Artificial neural network modeling to predict optimum power consumption in wood machining

This paper investigates and models the effects of wood species, feed rate, number of cutters and cutting depth on power consumption during the wood planing process. For this purpose, the samples were planed at a feed rate of 7 and 14 m/min, a cutting depth of 0.5, 1.5, 2.5 and 3.5 mm, and using 1, 2 and 4 cutters, with measurements taken during this process. According to the results, power consumption increased with increasing feed rate, cutting depth and number of cutters. In artificial neural network model, the mean absolute percentage error values between the actual and predicted values were 0.32% for the training data set and 1.15% for the testing data set. In addition, the values of R2 were found to be 0.99 and 0.97 in the training and testing data sets, respectively. It is evident from the results that the designed model may be used to optimize the effects of process parameters on power consumption during the planing process of different wood species. Thus, the findings of the current study can be effectively applied in the wood machining industry in order to reduce the time for further experimental investigations, to lower energy consumption and avoid high machining costs.

---

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę.