In order to reduce the computation of complex problems, a new surrogate-assisted estimation of distribution algorithm with Gaussian process was proposed. Coevolution was used in dual populations which evolved in paral...
In order to reduce the computation of complex problems, a new surrogate-assisted estimation of distribution algorithm with Gaussian process was proposed. Coevolution was used in dual populations which evolved in parallel. The search space was projected into multiple subspaces and searched by sub-populations. Also, the whole space was exploited by the other population which exchanges information with the sub-populations. In order to make the evolutionary course efficient, multivariate Gaussian model and Gaussian mixture model were used in both populations separately to estimate the distribution of individuals and reproduce new generations. For the surrogate model, Gaussian process was combined with the algorithm which predicted variance of the predictions. The results on six benchmark functions show that the new algorithm performs better than other surrogate-model based algorithms and the computation complexity is only 10% of the original estimation of distribution algorithm.
In recent years, immune genetic algorithm (IGA) is gaining popularity for finding the optimal solution of non-linear optimization problems encountered in many engineering applications. In IGA, the mutation factor valu...
详细信息
In recent years, immune genetic algorithm (IGA) is gaining popularity for finding the optimal solution of non-linear optimization problems encountered in many engineering applications. In IGA, the mutation factor values are either fixed or change together according to a function of the individual’s current generation number during all the search process. However, IGA with deterministic mutation factor suffers from the problem of premature convergence. A modified self-adaptive immune genetic algorithm (MSIGA) with two memory bases, in which immune concepts are applied to determine the mutation parameters, is proposed to strengthen the searching ability of the algorithm and maintain population diversity. Performance comparisons with other well-known population-based iterative algorithms show that the proposed method can quickly converge to the global optimum and overcome premature problem. Then, this algorithm is applied to optimize a feed forward neural network to measure the content of products in the combust ion side reaction of p-xylene oxidation, and satisfactory results are obtained.
States of traffic situations can be classified into peak and nonpeak periods. The complexity of peak traffic brings more difficulty to forecasting models. Travel time index (TTI) is a fundamental measure in transpor...
详细信息
States of traffic situations can be classified into peak and nonpeak periods. The complexity of peak traffic brings more difficulty to forecasting models. Travel time index (TTI) is a fundamental measure in transportation. How to master the characteristics and provide accurate real-time forecasts is essential to intelligent transportation systems (ITS). Cooperating with state space approach, least squares support vector machines (LS- SVMs) are investigated to solve such a practical problem in this paper. To the best of our knowledge, it is the first time to apply the technique and analyze the forecast performance in the domain. For comparison purpose, other two nonparametric predictors are selected because of their effectiveness proved in past research. Having good generalization ability and guaranteeing global minima, LS-SVMs perform better than the others. Providing sufficient improvement in stability and robustness reveals that the approach is practically promising.
Considering that outliers can disrupt the correlation structure of least square support vector machine (LS-SVM), and that the parameters of LS-SVM play an important role in the performance, a novel weighted least squa...
详细信息
Considering that outliers can disrupt the correlation structure of least square support vector machine (LS-SVM), and that the parameters of LS-SVM play an important role in the performance, a novel weighted least square support vector machine integrated with parameter optimization is proposed to obtain the optimal parameters and to eliminate the effect of outliers. Several LS-SVM variants are applied in simulation experimentation and chemicalprocess respectively to demonstrate the satisfactory performance of the proposed method.
Increasingly in practical applications, nonlinearity, non-Gaussianity, and constraint are considered when dealing with state estimation problems. This paper proposes a novel constrained particle filter (PF) approach f...
详细信息
The steam system is an important part of chemical utility system, but there are widespread phenomenon about lack of testing information, energy consumption configuration depend on given experience and wasting energy. ...
详细信息
The steam system is an important part of chemical utility system, but there are widespread phenomenon about lack of testing information, energy consumption configuration depend on given experience and wasting energy. So this paper puts forward a method about the steam pipe network system's status identification of different energy consumption based on the steam pipe network's characteristics of complex structure, much steam equipment, lack of testing information and difficult to build accurate mathematical model. The method based on affinity propagation clustering that can solve big set of data's clustering problem quickly and effective. As it is hard to find preference parameters and damping factor, this paper uses PSO to find the most optimal parameters in order to achieve the best clustering effect. This method is applied test both in classic data set and the steam pipe network of ethylene plant's status identification, the results show the effectiveness of this method.
Since the activity and selectivity of acetylene hydrogenation catalyst change with time, the operating parameters need to be changed to maximize the profit. Therefore, we collected the industrial process data and esti...
详细信息
The homogeneous metal/bromide-catalyzed aerobic oxidation of p-xylene with different catalyst concentrations was carried out, and the formation kinetics of COx including CO2 and CO was measured. The simplified element...
详细信息
This paper considers the problem of sliding mode control (SMC) for a class of linear uncertain switched systems. In the controlled systems, it is not required that each subsystem model shares the same input channel, w...
详细信息
ISBN:
(纸本)9781467325813
This paper considers the problem of sliding mode control (SMC) for a class of linear uncertain switched systems. In the controlled systems, it is not required that each subsystem model shares the same input channel, which is usually assumed in some existing works. By means of a transformation on input matrices, a single integral sliding surface is designed and the switching signals depending on the average dwell time are given. It is shown that the designed sliding mode controller can guarantee the reachability of the sliding surface. Moreover, the sliding motion on the specified integral sliding surface is exponentially stable under the designed switching signal. The efficiency of the proposed method is demonstrated by a simulation.
This paper is concerned with the problem of quantized H∞ control for networked control systems (NCSs) with multiple packet dropouts. A new model is given to describe the systems with the input and output quantization...
详细信息
This paper is concerned with the problem of quantized H∞ control for networked control systems (NCSs) with multiple packet dropouts. A new model is given to describe the systems with the input and output quantization and multiple packet dropouts. Both the multiple measurement and control packet dropouts are described by two binary switching sequences that obey certain conditional probability distribution. An observer-based controller is designed to ensure the exponentially mean-square stable of the closed-loop system and to guarantee an optimal H∞ disturbance attenuation level. Finally, a simulation example is given to demonstrate the effectiveness of the proposed method.
暂无评论