Yuanyuan Li, Haibo Zhang, Lei Cai, Junping Ren, Shengting Xiang
The current high-resolution remote sensing image road extraction methods mostly use an end-to-end network model to predict road, which is helpful to the global feature expression of road extraction, but ignores local feature express. Therefore, in order to better balance the global information and local information extracted by the road, in this paper, we use SEResNext to extract rich semantic information from low to high channel to construct the encoder, and use the global mixed feature module (GMFM) to upsample and recover to the original image size to construct the decoder, in which dense skip connections promote semantic information fusion. In addition, we use polynomial fitting and morphological-based methods to repair road breakpoints. Experiments show that compared with similar networks, the accuracy and completeness of road extraction in this paper have been significantly improved, the precision achieves 88.765%, the recall is 84.224%, and the achieves 86.435%.
{"title":"Remote sensing road segmentation and breakpoint repair based on deep learning","authors":"Yuanyuan Li, Haibo Zhang, Lei Cai, Junping Ren, Shengting Xiang","doi":"10.1145/3547578.3547609","DOIUrl":"https://doi.org/10.1145/3547578.3547609","url":null,"abstract":"The current high-resolution remote sensing image road extraction methods mostly use an end-to-end network model to predict road, which is helpful to the global feature expression of road extraction, but ignores local feature express. Therefore, in order to better balance the global information and local information extracted by the road, in this paper, we use SEResNext to extract rich semantic information from low to high channel to construct the encoder, and use the global mixed feature module (GMFM) to upsample and recover to the original image size to construct the decoder, in which dense skip connections promote semantic information fusion. In addition, we use polynomial fitting and morphological-based methods to repair road breakpoints. Experiments show that compared with similar networks, the accuracy and completeness of road extraction in this paper have been significantly improved, the precision achieves 88.765%, the recall is 84.224%, and the achieves 86.435%.","PeriodicalId":381600,"journal":{"name":"Proceedings of the 14th International Conference on Computer Modeling and Simulation","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121184015","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}
Formation maintenance control is one of the important methods to maintain the flight stability of multiple UAVs, and the inevitable wind disturbances during formation flight make many existing methods difficult to implement. In this paper, we study the formation maintenance problem when multiple UAVs fly according to the preset trajectory under wind disturbances, and propose a novel decentralized formation control method. A synchronized trajectory generation method that can resist wind disturbances is designed in this paper. The method generates a real-time formation trajectory for each UAV, estimates the time for local aircraft to complete this trajectory after eliminating errors caused by wind, and obtains the time to reach the next waypoint together through inter-aircraft communication. To satisfy the time constraint of the formation trajectory, the trajectory tracker of each UAV generates a virtual point for the local aircraft. A kinematic relationship is established for the UAV to track its virtual point, and a PD velocity controller with wind compensation is designed to enable the UAV to accurately track its virtual point location. We used hardware-in-the-loop simulations to demonstrate the effectiveness of the formation maintenance method in a variety of wind speeds. Subsequently, a field flight test of triangular formation was conducted using 6 miniature fixed-wing UAVs, and the designed formation method can reduce the formation error to about 3m under 6m/s wind speed disturbance.
