The Experts below are selected from a list of 210 Experts worldwide ranked by ideXlab platform
Pierre Comon - One of the best experts on this subject based on the ideXlab platform.
-
exploring multimodal data fusion through joint decompositions with Flexible Couplings
IEEE Transactions on Signal Processing, 2016Co-Authors: Rodrigo Cabral Farias, Jeremy E Cohen, Pierre ComonAbstract:A Bayesian framework is proposed to define Flexible coupling models for joint tensor decompositions of multiple datasets. Under this framework, a natural formulation of the data fusion problem is to cast it in terms of a joint maximum a posteriori (MAP) estimator. Data-driven scenarios of joint posterior distributions are provided, including general Gaussian priors and non Gaussian coupling priors. We present and discuss implementation issues of algorithms used to obtain the joint MAP estimator. We also show how this framework can be adapted to tackle the problem of joint decompositions of large datasets. In the case of a conditional Gaussian coupling with a linear transformation, we give theoretical bounds on the data fusion performance using the Bayesian Cramer–Rao bound. Simulations are reported for hybrid coupling models ranging from simple additive Gaussian models to Gamma-type models with positive variables and to the coupling of data sets which are inherently of different size due to different resolution of the measurement devices.
-
Exploring Multimodal Data Fusion Through Joint Decompositions with Flexible Couplings
IEEE Transactions on Signal Processing, 2016Co-Authors: Rodrigo Cabral Farias, Jeremy E Cohen, Pierre ComonAbstract:A Bayesian framework is proposed to define Flexible coupling models for joint tensor decompositions of multiple datasets. Under this framework, a natural formulation of the data fusion problem is to cast it in terms of a joint maximum a posteriori (MAP) estimator. Data-driven scenarios of joint posterior distributions are provided, including general Gaussian priors and non Gaussian coupling priors. We present and discuss implementation issues of algorithms used to obtain the joint MAP estimator. We also show how this framework can be adapted to tackle the problem of joint decompositions of large datasets. In the case of a conditional Gaussian coupling with a linear transformation, we give theoretical bounds on the data fusion performance using the Bayesian Cramér-Rao bound. Simulations are reported for hybrid coupling models ranging from simple additive Gaussian models to Gamma-type models with positive variables and to the coupling of data sets which are inherently of different size due to different resolution of the measurement devices.
-
joint decompositions with Flexible Couplings
International Conference on Latent Variable Analysis and Signal Separation, 2015Co-Authors: Rodrigo Cabral Farias, Jeremy E Cohen, Christian Jutten, Pierre ComonAbstract:A Bayesian framework is proposed to define Flexible coupling models for joint decompositions of data sets. Under this framework, a solution to the joint decomposition can be cast in terms of a maximum a posteriori estimator. Examples of joint posterior distributions are provided, including general Gaussian priors and non Gaussian coupling priors. Then simulations are reported and show the effectiveness of this approach to fuse information from data sets, which are inherently of different size due to different time resolution of the measurement devices.
-
LVA/ICA - Joint Decompositions with Flexible Couplings
Latent Variable Analysis and Signal Separation, 2015Co-Authors: Rodrigo Cabral Farias, Jeremy E Cohen, Christian Jutten, Pierre ComonAbstract:A Bayesian framework is proposed to define Flexible coupling models for joint decompositions of data sets. Under this framework, a solution to the joint decomposition can be cast in terms of a maximum a posteriori estimator. Examples of joint posterior distributions are provided, including general Gaussian priors and non Gaussian coupling priors. Then simulations are reported and show the effectiveness of this approach to fuse information from data sets, which are inherently of different size due to different time resolution of the measurement devices.
Rodrigo Cabral Farias - One of the best experts on this subject based on the ideXlab platform.
-
exploring multimodal data fusion through joint decompositions with Flexible Couplings
IEEE Transactions on Signal Processing, 2016Co-Authors: Rodrigo Cabral Farias, Jeremy E Cohen, Pierre ComonAbstract:A Bayesian framework is proposed to define Flexible coupling models for joint tensor decompositions of multiple datasets. Under this framework, a natural formulation of the data fusion problem is to cast it in terms of a joint maximum a posteriori (MAP) estimator. Data-driven scenarios of joint posterior distributions are provided, including general Gaussian priors and non Gaussian coupling priors. We present and discuss implementation issues of algorithms used to obtain the joint MAP estimator. We also show how this framework can be adapted to tackle the problem of joint decompositions of large datasets. In the case of a conditional Gaussian coupling with a linear transformation, we give theoretical bounds on the data fusion performance using the Bayesian Cramer–Rao bound. Simulations are reported for hybrid coupling models ranging from simple additive Gaussian models to Gamma-type models with positive variables and to the coupling of data sets which are inherently of different size due to different resolution of the measurement devices.
