The research work presents the dynamics of system based on the model of convective heat transfer in Magnetodydrodynamics (MHD) slip flow over stretching surface with single-wall carbon nanotubes (CNTs) by exploiting t...
详细信息
The research work presents the dynamics of system based on the model of convective heat transfer in Magnetodydrodynamics (MHD) slip flow over stretching surface with single-wall carbon nanotubes (CNTs) by exploiting the strengths of intelligent computing procedures including artificial neural networks (ANNs), genetic algorithms (GAs) and sequentialquadratic technique (SQP). Using similarity transformation, the boundary layer mechanism for the baseline nanofluidics system modeled by partial differential equations (PDEs) is reduced to coupled ordinary differential equations (ODEs). The transformed system is modeled in an unsupervised manner with feed-forward ANNs and efficient adaptation of these networks is performed with global search optimization using GA, aided with SQP for local search. The proposed scheme is evaluated to analyze the dynamics of nanofluidics by taking different concentrations of single wall CNTs based nano-materials mixed with base fluids such as water, kerosene oil or engine oil. Reliability and correctness of the proposed scheme is established through simulation experiments with results which consistently match with Adams numerical procedure. Moreover, Monte Carlo simulations based statistical analysis has been performed to validate the accuracy of the results in terms of performance metrics of variance account for (VAF), mean absolute error (MAE) and root mean square error (RMSE). (C) 2017 Taiwan Institute of Chemical Engineers. Published by Elsevier B.V. All rights reserved.
Medium voltage drive systems driven by high-power multi-level inverters operating at low switching frequency can reduce the switching losses of the power device and increase the output power. Employing subsection sync...
详细信息
Medium voltage drive systems driven by high-power multi-level inverters operating at low switching frequency can reduce the switching losses of the power device and increase the output power. Employing subsection synchronous current harmonic minimum pulse width modulation (CHMPWM) technique can maintain the total harmonic distortion of current at a very low level. It can also reduce the losses of the system, improve the system control performance and increase the efficiency of DC-link voltage accordingly. This paper proposes a subsection synchronous CHMPWM approach of active neutral point clamped five-level (ANPC-5L) inverter under low switching frequency operation. The subsection synchronous scheme is obtained by theoretical calculation based on the allowed maximum switching frequency. The genetic algorithm (GA) is adopted to get the high-precision initial values. So the expected switching angles can be achieved with the help of sequential quadratic programming (SQP) algorithm. The selection principle of multiple sets of the switching angles is also presented. Finally, the validity of the theoretical analysis and the superiority of the CHMPWM are verified through both the simulation results and experimental results.
In this work, a new stochastic computing technique is developed to study the nonlinear dynamics of Troesch's problem by designing the mathematical models of Morlet Wavelets Artificial Neural Networks (MW-ANNs) opt...
详细信息
In this work, a new stochastic computing technique is developed to study the nonlinear dynamics of Troesch's problem by designing the mathematical models of Morlet Wavelets Artificial Neural Networks (MW-ANNs) optimized with Genetic Algorithm (GA) integrated with sequential quadratic programming (SQP). The differential equation mathematical model for MW-ANNs are designed for Troesch's system by incorporating a windowing kernel based on Morlet Wavelets as an activation function and these networks are constructed to define a fitness function of Troesch's system in the mean squared sense. The unknown adjustable parameters of MW-ANNs are trained initially by an effective global search using GAs hybridized with SQP for rapid local refinement of the results. The proposed scheme is evaluated to solve the Troesch's problems for small and large values of the critical parameter in the system. Comparison of the proposed results with standard reference solutions of Adams method shows good agreement. Validation of accuracy and convergence of the proposed scheme is made using statistical analysis based on a sufficiently large number of independent runs, this is done in terms of performance measures of mean absolute deviation and root mean squared error. (C) 2017 Elsevier B.V. All rights reserved.
The random neural network (RNN) is a probabilitsic queueing theory-based model for artificial neural networks, and it requires the use of optimization algorithms for training. Commonly used gradient descent learning a...
