Control of system parameters by estimating screw withdrawal strength values of particleboards using artificial neural network-based statistical control charts

Abstract

In this study, with data obtained from a particleboard factory, screw withdrawal strength (SWS) values of particleboards were estimated using artificial neural networks (ANNs). Predictive control charts were also created. A total of seven independent variables were used for the ANN model: modulus of elasticity (MoE), surface soundness (SS), internal bond strength (IBS), density, press time, press temperature, and press pressure. The results showed that the ANN-based individual moving range (I-MR) and cumulative sum (CUSUM) control charts created for SWS values detected out-of-control signal points close to those of the real-time control charts. Among the selected independent variables, IBS was the most important parameter affecting SWS. The most suitable press temperatures and times for high SWS values were determined as 198–201 °C and 165–175 s, respectively. Moreover, the boards with 2500–2800 N/mm2 MoE and 0.55 N/mm2 IBS values exhibited the best SWS.

Modeling Xanthan Gum Foam’s Material Properties Using Machine Learning Methods

“…Analyzing materials and composites uses various methods such as multiple linear regression, support vector machines, artificial neural networks, and least squares methods for different purposes. These techniques have been utilized to predict screw pull-out strengths and flexural modulus values of particleboards [ 17 , 18 ], to classify alloys based on their shapes [ 19 ], to predict sound absorption coefficients of sandwich-structured materials [ 20 ], to detect protozoa in wastewater [ 21 ], to model the strength of lightweight foam concrete [ 22 ], and to determine the processing parameters for drilling glass-laminated aluminum-reinforced epoxy composites [ 23 ]. However, no studies on machine learning related to xanthan-gum-based foam materials exist.…”

“…Within the materials and composites domain, diverse methodologies, including multiple linear regression, support vector machines, artificial neural networks, and least squares methods, have been carried out for various purposes. These techniques have provided successful outcomes in predicting screw pull-out strengths and flexural modulus values of particleboards [ 17 , 18 ], classifying alloys based on their shapes [ 19 ], forecasting sound absorption coefficients of sandwich-structured materials [ 20 ], detecting protozoa in wastewater [ 21 ], modeling the strength of lightweight foam concrete [ 22 ], determining processing parameters for drilling glass-laminated aluminum-reinforced epoxy composites [ 23 ], estimating performance in different applications [ 24 ] and organic photovoltaic design [ 25 ]. Additionally, in the context of predicting material properties and minimizing both material waste and cost losses, machine learning methods provide considerable advantages.…”

Investigation of the usability of activated carbon as a filling material in nitrile butadiene rubber/natural rubber components and modeling by regression analysis

“…Therefore, it is important to use a sufficient number of experimental results to be able to estimate output values based on different levels of variables. 27 Finding the ideal circumstances without losing products or raw materials is beneficial from an industrial perspective. For this purpose, many mixed recipes, which result in high costs, may need to be tested.…”

Analysis and Impact of Activated Carbon Incorporation into Urea-Formaldehyde Adhesive on the Properties of Particleboard

“…Particleboard, born out of the need to utilize large quantities of wood waste, such as sawdust, planer shavings, and, to a lesser extent, mill residues generated by other wood industries, has become increasingly popular. It is widely used in manufacturing furniture, cabinets, and various structural products [3]. In 2021, 4,075,000 m 3 and 103,955,051 m 3 of particleboard were produced in Turkey and the world, respectively [4].…”