Order analysis is one of the most important technique means of condition monitoring and fault diagnosis for rotary machinery.The traditional order analyses usually employ the Vold-Kalman filtering,however this method ...Order analysis is one of the most important technique means of condition monitoring and fault diagnosis for rotary machinery.The traditional order analyses usually employ the Vold-Kalman filtering,however this method is confined to the expensive hardware equipments.This paper starts from Gabor transform and applies the Gabor time-frequency filtering to vibration signal.The order component＇s time-frequency coefficients are extracted by mask operation.The order component is reconstructed from the obtained coefficients.The following four key technologies,such as smoothing rotary speed curve,defining filtering band width,constructing the mask operation matrix and reconstructing signal component,are also deeply discussed.Moreover,the technique to smooth the rotary speed curve based on polynomial approximation,the method to determine filtering band width,the arithmetic to constitute mask array and the iterative algorithm to reconstruct signal based on minimum mean square error are specifically analyzed.The 4th order component is successfully gained by using the methods that Gabor time-frequency filter,and the validity and feasibility of this method are approved.This method can solve the problem of order tracking filter technologies which used to depend on hardware and efficiently improve the accuracy of order analysis.展开更多
Recently,deep learning has achieved great success in visual tracking tasks,particularly in single-object tracking.This paper provides a comprehensive review of state-of-the-art single-object tracking algorithms based ...Recently,deep learning has achieved great success in visual tracking tasks,particularly in single-object tracking.This paper provides a comprehensive review of state-of-the-art single-object tracking algorithms based on deep learning.First,we introduce basic knowledge of deep visual tracking,including fundamental concepts,existing algorithms,and previous reviews.Second,we briefly review existing deep learning methods by categorizing them into data-invariant and data-adaptive methods based on whether they can dynamically change their model parameters or architectures.Then,we conclude with the general components of deep trackers.In this way,we systematically analyze the novelties of several recently proposed deep trackers.Thereafter,popular datasets such as Object Tracking Benchmark(OTB)and Visual Object Tracking(VOT)are discussed,along with the performances of several deep trackers.Finally,based on observations and experimental results,we discuss three different characteristics of deep trackers,i.e.,the relationships between their general components,exploration of more effective tracking frameworks,and interpretability of their motion estimation components.展开更多
A technology for unintended lane departure warning was proposed. As crucial information, lane boundaries were detected based on principal component analysis of grayscale distribution in search bars of given number and...A technology for unintended lane departure warning was proposed. As crucial information, lane boundaries were detected based on principal component analysis of grayscale distribution in search bars of given number and then each search bar was tracked using Kalman filter between frames. The lane detection performance was evaluated and demonstrated in ways of receiver operating characteristic, dice similarity coefficient and real-time performance. For lane departure detection, a lane departure risk evaluation model based on lasting time and frequency was effectively executed on the ARM-based platform. Experimental results indicate that the algorithm generates satisfactory lane detection results under different traffic and lighting conditions, and the proposed warning mechanism sends effective warning signals, avoiding most false warning.展开更多
In this article we propose to combine an integrated method, the PCA-GMM method that generates a relatively improved segmentation outcome as compared to conventional GMM with Kalman Filtering (KF). The combined new met...In this article we propose to combine an integrated method, the PCA-GMM method that generates a relatively improved segmentation outcome as compared to conventional GMM with Kalman Filtering (KF). The combined new method the PCA-GMM-KF attempts tracking multiple moving objects;the size and position of the objects along the sequence of their images in dynamic scenes. The obtained experimental results successfully illustrate the tracking of multiple moving objects based on this robust展开更多
At present,ZPW-2000 track circuit fault diagnosis is artificially analyzed and monitored.Its discrimination method not only is low efficient and takes a long period,but also requires highly experienced personnel to an...At present,ZPW-2000 track circuit fault diagnosis is artificially analyzed and monitored.Its discrimination method not only is low efficient and takes a long period,but also requires highly experienced personnel to analyze the data.Therefore,we introduce kernel principal component analysis and stacked auto-encoder network(KPCA-SAD)into the fault diagnosis of ZPW-2000 track circuit.According to the working principle and fault characteristics of track circuit,a fault diagnosis model of KPCA-SAE network is established.The relevant parameters of key components recorded in the data collected by field staff are used as the fault feature parameters.The KPCA method is used to reduce the dimension and noise of fault document matrix to avoid information redundancy.The SAE network is trained by the processed fault data.The model parameters are optimized overall by using back propagation(BP)algorithm.The KPCA-SAE model is simulated in Matlab platform and is finally proved to be effective and feasible.Compared with the traditional method of artificially analyzing fault data and other intelligent algorithms,the KPCA-SAE based classifier has higher fault identification accuracy.展开更多
