Search

This paper proposes an intelligent control system called self-exploring-based intelligent control system (SEICS). The SEICS is comprised of three basic mechanisms, namely, controller, performance evaluator (PE), and adaptor. The controller is constructed by a fuzzy neural network (FNN) to carry out the control tasks. The PE is used to determine whether or not the controller's performance is satisfactory. The adaptor, comprised of two elements, action explorer (AE) and rule generator (RG), plays the main role in the system for generating new control behaviors in order to enhance the control performance. AE operates through a three-stage self-exploration process to explore new actions, which is realized by the multiobjective genetic algorithm (GA). The RG transforms control actions to fuzzy rules based on numerical method. The application of the adaptor can make a control system more adaptive in various environments. A simulation of the robotic path-planning is used to demonstrate the proposed model. The results show that the robot reaches the target point from the start point successfully in the lack-of-information and changeable environments. Index Terms--Fuzzy neural network (FNN), fuzzy rules, genetic algorithrn (GA), intelligent control systems, path-planning.

Quality function deployment (QFD) is a useful tool for maximising customer satisfaction in the new product planning (NPP) process. When applying QFD, recognising the importance levels of customer requirements (CRs) is a vital issue, since they have great influences on the values of decision variables, i.e. the fulfilment levels of design requirements (DRs), for NPP. Unlike existing researches, this study evaluates the importance scores of CRs from three different perspectives: the customer, competition and value perspectives. To cope with the vague and uncertain nature at the NPP stage, various fuzzy approaches are adopted for measuring the importance scores of CRs from different perspectives. The three measures are aggregated as the evaluated importance score of each CR. In addition, different to prior studies, this paper modifies Chen and Weng’s model to develop a new normalised relationship between CRs and DRs to improve the existing models’ drawbacks. A fuzzy linear programming model is established to determine the optimal fulfilment levels of DRs to maximally satisfy CRs. Based on an illustrative example, the proposed method achieves greater total customer satisfaction than previous methods. Furthermore, this paper also proposed a normalised relationship formulation with conventional way to reasonablely modify Wasserman’s model. [ABSTRACT FROM PUBLISHER]

The selection of the outsourcing manufacturing partners (OMPs) is an important issue for research and development (R&D) in the pharmaceutical industry. The selection process considers several main criteria, as well as a few sub-criteria for each main criterion. Such problems can be formulated as hierarchical structures and can usually be resolved with multi-criteria decision-making approaches. This paper presents an integrated fuzzy approach for selecting a suitable OMP in pharmaceutical R&D. In the integrated approach, fuzzy concepts are used for decision-makers' subjective judgments to reflect the vague nature of the selection process. Fuzzy AHP and fuzzy TOPSIS are included in the integrated approach. Fuzzy AHP is used to determine the fuzzy weights of criteria and sub-criteria because it can effectively determine various criteria's weights in a hierarchical structure. Fuzzy TOPSIS aims to find the OMP with the best performance with respect to the sub-criteria. We exemplify the integrated approach using a numerical application to demonstrate its feasibility. [ABSTRACT FROM AUTHOR]

This paper develops a two-phase fuzzy goal programming (FGP) approach for multi-level linear programming (MLLP) problems in an uncertain environment. A numerical MLLP model is established based on a confidence level. In the first phase, an FGP model is used to find a solution that reaches the overall satisfaction of all decision-makers (DMs), ensuring that the fuzzy goal of each higher-level DM is more satisfied than those of lower-level DMs. Since the higher-level DM has the direct authority to manage the subordinate DM, an adjustment scheme is provided in the second phase for each higher-level DM, who has the opportunity to increase or decrease the satisfaction degree of their fuzzy goal by changing the relative satisfaction of the lower-level DM compared to that of their higher-level DM. A fuzzy variable of the relative satisfaction containing a set of linguistic terms is provided for these adjustments. The adjustment processes are carried out sequentially, from the top to bottom in the hierarchical decision structure. The proposed FGP model in the second phase considers these sequential adjustments. A numerical example and comparisons with existing methods are used to demonstrate the applicability and performance of the proposed approach. [ABSTRACT FROM AUTHOR]

