Search

This paper investigates a finite-time adaptive fuzzy prescribed performance fault-tolerant control (FTC) issue for the steer-by-wire vehicle (SBWV) systems with intermittent actuator faults. Different from the steer-by-wire (SBW) system studied by the previous literatures, the SBWV system involved in this study consists of a vehicle dynamics model and an SBW system, including unmeasurable states and unknown nonlinear dynamics. Fuzzy logic systems (FLSs) are first used to identify the unknown model dynamics, and a fuzzy state observer is constructed to estimate the unmeasured states. Then, to compensate for the influence of intermittent actuator faults, a novel finite-time output-feedback prescribed performance adaptive FTC scheme is developed by using the adaptive backstepping control methodology and co-designing the last virtual controller. The presented control scheme not only guarantees that all signals of the closed-loop system are bounded in the presence of actuator faults, but also ensures that the tracking error converges to a small neighborhood of the zero within the prescribed performance bounded. The computer simulation and comparison results demonstrate the effectiveness of the proposed fuzzy control algorithm. [ABSTRACT FROM AUTHOR]

Categorical features appear in datasets from almost every practice area, including real estate datasets. One of the most critical handicaps of machine learning algorithms is that they are not designed to capture the qualitative nature of the categorical features, leading to sub-optimal predictions for the datasets with categorical observations. This study focuses on a new fuzzy regression functions framework, namely hierarchical fuzzy regression functions, that can handle categorical features properly for the regression task. The proposed framework is benchmarked with linear regression, support vector machines, deep neural networks, and adaptive neuro-fuzzy inference systems with real estate data having categorical features from six markets. It is observed that the proposed method produces better prediction performance for real estate price prediction than the benchmark methods in a wide variety of real estate markets. Since we provide all the required software codes to implement the proposed hierarchical fuzzy regression functions framework, our approach offers practitioners a readily applicable, high-performing tool for real estate price prediction and other regression problems involving categorical independent features. [ABSTRACT FROM AUTHOR]

This paper proposes a novel incipient fault estimation and fault-tolerant control approach for wireless power transfer (WPT) systems with disturbances and incipient sensor faults. Firstly, the dynamic models of the WPT system and incipient faults are established. Then, a k-step incipient fault estimation observer method is analyzed for estimating the states and incipient faults of the system. Based on it, a nonlinear dynamic output feedback fault-tolerant controller is devised to ensure the stability of the WPT system when considering incipient faults and disturbances. Further, the designed controller can monitor the system in real time without the knowledge of the system states. Besides, the stability analysis approach is rigorous, and the proof method can also apply to other similar systems. At last, the simulation example shows that the proposed fault diagnosis method is correct and effective. [ABSTRACT FROM AUTHOR]

This manuscript studies the fuzzy H ∞ control design problem for nonlinear time-varying delay systems in fuzzy form via adaptive event-triggered mechanism. The fuzzy model and an adaptive event-triggered controller are connected in closed-loop form. A looped-functional is established to conduct stability analysis, and the main feature of this functional can fully reflect the sampling feature of control systems. Thus, the achieved results are less conservative. The Wringter inequality is also used to further relax stability analysis. Finally, sufficient conditions are achieved for the existence of event-triggered fuzzy controller, and the resulting closed-loop system reaches an H ∞ control performance. Two examples verify the efficiency of the presented control strategy. [ABSTRACT FROM AUTHOR]

This paper addresses the finite-time control problem of a class of uncertain nonlinear systems subject to input saturation and actuator faults. To approximate the unknown system states, a fuzzy state observer is established where fuzzy logic systems are utilized to estimate the unknown nonlinearities. A nonlinear disturbance observer to estimate the external disturbance of the system. A new finite-time adaptive fuzzy controller is constructed together with the proposed disturbance and state observers, which can guarantee the tracking error into a small neighborhood around zero within finite time. To avoid the tedious and arithmetic problems brought by the traditional backstepping control, the dynamic surface technique is applied, which can effectively reduce the computation burden. It can be proved that not only the boundedness of the closed-loop system states can be guaranteed but also the tracking error is regulated into a small range near the equilibrium in finite time, despite unknown actuator faults and input saturation. Finally, the simulations of two-stage chemical reactor nonlinear system are conducted to demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The predefined-time fuzzy adaptive output feedback control problem is considered for non-strict feedback stochastic nonlinear systems with state constraints. Since the controlled plant contains unknown nonlinear dynamics and unmeasured states, the unknown nonlinear dynamics are handled by using fuzzy approximation technique, and a fuzzy state observer is established to estimate unmeasured states. Then, under the frameworks of a predefined-time stability theory and backstepping control design technique, a new fuzzy adaptive output feedback control method is proposed. It is proved that the controlled system is semi-global practically predefined-time stable in probability by constructing suitable barrier Lyapunov functions. Finally, the spring–mass–damper system is given to confirm the effectiveness of the presented control method. [ABSTRACT FROM AUTHOR]

This paper investigates the event-based adaptive fixed-time (FT) control problem for active suspension systems (ASSs) with actuator faults. The fuzzy approximator is utilized to estimate the continuous function with the unknown car body mass parameters. The FT controller with continuous piecewise function is presented to avoid the singularity problem caused by the derivation of the virtual controller in the backstepping method and to compensate the actuator faults. A switching threshold event-triggered mechanism is evolved for ASSs, which has the advantages of fixed threshold strategy and relative threshold strategy to reduce the communication burden more reasonably. The suspension vertical displacement is restricted by constructing a time-varying barrier Lyapunov function. It is proved that the signals in the closed-loop systems are bounded by Lyapunov stability criterion. Finally, simulation results show that the controller is effective in suppressing the vertical vibration of ASSs. [ABSTRACT FROM AUTHOR]

