Search results
1 – 10 of 47Yangtian Li, Haibin Li and Guangmei Wei
To present the models with many model parameters by polynomial chaos expansion (PCE), and improve the accuracy, this paper aims to present dimension-adaptive algorithm-based PCE…
Abstract
Purpose
To present the models with many model parameters by polynomial chaos expansion (PCE), and improve the accuracy, this paper aims to present dimension-adaptive algorithm-based PCE technique and verify the feasibility of the proposed method through taking solid rocket motor ignition under low temperature as an example.
Design/methodology/approach
The main approaches of this work are as follows: presenting a two-step dimension-adaptive algorithm; through computing the PCE coefficients using dimension-adaptive algorithm, improving the accuracy of PCE surrogate model obtained; and applying the proposed method to uncertainty quantification (UQ) of solid rocket motor ignition under low temperature to verify the feasibility of the proposed method.
Findings
The result indicates that by means of comparing with some conventional non-invasive method, the proposed method is able to raise the computational accuracy significantly on condition of meeting the efficiency requirement.
Originality/value
This paper proposes an approach in which the optimal non-uniform grid that can avoid the issue of overfitting or underfitting is obtained.
Details
Keywords
Minfen Shen, Jialiang Chen and Bin Li
The purpose of this paper is to present a novel algorithm for image inpainting, which has been widely used for removing unwanted objects from images or reconstructing damaged…
Abstract
Purpose
The purpose of this paper is to present a novel algorithm for image inpainting, which has been widely used for removing unwanted objects from images or reconstructing damaged photographs.
Design/methodology/approach
An image piecewise inpainting technique based on radial basis function (RBF) is used to transform the 2D image inpainting problem into 3D implicit surface reconstruction problem. And a RBF center reduction method is proposed. By RBF resampling, the algorithm can nicely fix the damaged image or remove specific objects.
Findings
Experimental results show that the proposed algorithms can prevent the edge blur caused by the isotropic character of RBF, and effectively reduce the RBF centers without a loss in accuracy.
Originality/value
The proposed inpainting approach is interesting for its combination of RBF method and region segmentation that can handle the restoring of high‐variation areas.
Details
Keywords
Zhihui Gao, Chao Yun and Yushu Bian
The purpose of this paper is to examine a new idea of vibration control which minimizes joint‐torques and suppresses vibration of the flexible redundant manipulator.
Abstract
Purpose
The purpose of this paper is to examine a new idea of vibration control which minimizes joint‐torques and suppresses vibration of the flexible redundant manipulator.
Design/methodology/approach
Using the kinematics redundancy feature of the flexible redundant manipulator, the self‐motion in the joint space can be properly chosen to both suppress vibration and minimize joint‐torques.
Findings
The study shows that the flexible redundant manipulator still has the second optimization feature on the premise of vibration suppression. The second optimization feature can be used to minimize joint‐torques on the premise of vibration suppression.
Research limitations/implications
To a flexible redundant manipulator, its joint‐torques and vibration can be reduced simultaneously via its kinematics redundancy feature.
Practical implications
The method and algorithm discussed in the paper can be used to minimize joint‐torques and suppress vibration for the flexible redundant manipulator.
Originality/value
The paper contributes to the study on improving dynamic performance of the flexible redundant manipulator via its kinematics redundancy feature. The second optimization capability of the flexible redundant manipulator is discovered and used to both minimize joint‐torques and suppress vibration.
Details
Keywords
Abstract
Purpose
Nowadays, automotive engines are controlled by electronic control units (ECUs), and the engine idle speed performance is significantly affected by the setup of control parameters in the ECU. The engine ECU tune‐up is done empirically through tests on a dynamometer (dyno). In this way, a lot of time, fuel and human resources are consumed, while the optimal control parameters may not be obtained. The purpose of this paper is to propose a novel ECU setup optimization approach for engine idle speed control.
Design/methodology/approach
In the first phase of the approach, Latin hypercube sampling (LHS) and a multi‐input/output least squares support vector machine (LS‐SVM) is proposed to build up an engine idle speed model based on dyno test data, and then a genetic algorithm (GA) is applied to obtain optimal ECU setting automatically subject to various user‐defined constraints.