-
Exploring Multimodal Data Fusion Through Joint Decompositions with Flexible Couplings
IEEE Transactions on Signal Processing, 2016Co-Authors: Rodrigo Cabral Farias, Jeremy E Cohen, Pierre ComonAbstract:A Bayesian framework is proposed to define Flexible coupling models for joint tensor decompositions of multiple datasets. Under this framework, a natural formulation of the data fusion problem is to cast it in terms of a joint maximum a posteriori (MAP) estimator. Data-driven scenarios of joint posterior distributions are provided, including general Gaussian priors and non Gaussian coupling priors. We present and discuss implementation issues of algorithms used to obtain the joint MAP estimator. We also show how this framework can be adapted to tackle the problem of joint decompositions of large datasets. In the case of a conditional Gaussian coupling with a linear transformation, we give theoretical bounds on the data fusion performance using the Bayesian Cramér-Rao bound. Simulations are reported for hybrid coupling models ranging from simple additive Gaussian models to Gamma-type models with positive variables and to the coupling of data sets which are inherently of different size due to different resolution of the measurement devices.
-
joint decompositions with Flexible Couplings
International Conference on Latent Variable Analysis and Signal Separation, 2015Co-Authors: Rodrigo Cabral Farias, Jeremy E Cohen, Christian Jutten, Pierre ComonAbstract:A Bayesian framework is proposed to define Flexible coupling models for joint decompositions of data sets. Under this framework, a solution to the joint decomposition can be cast in terms of a maximum a posteriori estimator. Examples of joint posterior distributions are provided, including general Gaussian priors and non Gaussian coupling priors. Then simulations are reported and show the effectiveness of this approach to fuse information from data sets, which are inherently of different size due to different time resolution of the measurement devices.
-
LVA/ICA - Joint Decompositions with Flexible Couplings
Latent Variable Analysis and Signal Separation, 2015Co-Authors: Rodrigo Cabral Farias, Jeremy E Cohen, Christian Jutten, Pierre ComonAbstract:A Bayesian framework is proposed to define Flexible coupling models for joint decompositions of data sets. Under this framework, a solution to the joint decomposition can be cast in terms of a maximum a posteriori estimator. Examples of joint posterior distributions are provided, including general Gaussian priors and non Gaussian coupling priors. Then simulations are reported and show the effectiveness of this approach to fuse information from data sets, which are inherently of different size due to different time resolution of the measurement devices.
Jeremy E Cohen - One of the best experts on this subject based on the ideXlab platform.
-
exploring multimodal data fusion through joint decompositions with Flexible Couplings
IEEE Transactions on Signal Processing, 2016Co-Authors: Rodrigo Cabral Farias, Jeremy E Cohen, Pierre ComonAbstract:A Bayesian framework is proposed to define Flexible coupling models for joint tensor decompositions of multiple datasets. Under this framework, a natural formulation of the data fusion problem is to cast it in terms of a joint maximum a posteriori (MAP) estimator. Data-driven scenarios of joint posterior distributions are provided, including general Gaussian priors and non Gaussian coupling priors. We present and discuss implementation issues of algorithms used to obtain the joint MAP estimator. We also show how this framework can be adapted to tackle the problem of joint decompositions of large datasets. In the case of a conditional Gaussian coupling with a linear transformation, we give theoretical bounds on the data fusion performance using the Bayesian Cramer–Rao bound. Simulations are reported for hybrid coupling models ranging from simple additive Gaussian models to Gamma-type models with positive variables and to the coupling of data sets which are inherently of different size due to different resolution of the measurement devices.
-
Exploring Multimodal Data Fusion Through Joint Decompositions with Flexible Couplings
IEEE Transactions on Signal Processing, 2016Co-Authors: Rodrigo Cabral Farias, Jeremy E Cohen, Pierre ComonAbstract:A Bayesian framework is proposed to define Flexible coupling models for joint tensor decompositions of multiple datasets. Under this framework, a natural formulation of the data fusion problem is to cast it in terms of a joint maximum a posteriori (MAP) estimator. Data-driven scenarios of joint posterior distributions are provided, including general Gaussian priors and non Gaussian coupling priors. We present and discuss implementation issues of algorithms used to obtain the joint MAP estimator. We also show how this framework can be adapted to tackle the problem of joint decompositions of large datasets. In the case of a conditional Gaussian coupling with a linear transformation, we give theoretical bounds on the data fusion performance using the Bayesian Cramér-Rao bound. Simulations are reported for hybrid coupling models ranging from simple additive Gaussian models to Gamma-type models with positive variables and to the coupling of data sets which are inherently of different size due to different resolution of the measurement devices.
