"Direct Active and Reactive Power Control for Grid-Connected PEC9 Inverter Using Finite Control Set Model Predictive Method","authors":"M. Babaie, M. Mehrasa, K. Al-haddad","doi":"10.1109/ICIT46573.2021.9453660","DOIUrl":"https://doi.org/10.1109/ICIT46573.2021.9453660","url":null,"abstract":"This paper is dealing with designing an advanced Direct Power Control (DPC) technique for a grid-connected nine-level Packed E-Cell (PEC9) inverter through Finite Control Set Model Predictive Control (FCSMPC) and Single-phase Direct-Quadrature (s-d-q) frame. Generating a nine-level voltage waveform using minimum active and passive components count makes PEC9 a cost-effective compact multilevel converter in single-phase applications. FSMPC symmetrically stabilizes the nine-level voltage waveform and accurately synchronizes the inverter current with the grid voltage by applying direct control to the switching operation of PEC9 inverter. The phase and the amplitude of the reference current in the proposed DPC are adjusted regarding the desired level of active and reactive power through s-d-q frame. In order to address the FCSMPC weighting factors tuning difficulty, some new adaptive functions using the error value of the capacitors voltages and the inverter current are also proposed. The experiments and simulations approve that PEC9 accurately generates the desired amounts of active and reactive power with standard level of THD and dc voltage ripple.","PeriodicalId":193338,"journal":{"name":"2021 22nd IEEE International Conference on Industrial Technology (ICIT)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121037223","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 : 2021-03-10DOI: 10.1109/ICIT46573.2021.9453536
Taichi Shimura, R. Tasaki, Harumo Sasatake, Takahito Yamashita, M. Fujimoto
The occurrence of convex part on metal surface of the product during casting is unpreventable. The purpose of this research is to propose a robot manipulation algorithm with a feedback control system for automatic removal of convex parts, which consists of a tool tip reaction force and a position feedback control, instead of manual removal as done by craftsmen. Removal experiments are carried out to identify the appropriate value of each of the parameters used in the proposed feedback control system. It is shown that better removal time and high-quality surface can be achieved by applying the proposed feedback control in the removal process of convex parts. Besides, sufficient machining performance obtained from the removal processing experiment of convex part of different shape proves that the proposed method is effective on convex parts of unknown shape. In addition, the generality of this system is proven by applying desired reaction force as reference input to the proposed feedback controller s not only to S50C but also to several metal materials such as SUS303, ANP79 and C2801P.
{"title":"Flexible Tool Manipulation for High-Accuracy Removal Processing of Unknown Shape Convex parts","authors":"Taichi Shimura, R. Tasaki, Harumo Sasatake, Takahito Yamashita, M. Fujimoto","doi":"10.1109/ICIT46573.2021.9453536","DOIUrl":"https://doi.org/10.1109/ICIT46573.2021.9453536","url":null,"abstract":"The occurrence of convex part on metal surface of the product during casting is unpreventable. The purpose of this research is to propose a robot manipulation algorithm with a feedback control system for automatic removal of convex parts, which consists of a tool tip reaction force and a position feedback control, instead of manual removal as done by craftsmen. Removal experiments are carried out to identify the appropriate value of each of the parameters used in the proposed feedback control system. It is shown that better removal time and high-quality surface can be achieved by applying the proposed feedback control in the removal process of convex parts. Besides, sufficient machining performance obtained from the removal processing experiment of convex part of different shape proves that the proposed method is effective on convex parts of unknown shape. In addition, the generality of this system is proven by applying desired reaction force as reference input to the proposed feedback controller s not only to S50C but also to several metal materials such as SUS303, ANP79 and C2801P.","PeriodicalId":193338,"journal":{"name":"2021 22nd IEEE International Conference on Industrial Technology (ICIT)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122279470","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 : 2021-03-10DOI: 10.1109/ICIT46573.2021.9453658
P. Denzler, D. Ramsauer, W. Kastner
Accessing runtime information originated from Operational Technology (OT) communication protocols by Information Technology (IT) applications remains a challenging task. Middlewares and gateways could provide a possible solution to bridge this OT/IT gap. In this context, this paper examines the feasibility of interconnecting legacy OT protocols via different middlewares and gateways by presenting two simplified scenarios. Each scenario exemplifies a possible use-case by either mimicking bidirectional tunnelling or propagating (mirroring) of automation data. Both scenarios use OPC Unified Architecture (OPC UA) and Message Queuing Telemetry Transport (MQTT) and a respective gateway prototype. The paper concludes by outlining future research challenges by discussing the limitations of the selected scenarios related to configuration, deployment and scalability.
