New fuzzy wavelet network for modeling and control: The modeling approach

In this paper, a fuzzy wavelet network is proposed to approximate arbitrary nonlinear functions based on the theory of multiresolution analysis (MRA) of wavelet transform and fuzzy concepts. The presented network combines TSK fuzzy models with wavelet transform and ROLS learning algorithm while still preserve the property of linearity in parameters. In order to reduce the number of fuzzy rules, fuzzy clustering is invoked. In the clustering algorithm, those wavelets that are closer to each other in the sense of the Euclidean norm are placed in a group and are used in the consequent part of a fuzzy rule. Antecedent parts of the rules are Gaussian membership functions. Determination of the deviation parameter is performed with the help of gold partition method. Here, mean of each function is derived by averaging center of all wavelets that are related to that particular rule. The overall developed fuzzy wavelet network is called fuzzy wave-net and simulation results show superior performance over previous networks.The present work is complemented by a second part which focuses on the control aspects and to be published in this journal([17]). This paper proposes an observer based self-structuring robust adaptive fuzzy wave-net (FWN) controller for a class of nonlinear uncertain multi-input multi-output systems.     

Robust fault tolerant control of continuous-time switched systems: An LMI approach

The present paper proposes a new robust fault tolerant control (RFTC) design for continuous-time switched systems. The main objective is to design in an integrated way the couple (controller, observer) that allows to stabilize switched systems even in the presence of actuator faults. A state/fault estimation observer is designed to simultaneously estimate system state and actuator faults. Based on this observer, a fault tolerant controller is developed to stabilize the system and accommodate the actuator faults automatically. The RFTC problem is formalized in the form of linear matrix inequalities (LMI) rather than bilinear matrix inequalities (BMI), to avoid the difficulty of solving BMIs. Finally, a numerical example composed of unstable subsystems is studied to show the applicability and efficiency of the obtained results.     

A new approach to fuzzy wavelet system modeling

In this paper, we propose simple but effective two different fuzzy wavelet networks (FWNs) for system identification. The FWNs combine the traditional Takagi–Sugeno–Kang (TSK) fuzzy model and discrete wavelet transforms (DWT). The proposed FWNs consist of a set of if–then rules and, then parts are series expansion in terms of wavelets functions. In the first system, while the only one scale parameter is changing with it corresponding rule number, translation parameter sets are fixed in each rule. As for the second system, DWT is used completely by using wavelet frames. The performance of proposed fuzzy models is illustrated by examples and compared with previously published examples. Simulation results indicate the remarkable capabilities of the proposed methods. It is worth noting that the second FWN achieves high function approximation accuracy and fast convergence.     

A new approach to fuzzy wavelet system modeling

In this paper, we propose simple but effective two different fuzzy wavelet networks (FWNs) for system identification. The FWNs combine the traditional Takagi–Sugeno–Kang (TSK) fuzzy model and discrete wavelet transforms (DWT). The proposed FWNs consist of a set of if–then rules and, then parts are series expansion in terms of wavelets functions. In the first system, while the only one scale parameter is changing with it corresponding rule number, translation parameter sets are fixed in each rule. As for the second system, DWT is used completely by using wavelet frames. The performance of proposed fuzzy models is illustrated by examples and compared with previously published examples. Simulation results indicate the remarkable capabilities of the proposed methods. It is worth noting that the second FWN achieves high function approximation accuracy and fast convergence.     

A fuzzy set-based approach to data reconciliation in material flow modeling

Material flow analysis is used to quantify the material turnover of a defined system, relying on data about flows and stocks from different sources with varying quality. In this study, the belief that the available data are representative for the value of interest is expressed via fuzzy sets, specifying the possible range of values of the data. A possibilistic framework for data reconciliation in MFA was developed and applied to a case study on wood flows in Austria. The framework consists of a data characterisation and a reconciliation step. Membership functions are defined based on the collected data and data quality assessment. Possible ranges and consistency levels (quantifying the agreement between input data and balance constraints) are determined. The framework allows problematic data and model weaknesses to be identified and can be used to illustrate the trade-off between confidence in the data and the consistency levels of resulting material flows.     

A bi-objective modeling approach applied to an urban semi-desirable facility location problem

This paper introduces a mixed-integer, bi-objective programming approach to identify the locations and capacities of semi-desirable (or semi-obnoxious) facilities. The first objective minimizes the total investment cost; the second one minimizes the dissatisfaction by incorporating together in the same function “pull” and “push” characteristics of the decision problem (individuals do not want to live too close, but they do not want to be too far, from facilities). The model determines the number of facilities to be opened, the respective capacities, their locations, their respective shares of the total demand, and the population that is assigned to each candidate site opened. The proposed approach was tested with a case study for a particular urban planning problem: the location of sorted waste containers. The complete set of (supported or unsupported) non-inferior solutions, consisting of combinations of multi-compartment containers for the disposal of four types of sorted waste in nineteen candidate sites, and population assignments, was generated. The results obtained for part of the historical center of an old European city (Coimbra, Portugal) show that this approach can be applied to a real-world planning scenario.     