{"title":"A Formation Maintenance Method of UAV Swarm under Wind Disturbances","authors":"Lei Fu, Ruizhi Mao, Yu Yang, Yachao Yang","doi":"10.1145/3547578.3547603","DOIUrl":"https://doi.org/10.1145/3547578.3547603","url":null,"abstract":"Formation maintenance control is one of the important methods to maintain the flight stability of multiple UAVs, and the inevitable wind disturbances during formation flight make many existing methods difficult to implement. In this paper, we study the formation maintenance problem when multiple UAVs fly according to the preset trajectory under wind disturbances, and propose a novel decentralized formation control method. A synchronized trajectory generation method that can resist wind disturbances is designed in this paper. The method generates a real-time formation trajectory for each UAV, estimates the time for local aircraft to complete this trajectory after eliminating errors caused by wind, and obtains the time to reach the next waypoint together through inter-aircraft communication. To satisfy the time constraint of the formation trajectory, the trajectory tracker of each UAV generates a virtual point for the local aircraft. A kinematic relationship is established for the UAV to track its virtual point, and a PD velocity controller with wind compensation is designed to enable the UAV to accurately track its virtual point location. We used hardware-in-the-loop simulations to demonstrate the effectiveness of the formation maintenance method in a variety of wind speeds. Subsequently, a field flight test of triangular formation was conducted using 6 miniature fixed-wing UAVs, and the designed formation method can reduce the formation error to about 3m under 6m/s wind speed disturbance.","PeriodicalId":381600,"journal":{"name":"Proceedings of the 14th International Conference on Computer Modeling and Simulation","volume":"197 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132844409","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 rheological properties of grease have a significant influence on the heat generation and heat transfer of bearings. However, due to the combined effects of shear rate, temperature and load, there are few studies on the bearing temperature field considering the rheological properties of grease. In this paper, the Bauser four-parameter model describing the rheological properties of grease is used to calculate the heat generation of bearings under grease lubrication conditions and conduct finite element analysis on the temperature field of bearings by considering the effects of viscosity of different grease base oils, plastic viscosity and shear rate affected by working conditions on heat generation and heat distribution. Considering the contact heat between the roller and inner and outer raceway and viscous friction heat of the cage, the raceway is regarded as a moving heat source, and the finite element analysis model of grease-lubricated cylindrical roller bearing is established. Taking a certain type of bearing as an example, the distribution law of bearing working temperature under different grease lubrication conditions is analyzed. The results show that under the condition of considering the rheological properties of grease, the heat generation of bearings under different grease lubrication conditions is quite different. The highest temperature inside the bearing appears at the contact center between the roller and the outer raceway, and the area with a higher temperature is more prone to surface damage.
{"title":"Temperature Field Analysis of Cylindrical Roller Bearing based on Rheological Properties of Grease","authors":"Liqun Wang, Yongzhi Pan, Zhenfeng Jiang, Yinhang Zhang, X. Fu, Xiuhua Men","doi":"10.1145/3547578.3547596","DOIUrl":"https://doi.org/10.1145/3547578.3547596","url":null,"abstract":"The rheological properties of grease have a significant influence on the heat generation and heat transfer of bearings. However, due to the combined effects of shear rate, temperature and load, there are few studies on the bearing temperature field considering the rheological properties of grease. In this paper, the Bauser four-parameter model describing the rheological properties of grease is used to calculate the heat generation of bearings under grease lubrication conditions and conduct finite element analysis on the temperature field of bearings by considering the effects of viscosity of different grease base oils, plastic viscosity and shear rate affected by working conditions on heat generation and heat distribution. Considering the contact heat between the roller and inner and outer raceway and viscous friction heat of the cage, the raceway is regarded as a moving heat source, and the finite element analysis model of grease-lubricated cylindrical roller bearing is established. Taking a certain type of bearing as an example, the distribution law of bearing working temperature under different grease lubrication conditions is analyzed. The results show that under the condition of considering the rheological properties of grease, the heat generation of bearings under different grease lubrication conditions is quite different. The highest temperature inside the bearing appears at the contact center between the roller and the outer raceway, and the area with a higher temperature is more prone to surface damage.","PeriodicalId":381600,"journal":{"name":"Proceedings of the 14th International Conference on Computer Modeling and Simulation","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132137490","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}
Assessment of the credit risk of small and medium-sized enterprises (SMEs) based on their strength and reputation is very important for the banks as the basis for credit decisions. We establish a model of credit risk assessment system for SMEs based on Nonparametric Maximum Likelihood Estimation (NPMLE) of survival function which addresses the Case Ⅱ interval-censored data. An empirical analysis of a real data set about 425 Chinese SMEs is carried out. Firstly, the data information of 425 SMEs are preprocessed and three main factors are considered: enterprise strength, development potential, situation of supply and demand relationship of upstream and downstream. Then we extract appropriate features based on those factors. The association between credit risk of SMEs and the extracted features is discussed and variable selection is implemented by Random Forest. What's more, the prediction of the credit risk is carried out by Double Random Forest (DRF), which is a competitive ensemble method in classification and prediction. The predictive accuracy is evaluated by ROC curves and confusion matrices, and the outcomes show that DRF outperforms Support Vector Machine (SVM) and Random Forest (RF). Combining the outcomes of prediction with the features, the intervals into which the repayment time fall are obtained, and hence the data set is Case Ⅱ interval-censored, i.e., the exact time of repayment is unknown and we only know that the repayment time falls into an interval. The issue of risk assessments based on Case Ⅱ interval-censored has received little attentions in the literature. Here the case of prepayment, on-time and late payment are all under discussion. The NPMLE is applied to estimate the probability of repayment varying with time. The survival curves of SMEs with different credit rating are drawn, thus establishing a credit risk assessment system for SMEs.
