Fuzzy Identification Research Articles

Research on RSSI–Based Localization System in the Wireless Sensor Network

Due to the rapid development in wireless sensor networks, the applications of the WSN have been extended to different environment and achieved a more diversified purpose. AS for the localization system, there are many related re- search achievements. A set of localization system is built through the system integration between the small-scale wireless hardware sensor and the wireless sensor platform, through the use of the RSSI and the integration of the fuzzy inference system. The blind nodes are experimented in the indoor environment so that the system's efficiency can be verified. The system is implemented in the 8 meters multiplying 8 meters indoor space which is divided into 16 sections. Then 4 anchor nodes are placed in the corners and the fuzzy identification system is built for the nodes' RSSI signal in the blocks. Later, the localization test is implemented in the random positions within the blocks. The experimental results show that the lo- calization system accuracy rate is more than 80% and can successfully reach the preliminary localization system.

An ant colony optimization-based fuzzy predictive control approach for nonlinear processes

In this paper, a new approach for designing an adaptive fuzzy model predictive control (AFMPC) based on the ant colony optimization (ACO) is proposed. On-line adaptive fuzzy identification is introduced to identify the system parameters. These parameters are used to calculate the objective function based on a predictive approach and structure of RST control. Then the optimization problem is solved based on an ACO algorithm, used at the optimization process in AFMPC to determine optimal controller parameters of RST control. The utility of the proposed controller is demonstrated by applying it to two nonlinear processes, where the proposed approach provides better performances compared with proportional integral-ant colony optimization controller and adaptive fuzzy model predictive controller.

Designing an intelligent control strategy for hybrid powertrains utilizing a fuzzy driving cycle identification agent

In this paper, a new idea for designing the control strategy for the energy management of hybrid powertrains based on the driving cycle type is presented. Here, every instance of an unknown driving cycle is considered to be similar to the reference driving cycles using similarity weights. To determine the control output in the unknown driving cycle, the weights are applied to a linear combination of the optimal control decisions generated in each of the reference driving cycles. The weights which are between zero and one are determined using a fuzzy driving cycle identification agent based on the comparison of preselected driving features. The simulation studies in seven different driving cycles show that, while all driving patterns in every driving cycle are considered for the generation of energy management by online implementation of the proposed intelligent control strategy, some driving patterns would be eliminated by using a non-fuzzy identification agent. This leads to a significant reduction in the fuel consumption of the hybrid powertrain utilized with the fuzzy identification agent in some driving cycles in comparison with those without the use of non-fuzzy driving cycle identification. In addition, in some driving cycles, the intelligent control strategy has a performance close to that for the offline optimized control strategy.

A robust time delay auto-regressive exogenous fuzzy inference system for real-time estimation of catalyst temperature over engines coldstart operation: a multiobjective implementation scenario

In the current investigation, the authors propose an intelligent real-time system to dynamically simulate the catalyst temperature in automotive engines over the coldstart period. In general, the behavior of an engine during the first few minutes of its operation, namely the coldstart period, is highly transient and nonlinear. However, it is important to the engineers of automotive industry to develop advanced simulation techniques capable of capturing the engine system’s behavior during coldstart periods. The main motivation behind such a fact emanates in the pursuit of making successful strides towards decreasing the amount of unburned hydrocarbon emissions (HCs) of the engine. Catalytic convertors play a pivotal role in reducing the amount of this emitted pollutant. Therefore, here, the authors develop a knowledge based intelligent identification system, based on the integration of a low-level fuzzy identification machine (FIM) identifier and a hyper-level multiobjective optimizer, to monitor the catalyst temperature over the coldstart period for a given automotive engine system. In the current investigation, the authors propose the use of synchronous self-learning Pareto strategy for the multi-objective optimization of the architecture of FIM. To suit the intelligent scheme for online applications, the authors capture the required database using the concept of nonlinear auto-regressive exogenous systems. The developed intelligent approach can be used as a real-time soft sensor to observe the state of the catalytic convertor and send the required data to the coldstart controller. To ensure the efficacy of the resulting time delay FIM framework, it is used for capturing the catalyst temperature in three different experimental conditions. Through a comparative numerical study, it is demonstrated that the proposed soft sensor can be efficiently used for real-time estimations of the catalyst temperature. Besides, the results let us make sure that intelligent approaches have an aptitude to be effectively used as real-time observers instead of expensive commercial sensors. Generally, the results of the current investigation substantiates the authenticity of advanced computational approaches for coping with the considered identification problem, to help resolving one of the challenging issues in the field of automotive engineering, that is, the coldstart HC emission reduction.

