In the fierce market competition, enterprises constantly evolve themselves according to market requirements to better survive and develop. This paper establishes a multi-agent enterprise model, decomposes the complex enterprise system into multiple Agent entities to form a multi-agent system (MAS), and jointly solves the overall goals of the system by multi-agents. Using genetic algorithms and learning classifiers, the concept of norm in organization semiotics was introduced. Then enterprise agents was objectively controlled and constrained by the norm based on the complex semantics of the specification. On this basis, a parallel, rule-based, enterprise intelligence was developed, which can be automatically updated with rules and reflects the subjective initiative of agents under the environment. Finally, a case study was carried out on the Swarm simulation platform. The simulation results show that the design of the enterprise agent intelligence provides support for selection of the dynamic behavior of the enterprise agent.
{"title":"Norm-based Enterprise Agent Intelligence Design","authors":"Caihua Gao, Jun Zhao","doi":"10.1145/3305275.3305276","DOIUrl":"https://doi.org/10.1145/3305275.3305276","url":null,"abstract":"In the fierce market competition, enterprises constantly evolve themselves according to market requirements to better survive and develop. This paper establishes a multi-agent enterprise model, decomposes the complex enterprise system into multiple Agent entities to form a multi-agent system (MAS), and jointly solves the overall goals of the system by multi-agents. Using genetic algorithms and learning classifiers, the concept of norm in organization semiotics was introduced. Then enterprise agents was objectively controlled and constrained by the norm based on the complex semantics of the specification. On this basis, a parallel, rule-based, enterprise intelligence was developed, which can be automatically updated with rules and reflects the subjective initiative of agents under the environment. Finally, a case study was carried out on the Swarm simulation platform. The simulation results show that the design of the enterprise agent intelligence provides support for selection of the dynamic behavior of the enterprise agent.","PeriodicalId":370976,"journal":{"name":"Proceedings of the International Symposium on Big Data and Artificial Intelligence","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127350104","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}
The hyperparameters tuning of machine learning has always been a difficult and time-consuming task in deep learning area. In many practical applications, the hyperparameter tuning directly affects the accuracy. Therefore, the tuning optimization of hyperparameters is an important topic. At present, hyperparameters can only be set manually based on experience, and use Violent Enumeration, Random Search or through Grid Search to try and error, lack of effective automatic search parameters. In this study, we proposed a machine learning hyperparameter fine tuning service on dynamic cloud resource allocation system, which leverages several mainstream hyperparameter tuning methods such as Hyperopt and Optunity. In the meanwhile, various tuning methods are measured and compared by example application in this work. Finally, we dedicated actual case - Heart Sounds, and then tested it. In order to verify that the system service can not only automate the task of tuning, but also break through the limitation of the number of adjustable parameters. Furthermore the proposed hyperparameter fine tune system makes optimization process more efficient.
{"title":"Machine Learning Hyperparameter Fine Tuning Service on Dynamic Cloud Resource Allocation System - taking Heart Sounds as an Example","authors":"Yu-Hsiang Peng, Chia-Chuan Chuang, Zhou-Jin Wu, Chia-Wei Chou, Hui-Shan Chen, Ting-Chia Chang, Yi-Lun Pan, Hsin-Tien Cheng, Chih-Chi Chung, Ken-Yu Lin","doi":"10.1145/3305275.3305280","DOIUrl":"https://doi.org/10.1145/3305275.3305280","url":null,"abstract":"The hyperparameters tuning of machine learning has always been a difficult and time-consuming task in deep learning area. In many practical applications, the hyperparameter tuning directly affects the accuracy. Therefore, the tuning optimization of hyperparameters is an important topic. At present, hyperparameters can only be set manually based on experience, and use Violent Enumeration, Random Search or through Grid Search to try and error, lack of effective automatic search parameters. In this study, we proposed a machine learning hyperparameter fine tuning service on dynamic cloud resource allocation system, which leverages several mainstream hyperparameter tuning methods such as Hyperopt and Optunity. In the meanwhile, various tuning methods are measured and compared by example application in this work. Finally, we dedicated actual case - Heart Sounds, and then tested it. In order to verify that the system service can not only automate the task of tuning, but also break through the limitation of the number of adjustable parameters. Furthermore the proposed hyperparameter fine tune system makes optimization process more efficient.","PeriodicalId":370976,"journal":{"name":"Proceedings of the International Symposium on Big Data and Artificial Intelligence","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122104081","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}
In order to realize the production of plastic sheet, a small rolling mill is designed according to the large metal rolling mill to roll the plastic products. Meanwhile, the rolling parts with different thickness need to be produced when rolling the products. Therefore, a movable design is required for therolling roll of the mill.