基于中小企业的实力和声誉对中小企业的信用风险进行评估是银行信贷决策的重要依据。针对Ⅱ区间剔除数据的情况，建立了基于生存函数非参数极大似然估计(NPMLE)的中小企业信用风险评估系统模型。本文对425家中国中小企业的真实数据进行了实证分析。首先对425家中小企业的数据信息进行预处理，主要考虑企业实力、发展潜力、上下游供需关系状况三个因素。然后根据这些因素提取相应的特征。讨论了中小企业信用风险与提取特征之间的关系，并采用随机森林方法进行变量选择。采用双随机森林(Double Random Forest, DRF)对信用风险进行预测，这是一种分类和预测的竞争集成方法。通过ROC曲线和混淆矩阵对预测精度进行评估，结果表明DRF优于支持向量机(SVM)和随机森林(RF)。将预测结果与特征相结合，得到还款时间落在哪个区间，因此数据集为CaseⅡinterval- censorship，即还款的确切时间未知，我们只知道还款时间落在某个区间。基于案例Ⅱ间隔审查的风险评估问题在文献中很少受到关注。在这里，提前付款、按时付款和延期付款都在讨论之中。应用NPMLE来估计随时间变化的还款概率。绘制不同信用等级的中小企业的生存曲线，从而建立中小企业信用风险评估体系。
{"title":"A Model Based on Survival-based Credit Risk Assessment System of SMEs","authors":"Jia Chen, Chunjie Wang, R. Leone","doi":"10.1145/3547578.3547615","DOIUrl":"https://doi.org/10.1145/3547578.3547615","url":null,"abstract":"Assessment of the credit risk of small and medium-sized enterprises (SMEs) based on their strength and reputation is very important for the banks as the basis for credit decisions. We establish a model of credit risk assessment system for SMEs based on Nonparametric Maximum Likelihood Estimation (NPMLE) of survival function which addresses the Case Ⅱ interval-censored data. An empirical analysis of a real data set about 425 Chinese SMEs is carried out. Firstly, the data information of 425 SMEs are preprocessed and three main factors are considered: enterprise strength, development potential, situation of supply and demand relationship of upstream and downstream. Then we extract appropriate features based on those factors. The association between credit risk of SMEs and the extracted features is discussed and variable selection is implemented by Random Forest. What's more, the prediction of the credit risk is carried out by Double Random Forest (DRF), which is a competitive ensemble method in classification and prediction. The predictive accuracy is evaluated by ROC curves and confusion matrices, and the outcomes show that DRF outperforms Support Vector Machine (SVM) and Random Forest (RF). Combining the outcomes of prediction with the features, the intervals into which the repayment time fall are obtained, and hence the data set is Case Ⅱ interval-censored, i.e., the exact time of repayment is unknown and we only know that the repayment time falls into an interval. The issue of risk assessments based on Case Ⅱ interval-censored has received little attentions in the literature. Here the case of prepayment, on-time and late payment are all under discussion. The NPMLE is applied to estimate the probability of repayment varying with time. The survival curves of SMEs with different credit rating are drawn, thus establishing a credit risk assessment system for SMEs.","PeriodicalId":381600,"journal":{"name":"Proceedings of the 14th International Conference on Computer Modeling and Simulation","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115931828","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 low cost and good properties, the use of powder metallurgy titanium alloy in automobile industry to reduce weight and improve performance has been approved by automobile manufacturers. Based on the finite element method, the hot extrusion preforming process of Ti6Al4V powder titanium alloy valve was numerically calculated, and the influences of billet temperature, extrusion speed and extrusion ratio on temperature distribution and porosity were analyzed. The results show that temperature and deformation degree are the main factors affecting densification. Increasing extrusion ratio and billet temperature can improve densification. The temperature rise at the die exit are the highest. Taking the phase transition temperature of Ti6Al4V powder titanium alloy as the critical temperature, the critical curve of temperature rise under different extrusion ratios were obtained. It provides a reference for the selection of valve forming process parameters.
