Pub Date : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926844
Da Teng, Daoerji Fan, Fengshan Bai, Yuecai Pan
An end-to-end model for Traditional Mongolian online handwritten word recognition is proposed in this paper. According to the characteristics of input and output data, the proposed model consists of a bidirectional Long Short-Term Memory(LSTM) network and a Connectionist Temporal Classification(CTC) network. Bidirectional LSTM network is the core of the model, and the CTC network is added to LSTM network. The key step of this research is to switch from the LSTM network output to the conditional probability distribution on the label sequence through the CTC layer. Therefore, for each given input sequence, the model completes the recognition task by choosing the most possible label. In addition, There is not many researchs on online handwritten Mongolian recognition. Therefore, in this study, we will also focus on recognizing wrong labels, finding out the types of errors, and analyzing the possible causes of errors.
{"title":"End-to-End Model Based on Bidirectional LSTM and CTC for Online Handwritten Mongolian Word Recognition","authors":"Da Teng, Daoerji Fan, Fengshan Bai, Yuecai Pan","doi":"10.1109/ICIST55546.2022.9926844","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926844","url":null,"abstract":"An end-to-end model for Traditional Mongolian online handwritten word recognition is proposed in this paper. According to the characteristics of input and output data, the proposed model consists of a bidirectional Long Short-Term Memory(LSTM) network and a Connectionist Temporal Classification(CTC) network. Bidirectional LSTM network is the core of the model, and the CTC network is added to LSTM network. The key step of this research is to switch from the LSTM network output to the conditional probability distribution on the label sequence through the CTC layer. Therefore, for each given input sequence, the model completes the recognition task by choosing the most possible label. In addition, There is not many researchs on online handwritten Mongolian recognition. Therefore, in this study, we will also focus on recognizing wrong labels, finding out the types of errors, and analyzing the possible causes of errors.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128806630","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926887
Zhuo Liu, Yifei Sun, Xin Sun, Jie Yang, Yifei Cao
The studies on structural balance of signed works have received a great attention due to its capability to describe the potential cooperation and conflicts among entities. Structure balance theory studies the unbalanced relationships in signed networks. The computation of structural balance aims to search for the least unbalance degree of a signed network to transform an unbalanced network into balanced one with the least cost. In this study, under the weak definition of structural balance theory, a node influenced memetic algorithm, called NIMA, is proposed to minimize the objective function. There are three main parts in NIMA. Firstly, a neighbor node influence-based initialization operation is applied to create an initial population for speeding the convergence process. Secondly, a node degree-based genetic operation is employed as the global search method. Moreover, a multi-level greedy local search is adopted to approach the potential optimum effectively. Extensive experiments on 9 real-world signed networks demonstrate that the proposed NIMA performs more efficiently, compared to other classic algorithms, on computing the structural balance of signed networks.
{"title":"Computing Signed Networks Structural Balance via Node Influenced Memetic Algorithm","authors":"Zhuo Liu, Yifei Sun, Xin Sun, Jie Yang, Yifei Cao","doi":"10.1109/ICIST55546.2022.9926887","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926887","url":null,"abstract":"The studies on structural balance of signed works have received a great attention due to its capability to describe the potential cooperation and conflicts among entities. Structure balance theory studies the unbalanced relationships in signed networks. The computation of structural balance aims to search for the least unbalance degree of a signed network to transform an unbalanced network into balanced one with the least cost. In this study, under the weak definition of structural balance theory, a node influenced memetic algorithm, called NIMA, is proposed to minimize the objective function. There are three main parts in NIMA. Firstly, a neighbor node influence-based initialization operation is applied to create an initial population for speeding the convergence process. Secondly, a node degree-based genetic operation is employed as the global search method. Moreover, a multi-level greedy local search is adopted to approach the potential optimum effectively. Extensive experiments on 9 real-world signed networks demonstrate that the proposed NIMA performs more efficiently, compared to other classic algorithms, on computing the structural balance of signed networks.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126821370","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926771
Wenxue Wang, Qingxia Li, Wenhong Wei, Simin Yang
Multi-objective optimization algorithms have been applied to community detection in recent years, notwithstanding, there are still problems such as poor stability and low computational efficiency. In order to improve the accuracy and calculation efficiency of community delineation, this paper proposed a multi-objective optimization algorithm (PDMOGA). PDMOGA fuses individual similarity to design a new mutation strategy and adds a de-duplication step to improve the quality of the Pareto frontier. Experimental results show that the algorithm improves stability and accuracy of community delineation compared with GA-NET, MOGA-NET and MOEA/D-NET.
