Pub Date : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179514
S. Manoharan, Wei-Yu Chiu, Chih-Yuan Yu
This paper examines a leader selection problem of a multirobot leader-follower system in maze-like environments. Behavior-based control and a repulsive force method are applied to the leader and follower robots navigating the environments; a Q-learning algorithm combined with a fuzzy-based state approximation is developed to automatically assign a leader when robots are stranded; a cross-entropy exploration storing algorithm is proposed to exploit the information learned. Numerical analyses illustrate the effectiveness of the proposed leader selection approach based on reinforcement learning: the multirobot system can dynamically select a leader and navigate maze-like environments of interest to reach the destination. Index Terms—Reinforcement learning, Q-learning, mobile robot, multirobot system, maze, behavior based model, repulsive force method, fuzzy inference system.
{"title":"Dynamic Leader Selection of a Multirobot System in Multiple Maze-like Environments Using Reinforcement Learning","authors":"S. Manoharan, Wei-Yu Chiu, Chih-Yuan Yu","doi":"10.1109/ICASI57738.2023.10179514","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179514","url":null,"abstract":"This paper examines a leader selection problem of a multirobot leader-follower system in maze-like environments. Behavior-based control and a repulsive force method are applied to the leader and follower robots navigating the environments; a Q-learning algorithm combined with a fuzzy-based state approximation is developed to automatically assign a leader when robots are stranded; a cross-entropy exploration storing algorithm is proposed to exploit the information learned. Numerical analyses illustrate the effectiveness of the proposed leader selection approach based on reinforcement learning: the multirobot system can dynamically select a leader and navigate maze-like environments of interest to reach the destination. Index Terms—Reinforcement learning, Q-learning, mobile robot, multirobot system, maze, behavior based model, repulsive force method, fuzzy inference system.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128073779","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 : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179501
Ya-Fen Chang, Chung-Yi Tsai, W. Tai
Recently, Wang et al. proposed a computationally transferable authenticated key agreement protocol for smart healthcare by adopting the certificateless public-key cryptography. They claimed that their protocol could ensure privacy, resist various attacks, and possess superior properties. After analyzing their protocol, we find that it suffers from some flaws. Firstly, user privacy is not ensured as claimed. Secondly, some statements are inaccurate or missing. Thirdly, it cannot resist DoS attack. In this paper, the details of how these flaws threaten Wang et al.’s protocol are shown.
{"title":"Comments on a Computation-Transferable Authenticated Key Agreement Protocol for Smart Healthcare","authors":"Ya-Fen Chang, Chung-Yi Tsai, W. Tai","doi":"10.1109/ICASI57738.2023.10179501","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179501","url":null,"abstract":"Recently, Wang et al. proposed a computationally transferable authenticated key agreement protocol for smart healthcare by adopting the certificateless public-key cryptography. They claimed that their protocol could ensure privacy, resist various attacks, and possess superior properties. After analyzing their protocol, we find that it suffers from some flaws. Firstly, user privacy is not ensured as claimed. Secondly, some statements are inaccurate or missing. Thirdly, it cannot resist DoS attack. In this paper, the details of how these flaws threaten Wang et al.’s protocol are shown.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133623374","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 : 2023-04-21DOI: 10.1109/icasi57738.2023.10179567
Jinjoo Song
With the advent of deep learning technology, the interest in artificial intelligence (AI) has been fast growing and many countries and institutions have devoted their energies into AI education with different levels from novice to expert. Especially, many Korean universities offer mandatory AI liberal art class to non-engineering major students since AI literacy, the ability to know, use, and evaluate AI fundamentals and applications, becomes an important skill. However, these students tend to be not motivated or interested in AI education because the contents of the AI liberal art class have no direct relation to their majors. To solve this problem, the curriculum of using various no-coding AI platforms was designed and implemented, such as Deep Dream Generator, Text Summarization Tool, Google Teachable Machine, and Orange3. The survey was performed after the three-month course to prove the effect of using AI platforms in AI literacy education.
