جستجوی مقالات مرتبط با کلیدواژه « الگوریتم فراابتکاری » در نشریات گروه « مدیریت »

In light of recent advancements in the modern world, multivariate-multistage quality control patterns are increasingly recognized as vital and indispensable in manufacturing industries. This study delves into the significance and necessity of multivariate-multistage quality control in manufacturing, specifically focusing on motor oil production. As a foundational factor, motor oil quality considerably influences engine performance, lifespan, customer satisfaction, and market positioning.

This research employs deep learning algorithms for monitoring and fault detection in quality components. The primary rationale for opting for deep learning algorithms over conventional statistical methods is the non-normal distribution of data and the large sample sizes, which can lead to inaccurate estimations and unstable analyses. Conversely, the unique capabilities of deep learning algorithms in handling complex data and extracting meaningful features from extensive motor oil production data justify their selection. To bolster accuracy and effective quality control, a combination of deep learning algorithms is utilized, including Long Short-Term Memory (LSTM) networks, Convolutional Neural Networks (CNN), and hybrid models such as LSTM-CNN, as well as Residual Networks (ResNet) with Dense Networks (DenseNet). The LSTM-CNN algorithm is applied to control numerical quality variables and identify temporal and sequential patterns in the data. Meanwhile, ResNet-DenseNet manages and analyzes visual data with non-uniform and intricate distributions.

By integrating LSTM networks, CNNs, and residual connections, these algorithms excel at extracting meaningful features and capturing complex relationships within the data. This enhances performance and efficiency in quality control processes and facilitates intelligent decision-making. Such an approach is adept at uncovering latent patterns and intricate relationships between variables and quality attributes, enhancing quality control procedures and intelligent decision-making. The amalgamation of these algorithmic capabilities enhances the efficacy of quality control processes, outperforming single-algorithm approaches. Additionally, the Bee Colony Clonal Algorithm (BCC) is employed to fine-tune the parameters of the LSTM-CNN and ResNet-DenseNet algorithms. This hybrid approach harnesses the Artificial Bee Colony (ABC) and Genetic Algorithm (GA) strengths, markedly improving the performance of deep learning algorithms in quality control and reducing the time required to achieve desired outcomes. To illustrate the practical applicability of the proposed algorithms, a case study in the motor oil production industry is examined. The proposed LSTM-CNN hybrid algorithm in fault detection demonstrated superior results compared to standalone CNN and LSTM algorithms, achieving performance improvements of approximately 15% and 8%, respectively. Furthermore, the proposed ResNet-DenseNet hybrid algorithm exhibited higher accuracy in visual components, enhancing performance by approximately 10% and 15% compared to ResNet and DenseNet algorithms, respectively.

From both academic and practical standpoints, this research scrutinizes deep learning algorithms' influence on enhancing motor oil quality and efficiency. Advanced data analysis methods, particularly hybrid deep learning algorithms, are employed to identify quality patterns in production data.

Recently, the supply chain of perishable goods, have been considered due to their impact on human life. On the other hand, in the packaging industry, considering paper as a primary and perishable material due to the nature of water absorption, severe rotting in front of sunlight, flammability and turning to ash and finally affecting the final quality of the product produced from this issue. It is not excluded, it has attracted more attention. The high level of speed of changes and ambiguity in decisions has made it impossible to predict the future conditions of supply chains. Therefore, the design and use of a mathematical model for the design of the closed-loop supply chain network, taking into account the optimal pricing of products, the return rate and demand, along with taking into account the wastage of materials in the system, is strongly needed. At first, the supply chain of the paper-cardboard industry was designed and modeled with mixed integer programming, then due to the high volume of calculations and data of the problem, we can't receive exact solution approaches, the innovative approach of searching for harmony was used for the solution. . The problem is a single-objective model that minimizes system costs by considering environmental considerations. The present research shows that the price increase has a positive effect on the product return rate and reducing the level of product corruption. Finally, to validate the model, the numerical solution of a closed loop network has been done in this industry.