{"title":"Multi-objective Community Detection Algorithm based on the Adaptive Mutation Operator","authors":"Wenxue Wang, Qingxia Li, Wenhong Wei, Simin Yang","doi":"10.1109/ICIST55546.2022.9926771","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926771","url":null,"abstract":"Multi-objective optimization algorithms have been applied to community detection in recent years, notwithstanding, there are still problems such as poor stability and low computational efficiency. In order to improve the accuracy and calculation efficiency of community delineation, this paper proposed a multi-objective optimization algorithm (PDMOGA). PDMOGA fuses individual similarity to design a new mutation strategy and adds a de-duplication step to improve the quality of the Pareto frontier. Experimental results show that the algorithm improves stability and accuracy of community delineation compared with GA-NET, MOGA-NET and MOEA/D-NET.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130512463","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926832
Qi Chen, Guozhong Wang, Lin Wang, Yong Sun, Xuguo Jiao, Xiaowen Zhou, Wenchao Meng, Qinmin Yang
Due to the randomness and intermittency of wind speed, the complexity of wind turbine operating environment and its own structure, the maximum power point tracking (MPPT) control of wind turbines is still a hot topic for control communities. In this study, a MPPT torque controller is designed for variable-speed wind turbines (VSWT) based on the bounded uncertainty and disturbance estimator (UDE). First, the optimal rotor speed is calculated according to the relationship between the wind turbine's power coefficient and the tip speed ratio. Based on the dynamic model of VSWT, a torque controller based on UDE, which can eliminate the control deviation caused by the uncertainties and disturbances, is designed. However, traditional UDE control have integral phenomenon, which will affect the tracking performance and even causes the system to run out of control. To deal with this, a bounded UDE torque controller along with a time-varying constraint coefficient is developed. It can avoid the integral windup issue caused by the input torque of the VSWT exceeding the maximum boundary of the actuator, and achieve a more stable optimal speed tracking performance. Finally, the effectiveness of the proposed MPPT torque controller is verified through the FAST (Fatigue, Aerodynamics, Structures, and Turbulence) platform.
{"title":"Bounded UDE based MPPT Control for Wind Turbines","authors":"Qi Chen, Guozhong Wang, Lin Wang, Yong Sun, Xuguo Jiao, Xiaowen Zhou, Wenchao Meng, Qinmin Yang","doi":"10.1109/ICIST55546.2022.9926832","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926832","url":null,"abstract":"Due to the randomness and intermittency of wind speed, the complexity of wind turbine operating environment and its own structure, the maximum power point tracking (MPPT) control of wind turbines is still a hot topic for control communities. In this study, a MPPT torque controller is designed for variable-speed wind turbines (VSWT) based on the bounded uncertainty and disturbance estimator (UDE). First, the optimal rotor speed is calculated according to the relationship between the wind turbine's power coefficient and the tip speed ratio. Based on the dynamic model of VSWT, a torque controller based on UDE, which can eliminate the control deviation caused by the uncertainties and disturbances, is designed. However, traditional UDE control have integral phenomenon, which will affect the tracking performance and even causes the system to run out of control. To deal with this, a bounded UDE torque controller along with a time-varying constraint coefficient is developed. It can avoid the integral windup issue caused by the input torque of the VSWT exceeding the maximum boundary of the actuator, and achieve a more stable optimal speed tracking performance. Finally, the effectiveness of the proposed MPPT torque controller is verified through the FAST (Fatigue, Aerodynamics, Structures, and Turbulence) platform.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130613190","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926852
Jian Yong, Junhong Zhao, Ting Liu, Ting Lei, W. Deng, Peng Liu
This article focuses on the tracking synchronization of the coupled non-identical neural networks. A kind of D-type iterative learning control (ILC) is proposed and the control input of each agent is updated iteratively such that tracking synchronization can be achieved under a repetitive environment. In addition, by virtue of the contraction mapping principle, some sufficient criteria for guaranteeing the tracking synchronization are established under the structurally fixed signed digraph. Finally, a numerical example is provided to demonstrate the viability of the theoretical results.