A new approach for online T-S fuzzy identification and model predictive control of nonlinear systems

This paper proposes a new unsupervised fuzzy clustering algorithm (NUFCA) to construct a novel online evolving Takagi–Sugeno (T-S) fuzzy model identification method and an adaptive predictive process control methodology. The proposed system identification approach consists of two main steps: antecedent T-S fuzzy model parameters identification and consequent parameters identification. The NUFCA combines the K-nearest neighbour and fuzzy C-means methods into a fuzzy modelling method for partitioning of the input–output data and identifying the antecedent parameters of the fuzzy system; then the recursive least squares method is exploited to obtain initialization type consequent parameters and to construct a method for on-line fuzzy model identification. The integration of the proposed adaptive identification method with the generalized predictive control results in an effective adaptive predictive fuzzy control methodology. For better demonstration of the robustness and efficiency of the proposed methodology, it is applied to the identification of a model for the estimation of the flour concentration in the effluent of a real-world wastewater treatment plant (WWTP); and to control a simulated continuous stirred tank reactor (CSTR), and a real experimental setup composed of two coupled DC motors. The results show that the developed evolving T-S fuzzy model methodology can identify nonlinear systems satisfactorily and can be successfully used for a prediction model of the process for the generalized predictive controller. It is also shown that the algorithm is robust to changes in the initial parameters, and to unexpected disturbances.

Study on Objective Evaluation Method of Taxi Driver Safety Consciousness

This study aims to conduct researches on the correlation between driver safety consciousness and several indices, and propose an objective evaluation criterion, which can covert immeasurable safety consciousness to measurable objective indices. A number of taxi drivers were selected as study subjects, and their safety consciousness was evaluated by using fuzzy comprehensive evaluation method. Combined with the number of accidents these drivers involve in a year, the correlation between driver safety consciousness and accident numbers was investigated. And combined with GPS surveillance data, the correlation between driver safety consciousness and the mean speed, speed dispersion, and max vehicle speed was analyzed. Then the identification model between max vehicle speed and driver safety consciousness level was established. The results show that driver safety consciousness level is correlated with accident numbers, and not correlated with the mean speed, correlated with vehicle speed dispersion, and highly correlated with max vehicle speed. According to fuzzy identification model, max vehicle speed obtained from statistics circle can be used to evaluate and categorize driver safety consciousness. Verification shows that the driver safety consciousness evaluation model, which based on the max vehicle speed, is effective. It can overcome the demerits of scale evaluation, effectively identify driver safety consciousness level, and provide guidance for driver safety education, management and training.

Decoupling Control for Bearingless Synchronous Reluctance Motor Based on Fuzzy Inverse Model

For the bearingless synchronous reluctance motor (BSRM) is a multivariable, strong coupling, multi-input and multi-output system, based on the adaptive inverse control theory, a decoupling control method based on the T-S fuzzy inverse model identification is put forward in this paper. According to the input and output information of the system, a fuzzy inverse model of the motor control system is established, then making the inverse model and the original control system in series forms pseudo linear hybrid system to realize the approximate linearization and dynamic decoupling of the motor control system. Building the composite system and proceeding research in the Matlab/Simulink environment, the simulation results show that the control strategy can realize dynamic decoupling among the electromagnetic torque subsystem and the radial suspension force subsystem and among thex- andy-direction of the suspension force, and with excellent static and dynamic performance and adaptive ability.