Findings
The study shows that the predicted results using the estimated model from LS‐SVM are in good agreement with the actual test results. Moreover, the optimization results show a significant improvement on idle speed performance in a test engine.
Practical implications
As the methodology is generic it can be applied to different vehicle control optimization problems.
Originality/value
The research is the first attempt to integrate a couple of paradigms (LHS, multi‐input/output LS‐SVM and GA) into a general framework for constrained multivariable optimization problems under insufficient system information. The proposed multi‐input/output LS‐SVM for modelling of multi‐input/output systems is original, because the traditional LS‐SVM modelling approach is suitable for multi‐input, but single output systems. Finally, this is the first use of the novel integrated framework for automotive engine idle‐speed control optimization.
Details
Keywords
Yunfeng Zhou and Feng Wan
The purpose of this paper is to present a neural network approach to control performance assessment.
Abstract
Purpose
The purpose of this paper is to present a neural network approach to control performance assessment.
Design/methodology/approach
The performance index under study is based on the minimum variance control benchmark, a radial basis function network (RBFN) is used as the pre‐whitening filter to estimate the white noise sequence, and a stable filtering and correlation analysis method is adopted to calculate the performance index by estimating innovations sequence using the RBFN pre‐whitening filter. The new approach is compared with the auto‐regressive moving average model and the Laguerre model methods, for both linear and nonlinear cases.
Findings
Simulation results show that the RBFN approach works satisfactorily for both linear and nonlinear examples. In particular, the proposed scheme shows merits in assessing controller performance for nonlinear systems and surpasses the Laguerre model method in parameter selection.
Originality/value
A RBFN approach is proposed for control performance assessment. This new approach, in comparison with some well‐known methods, provides satisfactory performance and potentials for both linear and nonlinear cases.
Details
Keywords
Lei Yang, James Dankert and Jennie Si
The purpose of this paper is to develop a mathematical framework to address some algorithmic features of approximate dynamic programming (ADP) by using an average cost formulation…
Abstract
Purpose
The purpose of this paper is to develop a mathematical framework to address some algorithmic features of approximate dynamic programming (ADP) by using an average cost formulation based on the concepts of differential costs and performance gradients. Under such a framework, a modified value iteration algorithm is developed that is easy to implement, in the mean time it can address a class of partially observable Markov decision processes (POMDP).
Design/methodology/approach
Gradient‐based policy iteration (GBPI) is a top‐down, system‐theoretic approach to dynamic optimization with performance guarantees. In this paper, a bottom‐up, algorithmic view is provided to complement the original high‐level development of GBPI. A modified value iteration is introduced, which can provide solutions to the same type of POMDP problems dealt with by GBPI. Numerical simulations are conducted to include a queuing problem and a maze problem to illustrate and verify features of the proposed algorithms as compared to GBPI.
Findings
The direct connection between GBPI and policy iteration is shown under a Markov decision process formulation. As such, additional analytical insights were gained on GBPI. Furthermore, motivated by this analytical framework, the authors propose a modified value iteration as an alternative to addressing the same POMDP problem handled by GBPI.
Originality/value
Several important insights are gained from the analytical framework, which motivate the development of both algorithms. Built on this paradigm, new ADP learning algorithms can be developed, in this case, the modified value iteration, to address a broader class of problems, the POMDP. In addition, it is now possible to provide ADP algorithms with a gradient perspective. Inspired by the fundamental understanding of learning and optimization problems under the gradient‐based framework, additional new insight may be developed for bottom‐up type of algorithms with performance guarantees.
Details
Keywords
The purpose of this paper is to provide a review of the issues related to cluster analysis, one of the most important and primitive activities of human beings, and of the advances…
Abstract
Purpose
The purpose of this paper is to provide a review of the issues related to cluster analysis, one of the most important and primitive activities of human beings, and of the advances made in recent years.
Design/methodology/approach
The paper investigates the clustering algorithms rooted in machine learning, computer science, statistics, and computational intelligence.
Findings
The paper reviews the basic issues of cluster analysis and discusses the recent advances of clustering algorithms in scalability, robustness, visualization, irregular cluster shape detection, and so on.
Originality/value
The paper presents a comprehensive and systematic survey of cluster analysis and emphasizes its recent efforts in order to meet the challenges caused by the glut of complicated data from a wide variety of communities.
