Search

Advanced modeling and optimization techniques are imperative today to deal with complex machining processes like electric discharge machining (EDM). In the present research, Titanium alloy has been machined by considering different electrical input parameters to evaluate one of the important surface integrity (SI) parameter that is surface roughness Ra. Firstly, the response surface methodology (RSM) has been adopted for experimental design and for generating training data set. The artificial neural network (ANN) model has been developed and optimized for Ra with the same training data set. Finally, an adaptive neuro-fuzzy inference system (ANFIS) model has been developed for Ra. Optimization of the developed ANFIS model has been done by applying the latest optimization techniques Rao algorithm and the Jaya algorithm. Different statistical parameters such as the mean square error (MSE), the mean absolute error (MAE), the root mean square error (RMSE), the mean bias error (MBE) and the mean absolute percentage error (MAPE) elucidate that the ANFIS model is better than the ANN model. Both the optimization algorithms results in considerable improvement in the SI of the machined surface. Comparing the Rao algorithm and Jaya algorithm for optimization, it has been found that the Rao algorithm performs better than the Jaya algorithm. [ABSTRACT FROM AUTHOR]

In this paper, a cumulative-sum-based fault detection algorithm is proposed for the power system relaying application. Literature suggests the successful application of this method to process control systems where the deviation of parameters is tracked to indicate any abnormal conditions. The effectiveness of the algorithm is found to be better than the traditional methods in the presence of noise, system frequency deviation, and other uncertainties. It is also not affected by load change in a system. Above all, it provides relatively higher index values without compromising detection speed. [ABSTRACT FROM AUTHOR]

This paper presents the generalized theory and an efficient graph-based technique for the calculation and representation of coefficients of multivariate canonic polynomials over arbitrary finite fields in any polarity. The technique presented for computing coefficients is unlike polynomial interpolation or matrix-based techniques and takes into consideration efficient graph-based forms which can be available as an existing resource during synthesis, verification, or simulation of digital systems. Techniques for optimization of the graph-based forms for representing the coefficients are also presented. The efficiency of the algorithm increases for larger fields. As a test case, the proposed technique has been applied to benchmark circuits over GF(2m). The experimental results show that the proposed technique can significantly speed up execution time. [ABSTRACT FROM AUTHOR]

Frequency is an important parameter in power system monitoring, control, and protection. A least mean square (LMS) algorithm in complex form is presented in this paper to estimate power system frequency where the formulated structure is very simple. The three-phase voltages are converted to a complex form for processing by the proposed algorithm. To enhance the convergence characteristic of the complex form of the LMS algorithm, a variable adaptation step-size is incorporated. The performance of the new algorithm is studied through simulations at different situations of the power system. [ABSTRACT FROM AUTHOR]

This letter proposes the application of a modular neural network as a mechanism to discriminate the direction of faults for transmission line protection. The modular neural network approach solves a relatively complex problem by decomposing it into simpler subtasks that are easier to manage and then assembles the solution from the results of the subtasks. In addition to the obvious advantages of a neural network as a fault classifier, incorporation of modularity to the network structure provides more important positive attributes like model complexity reduction, better learning capability, etc. The modular neural network concept has been utilized successfully to develop a directional relay algorithm for a transmission system and subsequently implemented on a DSP TMS320F243 EVM-board. [ABSTRACT FROM AUTHOR]