-
joint decompositions with Flexible Couplings
International Conference on Latent Variable Analysis and Signal Separation, 2015Co-Authors: Rodrigo Cabral Farias, Jeremy E Cohen, Christian Jutten, Pierre ComonAbstract:A Bayesian framework is proposed to define Flexible coupling models for joint decompositions of data sets. Under this framework, a solution to the joint decomposition can be cast in terms of a maximum a posteriori estimator. Examples of joint posterior distributions are provided, including general Gaussian priors and non Gaussian coupling priors. Then simulations are reported and show the effectiveness of this approach to fuse information from data sets, which are inherently of different size due to different time resolution of the measurement devices.
-
LVA/ICA - Joint Decompositions with Flexible Couplings
Latent Variable Analysis and Signal Separation, 2015Co-Authors: Rodrigo Cabral Farias, Jeremy E Cohen, Christian Jutten, Pierre ComonAbstract:A Bayesian framework is proposed to define Flexible coupling models for joint decompositions of data sets. Under this framework, a solution to the joint decomposition can be cast in terms of a maximum a posteriori estimator. Examples of joint posterior distributions are provided, including general Gaussian priors and non Gaussian coupling priors. Then simulations are reported and show the effectiveness of this approach to fuse information from data sets, which are inherently of different size due to different time resolution of the measurement devices.
Alan B. Palazzolo - One of the best experts on this subject based on the ideXlab platform.
-
VFD Machinery Vibration Fatigue Life and Multilevel Inverter Effect
IEEE Transactions on Industry Applications, 2013Co-Authors: Alan B. PalazzoloAbstract:This paper documents fatigue-related mechanical failures in variable-frequency drive (VFD) motor machinery due to mechanical vibrations excited by drive torque harmonics which are created by pulse width modulation (PWM) switching. Present effort models the coupled system with a full electrical system (including the rectifier, dc bus, inverter, and motor), and an industrial mechanical system (including Flexible Couplings, gearboxes, and multiple inertias). The models are formed by a novel combination of a commercial motor code with a general self-written mechanical code. The approach extends failure prediction beyond the simple occurrence of resonance to fatigue life evaluation based on the rain-flow algorithm, which is suitable for both steady state and transient start-up mechanical response. The second contribution is a demonstration that the common use of a multilevel inverter to reduce voltage/current harmonics may actually exacerbate resonance and fatigue failure. This is shown to be caused by a resulting amplitude increase of torque components in proximity to potential resonance frequencies.
-
VFD machinery vibration fatigue life and multi-level inverter effect
2012 IEEE Industry Applications Society Annual Meeting, 2012Co-Authors: Alan B. PalazzoloAbstract:The paper documents fatigue related mechanical failures in variable frequency drive (VFD) motor machinery due to mechanical vibrations excited by drive torque harmonics which are created by PWM switching. Present effort models the coupled system with full electrical system including rectifier, DC bus, inverter, motor, and an industrial mechanical system including Flexible Couplings, gearboxes and multiple inertias. The models are formed by a novel combining of a commercial motor code with a general, self-written mechanical code. The approach extends failure prediction beyond simple occurrence of resonance, to fatigue life evaluation based on Rain-flow algorithm, which is suitable for both steady state and transient startup mechanical response. The second contribution is a demonstration that the common use of multilevel inverter to reduce voltage/current harmonics may actually exacerbate resonance and fatigue failure. This is shown to be caused by a resulting amplitude increase of torque components in proximity to potential resonance frequencies.
-
Gear Coupling Misalignment Induced Forces
Proceedings of the twenty-first turbomachinery symposium, 1992Co-Authors: Alan B. Palazzolo, Michael Calistrat, Robert W Clark, Stephen R. Locke, Dan CalistratAbstract:Dr. Palazzolo's expertise is in machinery and structural vibra tions, rotordynamics and deflections, and stress. For simulations, he employs transfer matrices, and finite and boundary elements. He has also been extensively involved with field troubleshooting of me chanical malfunctions in rotating and reciprocating machinery. Dr. Palazzolo has presented papers at ASLE andASME Gas Turbine and Vibration Conferences, and has published many papers in various engineering journals. His current research includes cryogenic vi bration dampers, active vibrations control ,fluid film bearings, shaft currents, gear Couplings, magnetic bearings, and annular seals. 83 Stephen R. Locke is a Turbomachinery Consultant with E.l. duPont deN emours and Company, 1 ncorporated. He is located at the Cumberland Regional Consulting group in Old Hickory, Tennessee, and has 20 years of turbomachinery and rotating equipment experience with Dupont. He consults on up grading performance, mechanical reliabil ity, and specification of repairs and new ., equipment. Prior to this, Mr. Locke was assigned to a turbomachinery consulting group in Wilmington. During his first 10 years at Dupont, he was assigned to a petrochemicals plant where he provided technical assistance to operations and maintenance, par ticipated in several plant startups and the commissioning of several large process compressors. Mr. Locke graduated from Purdue University (1972) with a B.S. degree in Mechanical Engineering. He has written two other papers on turbomachinery and is a member of ASME. 84 PROCEEDINGS OF THE TWENTY-FIRST TURBOMACHINERY SYMPOSIUM Michael M. Calistrat has outstanding ex perience in the field of power transmission equipment, which he has accumulated work ing with oil drilling equipment, gearing and Flexible Couplings. He also has a solid back ground in industrial gas turbines. ABSTRACT Gear Couplings can produce large static forces and moments that can affect the vibrations of turbomachinery, even with nearly perfect alignment. Research, testing and case histories have veri fied this theory and are reported. Methods are suggested to control the direction of these forces for reduced vibration and enhanced turbomachinery reliability.