{"title":"Using AI Platforms in AI Liberal Art Class","authors":"Jinjoo Song","doi":"10.1109/icasi57738.2023.10179567","DOIUrl":"https://doi.org/10.1109/icasi57738.2023.10179567","url":null,"abstract":"With the advent of deep learning technology, the interest in artificial intelligence (AI) has been fast growing and many countries and institutions have devoted their energies into AI education with different levels from novice to expert. Especially, many Korean universities offer mandatory AI liberal art class to non-engineering major students since AI literacy, the ability to know, use, and evaluate AI fundamentals and applications, becomes an important skill. However, these students tend to be not motivated or interested in AI education because the contents of the AI liberal art class have no direct relation to their majors. To solve this problem, the curriculum of using various no-coding AI platforms was designed and implemented, such as Deep Dream Generator, Text Summarization Tool, Google Teachable Machine, and Orange3. The survey was performed after the three-month course to prove the effect of using AI platforms in AI literacy education.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124630446","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}
Software-Defined Networking(SDN) is a new type of network architecture that enables network management flexibility. As the network’s scale grows, its complexity increases at the same time. Since a single SDN controller can no longer match the rising demand, multiple SDN controllers are one of the alternatives (Multi SDN Controller). Because a single SDN controller can no longer keep up with the surging demand, one approach is to deploy numerous SDN controllers (Multi SDN Controller). In light of the scalability challenges bring behind, this paper aims to propose a solution by using Virtualized Network Function (VNF) to deploy the SDN controller. This paper uses Open Source MANO (OSM) and Openstack to deploy Virtualized Network Function (VNF). ONOS will be installed on the VNF as the SDN Controller and then combine the SDN Controllers into a cluster. In this way, users can dynamically deploy the SDN controller based on system load to achieve high scalability, high flexibility and rapid deployment. Finally, the measurement tool Cbench can be used to verify the scalability and reliability.
SDN (Software-Defined Networking)是一种新型的网络架构，能够实现灵活的网络管理。随着网络规模的增长，其复杂性也随之增加。由于单个SDN控制器不能满足不断增长的需求，多个SDN控制器是替代方案之一(Multi SDN controller)。由于单个SDN控制器已经无法满足不断增长的需求，一种方法是部署多个SDN控制器(Multi SDN controller)。针对其带来的可扩展性挑战，本文旨在提出一种利用VNF(虚拟化网络功能)部署SDN控制器的解决方案。本文采用Open Source MANO (OSM)和Openstack部署虚拟化网络功能(VNF)。ONOS将作为SDN控制器安装在VNF上，然后将SDN控制器组合成一个集群。这样，用户就可以根据系统负载动态部署SDN控制器，实现高扩展性、高灵活性和快速部署。最后，利用测量工具Cbench验证了系统的可扩展性和可靠性。
{"title":"A Dynamic VNF Deployment to Avoid Controller Overload in SDN-Cluster","authors":"Ming-Hua Cheng, W. Hwang, Yan-Jing Wu, Yu-Ting Guo, Menq Chyun Chen","doi":"10.1109/ICASI57738.2023.10179536","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179536","url":null,"abstract":"Software-Defined Networking(SDN) is a new type of network architecture that enables network management flexibility. As the network’s scale grows, its complexity increases at the same time. Since a single SDN controller can no longer match the rising demand, multiple SDN controllers are one of the alternatives (Multi SDN Controller). Because a single SDN controller can no longer keep up with the surging demand, one approach is to deploy numerous SDN controllers (Multi SDN Controller). In light of the scalability challenges bring behind, this paper aims to propose a solution by using Virtualized Network Function (VNF) to deploy the SDN controller. This paper uses Open Source MANO (OSM) and Openstack to deploy Virtualized Network Function (VNF). ONOS will be installed on the VNF as the SDN Controller and then combine the SDN Controllers into a cluster. In this way, users can dynamically deploy the SDN controller based on system load to achieve high scalability, high flexibility and rapid deployment. Finally, the measurement tool Cbench can be used to verify the scalability and reliability.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121239249","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 : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179558
J. Liou, Zhi-Yu Lin, Zong-Xuan Hsieh
The study using semiconductor manufacturing process, special material deposition, microfabrication, MEMS micro-electromechanical, measurement and detection technology, wafer temperature sensor components are used in the medical field. Usually, DNA extracted from a specimen is amplified and detected by a DNA chip. This research is an inkjet chip designed to control the size of DNA droplets through the design of high frequency signals, including counters, data inputs, and amplifier signals. This wafer can have as many as 1000 or more micro-structured nozzles. Each nozzle corresponds to a heater.
