A hybrid multi-objective approach based on the genetic algorithm and neural network to design an incremental cellular manufacturing system

Zeidi, Javad Rezaeian; Javadian, Nikbakhsh; Tavakkoli–Moghaddam, Reza; Jolai, Fariborz

doi:10.1016/j.cie.2013.08.015

Cited by 24 publications

(8 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results showed that the proposed MOVDO algorithm had a better performance in solving various small, medium, and large-scale problems. Saidi-Mehrabad and Safaei [8] Defersha and Chen [9] Tavakkoli-Moghaddam et al [10] Mahdavi et al [17] Bagheri and Bashiri [18] Saidi-Mehrabad et al [19] Mahdavi et al [11] Majazi Dalfard [12] Salarian et al [14] Bychkov and Batsyn [15] Zohrevand et al [16] Ghotboddini et al [34] Martins et al [35] Rafiei and Ghodsi [37] Zeidi et al [38] Shiyas and Madhusudanan Pillai [39] Rezazadeh et al [40] Buruk Sahin and Alpay [41] Durga Rajesh et al [42] Hajipour et al [48] Tavakkoli-Moghaddam et al [49] Hajipour et al [50] Hajipour et al [51] O2= considering costs (e.g., machine operating cost, machine modification costs, machine reconfiguration cost, and machine setup cost) O3= considering machine utilization. O4= considering operators costs (e.g., operator training cost and operator allocation cost , 1) X A L and t t  ;…”

Section: Resultsmentioning

confidence: 99%

“…Rafiei and Ghodsi [39]proposed a novel ant colony optimization algorithm to solve NP-hard instances of a biobjective CFP. Also, a mutation operator of the GA was added to the main procedure of the proposed algorithm to elaborate diversification characteristics of the proposed algorithm.Zeidi, et al [40]presented a novel hybrid metaheuristic algorithm to solve intricate examples of a nonlinear mixed-integer programming model of a dynamic a CFP. A specific procedure of the neural network method was implemented into the main mechanism of the GA to solve various instances of this problem and obtain more qualified near-optimal solutions.…”

Section: 3solution Algorithms Developed For Solving the Dynamic Cmsmentioning

confidence: 99%

“… (40) wherethe index of the nonlinear formulation is shown by . The value of this parameter plays a crucial role in obtaining suitable solutions.…”

Section: Multi-objective Invasive Weeds Optimization Algorithm (Moiwo)mentioning

confidence: 99%

See 2 more Smart Citations

A multi-objective vibration damping optimization algorithm for solving a cellular manufacturing system with manpower and tool allocation

et al. 2020

Self Cite

View full text Add to dashboard Cite

In this paper, a novel bi-objectivemathematical model is proposed to designa fourdimensional (i.e., part, machine, operator, and tool) cellular manufacturing system (CMS) in a dynamic environment. The main objectives of this model are to 1) minimize total costs including tools processing cost, costs of transporting cells between various cells, machine setup cost, and operators' educational costs, and 2) maximizing skill level of operators. The developed model is strictly NP-hard and exact algorithms cannot find globally optimal solutions in reasonably computational time. So, a multi-objective vibration damping optimization algorithm (MOVDO) with a new solution structure that satisfies all the constraints and generates feasible solutions is proposed to find near-optimal solutions in reasonablycomputational time. Since there is no benchmark available in the literature, three other meta-heuristic algorithms (i.e., non-dominated sorting genetic algorithm (NSGA-II), multi-objective particle swarm optimization (MOPSO) and multi-objective invasive weeds optimization (MOIWO)) with the similar solution structure are developed to validate the performance of the proposedMOVDO algorithm for solving various instances of the developed model. The result of comparing theirperformances based on statistical tests and different measuring metrics reveals that the proposed MOVDO algorithm outperforms remarkably better than other meta-heuristics used in this paper.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: 3solution Algorithms Developed For Solving the Dynamic Cmsmentioning

confidence: 99%

See 1 more Smart Citation

A multi-objective vibration damping optimization algorithm for solving a cellular manufacturing system with manpower and tool allocation

