Neuro-fuzzy Estimator Research Articles

Estimating microalgae Synechococcus nidulans daily biomass concentration using neuro-fuzzy network

In this study, a neuro-fuzzy estimator was developed for the estimation of biomass concentration of the microalgae Synechococcus nidulans from initial batch concentrations, aiming to predict daily productivity. Nine replica experiments were performed. The growth was monitored daily through the culture medium optic density and kept constant up to the end of the exponential phase. The network training followed a full 33 factorial design, in which the factors were the number of days in the entry vector (3,5 and 7 days), number of clusters (10, 30 and 50 clusters) and internal weight softening parameter (Sigma) (0.30, 0.45 and 0.60). These factors were confronted with the sum of the quadratic error in the validations. The validations had 24 (A) and 18 (B) days of culture growth. The validations demonstrated that in long-term experiments (Validation A) the use of a few clusters and high Sigma is necessary. However, in short-term experiments (Validation B), Sigma did not influence the result. The optimum point occurred within 3 days in the entry vector, 10 clusters and 0.60 Sigma and the mean determination coefficient was 0.95. The neuro-fuzzy estimator proved a credible alternative to predict the microalgae growth.

Intelligent braking system for stability enhancement of vehicle braking, using fuzzy logic controllers

In this research, a novel structure is proposed for vehicle braking stability improvement encountering critical driving conditions such as braking on slippery or μ-split surface. For these purposes, at first, a trained neuro-fuzzy estimator is used for vehicle path prediction according to vehicle speed, applied steering angle and also their changes. Then, slip of each wheel will be controlled by an anti-slip fuzzy controller which has been designed for each wheel. Also, another fuzzy controller has been designed so as to control the yaw angle concerning the yaw error. Then, the difference between the left and the right wheels’ braking torques is used by the ASBS controller in order to decrease the yaw error. Considering a model of Three-Degree-of-Freedom for chassis modelling and One-Degree-of-Freedom Dugoff’s tyre model for each wheel, a series of Matlab/Simulink simulation results will be presented in order to validate the effectiveness of the proposed controller.

Adaptive neuro fuzzy estimation of underactuated robotic gripper contact forces

It is known that robotic manipulators are highly nonlinear systems, and an accurate mathematical model is difficult to obtain, thus making it difficult tо analyze with conventional analytical methods. Here, a novel design of an adaptive neuro fuzzy inference system (ANFIS) for estimation contact forces of a new adaptive gripper is presented. Since the conventional analytical methods is a very challenging task, fuzzy logic based systems are considered as potential candidates for such an application. The main points of this paper are in explanation of kinetostatic analyzing of the new gripper structure using rigid body model with added compliance in every single joint. The experimental results can be used as training data for ANFIS network for estimation of gripping forces. An adaptive neuro-fuzzy network is used to approximate correlation between contact point locations and contact forces magnitudes. The simulation results presented in this paper show the effectiveness of the developed method. This system is capable to find any change in ratio of positions of the gripper contacts and magnitudes of the contact forces and thus indicates state of both finger phalanges.

Adaptive neuro-fuzzy estimation of conductive silicone rubber mechanical properties

Conductive silicone rubber has great advantages for tactile sensing applications. The electrical behavior of the elastomeric material is rate-dependent and exhibit hysteresis upon cyclic loading. Several constitutive models were developed for mechanical simulation of this material upon loading and unloading. One of the successful approaches to model the time-dependent behavior of elastomers is Bergstrom–Boyce model. An adaptive neuro-fuzzy inference system (ANFIS) model will be established in this study to predict the stress–strain changing of conductive silicone rubber during compression tests. Various compression tests were performed on the produced specimens. An ANFIS is used to approximate correlation between measured features of the material and to predict its unknown future behavior for stress changing. ANFIS has unlimited approximation power to match any nonlinear functions well and to predict a chaotic time series.

Air quality estimation by computational intelligence methodologies

The subject of this study is to compare different computational intelligence methodologies based on artificial neural networks used for forecasting an air quality parameter - the emission of CO2, in the city of Nis. Firstly, inputs of the CO2 emission estimator are analyzed and their measurement is explained. It is known that the traffic is the single largest emitter of CO2 in Europe. Therefore, a proper treatment of this component of pollution is very important for precise estimation of emission levels. With this in mind, measurements of traffic frequency and CO2 concentration were carried out at critical intersections in the city, as well as the monitoring of a vehicle direction at the crossroad. Finally, based on experimental data, different soft computing estimators were developed, such as feed forward neural network, recurrent neural network, and hybrid neuro-fuzzy estimator of CO2 emission levels. Test data for some characteristic cases presented at the end of the paper shows good agreement of developed estimator outputs with experimental data. Presented results are a true indicator of the implemented method usability.

A neuro-fuzzy online fault detection and diagnosis algorithm for nonlinear and dynamic systems

This paper presents a new fault detection and diagnosis approach for nonlinear dynamic plant systems with a neuro-fuzzy based approach to prevent developing of fault as soon as possible. By comparison of plants and neuro-fuzzy estimator outputs in the presence of noise, residual signal is generated and compared with a predefined threshold, the fault can be detected. To diagnose the type, size, time and fault conditions, are used analytical approach and neural network for tracking fault developing online. The neuro-fuzzy nets are compared with some other identification methods in application of power plant gas turbine. Faults are considered in two forms, step, and ramp shape. This work was implemented with real data from gas turbine of Kazeroun (Iran) power plant (Mitsubishi unit) and result is presented to demonstrate the benefits of the proposed method.

