Ethanol is a biofuel widely consumed in Brazil, which functions as a substitute for gasoline since the late 1970s. Due to several fluctuations in the characteristics of the Brazilian vehicle fleet and the political-economic conditions of the country, forecasting ethanol consumption has become a difficult task to perform. Under this scenario, the aim of this paper was to forecast ethanol consumption in Brazil using an approach of Long-Short Term Memory (LSTM) Recurrent Neural Networks (RNN) and Autoregressive Integrated Moving Average (ARIMA) models. The above, taking into consideration univariate and multivariate models for each case. Likewise, single-layer and multi-layer topologies of LSTM RNN were explored in this study. The results show that LSTM models overperformed ARIMA models even working with a relatively small training dataset of just 180 instances. This, for both univariate and multivariate models. A novel approach for searching suitable LSTM Neural Network topologies is proposed in this paper.

Footwear production is subject to the variability inherent in any process, and producers often need to apply tools that allow them to make the right decisions. This work documents the process to optimize the buffer allocation in a shoe manufacturing line minimizing the cycle time in the system, applying a metamodeling approach. It was found that the Front sewing operation, and the interaction between the Lining sewing operation and the assembly operation have the greatest effect on the flow time of the product within the process; the optimum assignment of spaces follows a non-uniform arrangement on the line saturating the slower stations; the cycle time follows a non-linear behavior vs. the total number of spaces (N) in the line. For a certain value of N, the cycle time reaches a minimum value.

Variability in manufacturing processes must be properly monitored and controlled to avoid incurring quality problems; otherwise, the probability of manufacturing defective products increases, and, consequently, production costs rise. This paper presents the development of a methodology to locate the source(s) of variation in the manufacturing process in case of a statistical deviation so that the user can quickly take corrective actions to eliminate the source of variation, thus avoiding the manufacture of out-of-specification products. The methodology integrates the multivariate cumulative sum control chart and the multilayer perceptron artificial neural network for the detection and interpretation of the source(s) of variation generated in the manufacturing processes. A case study was carried out with a printed circuit board manufacturing process, and it was possible to classify the origin of the variation with a sensitivity of 92.41% and specificity of 91.16%. The results demonstrate the viability of the proposed methodology to monitor and interpret the source of statistical variation present in production systems.

Las empresas, tiendas y negocios generan grandes cantidades de comprobantes de pago y con frecuencia son la única fuente de información sobre la forma en que se relacionan y agrupan los productos. Se analizaron los comprobantes de compra de una tienda minorista aplicando el enfoque de redes complejas. El catálogo consta de 272 productos pero los artículos se relacionan en promedio con 10 productos. A partir de la modularidad, se identificaron 39 familias de artículos; se muestran 2 ejemplos de ofertas de artículos para adquirirse juntos. Las compras forman una red tipo “mundo-pequeño” ordenada alrededor de tres productos relevantes. Esta red ha alcanzado un estado donde la probabilidad de que un artículo establezca una nueva conexión es baja. Los resultados se compararon con el sistema de clasificación ABC del inventario, los resultados muestran una clasificación que complementa el análisis y gestión de un inventario. Businesses, stores, and businesses generate large amounts of vouchers and are often the only source of information about how products are related and grouped. Vouchers from a retail store were analyzed using the complex networks approach. The catalog consists of 272 products; On average, a product is related to 10 other articles. From the modularity, 39 item families were identified, from these, 2 examples of offers with items that can be purchased together are shown. The sales form a "small-world" network ordered around three relevant products. His network has reached a state where the probability of a product establishing new connections is minimal. The results were compared with the ABC inventory classification system; the result shows a classification that complements the analysis and management of an inventory.

This article aims to serve as a guide for the construction of supply chain simulation models designed with a lean approach, using Promodel software. To achieve this, a supply chain was designed for a fictitious company located in the City of Celaya, Guanajuato and a set of suppliers located in different cities within the same State. It was used as a google tool to define the distances between each of the companies. As a final result, a representative model of a supply chain was obtained, as well as a methodology that allows the construction of lean supply chains regardless of the number of companies that comprise it. The effect of the variability in the delivery times between suppliers was incorporated into the simulation model, as well as an equation that calculates the pollution emissions of the vehicles that integrate the network that moves the products between the companies. With this work it is possible to represent networks of supply chains of real world companies, where the variability and contamination factor is included, to facilitate the decision making regarding the number of vehicles, inventory levels, quantities to be shipped, frequency in the shipments, etc. with the purpose of contaminating as little as possible and at the same time preventing interruptions in the supply chain using the least amount of resources possible.