Showing 68 results for Optimization
Hossein Khodami, Reza Kamranrad, Ehsan Mardan,
Volume 32, Issue 2 (6-2021)
Abstract
Quality plays important role for sale in the market. To attain this, many industrial managements are eager to use optimization methods to develop product quality. In this study, by evaluating the relationships between product defects and the factors affecting them, ways to improve product quality are presented. Hence, in this paper, a Structural Equation Modeling (SEM) approach is developed to identify the critical factors affecting product quality in paints industry. To this aim, 94 different laboratory samples including hydrocarbon solvent-based paints are assessed. Smart PLS software is utilized to construct the optimized model to determine critical factors. Results show that the different defects affecting the quality of paint are interrelated. In other words, the creation of a flaw will cause other flaws. It has been found that paint surface mottling that depends on the amount of usage of the Bentonite gel, pigment quantity, and resin quality used in the paint formulation affect the other defects such as orange peeling and Cratering.
Mostafa Soltani, R. Azizmohammadi, Seyed Mohammad Hassan Hosseini, Mahdi Mohammadi Zanjani,
Volume 32, Issue 2 (6-2021)
Abstract
The blood supply chain network is an especial case of the general supply chain network, which starts with the blood donating and ends with patients. Disasters such as earthquakes, floods, storms, and accidents usually event suddenly. Therefore, designing an efficient network for the blood supply chain network at emergencies is one of the most important challenging decisions for related managers. This paper aims to introduce a new blood supply chain network in disasters using the hub location approach. After introducing the last studies in blood supply chain and hub location separately, a new mixed-integer linear programming model based on hub location is presented for intercity transportation. Due to the complexity of this problem, two new methods are developed based on Particle Swarm Optimization and Differential Evolution algorithms to solve practical-sized problems. Real data related to a case study is used to test the developed mathematical model and to investigate the performance of the proposed algorithms. The result approves the accuracy of the new mathematical model and also the good performance of the proposed algorithms in solving the considered problem in real-sized dimensions. The proposed model is applicable considering new variables and operational constraints to more compatibility with reality. However, we considered the maximum possible demand for blood products in the proposed approach and so, lack of investigation of uncertainty conditions in key parameters is one of the most important limitations of this research.
Mohsen Khezeli, Esmaeil Najafi, Mohammad Haji Molana, Masoud Seidi,
Volume 32, Issue 2 (6-2021)
Abstract
One of the most important fields of logistic network is transportation network design that has an important effect on strategic decisions in supply chain management. It has recently attracted the attention of many researchers. In this paper, a multi-stage and multi-product logistic network design is considered.
This paper presents a hybrid approach based on simulation and optimization (Simulation based optimization), the model is formulated and presented in three stages. At first, the practical production capacity of each product is calculated using the Overall Equipment Effectiveness (OEE) index, in the second stage, the optimization of loading schedules is simulated. The layout of the loading equipment, the number of equipment per line, the time of each step of the loading process, the resources used by each equipment were simulated, and the output of the model determines the maximum number of loaded vehicles in each period. Finally, a multi-objective model is presented to optimize the transportation time and cost of products. A mixed integer nonlinear programming (MINLP) model is formulated in such a way as to minimize transportation costs and maximize the use of time on the planning horizon. We have used Arena simulation software to solve the second stage of the problem, the results of which will be explained. It is also used GAMS software to solve the final stage of the model and optimize the transporting cost and find the optimal solutions. Several test problems were generated and it showed that the proposed algorithm could find good solutions in reasonable time spans.