{"title":"Tunnelling and Mirroring Operational Technology Data with IP-based Middlewares","authors":"P. Denzler, D. Ramsauer, W. Kastner","doi":"10.1109/ICIT46573.2021.9453658","DOIUrl":"https://doi.org/10.1109/ICIT46573.2021.9453658","url":null,"abstract":"Accessing runtime information originated from Operational Technology (OT) communication protocols by Information Technology (IT) applications remains a challenging task. Middlewares and gateways could provide a possible solution to bridge this OT/IT gap. In this context, this paper examines the feasibility of interconnecting legacy OT protocols via different middlewares and gateways by presenting two simplified scenarios. Each scenario exemplifies a possible use-case by either mimicking bidirectional tunnelling or propagating (mirroring) of automation data. Both scenarios use OPC Unified Architecture (OPC UA) and Message Queuing Telemetry Transport (MQTT) and a respective gateway prototype. The paper concludes by outlining future research challenges by discussing the limitations of the selected scenarios related to configuration, deployment and scalability.","PeriodicalId":193338,"journal":{"name":"2021 22nd IEEE International Conference on Industrial Technology (ICIT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126657369","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 : 2021-03-10DOI: 10.1109/ICIT46573.2021.9453569
Gabriel R. Broday, G. Damm, W. Pasillas-Lépine, L. Lopes
Energy storage devices are frequently employed for dynamic voltage regulation in DC nano and microgrids. For that, the power electronic interface should allow fast and accurate control of the bidirectional power flow. This requires an appropriate set of power electronics topology and control strategy. This paper focuses on a novel 5-switch DC-DC converter capable of reversing the power flow direction without changing the current direction in the intermediate inductor. A tri-state buck-boost plus free-wheeling modulation scheme is discussed. One issue with conventional PI-type controllers designed for converter models linearized around a typical operating point is their performance deteriorates as the operating point changes. In such cases, advanced control methods based on non-linear control theory can be beneficial. This paper discusses an approach for the modelling and control by dynamic feedback linearization of a 5-switch bidirectional DC-DC converter. The performance is verified by means of simulation results.
{"title":"Modeling and dynamic feedback linearization of a 5-switch tri-state buck-boost bidirectional DC-DC converter","authors":"Gabriel R. Broday, G. Damm, W. Pasillas-Lépine, L. Lopes","doi":"10.1109/ICIT46573.2021.9453569","DOIUrl":"https://doi.org/10.1109/ICIT46573.2021.9453569","url":null,"abstract":"Energy storage devices are frequently employed for dynamic voltage regulation in DC nano and microgrids. For that, the power electronic interface should allow fast and accurate control of the bidirectional power flow. This requires an appropriate set of power electronics topology and control strategy. This paper focuses on a novel 5-switch DC-DC converter capable of reversing the power flow direction without changing the current direction in the intermediate inductor. A tri-state buck-boost plus free-wheeling modulation scheme is discussed. One issue with conventional PI-type controllers designed for converter models linearized around a typical operating point is their performance deteriorates as the operating point changes. In such cases, advanced control methods based on non-linear control theory can be beneficial. This paper discusses an approach for the modelling and control by dynamic feedback linearization of a 5-switch bidirectional DC-DC converter. The performance is verified by means of simulation results.","PeriodicalId":193338,"journal":{"name":"2021 22nd IEEE International Conference on Industrial Technology (ICIT)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124091823","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 : 2021-03-10DOI: 10.1109/ICIT46573.2021.9453654
Hongbo Ye, X. Chen, Yong Cui, Chao Lu, Jun Gu, Xiaobo Ling
Considering the inertia time-varying nature and its significance on frequency initial dynamics, it is meaningful to online real-time estimate available inertia with synchronous measurements. To avoiding the influence of neighboring connected systems on the inertia of specific concerned system, monitoring the system inertia is realized by estimating inertia of individual generator connected to it and aggregated them. Inertia estimation methods presented are swing equation based method with large disturbance measurements and system identification based method with ambient signals, which guarantee the accuracy and continuity of inertia monitoring respectively. The proposed generator inertia estimation system takes full advantage of effective information in PMU measurements, and achieves a useful input to adaptive protection and control application in a near-time way. The methods have been validated with the simulation of IEEE 39 bus system and PMU measurements in power grid in Shanghai, China.
