International Journal of Industrial Engineering: Theory, Applications and Practice
Not a member yet
943 research outputs found
Sort by
A New Decision Support System at Estimation of Project Completion Time Considering the Combination of Artificial Intelligence Methods based on Earn Value Management Framework
No full textOne of the important issues in project management is estimation of projects completion time. This paper proposes a model based on ensemble learning using certain features of projects in Earn Value Management (EVM) to estimate project completion time. Proper simulation of the dynamic nature of the project, higher reliability in comparison with individual methods, better robustness against the presence of a weak estimator, and appropriate control of the type and number of the existing regressions in ensemble are the important features of the proposed model. The proposed method is evaluated based on two datasets, which are created by three real projects, and promising results are obtained as compared to the other well-known estimators
AGENT-BASED NEGOTIATION MODEL FOR PUBLIC PROCUREMENT IN BRAZIL
No full textBrazil has specific legislation regarding public procurement, establishing rules for the Public Administration when hiring contractors. Despite clear legislation, corruption in the selection of suppliers is often noted. In order to bring more transparency to the process, as well as to minimize the possibility of corruption, the use of public e-procurement systems is growing. In this context, specifically in the Brazilian case, an agent-based negotiation model is proposed to automate the negotiation and selection of suppliers in the electronic auction modality. The model is composed of procedures to measure the utility of each proposal; generate counter-proposals through concession tactics; and to choose the most appropriate supplier, according to the utility of proposals at the end of the negotiation. A negotiation simulation was performed in an instance of the acquisition of a product by a Brazilian university. It was possible to verify the applicability of the model and evaluate the impact of the parameters in the result of the negotiation proces
Implementation of Prognostics and Health Management in South Korean Defense Systems
No full textAs an advanced reliability-estimation concept, prognostics and health management (PHM) has been widely used to estimate the remaining useful life of individual systems, especially those embedded in U.S. military applications. However, there have as yet been no specific attempts to apply PHM or another advanced reliability-estimation methods to South Korea’s defense systems. We herein examine a feasible application to improve the reliability, availability and maintainability (RAM) of defense system performance, mainly through simulation-study-based comparison of South Korean and United States reliability-estimation technologies and strategies. We then provide a long-term-perspective roadmap for the introduction ofPHM to South Korea’s defense systems. In particular, it is expected that availability improvement in South Korean defense systems can be achieved through accurate residual-life prediction by introducing PHM to defense system operation
A MOVING SHIFTING VECTOR METHOD FOR RELIABILITY-BASED DESIGN OPTIMIZATION USING EFFECTIVENESS CHECKING OF PROBABILISTIC CONSTRAINT
No full textReliability-based design optimization (RBDO) aims at making the best decisions when unavoidable efforts of uncertainties are taken into account. To generate an accurate RBDO solution using as small number of function evaluations as possible, a moving shifting vector method is proposed in this work. Reliability index combined with a moving scheme are used to calculate the optimal most probable point and shifting vector, which is much simpler than the original optimal shifting vector method. Moreover, the result of reliability analysis in the proposed method is used to check the effectiveness of probabilistic constraint, which results in a novel constraint handling scheme with the aim of simplifying the deterministic optimization model in MSV. The new MSV method is very efficient for nonlinear problems. Two mathematical problems and a multi-component Tailor-welded blank structure crashworthiness design application are tested to show considerable savings of function evaluations in the proposed method
RECENT ADVANCES IN MODELLING AND OPTIMIZING COMPLEX SYSTEMS BASED ON INTELLIGENT ALGORITHMS
No full textThe paper tries to understand recent research advances in modelling and optimizing complex systems to give references for interested researchers. Intelligent models have the capability of self-adapting to the changing environment, which may generate effective solutions for complex dynamic systems. Firstly, critical techniques and significant events in the development process of complex systems are reviewed. Then classical practical applications of modelling and optimizing complex systems over recent years based on several representative intelligent models are introduced and analysed. Thirdly, methodology of each intelligent M & O model is analysed and compared. Finally, this paper concludes and prospects relevant future work
AN ALTERNATIVE DEA APPROACH FOR EVALUATING THE SYSTEM EFFICIENCY IN THE PRESENCE OF DUAL-ROLE FACTORS