Nima Hamta, Samira Rabiee,
Volume 32, Issue 3 (9-2021)
Abstract
One of the challenging issues in today’s competitive world for servicing companies is uncertainty in some factors or parameters that they often derive from fluctuations of market price and other reasons. With regard to this subject, it would be essential to provide robust solutions in uncertain situations. This paper addresses an open vehicle routing problem with demand uncertainty and cost of vehicle uncertainty. Bertsimas and Sim’s method has been applied to deal with uncertainty in this paper. In addition, a deterministic model of open vehicle routing problem is developed to present a robust counterpart model. The deterministic and the robust model is solved by GAMS software. Then, the mean and standard deviations of obtained solutions were compared in different uncertainty levels in numerous numerical examples to investigate the performance of the developed robust model and deterministic model. The computational results show that the robust model has a better performance than the solutions obtained by the deterministic model.
Ali Fallahi, Mehdi Mahnam, Seyed Taghi Akhavan Niaki,
Volume 33, Issue 2 (6-2022)
Abstract
Integrated treatment planning for cancer patients has high importance in intensity modulated radiation therapy (IMRT). Direct aperture optimization (DAO) is one of the prominent approaches used in recent years to attain this goal. Considering a set of beam directions, DAO is an integrated approach to optimize the intensity and leaf position of apertures in each direction. In this paper, first, a mixed integer-nonlinear mathematical formulation for the DAO problem in IMRT treatment planning is presented. Regarding the complexity of the problem, two well-known metaheuristic algorithms, particle swarm optimization (PSO) and differential evolution (DE), are utilized to solve the model. The parameters of both algorithms are calibrated using the Taguchi method. The performance of two proposed algorithms is evaluated by 10 real patients with liver cancer disease. The statistical analysis of results using paired samples t-test demonstrates the outperformance of the PSO algorithm compared to differential evolution, in terms of both the treatment plan quality and the computational time. Finally, a sensitivity analysis is performed to provide more insights about the performance of algorithms and the results revealed that increasing the number of beam angles and allowable apertures improve the treatment quality with a computational cost.
Sofia Kassami, Abdelah Zamma, Souad Ben Souda,
Volume 33, Issue 3 (9-2022)
Abstract
Modeling supply chain planning problems is considered one of the most critical planning issues in Supply Chain Management (SCM). Nowadays, decisions making must be sufficiently sustainable to operate appropriately in a complex and uncertain environment of the market for many years to beyond the next decade. Therefore, making these decisions in the presence of uncertainty is a critical issue,as highlighted in a large number of relevant publications over the past two decades.The purpose of this investigation is to model a multilevel supply chain problem and determine the constraints that prevent the flow from performing properly, subject to various sources and types of uncertainty that characterize the flow. Therefore, it attempts to establish a generic model that relies on the stochastic approach. Several studies have been conducted on uncertainty in order to propose an optimal solution to this type of problem. Thus, in this study, we will use the method of "Mixed integer optimization program" which is the basis of the algorithm that will be employed. This inaccuracy of the supply chain is handled by the fuzzy sets. In this paper, we intend to provide a new model for determining optimal planning of tactical and strategical decision-making levels, by building a conceptual model. Therefore, it enables us to model the mathematical programming problem. We investigate in this attempt, attention to solving the mathematical model. So in the resolution we are going through the algorithm in machine learning, therefore providing as in the end an optimal solution for the planning of production.
Amol Dalavi,
Volume 33, Issue 4 (12-2022)
Abstract
Several industrial products such as moulds, dies, engine block, automotive parts, etc., require machining of a large number of holes. Similarly, applications like boiler plates, food-business processing separator's, printed circuit boards, drum and trammel screens, etc., consist of a matrix of a large number of holes. Many machining operations, such as drilling, enlargement, tapping, or reaming, are needed to achieve the final sizes of individual holes, resulting in a variety of possible sequences to complete the hole-making operations. The major issue involved in hole-making operations is the tool travel time. It is often vital to determine the optimal sequence of operations so that the overall processing cost of hole-making operations can be minimized. In this work, thus an attempt is made to minimize the total tool travel of hole-making operations by using a relatively new optimization algorithm known as modified shuffled frog leaping for the determination of the optimal sequence of operations. Modification is made in the present shuffled frog-leaping algorithm by using three parameters with their positive values in order to widen the search capability of the existing algorithm. This paper considers three case studies of a rectangular matrix of holes to explain the proposed procedure. The outcomes of optimization with a modified shuffled frog-leaping algorithm are compared to those obtained with the genetic algorithm and the ant colony algorithm. Additionally, the higher dimensional problem of 20 x 20 rectangular matrix of holes is considered in this work.
