Distributed Denial of Service (DDoS) attack is a standout amongst the most prominent attacks types going for the accessibility of framework. We consider the convenient identification and alleviation of DDoS attacks in Automated Traffic Management Systems (ATMS). Utilizing diverse attack traffic designs, it is conceivable to watch the conduct of the algorithm under investigation. The principle objective of this paper is to break down the recursive nonparametric CUSUM, since it is new to the information organize network and it guarantees to have a great deal of future applications in the region. A novel system for recognizing and relieving low-rate DDoS attacks in ITS dependent on nonparametric statistical anomaly/hybrid detection is proposed. The outcome will demonstrate that our proposed technique significantly beats two parametric strategies for opportune identification dependent on the Cumulative Sum (CUSUM) test, just as the conventional information filtering approach as far as normal recognition delay and false alert rate.
{"title":"Nonparametric Statistical Anomaly Detection Approach for ATMS DDoS Attack","authors":"Yunpeng Zhang, Anish Patel, Liang-Chieh Cheng, Jiming Peng","doi":"10.1109/SDPC.2019.00055","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00055","url":null,"abstract":"Distributed Denial of Service (DDoS) attack is a standout amongst the most prominent attacks types going for the accessibility of framework. We consider the convenient identification and alleviation of DDoS attacks in Automated Traffic Management Systems (ATMS). Utilizing diverse attack traffic designs, it is conceivable to watch the conduct of the algorithm under investigation. The principle objective of this paper is to break down the recursive nonparametric CUSUM, since it is new to the information organize network and it guarantees to have a great deal of future applications in the region. A novel system for recognizing and relieving low-rate DDoS attacks in ITS dependent on nonparametric statistical anomaly/hybrid detection is proposed. The outcome will demonstrate that our proposed technique significantly beats two parametric strategies for opportune identification dependent on the Cumulative Sum (CUSUM) test, just as the conventional information filtering approach as far as normal recognition delay and false alert rate.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114412048","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}
Xiaopeng Liu, Weifang Zhang, Xiangyu Wang, W. Dai, Guicui Fu
Fatigue crack is an important factor affecting structural safety, and it is of great significance for accurate monitoring of fatigue crack propagation. This paper presents a Lamb Wave-based method for quantitative monitoring of fatigue crack propagation. In this method, various types of damage features are extracted in both time and frequency domains to comprehensively describe the Lamb wave changes. To address the problem of multicollinearity in damage features, principal component regression (PCR) is adopted to establish a quantitative model between damage features and crack size. The PCR model is established and validated by the experimental data of aluminum alloy plates. Experimental results reveal that the proposed PCR model is able to accurately monitor the fatigue crack propagation, and it performs far better than traditional multiple linear regression (MLR) model.
{"title":"Lamb Wave-based Monitoring of Fatigue Crack Propagation using Principal Component Regression","authors":"Xiaopeng Liu, Weifang Zhang, Xiangyu Wang, W. Dai, Guicui Fu","doi":"10.1109/SDPC.2019.00011","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00011","url":null,"abstract":"Fatigue crack is an important factor affecting structural safety, and it is of great significance for accurate monitoring of fatigue crack propagation. This paper presents a Lamb Wave-based method for quantitative monitoring of fatigue crack propagation. In this method, various types of damage features are extracted in both time and frequency domains to comprehensively describe the Lamb wave changes. To address the problem of multicollinearity in damage features, principal component regression (PCR) is adopted to establish a quantitative model between damage features and crack size. The PCR model is established and validated by the experimental data of aluminum alloy plates. Experimental results reveal that the proposed PCR model is able to accurately monitor the fatigue crack propagation, and it performs far better than traditional multiple linear regression (MLR) model.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"162 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115714748","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}
This paper studies on the fault diagnosis of aircraft secondary power distribution system based on RBF neural network. Firstly, the basic principle and model of radial basis function neural network (RBF) are expounded,then the common fault types of the aircraft secondary distribution system are analyzed and the characteristic parameters extraction of the corresponding fault modes is studied. Then, based on the multisensor information fusion problem of the aircraft secondary distribution system, an RBF network model suitable for the aircraft secondary distribution system is established. The model was trained by MATLAB software, and an online fault diagnosis platform for aircraft secondary power distribution system is established.