In the realm of green supply chain management, the pivotal responsibilities of companies involve supplier selection and order allocation. These tasks were treated as independent challenges in prior studies. This issue holds significant importance within the context of green supply chain management, demanding the simultaneous consideration of both quantitative and qualitative criteria. These criteria, at times conflicting, necessitate an in-depth analysis of trade-offs. There is a pressing need for a comprehensive framework capable of concurrently addressing both aspects. In addition to accommodating green criteria, such a framework should enable the determination of order quantities allocated to suppliers.

The utilized approach in the present study included Fuzzy DNP, Fuzzy TOPSIS, and a Bi-objective optimization model. In the first stage, the criteria weights, encompassing both traditional and green criteria, were determined using the fuzzy DNP. Subsequently, the suppliers' scores were computed using the fuzzy TOPSIS. In the second stage, a non-linear bi-objective model was formulated, aiming to minimize the total cost and maximize the purchased value. The first objective function comprised the purchase price, suppliers' variable costs, ordering and setup costs, as well as buyer's and suppliers' inventory holding costs. Additionally, the second objective function ensured a higher allocation of orders to suppliers who had achieved a superior score in the supplier evaluation process. The model's constraints encompassed the suppliers' capacity, buyer's demand, and constraints associated with the suppliers' discounts. Acknowledging the bi-objective nature of the mathematical model, the Global Criterion method was employed to transform the bi-objective problem into a single-objective one. According to this method, the relative deviations of the objectives from their corresponding single-objective optimal values were minimized. Furthermore, due to the non-linearity of the mathematical model, a harmony search algorithm was developed for the problem, and a repair algorithm was proposed to handle constraints in the problem.

The previous studies and expert opinions were utilized to identify the criteria, encompassing both traditional and green criteria. The results of fuzzy DANP indicated that the supplier's credit holds the utmost importance, followed by quality, green purchasing, green design, green transportation, green production, on-time delivery, and distance. Furthermore, all criteria exhibit an effect on the supplier's credit. Subsequently, six suppliers underwent evaluation based on the criteria using fuzzy TOPSIS, and their final scores were employed as the suppliers' weights in the second objective function of the mathematical model. To validate the proposed approach, a case study with real data in the field of the medical equipment supply chain was examined, and the optimal solution to the problem was presented. Subsequently, by adjusting the weights of the objective functions in the single-objective problem, the Pareto solutions were identified. The proposed approach facilitates the optimal allocation to the suppliers by considering the green criteria.

The results showed that a decision maker can choose the best solution according to the Pareto solutions in such a way that there is a correct trade-off between the supply chain costs and purchased value.

As economic enterprises that seek to earn a profit, banks collect and accept financial resources from depositors in the form of financial intermediaries. They allocate the resources to economic activities (investors) by providing various facilities. Therefore, banks play a very sensitive and important role in the economic system of a country and have a significant effect in regulating the economic relationships in society. Banks need to pay attention to the accurate allocation of facilities and resources. Accordingly, in today's financial landscape, effective asset and debt management has become a crucial component for the success of banks and other financial institutions. It is now essential to optimize the provision and allocation of financial resources in the banking system to reduce the costs of collecting financial resources and increase income via the distribution of financial resources in the form of various facilities. Introducing a multi-objective mathematical model and considering the limitations of the problem, this study seeks to present a mathematical model for equipping and optimal allocation of financial resources.
After reviewing the literature and previous studies conducted in the field of the research topic, using the opinions of banking experts, the researchers defined the objectives of the study as maximizing the income from the allocation of resources and minimizing the costs from the collection of resources. The first objective was defined to maximize the income from the payment of facilities (allocation of financial resources) and the second objective was defined to minimize the costs of the collection of financial resources (equipment of financial resources). The objectives were determined according to the rules and regulations of the Iran Central Bank as well as the financial regulations governing the business of the Iranian banking system. After defining and coding the model, the problem was solved using meta-heuristic algorithms. Finally, the effectiveness of the algorithms in providing the desired answer was assessed. Due to the NP-HARD nature of the problem, three meta-heuristic algorithms NSGAII, MOPSO, and CUCKOO were chosen to solve the problem. Due to the high efficiency of the MATLAB program, this software was used to perform the coding and calculations.
The results of the research indicated that the credit and operational risks of the bank will be reduced in case the banking system's resources are equipped and allocated scientifically. The achieved results from the evaluation of the algorithms confirmed the superiority of the mass particle swarm algorithm (MOPSO) over the other two algorithms. Long calculation time was found to be one of the disadvantages of genetic algorithms. Also, in the evaluation of various indices, the cuckoo algorithm did not demonstrate any significant advantage over the other two algorithms under scrutiny.
The results showed that thanks to its optimal allocation of financial resources, the model presented by this study can significantly increase the profitability of banks.