{"title":"Numerical Simulation and Analysis of Hot Extrusion Preforming of Powder Titanium Alloy Valve","authors":"Ronge Liu, Bao-yu Wang, Shushan Hu","doi":"10.1145/3547578.3547583","DOIUrl":"https://doi.org/10.1145/3547578.3547583","url":null,"abstract":"Due to low cost and good properties, the use of powder metallurgy titanium alloy in automobile industry to reduce weight and improve performance has been approved by automobile manufacturers. Based on the finite element method, the hot extrusion preforming process of Ti6Al4V powder titanium alloy valve was numerically calculated, and the influences of billet temperature, extrusion speed and extrusion ratio on temperature distribution and porosity were analyzed. The results show that temperature and deformation degree are the main factors affecting densification. Increasing extrusion ratio and billet temperature can improve densification. The temperature rise at the die exit are the highest. Taking the phase transition temperature of Ti6Al4V powder titanium alloy as the critical temperature, the critical curve of temperature rise under different extrusion ratios were obtained. It provides a reference for the selection of valve forming process parameters.","PeriodicalId":381600,"journal":{"name":"Proceedings of the 14th International Conference on Computer Modeling and Simulation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127382434","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}
Based on the comprehensive analysis of the characteristics of logistics distribution center and logistics system simulation methods, a complete framework of the layout planning problem of logistics distribution center is established. By using the logistics simulation software Flexsim, a simple modeling simulation of the whole process of logistics distribution center is carried out, and according to the analysis of the simulation results, the problems of this logistics system are identified, and optimization and improvement are made. Firstly, the system model of the simulation model was established by analyzing and planning the layout and operation process of a small logistics distribution center. Secondly, Flexsim; simulation software is selected to model and simulate the distribution center and get the corresponding model of logistics distribution center. The problems of the logistics distribution center were found better, and the planning scheme of the logistics distribution center was evaluated scientifically and reasonably, and the model was optimized to some extent. The effectiveness of using Flexsim to optimize the model of the logistics distribution center is demonstrated by comparing the difference between the model before and after optimization at a lower cost and faster speed.