To improve the anti-disturbance and reliability performance for unmanned surface vehicles subject to actuator faults and external disturbances, an adaptive event-triggered observer-based output feedback control method is proposed. Firstly, a Takagi-Sugeno fuzzy system is established by considering unknown disturbances and actuator faults. Secondly, an adaptive event-triggered mechanism is designed and then the state and disturbance observers are constructed using the output of the event generator. Based on the outputs of the observers, an adaptive event-triggered observer-based output feedback dynamic positioning controller is developed and the asymptotical stability with H ∞ performance is analyzed via the Lyapunov function method. Finally, the advantages of the proposed method are demonstrated via an example. [ABSTRACT FROM AUTHOR]

The problem of adaptive arbitrary convergence time terminal sliding mode control (TSMC) for nonlinear networked systems with completely unknown functions and nonresponsive UDP stream disturbances is studied. In this work, an improved sliding surface based on arbitrary convergence time is designed to overcome the issue that the convergence rate depends on the system state. Different from the traditional TSMC, this paper introduces holistically an auxiliary term (nonautonomous differential equation) into the design of a sliding mode controller, which can compensate for the influence of neural adaptive approximation error and ensure the convergence of a closed-loop system at prescribed time. A robust compensation signal is also constructed by introducing a super twisting disturbance observer to process nonresponsive UDP flows. In addition, the controller is designed in a piecewise continuous manner, so that the sliding mode surface can be selected arbitrarily, according to the adaptation after the prescribed time. The effectiveness of the new controller is verified by extensive simulations in comparison with related works. [ABSTRACT FROM AUTHOR]

This paper is mainly concerned with the leaderless consensus problem for nonlinear multi-agent systems (MAS) with unknown mismatched nonlinear dynamics and external disturbances. First, a novel adaptive controller is designed to achieve bounded consensus with a linear feedback term, the RBF neural network (RBFNN) adaptive approximation term, a discontinuous feedback term, and a state constraint term. Furthermore, on this basis, an observer-based robust uniform control scheme against disturbance is proposed to achieve the leaderless consensus of MAS with unmeasurable states under the directed graph. Compared with the previous works, the proposed controller is less conservative. Finally, two simulation-based examples are provided to verify the effectiveness of the proposed control scheme. [ABSTRACT FROM AUTHOR]

In this article, the issue of neural adaptive decentralized finite-time prescribed performance (FTPP) control is investigated for interconnected nonlinear time-delay systems. First, to bypass the potential singularity difficulties, the hyperbolic tangent function and the radial basis function neural networks are integrated to handle the unknown nonlinear items. Then, an adaptive FTPP control strategy is developed, where an improved fractional-order filter is applied to tackle the tremendous "amount of calculation" and eliminate the filter error simultaneously. Furthermore, by considering the impact of bandwidth limitation, an adaptive self-triggered control law is designed, in which the next trigger instant is determined through the current information. Ultimately, it can be demonstrated that the proposed control scheme not only guarantees that all states of the closed-loop system are semi-globally uniformly ultimately bounded, but also that the system output is confined to a small area in finite time. Two simulation examples are carried out to verify the effectiveness and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

This article considers a fuzzy adaptive event-triggered control design problem for electro-hydraulic systems. The addressed electro-hydraulic system contains immeasurable states and unknown nonlinear dynamics. Fuzzy logic systems (FLSs) are utilized to model the controlled electro-hydraulic system, and a state observer is formulated to get the estimations of the immeasurable states. Subsequently, a novel event-triggered strategy is introduced by using first-order filter technique, which can reduce the frequent updating of the voltage input. Then, by constructing composite Lyapunov functions, an observer-based fuzzy adaptive event-triggered control method is presented. The stability of the controlled electro-hydraulic system and the convergence of the tracking error are proved. Finally, the computer-simulated studies confirm the effectiveness of the presented control method. [ABSTRACT FROM AUTHOR]

This article investigates adaptive fuzzy fixed-time fault-tolerant control for strict-feedback nonlinear systems with unknown nonaffine nonlinear faults. To address the nonaffine nonlinear fault, Butterworth filter signal is introduced into the adaptive backstepping control design procedures. The "explosion of complexity" is avoided by adopting command filter method, and the filter errors can be eliminated by introducing compensating signals. Fuzzy logic system as an approximator that is employed to estimate the unknown term in the system. Lyapunov stability analysis testifies that the closed loop system is semiglobally fixed-time stable, and the tracking error can converge to a small neighborhood of zero in a fixed time that the convergence time is not affected by the initial conditions of the system. The simulation consequences illustrate the effectiveness of the proposed control method. [ABSTRACT FROM AUTHOR]

In this article, a nonlinear mathematical model of the biological phenomena in chemotherapy cancer treatment is considered as a class of unknown discrete-time systems when the input data and the measured output are only available. The input data are the drug administration represented as the control effort and the output is the tumor cells population. As a result, the actor-critic architecture is constructed without the full-state observer. Two sets of IF-THEN rules are utilized for fuzzy rules emulated networks by human knowledge according to the pharmacokinetic and pharmacodynamic details. The learning laws are derived from the concept of the incoherent reward function. Thus, the convergence of the internal signals and the robustness are accomplished by the theoretical and numerical results. Furthermore, the comparative results are given to demonstrate the effectiveness of the proposed scheme. [ABSTRACT FROM AUTHOR]