The main solution for companies to simultaneously achieve economic and environmental goals is to implement a closed loop supply chain. The main goal of this research is to design a mathematical model to empower the environmental capabilities and profitability of the closed loop supply chain in military industries. The presented model is a 4-objective model, the first objective of which is to minimize emissions, the second objective is to minimize environmental waste, the third objective is to minimize cost, and the fourth objective is to minimize the risk of raw material supply. After designing the model, validation of the model has been done by solving it in small dimensions and then using four algorithms NSGAII, MOPSO, MOACO, MOSA to solve the model in medium and large dimensions and its results have been compared. Based on the results, the parameters of the model have been adjusted and the response of the model to different parameters has been investigated. The results show that simultaneous consideration of environmental and economic dimensions in the parameters leads to the improvement of the performance of the closed loop supply chain in terms of empowering the environmental capabilities and profitability.

When it comes to providing aid to the victims of natural and unnatural disasters, the main goal of a relief chain is to provide the items needed by the victims such as water and food, medicine, shelter and other necessities to reduce the number of deaths caused by reduce the occurrence of disasters as much as possible; therefore, designing, developing and implementing a relief chain can play an important role in finding a suitable answer. The most obvious differences in dealing with the relief supply chain are the unpredictability of demand in terms of time, place, type, scale and volume. Other reasons such chains are the sudden occurrence of a large amount of demand and a very short opportunity to provide a large amount of goods, lack of resources including goods, relief forces, appropriate technology, transportation capacity, the need to provide timely and sufficient supplies after the accident, and the risks in the relief environment. In the present research, a mathematical model for the location-inventory problem for planning response to casualties is presented; also, due to the NP-hard nature of the problem considered, meta-heuristic algorithms were used to solve it.

The aim of the present research was to optimize the competencies of strategic managers in state organizations. This applied research was conducted quantitatively to collect the data. A researcher-made questionnaire was used to determine the level of consensus among respondents on the priority of the proposed indicators for the competency of strategic managers. The relationship between the components of the metaheuristic model was determined by 122 senior and middle managers who were selected by random stratified sampling from the studied organizations: Tehran Governor's Office, Administrative and Recruitment Affairs Organization, Supreme Audit Court, Welfare Organization, Iran Health Insurance Organization (IHIO). Data were analyzed using the metaheuristic approach method based on genetic algorithm and decision tree, using the WEKA and RAPIDMINER software programs. Based on the results of the Shannon’s method, ethics earned the highest priority. Furthermore, 11 out of the 16 extracted factors affecting competency were selected as the optimal characteristics of strategic managers in state organizations using metaheuristic algorithms. These were knowledge competencies, skill competencies, basic competencies, psychological competencies, ethics, general competencies, interactions and communications, resource management, strategic thinking, transformism, and leadership. The findings also show that the most effective factors must be examined to identify and evaluate the competencies of strategic managers in state organizations.

