Search results

The facility layout problem aims to assign machines/departments to locations and modeled as a quadratic assignment problem (QAP). Multi period facility layout is a special case of this problem where the sum of material handling and re‐layout costs are minimized. Since the problem is proved to be NP‐hard, several exact and heuristic methods are proposed in the literature. The purpose of this paper is to solve the multi period layout problem by using the modified sub‐gradient (MSG) algorithm for the first time and to determine its parameters.

The MSG algorithm can solve a large‐scale of optimization problems that also includes multi period facility layout. Since the performance of the algorithm depends on parameters, a design of experiment is made to determine the appropriate parameter values.

The proposed method evaluates the parameters of the MSG algorithm and most suitable general algebraic modeling solvers. It is observed that the parameter α value and solver type have main effects for small and large size test problems. Further, the results stated that solver type has more influence on large size test problem.

This study is limited with the determination of the MSG algorithm parameters and solver types on the well known small and large size test problems. Further studies may include other test problem results obtained from the presented MSG algorithm parameters and compare them with best known results in the literature.

The paper determines the parameters of the MSG algorithm that is used to solve the multi period layout problem, for the first time in the literature.

Some improvements are made for Fast Boundary Tracking algorithm according to the practice of the electric machine design in the paper. As discrete variables play a dominant role in determining the values of the objective function and the constraint functions in the motor optimal design, the algorithm is improved in the paper. From the algorithm, a software is developed and used for the optimal design of the induction motors of Y series. The results show that the algorithm is reliable and efficient.

The cross-docking strategy has a significant influence on supply chain and logistics efficiency. This paper aims to investigate the most suitable and efficient way to schedule the transfer of logistics activities and present a meta-heuristic method of the truck scheduling problem in cross-docking logistics. A truck scheduling problem with products time window is investigated with objectives of minimizing the total product transshipment time and earliness and tardiness cost of outbound trucks.

This research proposed a meta-heuristic method for the truck scheduling problem with products time window. To solve the problem, a lower bound of the problem is built through a novel two-stage Lagrangian relaxation problem and on account of the NP-hard nature of the truck scheduling problem, the novel red deer algorithm with the mechanism of the heuristic oscillating local search algorithm, as well as adaptive memory programming was proposed to overcome the inferior capability of the original red deer algorithm in the aspect of local search and run time.

Theory analysis and simulation experiments on an industrial case of a cross-docking center with a product’s time window are conducted in this paper. Satisfactory results show that the performance of the red deer algorithm is enhanced due to the mechanism of heuristic oscillating local search algorithm and adaptive memory programming and the proposed method efficiently solves the real-world size case of truck scheduling problems in cross-docking with product time window.

The consideration of products time window has very realistic significance in different logistics applications such as cold-chain logistics and pharmaceutical supply chain. Furthermore, the novel adaptive memory red deer algorithm could be modified and applied to other complex optimization scheduling problems such as scheduling problems considering energy-efficiency or other logistics strategies.

For the first time in the truck scheduling problem with the cross-docking strategy, the product’s time window is considered. Furthermore, a mathematical model with objectives of minimizing the total product transshipment time and earliness and tardiness cost of outbound trucks is developed. To solve the proposed problem, a novel adaptive memory red deer algorithm with the mechanism of heuristic oscillating local search algorithm was proposed to overcome the inferior capability of genetic algorithm in the aspect of local search and run time.

Effective inventory management is very critical to market success. The purpose of this paper is to formulate an integrated model for the location of warehouse, the allocation of retailers to the opened warehouses, and finding the perfect policy for inventory control to managing order quantity and safety stock level. The goal is to select the optimum numbers, locations, capacities of the opening warehouses and inventory policy so that all stochastic customer demands can be satisfied.

It is assumed that the location of plant has already been determined and the paper answers the following questions: what are the location decisions over the planning horizon? How retailers are allocated to the warehouses? What are the optimum capacities for the opened warehouses? What is the best inventory policy for this supply chain? What are the total minimum costs?

The model was developed as a non‐linear mixed integer programming and solved using Lagrange relaxation and sub‐gradient search for the location/allocation module and a procedure for the capacity planning module. The results for the randomly selected problems show that the average duality gap ranges are between 0.51 and 1.58 percent. Also, from the CPU time point of view, the performance of the proposed algorithm was very good.

The paper addresses an integrated location, allocation, and inventory decisions in the design of a supply chain distribution network. In addition sensitivity analyses are conducted to evaluate the effects of the multi‐capacity levels on some performance measures.