A fixed-time adaptive fuzzy second-order sliding mode (SOSM) approach has been designed to handle the problem of nonlinear systems with output constraints. According to the advantages of using fuzzy logic systems, the unknown bounds of uncertainties can be approached dynamically. The problem of output constraints has been well handled by constructing a barrier Lyapunov function. Next, with the help of adding a power integrator technique and adaptive fuzzy control, a fixed-time adaptive fuzzy SOSM controller is designed for the considered systems. In addition to the above, the controller can not only promote the sliding variables to converge to the origin in fixed time, but also stabilize the variables in the constrained range. In other words, under the proposed method, the systems can be stable in a specified time no matter how the initial value changes. Lastly, a numerical example is used to verify the performance of the proposed SOSM control tactic. [ABSTRACT FROM AUTHOR]

In this paper, an adaptive fuzzy control approach for incommensurate fractional-order multi-input multi-output (MIMO) systems with unknown nonlinearities and input saturation is presented. First, the nonlinear terms of MIMO systems are identified by introducing the fuzzy logic systems, and an adaptive compensating control term is provided to estimate the approximation errors. Then, the drawback of "explosion of complexity" in the typical backstepping is effectively figured out via an improved command filter, and the influence of filtered error is avoided by constructing the error compensation laws. Meanwhile, the input saturation issue is addressed by utilizing the fractional-order auxiliary equations. Derived from the fractional-order Lyapunov stability theory, it is proved that all signals of the closed-loop system are guaranteed to be bounded. Finally, the availability of the investigated control scheme is verified by simulation examples. [ABSTRACT FROM AUTHOR]

This paper presents an in-depth study and analysis of the AC drive control simulation of a supercapacitor tram using a high-order neural network pattern discrimination algorithm. Firstly, the line conditions and shunting locomotive operation conditions of a freight coal loading station are analyzed, the capacity of the onboard supercapacitor energy storage device is estimated using traction simulation calculations, the supercapacitor is formed by the series–parallel connection of supercapacitor monoliths group module, and the mathematical model of the supercapacitor energy storage system is obtained. In response to the existence of fuzzy controllers with human-set parameters and potential errors when writing fuzzy rules, the self-learning capability possessed by the adaptive neuro-fuzzy network (ANFIS) is used to improve the accuracy of the prediction model by training and learning to the model a large amount of experimental data with the ANFIS controller, and the simulation model of the dynamic setting of the supercapacitor voltage threshold of the urban rail energy storage system is built using the software, and the comparison and analysis show that the traction network voltage amplitude under the adaptive neuro-fuzzy network control strategy is smaller than the traction network voltage amplitude under the fuzzy control strategy. The global searchability of the optimization algorithm is ensured. In the middle of the search, a medium-precision simplex is used for parallel local search to prevent the searcher from skipping the global optimum in the process of rapid convergence. In the later stage of the search, the optimization range is already within the global optimal range. Subsequently, the advantages and disadvantages of various locomotive topologies are analyzed by using software, and the topology of the supercapacitor shunting locomotive is analyzed according to the design requirements and the actual situation, and the supercapacitor power system scheme of the shunting locomotive is designed, and the traction electric drive system of the supercapacitor shunting locomotive is designed, and its main structural performance parameters are determined. Finally, the overall modeling of supercapacitor shunting locomotive is carried out, including the whole vehicle dynamics model, automatic charging model, supercapacitor model, and motor model, and then, simulation analysis is carried out based on building a relatively perfect model, followed by further stimulation through software to verify the rationality of the design. [ABSTRACT FROM AUTHOR]

Here, a multi-input–output control strategy-based adaptive system is implemented to regulate the glycaemic and hypertension (HT) level concurrently for post-operative patients. The current medical research identifies the relationship between diabetes and HT, and these two diseases have possible overlap in their disease aetiology. Based on the continuum, the blood glucose and blood pressure (BP) have to be measured independently and control the infusion to maintain optimally based on the variations of diabetic mellitus and HT to avoid the major complications for the perioperative condition. Based on the analysis, the post-operative strain may increase HT and may increase the glycaemic level, and this uncertainty of disparity may lead to BP, hyperinsulinemia, cardio diseases, and osmotic diuresis along with hyperglycaemia. The proposed adaptive cascade control strategy illustrates two different types of control loops independently, and these loops adopt an adaptive control strategy with parametric compensation. This adaptive control algorithm integrates the cascade methodology along with expert knowledge to treat these diseases by using adaptation laws with the help of fuzzy logic to regulate the proper insulin and sodium nitroprusside (SNP) infusion. The output response of the plasma glucose concentration and HT regulation was shown along with insulin infusion rate and SNP infusion rate based on the extensive simulation readings. The attained simulation results demonstrate that the adaptive control strategy shows better outcomes for the infusion and may achieve potentially better control on HT and glycaemic levels for post-operative patients. [ABSTRACT FROM AUTHOR]

The article titled "Retraction Note: A fuzzy-based adaptive multi-input-output scheme in lieu of diabetic and hypertension management for post-operative patients: an human-machine interface approach with its continuum" has been retracted by the Editor-in-Chief and the publisher. The retraction was due to concerns regarding compromised editorial handling and peer review process, inappropriate references, and the article not being in scope of the journal or guest-edited issue. The authors disagree with the retraction. Springer Nature, the publisher, remains neutral in regards to jurisdictional claims and institutional affiliations. [Extracted from the article]