Fuzzy identification of reactive distillation for acetic acid recovery from waste water

Acetic acid constitutes major component of waste water effluent in petrochemical and fine chemical industries but its recovery poses a serious environmental challenge in the industries. In this work, nonlinear model for multi-input multi-output reactive distillation process was developed for the treatment of waste water containing 30% g/g of acetic acid using fuzzy model technique based on autoregressive with exogenous inputs (ARX) models. It was aimed at obtaining a simplified model which should have essential dynamic behaviour of the process suitable for applications such as control design and dynamic optimization. Data sets used for the model development were obtained from simulated model built in CHEMCAD environment. Reflux flow rate and reboiler heat duty were used as input variables while ethyl acetate top product purity and acetic acid fractional conversion were used as output variables. Structured nonlinear parameter optimization method (SNPOM) was used for parameters estimation to effectively characterize the systems. The percentages of fitness for top product ethyl acetate purity and acetic acid fractional conversion were found to be 85.35% and 82.95%, respectively. The residual analysis carried out on the model showed that the proposed model was able to capture nonlinear dynamic behaviours of the process.

Autonomous takeoff control system design for unmanned seaplanes

Unmanned seaplanes are special kinds of fixed-wing airplanes which can achieve autonomous takeoff and landing on water. Due to complicated hydrodynamic forces and unpredictable sea states, researches on modeling, dynamic analysis and controller design are still facing great challenges. In this paper, the dynamic characteristics and motion stability of the unmanned seaplane are firstly analyzed based on a nonlinear mathematical model. The proposed autonomous takeoff control system consists of two main parts: T-S fuzzy identification and generalized predictive control (GPC). A linear CARIMA model obtained through T-S fuzzy identification is used to represent the dynamic characteristics in different motion stages. Wave forecasting is considered in the GPC algorithm to improve the anti-waves capability and avoid unstable phenomena in high sea states. Simulations are performed in three different wave conditions, including calm water, regular wave and irregular wave. Moreover, GPC controller is compared with other disturbance rejection control solutions. The simulation results show that the proposed controller has good performances for autonomous takeoff of the unmanned seaplane.

Human - robot collision detection and identification based on fuzzy and time series modelling

SUMMARYIn this paper, two methods are proposed and implemented for collision detection between the robot and a human based on fuzzy identification and time series modelling. Both methods include a collision detection system for each joint of the robot that is trained to approximate the external torque. In addition, the proposed methods are able to detect the occurrence of a collision, the link that collided and to some extent the magnitude of the collision without using the explicit model of the robot. Since the speed of the detection is of critical importance for mitigating the danger, attention is paid to recognise a collision as soon as possible. Experimental results conducted with a KUKALWR manipulator using two joints in planar motion, verify the validity on both methods.

Soft Computing Methods for Thermo-Acoustic Simulation

In the present study, soft computing methods are employed for thermoacoustic simulation. A ducted Burke-Schumann diffusion flame is used as the heat source for a horizontal duct. First, a dynamic model is constructed from the input-output data sets (velocity forcing - heat release) generated from the Burke-Schumann flame using Comsol. An efficient and cheap model of heat source is obtained using dynamic fuzzy identification. The full thermoacoustic system is simulated in a time domain with the Galerkin method using the identified heat source model. Finally, dynamic neural networks are utilized for obtaining a dynamic fit for a set of operating conditions for the acoustic velocity at the heater location. The overall agreement between the outputs of the soft computing tools (fuzzy and neural network tools) with the Comsol and Galerkin solver is found to be satisfactory.