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Some of the CMSs proposed are, including but not limited to, virtual CM, dynamic CM (Rheault et al, 1996), fractal CM (Montreuil et al, 1999), holonic manufacturing (Nomden et al, 2005), layered CMS (Süer et al, 2010), constrained optimisation (Brown, 2015), p-median approach (Won and Logendran, 2015), heuristics, etc. (Islam et al, 2013;Zeidi et al, 2013). Süer and Bera (1996) classified CMSs as labour-intensive and machine-intensive considering the degree of labour involvement in the process.…”

Section: Introductionmentioning

confidence: 99%

Hybrid cellular manufacturing system design with cellularisation ratio: an integrated mixed integer nonlinear programming and discrete event simulation approach

Eğilmez

Erenay

Süer

2019

IJSOM

View full text Add to dashboard Cite

This study investigates hybrid cellular manufacturing system design where products with highly similar process routes are formed as manufacturing cells, and products with dissimilar routes are produced in a process layout. A cell similarity threshold, cellularisation ratio (C-ratio), is proposed for product assignment to cells and process layout, and integrated into a mathematical modelling-based cell formation approach. The cell formation phase is carried out with the proposed mathematical model. Several case problems are tested, and selected cases are also studied with a newly developed simulation model where manufacturing system performance is also evaluated along with the proposed hybrid cellular manufacturing design alternatives. Results indicated that considering a C-ratio during cell formation can provide higher cell similarity thus better cell formation. The increase in the coverage levels resulted in higher number of cells formed. The proposed approach can be significantly beneficial for manufacturing design decisions where product mix and process complexity are high, and for a hybrid layout that consists of cellular plus process layouts could be implemented.

show abstract

“…Se logró aproximar los modelos teóricos a los prácticos, permitiendo obviar algunas limitaciones como el tamaño de los problemas con buenos resultados. (Zeidi et al, 2013) Se presenta un modelo de programación multiobjetivo en el cual se trata el plan de conversión de talleres de trabajo a sistemas de manufactura celular. Se emplea un algoritmo genético y una red neuronal, sobre ambientes dinámicos.…”

Section: Introductionunclassified

Programación de un Sistema Job Shop-Open Shop por medio de una Red Neuronal

2016

View full text Add to dashboard Cite

Se propone una metodología basada en redes neuronales para la programación de pedidos en un ambiente job shop-open shop. El problema de programación de la producción en sistemas job shop consiste en definir la mejor secuencia de pedidos para minimizar el tiempo total de proceso (makespan) u otras variables relevantes. Diversas técnicas inteligentes se han aplicado para resolver este tipo de problema. Sin embargo, estás presentan dificultades prácticas cuando se requieren cambios de programación, pues exigen reconfigurar nuevamente el problema para obtener una nueva solución. La metodología propuesta entrena la red mediante la combinación de los tiempos de proceso en cada nodo, por medio de funciones de transferencia multiplicadas por pesos que son generados por el algoritmo de programación de la red. La red neuronal propuesta permite obtener soluciones no solo para un problema en particular, sino para los nuevos que surjan sin necesidad de hacer una nueva reconfiguración. Las soluciones encontradas fueron comparadas con otras técnicas de programación de la producción, encontrándose desempeños superiores en el makespan del orden del 30% al 164%. Palabras clave: programación de la producción; redes neuronales; job shop-open shop; makespan

show abstract

A hybrid multi-objective approach based on the genetic algorithm and neural network to design an incremental cellular manufacturing system

Cited by 24 publications

References 27 publications

A multi-objective vibration damping optimization algorithm for solving a cellular manufacturing system with manpower and tool allocation

A multi-objective vibration damping optimization algorithm for solving a cellular manufacturing system with manpower and tool allocation

Hybrid cellular manufacturing system design with cellularisation ratio: an integrated mixed integer nonlinear programming and discrete event simulation approach

Programación de un Sistema Job Shop-Open Shop por medio de una Red Neuronal

Contact Info

Product

Resources

About