This paper handles the issue of adaptive control and faults estimation of a class of T-S singular fractional order systems(SFOSs) with H ∞ performance, where the fractional order belongs to (0, 1). Firstly, a novel observer for SFOSs is proposed, which estimate unmeasurable or partially measurable state and faults, simultaneously. Secondly, regarding to the information obtained by the above observer and the designed adaptive parameters, an adaptive controller is proposed to estimate actuator faults of the SFOSs. Further, it is indispensable to ensure the admissibility of the proposed fuzzy SFOSs with H ∞ performance, novel sufficient conditions are obtained by linear matrix inequalities (LMIs), Finally, to illustrate the method proposed above is available, simulation examples are presented. [ABSTRACT FROM AUTHOR]

This paper addresses a tracking control problem with prespecified accuracy for uncertain switching nonlinear systems under arbitrary switching with periodically time-varying parameters. To approximate the unknown nonlinear functions and unknown periodically time-varying parameters, the radial basis function neural network and Fourier series expansion are introduced, respectively. Compared with the previous results of unknown nonlinear switching system approximation, the upper bounds of the approximation errors are considered for the first time. And then, a new adaptive NN control scheme is constructed by using backstepping technique and common Lyapunov function theory. It can be proved that all the signals in the closed-loop system are semi-globally uniformly ultimately bounded and the tracking error converges to the prescribed neighborhood of zero. Two examples are provided to verify the feasibility and advantages of the proposed approach in this paper. [ABSTRACT FROM AUTHOR]

For the nonlinear TCP/AWM network congestion control system with external disturbances, under the framework of backstepping control method, an adaptive network congestion control strategy based on event-triggered mechanism is proposed. This strategy reduces the waste of network resources by introducing an event-triggered mechanism and uses RBF neural network to deal with external disturbances. The Lyapunov theory is used to prove that all signals in the closed-loop system are bounded. Finally, the proposed method is verified by simulation and is compared with PID, which further verifies the effectiveness of the proposed control method. [ABSTRACT FROM AUTHOR]

In this paper, an adaptive fuzzy generalized predictive controller is proposed for the anti-chaos control where the system dynamics are assumed to be unknown or uncertain in large. In the proposed mechanism, the control signal is generated by an input constraint generalized predictive controller to track the Duffing oscillator which is used as a chaotic reference system. The adaptive fuzzy system, as a real plant model, is employed to obtain prediction through the receding horizon. In order to show the capability of the proposed mechanism, three different payloads and noise cases are studied in the real-time control experiments of flexible-joint manipulator and tracking results are compared with three more non-model-based controllers which are conventional adaptive fuzzy control, indirect adaptive fuzzy sliding mode controller and proportional–integrative–derivative control. Results show that the proposed mechanism has better control performance than the others. [ABSTRACT FROM AUTHOR]

This paper focuses on a problem of composite adaptive fuzzy decentralized tracking control for a class of uncertain pure-feedback interconnected large-scale nonlinear systems with unmeasurable states. A fuzzy state observer is designed by using fuzzy logic systems; thus, the unmeasurable states of pure-feedback nonlinear systems are estimated based on the designed fuzzy state observer. A serial–parallel estimation model is designed by using the fuzzy state observer. To avoid the analytic computation, the command filters are employed to produce the command signals and their derivatives. The fuzzy adaptive laws are constructed by using prediction errors and compensating tracking errors. Finally, a controller is constructed by dynamic surface control technique. Through the proposed control method, all the signals in the closed-loop system are bounded, and the output of the system can track the given reference signal. The simulation studies verify the effectiveness of the proposed control method in this paper. [ABSTRACT FROM AUTHOR]

This paper presents an adaptive backstepping control scheme for electrically driven robotic manipulator (EDRM) system with uncertainties and external disturbances by using neural network disturbance observer (NNDO) and dynamic surface control (DSC) design technique. NNDO is employed to estimate the uncertainties and external disturbances such that the priori information of the unknown dynamics will not be needed. To overcome the problem of "explosion of complexity" inherent in the backstepping design method, the DSC technique is integrated into the adaptive backstepping control design framework, where the NNDOs with adaptive composite law are utilized to compensate the uncertainties and external disturbances of EDRM. Based on the Lyapunov stability theory, it can be proven that the closed-loop system is stable in the sense that all the variables are guaranteed to be uniformly ultimately bounded. The results of simulation and experimental tests demonstrate the approximation capability of NNDO and the effectiveness of the proposed adaptive DSC scheme. [ABSTRACT FROM AUTHOR]

In this paper, an event-triggered neural intelligent control for uncertain nonlinear systems with specified-time guaranteed behaviors is proposed. To cope with constrained communication resources, an event-triggered mechanism using switched thresholds is devised without involving input-to-state stability assumption, such that a better design flexibility and freedom can be provided. In addition, a minimum-learning-parameter-based state observer is developed to online estimate the unavailable states and uncertainties at the same time, which effectively eliminates the issue of learning explosion without sacrificing the identification precision. Furthermore, in pursuit of making a compromise between sampling cost and tracking performance, a modified barrier Lyapunov function based on a time-varying finite-time behavior boundary is constructed in the controller design, which can guarantee that the tracking error converges to a predetermined region within a specified time. Then by introducing the Nussbaum gain technique to handle the unknown control direction, an event-triggered neural output feedback control strategy is synthesized within the framework of dynamic surface control. Meanwhile, with the aid of Lyapunov synthesis, all the signals involved in the closed-loop system are proved to be bounded while Zeno phenomena is circumvented, and system outputs are well within the predefined region. Finally, an application on control design for a micro-electro-mechanical system gyroscope is given to validate the efficiency and superiority of proposed intelligent control scheme. [ABSTRACT FROM AUTHOR]