Details
Keywords
Robert Reynolds and Mostafa Ali
The purpose of this paper is to introduce the notion of a social fabric (SF) in which the expression of knowledge sources (KS) in cultural algorithms (CA) can be distributed…
Abstract
Purpose
The purpose of this paper is to introduce the notion of a social fabric (SF) in which the expression of knowledge sources (KS) in cultural algorithms (CA) can be distributed through the population. The SF influence function is applied to the solution of selected complex engineering problems and it is shown that different parameter combinations for the SF influence function can affect the rate of solution. This enhanced approach is compared with previous approaches.
Design/methodology/approach
KS are allowed to influence individuals through a network. From a theoretical perspective, individuals in the real world are viewed as participating in a variety of different networks. Several layers of such networks can be supported within a population. The interplay of these various network computations is designated as the “social fabric.” Using this new influence function, when an individual is to be modified, one KS is selected to perform the modification at each generation. The selection process is done via weaving the SF, hence changing the number of individuals that follow a certain KS.
Findings
Simulation experiments show that the choice of influence function has a great impact on the problem‐solving phase. For some problems, a social network is not necessary to produce frequent convergence to an optimum. On the other hand, it is observed that the social network can help to focus search by allowing a KS to influence groups of individuals within a network rather than single unrelated individuals. The new approach shows a more focused convergence to optimal values in complex engineering problems with numerous constraints. Also, it is suggested that a SF configuration can be robust in the sense that a configuration that works well for one problem can also perform well in a more complex but unrelated problem. This suggests that a configuration can be evolved to solve suites of problems.
Originality/value
The introduced approach is interesting for the optimization of problems of a non‐linear complex nature.
Details
Keywords
Michael A. Pratt, Sharath Konda and Chee‐Hung Henry Chu
The purpose of this paper is to present research results in analyzing image contents to improve the accuracy of using an artificial neural network (ANN) to detect embedded data in…
Abstract
Purpose
The purpose of this paper is to present research results in analyzing image contents to improve the accuracy of using an artificial neural network (ANN) to detect embedded data in a digital image.
Design/methodology/approach
A texture measure based on the MPEG‐7 texture descriptor is applied to assess the local texture amount. Those image blocks with high texture are masked out and the remaining blocks with low texture are used to derive features for an ANN to classify an image as embedded or clear. The high‐texture blocks are not discarded and can be tested independently for embedded data.
Findings
By masking out the high‐texture image blocks, an ANN has improved detection performance especially when the original embedding rate is low. Bypassing the low‐texture image blocks do not pay off for a steganographer because the effective embedding rate in the high‐texture blocks is driven higher.
Research limitations/implications
Hidden data detectors should take the image content into account in order to improve detection performance.
Practical implications
The results can be integrated into a steganalytic system.
Originality/value
This paper presents evidence that image texture affects steganalytic performance and proposes a solution that incorporates texture that has improved detection performance.
Details
Keywords
Qiang Xue and Duan Haibin
The purpose of this paper is to propose a new approach for aerodynamic parameter identification of hypersonic vehicles, which is based on Pigeon-inspired optimization (PIO…
Abstract
Purpose
The purpose of this paper is to propose a new approach for aerodynamic parameter identification of hypersonic vehicles, which is based on Pigeon-inspired optimization (PIO) algorithm, with the objective of overcoming the disadvantages of traditional methods based on gradient such as New Raphson method, especially in noisy environment.
Design/methodology/approach
The model of hypersonic vehicles and PIO algorithm is established for aerodynamic parameter identification. Using the idea, identification problem will be converted into the optimization problem.
Findings
A new swarm optimization method, PIO algorithm is applied in this identification process. Experimental results demonstrated the robustness and effectiveness of the proposed method: it can guarantee accurate identification results in noisy environment without fussy calculation of sensitivity.
Practical implications
The new method developed in this paper can be easily applied to solve complex optimization problems when some traditional method is failed, and can afford the accurate hypersonic parameter for control rate design of hypersonic vehicles.
Originality/value
In this paper, the authors converted this identification problem into the optimization problem using the new swarm optimization method – PIO. This new approach is proved to be reasonable through simulation.
Details