hassan masoomi

This research aimed to predict the bearing capacity of hammer piles using genetic and Lorenberg algorithms and Machine Learning (ML) methods. The studied samples as input parameters in this research include the parameters of soil internal friction angle, soil elastic modulus, pile diameter (D), and pile length (L) as input to the considered models, and the target in this research is the bearing capacity of the pile. 15% of the input data were considered training data, 15% validation data, and neural network training was done. At first, using the trial and error method, the number of hidden layers was determined as 6, and the target network was trained using the genetic algorithm. The results of training the target network using the genetic algorithm showed that the regression coefficient obtained from the model prediction for the learning and validation data was 99. 0 has been obtained. The results of neural network training using Lorenberg's algorithm showed that the correlation coefficient between training and validation data is 0.96548 and 0.993889, respectively. By comparing the results of the neural network with the laboratory data, it has been observed that the genetic algorithm can make the desired prediction better.

One of the ways to convert mechanical energy into electricity is the use of triboelectric generators. In this paper, we have tried to discuss the principles of these generators and improve their performance, as well as present new structures for their use. The most important research on improving performance, including improving materials, improving surface geometry, improving structures, and more. A solution is proposed to improve the surface geometry, which involves changing the angle of the double-corrected surface by sandpaper with different grit sizes. The output voltage was investigated for different angles of adjustment of the two modified tribo surface relative to each other, including a PVC surface and another surface of aluminum. It was found that the produced voltage for the two-page placement ratio with non-zero polishing angle in different grit sizes of sandpaper was significantly improved in comparison with zero-degree mentioning in previous studies. Next studies will follow applications of this technology.

Routinely, behavior of floor diaphragms is assumed completely rigid in their plane, which leads to erroneous results in analysis and design of some particular buildings. In this study, 4-story RC buildings, with end shear walls and plan aspect ratio of 3, are considered in order to investigate the influence of diaphragm openings on their seismic response. It is concluded that although in-plane floor flexibility has enormous effects on pre-yielding part of pushover curve, it has no influence on post-yielding part of that. Furthermore, the opening beside shear walls has crucial impact on response of building. Hence, it would be better off avoiding opening near the shear walls; if not, the in-plane flexibility of diaphragm has not to be overlooked even if the plan aspect ratio of building is 3.