{"title":"Tracking Synchronization of Coupled Non-identical Neural Networks Via Iterative Learning Control","authors":"Jian Yong, Junhong Zhao, Ting Liu, Ting Lei, W. Deng, Peng Liu","doi":"10.1109/ICIST55546.2022.9926852","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926852","url":null,"abstract":"This article focuses on the tracking synchronization of the coupled non-identical neural networks. A kind of D-type iterative learning control (ILC) is proposed and the control input of each agent is updated iteratively such that tracking synchronization can be achieved under a repetitive environment. In addition, by virtue of the contraction mapping principle, some sufficient criteria for guaranteeing the tracking synchronization are established under the structurally fixed signed digraph. Finally, a numerical example is provided to demonstrate the viability of the theoretical results.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133970645","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}
Due to the complexity and diversity of underwater environment, high-precision and fast target detection is a scientific problem in underwater acoustic information extraction, especially the underwater target detection of sonar images still has a technical bottleneck. With the development of intelligent detection technology, as the state of the art model, target detection model based on deep neural network adopts different scale feature extraction mechanism, which is easy to generate false alarm for important targets and difficult to overcome the contradiction between false detection and missed detection. The attention mechanism can fully learn the features of the target and improve the accuracy of target detection. Considering the characteristics of seabed exploration task and underwater target, we propose a deep convolution network based on dual channel attention mechanism (DCNet), This model can strengthen the features of the target of interest while weakening the irrelevant background noise information, so as to improve the detection accuracy of the target and enhance the detection ability of the underwater target. The experimental results show that the average accuracy of the dual channel attention mechanism can achieve higher accuracy than the original model, and is superior to other target detection models in accuracy and performance. This research has important practical significance for improving the task of underwater target detection of sonar images and has a wide range of engineering application prospects in the detection of underwater acoustic systems.
{"title":"Sonar Target Detection Based on a Dual Channel Attention Convolutional Network","authors":"Yang Liu, Ruiyi Wang, Kejing Cao, Jiu-Ling Wang, Zezhao Shi, Yadi Wang, Yingjie Zhou","doi":"10.1109/ICIST55546.2022.9926829","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926829","url":null,"abstract":"Due to the complexity and diversity of underwater environment, high-precision and fast target detection is a scientific problem in underwater acoustic information extraction, especially the underwater target detection of sonar images still has a technical bottleneck. With the development of intelligent detection technology, as the state of the art model, target detection model based on deep neural network adopts different scale feature extraction mechanism, which is easy to generate false alarm for important targets and difficult to overcome the contradiction between false detection and missed detection. The attention mechanism can fully learn the features of the target and improve the accuracy of target detection. Considering the characteristics of seabed exploration task and underwater target, we propose a deep convolution network based on dual channel attention mechanism (DCNet), This model can strengthen the features of the target of interest while weakening the irrelevant background noise information, so as to improve the detection accuracy of the target and enhance the detection ability of the underwater target. The experimental results show that the average accuracy of the dual channel attention mechanism can achieve higher accuracy than the original model, and is superior to other target detection models in accuracy and performance. This research has important practical significance for improving the task of underwater target detection of sonar images and has a wide range of engineering application prospects in the detection of underwater acoustic systems.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132715179","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926891
Man-Fai Leung, Hangjun Che, Chin-Hung Kwok, Lewis Chan
Because people with low vision have difficulty pur-chasing and taking the correct medicine and dosages on time, this paper presents a system with a Flask Server and Android application that assists low-vision people with using over-the-counter (OTC) medication correctly. The system is mainly divided into three parts: an Android application, a Flask server and a MongoDB database. The application provides a medication time reminder, medicine information retrieval and image capture for recognition functions. A server recognizes the medication package by combining optical character recognition (OCR) and an image classification convolutional neural network (CNN). A database is used to store and provide medicine information. The experimental results show that the recognition performance has up to 96.1% accuracy. Moreover, the approach is shown to be able to handle out-of-distribution images.