A Fuzzy Recognition of early Crack of Metal Deep Drawing Stamping Based on the Fuzzy Clustering

This paper was according to the early crack identification on metal deep drawing, combined with the characteristics of the AE singal of deep drawing forming, determined to analyze it by db4 wavelet basis function for 3 layers, extracted the energy value at every point of the eight AE signal samples from deep drawing forming which crack state was known to constituted characteristic matrix, fuzzy equivalence matrix was obtained by a series of matrix transformation,which was regard as pattern library of crack that used in cluster analysis. Then extracted energy value at every point of AE signal from deep drawing experiments with there states unknown, calculate similarity between samples and the model we established by using euclidean distance formula after normalization processing, deep drawing state was determined by the principle of selecting near, finally compared the recognition result with crack situation deviced by naked eye and microscope, results show that the accuracy of fuzzy identification of early crackn based on fuzzy clustering is up to 90%.

Fuzzy Relational Control of an Uncertain System

The paper considers the usefulness of a control strategy based on a fuzzy relational model of the controller to counteract uncertainties caused by measurement noise and unmeasured disturbances. The fuzzy relational model is identified using a combination of feedback error learning and fuzzy identification. An important feature of the resulting fuzzy relational model is that it will generate a fuzzy output in the presence of uncertainties. Two causes of uncertainty are considered separately, the first cause of uncertainty is due to the noise on the sensor measuring the controlled variable and the second one is an unmeasured input disturbance. Results are presented that show that the fuzzy control signal is representative of the uncertainties and that conditional defuzzification can then be used to improve the control performance by reducing the control activity.

Dynamic model identification of IPMC actuator using fuzzy NARX model optimized by MPSO

In this paper, a novel inverse dynamic fuzzy NARX model is used for modeling and identifying the IPMC-based actuator’s inverse dynamic model. The contact force variation and highly nonlinear cross effect of the IPMC-based actuator are thoroughly modeled based on the inverse fuzzy NARX model-based identification process using experiment input-output training data. This paper proposes the novel use of a modified particle swarm optimization (MPSO) to generate the inverse fuzzy NARX (IFN) model for a highly nonlinear IPMC actuator system. The results show that the novel inverse dynamic fuzzy NARX model trained by MPSO algorithm yields outstanding performance and perfect accuracy.

Variable step-size numerical atlas method for path generation of spherical four-bar crank-slider mechanism

This paper presents a new method for the path generation of spherical four-bar crank-slider mechanism. Based on the established mathematical model of the spherical four-bar crank-slider mechanism, the expression of the coupler curve is determined. Then, depending on Fourier series theory, the immanent connection between coupler curve and its corresponding harmonic characteristic parameters is discovered. Meanwhile, by the analysis of the basic dimensional type and the coupler curve, different step size for each parameter of the basic dimensional type is chosen. Thus, by putting the harmonic characteristic components and associated basic dimensional type of spherical four-bar crank-slider mechanism together, a variable step size numerical atlas database of the spherical four-bar crank-slider mechanism is created. Furthermore, by using fuzzy identification method, the best suitable basic dimensional type of spherical four-bar crank-slider mechanism for prescribed coupler curve is obtained. Finally, an example is given to illustrate the synthesis process and the application of this method.

Modeling Based on T-S Model for Thermal Process in Metallurgical Performance Testing

Most of metallurgical performance testing devices use small high-temperature furnace to simulate physical environment for the sample testing. Since the controlled object has the dynamic characteristics of nonlinear, time-varying, large delay and large inertia during heating process, it is difficult to establish an accurate models to control thermal processes and optimize. This paper presents an adaptive neural fuzzy modeling approach based on T-S model for the heating process. Using the fuzzy system structure identification and parameter identification, the more accurate nonlinear model can be obtained. Duo to the fuzzy neural network has the capability of autonomous, quickly and effectively converging to the required relations of the input and output, the modeling accuracy has been improved. The simulation results demonstrate the effectiveness of the proposed algorithm, and the method can provide a reference for obtaining accurate nonlinear model.

