Forecasting factory productivity is a critical task. However, it is not easy owing to the uncertainty of productivity. Existing methods often forecast productivity using a fuzzy number. However, the range of a fuzzy p...
详细信息
Forecasting factory productivity is a critical task. However, it is not easy owing to the uncertainty of productivity. Existing methods often forecast productivity using a fuzzy number. However, the range of a fuzzy productivity forecast is wide owing to the consideration of extreme cases. In this study, a fuzzy collaborative forecasting approach is proposed to forecast factory productivity using a type-II fuzzy number and by narrowing the forecast's range. The outer section of the type-II fuzzy number determines the range of productivity, while the inner section is defuzzified to derive the most likely value. Based on the experimental results, the proposed methodology surpassed existing methods in improving forecasting precision and accuracy, with a reduction in the mean absolute percentage error (MAPE) of up to 74%.
Most existing fuzzy collaborative forecasting (FCF) methods adopt type-1 fuzzy numbers to represent fuzzy forecasts. FCF methods based on interval-valued fuzzy numbers (IFNs) are not widely used. However, the inner an...
详细信息
Most existing fuzzy collaborative forecasting (FCF) methods adopt type-1 fuzzy numbers to represent fuzzy forecasts. FCF methods based on interval-valued fuzzy numbers (IFNs) are not widely used. However, the inner and outer sections of an IFN-based fuzzy forecast provide meaning information that serves different managerial purposes, which is a desirable feature for a FCF method. This study proposed an IFN-based FCF approach. Unlike existing IFN-based fuzzy association rules or fuzzy inference systems, the IFN-based FCF approach ensures that all actual values fall within the corresponding fuzzy forecasts. In addition, the IFN-based FCF approach optimizes the forecasting precision and accuracy with the outer and inner sections of the aggregation result, respectively. Based on the experimental results, the proposed FCF-II approach surpassed existing methods in forecasting the yield of a dynamic random access memory product.
The components in a system can degrade differently, due to the operational loads or environmental conditions, or both, in their positions being different. Therefore, reassignment of the functionally exchangeable compo...
详细信息
The components in a system can degrade differently, due to the operational loads or environmental conditions, or both, in their positions being different. Therefore, reassignment of the functionally exchangeable components to the positions at appropriate time can increase system reliability and extend system lifetime. In this article, a new component reassignment problem is proposed, and a mixed binary nonlinear programming model is built to determine the optimal reassignment time and optimal reassignment of degrading components with the objective of maximizing system lifetime. The model integrates continuous optimization and combinatorial optimization, and provides a framework for optimizing the component reassignment decisions for various degradation models and system structures. Furthermore, the optimization model and analytical results are derived for k-out-of-n systems of linearly degrading components or exponentially degrading components. The analytical results reduce the complexity of solving the optimization model and are used to design an efficient solution method. Finally, numerical examples in a power supply system demonstrate applications of the optimization model and further provide managerial insights for the component reassignment problem of degrading components.
An interval fuzzy number-based approach was proposed in this study to model an uncertain yield learning process. The study aimed to overcome the limitations of present methods, wherein the lower and upper bounds of th...
详细信息
An interval fuzzy number-based approach was proposed in this study to model an uncertain yield learning process. The study aimed to overcome the limitations of present methods, wherein the lower and upper bounds of the yield are generally determined by few extreme cases, thus resulting in an unacceptable widening of the yield range. In the proposed interval fuzzy number-based approach, the range of yield was divided into two sections, namely inner and outer sections, which corresponded with the lower and upper membership functions of a fuzzy yield forecast based on interval fuzzy numbers, respectively. To fulfill different managerial objectives, in this approach, all actual values are included in the outer section, whereas most of these values fall within the inner section. To derive the values of parameters in a fuzzy yield learning model based on interval fuzzy numbers, a mixed binary nonlinear programming model was proposed and optimized. The interval fuzzy number-based approach was applied to two real-time cases for evaluating its effectiveness. According to experimental results, the performance of the proposed method was superior to that of several existing methods, particularly in terms of forecasting precision for the average range. Forecasting accuracy obtained using the interval fuzzy number-based approach was satisfactory.