{"title":"A hybrid intelligent system for assisting low-vision people with over-the-counter medication","authors":"Man-Fai Leung, Hangjun Che, Chin-Hung Kwok, Lewis Chan","doi":"10.1109/ICIST55546.2022.9926891","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926891","url":null,"abstract":"Because people with low vision have difficulty pur-chasing and taking the correct medicine and dosages on time, this paper presents a system with a Flask Server and Android application that assists low-vision people with using over-the-counter (OTC) medication correctly. The system is mainly divided into three parts: an Android application, a Flask server and a MongoDB database. The application provides a medication time reminder, medicine information retrieval and image capture for recognition functions. A server recognizes the medication package by combining optical character recognition (OCR) and an image classification convolutional neural network (CNN). A database is used to store and provide medicine information. The experimental results show that the recognition performance has up to 96.1% accuracy. Moreover, the approach is shown to be able to handle out-of-distribution images.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114037181","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926885
Kunpeng Jiang, Huifang Guo, Kun Yang, Haipeng Qu, Miao Li, Liming Wang
It is called unsupervised learning that does not rely on any labeled value, and finds the relationship between samples by mining the intrinsic characteristics of samples. Clustering algorithm is a kind of unsupervised learning algorithm. Although many clustering algorithms have been studied in modern science and applied in many fields, it is their common problem that the quantity of clusters has to be specified. Based on EM algorithm, this paper proposes a cluster centers learning algorithm (CCL) which can self-adaptively calculate the quantity and parameters of clusters according to the characteristics of samples themselves. The algorithm tentatively fills the shortage of existing clustering algorithms. The paper proposes the elementary merger and splitting criteria. The criteria can determine whether a point is the cluster center according to the characteristics of samples. Based on the elementary criteria, the algorithm proposed by the paper can adapt to calculate the correct quantity of clusters and gives the corresponding clustering parameters. Monte Carlo simulation is used to evaluate the effectiveness of the proposed algorithm. The experimental results show that the algorithm proposed by the paper can start from an arbitrary given cluster center and calculates the cluster centers close to the actual cluster centers of the samples themselves, so as to complete the self-adaptive unsupervised clustering.
{"title":"An self-adaptive cluster centers learning algorithm based on expectation maximization algorithm","authors":"Kunpeng Jiang, Huifang Guo, Kun Yang, Haipeng Qu, Miao Li, Liming Wang","doi":"10.1109/ICIST55546.2022.9926885","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926885","url":null,"abstract":"It is called unsupervised learning that does not rely on any labeled value, and finds the relationship between samples by mining the intrinsic characteristics of samples. Clustering algorithm is a kind of unsupervised learning algorithm. Although many clustering algorithms have been studied in modern science and applied in many fields, it is their common problem that the quantity of clusters has to be specified. Based on EM algorithm, this paper proposes a cluster centers learning algorithm (CCL) which can self-adaptively calculate the quantity and parameters of clusters according to the characteristics of samples themselves. The algorithm tentatively fills the shortage of existing clustering algorithms. The paper proposes the elementary merger and splitting criteria. The criteria can determine whether a point is the cluster center according to the characteristics of samples. Based on the elementary criteria, the algorithm proposed by the paper can adapt to calculate the correct quantity of clusters and gives the corresponding clustering parameters. Monte Carlo simulation is used to evaluate the effectiveness of the proposed algorithm. The experimental results show that the algorithm proposed by the paper can start from an arbitrary given cluster center and calculates the cluster centers close to the actual cluster centers of the samples themselves, so as to complete the self-adaptive unsupervised clustering.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127103092","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926819
Tong Xiao, Guoliang Yu, Zhiyu Jin, Chunxue Ji, Longshan Wang, Fan Zhang
An improved RFID tag anti-collision algorithm based on ALOHA is proposed to aim at the tag conflict problem in the RFID technology system. By effectively grouping the tags to be identified and finding out the best response probability for each time slot of each group, the recognition time of the reader is shortened, and the tag conflict chance is effectively reduced. Proposes a system label estimation method, realizes the read-write system label automatic estimation and improves the system recognition label efficiency. Simulation results show that the algorithm proposed in this paper compared with the traditional dynamic frame time slot ALOHA algorithm, the throughput rate is significantly improved, the average consumption time slot number is significantly reduced, and the conflict probability is reduced by 7.3%, effectively reducing the occurrence of conflict in the process of multi-tag recognition, and at the same time improving the system operating efficiency.