The supply chain management is an important factor in current competitive market. In recent years, the shortage of resources for answering an increasing food demand has increased researchers’ attention to the food supply chain. Given the importance of fish in the Household Food Basket, the development of aquaculture and recycling of returned goods in reverse logistics would significantly help with preserving water resources, as well as sustainable development. Therefore, government agencies and aquaculture industry beneficiaries are interested in reverse logistics. This study is focused on the optimization of a closed-loop supply chain of fish. To this end, a new bi-objective mathematical model is proposed that both minimizes total costs and maximizes fulfilling customers demand in uncertainty situation. Several well-known multi-objective meta-heuristic algorithms and a proposed hybrid meta-heuristic algorithm are applied to identify Pareto solutions. The solutions are then compared in terms of performance metrics. Also, the epsilon-constraint method and sensitivity analysis are used to validate the algorithms and evaluate the performance of the model. Lastly, the VIKOR method is used to select the superior method. To demonstrate the capability of the proposed model, a closed-loop supply chain of trout in northern Iran is investigated as a case study. The results show that the developed model could be effective in reducing the costs and increasing customer satisfaction.

In this paper a stable multi-objective model of location,inventory,supply chain routing in conditions of uncertainty with a passive defense approach is presented.In the studied model,parameters such as demand.facility establishment cost and inventory maintenance cost are considered as indefinite and in the form of triangular fuzzy numbers.Also, in order to increase the resilience of the supply chain,the characteristics and capabilities of passive defense in the supply chain such as"ready flow rate","security of backup routes"and "possibility of deployment of resources and equipment" and the principle of dispersion for location were considered.First, a fuzzy multi-objective mathematical model was designed and then a stable supply chain model with a passive defense approach, using methods such as LP metric, a unique single-objective model, was generated and solved in Gomez software environment for small problems. The presented mathematics was validated. After checking the validity of the model, multivariate multi-objective particle mass algorithms based on Pareto archive and NSGA-II were used to solve the model. Sample problems in three groups of small, medium and large were solved by two algorithms MOPSO and NSGA-II and the results of the two algorithms were compared based on quality, scatter,uniformity and execution time.The results of this section showed that the multi-objective particle mass algorithm in all cases has a higher ability to produce higher quality solutions and explore and extract the scalable area of the answer than the NSGA-II algorithm.Also, the comparison of the execution time of the algorithms indicates that the multi-objective particle mass algorithm has a higher solution time

Multi-criteria decision making methods have been of the most popular and practical areas in recent years. Among these methods, the AHP method has been considered by many researchers due to its unique features and has been used in numerous studies. This method facilitates decision-making for the decision-maker by allowing pairwise comparison between alternatives using language expressions. But this feature causes inconsistency in the decision matrix. One of the sources of inconsistency is the use of a predetermined scale to convert linguistic variables into quantitative values due to the different intellectual background of experts and their information about the problem. Therefore, the purpose of this study is to provide a customized scale for converting linguistic variables using the granularization of linguistic variables, which is in line with expert opinions and reduces the inconsistency. The unique feature of this framework is that the distribution of cut-off points is not known in advance and is determined according to expert opinions. To optimize the proposed model, a particle swarm optimization metaheuristic algorithm is used, which is modified to adapt to the specific characteristics of the problem. The results show the good performance of the proposed framework in reducing incompatibility.

In the present study, the redundancy allocation problem (RAP) of series-parallel system has been investigated to maximize the system's availability. To achieve the research objective, budget, weight and volume constraints, and the maximum and minimum number of elements assigned to each subsystem have been considered. The main innovation of this research is to consider the failure and repair rates of components with non-exponential distribution function in the process of optimization. The parameters affecting the under-study system in this paper make it impossible to calculate the availability using mathematical relations. Therefore, the present study has used simulation method to calculate system availability. Since the simulation has no optimization capability, this research tries to represent the results of the simulation as a mathematical function, which explains the way decision variables affect the system's availability. Further, due to the high degree of difficulty of developed mathematical function, the genetic metaheuristic algorithm was used to solve it. Finally, the efficiency of the genetic algorithm was measured against particle swarm algorithm and simulated annealing algorithm. To compare fairly, the parameters affecting the algorithms are adjusted using the Taguchi method and the algorithms are in their best practice. The computational results prove the high ability of the genetic algorithm in optimizing the concerned problem.