{"title":"Research on Fault Diagnosis Method of Aircraft Secondary Distribution System Based on RBF Neural Network","authors":"Yetong Qian, Li Wang, Qingwen Chen","doi":"10.1109/SDPC.2019.00075","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00075","url":null,"abstract":"This paper studies on the fault diagnosis of aircraft secondary power distribution system based on RBF neural network. Firstly, the basic principle and model of radial basis function neural network (RBF) are expounded,then the common fault types of the aircraft secondary distribution system are analyzed and the characteristic parameters extraction of the corresponding fault modes is studied. Then, based on the multisensor information fusion problem of the aircraft secondary distribution system, an RBF network model suitable for the aircraft secondary distribution system is established. The model was trained by MATLAB software, and an online fault diagnosis platform for aircraft secondary power distribution system is established.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116165490","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 the process of inspecting the rear torsion beam, there will be measurement error because of the manufacturing error, vibration of the automatic inspection tool and the deformation of the workpiece. This paper presents an error compensation method for parameter of rear torsion beam based on PSO-BP (particle swarm optimization and back propagation neural network) algorithm. In order to solve the problem that BP neural network converges slowly and is easy to fall into local optimum, the paper uses PSO algorithm to optimize its weight and threshold. The research results show that the PSO-BP algorithm has good error compensation accuracy.
在对后扭力梁进行检测的过程中，由于制造误差、自动检测工具的振动以及工件的变形等原因，会产生测量误差。提出了一种基于PSO-BP (particle swarm optimization and back propagation neural network)算法的后扭力梁参数误差补偿方法。为了解决BP神经网络收敛速度慢、容易陷入局部最优的问题，本文采用粒子群算法对BP神经网络的权值和阈值进行优化。研究结果表明，PSO-BP算法具有良好的误差补偿精度。
{"title":"Measurement Error Compensation Method for Parameters of Rear Torsion Beam With PSO-BP","authors":"Kangkang Zhang, Bo Liu","doi":"10.1109/SDPC.2019.00032","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00032","url":null,"abstract":"In the process of inspecting the rear torsion beam, there will be measurement error because of the manufacturing error, vibration of the automatic inspection tool and the deformation of the workpiece. This paper presents an error compensation method for parameter of rear torsion beam based on PSO-BP (particle swarm optimization and back propagation neural network) algorithm. In order to solve the problem that BP neural network converges slowly and is easy to fall into local optimum, the paper uses PSO algorithm to optimize its weight and threshold. The research results show that the PSO-BP algorithm has good error compensation accuracy.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121827867","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}
An aero-engine fuel system is an important part of an aero-engine, and its reliability directly affects the operation of the aero-engine. To improve the reliability of aero-engines, this paper uses Goal-Oriented (GO) method to analyze the reliability of an aero-engine fuel system with afterburner combustion chamber. Firstly, the GO model is established by the structural schematic diagram of an aero-engine fuel system with an afterburner combustion chamber, and the qualitative analysis and quantitative calculation are carried out according to the operation rules of operators and signal flows in the GO model. Then the minimum cut set and quantitative reliability level of the fuel system are obtained respectively. Finally, the results are compared with the results by the fault tree analysis (FTA) method. The comparison result shows that the reliability analysis of the aero-engine fuel system by the GO method is reasonable and the GO method can be used for the reliability analysis of aero-engine systems.