The design of networked nonlinear control system is a very challenging problem due to the coupling of the system uncertainties (e.g., model accuracy, noise, nonlinearity) and network effects (e.g., packet dropouts, time delay). In this paper, a deep representation-based predictive compensation method is proposed for networked nonlinear systems with packet-dropouts in the feedback and forward channel. Different from the existing compensation methods based on open-loop prediction, the proposed method is based on feedback compensation and does not require a nominal system model, so that it can avoid the coupling of system uncertainties and network effects as well as the occupation of network bandwidth. Specifically, a deep sequence to sequence learning scheme is firstly employed to encode the correlations of state and control sequences into deep feature representations. Furthermore, within the embedding space spanned by the learned features, according to the state-control sequence of each sampling step, a prediction of the next control command is generated as compensation for packet dropout. The stability of the overall system is rigorously proved by the Lyapunov theory, which reveals that the control errors for the networked control systems with packet dropouts asymptotic converge to a small neighborhood of the origin. We further evaluate the performance of the proposed strategy on a wheeled mobile robots simulation platform, and the experimental results demonstrate that our method can achieve high compensation accuracy and robustness concerning packet dropouts, even in the case of the maximum continuous packet dropouts specified by the network communication protocol. [ABSTRACT FROM AUTHOR]

In this paper, an adaptive neural network (NN) output feedback control is investigated for incommensurate fractional-order permanent magnet synchronous motors under the condition of input saturation. First, a NN state observer is presented to obtain the 'virtual estimate' of angle speed, where the unknown function is approximated by the NN. Then, in order to solve the input saturation problem, an auxiliary system is developed under fractional-order framework. Next, the command filtered technology with an error compensation mechanism is used to handle the 'explosion of complexity' in backstepping and remove the filtering errors. In addition, the frequency distributed model is utilized such that the Lyapunov theory is available in the backstepping design and the system stability is demonstrated. Finally, numerical simulations confirm the availability of the proposed design. [ABSTRACT FROM AUTHOR]

This document is a correction notice for an article titled "Novel neural adaptive terminal sliding mode control for TCP network systems with arbitrary convergence time" published in the journal Neural Computing & Applications. The correction addresses errors in the reference citations of the original article, specifically on pages 20372 and 20373. The incorrect citation information was given as 22, but it should have been 24. The original article has been corrected. The publisher, Springer Nature, maintains a neutral stance on jurisdictional claims and institutional affiliations. The authors of the article are Xuelei Qi, Chen Li, Bao Chen, Wei Ni, and Hongjun Ma. [Extracted from the article]

This paper presents an adaptive fuzzy fault-tolerant tracking control for a class of unknown multi-variable nonlinear systems, with external disturbances, unknown control sign, and actuator faults. By employing fuzzy logic systems, the unknown nonlinear dynamics and the state-dependent actuator faults are approximated, and by utilizing a Nussbaum-type function, the issue of unknown control sign is solved. The proposed control scheme is based on two forms, an adaptive fuzzy controller along with a robust controller that is equipped with a Nussbaum-type gain function, which guarantees stability with the boundedness of all signals involved in the closed-loop system. To prove the accuracy, and the effectiveness of the proposed control scheme, a simulation example on two-inverted pendulums system is carried out. [ABSTRACT FROM AUTHOR]

Current oil prices and global financial situations underline the need for the best engineering practices to recover remaining hydrocarbons. A good understanding of the elastic behavior of the reservoir rock is extremely imperative in avoiding the severe well drilling problems such as wellbore in-stability, differential sticking, kicks, and many more. Therefore, it is plausible to have a good estimation of the rock elastic behavior for successful well operations. This study presents a generalized empirical model to predict static Poisson's ratio of the carbonate rocks. Petrophysical well logs were used as inputs, and the laboratory measured static Poisson's ratio was used as an output. Three supervised artificial intelligence (AI) techniques were used, viz. artificial neural network (ANN), support vectors regression, and adaptive network-based fuzzy interference system. An extensive prediction comparison was made between these three AI techniques. Based on the lowest average absolute percentage error (AAPE) and highest coefficient of determination (R2), the ANN model proposed to be the best model to predict static Poisson's ratio. To transform black box nature of AI model into a white box, ANN-based empirical correlation is also developed to predict the static Poisson's ratio. Comparison of the developed empirical correlation with previously established approaches to find static Poisson's ratio on an unseen published dataset revealed that the equation of ANN can predict the static Poisson's ratio with implicitly less AAPE and with high R2 value. The proposed model with the empirical correlation can assist geo-mechanical engineers to predict the static Poisson's ratio in the absence of core data. The novelty of the new equation is that it can be used without the need of any AI software. [ABSTRACT FROM AUTHOR]