The combined heat and power dispatch (CHPD) aims to optimize the outputs of online units in a power plant consisting thermal generators, co-generators and heat-only units. Identifying the operating point of a co-generator within its feasible operating region (FOR) is difficult. This paper aims to solve the CHPD problem in static and dynamic environments.

The CHPD plant operation is formulated as an optimization problem under static and dynamic load conditions with the objectives of minimizations of cost and emissions subject to various system and operational constraints. A novel bio-inspired search technique, grey wolf optimization (GWO) algorithm is used as an optimization tool.

The GWO-based algorithm has been developed to determine the preeminent power and heat dispatch of operating units within the FOR region. The proposed methodology provides fuel cost savings and lesser pollutant emissions than those in earlier reports. Particularly, the GWO always keeps the co-generator’s operating point within the FOR, whereas most of the existing methods fail.

The GWO is applied for the first time to solve the CHPD problems. New dispatch schedules are reported for 7-unit system with the objectives of total fuel cost and emission minimizations, 24-unit system for economic operation and 11-unit system in dynamic environment. The simulation experiments reveal that GWO converges quickly, consistent and the statistical performance clears its applicability to CHPD problems.

This paper aims to study a dynamic post-disaster emergency planning (PDEP) problem in an integrated network through the investigation of the selection of shelters, medical centers and distribution centers (DCs), and the allocation of evacuees and injured people. The resource and people assignment in multiple periods are considered.

A mathematical formulation is provided for the PDEP problem. The authors decompose the model into two sub-models as follows: the primary model is an integer programming model and the subproblem is a nonlinear programming model with continuous variables. The simulated annealing is used to solve the primary problem, and particle swarm optimization (PSO) mixed with beetle antennae search (BAS) is used to solve the subproblem.

The paper finds that BAS can increase the stability of PSO and keep the advantages of PSO’s rapid convergence. By implementing these algorithms on emergency planning after the Wenchuan earthquake that happened in China in 2008, this paper finds that the priority of different levels of injured people is influenced by several factors. Even within the same disaster, the priority of different levels of injured can be inconsistent because of the differences in resource levels.

The authors integrate the shelters, medical centers and DCs as a system, and simultaneously, consider evacuees and injured people and different resource assignments. The authors divide the injured people into three levels and use survival rate function to simulate the survival conditions of different people. The authors provide an improved PSO algorithm to solve the problem.

Train re-scheduling remains a longstanding challenge in railway operation. To design high-quality timetable in fuzzy environment, the purpose of this paper is to study train re-scheduling problem under the fuzzy environment, in which the fuzzy coefficients of the constraint resources have the fuzzy boundaries.

Based on the improved fuzzy linear programming, the train re-scheduling model is constructed. Aiming at dealing with the fuzzy characteristics of the constraint coefficients value range boundaries, the description method of this kind of objective function is proposed and the solving approach is presented. The model has more adaptability to model a common train re-scheduling problem, in which some resources of the constraints are uncertain and have the characteristics of fuzziness and the boundaries of the resources are fuzzy.

Two numerical examples are carried out and it shows that the model proposed in this paper can describe the train re-scheduling problem precisely, dealing with the fuzzy boundaries of the fuzzy coefficients of the constraint resources. And the algorithm present is suitable to solve the problem. The approach proposed in this paper can be a reference for developers of railway dispatching system.

It is the first time to study train re-scheduling problem under the fuzzy environment, in which the fuzzy coefficients of the constraint resources have the fuzzy boundaries.

The purpose of this paper is to solve the problem of committing electric power generators (unit commitment, UC), considering network constraints.

The UC is first solved with a local search based meta‐heuristic, following the assumption that all generators and loads are connected to a single network node. For evaluation purposes, the economical production levels of the units committed are computed by running a pre‐dispatch algorithm where network constraints are not included. If a good quality solution is reached, an economic dispatch (ED) with network constraints is performed, where the geographic location of generators and loads are considered. Therefore, the production level of each committed generator is performed that leads to the global lowest solution cost, regarding both the generators' costs and constraints and the power system network constraints.

The algorithm proposed is computationally efficient, given the time available for decision making. In addition, the solution for this algorithm, in terms of minimization of total costs, is generally better than the solution of the two phases approach. Some contractual and legal aspects related with the injection in network connections can also be included in the model.

UC with network constraints has a large potential of use, especially for small and medium size power systems. It reflects reality in a closer way and provides a more complete and realistic knowledge about the system in operation.

The paper presents an approach where the ED with network constraints is integrated with the UC procedure. The model described is currently implemented in an EMS package offered in the market – making it a case of successful transfer from science to industry.