Motahare Gitinavard, Parviz Fattahi, Seyed Mohammad Hassan Hosseini, Mahsa Babaei,
Volume 33, Issue 4 (12-2022)
Abstract
This paper aims to introduce a joint optimization approach for maintenance, quality, and buffer stock policies in single machine production systems based on a P control chart. The main idea is to find the optimal values of the preventive maintenance period, the buffer stock size, the sample size, the sampling interval, and the control limits simultaneously, such that the expected total cost per time unit is minimized. In the considered system, we have a fixed rate of production and stochastic machine breakdowns which directly affect the quality of the product. Periodic preventive maintenance (PM) is performed to reduce out-of-control states. In addition, corrective maintenance is required after finding each out-of-control state. A buffer is used to reduce production disturbances caused by machine stops. To ensure that demand is met during a preventive and corrective maintenance operation. All features of three sub-optimization problems including maintenance, quality control, and buffer stock policies are formulated and the proposed integrated approach is defined and modeled mathematically. In addition, an iterative numerical optimization procedure is developed to provide the optimal values for the decision variables. The proposed procedure provides the optimal values of the preventive maintenance period, the buffer stock size, the sample size, the sampling interval, and the control chart limits simultaneously, in a way that the total cost per time unit is minimized. Moreover, some sensitivity analyses are carried out to identify the key effective parameters.
Islam Gomaa, Hegazy Zaher, Naglaa Ragaa Saeid, Heba Sayed ,
Volume 34, Issue 1 (3-2023)
Abstract
Researchers in many fields, such as operations research, computer science, AI engineering, and mathematical engineering, extra, are increasingly adopting nature-inspired metaheuristic algorithms because of their simplicity and flexibility. Natural metaheuristic algorithms are based on two essential terms: exploration (diversification) and exploitation (intensification). The success and limitations of these algorithms are reliant on the tuning and control of their parameters. When it comes to tackling real optimization problems, the Gorilla Troop Optimizer (GTO) is an extremely effective algorithm that is inspired by the social behavior of gorilla troops. Three operators of the original GTO algorithm are committed to exploration, and the other two operators are dedicated to exploitation. Even though the superiority of GTO algorithm to several metaheuristic algorithms, it needs to improve the balance between the exploration process and the exploitation process to ensure an accurate estimate of the global optimum. For this reason, a Novel Enhanced version of GTO (NEGTO), which focuses on the correct balance of exploration and exploitation, has been proposed. This paper suggests a novel modification on the original GTO to enhance the exploration process and exploitation process respectively, through introducing a dynamic controlling parameter and improving some equations in the original algorithm based on the new controlling parameter. A computational experiment is conducted on a set of well-known benchmark test functions used to show that NEGTO outperforms the standard GTO and other well-known algorithms in terms of efficiency, effectiveness, and stability. The proposed NEGTO for solving global optimization problems outperforms the original GTO in most unimodal benchmark test functions and most multimodal benchmark test functions, a wider search space and more intensification search of the global optimal solution are the main advantages of the proposed NEGTO.