{"title":"Generator Available Inertia Estimation Based on Various Disturbance Measurements of PMU","authors":"Hongbo Ye, X. Chen, Yong Cui, Chao Lu, Jun Gu, Xiaobo Ling","doi":"10.1109/ICIT46573.2021.9453654","DOIUrl":"https://doi.org/10.1109/ICIT46573.2021.9453654","url":null,"abstract":"Considering the inertia time-varying nature and its significance on frequency initial dynamics, it is meaningful to online real-time estimate available inertia with synchronous measurements. To avoiding the influence of neighboring connected systems on the inertia of specific concerned system, monitoring the system inertia is realized by estimating inertia of individual generator connected to it and aggregated them. Inertia estimation methods presented are swing equation based method with large disturbance measurements and system identification based method with ambient signals, which guarantee the accuracy and continuity of inertia monitoring respectively. The proposed generator inertia estimation system takes full advantage of effective information in PMU measurements, and achieves a useful input to adaptive protection and control application in a near-time way. The methods have been validated with the simulation of IEEE 39 bus system and PMU measurements in power grid in Shanghai, China.","PeriodicalId":193338,"journal":{"name":"2021 22nd IEEE International Conference on Industrial Technology (ICIT)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126604600","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 : 2021-03-10DOI: 10.1109/ICIT46573.2021.9453473
Z. Bakhshi, G. Rodríguez-Navas, Hans A. Hansson
Container-based architectures are widely used for cloud computing and can have an important role in the implementation of fog computing infrastructures. However, there are some crucial dependability aspects that must be addressed to make containerization suitable for critical fog applications, e.g., in automation and robotics. This paper discusses challenges in applying containerization at the fog layer, and focuses on one of those challenges: provision of fault-tolerant permanent storage. The paper also presents a container-based fog architecture utilizing so-called storage containers, which combine built-in fault-tolerance mechanisms of containers with a distributed consensus protocol to achieve data consistency.
{"title":"Fault-tolerant Permanent Storage for Container-based Fog Architectures","authors":"Z. Bakhshi, G. Rodríguez-Navas, Hans A. Hansson","doi":"10.1109/ICIT46573.2021.9453473","DOIUrl":"https://doi.org/10.1109/ICIT46573.2021.9453473","url":null,"abstract":"Container-based architectures are widely used for cloud computing and can have an important role in the implementation of fog computing infrastructures. However, there are some crucial dependability aspects that must be addressed to make containerization suitable for critical fog applications, e.g., in automation and robotics. This paper discusses challenges in applying containerization at the fog layer, and focuses on one of those challenges: provision of fault-tolerant permanent storage. The paper also presents a container-based fog architecture utilizing so-called storage containers, which combine built-in fault-tolerance mechanisms of containers with a distributed consensus protocol to achieve data consistency.","PeriodicalId":193338,"journal":{"name":"2021 22nd IEEE International Conference on Industrial Technology (ICIT)","volume":"181 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126880817","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 : 2021-03-10DOI: 10.1109/ICIT46573.2021.9453492
Anja Elser, A. Lechler
Automation of gravity die casting can be achieved by Numerical Controls (NC). However, NCs are not inherently capable to control every process, but rather have to be extended accordingly. In this paper, we show how a Numerical Control can be extended by a process model for the gravity die casting process. The extension enables either flow rates or machine axes positions to be passed to the NC. Then the NC interpolates those values and they are either fed directly to the machine axes or, when the casting process is running, processed further. We define some more functions for process safety. The implemented behavior is tested with dedicated tests and test software. First results confirm that the presented concept for model integration is valid.
