A navigation system based on P300 brain computer interface system (BCIs) and steady-state visual evoked potentials (SSVEP) BCIs respectively was designed in this paper. In the experiment, subjects were required to mov...
详细信息
A navigation system based on P300 brain computer interface system (BCIs) and steady-state visual evoked potentials (SSVEP) BCIs respectively was designed in this paper. In the experiment, subjects were required to move a ball on the computer screen to the target position by P300 BCI system and SSVEP BCI system. Bayesian linear discriminant analysis (BLDA) is used to detect P300 potentials and canonical correlation analysis (CCA) is used to detect SSVEP. The aim of this paper is to show the drawbacks and advantages of these two BCIs, when they were used in navigation task. The online experimental results show that P300 BCIs is more robust for subjects compared to SSVEP BCIs.
For complex industrial processes with multiple operating conditions, it is important to develop effective monitoring algorithms to ensure the safety of the producing processes. This paper proposes a novel monitoring s...
详细信息
For complex industrial processes with multiple operating conditions, it is important to develop effective monitoring algorithms to ensure the safety of the producing processes. This paper proposes a novel monitoring strategy based on fuzzy c-means (FCM). First, the high dimensional historical data are transferred to a low dimensional subspace space by locality preserving projection (LPP). Then the scores in the novel subspace are classified into several overlapped clusters, each representing an operating mode. After that, the distance statistics of each cluster are integrated though the membership values into a novel BID monitoring index. The efficiency and effectiveness of the proposed method are validated though the Tennessee Eastman (TE) benchmark process.
Semi-supervised dimensionality reduction is an important research area for data classification. A new linear dimensionality reduction approach, global inference preserving projection （GIPP）, was proposed to perform ...
详细信息
Semi-supervised dimensionality reduction is an important research area for data classification. A new linear dimensionality reduction approach, global inference preserving projection （GIPP）, was proposed to perform classification task in semi-supervised case. GIPP provided a global structure that utilized the underlying discriminative knowledge of unlabeled samples. It used path-based dissimilarity measurement to infer the class label information for unlabeled samples and transformd the diseriminant algorithm into a generalized eigenequation problem. Experimental results demonstrate the effectiveness of the proposed approach.
In recent years, immune genetic algorithm (IGA) is gaining popularity for finding the optimal solution for non-linear optimization problems in many engineering applications. However, IGA with deterministic mutation fa...
详细信息
In recent years, immune genetic algorithm (IGA) is gaining popularity for finding the optimal solution for non-linear optimization problems in many engineering applications. However, IGA with deterministic mutation factor suffers from the problem of premature convergence. In this study, 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 improve 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 converges quickly to the global optimum and overcomes premature problem. This algorithm is applied to optimize a feed forward neural network to measure the content of products in the combustion side reaction of p-xylene oxidation, and satisfactory results are obtained.
With a multitude of reaction pathways, poly (ethylene-terephthalate) (PET) polymerization of industrial practice is complex, and the quality of PET is normally described in terms of several experimentally measured ind...
详细信息
A discrete artificial bee colony algorithm is proposed for solving the blocking flow shop scheduling problem with total flow time criterion. Firstly, the solution in the algorithm is represented as job permutation. Se...
详细信息
A discrete artificial bee colony algorithm is proposed for solving the blocking flow shop scheduling problem with total flow time criterion. Firstly, the solution in the algorithm is represented as job permutation. Secondly, an initialization scheme based on a variant of the NEH (Nawaz-Enscore-Ham) heuristic and a local search is designed to construct the initial population with both quality and diversity. Thirdly, based on the idea of iterated greedy algorithm, some newly designed schemes for employed bee, onlooker bee and scout bee are presented. The performance of the proposed algorithm is tested on the well-known Taillard benchmark set, and the computational results demonstrate the effectiveness of the discrete artificial bee colony algorithm. In addition, the best known solutions of the benchmark set are provided for the blocking flow shop scheduling problem with total flow time criterion.
This paper is concerned with the problem of quantized H-infinity control for networked control systems (NCSs) with time-varying delay and multiple packet dropouts. The packet dropouts in both the measurement channel a...
详细信息
This paper is concerned with the problem of quantized H-infinity control for networked control systems (NCSs) with time-varying delay and multiple packet dropouts. The packet dropouts in both the measurement channel and the control channel are considered simultaneously, and are modeled as stochastic variables with Bernoulli random binary distribution. Both the control input and measurement output are quantized before transmission and the quantization errors are described as sector-bound uncertainties. Sufficient conditions for the existence of an observer-based, delay-dependent controller are developed to ensure the exponentially mean-square stability of the closed-loop system and to achieve the optimal H-infinity disturbance attenuation. A numerical example is given to illustrate the effectiveness of the proposed method.
Particle swarm optimization methods for optimization problems tend to search premature solutions. This paper presents an improved particle swarm optimization algorithm merging chaotic and harmony searches. The chaos p...
详细信息
Particle swarm optimization methods for optimization problems tend to search premature solutions. This paper presents an improved particle swarm optimization algorithm merging chaotic and harmony searches. The chaos particle swarm optimization method is stable, robust and adaptable. The harmony search algorithm is a meta heuristic algorithm for simulating band tuning to obtain an optimal harmonized process with a global search. Results for four standard test functions show that this chaos particle swarm optimization algorithm with a harmony search (CPSO-HS) can jump out of local optimums with fast convergence and good stability. This algorithm has been successfully applied to parameter estimates for a heavy oil thermal cracking model.
In ethylene plant, charge gas compressor is one of the most important units. The charge gas compressor usually is a centrifugal compressor. The information of centrifugal compressors’ performance is not applicable to...
详细信息
In ethylene plant, charge gas compressor is one of the most important units. The charge gas compressor usually is a centrifugal compressor. The information of centrifugal compressors’ performance is not applicable to all of the conditions, which restricts the operation optimization of the compressor. To solve this problem, a tri-layer BP neural network was introduced to model the performance of compressor by using the data provided by manufacturers. The input data of the model in other conditions should be corrected according to the similar theory. At last, the method was used to optimize the system of charge gas compressor by embedding compressor performance model into the ASPEN PLUS model of compressor. The result shows that it is an effective method to optimize the compressor system.
A double-layer optimization algorithm (DLOA) was proposed to solve the minimum time dynamic optimization problem. The first step of DLOA was to discrete time region and control region. The inner optimization is to con...
详细信息
A double-layer optimization algorithm (DLOA) was proposed to solve the minimum time dynamic optimization problem. The first step of DLOA was to discrete time region and control region. The inner optimization is to construct optimal control problem with free final states. Differential evolution algorithm is used to find the optimal solution in given terminal time, then the optimization results was compared with the threshold set. In the outer, DLOA calculated the time range of next iteration according to the inner calculation. When applied to typical minimum time dynamic optimization problem, DLOA demonstrated a competitive optimal searching ability and more accurate optimization results. DLOA could solve the optimization problem with local optimum and applied to models without gradient information.
暂无评论