Search

This paper aims at proposing a novel quadratic assignment-based mathematical model for designing an optimal facility layout in each period of the stochastic dynamic facility layout problem (SDFLP). Considering routing flexibility is the main assumption of this problem so that parts can pass through multiple routes. It is also assumed that product demands are independent, normally distributed random variables with known expected value and variance changing from period to period at random. In addition, to solve the proposed model, a new hybrid meta-heuristic algorithm is developed by combining simulated annealing (SA) and the CRAFT approaches. Finally, the proposed model and the hybrid algorithm are verified and validated using design of experiment, real case study and sensitivity analysis methods as well as solving some numerical examples.The results show that the hybrid algorithm has an outstanding performance from both solution quality and computational time perspectives. Moreover, the proposed model can be used to design the layout of facilities in both of the stochastic and deterministic environments of traditional and modern manufacturing systems.

The facility layout problem (FLP) is a combinatorial optimization problem. The performance of the layout design is significantly impacted by diverse, multiple factors. The use of algorithmic or procedural design methodology in ranking and identification of efficient layout is ineffective. In this context, this study proposes a three‐stage methodology where data envelopment analysis (DEA) is augmented with unsupervised and supervised machine learning (ML). In stage 1, unsupervised ML is used for the clustering of the criteria in which the layouts need to be evaluated using homogeneity. Layouts are generated using simulated annealing, chaotic simulated annealing, and hybrid firefly algorithm/chaotic simulated annealing meta‐heuristics. In stage 2, the nonparametric DEA approach is used to identify efficient and inefficient layouts. Finally, supervised ML utilizes the performance frontiers from DEA (efficiency scores) to generate a trained model for getting the unique rankings and predicted efficiency scores of layouts. The proposed methodology overcomes the limitations associated with large datasets that contain many inputs / outputs from the conventional DEA and improves the prediction accuracy of layouts. A Gaussian distribution product demand dataset for time period T = 5 and facility size N = 12 is used to prove the effectiveness of the methodology. [ABSTRACT FROM AUTHOR]

Sustainable Operations due to depleting natural resources, socio-economic disparities and climatic conditions has attracted researchers to proposed new models and techniques. The paper proposes a novel technique to address the 3P's (planet, people and profit) of sustainability and following are the highlights, • Integrated 4-stage method to find an energy efficient sustainable facility layout • Big Data-Machine Learning (ML) is used to reduce and derive sustainable criteria • Criteria are mathematically formulated as multi-objective sustainable FLP • Meta-heuristic applied to get layout pool that is evaluated for efficiency computation using DEA-ML • K-mean clustering applied to get a layout that maximally satisfy sustainability criteria Facility Layout Design (FLP) is an NP-Hard, which is related to the optimization of the arrangement of facilities in a shop floor or manufacturing unit to maximize the performance and minimize the operating cost. An efficient layout must not only consider the profit but also emphasize on other social causes such as energy consumption, pollution, and people's safety. These are referred to as the three pillars of sustainability. This paper identifies the criteria for sustainability in a manufacturing layout and presents an aggregate mathematical formulation for Sustainable Facility Layout Problem (SFLP). The paper proposes a novel 4-stage methodology using Big Data Analytics, Machine Learning, Hybrid Meta-heuristic, Data Envelopment Analysis (DEA), and K-mean clustering for designing an energy-efficient sustainable sub-optimal layout under uncertain (stochastic) demand over multiple periods. The goal of this framework is to 1) uniquely rank and predict an efficient SFLP that overcomes the dimensionality curse associated with handling large data set, 2) use K-mean to identify the criteria that maximally satisfied an efficient sustainable layout and propose an SFLP model that can be customized depending social, political and economic conditions, and 3) evaluate the total energy consumption and CO 2 emission for an efficient sustainable facility layout. To show the running methodology a case is presented using hypothetical data from the literature. [ABSTRACT FROM AUTHOR]