International Journal of Fuzzy Systems最新文献

In the environment of global warming, it is very important to choose rail transport solutions with the lowest possible CO₂ emissions, taking into account economic, technical and safety factors. As an important part of the modern transportation system, railway transportation appears in most transportation scenarios. Therefore, choosing an eco-friendly railway transport selection scheme is conducive to further reducing pollution emissions and preventing the further deterioration of the ecological environment. Triangular Dense Fuzzy Linguistic Term Lock Set (TDFLTS) is a tool for describing uncertain information. CODAS-COPRAS is a method to solve the multi-attribute group decision-making problem. This paper first introduces TDFLTS to describe uncertain information. Secondly, the distance measure and similarity measure between TDFLTS are proposed. Then, MEREC and DEMATEL methods are used to obtain attribute weights. Finally, CODAS-COPRAS method is used to solve the multi-attribute decision-making problem under TDFLTS environment, and it is applied to the research of railway transportation scheme selection.

A formation and containment control problem is discussed for the Nonlinear Multi-Autonomous Ship Systems (NM-ASSs) with uncertainties and disturbances based on the Interval Type-2 (IT-2) Takagi-Sugeno Fuzzy Model (T-SFM) in this paper. A different formation control scheme is provided by using the state feedback controller of leader ships. Because of this feature, information communication between leader ships, which are farthest from each other in formation and containment problems, isn’t required. However, the analysis problem in the IT-2 fuzzy containment controller design method is caused by the leader’s formation controller. A design concept for the unknown leader’s input of linear multi-agent systems is successfully extended to solve the problem by the expression of IT-2 T-SFM. Nevertheless, the analysis process will become conservative while the agent number or fuzzy rule number is increased. Thus, a relaxed analysis method is also considered for the containment controller design. Additionally, the passive performance constraint is combined into the IT-2 fuzzy formation controller design method to dissipate the disturbance effect and improve the control performance. Finally, two examples are provided to illustrate the advantage of the proposed IT-2 fuzzy controller design method in the formation and containment control problem of NM-ASSs.

In the field of fuzzy sets, distance measures can effectively quantify the relevant uncertainty. Regarding hesitant fuzzy sets (HFSs), improved hesitant fuzzy distance measures have recently been proposed by fusing classical distance measures with hesitation degrees, and the corresponding information enrichment can be probabilistically advanced to pursue new distance measures of probabilistic hesitant fuzzy sets (PHFSs). Aiming at PHFSs, the improved distance measures of HFSs are simulated and extended in this paper, and thus improved distance measures of PHFSs are proposed; the new PHFSs distances are utilized to construct a new method of probabilistic hesitant fuzzy decision-making, called MEREC-TODIM. Firstly, the new probabilistic hesitant fuzzy Hamming distance and Euclidean distance are directly and parametrically established by incorporating hesitation degrees; accordingly, the improved distance measures exhibit a (2times 2) system on (non-parameter, parameter) and (Hamming, Euclidean), and their distance property, measure size, parameter monotonicity, and promotion degeneration are investigated and acquired. Furthermore, a modified score function is proposed for MEREC to determine attribute weights, and thus a corresponding decision method with TODIM (i.e., MEREC-TODIM) is established for PHFSs applications on evaluation sorting and optimization selection. Finally, MEREC-TODIM is validated through parameter analyses and decision comparisons, and it is effectively applied to two practical examples: Carbon Capture Utilization Storage and PhD Admission Interviews.

This paper displays the set up and simulation of a compact neuro-fuzzy adaptive scheme for the filling regulation of two coupled spherical tanks. The suggested scheme employs two compact neuro-fuzzy blocks: the first one to model the plant, and the second one for the controller implementation. In this scheme, the controller is trained employing the fuzzy model estimated with data of the system working in closed-loop. Thus, the controller optimization iteratively is performed when plant variations occur. The work also includes the deduction of the equations for training, showing the adaptive process employing neuro-fuzzy systems. Moreover, the training (optimization) process of the controller’s neuro-fuzzy system includes within the adjustment function the control action and the error signal. Various experimental cases are considered using statistical analysis to verify behaviors in the adaptive control system. In this order, the main contribution of this work consists of the adjustment (coupling) of two structures of compact neuro-fuzzy systems used for identification and control, as well as the deduction and adjustment of the training algorithms to implement the adaptive control system.

This paper deals with the problems of finite-time boundedness and dissipative analysis for a class of discrete-time nonlinear Markov jump systems (MJSs) with disturbances. In particular, the Takagi-Sugeno fuzzy model is applied to the nonlinear plant, and the impact of time-varying actuator saturation is considered in the controller design. The main purpose of this paper is to develop a mode-dependent fuzzy saturation control for fuzzy MJSs over a finite-time interval. With the help of the Lyapunov stability theory and Abel lemma-based finite-sum inequality, it is established that convergence of all states are confirmed through the addressed control design. Correspondingly, the resulting closed-loop system is stochastically finite-time bounded and (({mathcal {Q}},{mathcal {S}},{mathcal {R}}))-(gamma)-dissipative under linear matrix inequality (LMI) framework. At last, two numerical examples are given to demonstrate the effectiveness and usefulness of the obtained LMI conditions.