{"title":"Quantitative controlled of DNA droplets size inkjet printhead","authors":"J. Liou, Zhi-Yu Lin, Zong-Xuan Hsieh","doi":"10.1109/ICASI57738.2023.10179558","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179558","url":null,"abstract":"The study using semiconductor manufacturing process, special material deposition, microfabrication, MEMS micro-electromechanical, measurement and detection technology, wafer temperature sensor components are used in the medical field. Usually, DNA extracted from a specimen is amplified and detected by a DNA chip. This research is an inkjet chip designed to control the size of DNA droplets through the design of high frequency signals, including counters, data inputs, and amplifier signals. This wafer can have as many as 1000 or more micro-structured nozzles. Each nozzle corresponds to a heater.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126840159","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 : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179601
Jieh-Ren Chang, Chao-Jen Wang, Zhong Wei, Chiu-Ju Lu, H. Lin
In recent years, many deep learning techniques have been widely applied in sports events. Therefore, the research based on the collection of big data and applied to the analysis of the overall playing tactics of table tennis is competitive. This study proposes a structure to support this idea, which includes the match video collection raw database, video processing, action classification machine learning model, knowledge database and big data analysis website. Under the above structure, this research focuses on using machine learning model to automatically classify the types of serve motions. The table tennis motion dataset is created by professional players. They cut and label the competition video to complete the database. Then, use these data to train a 3-dimension convolutional neural network (3D-CNN). This experiment selected three common types of serve motions to classify. After training the model, with the validation dataset, the accuracy can reach 89.5%. This result shows that machine learning models have sufficient accuracy to recognize motion categories in table tennis serve motions. Therefore, the proposed method will also be extended to all kinds of motion classification to accomplish efficient and accurate table tennis player competition record. Finally, hoping this model structure can be applied to the variety of sports.
{"title":"A Research Structure of Big Data Analysis and Application for Table Tennis Match Tactics Based on Computer Vision","authors":"Jieh-Ren Chang, Chao-Jen Wang, Zhong Wei, Chiu-Ju Lu, H. Lin","doi":"10.1109/ICASI57738.2023.10179601","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179601","url":null,"abstract":"In recent years, many deep learning techniques have been widely applied in sports events. Therefore, the research based on the collection of big data and applied to the analysis of the overall playing tactics of table tennis is competitive. This study proposes a structure to support this idea, which includes the match video collection raw database, video processing, action classification machine learning model, knowledge database and big data analysis website. Under the above structure, this research focuses on using machine learning model to automatically classify the types of serve motions. The table tennis motion dataset is created by professional players. They cut and label the competition video to complete the database. Then, use these data to train a 3-dimension convolutional neural network (3D-CNN). This experiment selected three common types of serve motions to classify. After training the model, with the validation dataset, the accuracy can reach 89.5%. This result shows that machine learning models have sufficient accuracy to recognize motion categories in table tennis serve motions. Therefore, the proposed method will also be extended to all kinds of motion classification to accomplish efficient and accurate table tennis player competition record. Finally, hoping this model structure can be applied to the variety of sports.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132376108","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 : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179572
Hung-Tse Chan, Yan-Wei Liao, Sin-Ye Jhong, S. Chien, K. Hua, Yung-Yao Chen
Skin care products should be tailored to suit different skin types. However, skin testing can be expensive and time-consuming, particularly for students or office workers who may need access to specialized equipment. In the present study, we developed a skin type detection system by using computer-vision and deep-learning techniques that can be easily accessed through a mobile phone application. Our system integrates with the TensorFlow Lite framework on the Android platform and therefore supports various hardware accelerations and easy model validation. TensorFlow Lite, an open-source library developed by Google, is a lightweight, cross-platform, machine-learning framework for mobile and Internet of Things devices. It also supports various hardware accelerations. Our experimental results reveal that the proposed method has an accuracy of 96% and is easy to use on mobile devices. This system provides a convenient and cost-effective means of identifying the skin type and selecting appropriate skin care products.
{"title":"A Skin Type Classification Method Using Mobile Device-Based Deep Learning Model","authors":"Hung-Tse Chan, Yan-Wei Liao, Sin-Ye Jhong, S. Chien, K. Hua, Yung-Yao Chen","doi":"10.1109/ICASI57738.2023.10179572","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179572","url":null,"abstract":"Skin care products should be tailored to suit different skin types. However, skin testing can be expensive and time-consuming, particularly for students or office workers who may need access to specialized equipment. In the present study, we developed a skin type detection system by using computer-vision and deep-learning techniques that can be easily accessed through a mobile phone application. Our system integrates with the TensorFlow Lite framework on the Android platform and therefore supports various hardware accelerations and easy model validation. TensorFlow Lite, an open-source library developed by Google, is a lightweight, cross-platform, machine-learning framework for mobile and Internet of Things devices. It also supports various hardware accelerations. Our experimental results reveal that the proposed method has an accuracy of 96% and is easy to use on mobile devices. This system provides a convenient and cost-effective means of identifying the skin type and selecting appropriate skin care products.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133153733","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 : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179551
Ching-Yun Tseng, Ju-Chin Chen, Yen-Liang Pan
Instead of the mass production industry in the past, over these decades, precision and automatic manufacturing have become more and more widely accepted in the production area. With highly variable productivity and flexibility, Flexible Manufacturing Systems (FMS) can decrease production costs and increase efficiency. Due to its resource sharing, unexpected system deadlock may occur in some situations. In research on system deadlock control, lots of existing literature use deadlock prevention as the primary control method, while it could block resources transporting and downscale the system reachability graph. This paper adopts a deadlock recovery policy as the direct control strategy based on control transition technology. This kind of control strategy and its benefit could be demonstrated through classical systems of simple sequential processes with resources (S3PR) nets and their Petri nets model.