{"title":"Application of GO Method in Reliability Analysis of Aero-engine","authors":"Yuxi Tao, Hai-ping Dong, X. Yi, Chenhui Ren","doi":"10.1109/SDPC.2019.00079","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00079","url":null,"abstract":"An aero-engine fuel system is an important part of an aero-engine, and its reliability directly affects the operation of the aero-engine. To improve the reliability of aero-engines, this paper uses Goal-Oriented (GO) method to analyze the reliability of an aero-engine fuel system with afterburner combustion chamber. Firstly, the GO model is established by the structural schematic diagram of an aero-engine fuel system with an afterburner combustion chamber, and the qualitative analysis and quantitative calculation are carried out according to the operation rules of operators and signal flows in the GO model. Then the minimum cut set and quantitative reliability level of the fuel system are obtained respectively. Finally, the results are compared with the results by the fault tree analysis (FTA) method. The comparison result shows that the reliability analysis of the aero-engine fuel system by the GO method is reasonable and the GO method can be used for the reliability analysis of aero-engine systems.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121934364","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}
Vehicle tracking based on video images has been widely used in military and civilian fields. The tracking method must robust enough to hand the unexpected situations that may occur during the tracking process. In this paper, a novel vehicle tracking method based on convolutional neural networks (CNNs) is proposed to target the accurate and speed demand of vehicle tracking. The proposed method contains two networks with shared weights. It utilizes the residual block to reduce the train error. Offline training is used to achieve real-time tracking. It also use transfer learning to reduce training time. The experimental results under the real aerial video demonstrate that vehicle tracker achieves an accuracy of 70.8% and the speed of 135fps with GPU. The proposed method is robust enough to handle occlusion and other interference conditions.
{"title":"Real-Time Vehicle Tracking using Convolutional Neural Networks in Aerial Video","authors":"Yu Yang, Chengpo Mu, Ruixin Yang, Yanjie Wang","doi":"10.1109/SDPC.2019.00052","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00052","url":null,"abstract":"Vehicle tracking based on video images has been widely used in military and civilian fields. The tracking method must robust enough to hand the unexpected situations that may occur during the tracking process. In this paper, a novel vehicle tracking method based on convolutional neural networks (CNNs) is proposed to target the accurate and speed demand of vehicle tracking. The proposed method contains two networks with shared weights. It utilizes the residual block to reduce the train error. Offline training is used to achieve real-time tracking. It also use transfer learning to reduce training time. The experimental results under the real aerial video demonstrate that vehicle tracker achieves an accuracy of 70.8% and the speed of 135fps with GPU. The proposed method is robust enough to handle occlusion and other interference conditions.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"222 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122126618","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}
Protein subcellular location is an important biological information for understanding protein’s function in normal cells. Automatic analysis of protein subcellular location based on bioimage has been received much attention in recent years. Since preprocessing is a critical step in the automatic image-based analysis system for source separation, this research focuses on the protein subcellular location. Some problems exist in most existing separation methods, such as, the lack of strong explanation and low accuracy. In this paper, a new separation method called minimum volume constrain nonnegative matrix factorization for image preprocessing has been proposed. To examine the effectiveness of the proposed method, both local and global features are extracted from the separated channels, and multi-label classifier is used to make prediction for subcellular localization. The results show the proposed method can generally improve the accuracy of final prediction compared with other methods.
{"title":"Constrained Nonnegative Matrix Factorization for Image-based Protein Subcellular Localization Prediction","authors":"Huaqun Zhan, Ping Zhou, Hualin Zhan","doi":"10.1109/SDPC.2019.00132","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00132","url":null,"abstract":"Protein subcellular location is an important biological information for understanding protein’s function in normal cells. Automatic analysis of protein subcellular location based on bioimage has been received much attention in recent years. Since preprocessing is a critical step in the automatic image-based analysis system for source separation, this research focuses on the protein subcellular location. Some problems exist in most existing separation methods, such as, the lack of strong explanation and low accuracy. In this paper, a new separation method called minimum volume constrain nonnegative matrix factorization for image preprocessing has been proposed. To examine the effectiveness of the proposed method, both local and global features are extracted from the separated channels, and multi-label classifier is used to make prediction for subcellular localization. The results show the proposed method can generally improve the accuracy of final prediction compared with other methods.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"81 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131349396","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}
Deep learning is gaining growing interests in the field of remaining useful life (RUL) prediction and has achieved state-of-the-art results. Current deep learning-based prognostics approaches, however, do not consider the distinctions of different sensor data during representation learning, which affects their prediction accuracy and limits their generalization. To overcome this weakness, a new deep prognostics network called deep residual attention network (DRAN) is proposed in this paper. DRAN is composed of representation learning sub-network and RUL prediction sub-network. In particular, a new module, i.e., attention module, is constructed in DRAN, aiming to emphasize the important degradation information hidden in sensor data and suppress the useless information during representation learning. The proposed DRAN is validated using the vibration signals acquired by accelerated degradation tests of rolling element bearings. The experimental results show that the proposed DRAN is able to provide accurate RUL prediction results and is superior to some existing convolutional networks.