A fuzzy clustering approach to real-time demand-responsive bus dispatching control

Quick response (QR) to passenger needs is a key objective for advanced public transportation systems (APTS), and it has become increasingly important for contemporary metropolitan bus operations to gain a competitive advantage over private transportation. This paper presents a real-time control methodology for demand-responsive bus operations that respond quickly to passenger needs. The proposed method primarily involves two levels of functionality: (1) short-term forecasting of passenger demands using time-series prediction models, and (2) identification of service strategies coupled with the associated bus service segments using fuzzy clustering technologies in response to variances in passenger demand attributes and traffic conditions. The proposed bus operations method identifies the demand-responsive vehicle service strategies primarily according to the predicted up-to-date attributes of passengers’ demands, rather than deterministic passenger arrival rates, which were generally used in previous literature. In addition, the variation of traffic conditions along bus lines is considered in the proposed method. Results from numerical studies using real data of passengers’ demands, including passenger volume at each bus stop and the passenger origin-destination (O-D) patterns, are presented to demonstrate the effectiveness of the proposed method for real-world applications.     

Reliable control for nonlinear systems with stochastic actuators fault and random delays through a T-S fuzzy model approach

This paper considers the reliable control design for T-S fuzzy systems with probabilistic actuators faults and random time-varying delays. The faults of each actuator occurs randomly and its failure rates are governed by a set of unrelated random variables satisfying certain probabilistic distribution. In terms of the probabilistic failures of each actuator and time-varying random delays, new fault model is proposed. Based on the new fuzzy model, reliable controller is designed and sufficient conditions for the exponentially mean square stability (EMSS) of T-S fuzzy systems are derived by using Lyapunov functional method and linear matrix inequality (LMI) technique. It should be noted that the obtained criteria depend on not only the size of the delay, but also the probability distribution of it. Finally, a numerical example is given to show the effectiveness of the proposed method.     

On-line model-based fault detection and isolation for PEM fuel cell stack systems

Efficient and reliable operation of Polymer Electrolyte Membrane (PEM) fuel cells are key requirements for their successful commercialization and application. The use of diagnostic techniques enables the achievement of these requirements. This paper focuses on model-based fault detection and isolation (FDI) for PEM fuel cell stack systems. The work consists in designing and selecting a subset of consistency relations such that a set of predefined faults can be detected and isolated. Despite a nonlinear model of the PEM fuel cell stack system will be used, consistency relations that are easily implemented by a variable back substitution method will be selected. The paper also shows the significance of structural models to solve diagnosis issues in complex systems.     

Robust statistical modeling using the Birnbaum‐Saunders‐t distribution applied to insurance

In this paper, we carry out robust modeling and influence diagnostics in Birnbaum‐Saunders (BS) regression models. Specifically, we present some aspects related to BS and log‐BS distributions and their generalizations from the Student‐t distribution, and develop BS‐t regression models, including maximum likelihood estimation based on the EM algorithm and diagnostic tools. In addition, we apply the obtained results to real data from insurance, which shows the uses of the proposed model. Copyright © 2011 John Wiley & Sons, Ltd.     

Mathematical modeling and fuzzy control of a flexible-link robot arm

In this paper, the Timoshenko theory is applied to investigate a new mathematical model for the “shoulder-elbow-like” single flexible-link robot arm with dampings. Detailed analysis and derivation are given to support the mathematical modeling of this particular flexible mechanism. A new design of a fuzzy-logic-based (PI + D)² control scheme is developed for both vibration suppression and set-point tracking. Computer simulation results for the modeling are performed to observe the significant vibration modes, and simulation results for the control scheme demonstrate that the controllers perform very well for the tracking based on this flexible-link model. A newly developed method for stability analysis using the “two-straight-lines” criterion is also presented.     

Hybrid modeling based double-granularity fault detection and diagnosis for quadrotor helicopter

Fault detection and diagnosis (FDD) is an effective technology to assure the safety and reliability of quadrotor helicopters. However, there are still some unsolved problems in the existing FDD methods, such as the trade-offs between the accuracy and complexity of system models used for FDD, and the rarely explored structure faults in quadrotor helicopters. In this paper, a double-granularity FDD method is proposed based on the hybrid modeling of a quadrotor helicopter which has been developed in authors’ previous work. The hybrid model consists of a prior model and a set of non-parametric models. The coarse-granularity-level FDD is built on the prior model which can isolate the faulty channel(s); while the fine-granularity-level FDD is built on the nonparametric models which can isolate the faulty components in the faulty channel. In both coarse and fine granularity FDD procedures, principal component analysis (PCA) is adopted for online fault detection. Using such a double-granularity scheme, the proposed FDD method has inherent ability in detecting and diagnosing structure faults or failures in quadrotor helicopters. Experimental results conducted on a 3-DOF hover platform can demonstrate the feasibility and effectiveness of the proposed hybrid modeling technique and the hybrid model based FDD method.     