{"title":"Design of roller and roll gap adjustment mechanism for small mill","authors":"Haixiong Wang, Chengan Wang, Junli Wang","doi":"10.1145/3305275.3305300","DOIUrl":"https://doi.org/10.1145/3305275.3305300","url":null,"abstract":"In order to realize the production of plastic sheet, a small rolling mill is designed according to the large metal rolling mill to roll the plastic products. Meanwhile, the rolling parts with different thickness need to be produced when rolling the products. Therefore, a movable design is required for therolling roll of the mill.","PeriodicalId":370976,"journal":{"name":"Proceedings of the International Symposium on Big Data and Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130315171","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}
Using the structured text STL language for programmable logic controller (PLC), the implementation of Calman filter on PLC is studied. In this paper, two implementation methods are introduced in detail. The detailed implementation of the second methods is based on S7-1200PLC, and the algorithm is applied to the temperature detection experiment. SIMULINK model and simulation results were compared, show that the Kalman filter in PLC to a certain extent can be achieved, and can very good filtering PLC analog data acquisition module with all kinds of disturbance, increase in measurement accuracy from the enhanced control effect to test the ideal.
{"title":"Implementation of Kalman Filter in plc","authors":"Wenxuan Wang, Jinfeng Yao, Shengpeng Qiu","doi":"10.1145/3305275.3305324","DOIUrl":"https://doi.org/10.1145/3305275.3305324","url":null,"abstract":"Using the structured text STL language for programmable logic controller (PLC), the implementation of Calman filter on PLC is studied. In this paper, two implementation methods are introduced in detail. The detailed implementation of the second methods is based on S7-1200PLC, and the algorithm is applied to the temperature detection experiment. SIMULINK model and simulation results were compared, show that the Kalman filter in PLC to a certain extent can be achieved, and can very good filtering PLC analog data acquisition module with all kinds of disturbance, increase in measurement accuracy from the enhanced control effect to test the ideal.","PeriodicalId":370976,"journal":{"name":"Proceedings of the International Symposium on Big Data and Artificial Intelligence","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124424700","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}
The mechanical properties of the main hydraulic cylinder, slider, and piston rod of hydraulic impact the overall performance in hydraulic press slow compression process. In this paper, a three beam four-column hydraulic press was regarded as the research object, the working principle of hydraulic press and the stress characteristics of important components of hydraulic press was analyzed, the mechanics model was set up, and thus established the optimization scheme of slider and piston rod; the finite element model of the important components of the hydraulic press was set up by using ANSYS software. The results show that the maximum pressure of the main hydraulic cylinder is 36.0032 MPa in the maximum liquid stress value 25 MPa;when the piston rod and the slider work at the maximum nominal force of 1000KN, the maximum stress occurs at the joint, and the value is 55.4125MPa. After optimization, the maximum stress value is 48.9255MPa, which effectively reduces the risk of stress. This result provides the basis for the design and application of the hydraulic press.
{"title":"Research on Mechanical Characteristics and Optimization of Important Parts of Hydraulic Press Based on Finite Element in Slow Loading Condition","authors":"Jie-jun Luo, J. Qin, G. Qin","doi":"10.1145/3305275.3305310","DOIUrl":"https://doi.org/10.1145/3305275.3305310","url":null,"abstract":"The mechanical properties of the main hydraulic cylinder, slider, and piston rod of hydraulic impact the overall performance in hydraulic press slow compression process. In this paper, a three beam four-column hydraulic press was regarded as the research object, the working principle of hydraulic press and the stress characteristics of important components of hydraulic press was analyzed, the mechanics model was set up, and thus established the optimization scheme of slider and piston rod; the finite element model of the important components of the hydraulic press was set up by using ANSYS software. The results show that the maximum pressure of the main hydraulic cylinder is 36.0032 MPa in the maximum liquid stress value 25 MPa;when the piston rod and the slider work at the maximum nominal force of 1000KN, the maximum stress occurs at the joint, and the value is 55.4125MPa. After optimization, the maximum stress value is 48.9255MPa, which effectively reduces the risk of stress. This result provides the basis for the design and application of the hydraulic press.","PeriodicalId":370976,"journal":{"name":"Proceedings of the International Symposium on Big Data and Artificial Intelligence","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127803485","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}
The working conditions of different driving modes can affect the speed and acceleration of the handling part of the handling robot. In this paper, the cylindrical coordinate four-degree-of-freedom handling robot was taken as the research object, and the dynamic model was established by the Lagrangian equation for the handling robot. In this paper, three driving modes of the handling robot were set up, and the dynamics simulation analysis was carried out in the Adams simulation software. The speed and acceleration of the grabbing position under the three conditions of low speed, normal and critical speed were studied. The results shown that the speed of the hand end of the robot was proportional to the speed required under different working conditions. The acceleration was proportional to the normal and low speed conditions, but under the critical condition, the acceleration has a "W" type change instead of Linear change. This result provides an effective experimental basis for the subsequent optimization design of such robot transmission rods.
