Taxi drivers' cruising patterns are learnt with GPS trajectory data collected in Shenzhen, China. By employing Ripley's K function, the impacts of land use and pick-up experience on taxis' cruising behavio...Taxi drivers' cruising patterns are learnt with GPS trajectory data collected in Shenzhen, China. By employing Ripley's K function, the impacts of land use and pick-up experience on taxis' cruising behavior are investigated concerning about both intensity of influence and radius of influence. The results indicate that, in general, taxi drivers tend to learn more from land use characteristics than from pick-up experience. The optimal radius of influence of land use points and previous pick-up points is 14.18 km and 9.93 km, respectively. The findings also show that the high-earning drivers or thorough drivers pay more attention to land use characteristics and tend to cruise in high-density area, while the low-earning drivers or focus drivers prefer to learn more from previous pick-up experience and select the area which is far away from the high-density area. These findings facilitate the development of measures of managing taxi's travel behavior by providing useful insights into taxis' cruising patterns. The results also provide useful advice for taxi drivers to make efficient cruising decision, which will contribute to the improvement of cruising efficiency and the reduction of negative effects.展开更多
The impulsive components induced by bearing faults are key features for assessing gear-box bearing faults.However,because of heavy background noise and the interferences of other vibrations,it is difficult to extract ...The impulsive components induced by bearing faults are key features for assessing gear-box bearing faults.However,because of heavy background noise and the interferences of other vibrations,it is difficult to extract these impulsive components caused by faults,particularly early faults,from the measured vibration signals.To capture the high-level structure of impulsive components embedded in measured vibration signals,a dictionary learning method called shift-invariant K-means singular value decomposition(SI-K-SVD)dictionary learning is used to detect the early faults of gear-box bearings.Although SI-K-SVD is more flexible and adaptable than existing methods,the improper selection of two SI-K-SVD-related parameters,namely,the number of iterations and the pattern lengths,has an adverse influence on fault detection performance.Therefore,the sparsity of the envelope spectrum(SES)and the kurtosis of the envelope spectrum(KES)are used to select these two key parameters,respectively.SI-K-SVD with the two selected optimal parameter values,referred to as optimal parameter SI-K-SVD(OP-SI-K-SVD),is proposed to detect gear-box bearing faults.The proposed method is verified by both simulations and an experiment.Compared to the state-of-the-art methods,namely,empirical model decomposition,wavelet transform and K-SVD,OP-SI-K-SVD has better performance in diagnosing the early faults of a gear-box bearing.展开更多
基金Project(NCET-14-0318) supported by the Humanity and Social Science Youth Foundation of Ministry of Education,ChinaProject supported by the Training Program for Outstanding Young Teachers in Jilin University,ChinaProject(2014M551191) supported by China Postdoctoral Science Foundation
文摘Taxi drivers' cruising patterns are learnt with GPS trajectory data collected in Shenzhen, China. By employing Ripley's K function, the impacts of land use and pick-up experience on taxis' cruising behavior are investigated concerning about both intensity of influence and radius of influence. The results indicate that, in general, taxi drivers tend to learn more from land use characteristics than from pick-up experience. The optimal radius of influence of land use points and previous pick-up points is 14.18 km and 9.93 km, respectively. The findings also show that the high-earning drivers or thorough drivers pay more attention to land use characteristics and tend to cruise in high-density area, while the low-earning drivers or focus drivers prefer to learn more from previous pick-up experience and select the area which is far away from the high-density area. These findings facilitate the development of measures of managing taxi's travel behavior by providing useful insights into taxis' cruising patterns. The results also provide useful advice for taxi drivers to make efficient cruising decision, which will contribute to the improvement of cruising efficiency and the reduction of negative effects.
基金Project(51875481) supported by the National Natural Science Foundation of ChinaProject(2682017CX011) supported by the Fundamental Research Foundations for the Central Universities,China+2 种基金Project(2017M623009) supported by the China Postdoctoral Science FoundationProject(2017YFB1201004) supported by the National Key Research and Development Plan for Advanced Rail Transit,ChinaProject(2019TPL_T08) supported by the Research Fund of the State Key Laboratory of Traction Power,China
文摘The impulsive components induced by bearing faults are key features for assessing gear-box bearing faults.However,because of heavy background noise and the interferences of other vibrations,it is difficult to extract these impulsive components caused by faults,particularly early faults,from the measured vibration signals.To capture the high-level structure of impulsive components embedded in measured vibration signals,a dictionary learning method called shift-invariant K-means singular value decomposition(SI-K-SVD)dictionary learning is used to detect the early faults of gear-box bearings.Although SI-K-SVD is more flexible and adaptable than existing methods,the improper selection of two SI-K-SVD-related parameters,namely,the number of iterations and the pattern lengths,has an adverse influence on fault detection performance.Therefore,the sparsity of the envelope spectrum(SES)and the kurtosis of the envelope spectrum(KES)are used to select these two key parameters,respectively.SI-K-SVD with the two selected optimal parameter values,referred to as optimal parameter SI-K-SVD(OP-SI-K-SVD),is proposed to detect gear-box bearing faults.The proposed method is verified by both simulations and an experiment.Compared to the state-of-the-art methods,namely,empirical model decomposition,wavelet transform and K-SVD,OP-SI-K-SVD has better performance in diagnosing the early faults of a gear-box bearing.