This paper investigates multi-level multi-objective linear programming problems in fuzzy environments, where each decision level has one decision-maker (DM) with a vector of decision variables and possibly more than one objective function. The objective functions of each DM and the decision variables of higher-level DMs are characterized by membership functions, which are considered as fuzzy goals. In related studies, the tolerances used to define membership functions of higher-level DMs' decision variables are usually subjectively determined. This may lead to infeasible solutions. This paper focuses on the determination of required minimum tolerances for higher-level DMs' decision variables to ensure feasibility in the solution process. A fuzzy goal programming model is established to optimally satisfy all defined fuzzy goals by minimizing satisfaction deviations under the constraint of the leader-follower relationship. A numerical example is provided for demonstrating the proposed approaches. It is shown that existing approaches may not have feasible solutions if the required minimum tolerances are not adopted. [ABSTRACT FROM AUTHOR]

Highlights: [•] A simple two-stage approach is proposed to construct a fuzzy regression model. [•] The fuzzy model contains the crisp coefficients and a fuzzy adjustment term. [•] The negative coefficients are taken into account in the fuzzy regression model. [•] The fuzzy model has the highest explanatory performance using various criteria. [ABSTRACT FROM AUTHOR]

Abstract: This paper investigates decentralized bi-level multi-objective linear programming (DBL-MOLP) problems with a single decision-maker (DM) at the higher level and more than one DM at the lower level. Each DM can have more than one objective function, which is formulated as a fuzzy goal. To characterize the decision decentralization in a DBL-MOLP problem, this paper proposes an assignment scheme of relative satisfaction for the higher-level DM to ensure his leadership and therefore prevent the paradox problem reported in the literature, where lower-level DMs have higher satisfaction degrees than that of the higher-level DM. Through the assignment scheme, if the higher-level DM is not satisfied with the resulting solutions of objective functions, the re-solving process is easily conducted by adjusting the level of relative satisfaction for the associated lower-level DMs. A linearization transformation approach is also presented to facilitate the solution process. To emphasize some important fuzzy goals, a weighting scheme is considered in this paper. A numerical example is used for illustration, and comparisons with existing approaches are conducted to demonstrate the feasibility of the proposed method. [Copyright &y& Elsevier]

Quality function deployment (QFD) is a useful planning approach for constructing new product designs or modifying existing products. The approach has been widely adopted in various applications. For QFD processes, the house of quality (HOQ) is first constructed to describe customer requirements (CRs) and their importance, design requirements (DRs), the relationships between CRs and DRs, and the correlations among DRs. This study proposes a systematic procedure for constructing the HOQ and describes its application from a group decision-making (GDM) perspective. Considering the imprecise information in the design stage, fuzzy set theory is employed to develop fuzzy approaches for constructing the HOQ. In practical applications, a QFD team is usually organized to collect relevant information; therefore, GDM approaches are incorporated into the construction process of the HOQ. To reflect the differences between decision-makers’ evaluations of elements in the HOQ, various ways of assessing the components of the HOQ are allowed. A modified fuzzy clustering approach is proposed for finding the consensus of the QFD team. Based on the established HOQ, approaches are presented for prioritizing DRs as a reference for allocating internal resources to appropriate DRs in order to optimally satisfy CRs. A numerical example is used to demonstrate the applicability of the proposed approaches. [ABSTRACT FROM PUBLISHER]

Quality function deployment (QFD) frameworks are useful tools for constructing a new product development (NPD) plan that enables the clear itemization of customer needs and the systematic evaluation of each solution to maximize customer satisfaction. A complete QFD process includes four sequential phases in which four important decision outcomes are determined for NPD, namely, the fulfillment levels of design requirements (DRs), part characteristics, process parameters, and production requirements. Unlike prior studies which have focused only on determining DRs, this paper extends Chen and Ko's models to consider the close link between the four phases in NPD using the means-end chain concept to build up a series of fuzzy nonlinear programming models for determining the fulfillment levels of each decision outcome for customer satisfaction. In addition, this paper incorporates risk analysis, which is treated as the constraint in the models, into the QFD process. To deal with the vague nature of product development processes, fuzzy sets are applied for both QFD and risk analysis. A numerical example is used to demonstrate the applicability of the proposed model. [ABSTRACT FROM PUBLISHER]