No full textIn evaluating the performance of production systems, the role of a measure from input and output aspects is usually certain and known. Nevertheless, there are occasions in the real world that some factors can play both input and output roles. In data envelopment analysis (DEA) literature, these factors are called dual-role factors. In the current paper, an alternative DEA approach is proposed for incorporating dual-role factors in the production process. In previous models, a dual-role factor can only take one role (input, output or indifference to being an input or an output) after the evaluation while in the proposed model herein a dual-role factor can simultaneously take both input role and output role in estimating the efficiency of each decision making unit (DMU). Indeed, a portion of a dual-role factor is obtained as a mixture of input and output roles. Numerical examples are used to illustrate the suggested approach
NEW MODELS FOR A SINGLE-MANUFACTURER MULTI-RETAILER SUPPLY CHAIN UNDER VENDOR MANAGED INVENTORY PROGRAM
No full textVendor managed inventory (VMI) is a partnership between a supplier and buyers whereby supplier makes inventory replenishment decisions on behalf of buyers. A (z, Z) VMI contract is one of the strategies that protects the buyers from dispatching a lot of inventory by the supplier using lower bound z and upper bound Z on the buyer’s inventory level. This paper develops a model for a single vendor and multiple retailers supply chain under (z, Z) VMI contracts by considering the time value of money and also introduces a novel approach designated as “secondary negotiations” in order to improve manufacturer’s cost or retailers’ profits. Numerical analysis is designed to compare the performance (z, Z) VMI contract and independent system (without VMI) that both consider the time value of money. Furthermore, computational results shows that secondary negotiation how change in both upper bounds and replenishment quantity and cause to absorb and keep important retailers and increase their level of satisfaction for developing more mutual cooperation.
FRUITS AND VEGETABLES MARKET HALL LOCATION SELECTION BY USING INTERVAL-VALUED TRAPEZOIDAL FUZZY GREY RELATIONAL ANALYSIS: AN APPLICATION FOR ISTANBUL
No full textIn urban areas, effectively delivering the necessary products for people to survive to the desired points has a vital importance. Determining the urban distribution centers locations truly, which have an important role in distribution networks, will satisfy determining the number of vehicles, minimizing the traffic congestion by determining the routes of vehicles correctly and thus decreasing the environmental effects like noise and emission. In this study, fresh fruits and vegetables market hall (F&VMH), which is an important urban distribution center type that fulfills the food requirements of city residents, location determination problem is investigated. To solve this problem, interval-valued trapezoidal fuzzy grey relational analysis (GRA) method is used because is suitable to deal with poor, incomplete, and uncertain information. When the results are analyzed, it is seen that F&VMHs have to be located in the district which is closer to producers and which has the lower building and land costs
A robust possibilistic-M/G/c queuing model for a hub location problem with a ring topology of a backbone network
No full textIn a telecommunication industry as one of the oldest users of the hub network concept, networks do not operate on a complete hub network and hubs can configure different structures. A ring topology, especially synchronous optical network (SONET) rings in telecommunication networks, has increasing importance because of the self-healing properties associated with them. In this paper, a novel model is presented for a hub location problem with a ring topology of a hub network under the inherent uncertainty of input data. In this model, hubs are considered as M/G/c queuing system. To solve the model, a new hybrid solution methodology is introduced by combining a robust possibilistic programming approach and queuing theory. To study the behavior of the robustness of the proposed model, computational experiments are considered for a number of test problems. A comparative analysis is carried out to show the performance and superiority of the robust approach over the basic possibilistic chance constrained programming approach
A RUN SUM S CHART WITH TWO SAMPLING INTERVALS
No full textThe variable sampling interval run sum (VSI RS) S chart that adopts two different sampling interval lengths on the run sum (RS) S chart is proposed. The Markov chain method is used to compute the optimal parameters that minimize the out-of-control zero state average time to signal (ATS), steady state ATS (SATS), expected ATS (EATS) and expected SATS (ESATS). The results show that the optimal VSI RS S chart outperforms the EWMA S chart in detecting moderate and large shifts while surpassing the RS S and standard S charts in detecting all sizes of shifts, in the process standard deviation. The ability of the VSI RS S chart to detect shifts in the process standard deviation quickly can improve productivity in manufacturing and reduce scrap and rework costs. An illustrative example is provided to facilitate the implementation of the proposed chart