Search

Because of the impact on productivity and cost reduction, decision making in industrial processes is one of the most required aspects in the industry. Specifically in the panel industries, product quality depends on multiple variables, especially wood variability. Among other factors, quality depends on the adhesion of veneers or perpendicular tensile strength. The main objective of this study was to evaluate a Machine Learning approach to predict the adhesion under industrial conditions in the gluing and pre-pressing stage. The control variables that determine this adhesion are mainly: operational times, amount of adhesive, environmental conditions, and veneer temperature. Using Knowledge Discovery in Databases data analytics methodology, Artificial Neural Networks and Support Vector Machine were evaluated. Sigmoid activation function was used with 3 hidden layers and 245 neurons. In addition to the Adam optimizer, Multi-Layer Perceptron, Artificial Neural Networks delivered the best accuracy levels of over 66 %. Best result with Relu and Sigmoid functions were obtained. Sigmoid showed accuracy over 66 %, precision fit good to find positive results (70 %). Relu function obtained the best recall (over 74 %) showing a good capacity to identify reality. Results show that it is not sufficient to generate a data set using the averages of each process variable, since it is difficult to obtain better results with the algorithms evaluated. This work contributes to defining a methodology to be used in plywood plants using industrial data to train and validate Machine Learning models. [ABSTRACT FROM AUTHOR]

Species identification from timber helps combat ilegal wood trafficking. In the present work, it is shown a method that aims to detect wood species from previously cut and stored pieces through the interaction of the volatile compounds that they emanate with an array of chemical sensors (electronic nose). The device processes the response of the chemical sensor array using linear regularization and probabilistic machine learning methods trying to resemble current biometric systems. In particular, this method includes a heuristic parameter estimation stage on the signals provided by the sensor array, followed by a variable selection stage through L¹ regularization, to finally use Gaussian mixture models [GMMs] for the process of probabilistic modeling. As a result, a performance (measured by EER) of 17.5 % is obtained for the detection of four wood species; and, for the particular case of Sapán, an EER of 12 % is achieved. In conclusion, this biometric approach gives good results compared to previous works, taking into account that in the present work, the experiments are carried out in conditions that are closer to reality. [ABSTRACT FROM AUTHOR]

Contextualization: The noise exposure assessment is an essential component of hearing loss prevention programs to recognize vulnerable workers, to propose control measures and / or to evaluate the measures implemented. Knowlegdge gap: In Colombia, there is a limited number of works that address noise exposure and its assessment. Purpose: Occupational noise exposure in the operating area of two microenterprises in the city of Neiva was evaluated by dosimetry and sonometry. These companies are dedicated to the commercialization of chipboard using specialized machines such as vertical saws and veneers. Methodology: Initially, a diagnosis of working conditions was made; later, noise measurements were carried out following the workbased strategy pursuant ISO 9612-2010. Results and conclusions: The equivalent sound pressure levels (73,0 and 82,4 dB (A)) registered by the sonometry system are similar to those reported in carpentry workshops and furniture factories. The dosimetry results reveal that the vertical saw and the veneer machine operators are exposed 8 hours daily to noise levels between 88,50 and 89,9 dB (A), which exceed the permissible limit value (85 dB), as stipulated by resolution 1792 of 1990. However, the chipboard microenterprise operators evaluated were not overexposed to noise thanks to the attenuation brought by the hearing protectors used. [ABSTRACT FROM AUTHOR]

Copyright of Ingeniería Solidaria is the property of Universidad Cooperativa de Colombia and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the simulation and optimization of a manufacturing system, the input parameters are sought to obtain the best performance of the system, considering in many cases a single objective or measure of performance. However, many decisions involve multiple criteria, usually in conflict. Currently, companies are required to improve their profitability as well as to reduce their impact on the environment and use energy rationally. In this paper, the wood products manufacturing process of a small company was studied to determine redesign alternatives, with simultaneous economic and environmental criteria. A simulation model of the system was built, which was validated and verified, and an optimization model for it in which two objectives were combined in a single function, incorporating in it the preferences of the decision makers with respect to each criterion. Results expose that combining both criteria it is possible to achieve substantial improvements in the benefit, at the same time that generating less emissions than if only the economic objective were pursued. It is concluded that simulation and optimization combining both criteria can improve economic-environmental performance in wood manufacturing systems, even in small companies. [ABSTRACT FROM AUTHOR]

In commodity export-based economies the development of innovation capacities is a recent phenomenon that is pushing companies to make changes in their industrial processes. In order to describe the particular dynamics in primary wood industry, an innovation survey was conducted among 30 companies. The study results revealed that innovation efforts are individual and non-associative, based on acquisition and not on research and development of technological solutions, and there is a lack of a knowledge infrastructure that supports innovation activities. As outcomes of innovation efforts, companies achieve process optimization, quality improvements, organizational learning and market share growth. [ABSTRACT FROM AUTHOR]

This article results from a research on "Design of a Model for Wood and Furniture Supply in the Caribbean Region of Colombia", limiting its scope to Cartagena, Barranquilla and Santa Marta cities. This project was supported by "Colciencia's Young Researcher" Fellowship, 2011, and its main purpose was analyzing the structure of companies in the Wood and Furniture Business, and therefore, get a better sense of this sector's current state in order to identify opportunities to improve at a structural, productive and organizational level. This will grant a rise, not only of national competitivity, but also of the need that emerging markets will have when facing what Exportation offers them, and it will generate more scenarios for economic development. To summarize, the objective is to outline Wood and Furniture Sector's reality in the Caribbean Region of Colombia, in terms of its capacity, its potential, weaknesses and relevant features. [ABSTRACT FROM AUTHOR]