Search

Digital Image Correlation (DIC) experimental method is receiving a significant attention recently both in research and industry since it enables full-field, non-contact optical measurements of deformations and strains on almost any material and any geometry [1, 2]. In this study, DIC measurement system was used for determination and analysis of the values of strains and stresses in plate specimens with central hole loaded elastically in tension using a tensile testing machine. In order to determine the applicability of the method and the sizes of geometrical discontinuities i.e., stress concentrators that can be successfully characterized with available equipment, plate specimens made of various materials and with central holes of different sizes were studied. An important step in preparation of the specimens, which can have significant influence on results, is creation of the appropriate random speckle pattern on the specimen’s surface which is usually done by spraying paint [3]. In this work, speckle pattern was applied using airbrush system and influence of speckle pattern on measurement results was considered. Values of strains and stresses on individual specimens were determined using basic empirical equations, numerically with the FEA software and compared with those determined experimentally using the DIC system. Results of the study are reported.

To adequately design a structure or a part, the behavior of a material, more precisely, relation between its stresses and strains, must be known. Considering that the experimental determination of fatigue and cyclic material parameters is costly and long-lasting, as opposed to monotonic tensile tests, it is of great interest to use more easily obtainable monotonic properties to estimate cyclic and fatigue material behavior [1]. Building a predictive model from acquired data can be done using classical approaches, such as regression, or more recently, various available machine learning methods. The dataset which is used as an input for such models needs to be of appropriate size and have an adequate number of input variables, also called predictors, to avoid underfitting or overfitting a model. Higher ratio of number of samples to number of predictors makes the model less likely to be affected by possible errors in data and to generalize new cases well [2]. To increase the data volume, additional datasets can be acquired by performing experiments which take a great amount of time. Therefore, it is more economical to implement a feature selection (i.e. feature engineering) techniques instead, which enable the detection of redundant input variables followed by their removal which then consequently reduces model complexity [2]. In this study, using several chosen feature selection techniques, importance of each predictor in relation with the response is determined and a subset of the most relevant variables for predicting the cyclic and fatigue parameters is selected. Building models with newly acquired subset should reduce overfitting, improve interpretability and decrease the complexity of the model.

Rad ne sadrži sažetak.