This paper deals with the problem of two-stage assembly flow shop scheduling with considering sequence-independent setup times. The objective is to minimize total completion times of all orders. In this problem, there are several orders for one type of product. Each ordered product is formed of several different parts. At first, the parts are manufactured in a flow shop stage with some different machines and then they are assembled into a final product on a single machine. This paper presents three meta-heuristic algorithms, namely Parallel Variable Neighborhood Search (PVNS), Artificial Immune Algorithm (AIA) and Simulated Annealing (SA), for solving under studied problem. The Taguchi experimental design method as an optimization technique is employed to tune different parameters and operators of presented algorithms. Also, Numerical experiments are used to evaluate the performance of the proposed algorithms. The results show that the PVNS algorithm performs better than the other algorithms.

Emphasizing the importance of competition and cooperation in supply chains promote the revitalization of game theory as a convenient tool for analyzing interactions, as well as how it affects the different levels of cooperation and coordination in a supply chain. Therefore, using the game theory concept, and based on a side-contract of partnership in profits and marketing costs, in which profit is shared between all the chain levels’ members and marketing expenses is shared between producer and retailer, a cooperation model has been designed with the aim of maximizing the supply chain profit.In this research for the first time in fuzzy enviormet and with considering discount costs, a mathematical modeling is proposed in which to get closer to real conditions, marketing cost is considered as a triangular fuzzy number. The proposed model has been solved using Genetic algorithm (GA), simulated annealing algorithm (SA) and a hybrid algorithm based on GA-SA, for some random examples, and the model has been validated using GAMS software.

Hazardous materials which are materials due to their chemical and physical properties impose significant risk to the safety of people and the environment. It's more complex routing transport of such material than normal materials. The Combination of the two subjects as the problem of locating and routing, it has created unified system to locating- routing problems. These problems determined optimal number and location of facilities at the same time and also set the optimal number of vehicles and their routes. The purpose of this study was design a network for the transportation of hazardous materials and includes supply levels, distribution (hub) and customers. Hence, it presented a mathematical model in order to minimizing costs and risk simultaneously. Hazardous materials sent from supplier to the hubs and deliveries to customers from there via routing by road transportation. It should be mentioned that in proposal model the hubs been locating In order to validate the model, prepared code GAMS In software and for the exact solution, sample problems with various dimensions were produced in the form of smart and random. For this purpose, was written an algorithm design in Matlab software. According to the problem was NP-Hard, presented a hybrid algorithm based on simulated annealing and genetic algorithms to solve large-scale. At the end of research the proposed algorithm were compared with the results of exact solution.

The purpose of this paper is to provide a model to solve the problem of discrete resource constraints project scheduling with multi objectives of reliability, risk, time and cost of the project, taking into account the multiple crashable modes and mode-identity capabilities.

Studying the literature on the subject, a mathematical programming model for the problem is presented. Due to the NP-hardness of discrete project scheduling problems, the NSGA-II, NSGA-III and MODA, meta-heuristic algorithms are developed within different dimensions to solve the problem. After presenting the results, the comparison of these algorithms has been done using a number of multi-objective performance measures.

Using multiple crashable modes concept and mode-identity in the subset of activities, and, consequently, choosing the best mode for executing activities in each subset and also determining the number of suitable units to reduce the time span, will lead to much better results in terms of project objectives.  As a result, the reliability of the project will be maximized and the risk, the time and the cost of project completion will be minimized.

While most previous studies have mainly focused on the time and costs of the project objectives, considering the reliability and risk of the project can help projects to yield better results. In addition, the features such as multiple crashable modes and mode-identity will lead to the real world situations and also better solutions can be found.

In this paper, we investigate a new optimization for territory design in the distribution system and allocation of the customers to supply centers which are considered as territory centers using MIP model. The objective is to balance the work load through minimizing the maximum differences the minimum customers allocated to the various centers. The study constraints guarantee continuity of the territories and the lack of gaps in the territories. Also, other constraints include allocation of a center to each territory and exclusive allocation of each customer to only one territory. Since, territory design and positioning are among NP-hard issues, in order to solve real-world case and big problems we have to propose meta-heuristic algorithms. For this purpose, in this paper, a grey wolf optimizer and a salp optimizer algorithm are proposed. Based on the literature review, it is very difficult to use encoding-decoding solution  without any modifier algorithm. Therefore, we design a novel solution scheme based on a minimum spanning tree in order to obviate the complexities, guarantee the continuity of the territory structures and the lack of gaps, and generate feasible solutions. Computational results on random instances showed that the proposed algorithms can effectively help to generate reasonable responses. The model proposed here could be a useful tool to aid the decision-making in distribution management, as well as for the better organization of any distribution.