-
Gear Coupling Misalignment Induced Forces and Their Effects on Machinery Vibration
Proceedings of the 21st Turbomachinery Symposium Turbomachinery Laboratory Texas A&M University College Station TX September, 1992Co-Authors: Alan B. Palazzolo, Michael Calistrat, Dan Calistrat, Stephen R. Locke, Akram Ayoub, R. Clark, Punan TangAbstract:Dr. Palazzolo's expertise is in machinery and structural vibra tions, rotordynamics and deflections, and stress. For simulations, he employs transfer matrices, and finite and boundary elements. He has also been extensively involved with field troubleshooting of me chanical malfunctions in rotating and reciprocating machinery. Dr. Palazzolo has presented papers at ASLE andASME Gas Turbine and Vibration Conferences, and has published many papers in various engineering journals. His current research includes cryogenic vi bration dampers, active vibrations control ,fluid film bearings, shaft currents, gear Couplings, magnetic bearings, and annular seals. 83 Stephen R. Locke is a Turbomachinery Consultant with E.l. duPont deN emours and Company, 1 ncorporated. He is located at the Cumberland Regional Consulting group in Old Hickory, Tennessee, and has 20 years of turbomachinery and rotating equipment experience with Dupont. He consults on up grading performance, mechanical reliabil ity, and specification of repairs and new ., equipment. Prior to this, Mr. Locke was assigned to a turbomachinery consulting group in Wilmington. During his first 10 years at Dupont, he was assigned to a petrochemicals plant where he provided technical assistance to operations and maintenance, par ticipated in several plant startups and the commissioning of several large process compressors. Mr. Locke graduated from Purdue University (1972) with a B.S. degree in Mechanical Engineering. He has written two other papers on turbomachinery and is a member of ASME. 84 PROCEEDINGS OF THE TWENTY-FIRST TURBOMACHINERY SYMPOSIUM Michael M. Calistrat has outstanding ex perience in the field of power transmission equipment, which he has accumulated work ing with oil drilling equipment, gearing and Flexible Couplings. He also has a solid back ground in industrial gas turbines. ABSTRACT Gear Couplings can produce large static forces and moments that can affect the vibrations of turbomachinery, even with nearly perfect alignment. Research, testing and case histories have veri fied this theory and are reported. Methods are suggested to control the direction of these forces for reduced vibration and enhanced turbomachinery reliability.
J Homisin - One of the best experts on this subject based on the ideXlab platform.
-
determining the properties of pneumatic Flexible shaft Couplings with wedge Flexible elements
Zeszyty Naukowe. Transport Politechnika Śląska, 2013Co-Authors: P Kassay, J HomisinAbstract:At the Department we deal with the development of pneumatic Flexible shaft Couplings, which in addition to other Flexible Couplings are able to change their torsional stiffness by adjusting the air pressure in their Flexible elements. This article deals with the computation of static load characteristics of pneumatic Flexible shaft coupling with wedge Flexible elements. This coupling was developed to improve the properties of pneumatic Flexible Couplings, especially the nominal and maximal torque and maximum angle of distortion. Due to the reason that coupling with wedge elements isn’t manufactured yet, we will use only a mathematic model of this coupling.
-
comparation of selected pneumatic Flexible shaft Couplings
Zeszyty Naukowe. Transport Politechnika Śląska, 2011Co-Authors: P Kassay, J Homisin, Robert Grega, J KrajnakAbstract:At our Department we deal with the development of pneumatic Flexible shaft Couplings, which in addition to other Flexible Couplings are able to change their torsional stiffness by adjusting the air pressure in their Flexible elements. This article deals with comparison of two selected pneumatic Flexible shaft coupling. The first coupling is a newly developed pneumatic Flexible shaft coupling with wedge elements. Pneumatic Flexible shaft coupling with wedge elements was developed to improve the properties of pneumatic Flexible Couplings, especially the nominal and maximal torque and maximum angle of distortion. Due to the reason that coupling with wedge elements isn’t manufactured yet, we will use only a mathematic model of this coupling. The second coupling is a tangential pneumatic Flexible shaft coupling manufactured by FENA company.