The objective of this paper is to design a new method,based on machine learning,to detect the abnormal status of the suspension system of maglev train by using the real-time signals collected by the levitation *** abn...
详细信息
ISBN:
(纸本)9781509046584
The objective of this paper is to design a new method,based on machine learning,to detect the abnormal status of the suspension system of maglev train by using the real-time signals collected by the levitation *** abnormal status is harmful to the operation of maglev *** is necessary to detect the abnormity ***,the operation data of train is recorded online,but it is analyzed by experts off-line,the efficiency of this approach is very ***,an efficient and accurate method is urgently *** are 120 levitation sensors in a carriage,which measure the levitation states with nearly 40 khz sampling *** tradition,the information of sensors is just used as the feedback of suspension *** paper will study how to use these information for detecting the abnormal status of suspension system by using support vertical machine(SVM).Firstly,some reasonable features originate from experience are extracted from levitation ***,considering that the fault rate is very low,resulting in less fault ***,the SVM method is *** last,the raised machine learning model is applied in the practical usage on maglev train by using the programming in the Digital signal processor(DSP) *** this method,the existing abnormal status of suspension system can be diagnosed in *** experiment results show that this algorithm can achieve the detection accuracy of 91.3%.
This paper presents a sitting posture detection method based on a depth sensor. Effectively detecting bad sitting posture can help protect eyesight and prevent cervical *** most current approaches conduct the sitting ...
详细信息
ISBN:
(纸本)9781509064151;9781509064144
This paper presents a sitting posture detection method based on a depth sensor. Effectively detecting bad sitting posture can help protect eyesight and prevent cervical *** most current approaches conduct the sitting detection with traditional sensors, which leads to inferior performance. Therefore, this paper introduces a novel method based on a depth sensor, in which we 1) model the sitting posture by splitting body profile and locating six body joints, 2) extract two kinds of features: relative topological characters and local edge features, and 3) jointly fuse the two features for sitting posture detection. The proposed method is tested on our 3 D sitting posture dataset, which includes 18 individuals, and totally 9 different sitting postures. The experimental results show that, using an adaptively fusion of the joints features, this method performs a high accuracy(more than 94%) and achieves a real-time detection(17 fps).
Modeling is the basis work of the analysis and design of a control system,and models obtained by different modeling methods have different *** the maglev system,current is generally used as a state to *** analysis and...
详细信息
ISBN:
(纸本)9781538629185
Modeling is the basis work of the analysis and design of a control system,and models obtained by different modeling methods have different *** the maglev system,current is generally used as a state to *** analysis and comparison in this paper,compared with modeling with current state,using magnetic flux density as a state to model the maglev system,the model is much simpler,the linear model is more accurate and more close to the real ***,based on the model built by magnet flux density state method,state feedback is more beneficial to the stabilization of the system,the control performance is better and the coupling interference between suspension points is smaller.
In the control of maglev systems,decentralized control structure is widely used due to its *** to the existence of mechanical coupling,the performance of decentralized control is *** paper focuses on designing a centr...
详细信息
ISBN:
(纸本)9781538629185
In the control of maglev systems,decentralized control structure is widely used due to its *** to the existence of mechanical coupling,the performance of decentralized control is *** paper focuses on designing a centralized controller for a small maglev platform that already has a decentralized control structure.A distributed reduced-order observer is first proposed for one suspension point to estimate the state of other suspension points using the model of the ***,a centralized control is designed and implemented with the help of the proposed decentralized *** simulation results show that centralized control based on distributed observer can reject the state coupling of maglev system and improve the maglev control performances *** future,the proposed distributed observer based centralized controller will be tested on the small maglev platform.
We propose a novel scheme to probabilistically transmit an arbitrary unknown two-qubit quantum state via Positive Operator-Valued Measurement with the help of two partially entangled states. In this scheme, the telepo...
详细信息
We propose a novel scheme to probabilistically transmit an arbitrary unknown two-qubit quantum state via Positive Operator-Valued Measurement with the help of two partially entangled states. In this scheme, the teleportation with two senders and two receives can be realized when the information of non-maximally entangled states is only available for the senders. Furthermore, the concrete implementation processes of this proposal are presented, meanwhile the classical communication cost and the successful probability of our scheme are calculated.
