Determining the Natural Frequency of Cantilever Beams Using ANN and Heuristic Search. Issue 3 (16th March 2018)

• Record Type: Journal Article
• Authors: Nikoo, Mehdi; Hadzima-Nyarko, Marijana; Karlo Nyarko, Emmanuel; Nikoo, Mohammad
• Is Part Of: Applied artificial intelligence. Volume 32:Issue 3(2018)
• Page Start: 309
• Page End: 334
• Publication Date: 2018-03-16
• Subjects: Artificial intelligence -- Periodicals; 006.3
• DOI: 10.1080/08839514.2018.1448003
• Languages: English
• ISSNs: 0883-9514

Abstract

ABSTRACT: An artificial neural network (ANN) is used to model the frequency of the first mode, using the beam length, the moment of inertia, and the load applied on the beam as input parameters on a database of 100 samples. Three different heuristic optimization methods are used to train the ANN: genetic algorithm (GA), particle swarm optimization algorithm and imperialist competitive algorithm. The suitability of these algorithms in training ANN is determined based on accuracy and runtime performance. Results show that, in determining the natural frequency of cantilever beams, the ANN model trained using GA outperforms the other models in terms of accuracy.