This paper pays attention to the non-fragile observer-based (H_infty ) control problem of switched Takagi-Sugeno (T–S) fuzzy systems, where every subsystem is described by the T–S fuzzy model with local nonlinear terms. Different from the existing observer-based control strategy, a distinguishing feature of this paper is that constructed observers can make full use of current and past output measurements to enhance the performance of the observers in state estimation. However, the introduction of past output measurements has brought challenges to stability analysis and controller design. To tackle these difficulties and design a set of non-fragile fuzzy controllers to stabilize the systems, a new augmented state vector is constructed. First, a new non-fragile observer-based (H_infty ) control criterion is deduced based on the fuzzy Lyapunov function method. Then, the method of simultaneously solving observer and controller gains is obtained by introducing free matrix variables and using the linear matrix inequality approach. This solving method is more efficient than the traditional two-step method. Finally, two confirmatory instances are given.

To improve the efficiency of the double-loop fuzzy simulation (DLFS) for estimating the time-dependent failure possibility (TDFP), a single-loop fuzzy simulation (SLFS) is proposed in this paper. In the SLFS, an equivalent transformation formula of TDFP is put forward for the first time, then the estimation of TDFP is transformed into a single-loop fuzzy simulation procedure where the fuzzy inputs and time parameter are sampled in the same level. As only single-loop sampling is needed in the SLFS, the computational complexity and cost of the proposed method are both reduced compared to the DLFS. Subsequently, a single-loop Kriging model based SLFS (ASLK-SLFS) is developed to enhance the performance of the SLFS. Based on the candidate sampling pool of SLFS to sample the fuzzy inputs and the time parameter in the same level, a single Kriging can be more efficiently constructed and updated. To further improve the efficiency of ASLK-SLFS, an improved version is then developed by using a candidate sampling pool reduction strategy. Finally, three examples are employed to illustrate the advantages of the proposed methods. Through the proposed ASLK-SLFS, the safety degree of the time-dependent structure with fuzzy uncertainty can be efficiently evaluated.

This study examines the stability and stabilization issues of a type of state-quantized, time-varying delayed (TVD) Takagi–Sugeno (T–S) fuzzy semi-Markov jump systems. First of all, in order to obtain more information of T–S fuzzy systems, an augmented fuzzy Lyapunov–Krasovskii Functional (LKF) is formatted including a quadratic fuzzy Lyapunov matrix (QFLM). In addition, a novel quadratic polynomial inequality (QPI) is applied to narrow the estimation gap for TVD and a quantized controller is used to reduce control accuracy. Then, the sufficient conditions for system stability and stabilization via quantized controller are attained on the basis of Lyapunov stability theory and linear matrix inequalities method. Finally, three examples show how the constructed controller can successfully regulate the examined system and the proposed technique is less conservative than those of the former ones.

This paper investigates the multiplicative sampled-data control for the interconnected non-linear partial differential equation (PDE) systems with parameter uncertainties. First, an interval type-2 (IT2) Takagi–Sugeno fuzzy model is employed to reconstruct the studied system. In contrast to type-1 fuzzy sets, IT2 fuzzy sets can handle parameter uncertainties that type-1 fuzzy sets cannot handle, and they can characterize parameter uncertainties by utilizing upper and lower membership functions. Next, based on the IT2 fuzzy model, a sampled-data IT2 fuzzy controller containing multiplicative control gain uncertainties is designed to reduce the control cost, where a Bernoulli distribution is adopted to depict the stochastically occurring multiplicative gain uncertainties. Moreover, to conserve communication resources, a memory event-triggered strategy (METS) is employed to decrease the amount of useless data transmitted in the network channel. In contrast to the event-triggered strategy (ETS), the METS triggers these data with a small relative error between the current data and the latest published data, thereby achieving better control. Finally, an example is given to demonstrate the validity of the proposed methodology.

Label-specific features learning is a prominent research hotspot in the field of multi-label learning, which aims to construct a classification model based on the distinctive features of each label rather than the whole features. Existing approaches regarding label-specific features usually assume that the importance of each label to an instance is equal. However, this popular strategy might be suboptimal as the importance of labels actually is different. In this paper, a multi-label-specific features learning algorithm based on label importance and fuzzy rough set is proposed. First, the importance of labels is measured based on the similarity of instances, which not only preserves the ranking of relevant and irrelevant labels, but also follows the principles of smoothness and normalization. Second, the correlation between labels is analyzed, and label-specific features of each label are extracted through a fuzzy rough set model. Experiments on several public available data sets demonstrate the effectiveness of the proposed algorithm.