Stochastic plans in SMEs: A novel multidimensional fuzzy logic system (mFLS) approach
Fuente:
Redalyc
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Artículo científico |
| Lenguaje: | en |
| Publicado: |
Universidad Nacional de Colombia
2018
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1876471550823104512 |
|---|---|
| author | Roberto Baeza-Serrato |
| author_facet | Roberto Baeza-Serrato |
| contents | Stochastic plans in SMEs: A novel multidimensional fuzzy logic system (mFLS) approach Roberto Baeza-Serrato Ingeniería fuzzy system neural network Stochastic plans normal probability density Manufacturing planning in small and medium enterprises (SMEs) uses a deterministic behavior, and the execution of these plans has a stochastic behavior. The evaluation of the manufacturing planning is based on a simple criterion as job on time or job delayed, without integrating conditions of uncertainty in the cycle times for each job. The aim of this paper is to propose a novel multidimensional stochastic Fuzzy Logic System (msFLS) approach to execute a plan with stochastic behavior in knitting SMEs and their evaluation. In this paper, two main contributions are identified. On one hand, the generation of a multi-dimensional diffuse system is proposed. Normal probability density function is used to generate multi linguistic variables to transform deterministic plans to stochastic plans in knitting SMEs. The fuzzy subsets or linguistic terms are labelled and categorized in a simple and clear language as poor (P), regular (R), good (G) and excellent (E). The Gaussian function was used as a membership function. On the other hand, the second contribution is the use of the sum of frequencies in the stage of implication for the multi-Fuzzy system. This research was validated through an integration of two different intelligent techniques such as the proposed novel msFLS and artificial neural networks. Neural networks were used as a generalization mechanism to perform any stochastic planning in the knitting companies. The inputs and outputs of the fuzzy system are used as training patterns in the neural network. The stages of the proposed approach are explicitly described and applied to random data and validated with real data of SMEs of the South of Guanajuato, Mexico. The proposed system had a positive response in the textile company, which continues to be used to carry out its manufacturing planning and the evaluation of its execution. 2018 artículo científico 0120-5609 https://www.redalyc.org/articulo.oa?id=64358073009 https://www.redalyc.org/journal/643/64358073009/ https://www.redalyc.org/journal/643/64358073009/html/ https://www.redalyc.org/journal/643/64358073009/64358073009.epub https://www.redalyc.org/journal/643/64358073009/movil 10.15446/ing.investig.v38n2.65357 en http://www.redalyc.org/revista.oa?id=643 Ingeniería e Investigación application/pdf Universidad Nacional de Colombia Ingeniería e Investigación (Colombia) Num.2 Vol.38 |
| format | Artículo científico |
| id | redalyc_64358073009 |
| institution | Redalyc |
| language | en |
| publishDate | 2018 |
| publisher | Universidad Nacional de Colombia |
| spellingShingle | Stochastic plans in SMEs: A novel multidimensional fuzzy logic system (mFLS) approach Roberto Baeza-Serrato Ingeniería fuzzy system neural network Stochastic plans normal probability density Stochastic plans in SMEs: A novel multidimensional fuzzy logic system (mFLS) approach Roberto Baeza-Serrato Ingeniería fuzzy system neural network Stochastic plans normal probability density Manufacturing planning in small and medium enterprises (SMEs) uses a deterministic behavior, and the execution of these plans has a stochastic behavior. The evaluation of the manufacturing planning is based on a simple criterion as job on time or job delayed, without integrating conditions of uncertainty in the cycle times for each job. The aim of this paper is to propose a novel multidimensional stochastic Fuzzy Logic System (msFLS) approach to execute a plan with stochastic behavior in knitting SMEs and their evaluation. In this paper, two main contributions are identified. On one hand, the generation of a multi-dimensional diffuse system is proposed. Normal probability density function is used to generate multi linguistic variables to transform deterministic plans to stochastic plans in knitting SMEs. The fuzzy subsets or linguistic terms are labelled and categorized in a simple and clear language as poor (P), regular (R), good (G) and excellent (E). The Gaussian function was used as a membership function. On the other hand, the second contribution is the use of the sum of frequencies in the stage of implication for the multi-Fuzzy system. This research was validated through an integration of two different intelligent techniques such as the proposed novel msFLS and artificial neural networks. Neural networks were used as a generalization mechanism to perform any stochastic planning in the knitting companies. The inputs and outputs of the fuzzy system are used as training patterns in the neural network. The stages of the proposed approach are explicitly described and applied to random data and validated with real data of SMEs of the South of Guanajuato, Mexico. The proposed system had a positive response in the textile company, which continues to be used to carry out its manufacturing planning and the evaluation of its execution. 2018 artículo científico 0120-5609 https://www.redalyc.org/articulo.oa?id=64358073009 https://www.redalyc.org/journal/643/64358073009/ https://www.redalyc.org/journal/643/64358073009/html/ https://www.redalyc.org/journal/643/64358073009/64358073009.epub https://www.redalyc.org/journal/643/64358073009/movil 10.15446/ing.investig.v38n2.65357 en http://www.redalyc.org/revista.oa?id=643 Ingeniería e Investigación application/pdf Universidad Nacional de Colombia Ingeniería e Investigación (Colombia) Num.2 Vol.38 |
| title | Stochastic plans in SMEs: A novel multidimensional fuzzy logic system (mFLS) approach |
| topic | Ingeniería fuzzy system neural network Stochastic plans normal probability density |
| url | https://www.redalyc.org/articulo.oa?id=64358073009 https://www.redalyc.org/journal/643/64358073009/ https://www.redalyc.org/journal/643/64358073009/html/ https://www.redalyc.org/journal/643/64358073009/64358073009.epub https://www.redalyc.org/journal/643/64358073009/movil |