The paper analyzes the problem of blind source separation （BSS） based on the nonlinear principal component analysis （NPCA） criterion. An adaptive strong tracking filter （STF） based algorithm was developed, which...The paper analyzes the problem of blind source separation （BSS） based on the nonlinear principal component analysis （NPCA） criterion. An adaptive strong tracking filter （STF） based algorithm was developed, which is immune to system model mismatches. Simulations demonstrate that the algorithm converges quickly and has satisfactory steady-state accuracy. The Kalman filtering algorithm and the recursive leastsquares type algorithm are shown to be special cases of the STF algorithm. Since the forgetting factor is adaptively updated by adjustment of the Kalman gain, the STF scheme provides more powerful tracking capability than the Kalman filtering algorithm and recursive least-squares algorithm.展开更多
In this paper, a model order reduction strategy is adopted for the static and dynamic behaviour simulation of a high-speed tracked vehicle. The total number of degree of freedom of the structure is condensed through a...In this paper, a model order reduction strategy is adopted for the static and dynamic behaviour simulation of a high-speed tracked vehicle. The total number of degree of freedom of the structure is condensed through a selection of interface degrees of freedom and significant global mode shapes, for an approximated description of vehicle dynamic behaviour. The methodology is implemented in a customised open-source software to reduce the computational efforts. The modelled tracked vehicle includes the sprung mass, the unsprung masses, connected by means of torsional bars, and all the track assemblies, composing the track chain. The proposed research activity presents a comprehensive investigation of the influence of the track chain, combined with longitudinal vehicle speed, on statics and vehicle dynamics, focusing on vertical dynamics. The vehicle response has been investigated both in frequency and time domain. In this last case road-wheel displacements are assumed as inputs for the model, under different working conditions, hence considering several road profiles with different amplitudes and characteristic excitation frequencies. Simulation results have proven a high fidelity in model order reduction approach and a significant contribution of the track chain in the global dynamic behaviour of the tracked vehicle.展开更多
We first discuss the relationship between the optimal track maintenance scheduling model and an efficient detection method for abnormal track irregularities given by the longitudinal level irregularity displaceme...We first discuss the relationship between the optimal track maintenance scheduling model and an efficient detection method for abnormal track irregularities given by the longitudinal level irregularity displacement (LLID). The results of applying the cluster analysis technique to the sampling data showed that maintenance operation is required for approximately 10% of the total lots, and these lots were further classified into three groups according to the degree of maintenance need. To analyze the background factors for detecting abnormal LLID lots, a principal component analysis was performed;the results showed that the first principal component represents LLIDs from the viewpoints of the rail structure, equipment, and operating conditions. Binomial and ordinal logit regression models (LRMs) were used to quantitatively investigate the determinants of abnormal LLIDs. Binomial LRM was used to characterize the abnormal LLIDs, whereas ordinal LRM was used to distinguish the degree of influence of factors that are considered to have a significant impact on LLIDs.展开更多
基金supported by National Hi-tech Research and Development Program of China (863 Program,Grant No.2008AA042408)
文摘Order analysis is one of the most important technique means of condition monitoring and fault diagnosis for rotary machinery.The traditional order analyses usually employ the Vold-Kalman filtering,however this method is confined to the expensive hardware equipments.This paper starts from Gabor transform and applies the Gabor time-frequency filtering to vibration signal.The order component＇s time-frequency coefficients are extracted by mask operation.The order component is reconstructed from the obtained coefficients.The following four key technologies,such as smoothing rotary speed curve,defining filtering band width,constructing the mask operation matrix and reconstructing signal component,are also deeply discussed.Moreover,the technique to smooth the rotary speed curve based on polynomial approximation,the method to determine filtering band width,the arithmetic to constitute mask array and the iterative algorithm to reconstruct signal based on minimum mean square error are specifically analyzed.The 4th order component is successfully gained by using the methods that Gabor time-frequency filter,and the validity and feasibility of this method are approved.This method can solve the problem of order tracking filter technologies which used to depend on hardware and efficiently improve the accuracy of order analysis.
基金supported by National Natural Science Foundation of China(Nos.61922064 and U2033210)Zhejiang Provincial Natural Science Foundation(Nos.LR17F030001 and LQ19F020005)the Project of Science and Technology Plans of Wenzhou City(Nos.C20170008 and ZG2017016)。
文摘Recently,deep learning has achieved great success in visual tracking tasks,particularly in single-object tracking.This paper provides a comprehensive review of state-of-the-art single-object tracking algorithms based on deep learning.First,we introduce basic knowledge of deep visual tracking,including fundamental concepts,existing algorithms,and previous reviews.Second,we briefly review existing deep learning methods by categorizing them into data-invariant and data-adaptive methods based on whether they can dynamically change their model parameters or architectures.Then,we conclude with the general components of deep trackers.In this way,we systematically analyze the novelties of several recently proposed deep trackers.Thereafter,popular datasets such as Object Tracking Benchmark(OTB)and Visual Object Tracking(VOT)are discussed,along with the performances of several deep trackers.Finally,based on observations and experimental results,we discuss three different characteristics of deep trackers,i.e.,the relationships between their general components,exploration of more effective tracking frameworks,and interpretability of their motion estimation components.