{"title":"Flexsim-based Simulation and Optimization of Green Logistics Distribution Center","authors":"Shuai Wang, Shumeng Wang, Nianbing Zhang","doi":"10.1145/3547578.3547590","DOIUrl":"https://doi.org/10.1145/3547578.3547590","url":null,"abstract":"Based on the comprehensive analysis of the characteristics of logistics distribution center and logistics system simulation methods, a complete framework of the layout planning problem of logistics distribution center is established. By using the logistics simulation software Flexsim, a simple modeling simulation of the whole process of logistics distribution center is carried out, and according to the analysis of the simulation results, the problems of this logistics system are identified, and optimization and improvement are made. Firstly, the system model of the simulation model was established by analyzing and planning the layout and operation process of a small logistics distribution center. Secondly, Flexsim; simulation software is selected to model and simulate the distribution center and get the corresponding model of logistics distribution center. The problems of the logistics distribution center were found better, and the planning scheme of the logistics distribution center was evaluated scientifically and reasonably, and the model was optimized to some extent. The effectiveness of using Flexsim to optimize the model of the logistics distribution center is demonstrated by comparing the difference between the model before and after optimization at a lower cost and faster speed.","PeriodicalId":381600,"journal":{"name":"Proceedings of the 14th International Conference on Computer Modeling and Simulation","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125385143","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}
Based on CFD software, the flow field of ECMO centrifugal blood pump is numerically simulated, the head characteristics of blood pump under different flow rates are calculated, the pressure, velocity and shear stress distribution of blood flowing through the impeller are studied, the cor/responding cloud images are obtained, and the effects of velocity and shear stress on blood damage are analyzed. The results show that the head curves of different flow rates coincide approximately, and all meet the requirements of blood pump parameters. When the flow rate of blood pump is lower than 6m / s, the volume fraction is 92.8%, and the volume fraction in the area with shear stress of 0-150pa is 97.95%. The blood damage of pump is small and hemolysis is not easy to occur.
{"title":"Blood Damage Analysis of ECMO Centrifugal Pump Based on CFD","authors":"Zheng-tang Tan","doi":"10.1145/3547578.3547582","DOIUrl":"https://doi.org/10.1145/3547578.3547582","url":null,"abstract":"Based on CFD software, the flow field of ECMO centrifugal blood pump is numerically simulated, the head characteristics of blood pump under different flow rates are calculated, the pressure, velocity and shear stress distribution of blood flowing through the impeller are studied, the cor/responding cloud images are obtained, and the effects of velocity and shear stress on blood damage are analyzed. The results show that the head curves of different flow rates coincide approximately, and all meet the requirements of blood pump parameters. When the flow rate of blood pump is lower than 6m / s, the volume fraction is 92.8%, and the volume fraction in the area with shear stress of 0-150pa is 97.95%. The blood damage of pump is small and hemolysis is not easy to occur.","PeriodicalId":381600,"journal":{"name":"Proceedings of the 14th International Conference on Computer Modeling and Simulation","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115467614","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 three-dimensional numerical simulation of the quenching process of strip steel were carried out based on the finite element method, and analyzed the effect of water penetration speed on the cooling uniformity of strip steel in the wide direction. The results show that with the increase of water penetration speed, the temperature of each point in the width direction of strip steel increases continuously. After cooling, the temperature variance of each point first increases and then decreases; By comparison, the cooling uniformity along the width direction is best when the strip speed is 1m/s, and which is worst when the strip speed is 2m/s. Good cooling effect can be obtained by changing the spray speed of nozzle under different water penetration speed of strip steel. The results can provide reference and basis for water quenching process of strip steel in practical industrial production.
{"title":"The Effect of Water Penetration Velocity on Temperature Field of Strip Steel","authors":"Shushan Hu, Q. Zhang, Ronge Liu","doi":"10.1145/3547578.3547601","DOIUrl":"https://doi.org/10.1145/3547578.3547601","url":null,"abstract":"The three-dimensional numerical simulation of the quenching process of strip steel were carried out based on the finite element method, and analyzed the effect of water penetration speed on the cooling uniformity of strip steel in the wide direction. The results show that with the increase of water penetration speed, the temperature of each point in the width direction of strip steel increases continuously. After cooling, the temperature variance of each point first increases and then decreases; By comparison, the cooling uniformity along the width direction is best when the strip speed is 1m/s, and which is worst when the strip speed is 2m/s. Good cooling effect can be obtained by changing the spray speed of nozzle under different water penetration speed of strip steel. The results can provide reference and basis for water quenching process of strip steel in practical industrial production.","PeriodicalId":381600,"journal":{"name":"Proceedings of the 14th International Conference on Computer Modeling and Simulation","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126439486","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}
As a key part of CNC machine, the degradation state of tools directly affects the quality of workpieces processing. It is an urgent problem to extract effective feature information from multiple sensors signals and establish an accurate tool wear prediction model. In this article, a tool wear prediction method based on bidirectional long short-term memory attention neural networks (BiLSTMA) is proposed to this problem. Firstly, the paper divides the time series data into data of different time periods and extracts the time domain, frequency domain, time-frequency domain features of the local time period. Secondly, BiLSTM neural network is used to further extract deep features of time dimension from all local features. Finally, an attention mechanism is introduced to reasonably allocate attention weights of the deep features for tool wear prediction. The effectiveness of this method in improving tool wear prediction accuracy is verified by experiments.
