Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Computer Assisted Methods in Engineering and Science

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Structural design optimization of steel beamsand frames with web-tapered members usingthe PSO-FEM algorithm

Sych Piotr, Słoński Marek

Computer Assisted Methods in Engineering and Science

2021

Vol. 28, no. 1

39--55

This paper presents an algorithm for structural design optimization of steel beams andframes with web-tapered members using the particle swarm optimization (PSO) algorithmand the finite element method (FEM). The design optimization is done in accordancewith Eurocode 3 (EC 3) for the minimum mass. The proposed algorithm is more flexibleand efficient than traditional design methods based on a trial and error approach. Theeffectiveness of the presented PSO-FEM algorithm is evaluated on examples of the sizeoptimization of web-tapered members cross-section. The results show that the PSO-FEM algorithm is feasible and effective for finding useful designs.

A comparison of deep convolutional neural networksfor image-based detection of concrete surface cracks

Słoński Marek

Computer Assisted Methods in Engineering and Science

2019

Vol. 26, no. 2

105--112

The aim of this paper is to compare the performance of four deep convolutional neural networks in theproblem of image-based automated detection of concrete surface cracks in the case of a small dataset. Thiscrack detection problem is treated as a binary classification problem, and it is solved by training a deepconvolutional neural network on the small dataset. In this context, overfitting during training was the mainissue to cope with and various techniques were applied to overcome this issue. The results of the experi-ments suggest that the best approach for this problem is to use the pretrained convolutional base of a largepretrained convolutional neural network as an automatic feature extraction method and adding a new bi-nary classifier on top of the convolutional base. Then, at the training the new classifier and fine-tuningthe last few layers of the pretrained network take place at the same time. The classification accuracy of thebest deep convolutional neural network on the testing set is about 94%.