PRODUCTION AND OPERATIONS MANAGEMENT
Year:2016 | Volume:7 | Issue:1 (12) |Papers Count:14

Since market segmentation is essential to develop and implement marketing strategies, has always been focus of marketing researchers’ attention. The advent of new technology and emerging E-businesses, which accumulating immense customer data in their databases, made the market segmentation more fascinating for researchers. Since they found customer database as one of the most valuable asset that if being managed and manipulated effectively, can provide useful knowledge about the customers and prospects. There are numerous noncoherent methods of customer clustering and classification which has been proposed in different disciplines. This paper utilizes different clustering and classification methods and compares their performance in order to propose a comprehensive and integrated algorithm for e-businesses to exploit their databases in a competent manner. In the first step, regency, frequency, monetary (RFM) data is used to ensemble K-Means, Self-Organizing-Map (SOM) and Two-Step clustering methods and Silhouette index is used to evaluate the cluster quality. In second step, different classification methods vis-a-vis multi-group discriminate linear programming (MDLP) are used to compare the performances of the methods in terms of percentage of correct classification. The results show that the performance of MDLP is better than other methods. The problem of insufficient data in databases for classification purpose is also takes into account and fuzzy Delphi method is proposed to select the required data.

Nowadays, most of manufacturing firms are in accordance with continuous changes in the market and the today’s competitive world is competing for meeting demand, increasing quality and decreasing costs. So, it is necessary to select a suitable flexible manufacturing system (FMS) for the most of manufactures. The purpose of this paper is to evaluate FMS in one of the Iranian companies producing home-appliance.In this paper, we use Multi Attribute Decision Making (MADM) process to select the best type of flexibility from these alternatives such as “volume flexibility”, “product flexibility”, “process flexibility”, “material handling flexibility”, and “without using FMS”. For this purpose, the methods of AHP, SAW, TOPSIS, SMARTER and permutation have been used. Finally, the results are combined through an integrated method. The results indicate that the FMS option with flexibility in handling approach is appropriate for this company. Moreover, the obtained results are in consistency with expectation of company's managers.

Decision making techniques are often used for choosing the best solution among all available alternatives. Among many mathematical methods proposed to simplify decision making process, PROMETHEE and LINMAP are the most applied techniques to multi-attribute decision making (MADM) problems. Many of MADM problems include ranking finite number of discrete alternatives or selecting the best solution among them. But in many cases, for example in some locating problems, it is necessary to consider multiple contradictory criteria to determine the optimal facility location in infinite and continuous set of alternatives. This paper deals with continuous alternative MADM problems. In addition to the use of PROMETHEE-IV, an extended LINMAP technique is proposed and tested for a continuous problem. Results of a numerical example and data analysis using Excel and Lingo indicate the efficiency of these techniques in our continuous alternative multi-attribute problem.

In this paper, a mixed integer programming formulation for flexible flow shop scheduling problem with unrelated machines and sequence dependent setup times is proposed in order to minimize sum of earliness and tardiness. Due to the fact that this problem is NP-Hard, a SA-based heuristic as well as a PSO-based heuristic are proposed to tackle the complexity of the problem. Later, the parameters of these algorithms are set by Taguchi method and then, these meta-heuristic algorithms are compared with each other by 410 test problems. At the end, a number of topics are proposed for future research.

Mutual funds are used in stock exchanges in the world with the goal of increasing efficiency and boosting investment in capital markets and have an important role in financing resources and leading it to the production capacity. The philosophy of establishing these mutual funds is to gather funds and invest them in a collection of diverse securities (stocks, bonds and other kinds of securities). The efficiency of mutual funds with regard to the high volume of their buying and selling in the capital market is the main discussions about them. In this research, based on Data Envelopment Analysis that is a nonparametric method, the mutual funds existing until May 2011 are ranked based on BCC and CCR models, then return on scale of them is examined and finally, mutual funds are ranked by A& P model. The results show that 16 and 18 mutual funds are on the efficiency boundary based on CCR and BCC models, respectively. Return on scale for mutual funds is not constant.

Many small and medium enterprises are required to understand the situation and the gaps to get optimum conditions before any change or movement toward excellence. Statistical analysis such as average test, Friedman test and descriptive analysis, inference to identify problems and weak areas of the Shannon entropy method was used to determine the weight of each of the EFQM model criteria.Research results indicate issues such as poor management skills, financial problems for investment in research and development, technology acquisition, training and employment of highly skilled manpower and et al. The most important guidelines are offered: Investment in research and development organizations to increase cooperation with peers, management and human resource development, management training expressed by managers.

In this paper, the problem of batch scheduling in parallel machines environment with the objective of minimizing make span (Cmax) is addressed. The main contribution of this research is the stochastic nature of the processing times of jobs and release times for better depiction of the real world. It has been proved that the problem is NP-hard. Therefore, we apply heuristic approaches to solve this problem. The provided problem includes two stages of decision making. In the first stage, the jobs are classified into batches and in the next stage; these batches should be assigned to parallel machines. Two and three heuristic methods are used for producing batches and sequencing batches, respectively. 10, 000 test problems are randomly generated due to stochastic nature of processing times and release dates. Using the results of simulating test problems, six combinations of heuristic methods are compared. The results show that applying MBF heuristic method in the first stage and ERT-LPT method in the second stage provide better and efficient solutions.