{"title":"Dynamic Simulation of Four-DOF Handling Robot under Different Driving Modes","authors":"Fang Jiang, J. Qin, Sheng Chen","doi":"10.1145/3305275.3305311","DOIUrl":"https://doi.org/10.1145/3305275.3305311","url":null,"abstract":"The working conditions of different driving modes can affect the speed and acceleration of the handling part of the handling robot. In this paper, the cylindrical coordinate four-degree-of-freedom handling robot was taken as the research object, and the dynamic model was established by the Lagrangian equation for the handling robot. In this paper, three driving modes of the handling robot were set up, and the dynamics simulation analysis was carried out in the Adams simulation software. The speed and acceleration of the grabbing position under the three conditions of low speed, normal and critical speed were studied. The results shown that the speed of the hand end of the robot was proportional to the speed required under different working conditions. The acceleration was proportional to the normal and low speed conditions, but under the critical condition, the acceleration has a \"W\" type change instead of Linear change. This result provides an effective experimental basis for the subsequent optimization design of such robot transmission rods.","PeriodicalId":370976,"journal":{"name":"Proceedings of the International Symposium on Big Data and Artificial Intelligence","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114341096","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}
For the stability problem of the active magnetic levitation ball, the application of the PID controller on the system is determined. Firstly, the linearized mathematical model of the active magnetic levitation ball system is established. Then the PID parameters are adjusted by the trial method. The influence of three PID parameters on the system is introduced, and a PID controller is designed for a set of actual systems. The performance is simulated and experimentally studied. The research results show that the active electromagnetic suspension ball system based on PID controller has high anti-interference performance and stability.
{"title":"PID controller for active magnetic levitation ball system","authors":"Yanying Qi, Z. Zhong, Yixin Liu","doi":"10.1145/3305275.3305337","DOIUrl":"https://doi.org/10.1145/3305275.3305337","url":null,"abstract":"For the stability problem of the active magnetic levitation ball, the application of the PID controller on the system is determined. Firstly, the linearized mathematical model of the active magnetic levitation ball system is established. Then the PID parameters are adjusted by the trial method. The influence of three PID parameters on the system is introduced, and a PID controller is designed for a set of actual systems. The performance is simulated and experimentally studied. The research results show that the active electromagnetic suspension ball system based on PID controller has high anti-interference performance and stability.","PeriodicalId":370976,"journal":{"name":"Proceedings of the International Symposium on Big Data and Artificial Intelligence","volume":"06 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127195156","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}
In this paper, the mechanism study of sugarcane leaf stripping method was proposed, and the stress analysis of sugarcane leaf stripping process was conducted. First peel leaf component alignment and experimental study on the screw is arranged in two ways, respectively, examines the ways for stripping leaves, along with the change of sugar cane blow force analysis of two kinds of stripping leaves brush the installation method of damage effect of sugarcane sprout, considering the spiral Angle is 15° can meet the requirements. Secondly, a single factor test was carried out according to the main factors affecting seed bud damage, and the significance of each factor was studied. Finally, a new type of stripping element is designed based on this. The optimal parameter combination is that the rotor speed of the stripping cylinder is 750r/min, the staggered depth of the blade element is 10cm, and the side deviation distance is 10mm.