{"title":"Improved ALOHA-based RFID Tag Anti-collision Algorithm","authors":"Tong Xiao, Guoliang Yu, Zhiyu Jin, Chunxue Ji, Longshan Wang, Fan Zhang","doi":"10.1109/ICIST55546.2022.9926819","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926819","url":null,"abstract":"An improved RFID tag anti-collision algorithm based on ALOHA is proposed to aim at the tag conflict problem in the RFID technology system. By effectively grouping the tags to be identified and finding out the best response probability for each time slot of each group, the recognition time of the reader is shortened, and the tag conflict chance is effectively reduced. Proposes a system label estimation method, realizes the read-write system label automatic estimation and improves the system recognition label efficiency. Simulation results show that the algorithm proposed in this paper compared with the traditional dynamic frame time slot ALOHA algorithm, the throughput rate is significantly improved, the average consumption time slot number is significantly reduced, and the conflict probability is reduced by 7.3%, effectively reducing the occurrence of conflict in the process of multi-tag recognition, and at the same time improving the system operating efficiency.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131320802","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926842
Pan Zhang, Jiulin Cheng, Wei Zhang, Xin Lu, Yuhao Chen
In order to improve the accuracy and efficiency of the baggage pick-up and placement process, the problem of bag-gage pick-up and placement trajectory planning of the airline bag-gage palletizing robot is studied. Taking the baggage palletizing experiment platform as the application scenario, the trajectory of the pick-up segment for accurately picking up the baggage with the pallet is planned. The 4-3-4 polynomial interpolation method is used to plan the trajectory of the placement segment, and MATLAB is used to simulate the trajectory. The simulation results show that the planned trajectory is smooth and continuous, there is no major impact during operation. Finally, the multi-ob-jective particle swarm optimization (MOPSO) algorithm is used to optimize the trajectory with the target of trajectory running time, luggage pallet motion impact and angular acceleration. Field experiments in the laboratory show that the actual trajectory of the robot is basically consistent with the planned trajectory. The optimized trajectory running time is less than 7 seconds, the trajectory running is stable. The angular acceleration distribution of each axis is relatively uniform, which can realize the accurate retrieval and stable placement of baggage, and effectively improve the accuracy and efficiency of baggage pick-up and placement.
{"title":"Research on trajectory planning of airline baggage handling robot","authors":"Pan Zhang, Jiulin Cheng, Wei Zhang, Xin Lu, Yuhao Chen","doi":"10.1109/ICIST55546.2022.9926842","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926842","url":null,"abstract":"In order to improve the accuracy and efficiency of the baggage pick-up and placement process, the problem of bag-gage pick-up and placement trajectory planning of the airline bag-gage palletizing robot is studied. Taking the baggage palletizing experiment platform as the application scenario, the trajectory of the pick-up segment for accurately picking up the baggage with the pallet is planned. The 4-3-4 polynomial interpolation method is used to plan the trajectory of the placement segment, and MATLAB is used to simulate the trajectory. The simulation results show that the planned trajectory is smooth and continuous, there is no major impact during operation. Finally, the multi-ob-jective particle swarm optimization (MOPSO) algorithm is used to optimize the trajectory with the target of trajectory running time, luggage pallet motion impact and angular acceleration. Field experiments in the laboratory show that the actual trajectory of the robot is basically consistent with the planned trajectory. The optimized trajectory running time is less than 7 seconds, the trajectory running is stable. The angular acceleration distribution of each axis is relatively uniform, which can realize the accurate retrieval and stable placement of baggage, and effectively improve the accuracy and efficiency of baggage pick-up and placement.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116525172","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：