In this paper, Steel-making Continuous Casting (SCC) scheduling problem is investigated. The scheduling of SCC processes is of major importance in steel industries. Since it is often a bottleneck in steel production, optimal scheduling of it can minimize production cost and increase profit notably. This problem is a specific case of hybrid flow shop scheduling problem accompanied by technological constraints of steel-making and hence classic optimization methods fail to obtain an optimal solution for a real life problem over a suitable time. In this paper, a meta-heuristic algorithm based on an Ant colony algorithm (ACO) which is accompanied with a heuristic timing algorithm is developed. In the proposed algorithm the resource assignment and sequencing is determined with ACO and the timing of jobs is determined using a heuristic forward-backward algorithm. Considering the real constraints in the problem definition, designing a heuristic timing algorithm, embedding the proposed timing algorithm in ACO framework and a novel design of ACO algorithm in pheromone matrix and heuristic information are the main features of this paper. The proposed algorithm is implemented in Khuzestan steel complex and the efficiency of it is compared with a heuristic algorithm of commercial scheduling software which is used in Mobarakeh Steel Company. Numerical results show that the average percent of improvement is about 65% in a limited scheduling time.

The importance of resource leveling cannot be ignored throughout a project, especially in cases where a trivial fluctuation in using resources will lead into high financial risks or costs. Traditional approaches are usually insufficient in solving the problems of multi-objective constraint resource leveling. In this paper, we propose an optimized technique based on Differential Evolution (DE) algorithm and ELECTERE method in order to overcome the drawbacks of the traditional resource leveling algorithms. Furthermore, obviating the challenges of normalizing and weighting objective functions, this approach takes the uncertainty and ambiguity of the objective functions into account through application of pseudo-criterion. The structure of proposed model is designed based on real situations. Results obtained from the numerical example verify the efficiency of the proposed model in solving the problems of resource leveling, and in comparison with traditional models; they confirm the better performance of this model to overcome single and multi-objective problems.

This paper studies combined DEA with strong complementary slackness condition in fuzzy environment. In the past studies, DEA was used for unit assessment but this method is not perfect because it does not fully utilize information on inputs and outputs data. For this reason, combined DEA with other methods caused better accuracy and quality. Combined DEA with strong complementary slackness condition caused strong method in determinant and assessment of decision making units. In this study, a combined model is used in fuzzy environment and a new model is proposed which is more applicable and similar to real conditions.

Among many enterprise assets, technology is a critical driving force for the purposes of performance, behavior and better business decisions. However, the management of technology provides a systematic approach to full utilization of a technology-based organization. Knowledge of agile manufacturing and agile workforce to develop the concept of agility in organizations has been reviewed by investigators. Based on the review of literature in both areas (management, technology and agility), the indicators presented in the form of a questionnaire proved their reliability and validity. After evaluation of these components, results in a steel factory in Kashan Desert indicate a strong relationship and significant management and technical capabilities of agility. To examine the impact of the technology management on capabilities of agility, some questionnaires are examined and prioritized in terms of influence.

This paper considers the vehicle routing problem with backhaul (VRPB) and some applicable constraints, in which a set of costumers are divided into two subsets of linehaul and backhaul costumers. Each linehaul costumer requires its demands to be delivered from the depot. In addition, a specified quantity of products should be picked up from the backhaul nodes to the depot. The main point in this study is that the customer demands, which are over than the maximum of available vehicles, can be divided to different customers. In addition, there is limited vehicle access availability for some costumers. The central depot includes a fleet of vehicles with different capacities, in which the number of vehicles of each type is not limited and customer demands are dynamic and can change in each period. This problem is a wellknown NP-hard one; therefore, a new multi-ant colony optimization algorithm is proposed to solve the given problem. This proposed algorithm contains two phases, namely clustering and routing. Finally, the numerical results of designed test problems have been discussed and analyzed.

In this paper, the problem of selecting and scheduling projects regarding the maximum amount of resource constraints and the net present value of the project is modeled, analyzed and solved. This study shows the condition in which some projects should be performed among all available projects. Decision makers should choose a subset of these projects based on resource constraints in order to maximize final profit. Project selection models usually do not consider project scheduling as a part of selection process. However, except in cases where only one project is active at any time during the project, prioritizing selected projects regardless of their schedule is not optimal. Project scheduling in the level of project activities, increases the complexity of search space and spreads the decision space for selecting a portfolio of projects. Hence, in this study a particle swarm optimization algorithm is developed for solving large scale problems. Finally, in order to validate the quality of the proposed meta-heuristic approach, several test problems have been solved in small and large sizes. The results show the good performance of the presented algorithm.

The largest share of natural gas consumption in the country is allocated to the residential and commercial sectors. Therefore, the prediction of the consumption rate of these two sectors is very important for planning in the National Iranian Gas Company. This paper develops an artificial neural network model to forecast the natural gas consumption for residential and commercial sectors in the city of Isfahan. In order to find an appropriate architecture, three different methods named dynamic method, radial basis function network method, and exhaustive prune method are investigated. The actual gas consumption data for the previous 10 years are used to predict consumption of the next five years. Factors of population, climate, total number of clients and gas prices are included in the prediction model. In this study, the neural network structures are compared with each other and with other traditional methods such as regression and time series methods. To evaluate the proposed model, we compare the results of three different architectures of neural network considering training times and accuracy of neural networks on the test data set. In addition, the neural networks have been compared with other well-known prediction methods such as auto-regressive integrated moving average and regression. The results indicate that the artificial neural network with exhaustive prune architecture is the most efficient and accurate model. The generated model is applied to predict residential and commercial gas consumption for five years. To the best of our knowledge, this method has not been used in the literature for predicting gas consumption in Esfahan.