Controlling disturbances of islanding in a gas power plant via fuzzy-based neural network approach with a focus on load-shedding system

Abstract

In a number of power plants such as the South Pars Gas Company, efficient control performance regarding the turbine generator is always needed to avoid facing disturbances of islanding in the supply of power, at each instance of time. It is particularly important to deal with through state-of-the-art techniques, due to the fact that the separation of the electrical grid may increase or reduce the speed of the above-referenced turbine generator and correspondingly the frequency, in its permitted range, may be deviated to stop power generation, abruptly. With this key goal, a set of control strategies through the representation of the gas turbine via Rowen is proposed in the present research. In a word, there are some classical and intelligence-based control approaches to cope with the disturbance of islanding with a focus on load-shedding system. In reality, the proposed investigation is mainly concentrating on the fuzzy-based neural network control approach to cope with the turbulence of frequency deviation. The main contribution made in this research is to deal with gas turbine model in association with generator in conjunction with load-shedding system, while intelligence-based techniques considering fuzzy, neural network and genetic algorithm are synchronously established to design the control strategy with high accuracy. In the sequel, the effectiveness of the proposed intelligence-based control approach is verified, while the classical proportionalintegral-derivative control approach via the Ziegler-Nichols and also the simulated annealing tuning processes are taken as the benchmarks.

Enhancing the accuracy and precision of forecasting the productivity of a factory: a fuzzified feedforward neural network approach

“…In the proposed FFNN approach, an FFNN [1,3,27] is constructed to forecast the productivity of a factory. The training of the FFNN is divided into three steps.…”

Appropriate Feature Set and Window Parameters Selection for Efficient Motion Intent Characterization towards Intelligently Smart EMG-PR System

“…Meanwhile, five-fold cross validation technique was employed for the partitioning of the extracted feature matrix into training and testing sets. The rationale behind considering these classification schemes is that their performances are relatively good, especially when considering multi-class problems [1,10,36]. Therefore, we built an SVM classifiers driven by radial basis function, and compared its classification performance with that of the LDA classifiers.…”

“…Meanwhile, the LDA classification scheme runs much faster than its SVM counterpart. Also due to its relatively simple structure, and easy implemented in real-time, it was adopted in the current study [6,8,10].…”

“…Afterwards, the deciphered movement intents are coded into control commands that drives the intelligently smart prostheses in a way similar to the natural human arm [6][7][8][9][10]. The pattern recognition based control strategy consist of sequentially connected phases in which the machine learning algorithm and feature extraction phases are well-thought-out as important with the latter being the most significant.…”

High efficiency fault-detection and fault-tolerant control approach in Tennessee Eastman process via fuzzy-based neural network representation

“…The TE process is unstable in open-loop mode and the first limitation that causes this instability is exceeding from reactor allowed pressure range. Realized control structure should be able to save process in operational conditions and can put process variables in its proposed constraints range [4][5][6][7][8][9][10][11][12][13][14][15][16][17]. Regarding the proposed research novelty and its innovation, it can be expressed in three lines.…”