One of the most important problems of logistic networks is designing and analyzing of the distribution network. The design of distribution systems raises hard combinatorial optimization problems. In recent years, two main problems in the design of distribution networks that are location of distribution centres and routing of distributors are considered together and created the location-routing problem. The location-routing problem (LRP), integrates the two kinds of decisions. The classical LRP, consists in opening a subset of depots, assigning customers to them and determining vehicle routes, to minimize total cost of the problem. In this paper, a dynamic capacitated location-routing problem is considered that there are a number of potential depot locations and customers with specific demand and locations, and some vehicles with a certain capacity. Decisions concerning facility locations are permitted to be made only in the first time period of the planning horizon but, the routing decisions may be changed in each time period. In this study, customer demands depend on the products offering prices. The corresponding model and presented results related to the implementation of the model by different solution methods have been analysed by different methods. A hybrid heuristic algorithm based on particle swarm optimization is proposed to solve the problem. To evaluate the performance of the proposed algorithm, the proposed algorithm results are compared with exact algorithm optimal value and lower bounds. The comparison between hybrid proposed algorithm and exact solutions are performed and computational experiments show the effectiveness of the proposed algorithm.

Today, intense competition in global markets has forced companies to design and manage of supply chains in a better way. Since the role of three factors: location, routing and inventory is important to continue the life of a supply chain so, integration of these three elements will create an efficient and effective supply chain. In this study, we investigate the problem of supply chain network design that including routing and inventory problem consist of flow allocation, vehicle routing between facilities, locating distribution centers and also consider the maximum coverage for respond to customer demand. Proposed mathematical model is a nonlinear mixed integer programming model for location-routing-inventory problem in the four-echelon supply chain by considering the multiple conflicting goals of total cost, travel time and maximum coverage. In order to solve the proposed model, three meta-heuristic algorithms (MOPSO, MSGA_II and NRGA) has been used. The accuracy of mathematical model and proposed algorithms are evaluated through numerical examples

Models presented in inventory management, encompass varied parameters. Primary factor in classic models related to determination of the economical ordering quantity (EOQ) and the economical production quantity (EPQ), is to consider parameters like the setup cost, the holding cost and the demand rate, to be fixed. This characteristic leads to a great difference among the quantity of the economical ordering obtained in classic models and real-word conditions. For instance, It should be stated that not only the holding costs of spoiled and useless products are not always fixed, but also, they would be increased by passing time. This article is an attempt to develop classical EOQ and EPQ models by considering holding and purchasing cost as an increasing continuous function of the ordering cycle time. Due to the complexity of the considered problem, two meta-heuristic algorithms, including Non-dominated Sorting Genetic Algorithm (NSGA-II) and Multi-objective Particle Swarm Optimization (MOPSO) are developed. Optimizing service level is considered as one of main apprehension in management science, that’s why increasing service level optimization would be evaluated as the second objective. As the performance of meta-heuristic algorithms is significantly influenced by calibrating their parameters, Taguchi methodology has been used to tune the parameters of the developed algorithms .

In the single-mode resource-constrained project scheduling problem, it is assumed that each activity has a specified known execution time and resource consumption can be done only in one way. In practice, there are many cases in which the make span can be reduced by providing additional resources activities. In this case, each activity can be done in one of the procedures, which is called the multi-mode resource-constrained project scheduling. In this paper, the problem includes determination of the basic schedule for the project activities which may be done in several models and the precedence relations are met, While the project make-span, cost and resource fluctuations are minimal. In this research project scheduling problem network will model using ED simulation software and the results of the simulation and a meta-heuristic algorithm has been compared. Finally, management strategies to optimize the scheduling, i.e such minimize total time, cost and resource leveling, will be offered.