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
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
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.