{"title":"Implementation of a Model Based Numerical Control for the Gravity Die Casting Process","authors":"Anja Elser, A. Lechler","doi":"10.1109/ICIT46573.2021.9453492","DOIUrl":"https://doi.org/10.1109/ICIT46573.2021.9453492","url":null,"abstract":"Automation of gravity die casting can be achieved by Numerical Controls (NC). However, NCs are not inherently capable to control every process, but rather have to be extended accordingly. In this paper, we show how a Numerical Control can be extended by a process model for the gravity die casting process. The extension enables either flow rates or machine axes positions to be passed to the NC. Then the NC interpolates those values and they are either fed directly to the machine axes or, when the casting process is running, processed further. We define some more functions for process safety. The implemented behavior is tested with dedicated tests and test software. First results confirm that the presented concept for model integration is valid.","PeriodicalId":193338,"journal":{"name":"2021 22nd IEEE International Conference on Industrial Technology (ICIT)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131406738","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 : 2021-03-10DOI: 10.1109/ICIT46573.2021.9453509
Pinjie Lv, Xinyue Wang, Chengqi Xue
Icon is an important element in human-computer interaction, and icon style is the most intuitive visual expression of icon design. Aiming at the problem of material classification in the icon style design process, this paper proposes an icon style recognition method based on deep learning. This paper first established the icon style dataset, and then used Visual Geometry Group Network (VGGNet), AlexNet and self-built neural network for training. The results show that the accuracy of the trained icon style recognition model is up to 100%. In addition, convolved features were visualized for explaining the recognition progress. This method can help designers quickly collect and filter a large number of icons of the same type, sequentially improving and accelerating the icon design process.
图标是人机交互的重要元素，图标风格是图标设计最直观的视觉表达。针对图标样式设计过程中的材料分类问题，提出了一种基于深度学习的图标样式识别方法。本文首先建立了图标风格数据集，然后使用Visual Geometry Group Network (VGGNet)、AlexNet和自建神经网络进行训练。结果表明，所训练的图标样式识别模型的准确率达到100%。此外，将卷积特征可视化，以解释识别过程。这种方法可以帮助设计师快速收集和过滤大量相同类型的图标，从而逐步改进和加速图标设计过程。
{"title":"Research on Automatic Recognition Method of Icon Style","authors":"Pinjie Lv, Xinyue Wang, Chengqi Xue","doi":"10.1109/ICIT46573.2021.9453509","DOIUrl":"https://doi.org/10.1109/ICIT46573.2021.9453509","url":null,"abstract":"Icon is an important element in human-computer interaction, and icon style is the most intuitive visual expression of icon design. Aiming at the problem of material classification in the icon style design process, this paper proposes an icon style recognition method based on deep learning. This paper first established the icon style dataset, and then used Visual Geometry Group Network (VGGNet), AlexNet and self-built neural network for training. The results show that the accuracy of the trained icon style recognition model is up to 100%. In addition, convolved features were visualized for explaining the recognition progress. This method can help designers quickly collect and filter a large number of icons of the same type, sequentially improving and accelerating the icon design process.","PeriodicalId":193338,"journal":{"name":"2021 22nd IEEE International Conference on Industrial Technology (ICIT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132642904","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：