In this paper we present a new accurate optimization method to find an optimal solution for the heterogeneous resources offline allocation problem in embedded systems. The proposed method is based on mixedbinary Nonl...
详细信息
ISBN:
(数字)9783319461403
ISBN:
(纸本)9783319461403;9783319461397
In this paper we present a new accurate optimization method to find an optimal solution for the heterogeneous resources offline allocation problem in embedded systems. The proposed method is based on mixed binary nonlinear programming (MBNLP) using piecewise linear relaxations and uses the fast branch and bound algorithm for the minimization of a convex nonlinear objective function over binary variables subject to convex nonlinear constraints. The produced numerical results show the robustness of the proposed method compared with conventional method in terms of performance.
This paper presents an efficient tabu search algorithm (TSA) to solve the problem of feeder reconfiguration of distribution systems. The main characteristics that make the proposed TSA particularly efficient are a) th...
详细信息
ISBN:
(纸本)9781467327299
This paper presents an efficient tabu search algorithm (TSA) to solve the problem of feeder reconfiguration of distribution systems. The main characteristics that make the proposed TSA particularly efficient are a) the way in which the neighborhood of the current solution was defined;b) the way in which the objective function value was estimated;and c) the reduction of the neighborhood using heuristic criteria. Four electrical systems, described in detail in the specialized literature, were used to test the proposed TSA. The result demonstrate that it is computationally very fast and finds the best solutions known in the specialized literature.
This paper presents an efficient tabu search algorithm (TSA) to solve the problem of feeder reconfiguration of distribution systems. The main characteristics that make the proposed TSA particularly efficient are a) th...
详细信息
ISBN:
(纸本)9781467327275
This paper presents an efficient tabu search algorithm (TSA) to solve the problem of feeder reconfiguration of distribution systems. The main characteristics that make the proposed TSA particularly efficient are a) the way in which the neighborhood of the current solution was defined;b) the way in which the objective function value was estimated;and c) the reduction of the neighborhood using heuristic criteria. Four electrical systems, described in detail in the specialized literature, were used to test the proposed TSA. The result demonstrate that it is computationally very fast and finds the best solutions known in the specialized literature.
A constructive heuristic algorithm (CHA) to solve distribution system planning (DSP) problem is presented. The DSP is a very complex mixed binary nonlinear programming problem. A CHA is aimed at obtaining an excellent...
详细信息
A constructive heuristic algorithm (CHA) to solve distribution system planning (DSP) problem is presented. The DSP is a very complex mixed binary nonlinear programming problem. A CHA is aimed at obtaining an excellent quality solution for the DSP problem. However, a local improvement phase and a branching technique were implemented in the CHA to improve its solution. In each step of the CHA, a sensitivity index is used to add a circuit or a substation to the distribution system. This sensitivity index is obtained by solving the DSP problem considering the numbers of circuits and substations to be added as continuous variables (relaxed problem). The relaxed problem is a large and complex nonlinearprogramming and was solved through an efficient nonlinear optimization solver. Results of two tests systems and one real distribution system are presented in this paper in order to show the ability of the proposed algorithm.
An optimization technique to solve distribution network planning (DNP) problem is presented. This is a very complex mixed binary nonlinear programming problem. A constructive heuristic algorithm (CHA) aimed at obtaini...
详细信息
ISBN:
(纸本)9781424442409
An optimization technique to solve distribution network planning (DNP) problem is presented. This is a very complex mixed binary nonlinear programming problem. A constructive heuristic algorithm (CHA) aimed at obtaining an excellent quality solution for this problem is presented. In each step of the CHA, a sensitivity index is used to add a circuit or a substation to the distribution network. This sensitivity index is obtained solving the DNP problem considering the numbers of circuits and substations to be added as continuous variables (relaxed problem). The relaxed problem is a large and complex nonlinearprogramming and was solved through an efficient nonlinear optimization solver. A local improvement phase and a branching technique were implemented in the CHA. Results of two tests using a distribution network are presented in the paper in order to show the ability of the proposed algorithm.
暂无评论