This paper presents a novel observer-based hybrid adaptive fuzzy controller for affine and nonaffine nonlinear systems with external disturbance. The suggested design is so easy and does not need a mathematical model for system under control and also it is very simple, efficient and robust. Based on the adaptive method and the system states observer, an observer-based adaptive fuzzy method is proposed to control an uncertain nonlinear system. Also, a supervisory controller term is employed to attenuate the residual error to a desired level and compensate the both uncertainties and observer errors. Although proposed control method needs the uncertainties to be bounded, it does not need this bound to be identified. Stability of the proposed method is shown based on Lyapunov theory and also the strictly positive real condition if all the implicated signals are uniformly bounded. Finally, in our simulation studies, to demonstrate the usefulness and efficiency of the suggested technique, an uncertain nonlinear system is employed. [ABSTRACT FROM AUTHOR]

This paper deals with the problem of adaptive fuzzy tracking control for a single-link robotic manipulator coupled to a brushed direct current motor with actuator saturation. Fuzzy logic systems are used to approximate the unknown nonlinear systems. The filtered signals are introduced to eliminate the interference of high-frequency signals. The virtual/actual control inputs are derived from the solutions of a series of dynamical equations. Under the framework of the backstepping control design, an observer-based output feedback control design scheme is proposed. It is proved that the control approach can guarantee that all the signals in the closed-loop system are bounded. [ABSTRACT FROM AUTHOR]

In this paper, a novel adaptive fuzzy variable-structure control approach is proposed for a class of multivariable nonaffine uncertain systems subject to dynamic nonlinear disturbances and actuator nonlinearities (dead zone and sector nonlinearities). By using the Taylor series expansion, an equivalent model in affine-like form is first derived for the nonaffine system. Then after, an adaptive fuzzy variable-structure controller is designed based on this affine-like equivalent model. The adaptive fuzzy systems are used to appropriately approximate the unknown nonlinear functions. The so-called SDU decomposition of the control gain matrix is exploited in the controller design and the stability analysis. It is proved that the proposed adaptive fuzzy control scheme can guarantee that all involved signals in the closed-loop system are semi-globally uniformly ultimately bounded, and the tracking error converges to a small neighborhood of the origin. Finally, simulation results are presented to illustrate the effectiveness of this adaptive control system. [ABSTRACT FROM AUTHOR]

In this paper, the adaptive fuzzy decentralized tracking control problem is investigated for a class of uncertain large-scale nonlinear systems, interacted through their outputs with completed unknown time-varying delays. The novel contribution is to remove the common assumptions on the unknown time delays by the proposed delay replacement technique, so that the controller design is not dependent on these assumptions any more, and thus, added flexibility in decentralized control design is achieved. Furthermore, the approximation and replacement errors are handled by the adaptive technique. All closed-loop signals are proved to be semiglobal uniform ultimate boundedness, and the tracking errors are guaranteed to converge to a small residual set around the origin. The simulation studies illustrate the effectiveness of the control scheme. [ABSTRACT FROM AUTHOR]

In this paper, the projective synchronization problem of two fractional-order different chaotic (or hyperchaotic) systems with both uncertain dynamics and external disturbances is considered. More particularly, a fuzzy adaptive control system is investigated for achieving an appropriate projective synchronization of unknown fractional-order chaotic systems. The adaptive fuzzy logic systems are used to approximate some uncertain nonlinear functions appearing in the system model. These latter are augmented by a robust control term to compensate for the unavoidable fuzzy approximation errors and external disturbances as well as residual error due to the use of the so-called e-modification in the adaptive laws. A Lyapunov approach is adopted for the design of the parameter adaptation laws and the proof of the corresponding stability as well as the asymptotic convergence of the underlying synchronization errors towards zero. The effectiveness of the proposed synchronization system is illustrated through numerical experiment results. [ABSTRACT FROM AUTHOR]

Reinforced concrete slabs, just as the other structural elements, are highly affected by the high temperatures. Due to the decrease in strength of reinforced concrete members under high temperature, bearing moment capacity of reinforced concrete slabs also decreases. In this study, a prediction model is investigated in order to determine the bearing moment capacities of reinforced concrete slabs under high temperature. Pre-calculated moment capacities of slabs exposed to fire are predicted by the implementation of adaptive neuro-fuzzy inference system (ANFIS) and the prediction performance of ANFIS model is investigated. The bending capacities of slabs with different concrete characteristics and different times of exposure are calculated. High temperature resulting from the duration of fire exposure is calculated as a function of time in accordance with ISO 834. The temperature distribution inside the slab is determined by the adoption of a steady-state one-dimensional heat transfer. The slab was separated into slim slices and the heat in each slice is determined depending on the time of exposure. Forces and resistance of materials under fire exposure are calculated by applying the reduction coefficients in Eurocode 2. Results confirm the high prediction capability of ANFIS model. [ABSTRACT FROM AUTHOR]

This paper focuses on the problem of decentralized adaptive fuzzy control for a class of pure-feedback large-scale nonlinear systems with time-delay. By combining fuzzy logical systems' universal approximation capability with adaptive backstepping technique, an adaptive fuzzy control scheme is proposed. It is proved that the developed controller guarantees that all the signals in the closed-loop system are semi-globally uniformly ultimately bounded in mean square. Simulation results are provided to demonstrate the effectiveness of the proposed control scheme. [ABSTRACT FROM AUTHOR]

