Adaptive Neuro-fuzzy Architecture Research Articles

Modeling of biotechnological objects

The article discusses the system of modeling biotechnological objects and biogas production in the process of fermentation of various agricultural wastes. The complexity of automation of biotechnological processes, which consists in the lack of sufficient knowledge about the phenomena associated with the process of fermentation and the synthesis of target materials, is shown. Solutions to control problems using intelligent methods, intelligent control systems, based on fuzzy logic and on the basis of on the basis of neural network technologies, which have proven themselves in the control of complex objects with parameters that vary widely, as well as the analysis of algorithms for the operation of programmable logic controllers that perform the functions of regulators in the systems of operational control of complex processes, adaptive neuro-fuzzy architecture. Distributed in management decision support systems, it is made in the form of a six-layer neural structure, i.e. systems with neuro-fuzzy regulators, are able to largely meet the modern requirements of the designed systems, as a result of which the systems, using the technology of synthesis of intelligent control algorithms, can optimize complex circuits of automatic control systems.

Adaptive Neuro-Fuzzy Structure Based Control Architecture

The purpose of this paper is to present a practical application of a Sugeno model based adaptive neuro-fuzzy architecture. The main challenge of the project was to realize the real-time control of the system and the real-time parameter adaptation of the controller. The neuro-fuzzy controller module is implemented using High Level Synthesis technique, and it's integrated into a microprocessor based architecture on a System on Chip (SoC) type integrated circuit. The architecture is used to control a two degrees of freedom system, which is composed of two horizontal arms attached to a linear bearing. The bearing is running on a vertical beam so the system can execute a vertical motion and a rotary motion around the vertical axle. The positions according to the two degrees of freedom are determined using an ultrasonic and a magnetic sensor.

A Distributed Adaptive Neuro-Fuzzy Network for Chaotic Time Series Prediction

Abstract In this paper a Distributed Adaptive Neuro-Fuzzy Architecture (DANFA) model with a second order Takagi-Sugeno inference mechanism is presented. The proposed approach is based on the simple idea to reduce the number of the fuzzy rules and the computational load, when modeling nonlinear systems. As a learning procedure for the designed structure a two-step gradient descent algorithm with a fixed learning rate is used. To demonstrate the potentials of the selected approach, simulation experiments with two benchmark chaotic time systems − Mackey-Glass and Rossler are studied. The results obtained show an accurate model performance with a minimal prediction error.

Hybrid PID Control Algorithms for Nonlinear Process Control

Hybrid PID Control Algorithms for Nonlinear Process ControlThis paper presents modifications of the classical PID control algorithm, implemented by an Adaptive Neuro-Fuzzy Architecture (ANFA). The main goal here is to design a fuzzy PID controller with a flexible structure, adaptive tuning of its parameters and algorithm modifications, which leads to improvement of the system performance. Thus the controlling process and system are prevented from the undesired and non expected changes of the system input signals. The antecedent part of the applied fuzzy rules contains a linear function, similar to the modified discrete equation of the corresponding conventional PID controller. The simulations demonstrate satisfactory results of these performances and implementations applied to a nonlinear plant.

Tool Condition Monitoring Based on an Adaptive Neurofuzzy Architecture

Metal cutting operations constitute a large percentage of the manufacturing activity. One of the most important objectives of metal cutting research is to develop techniques that enable optimal utilization of machine tools, improved production efficiency, high machining accuracy and reduced machine downtime and tooling costs. Machining process condition monitoring is certainly the important monitoring requirement of unintended machining operations. A multi-purpose intelligent tool condition monitoring technique for metal cutting process will be introduced in this paper. The knowledge based intelligent pattern recognition algorithm is mainly composed of a fuzzy feature filter and algebraic neurofuzzy networks. It can carry out the fusion of multi-sensor information to enable the proposed intelligent architecture to recognize the tool condition successfully.