Dynamic model is the basis of dynamic optimization in chemical process. In this paper a dynamic model for esterification section of poly(ethylene-terephthalate) (PET) was developed using segment method. Different from...
详细信息
In this paper, a soft sensor technique on the basis of support vector machines (SVM) was proposed to estimate the propylene concentration on the bottom of the distillation column, which took into consideration of the ...
详细信息
Moving object segmentation and marking object area is one of the key technologies of intelligent surveillance. In this paper, combining the background modeling in pixel level, the proposed algorithm presented gradient...
详细信息
This paper presents an approach to search robust optimal solutions with the concept of degree of robustness in multi-objective optimization problems. The definition of the degree of robustness is used in the calculati...
详细信息
This paper presents an approach to search robust optimal solutions with the concept of degree of robustness in multi-objective optimization problems. The definition of the degree of robustness is used in the calculation of the mean effective objective function(f eff (X)) and in the evolutionary process, degree of robustness is considered as a factor to select robust solutions which can meet the demand for better robustness. Some simulation results are shown to prove that this approach can control the distribution of objective value and help system improve robustness by finding solutions with better robustness. Also, the decision maker(DM) can modulate some robust parameters according to the actual robust demands which makes this approach have more practical significance.
With regards to the petrochemicalprocesses with various operating states and dynamic performance which will affect estimation precision for the static soft sensor, a time series soft sensor model which uses the time ...
详细信息
With regards to the petrochemicalprocesses with various operating states and dynamic performance which will affect estimation precision for the static soft sensor, a time series soft sensor model which uses the time series of process variables to estimate the dynamic performance of quality variable was proposed. Meanwhile, the integrated Adaboost learning algorithm is introduced. With the help of this method, training samples and modeling for several times, according to the modeling error to renew the next sample data, in order to obtain a series of different basic models. Every basic model will be weighted in the last step; as a result, a more precise combined LS-SVM model will be established. According to the prediction of benzene content of column reactor in the azeotropic rectification tower, the effectiveness of the method is demonstrated.
In petrochemical field, the process simulation for distillation is an important task. The key parameter in the distillation process simulation is the tray efficiency, which can not be obtained easily. Thus the determi...
详细信息
PSO has been proved as an effective supervised learning system in recent years, but it's not an effective method for incremental learning problems. Aiming at the incremental learning target for classification, a h...
详细信息
PSO has been proved as an effective supervised learning system in recent years, but it's not an effective method for incremental learning problems. Aiming at the incremental learning target for classification, a hybrid algorithm of Particle Swarm optimization (PSO) and Artificial Immune System (AIS) called Immune based PSO (IPSO) is presented in this paper. IPSO inherits the incremental learning ability of AIS. In IPSO, training data is presented to the algorithm one by one, and the training proceed is a one-shot incremental algorithm. Besides, the swarm does not converge to a single solution;instead, each particle is a part of the classifier, and the whole memory population is taken as the integral classifier to the problem. Compared the results of standard PSO and IPSO in several benchmark problems from the UCI data sets, we found that IPSO achieved a better classification accuracy than standard PSO in most cases. It is also competitive with some of the algorithms most commonly used for classification.
A comparative study of θ-PSO and its improved model with partial particles randomization strategy on their abilities of tracking extrema in dynamic environments was carried out in our earlier work. And the results sh...
详细信息
A comparative study of θ-PSO and its improved model with partial particles randomization strategy on their abilities of tracking extrema in dynamic environments was carried out in our earlier work. And the results shown that θ-PSO has better performance in dynamic optimization than standard PSO. In this paper, an improved θ-PSO with memory recall and varying scale randomization strategy (θ-PSO-MR) is put forward. The eligible memory particles are recalled when the landscape changes. And the vary scale randomization is introduced through the evolution to maintain the swarm diversity. The offline error in the non-trivial multimodal dynamic functions MPB indicates that this improved θ-PSO deals well with the complex dynamic tracking and optimization. And in some cases, θ-PSO-MR outperforms θ-PSO-Rn for the introduction of memory recall.
The previous studies on Human-machine Interface (HMI) based on surface electromyogram (SEMG) control seldom considered individual difference. In this paper, we proposed a novel method to distinguish the handedness of ...
详细信息
The previous studies on Human-machine Interface (HMI) based on surface electromyogram (SEMG) control seldom considered individual difference. In this paper, we proposed a novel method to distinguish the handedness of subjects, and extract the real-time control signals from SEMG. SEMG signals recorded at left calf, right calf, left shoulder and right shoulder were analyzed. The instantaneous power of SEMG signals were calculated based on Filter technique and short-time Fourier transformation (STFT).The handedness was discriminated to determine the proper threshold for different subjects. The real-time control signals were generated automatically by comparing the instantaneous power and the thresholds preset.
In order to extract from the video sequence in a complete and consistent moving target, a novel algorithm for video object segmentation based on improved particle swarm optimization (IPSO) is presented. The algorithm ...
详细信息
In order to extract from the video sequence in a complete and consistent moving target, a novel algorithm for video object segmentation based on improved particle swarm optimization (IPSO) is presented. The algorithm fuses brightness segmentation and color information at `region level', as to make up for conventional `pixel level' approaches. The IPSO is taken into account for spatial segmentation of the video frame, which combines the mixture Gaussian model of temporal framework in achieving better segmentation. Adapting to the real-time video surveillance, the proposed algorithm can speed up the process of image segmentation, and make background modeling accurately to update. Comparisons were performed with other method that the proposed algorithm can detect intact moving objects even when objects appear and disappear suddenly. The experiment across different types of video shows the efficiency and stability of video object segmentation by the novel approach.
暂无评论