Variational approach to modeling and control of dynamic systems with distributed parameters

Controlled motions of a thin elastic rod are studied. A variational statement of the initial-boundary value problem is given based on the integral formulation of constitutive relations. An approach relying on the Ritz method and finite element technique is proposed to design the boundary control that moves the rod with certain accuracy to a given final state and minimizes the mean energy. The results of numerical simulation and the estimates of solution quality are presented and discussed. (© 2014 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim)     

Multivariable fuzzy control applied to the physical–chemical treatment facility of a Cellulose factory

Feedback linearization is a well-known technique in nonlinear control in which known system nonlinearities are canceled by the control input leaving a linear control problem. Feedback linearization requires an exact model for the system. Fundamental and advanced developments in neuro-fuzzy synergy for modeling and control are used to apply the feedback linearization control law on second-order plants. In the models that are used, the nonlinear plant is decomposed on six fuzzy systems necessary to apply the control signal to allow the following of a reference value. A practical application is also presented using a waste water plant. This method can be extended to multiple input–multiple output (MIMO) plants based on input–output data pairs collected directly from the plant.     

Robust control for Takagi–Sugeno fuzzy systems with time-varying state and input delays

The paper investigates the robust control for uncertain Takagi–Sugeno (T–S) fuzzy systems with time-varying state and input delays. Delay-dependent stabilization criterion is proposed to guarantee the asymptotic stabilization of fuzzy systems with parametric uncertainties. The result of [Lee HJ, Park JB, Joo YH. Robust control for uncertain Takagi–Sugeno fuzzy systems with time-varying input delay. ASME J Dyn Syst Meas Control 2005;127:302–6] is extended to uncertain fuzzy systems with time-varying state and input delays. Simulations show that significant improvement over the previous results can be obtained.     

Real-time distributed control: A fuzzy and model predictive control approach for a nonlinear problem

Nowadays the study of faults and their consequences has become an issue for highly safety critical computer network systems. How to bound the effects of a fault and how to tackle them in a dynamic system is still an open field. Here, an approach to studying this problem is presented as a hybrid strategy. The use of a multi-model technique from the point of view of real-time systems and intelligent control structure is described, in order to accomplish one challenge: to overcome the problem of the presence of local faults and the respective time delays within a real-time distributed system. This approach is pursued as a reconfigurable strategy according to communication time delays within a real-time distributed system. In fact, it is pursued as a reconfigurable strategy according to communication delays and local faults where the control strategy is modified from several perspectives.     

A new approach to discretization applied to a continuous, nonlinear, sliding-mode-like control using nonsmooth analysis

This paper introduces a new approach to discretization of nonlinearcontrol laws with a Lipschitz property. The sampling time isdefined as a parameter, which must be selected sufficientlysmall so that the closed-loop system is stable. In contrastto similar results, the stabilizing effect of the control istaken into account. This can result in less conservative constraintson the minimum sampling frequency. The discretization techniquesare explained on a general nonlinear model and applied to thediscretization of a novel nonlinear, robust sliding-mode-likecontrol law. Similar robustness features as for continuous controlare demonstrated. Nonsmooth Lyapunov functions are used forthe discretized sliding-mode-like control introducing cone shapedregions of the state space. One of these cone shaped regionscoincides with a cone shaped layer around the sliding mode definedby the continuous sliding-mode-like control. A stability theoremusing nonsmooth Lyapunov functions is provided.     

A modeling approach to logistics in concurrent engineering

This paper advocates logistics involvement in the early phases of product design and development in a concurrent engineering environment. A concurrent engineering environment and the benefits of such involvement are explained in detail. The paper focuses on facilitating an interface and a collaboration between the designer and the logistician. A conceptual interface for design for logistics is presented. Four areas of interface are considered: (a) logistics engineering, (b) manufacturing logistics, (c) design for packaging, and (d) design for transportability. A set of detailed design factors pertaining to each area are presented. A modeling approach, Bond Energy Algorithm, is used to accomplish the design for logistics concerns developed throughout the paper. An example is provided to test and validate the algorithm. The results are analyzed and appropriate perspectives for managerial implication of the methodology are provided. Finally, some conclusions and assessments are presented.     

A parameterized approach to modeling and forecasting mortality

A new method is proposed of constructing mortality forecasts. This parameterized approach utilizes Generalized Linear Models (GLMs), based on heteroscedastic Poisson (non-additive) error structures, and using an orthonormal polynomial design matrix. Principal Component (PC) analysis is then applied to the cross-sectional fitted parameters. The produced model can be viewed either as a one-factor parameterized model where the time series are the fitted parameters, or as a principal component model, namely a log-bilinear hierarchical statistical association model of Goodman [Goodman, L.A., 1991. Measures, models, and graphical displays in the analysis of cross-classified data. J. Amer. Statist. Assoc. 86(416), 1085-1111] or equivalently as a generalized Lee-Carter model with p interaction terms. Mortality forecasts are obtained by applying dynamic linear regression models to the PCs. Two applications are presented: Sweden (1751-2006) and Greece (1957-2006).