Amir Nayeb, Esmaeil Mehdizadeh, Seyed Habib A. Rahmati,
Volume 34, Issue 2 (6-2023)
Abstract
In the field of scheduling and sequence of operations, one of the common assumptions is the availability of machines and workers on the planning horizon. In the real world, a machine may be temporarily unavailable for a variety of reasons, including maintenance activities, and the full capacity of human resources cannot be used due to their limited number and/or different skill levels. Therefore, this paper examines the Dual Resource Constrained Flexible Job Shop Scheduling Problem (DRCFJSP) considering the limit of preventive maintenance (PM). Due to various variables and constraints, the goal is to minimize the maximum completion time. In this regard, Mixed Integer Linear Programming (MILP) model is presented for the mentioned problem. To evaluate and validate the presented mathematical model, several small and medium-sized problems are randomly generated and solved using CPLEX solver in GAMS software. Because the solving of this problem on a large scale is complex and time-consuming, two metaheuristic algorithms called Genetic Algorithm (GA) and Vibration Damping Optimization Algorithm (VDO) are used. The computational results show that GAMS software can solve small problems in an acceptable time and achieve an accurate answer, and also meta-heuristic algorithms can reach appropriate answers. The efficiency of the two proposed algorithms is also compared in terms of computational time and the value obtained for the objective function.
Ahmad Lotfi, Parvaneh Samouei,
Volume 34, Issue 3 (9-2023)
Abstract
As efficient instruments, there have been increasing studies on contract optimization in the supply chain field over the recent two decades. The lack of review papers is one of the gaps in contract optimization studies. Hence, the extant study aimed to provide researchers with an attitude to direct future studies on this topic. Therefore, the collected studies on contract optimization were reviewed and analyzed primarily. Then papers were classified based on the selected categories and themes. Finally, evaluation and results were presented based on the classified topics. They conducted studies, then achievements and limitations of the literature and future research opportunities were introduced to pave the way for researchers’ further studies.
Mohammad Reza Ghatreh Samani, Jafar Gheidar-Kheljani,
Volume 34, Issue 3 (9-2023)
Abstract
In this paper, a brief review of the recently developed blood supply chain (BSC) management studies is firstly presented. Then, a first-ever multi-objective robust BSC model is proposed, which is inspired by the need for an integrated approach towards improving the performance of BSC networks under uncertain conditions. The network efficiency by minimizing cost, adequacy by providing reliable and sufficient blood supply, and effectiveness by controlling blood freshness are aimed at the proposed model. A two-phase approach based on robust programming and an augmented epsilon-constraint method is devised to model the uncertainty in parameters and provides a single-objective counterpart of the original multi-objective robust model. We investigate a case to illustrate the real-world applicability of the problem. The research comes to an end by performing some sensitivity analyses on critical parameters, and the results imply the capability of the model and its solution technique.
Seyed Erfan Mohammadi, Emran Mohammadi, Ahmad Makui, Kamran Shahanaghi,
Volume 34, Issue 4 (12-2023)
Abstract
Since 1952, when the mean-variance model of Markowitz introduced as a basic framework for modern portfolio theory, some researchers have been trying to add new dimensions to this model. However, most of them have neglected the nature of decision making in such situations and have focused only on adding non-fundamental and thematic dimensions such as considering social responsibilities and green industries. Due to the nature of stock market, the decisions made in this sector are influenced by two different parameters: (1) analyzing past trends and (2) predicting future developments. The former is derived objectively based on historical data that is available to everyone while the latter is achieved subjectively based on inside-information that is only available to the investor. Naturally, due to differences in the origin of their creation the bridge between these two types of analysis in order to optimize the portfolio will be a phenomenon called "ambiguity". Hence, in this paper, we revisited Markowitz's model and proposed a modification that allow incorporating not only return and risk but also incorporate ambiguity into the investment decision making process. Finally, in order to demonstrate how the proposed model can be applied in practice, it is implemented in Tehran Stock Exchange (TSE) and the experimental results are examined. From the experimental results, we can extract that the proposed model is more comprehensive than Markowitz's model and has greater ability to cover the conditions of the stock market.
