As field data collection is a very time-consuming and costly task, the aim of the thesis was to determine how accurately parts of the working time and working operations of chainsaw felling can be determined using noise data and machine learning. In addition to the three machine learning methods (Random Forest, Neural Network, Decision Tree), we also performed the determination using conditional statements in MS Excel. The data on the composition of the working time and noise exposure were split into a training set (27 trees) and a test set (26 trees). Random Forest has proven to be the most successful method. The effective and operating time of the chainsaw was determined with 96.0% and 99.4% accuracy, the main and auxiliary productive time with 92.0% and 65.7% accuracy and the sub-phases of felling and timber production with 84.1% and 94.9% accuracy. The highest accuracy in determining work operations was observed in the case of notch-cutting and delimbing (80.3% and 89.5%, respectively), while the lowest accuracy was observed in the case of stump debarking, butt trimming and cross-cutting (7.6% to 14.0%). The results show great potential for collecting time study data through machine learning.
|
