Ognjen Kuljača

Design and implementation of industrial neural network controller using backstepping

In this paper, a novel neural network (NN) backstepping controller is modified for application to an industrial motor drive system. A control system structure and NN tuning algorithms are presented that are shown to guarantee stability and performance of the closed-loop system. The NN backstepping controller is implemented on an actual motor drive system using a two-PC control system developed at The University of Texas at Arlington. The implementation results show that the NN backstepping controller is highly effective in controlling the industrial motor drive system. It is also shown that the NN controller gives better results on actual systems than a standard backstepping controller developed assuming full knowledge of the dynamics. Moreover, the NN controller does not require the linear-in-the-parameters assumption or the computation of regression matrices required by standard backstepping.

Describing Function Recording with Simulink and MATLAB

Describing function is an equivalent gain of nonlinear element, defined by the harmonic linearization method of nonlinear static characteristic (Novogranov, 1986, Slotine and Li, 1991, Schwarz and Gran, 2001, Vukic et al. 2003 and many others). It is a known method of analysis and synthesis when nonlinear system can be decoupled into linear and nonlinear parts (Fig. 1). If the linear part of the system has the characteristics of low-pass filter and if we apply periodical signal to the system, output signal will have the same base frequency as input signal with damped higher frequencies.

Marine Diesel Engine Faults Diagnosis Based on Observed Symptoms and Expert Knowledge

Abstract The paper deals with two methods to fault detection and isolation in ships propulsion diesel engine. The first diagnosis method is based on real-time diagnostic signals i.e. symptoms and their relation to faults in an extended form with tracking times of symptoms occurrence. The effectiveness of this method has been evaluated with concurrently simulating two very similar engine cylinder faults. The second diagnosis method introduced in the paper based on human expert heuristic knowledge showed very good result in diagnosis the same engine fault. In both simulation examples, in a certain way, a form of integration of these two methods is used. The hybrid method based on good monitoring system and heuristic knowledge base could become more attractive in marine applications.