{"title":"A Novel and Advantageous Recovery Solution for Deadlock Problem of Flexible Manufacturing Systems Based on Petri Nets Modeling Theory","authors":"Ching-Yun Tseng, Ju-Chin Chen, Yen-Liang Pan","doi":"10.1109/ICASI57738.2023.10179551","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179551","url":null,"abstract":"Instead of the mass production industry in the past, over these decades, precision and automatic manufacturing have become more and more widely accepted in the production area. With highly variable productivity and flexibility, Flexible Manufacturing Systems (FMS) can decrease production costs and increase efficiency. Due to its resource sharing, unexpected system deadlock may occur in some situations. In research on system deadlock control, lots of existing literature use deadlock prevention as the primary control method, while it could block resources transporting and downscale the system reachability graph. This paper adopts a deadlock recovery policy as the direct control strategy based on control transition technology. This kind of control strategy and its benefit could be demonstrated through classical systems of simple sequential processes with resources (S3PR) nets and their Petri nets model.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124313600","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 : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179575
Huan-Iu Liou, Kuo-Chan Huang
As deep learning emerges and achieves remarkable success in many application areas, this paper presents a deep learning model for stock price prediction based on Multi-Input LSTM (MI-LSTM). In addition to new neural network architecture, we also try to take advantage of human traders’ wisdom by including the values of some recognized technical indicators in the network input in addition to raw prices. Experimental results show that our model could achieve more than 10% loss reduction, promising in higher potential trading profits.
{"title":"A Deep Learning Model for Stock Price Prediction in Swing Trading","authors":"Huan-Iu Liou, Kuo-Chan Huang","doi":"10.1109/ICASI57738.2023.10179575","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179575","url":null,"abstract":"As deep learning emerges and achieves remarkable success in many application areas, this paper presents a deep learning model for stock price prediction based on Multi-Input LSTM (MI-LSTM). In addition to new neural network architecture, we also try to take advantage of human traders’ wisdom by including the values of some recognized technical indicators in the network input in addition to raw prices. Experimental results show that our model could achieve more than 10% loss reduction, promising in higher potential trading profits.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121325606","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 : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179547
J. Lin, Cheng-Jen Lin, Bo-Yu Cai, Wei-Zhe Huang
The purpose of this study is to optimize the process parameters for sheet metal pressing of automotive side panels. This research is mainly based on the mold design parameters, which are: (1) thickness of molding material, (2) rounded corner of punch; (3) gap between upper and lower dies, etc. optimization parameters. The deformation of the simulated value of the final stamping verification experiment is: measuring point A2.5486X0.2916mm, the actual measured deformation is 2mmX(−0.27714mm), and the error value is 11%. Measurement point B: The simulated deformation is 5.0986mmX (−0.27714mm), the actual measured deformation is 4.85mmX (−1.5mm), and the error value is 14%. These are all within the acceptable range of sheet metal forming, and relevant information can be provided Partner reference.
{"title":"Optimum Design of Metal Stamping Parameters for Automobile Side Cover","authors":"J. Lin, Cheng-Jen Lin, Bo-Yu Cai, Wei-Zhe Huang","doi":"10.1109/ICASI57738.2023.10179547","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179547","url":null,"abstract":"The purpose of this study is to optimize the process parameters for sheet metal pressing of automotive side panels. This research is mainly based on the mold design parameters, which are: (1) thickness of molding material, (2) rounded corner of punch; (3) gap between upper and lower dies, etc. optimization parameters. The deformation of the simulated value of the final stamping verification experiment is: measuring point A2.5486X0.2916mm, the actual measured deformation is 2mmX(−0.27714mm), and the error value is 11%. Measurement point B: The simulated deformation is 5.0986mmX (−0.27714mm), the actual measured deformation is 4.85mmX (−1.5mm), and the error value is 14%. These are all within the acceptable range of sheet metal forming, and relevant information can be provided Partner reference.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121332087","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：