{"title":"Mechanism study on the sugarcane seed peeling method","authors":"Yiwei Liu, Jingbo Cong, Z. Shen","doi":"10.1145/3305275.3305286","DOIUrl":"https://doi.org/10.1145/3305275.3305286","url":null,"abstract":"In this paper, the mechanism study of sugarcane leaf stripping method was proposed, and the stress analysis of sugarcane leaf stripping process was conducted. First peel leaf component alignment and experimental study on the screw is arranged in two ways, respectively, examines the ways for stripping leaves, along with the change of sugar cane blow force analysis of two kinds of stripping leaves brush the installation method of damage effect of sugarcane sprout, considering the spiral Angle is 15° can meet the requirements. Secondly, a single factor test was carried out according to the main factors affecting seed bud damage, and the significance of each factor was studied. Finally, a new type of stripping element is designed based on this. The optimal parameter combination is that the rotor speed of the stripping cylinder is 750r/min, the staggered depth of the blade element is 10cm, and the side deviation distance is 10mm.","PeriodicalId":370976,"journal":{"name":"Proceedings of the International Symposium on Big Data and Artificial Intelligence","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130708240","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}
Support Vector Machine (SVM) is a machine learning method based on statistical learning theory, solving the problems of classification and regression by means of optimization methods. The method can effectively solve the problem of small number of samples, nonlinearity and high dimensionality, and largely avoids the problems of "dimensionality disaster", "over-fitting" and local minimum caused by traditional statistical theory. However, there are still some problems, such as high complexity of the algorithm and difficulty in adapting to large-scale data. The article systematically introduces the theory of support vector machine, summarizes the common training algorithms of standard (traditional) support vector machine and their existing problems, the new learning models and algorithms developed on this basis. And verify the actual effect and scope of each support vector machine model through the application of transformer fault diagnosis.
{"title":"Research on Development and Application of Support Vector Machine - Transformer Fault Diagnosis","authors":"Ruifang Zhang, Yangxue Liu","doi":"10.1145/3305275.3305328","DOIUrl":"https://doi.org/10.1145/3305275.3305328","url":null,"abstract":"Support Vector Machine (SVM) is a machine learning method based on statistical learning theory, solving the problems of classification and regression by means of optimization methods. The method can effectively solve the problem of small number of samples, nonlinearity and high dimensionality, and largely avoids the problems of \"dimensionality disaster\", \"over-fitting\" and local minimum caused by traditional statistical theory. However, there are still some problems, such as high complexity of the algorithm and difficulty in adapting to large-scale data. The article systematically introduces the theory of support vector machine, summarizes the common training algorithms of standard (traditional) support vector machine and their existing problems, the new learning models and algorithms developed on this basis. And verify the actual effect and scope of each support vector machine model through the application of transformer fault diagnosis.","PeriodicalId":370976,"journal":{"name":"Proceedings of the International Symposium on Big Data and Artificial Intelligence","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122642526","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}
The parameters of the traditional wireless signal propagation model are generally obtained by fitting or directly based on experience, and are affected by factors such as complex environment and multipath effect, which makes the positioning accuracy is not high. In view of this, a new node location algorithm of Particle Swarm Optimization-Generalized Regression Neural Network (PSO-GRNN) was presented. The RSSI received at each reference point is taken as the input of the network, the position coordinates of which are used as the output of the network to construct the GRNN, training the neural network by PSO algorithm with linear decreasing inertia weight, and the best Spread is cycled, avoid interference from human factors when adjusting this parameter, finally the trained model using the forecast point positioning. Simulation verified by MATLAB and Zigbee experiments, compared with the non-optimized GRNN model and BP neural network model, this algorithm has higher positioning accuracy in node localization.
{"title":"Research on Node Location Algorithm of Zigbee Based on PSO-GRNN Neural Network","authors":"Ziming Zou, Fu‐mian Li, Xinxin Qiao","doi":"10.1145/3305275.3305345","DOIUrl":"https://doi.org/10.1145/3305275.3305345","url":null,"abstract":"The parameters of the traditional wireless signal propagation model are generally obtained by fitting or directly based on experience, and are affected by factors such as complex environment and multipath effect, which makes the positioning accuracy is not high. In view of this, a new node location algorithm of Particle Swarm Optimization-Generalized Regression Neural Network (PSO-GRNN) was presented. The RSSI received at each reference point is taken as the input of the network, the position coordinates of which are used as the output of the network to construct the GRNN, training the neural network by PSO algorithm with linear decreasing inertia weight, and the best Spread is cycled, avoid interference from human factors when adjusting this parameter, finally the trained model using the forecast point positioning. Simulation verified by MATLAB and Zigbee experiments, compared with the non-optimized GRNN model and BP neural network model, this algorithm has higher positioning accuracy in node localization.","PeriodicalId":370976,"journal":{"name":"Proceedings of the International Symposium on Big Data and Artificial Intelligence","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124153004","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：