基金Project(51175159)supported by the National Natural Science Foundation of ChinaProject(2013WK3024)supported by the Science andTechnology Planning Program of Hunan Province,ChinaProject(CX2013B146)supported by the Hunan Provincial InnovationFoundation for Postgraduate,China
文摘A technology for unintended lane departure warning was proposed. As crucial information, lane boundaries were detected based on principal component analysis of grayscale distribution in search bars of given number and then each search bar was tracked using Kalman filter between frames. The lane detection performance was evaluated and demonstrated in ways of receiver operating characteristic, dice similarity coefficient and real-time performance. For lane departure detection, a lane departure risk evaluation model based on lasting time and frequency was effectively executed on the ARM-based platform. Experimental results indicate that the algorithm generates satisfactory lane detection results under different traffic and lighting conditions, and the proposed warning mechanism sends effective warning signals, avoiding most false warning.
文摘In this article we propose to combine an integrated method, the PCA-GMM method that generates a relatively improved segmentation outcome as compared to conventional GMM with Kalman Filtering (KF). The combined new method the PCA-GMM-KF attempts tracking multiple moving objects;the size and position of the objects along the sequence of their images in dynamic scenes. The obtained experimental results successfully illustrate the tracking of multiple moving objects based on this robust
基金National Natural Science Foundation of China(No.61763023)。
文摘At present,ZPW-2000 track circuit fault diagnosis is artificially analyzed and monitored.Its discrimination method not only is low efficient and takes a long period,but also requires highly experienced personnel to analyze the data.Therefore,we introduce kernel principal component analysis and stacked auto-encoder network(KPCA-SAD)into the fault diagnosis of ZPW-2000 track circuit.According to the working principle and fault characteristics of track circuit,a fault diagnosis model of KPCA-SAE network is established.The relevant parameters of key components recorded in the data collected by field staff are used as the fault feature parameters.The KPCA method is used to reduce the dimension and noise of fault document matrix to avoid information redundancy.The SAE network is trained by the processed fault data.The model parameters are optimized overall by using back propagation(BP)algorithm.The KPCA-SAE model is simulated in Matlab platform and is finally proved to be effective and feasible.Compared with the traditional method of artificially analyzing fault data and other intelligent algorithms,the KPCA-SAE based classifier has higher fault identification accuracy.
基金Supported by the Basic Research Foundation of Tsinghua National Laboratory for Information Science and Technology (TNList) the National Natural Science Foundation of China (No. 60675002)
文摘The paper analyzes the problem of blind source separation （BSS） based on the nonlinear principal component analysis （NPCA） criterion. An adaptive strong tracking filter （STF） based algorithm was developed, which is immune to system model mismatches. Simulations demonstrate that the algorithm converges quickly and has satisfactory steady-state accuracy. The Kalman filtering algorithm and the recursive leastsquares type algorithm are shown to be special cases of the STF algorithm. Since the forgetting factor is adaptively updated by adjustment of the Kalman gain, the STF scheme provides more powerful tracking capability than the Kalman filtering algorithm and recursive least-squares algorithm.
文摘In this paper, a model order reduction strategy is adopted for the static and dynamic behaviour simulation of a high-speed tracked vehicle. The total number of degree of freedom of the structure is condensed through a selection of interface degrees of freedom and significant global mode shapes, for an approximated description of vehicle dynamic behaviour. The methodology is implemented in a customised open-source software to reduce the computational efforts. The modelled tracked vehicle includes the sprung mass, the unsprung masses, connected by means of torsional bars, and all the track assemblies, composing the track chain. The proposed research activity presents a comprehensive investigation of the influence of the track chain, combined with longitudinal vehicle speed, on statics and vehicle dynamics, focusing on vertical dynamics. The vehicle response has been investigated both in frequency and time domain. In this last case road-wheel displacements are assumed as inputs for the model, under different working conditions, hence considering several road profiles with different amplitudes and characteristic excitation frequencies. Simulation results have proven a high fidelity in model order reduction approach and a significant contribution of the track chain in the global dynamic behaviour of the tracked vehicle.
文摘We first discuss the relationship between the optimal track maintenance scheduling model and an efficient detection method for abnormal track irregularities given by the longitudinal level irregularity displacement (LLID). The results of applying the cluster analysis technique to the sampling data showed that maintenance operation is required for approximately 10% of the total lots, and these lots were further classified into three groups according to the degree of maintenance need. To analyze the background factors for detecting abnormal LLID lots, a principal component analysis was performed;the results showed that the first principal component represents LLIDs from the viewpoints of the rail structure, equipment, and operating conditions. Binomial and ordinal logit regression models (LRMs) were used to quantitatively investigate the determinants of abnormal LLIDs. Binomial LRM was used to characterize the abnormal LLIDs, whereas ordinal LRM was used to distinguish the degree of influence of factors that are considered to have a significant impact on LLIDs.