{"title":"Tool Wear Prediction Based on BiLSTMA Networks","authors":"Chunyan Qian, Qingqing Huang, Haofei Xie, Dong Yan, Yushuang Wu","doi":"10.1145/3547578.3547594","DOIUrl":"https://doi.org/10.1145/3547578.3547594","url":null,"abstract":"As a key part of CNC machine, the degradation state of tools directly affects the quality of workpieces processing. It is an urgent problem to extract effective feature information from multiple sensors signals and establish an accurate tool wear prediction model. In this article, a tool wear prediction method based on bidirectional long short-term memory attention neural networks (BiLSTMA) is proposed to this problem. Firstly, the paper divides the time series data into data of different time periods and extracts the time domain, frequency domain, time-frequency domain features of the local time period. Secondly, BiLSTM neural network is used to further extract deep features of time dimension from all local features. Finally, an attention mechanism is introduced to reasonably allocate attention weights of the deep features for tool wear prediction. The effectiveness of this method in improving tool wear prediction accuracy is verified by experiments.","PeriodicalId":381600,"journal":{"name":"Proceedings of the 14th International Conference on Computer Modeling and Simulation","volume":"4 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120808745","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}
Aiming at the problem of insufficient stability of traditional motor skill training auxiliary decision-making system in dark or dark environment, this paper designs a motor skill training auxiliary decision-making support system based on Kinect. In terms of hardware design, Kinect is used as the main hardware and TOF technology is used to set the parameters of distance and reachable field of view to obtain motor skill training data. In terms of software design, Kinect is used to determine the bone node of human characteristics, track human data and smooth it, store the smoothed data in the designed data warehouse, and connect the scattered databases together as the support of auxiliary decision-making. On this basis, priority constraints are set for each module in the system to ensure the normal operation of the system. So far, the overall design of the system has been completed. The experimental results show that the motion training aided decision support system based on Kinect designed in this paper has more accurate recognition angle of human motion image and less joint position positioning error in the case of darkness or dark light, which proves that the system has good stability.
{"title":"Design of Motor Skill Training Auxiliary Decision-Making Support System Based on Kinect","authors":"Fan Zhang","doi":"10.1145/3547578.3547610","DOIUrl":"https://doi.org/10.1145/3547578.3547610","url":null,"abstract":"Aiming at the problem of insufficient stability of traditional motor skill training auxiliary decision-making system in dark or dark environment, this paper designs a motor skill training auxiliary decision-making support system based on Kinect. In terms of hardware design, Kinect is used as the main hardware and TOF technology is used to set the parameters of distance and reachable field of view to obtain motor skill training data. In terms of software design, Kinect is used to determine the bone node of human characteristics, track human data and smooth it, store the smoothed data in the designed data warehouse, and connect the scattered databases together as the support of auxiliary decision-making. On this basis, priority constraints are set for each module in the system to ensure the normal operation of the system. So far, the overall design of the system has been completed. The experimental results show that the motion training aided decision support system based on Kinect designed in this paper has more accurate recognition angle of human motion image and less joint position positioning error in the case of darkness or dark light, which proves that the system has good stability.","PeriodicalId":381600,"journal":{"name":"Proceedings of the 14th International Conference on Computer Modeling and Simulation","volume":"237 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133772669","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：