In machinery fault diagnosis,labeled data are always difficult or even impossible to obtain.Transfer learning can leverage related fault diagnosis knowledge from fully labeled source domain to enhance the fault diagno...In machinery fault diagnosis,labeled data are always difficult or even impossible to obtain.Transfer learning can leverage related fault diagnosis knowledge from fully labeled source domain to enhance the fault diagnosis performance in sparsely labeled or unlabeled target domain,which has been widely used for cross domain fault diagnosis.However,existing methods focus on either marginal distribution adaptation(MDA)or conditional distribution adaptation(CDA).In practice,marginal and conditional distributions discrepancies both have significant but different influences on the domain divergence.In this paper,a dynamic distribution adaptation based transfer network(DDATN)is proposed for cross domain bearing fault diagnosis.DDATN utilizes the proposed instance-weighted dynamic maximum mean discrepancy(IDMMD)for dynamic distribution adaptation(DDA),which can dynamically estimate the influences of marginal and conditional distribution and adapt target domain with source domain.The experimental evaluation on cross domain bearing fault diagnosis demonstrates that DDATN can outperformance the state-of-the-art cross domain fault diagnosis methods.展开更多
A new centrifuge based method for determining the response of continuous buried pipe to PGD is presented. The physical characteristics of the RPI's 100 g-ton geotechnical centrifuge and the current lifeline experi...A new centrifuge based method for determining the response of continuous buried pipe to PGD is presented. The physical characteristics of the RPI's 100 g-ton geotechnical centrifuge and the current lifeline experiment split-box are described: The split-box contains the model pipeline and surrounding soil and is manufactured such that half can be offset, in flight, simulating PGD. In addition, governing similitude relations which allow one to determine the physical characteristics, (diameter, wall thickness and material modulus of elasticity) of the model pipeline are presented. Finally, recorded strains induced in two buried pipes with prototype diameters of 0.63 m and 0.95 m (24 and 36 inch) subject to 0.6 and 2.0 meters (2 and 6 feet) of full scale fault offsets and presented and compared to corresponding FE results.展开更多
On the basis of the comparison data of Stage II of the tunnel site leveling project at Hutubi seismic station and the observation data of Stage IV of the site cross fault leveling project at Hutubi and the level obser...On the basis of the comparison data of Stage II of the tunnel site leveling project at Hutubi seismic station and the observation data of Stage IV of the site cross fault leveling project at Hutubi and the level observation data from the cross fault survey lines in Dafeng from 1987 to 2012,this paper analyses the variation rates of the tunnel site leveling observation results and the difference of annual change rates of the cross fault level observations at Hongshan seismic station in Hutubi. This paper concludes the reliability of the Ni004 optical level used by the station and puts forward a proposal based on the analysis. This paper also explores the cross fault leveling research on the ground deformation in the region concerned on the basis of the historical observation of the cross fault level at Dafeng and the comparison results of the tunnel site leveling observation in Hutubi.展开更多
基金Supported by National Natural Science Foundation of China(Grant Nos.51875208,51475170)National Key Research and Development Program of China(Grant No.2018YFB1702400).
文摘In machinery fault diagnosis,labeled data are always difficult or even impossible to obtain.Transfer learning can leverage related fault diagnosis knowledge from fully labeled source domain to enhance the fault diagnosis performance in sparsely labeled or unlabeled target domain,which has been widely used for cross domain fault diagnosis.However,existing methods focus on either marginal distribution adaptation(MDA)or conditional distribution adaptation(CDA).In practice,marginal and conditional distributions discrepancies both have significant but different influences on the domain divergence.In this paper,a dynamic distribution adaptation based transfer network(DDATN)is proposed for cross domain bearing fault diagnosis.DDATN utilizes the proposed instance-weighted dynamic maximum mean discrepancy(IDMMD)for dynamic distribution adaptation(DDA),which can dynamically estimate the influences of marginal and conditional distribution and adapt target domain with source domain.The experimental evaluation on cross domain bearing fault diagnosis demonstrates that DDATN can outperformance the state-of-the-art cross domain fault diagnosis methods.
基金National Science Foundation Under Grant No.CMS-0085256
文摘A new centrifuge based method for determining the response of continuous buried pipe to PGD is presented. The physical characteristics of the RPI's 100 g-ton geotechnical centrifuge and the current lifeline experiment split-box are described: The split-box contains the model pipeline and surrounding soil and is manufactured such that half can be offset, in flight, simulating PGD. In addition, governing similitude relations which allow one to determine the physical characteristics, (diameter, wall thickness and material modulus of elasticity) of the model pipeline are presented. Finally, recorded strains induced in two buried pipes with prototype diameters of 0.63 m and 0.95 m (24 and 36 inch) subject to 0.6 and 2.0 meters (2 and 6 feet) of full scale fault offsets and presented and compared to corresponding FE results.
基金sponsored by the Natural Science Foundation of Xinjiang Uighur Autonomous Region2012211B56)the Natural Science Foundation of China(41374031)the Earthquake Science and Technology Spark Plan(XH1030),and the Earthquake Science and Technology Spark Progam XH14054Y)
文摘On the basis of the comparison data of Stage II of the tunnel site leveling project at Hutubi seismic station and the observation data of Stage IV of the site cross fault leveling project at Hutubi and the level observation data from the cross fault survey lines in Dafeng from 1987 to 2012,this paper analyses the variation rates of the tunnel site leveling observation results and the difference of annual change rates of the cross fault level observations at Hongshan seismic station in Hutubi. This paper concludes the reliability of the Ni004 optical level used by the station and puts forward a proposal based on the analysis. This paper also explores the cross fault leveling research on the ground deformation in the region concerned on the basis of the historical observation of the cross fault level at Dafeng and the comparison results of the tunnel site leveling observation in Hutubi.