Rabie Mosaad Rabie, Hegazy Zaher, Naglaa Ragaa Saied, Heba Sayed,
Volume 35, Issue 1 (3-2024)
Abstract
Harris Hawks Optimization (HHO) algorithm, which is a new metaheuristic algorithm that has shown promising results in comparison to other optimization methods. The surprise pounce is a cooperative behavior and chasing style exhibited by Harris' Hawks in nature. To address the limitations of HHO, specifically its susceptibility to local optima and lack of population diversity, a modified version called Modified Harris Hawks Optimization (MHHO) is proposed for solving global optimization problems. A mutation-selection approach is utilized in the proposed Modified Harris Hawks Optimization (MHHO) algorithm. Through systematic experiments conducted on 23 benchmark functions, the results have demonstrated that the MHHO algorithm offers a more reliable solution compared to other established algorithms. The MHHO algorithm exhibits superior performance to the basic HHO, as evidenced by its superior average values and standard deviations. Additionally, it achieves the smallest average values among other algorithms while also improving the convergence speed. The experiments demonstrate competitive results compared to other meta-heuristic algorithms, which provide evidence that MHHO outperforms others in terms of optimization performance.
Welly Sugianto, Reazul Haq Abdul Haq, Mohd Nasrull Bin Abdol Rahman,
Volume 35, Issue 1 (3-2024)
Abstract
The automobile workshop queue system has been optimized using various approaches, such as queuing theory, simulation, and probability. The utilization of response surface methodology (RSM) for optimizing automobile workshop queue systems is not yet established. The utilization of RSM with direct observation enables the detection of patterns of correlations between variables and responses, which are then represented through mathematical equations. The optimization process involves numerous factors that impact queue performance, which can be categorized into two parts. The number of servers, number of phases, number of workers, worker experience, and layout are classified in inner design. This study examines the relationship between two components of the outer design, specifically the arrival rate and the interarrival time. The responses analyzed are queue cost, service time, average customer waiting time, and number of customers. The findings indicate that queue costs are not reliable for establishing the optimum value due to the significant impact of the cost structure on the structure of the optimal location. This study discovered that the number of leaving customers is related to queue costs and is relevant in selecting the optimal point. This study also formulates mathematical equations for predicting the optimal point. This study emphasizes the necessity for further investigation to uncover alternative mathematical equations that can precisely predict the optimal conditions for various types of services.
Ali Salmasnia, Elahe Heydarnezhad, Hadi Mokhtari,
Volume 35, Issue 2 (6-2024)
Abstract
Abstract. One of the important problems in managing construction projects is selecting the best alternative for activities' execution to minimize the project's total cost and time. However, uncertain factors often have negative effects on activity duration and cost. Therefore, it is crucial to develop robust approaches for construction project scheduling to minimize sensitivity to disruptive noise factors. Additionally, existing methods in the literature rarely focus on environmentally conscious construction management. Achieving these goals requires incorporating the project scheduling problem with multiple objectives. This study proposes a robust optimization approach to determine the optimal construction operations in a project scheduling problem, considering time, cost, and environmental impacts (TCE) as objectives. An analytical algorithm based on Benders decomposition is suggested to address the robust problem, taking into account the inherent uncertainty in activity time and cost. To evaluate the performance of the proposed solution approach, a computational study is conducted using real construction project data. The case study is based on the wall of the east coast of Amirabad port in Iran. The results obtained using the suggested solution approach are compared to those of the CPLEX solver, demonstrating the appropriate performance of the proposed approach in optimizing the time, cost, and environment trade-off problem.