INTELLIGENT BRAKING SYSTEM USING FUZZY LOGIC AND SLIDING MODE CONTROLLER

In this paper, an antilock–antiskid braking system controller, which has been designed for stability enhancement of vehicles during braking and turning, is presented. Using available signals, a novel structure is proposed for vehicle stability improvement for critical driving conditions such as braking on slippery or µ-split road surfaces. In conventional vehicles, undesired lane changes may occur due to equal dispatch of braking torques to all wheels simultaneously. Also, intensive pressure on brake pedal can bring about wheel lockup which results in vehicle instability and undesired lane changes. Antilock braking system (ABS) along with Antiskid braking system (ASBS) can serve as a driver-assistance system in vehicle path correction facing critical driving conditions during braking and turning round on different road surfaces. For these purposes, at first, a trained Neuro-Fuzzy estimator is used for vehicle path prediction according to vehicle’s speed, applied steering angle and their changes. Then, slip of each wheel will be controlled by an antilock fuzzy controller which has been designed for each wheel. Also, a sliding mode controller has been designed so as to control the yaw angle considering the yaw error, where the yaw error is resulted from the difference of the Neuro-Fuzzy estimator’s output and actual yaw angle. Then, the difference of the left and the right wheels’ braking torques are used by the sliding mode controller in order to reduce the yaw error. Considering a model of three-degreeof-freedom for chassis and one-degree-of-freedom Dugoff’s tire model for each wheel, a series of Matlab/Simulink simulation results will be presented to validate the effectiveness of the proposed controller. Finally, a comparison will be made between the proposed method and one of the recent control systems which shows the superiority of its performance.

A neurofuzzy system to analyze liquefaction-induced lateral spread

Lateral spreads of liquefied granular soil masses have caused severe damages to many engineered structures. Accordingly, many empirical procedures have been developed from field-direct observations and from multiple regression analyses carried out on the database gathered from many case histories. The intricacy and nonlinearity of the underlying phenomena makes the above approaches somewhat unreliable for estimating liquefaction-induced lateral spreads. The database has inconsistencies and contradictions because of inevitable subjective interpretations and neural network approaches have been proposed for dealing with these. To overcome these difficulties in this paper a hybrid system named neurofuzzy, which profits from fuzzy and neural paradigms, is advanced. The resulting model called NEFLAS (NEuroFuzzy estimation of liquefaction induced LAteral Spread) is shown to yield a much improved forecasting than both multiple regression and neural network procedures. The corresponding software can be obtained from the first author.

Soft computing based multi-agent marketing decision support system

The new concept of soft computing based distributed multi-agent marketing decision support system (DSS) is proposed in this paper. The DSS is composed of a number of parallel intelligent agents acting in a distributed mode, and one coordinating agent for evaluation of solutions. Generation of a final solution in DSS is achieved through cooperative and competitive interactions among intelligent agents. The main idea of the proposed DSS is based on decomposition of the overall system intelligence among cooperative autonomous intelligent agents capable of competing and cooperating with each other in order to propose total solution to the problem and to integrate local solutions into the final solution. Each distributed intelligent agent is implemented as fuzzy knowledge based system with modest number of rules. The agent-coordinator (evaluator) evaluates the proposals and ranks the fuzzy values of the outcome produced by intelligent contending agents. The outcome of each agent is estimated on the basis of its solution, input information, and other necessary information using a neuro-fuzzy estimator tuned by a genetic algorithm. The proposed concept for designing DSS is illustrated through a marketing-mix DSS.

Visual Surveillance and Tracking of Humans by Face and Gait Recognition

Increased emphasis on automated real time intelligent surveillance system has led to the need to identify and track people in complex environments. Independent features such as face, gait provide valuable clues as to identity, which coupled with data fusion and tracking algorithms offer a potential solution to this problem. In this paper we address the first problem of recognizing humans in real time, data fusion and tracking will be performed by neurofuzzy state estimators. A new approach which combines eigenspace transformation with canonical space transformation is proposed here. This method can be used to reduce data dimensionality and to optimize the class separability of different classes simultaneously.

Neuro-Fuzzy Approach to Real Time Total Velocity Vector Estimation of a Passenger Car Covering Critical Situations

This paper presents the concept of a neuro-fuzzy estimation of the variables of complex, fast, closed-loop systems. It was used to develop an original real time total velocity vector estimator for FWD cars, that covers highly critical driving situations and avoids the use of expensive optical cross-correlation sensors. The aim of this application is to provide vehicle monitoring processes or supervisors, with a reliable value of the longitudinal and transverse velocity components. Fuzzy logic was used to build aggregate indicators with the measured variables, in order to identify and detect the different ways a vehicle behaves. Considering these different typical vehicle behaviours and the complexity of tyre modelling, neural networks were chosen for the estimate of the transverse velocity. A production vehicle was used to validate the implementation of the estimation algorithm.