Reza Mikaeil; Mostafa Piri; Sina Shaffiee Haghshenas; Nicola Careddu; Hamid Hashemolhosseini
Abstract
The noise of drilling in the dimension stone business is unbearable for both the workplace and the people who work there. In order to reduce the negative effects drilling has on the health of the environment, the drilling noise has to be measured, assessed, and controlled. The main purpose of this work ...
Read More
The noise of drilling in the dimension stone business is unbearable for both the workplace and the people who work there. In order to reduce the negative effects drilling has on the health of the environment, the drilling noise has to be measured, assessed, and controlled. The main purpose of this work is to investigate an experimental-intelligent method to predict the noise value of drilling in the dimension stone industry. For this purpose,135 laboratory tests are designed on five types of rocks (four types of hard rock and one type of soft rock), and their results are measured in the first step. In the second step, due to the unpredicted and uncertain issues in this case, artificial intelligence (AI) approaches are applied, and the modeling is conducted using three intelligent systems (IS), namely an adaptive neuro-fuzzy inference system-SCM (ANFIS-SCM), an adaptive neuro-fuzzy inference system-FCM (ANFIS-FCM), and the radial basis function network (RBF) neural network. 75% of the samples are considered for training, and the rest for testing. Several models are constructed, and the results indicate that although there is no significant difference between the models according to the performance indices, the proposed construction of ANFIS-SCM can be considered as an efficient tool in the evaluation of drilling noise. Finally, several scenarios are designed with different input modes, and the results obtained prove that the types of rock and the drill bits are more important than the operational characteristics of the machine.
Sh. Rezaei; A. Imam Ali Pour
Abstract
In the recent years, according to the difficulty of accurately measuring parameters and demarcation of earth sciences, attempts have been made to simplify the natural events for better investigation using geo-modelling. Modeling with intelligent methods is one of the new methods that has been considered ...
Read More
In the recent years, according to the difficulty of accurately measuring parameters and demarcation of earth sciences, attempts have been made to simplify the natural events for better investigation using geo-modelling. Modeling with intelligent methods is one of the new methods that has been considered in this field in the recent years. In this work, the intelligent method of adaptive neural-fuzzy inference system (ANFIS) is used to predict the elements of lead and zinc located in the Guard Kooh area, north of Yazd province in Iran. Descriptive statistics of data and correlation matrices of studied elements are obtained using the SPSS software. After the data is standardized, imported to the MATLAB software, and the lead and zinc elements are predicted using the ANFIS-SCM method. In this method, 70% of the data (175 samples) are set as the training data, and the rest (75 samples) are set as the test data, which are randomly selected. Using the obtained results, it is found that the grade of the estimated elements in the studied area has a good accuracy and a high correlation with the grade of the analyzed elements. As a result, the ANFIS-SCM intelligent method is a useful and accurate method for estimating the lead and zinc elements.