Francisco García Fernández*
Department of Systems and Natural Resources, Polytechnic University of Madrid, Spain
Received: January 07, 2016 Accepted: January 09, 2016 Published: January 10, 2016
Citation: Fernández FG (2016) The Use of Artificial Intelligence in Forest Product Manufacturing: A Low-cost Improvement in Competitiveness. Ind Eng Manage 5:e132. doi:10.4172/2169-0316.1000e132
Copyright: © 2016 Fernández FG. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Visit for more related articles at Industrial Engineering & Management
Quality control of wood-based products before they are placed in the market, require a series of costly tests which often include long ageing periods. This often forces manufacturers to maintain a stock of product immobilized for long periods, which in the case of structural wood-based panels can exceed a month (Figures 1 and 2) .
On the other hand, the wood product manufacturing industry is characterized by significant competition, high variability in customer's requirements, and the need to develop more and more price competitive products. These interrelated factors force manufacturers to continuously adjust, control and optimize their manufacturing parameters in order to develop products of higher quality that better fit the customer needs at a lower cost.
These characteristics of the industry make it very desirable to develop a high accuracy and reliable tool to obtain the final characteristics of a product by means of its manufacturing parameters, rather than testing after several weeks of manufacturing .
In this respect, artificial neural networks and fuzzy logic are a two promising tools based on artificial intelligence to improve the competiveness of forest product manufacturing companies. These new modeling and manufacturing control techniques allow companies to significantly increase their competitiveness by reducing manufacturing and testing times and costs without decreasing the reliability of the results.
These techniques can act as a realistic simulator of the production line itself, allowing adjusting manufacturing parameters to obtain a better product with lower costs.
Two of the main challenges of these techniques, and which for years prevented their industrial applications, have recently been solved (Figure 3). The first one was that these techniques act as a black box where it is impossible to know how variables relate to each other . The second one is that neither technique provides the uncertainty or reliability of its results . These two challenges can now be solved through Monte Carlo and Bootstrap simulation methods to provide manufacturers with a reliable optimization tool [5-8].
These new tools will allow modern forest companies to adapt in very a flexible and cost-effective way to their market requirements.
Make the best use of Scientific Research and information from our 700 + peer reviewed, Open Access Journals