Faikul Umam, Hanifudin Sukri, Ach Dafid, Firman Maolana, Mycel Natalis Stopper Ndruru,
Volume 35, Issue 4 (12-2024)
Abstract
Robots are one of the testbeds that can be used as objects for the application of intelligent systems in the current era of Industry 4.0. With such systems, robots can interact with humans through perception (sensors) like cameras. Through this interaction, it is expected that robots can assist humans in providing reliable and efficient service improvements. In this research, the robot collects data from the camera, which is then processed using a Convolutional Neural Network (CNN). This approach is based on the adaptive nature of CNN in recognizing visuals captured by the camera. In its application, the robot used in this research is a humanoid model named Robolater, commonly known as the Integrated Service Robot. The fundamental reason for using a humanoid robot model is to enhance human-robot interaction, aiming to achieve better efficiency, reliability, and quality. The research begins with the implementation of hardware and software so that the robot can recognize human movements through the camera sensor. The robot is trained to recognize hand gestures using the Convolutional Neural Network method, where the deep learning algorithm, as a supervised type, can recognize movements through visual inputs. At this stage, the robot is trained with various weights, backbones, and detectors. The results of this study show that the F-T Last Half technique exhibits more stable performance compared to other techniques, especially with larger input scales (640×644). The model using this technique achieved a mAP of 91.6%, with a precision of 84.6%, and a recall of 80.6%.
Ahmad Aliyari Boroujeni, Ameneh Khadivar,
Volume 36, Issue 2 (6-2025)
Abstract
The Traveling Salesman Problem (TSP) is a well-known problem in optimization and graph theory, where finding the optimal solution has always been of significant interest. Optimal solutions to TSP can help reduce costs and increase efficiency across various fields. Heuristic algorithms are often employed to solve TSP, as they are more efficient than exact methods due to the complexity and large search space of the problem. In this study, meta-heuristic algorithms such as the Genetic Algorithm and the Teaching-Learning Based Optimization (TLBO) algorithm are used to solve the TSP. Additionally, a discrete mutation phase is introduced to the TLBO algorithm to enhance its performance in solving the TSP. The results indicate that, in testing two specific models of the TSP, the modified TLBO algorithm outperforms both the Genetic Algorithm and the standard TLBO algorithm in terms of convergence to the optimal solution and response time.
Ahmad Mohammadpour Larimi, Babak Shirazi, Iraj Mahdavi,
Volume 36, Issue 2 (6-2025)
Abstract
location-inventory problem (LIP) is a significant issue in supply chain management (SCM), aiming to reduce and integrate the costs of inventory and location. Perishable-LIP (PLIP) includes products, particularly those with a short expiration date, also known as perishable items. This feature necessitates the supply chain to maintain high reliability and resilience to minimize costs faced with disruption risks. Implementing reliability and resilience in PLIP (R2-PLIP) requires methods such as lateral transshipment. These methods not only enhance the reliability and resiliency of the SC but also mitigate the risks associated with supply disruptions and demand fluctuations. Demand for perishable products is influenced by their expiration dates. By incorporating lateral transshipment, companies can ensure a more balanced inventory distribution. This study investigates the role of lateral transshipment in enhancing supply chain robustness. A multi-objective optimization model is developed, focusing on minimizing costs while maximizing resilience and service levels. The project aims to optimize the overall system efficiency. Additionally, the sensitivity analysis conducted in the research indicates that the shortage cost and the DC capacity each had the greatest variations in one of the objective functions. This research provides practical insights for designing resilient perishable supply chains.
Ida Lumintu, Achmad Maududie,
Volume 36, Issue 3 (9-2025)
Abstract
Effective inventory management is critical for mitigating inefficiencies such as overproduction, excessive holding costs, and stockouts. This study leverages DBSCAN and GMM clustering methods, combined with Principal Component Analysis (PCA) for dimensionality reduction, to categorize inventory data into distinct risk-based clusters. The analysis highlights that DBSCAN outperformed GMM, achieving a silhouette score of 0.62 compared to 0.49, while identifying three meaningful inventory clusters. Each cluster reflects unique combinations of risk factors, providing actionable insights for optimizing inventory levels. The study demonstrates how these clusters enable targeted strategies to address inefficiencies and improve overall inventory management. Limitations include the reliance on historical data, which may not fully capture dynamic market conditions, and the assumption of fixed clustering parameters. The findings underscore the importance of choosing clustering algorithms suited to the data's characteristics and highlight the potential of PCA in enhancing computational efficiency. Future research should explore dynamic clustering techniques and integrate real-time data streams to refine inventory management strategies further.