{"title":"Remaining Useful Life Prediction Based on Deep Residual Attention Network","authors":"Biao Wang, Tianyu Han, Y. Lei, Naipeng Li","doi":"10.1109/SDPC.2019.00023","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00023","url":null,"abstract":"Deep learning is gaining growing interests in the field of remaining useful life (RUL) prediction and has achieved state-of-the-art results. Current deep learning-based prognostics approaches, however, do not consider the distinctions of different sensor data during representation learning, which affects their prediction accuracy and limits their generalization. To overcome this weakness, a new deep prognostics network called deep residual attention network (DRAN) is proposed in this paper. DRAN is composed of representation learning sub-network and RUL prediction sub-network. In particular, a new module, i.e., attention module, is constructed in DRAN, aiming to emphasize the important degradation information hidden in sensor data and suppress the useless information during representation learning. The proposed DRAN is validated using the vibration signals acquired by accelerated degradation tests of rolling element bearings. The experimental results show that the proposed DRAN is able to provide accurate RUL prediction results and is superior to some existing convolutional networks.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131748060","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 large weight coefficient of AGV (Automated guided vehicle) car body at present, taking equal strength and light weight as the research target, the mechanical analysis of car body structure was carried out. The relationship between load distribution and wheel position was obtained by mathematical programming, and the constraint conditions of the topology optimization problem were obtained. An adaptive mechanism was proposed to adjust the moving window according to the change of design variables before and after iteration. An adaptive improved variable density method based on sliding window was established to optimize the topological structure of AGV car body. Finally, the structure simulation and verification were carried out to verify the effectiveness and practicability of the method, which can optimize the performance of the AGV car body structure, reduce the weight of the structure, and then improve the efficiency and rationality of the AGV operation.
{"title":"An Optimization Method of AGV Body Topology Based on Improved Variable Density Method","authors":"Huadong Zhao, Nan-Yun Jiang, Chaofan Lei","doi":"10.1109/SDPC.2019.00151","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00151","url":null,"abstract":"Aiming at the problem of large weight coefficient of AGV (Automated guided vehicle) car body at present, taking equal strength and light weight as the research target, the mechanical analysis of car body structure was carried out. The relationship between load distribution and wheel position was obtained by mathematical programming, and the constraint conditions of the topology optimization problem were obtained. An adaptive mechanism was proposed to adjust the moving window according to the change of design variables before and after iteration. An adaptive improved variable density method based on sliding window was established to optimize the topological structure of AGV car body. Finally, the structure simulation and verification were carried out to verify the effectiveness and practicability of the method, which can optimize the performance of the AGV car body structure, reduce the weight of the structure, and then improve the efficiency and rationality of the AGV operation.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121076594","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 an alternative to reliability analysis, the non-probabilistic model is an effective supplement when the interval information exists. We describe the uncertain parameters of the structures with interval variables, and establish a non-probabilistic reliability model of structures. Then, we analyze the relation between the typical interference mode and the reliability according to the structure stress-strength interference model, and propose a new measure of structure non-probabilistic reliability. Furthermore we describe other uncertain parameters with random variables when probabilistic information also exists. For the complex structures including both random variables and interval variables, we propose a probabilistic and non-probabilistic synthetic reliability model. The illustrative example shows that the presented model is feasible for structure reliability analysis and design.
{"title":"Probabilistic and Non-probabilistic Synthetic Reliability Model of Structures","authors":"Jiao Shi, Dongpao Hong, Peihao He, Guangyu Jing","doi":"10.1109/SDPC.2019.00200","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00200","url":null,"abstract":"As an alternative to reliability analysis, the non-probabilistic model is an effective supplement when the interval information exists. We describe the uncertain parameters of the structures with interval variables, and establish a non-probabilistic reliability model of structures. Then, we analyze the relation between the typical interference mode and the reliability according to the structure stress-strength interference model, and propose a new measure of structure non-probabilistic reliability. Furthermore we describe other uncertain parameters with random variables when probabilistic information also exists. For the complex structures including both random variables and interval variables, we propose a probabilistic and non-probabilistic synthetic reliability model. The illustrative example shows that the presented model is feasible for structure reliability analysis and design.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121126980","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：