In the present work, layer thickness of duplex coating made from thermo-reactive deposition and diffusion has been predicted by Adaptive network-based fuzzy inference systems (ANFIS). A duplex surface treatment on five steels has been developed involving nitrocarburizing and followed by chromium thermo-reactive deposition (TRD) techniques. The TRD process was performed in molten salt bath at 550, 625 and 700 °C for 1-30 h. The process formed a thickness up to 9.5 μm of chromium carbonitride coatings on a hardened diffusion zone. A model based on ANFIS for predicting the layer thickness of duplex coating of the specimens has been presented. To build the model, training and testing using experimental results from 84 specimens were conducted. The data used as inputs in ANFIS models are arranged in a format of twelve parameters that cover the chemical composition (C, Mn, Si, Cr, Mo, V, W), the pre-nitriding time, ferro-chromium particle size, ferro-chromium weight percent, salt bath temperature and coating time. According to these input parameters, in the Adaptive network-based fuzzy inference system models, the layer thickness of duplex coating of each specimen was predicted. The training and testing results in ANFIS models have shown a strong potential for predicting the layer thickness of duplex coating. [ABSTRACT FROM AUTHOR]

In this paper, an adaptive fuzzy output feedback fault-tolerant control scheme is developed for a class of nonlinear systems with actuator faults, unmodeled dynamics and without assuming the states being available for control design. Fuzzy logic systems are employed to approximate unknown nonlinear functions, and a fuzzy state observer is established to estimate the unmeasured states. By combining adaptive backstepping technique with changing supplying function technique and the nonlinear fault-tolerant control theory, a novel adaptive fuzzy fault-tolerant output feedback control approach is developed. It is proved that proposed control approach guarantees that all the variables of the closed-loop system are bounded. The simulation results are provided to illustrate the effectiveness of the proposed control approach. Compared with the existing results, the main contributions of this paper are as follows: (1) the proposed control method removes the restrictive assumption that all the states of the controlled system be measured directly; and (2) the proposed control method cannot only compensate for the actuator faults, but also solve the problem of the unmodeled dynamics. [ABSTRACT FROM AUTHOR]

Roof fall is one of the most important problems connected with underground coal mines because it plays a significant role in financial and human losses. Hence, it is essential to accurately predict the roof fall rate for the purpose of controlling, reducing, and/or even eliminating the risk of the involved problems. On the other hand, there are many different parameters that make a considerable impact on the occurring roof rate. Most of these factors are not completely known or measurable. Therefore, the problem of predicting roof fall is vague, sophisticated, and complex. Adaptive neuro-fuzzy inference system (ANFIS) is a powerful and robust tool for modeling linear and non-linear patterns in science and engineering problems. In this paper, the ANFIS system is applied to model the roof fall rate in coal mines. The constructed model uses the subtractive clustering method to generate fuzzy rules based on 109 data of roof performance from US coal mines. The results demonstrate that prediction of roof fall rate by the ANFIS model is satisfactory. [ABSTRACT FROM AUTHOR]

Conventional particle swarm optimization (PSO) is an appropriate optimization method, yet it suffers from some drawbacks. Trapping in local minimums or premature convergence of particles leads to unsatisfactory levels of optimization. In this paper, a new method for improving PSO is provided. In the proposed method (FAIPSO), the acceleration coefficients c1 and c2 are adaptively adjusted for each particle in each iteration. For the adaptive controlling of the acceleration coefficients, a fuzzy inference system is used. This fuzzy inference system comprises six inputs, two outputs, and ten rules. In order to reduce inertia weight (ω), a parabolic model is used. In addition to this, a range of vision (Mu) is defined for each of the particles and every one of the particles searches within this range. This range of vision changes adaptively. In order to adaptively control the range of vision, a fuzzy inference system is employed. This system has two inputs, one output, and 14 rules. To test the proposed method, 16 benchmarks, each inheriting special characteristics, are used. The performance of the proposed method was compared with that of ten types of PSOs (each of which are among the reputable works of the PSO subject). According to the results, the proposed method shows a good performance and is more appropriate than other methods. [ABSTRACT FROM AUTHOR]

In this study, an adaptive network-based fuzzy inference system (ANFIS) approach is presented for modeling of high-strength concrete under uniaxial loading. The ANFIS approach applied to test the data of concrete cylinder test is available in the literature. In this paper, the stress–strain behavior of high-strength concrete subjected to axial load is obtained by using the ANFIS model. It is shown that the present model can predict the stress–strain behavior of concrete accurately by taking into account the effective parameters. The advantage of the proposed approach is that the stress–strain behavior of high-strength concrete can be predicted easily. The results of ANFIS approach are compared with the analytical models given in various studies concerning cylinder tests. The ANFIS approach results given show a good agreement with the experimental results. [ABSTRACT FROM AUTHOR]

In this paper, the performances of fuzzy proportional-integral-derivative (PID) and classic PID controllers are compared through simulation studies. For this purpose, the level control of a two interacting tanks system, temperature control of unstable continuous stirred tank reactor (CSTR), and pH control of pH neutralization process were selected. In the level control process, results indicated that both of classic and fuzzy PID controllers have approximately the same performance. However, adjusting the classic PID controller is simpler than fuzzy PID controller. Therefore, in simple processes like level control in two interacting tanks, classic PID controllers are preferred. In an unstable CSTR, classic PID controller is not suitable due to the instability of the system. Fuzzy PID controller is more useful than classic PID controller in this type of systems. In pH neutralization process, using classic PID controller is inappropriate because of nonlinearity of the system and the fuzzy PID controller is more efficient. [ABSTRACT FROM AUTHOR]