This paper presents an improved gait energy image(GEI) named D-GEI. Nowadays, numerical literatures have focused on gait analysis, yet most approaches do not fully exploit the dynamic walking information, which leads ...
详细信息
ISBN:
(纸本)9781509064151;9781509064144
This paper presents an improved gait energy image(GEI) named D-GEI. Nowadays, numerical literatures have focused on gait analysis, yet most approaches do not fully exploit the dynamic walking information, which leads to inferior performance under the appearance change and viewpoint variation. Furthermore, an improved gait energy image, D-GEI,is proposed. Firstly, we calculate and divide the GEI into dynamic region. Then the region of GEI has the logic ‘and'operation with the sequence to get the dynamic region of ***, we calculate the weighted average of these dynamic regions to get the D-GEI. In tests, HOG characteristics of D-GEI is regarded as features representation and the tests based on the CASIA dataset are conducted, in which we select the SVM as classifier. The experimental results show that with HOG based on dynamic gait energy image, the proposed method outperforms HOG based on GEI method.
With the development of new industries such unmanned aerial vehicles (UAV), the accuracy and reliability of positioning and navigation are higher. Relying on the existing satellite system, it is impossible to provide ...
详细信息
ISBN:
(数字)9781538611715
ISBN:
(纸本)9781538611722
With the development of new industries such unmanned aerial vehicles (UAV), the accuracy and reliability of positioning and navigation are higher. Relying on the existing satellite system, it is impossible to provide high precision three-dimensional positioning because of the poor Vertical Dilution of Precision (VDOP). We use pseudo-satellite (pseudolite) technology to improve the DOP value, and give some suggestions for the construction of the whole system.
This paper focus on the modelling and control of a hydraulically-actuated biologically-inspired articulated robotic *** leg has two hydraulically-actuated degrees of freedom(DoF),the hip and knee joints,and a passive ...
详细信息
ISBN:
(纸本)9781509046584
This paper focus on the modelling and control of a hydraulically-actuated biologically-inspired articulated robotic *** leg has two hydraulically-actuated degrees of freedom(DoF),the hip and knee joints,and a passive spring DoF,the ankle *** a brief description of the prototype leg,the paper developed a nonlinear model of the leg,including its kinematics and ***,an actively compliant control architecture based on outer virtual compliant leg model and inner torque controller was designed to achieve a spring-damper like touchdown dynamics ***,both a Pushdown experiment and a Dropdown experiment were carried to verify the designed *** result confirmed that a hydraulically-actuated robot articulated leg can successfully emulate virtual passive components through proper mechanical design and actively compliant control under dynamic situations.
With suspension control of the medium speed maglev train as the research background,a new suspension joint structure is proposed and an active fault-tolerant control algorithm based on state gain refactoring is design...
详细信息
ISBN:
(纸本)9781509046584
With suspension control of the medium speed maglev train as the research background,a new suspension joint structure is proposed and an active fault-tolerant control algorithm based on state gain refactoring is designed by referring to the joint structure of high speed maglev train of German and the patent from *** new structure connects the two adjacent bogies by mechanical structure,which not only increases the redundancy degree of the system but also takes the fault-tolerant control problem of the end bogie into *** demonstrates that the joint structure and its active fault-tolerant control method can increase significantly the fault-tolerant performance of suspension system,which can contribute greatly to engineering application.
The purpose of this paper is to design a practical flux density observer which provides the accurate magnetic flux density signal for the flux feedback control of electromagnet-permanent magnet(EM-PM) hybrid suspens...
详细信息
ISBN:
(纸本)9781538629185
The purpose of this paper is to design a practical flux density observer which provides the accurate magnetic flux density signal for the flux feedback control of electromagnet-permanent magnet(EM-PM) hybrid suspension system in maglev ***,the property of two basic kinds of flux observers based on current model and voltage model are *** improve the design of the observed flux density,a practical observer is raised by extracting the low frequency flux density signal from current model and high frequency flux density signal from voltage *** more,based on the analysis of error source of the flux observer,the parameter self-tuning scheme using model reference adaptive system(MRAS) and the track irregularity estimation are applied in it for the purpose of higher *** then,based on the suspension module,the numerical comparisons and related experiments are carried *** show that the raised observer can get satisfied signal for the control in suspension *** the closed loop control system with observed flux feedback can achieve satisfied performance.
暂无评论