Home  About us  Contact
 

Gradient Information (gradient + information)

Distribution by Scientific Domains
Engineering80%

Selected Abstracts

Multi-objective turbomachinery optimization using a gradient-enhanced multi-layer perceptron

INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN FLUIDS, Issue 6 2009
M. C. Duta
Abstract Response surface models (RSMs) have found widespread use to reduce the overall computational cost of turbomachinery blading design optimization. Recent developments have seen the successful use of gradient information alongside sampled response values in building accurate response surfaces. This paper describes the use of gradients to enhance the performance of the RSM provided by a multi-layer perceptron. Gradient information is included in the perceptron by modifying the error function such that the perceptron is trained to fit the gradients as well as the response values. As a consequence, the back-propagation scheme that assists the training is also changed. The paper formulates the gradient-enhanced multi-layer perceptron using algebraic notation, with an emphasis on the ease of use and efficiency of computer code implementation. To illustrate the benefit of using gradient information, the enhanced neural network model is used in a multi-objective transonic fan blade optimization exercise of engineering relevance. Copyright © 2008 John Wiley & Sons, Ltd. [source]

Robust hyperplane synthesis for sliding mode control systems via sensitivity minimization

OPTIMAL CONTROL APPLICATIONS AND METHODS, Issue 3 2002
Hei Ka Tam
Abstract A robust hyperplane computation scheme for sliding mode control systems is proposed in this paper. A novel sensitivity index for the sliding eigenvalues with respect to perturbations in the system matrix, the input matrix and the hyperplane matrix is derived in the first instance. The robust hyperplane design problem is then formulated as an optimization task in which the proposed sensitivity index is accordingly minimized. Gradient information of the objective function is established which permits optimization to be proceeded effectively. A numerical example with statistical testing is employed to illustrate the design technique. Copyright © 2002 John Wiley & Sons, Ltd. [source]

Gravity gradiometer systems , advances and challenges

GEOPHYSICAL PROSPECTING, Issue 4 2009
Daniel DiFrancesco
ABSTRACT The past few years have witnessed significant advances and unparalleled interest in gravity gradiometer instrument technology as well as new deployment scenarios for various applications. Gravity gradiometry is now routinely considered as a viable component for resource exploration activities as well as being deployed for global information gathering. Since the introduction of the torsion balance in the 1890s, it has been recognized that gravity gradient information is valuable , yet difficult and time-consuming to obtain. The recent acceptance and routine use of airborne gravity gradiometry for exploration has inspired many new technology developments. This paper summarizes advances in gravity gradient sensor development and also looks at deployment scenarios and gradiometer systems that have been successfully fielded. With projected improved system performance on the horizon, new challenges will also come to the forefront. Included in these challenges are aspects of instrument and system intrinsic noise, vehicle dynamic noise, terrain noise, geologic noise and other noise sources. Each of these aspects is briefly reviewed herein and recommendations for improvements presented. [source]

Multi-objective turbomachinery optimization using a gradient-enhanced multi-layer perceptron

INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN FLUIDS, Issue 6 2009
M. C. Duta
Abstract Response surface models (RSMs) have found widespread use to reduce the overall computational cost of turbomachinery blading design optimization. Recent developments have seen the successful use of gradient information alongside sampled response values in building accurate response surfaces. This paper describes the use of gradients to enhance the performance of the RSM provided by a multi-layer perceptron. Gradient information is included in the perceptron by modifying the error function such that the perceptron is trained to fit the gradients as well as the response values. As a consequence, the back-propagation scheme that assists the training is also changed. The paper formulates the gradient-enhanced multi-layer perceptron using algebraic notation, with an emphasis on the ease of use and efficiency of computer code implementation. To illustrate the benefit of using gradient information, the enhanced neural network model is used in a multi-objective transonic fan blade optimization exercise of engineering relevance. Copyright © 2008 John Wiley & Sons, Ltd. [source]

Support vector machines-based generalized predictive control

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, Issue 17 2006
S. Iplikci
Abstract In this study, we propose a novel control methodology that introduces the use of support vector machines (SVMs) in the generalized predictive control (GPC) scheme. The SVM regression algorithms have extensively been used for modelling nonlinear systems due to their assurance of global solution, which is achieved by transforming the regression problem into a convex optimization problem in dual space, and also their higher generalization potential. These key features of the SVM structures lead us to the idea of employing a SVM model of an unknown plant within the GPC context. In particular, the SVM model can be employed to obtain gradient information and also it can predict future trajectory of the plant output, which are needed in the cost function minimization block. Simulations have confirmed that proposed SVM-based GPC scheme can provide a noticeably high control performance, in other words, an unknown nonlinear plant controlled by SVM-based GPC can accurately track the reference inputs with different shapes. Moreover, the proposed SVM-based GPC scheme maintains its control performance under noisy conditions. Copyright © 2006 John Wiley & Sons, Ltd. [source]