Electronic throttle valves are electromechanical systems which regulate the air flow inside gasoline engines. The objective of electronic throttle valve control is to ensure fast and accurate reference tracking of the valve plate angle. This control demands are hard to accomplish since the plant is burdened with strong nonlinear effects and parameters uncertainty. In this paper, a genetic algorithm-based adaptive fuzzy sliding mode controller (AFSMC) is proposed for an electronic throttle considering actuator nonlinearities. In the AFSMC approach, fuzzy logic system is applied to approximate the plant model and the actuator model, the sliding mode controller makes full use of the plant model to guarantee robust control even in the presence of parameters uncertainty, and genetic algorithm is developed to search the optimal control gains values of the AFSMC. The performance of the AFSMC is verified by computer simulation and experiment. [ABSTRACT FROM AUTHOR]

In this paper, fuzzy BAM neural networks with distributed delays and time-varying delays in the leakage terms are studied. Sufficient conditions for the global exponential stability of equilibrium point are established by constructing suitable Lyapunov functional and differential inequality techniques, which complement and improve the main results of Zhang et al. (Adv Differ Equ 8:1–12; 2011 ) and Gopalsamy (J Math Anal Appl 325:1117–1132; 2007 ). Moreover, an example is given to demonstrate the feasibility of our method. [ABSTRACT FROM AUTHOR]

This study aims to examine the fundamental forces driving stock returns and volatility across the international stock markets. Logistic regression analysis is used to investigate possible highly correlated among 9 international stock markets with stock market of Taiwan. Afterward, the highly correlated stock indices with Taiwan would be selected as the input variables of adaptive network-based fuzzy inference system (ANFIS) model to predict stock prices and their direction of Taiwan Stock Exchange Capitalization Weighted Stock Index. The experimental results of the proposed model are contrasted with other models including the first-order model (Chen in Fuzzy Sets Syst 81(3):311–319, 1996 ), weighted fuzzy time series model (Yu in 349:609–624, 2005 ), simple neural network model (Huarng and Yu in Phys A 363(2):481–491, 2006 ), multivariate model (Huarng et al. in J Travel Tour Mark 21(4):15–24, 2007 ), ANFIS with volatility causality (Cheng et al. in Neurocomputing 72(16–18):3462–3468, 2009 ), ANFIS with AR model (Chang et al. in Appl Soft Comput 11:1388–1395, 2011 ), and artificial bee colony-recurrent neural network model (Hsieh et al. in Applied Soft Computing 11:2510–2525, 2011 ). Finally, the proposed model produces with lower inaccuracy rate and offers higher direction preciseness than above previous models. The benefit of this methodology depended on its application of a hybrid approach to predict the stock prices and direction with higher accuracy. [ABSTRACT FROM AUTHOR]

In today’s competitive world, most organizations need to successfully develop new products. The success of new products can be a competitive weapon and advantage for a firm to survive in the current dynamic markets. The most important aspect of the product design is identifying customers’ needs of products. One of the most common methods to satisfy customers’ needs is improvement of customers’ satisfaction. The present paper applies the aspects of the 4P marketing mix (product, price, place, and promotion) for modeling the relationship between customers’ satisfaction and new product design with handling nonlinearity as well as fuzziness. A methodology based on the adaptive neuro-fuzzy inference systems (ANFIS) approach is presented to improve customers’ satisfaction while setting products’ design attributes in a fuzzy environment. The intelligent approach of the present study is then applied to predict customers’ satisfaction and design new product through 4P marketing mix concept in an actual case in the freezer refrigerator industry. A complete sensitivity analysis is run to assess significance or influence of each input variable on customers’ satisfaction. The superiority of ANFIS is proved by error analysis. The proposed approach would help practitioners within the field of marketing and new product design teams to enhance customers’ satisfaction and set new products’ attributes. [ABSTRACT FROM AUTHOR]

This paper proposes an adaptive functional-link-based neural fuzzy control (AFNFC) system based on complementary sliding-mode approach. The proposed AFNFC system is composed of a neural controller and a robust compensator. The neural controller uses a functional-link-based neural fuzzy system (FNFS) to approximate an ideal complementary sliding-mode controller, and the robust compensator is designed to eliminate the effect of the approximation error between a neural controller and an ideal complementary sliding-mode controller. Since the consequent part of the fuzzy rules in FNFS uses an orthogonal Hermite polynomial-based non-linear combination, the proposed FNFS can approximate an ideal complementary sliding-mode controller with good learning accuracy. Finally, to enhance the control performance of the proposed AFNFC system, a 32-bit ×86-microprocessor is adopted for the implementation of the proposed control system. A comparison among the fuzzy sliding-mode control, the intelligent-complementary sliding-mode control, the supervisory fuzzy neural network control, and the proposed AFNFC system is made. The experimental results demonstrate that the proposed AFNFC system can achieve favorable tracking performance and robust with regard to parameter variations for a DC gear motor driver. [ABSTRACT FROM AUTHOR]

In this paper, an adaptive fuzzy output feedback control approach is presented for a class of single-input single-output uncertain nonlinear systems with unknown backlash-like hysteresis and unmeasured states. Fuzzy logic systems are utilized to approximate the unknown nonlinear functions, and a state filter observer is designed to estimate unmeasured states. Combining the backstepping recursive design with modular design techniques, a new adaptive fuzzy output control scheme is developed. It is proved that the proposed control approach can guarantee that all the signals of the resulting closed-loop system are semiglobally uniformly ultimately bounded, and the tracking error converges to a small neighborhood of the origin. A simulation is included to illustrate the effectiveness of the proposed approach. The important feature of the proposed control approach is that it can solve the states immeasurable problem of nonlinear systems with unknown backlash-like hysteresis and the problem of unknown virtual control coefficients. [ABSTRACT FROM AUTHOR]