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.

Recently, water has become a resource that generates controversy due to shortage alarms and high consumption by production companies. Making good use of water has become the main objective of government institutions. The food industry generates a large amount of wastewater, concentrating the largest number of contaminants originated in its processes. Wastewater from the food industry is characterized by having a large amount of organic matter, especially fats and oils, as well as suspended solids. The objective of this research is to carry out a characterization of effluents generated in a wastewater treatment plant in the food sector based on Mexican and international regulations to determine whether it is reusable. This article addresses Mexico’s lag in the reuse of treated wastewater in the face of the water crisis, highlighting the urgency of adopting these practices to mitigate water scarcity. For the development of this investigation, samples were collected at the discharge point produced by the company’s effluents, followed by an evaluation of their physical, chemical, and biological parameters, and finally, it was determined that the effluent follows the regulatory standards for discharge into the city sewer but outside the range for reuse in productive processes or irrigation of green areas.

Multivariate Statistical Process Control (MSPC) seeks to monitor several quality characteristics simultaneously. However, it has limitations derived from its inability to identify the source of special variation in the process. In this research, a proposed model that does not have this limitation is presented. In this paper, data from two scenarios were used: (A) data created by simulation and (B) random variable data obtained from the analysed product, which in this case corresponds to cheese production slicing process in the dairy industry. The model includes a dimensional reduction procedure based on the centrality and data dispersion. The goal is to recognise a multivariate pattern from the conjunction of univariate variables with variation patterns so that the model indicates the univariate patterns from the multivariate pattern. The model consists of two stages. The first stage is concerned with the identification process and uses Moving Windows (MWs) for data segmentation and pattern analysis. The second stage uses Bayesian Inference techniques such as conditional probabilities and Bayesian Networks. By using these techniques, the univariate variable that contributed to the pattern found in the multivariate variable is obtained. Furthermore, the model evaluates the probability of the patterns of the individual variables generating a specific pattern in the multivariate variable. This probability is interpreted as a signal of the performance of the process that allows to identify in the process a multivariate out-of-control state and the univariate variable that causes the failure. The efficiency results of the proposed model compared favourably with respect to the results obtained using the Hotelling’s $T^2$ chart, which validates our model.

The correct management of operations in thermoelectric plants is based on the continuous evaluation of the structural integrity of its components, among which there are elements made of stainless steel that perform water conduction functions at elevated temperatures. The working conditions generate progressive wear that must be monitored from the perspective of the microstructure of the material. When AISI 304 stainless steel is subjected to a temperature range between 450 and 850 °C, it is susceptible to intergranular corrosion. This phenomenon, known as sensitization, causes the material to lose strength and generates different patterns in its microstructure. This research analyzes three different patterns present in the microstructure of stainless steel, which manifest themselves through the following characteristics: the absence of intergranular corrosion, the presence of intergranular corrosion, and the precipitation of chromium carbides. This article shows the development of a methodology capable of recognizing the corrosion patterns generated in stainless steel with an accuracy of 98%, through the integration of a multilayer perceptron neural network and the following digital image processing methods: phase congruence and a gray-level co-occurrence matrix. In this way, an automatic procedure for the analysis of the intergranular corrosion present in AISI 304 stainless steel using artificial intelligence is proposed.

This paper describes a statistical and mathematical approach to optimize the mechanical properties of a wood plastic composite with Polyethylene Terephthalate (PET) as polymeric matrix. Wood plastic composite are materials that consist of a primary continuous polymer phase, where a secondary filler dispersed phase is embedded, the filler generally is wood fibers or sawdust. The slack variable approach in mixture experiments, consist in selecting a component of the mixture as slack variable, to subsequently design and analyze the experiment in terms of the remaining components. With the experimental design information three slack variable model were fit. Using response surface graphs, we show how different compositions modify the mechanical properties of wood plastic composite. Besides, by the desirability function, the optimal formulation of the compound that simultaneously maximizing the mechanical properties of wood plastic composite, was obtained. Finally, the components proportions that provides the best tensile, flexural and compression strength are presented.

Wood–plastic composites (WPCs) are materials that combine a polymeric phase with a filler, typically wood powder or fiber. This common practice significantly enhances certain mechanical properties of WPCs, such as tensile, compressive, and flexural strength, especially when coupling agents are added. Polyethylene terephthalate (PET) is a thermoplastic commonly used due to its high stiffness, mechanical strength, and chemical resistance. However, the increasing demand for PET has led to a rise in plastic waste accumulation, posing an environmental challenge. Therefore, recycling and promoting a circular economy are considered key strategies to reduce environmental impact and achieve sustainable development. The main challenge in WPC production lies in its formulation—specifically, determining the appropriate proportion of thermoplastic polymer, wood filler, and coupling agent. To optimize the mechanical properties of WPCs, it is necessary to vary these component proportions and understand how these changes affect the composite properties. This article describes a statistical approach for optimizing the mechanical properties of a WPC with PET as the polymer matrix. It is assumed that the mechanical properties of the WPC are a function of the proportions of the components that make up the mixture, so the optimization consists of determining these proportions in a way that maximizes the mechanical properties. With the experimental design, three models with inverse terms were fitted, which modeled the relationship between the component proportions and the flexural, compression, and tensile strength. The optimal formulation for maximizing flexural strength was found to be 58% PET, 39% wood, and 3% E‐GMA. The optimal formulation for maximizing compressive strength was found to be 58% PET, 40% wood, and 2% E‐GMA. The optimal formulation for maximizing tensile strength was found to be 86% PET, 11% wood, and 3% E‐GMA. The results are validated through analysis of variance of the mixture experimental design for mixtures. Finally, three response surface plots are presented for each mechanical property, which graphically describe the relationship between the different proportions of the mixture components and the mechanical properties.