详细信息
The random neural network (RNN) is a probabilitsic queueing theory-based model for artificial neural networks, and it requires the use of optimization algorithms for training. Commonly used gradient descent learning algorithms may reside in local minima, evolutionary algorithms can be also used to avoid local minima. Other techniques such as artificial bee colony (ABC), particle swarm optimization (PSO), and differential evolution algorithms also perform well in finding the global minimum but they converge slowly. The sequential quadratic programming (SQP) optimization algorithm can find the optimum neural network weights, but can also get stuck in local minima. We propose to overcome the shortcomings of these various approaches by using hybridized ABC/PSO and SQP. The resulting algorithm is shown to compare favorably with other known techniques for training the RNN. The results show that hybrid ABC learning with SQP outperforms other training algorithms in terms of mean-squared error and normalized root-mean-squared error.
A novel formulation of gradient-enhanced surrogate model, called weighted gradient-enhanced kriging, is proposed and used in combination with the cheap gradients obtained by the adjoint method to ameliorate the curse ...
详细信息
A novel formulation of gradient-enhanced surrogate model, called weighted gradient-enhanced kriging, is proposed and used in combination with the cheap gradients obtained by the adjoint method to ameliorate the curse of dimensionality. The core idea is to build a series of submodels with much smaller correlation matrices and then sum them up with appropriate weight coefficients, aiming to avoid the prohibitive cost associated with decomposing the large correlation matrix of a gradient-enhanced kriging. A self-contained derivation of the proposed method is presented, and then it is verified by surrogate modeling test cases. The present method is integrated into a surrogate-based optimizer and tested for design optimizations. It is further demonstrated for inverse design of a transonic wing, parameterized with a number of design variables in the range from 36 to 108, using Reynolds-averaged Navier-Stokes flow and adjoint solvers. It is observed that, for the wing design with 36 and 54 variables, the weighted and conventional gradient-enhanced kriging are comparable, and both are much more efficient than kriging without using any gradient. For the wing design with 72 and 108 variables, the cost of training a gradient-enhanced kriging increases rapidly and becomes prohibitive. In contrast, the cost of training a weighted gradient-enhanced kriging is kept in an acceptable level, which makes it more practical for higher-dimensional problems.
The layout design problem of a propulsion system is complex and time-consuming process. This is mainly due to geometrical and performance constraints and system requirements. In addition, layout design optimization of...
详细信息
The layout design problem of a propulsion system is complex and time-consuming process. This is mainly due to geometrical and performance constraints and system requirements. In addition, layout design optimization of a space propulsion system is non-linear, non-convex, and multimodal, which makes it difficult to implement conventional optimization methods to this class of design problems. This paper presents a hybrid optimization algorithm using genetic algorithm and sequential quadratic programming for optimal layout design of a space propulsion system. Previous research works mainly focused on the layout design components with constant parts. However, the approach adopted in this paper involves both variable mass component and hybrid optimization algorithm (GA-SQP) of a space propulsion system. The proposed hybrid optimization algorithm explores globally the design search space to locate the most promising region using genetic algorithm, whereas gradient-based sequential quadratic programming algorithm is used to reduce the computational time with a high degree of accuracy. The results obtained show that the proposed method provides an effective way of solving layout design optimization problem using both variable mass components method and a hybrid optimization for optimal layout design of a space propulsion system.
This paper develops a nonlinear model predictive controller for constrained attitude maneuvering of a fully actuated spacecraft with reaction wheels. In the proposed control algorithm, a Lie group variational integrat...
详细信息
This paper develops a nonlinear model predictive controller for constrained attitude maneuvering of a fully actuated spacecraft with reaction wheels. In the proposed control algorithm, a Lie group variational integrator is used as a predictive model. The nonlinear model predictive control problem is formulated in the form of a discrete-time optimal control problem over each prediction horizon, and a numerical solver is used to solve the necessary conditions for optimality for this discrete-time optimal control problem. The numerical solver uses the indirect single shooting method. The control constraints and exclusion zone constraints are handled using the exterior penalty function approach. Simulation results are presented and compared with the case of a fully actuated spacecraft without reaction wheels. The nonlinear model predictive controller is shown to provide a large domain of attraction.
暂无评论