Fuzzy identification of γ ray fingerprints based on adaptive network-based fuzzy inference system

An identification method of γ-ray fingerprints based on adaptive network-based fuzzy inference system is brought forward. By setting up model and performing simulation, the parameters of the system relevant to the γ-ray fingerprints are extracted as the identification features. The two-dimensional fuzzy set about the identification features is put forward, and the fundamental principle for identification is established. The types and the individuals of nuclear materials are identified successfully with high degree of confidence. The simulation materials as radiation sources are identified with the method, and the performance of the method is studied and discussed. The results show that the method has not only strong capabilities for identifying the types and the individuals of the radiation sources, but also strong de-noising capability and low identification limit, and it can be applied to the nuclear materials safeguard.

Fuzzy Adaptive Inverse Control for Pneumatic Loading System

The pneumatic loading system has the characteristics of time delay, time-varying and serious nonlinearity. In order to improve the control precision and overcome the shortcomings of traditional PI control algorithm, fuzzy adaptive inverse control is proposed to control the pressure of pneumatic loading system. Inverse model the pneumatic loading system off-line with fuzzy identification theory and get the initial inverse model. Take the initial inverse model as the initial controller to control the output pressure of the pneumatic loading system, and update the parameters of the controller online with the LMS filtering algorithm. Based on VC++ 6.0 software development platform, real-time control program is designed and tested on a pneumatic loading system. By comparing to the PI control algorithm, and fuzzy proportion, integration, differentiation control algorithm, the results prove that the proposed controller has high control accuracy, fast response and strong anti-disturbance ability for the pneumatic loading system.

Residual Generator Fuzzy Identification for Wind Farm Fault Diagnosis

In the recent years the wind turbine industry has focused on optimising the cost of energy. One of the important factors in the achievement of this task consists of increasing the reliability of the wind turbines, which can be obtained using advanced fault detection and isolation strategies. Clearly, most faults are managed quite easily at a wind turbine control level. However, some faults are better dealt with at wind farm level, when the wind turbine is located in a wind farm. This paper aims at proposing a fault detection and isolation solution with application to a wind farm benchmark model. The considered benchmark includes a small wind farm of nine wind turbines, based on simple models of wind turbines, as well as the wind and interactions between wind turbines in the wind farm. The solution relies on a set of piecewise affine Takagi–Sugeno models, which are identified from the noisy measurements acquired from the simulated wind park. The design of the fault isolation strategy is also enhanced by the use of the proposed fuzzy approach. Finally, the wind park simulator is exploited for validating the achieved performances of the suggested methodology.

Hammerstein identification of supercharged boiler superheated steam pressure using Laguerre-Fuzzy model

System identification plays an important role in many fields of science and engineering. This paper deals with a new nonlinear identification method fit for supercharged boiler superheated steam pressure. The superheated steam pressure is influenced by fuel and superheated steam flow, whereas traditional identification methods always omit the influence of superheated steam flow, and receive limited identification precision due to the uncertain time delay and strong nonlinearity. Taking into account that Laguerre filters can approximate linear systems (even with time delay) with a model order lower than ARX model and fuzzy identification from measured data is effective enough to approximate uncertain nonlinear systems, Laguerre filters and fuzzy model are firstly combined into Hammerstein structure to construct Laguerre-Fuzzy Hammerstein model. The defined model is a two inputs single output model which considers both of the two nonlinear variables and can avoids the decrease of identification precision resulted by uncertain time delay. The proposed model is applied in the nonlinear identification of supercharged boiler superheated steam pressure. Simulation results show that the Laguerre-Fuzzy Hammerstein model can trace the process nonlinearity precisely and has higher prediction accuracy than ARX model and basic Hammerstein model with a lower model order. Moreover, Laguerre-Fuzzy Hammerstein model improves the computation efficiency and system stability greatly.