A method for detection and characterisation of structural non-linearities using the Hilbert transform and neural networks. (15th January 2017)

• Record Type: Journal Article
• Authors: Ondra, V.; Sever, I.A.; Schwingshackl, C.W.
• Is Part Of: Mechanical systems and signal processing. Volume 83(2017)
• Page Start: 210
• Page End: 227
• Publication Date: 2017-01-15
• Subjects: Non-linear system characterisation -- Hilbert transform -- Neural network classification -- Nonlinearity indexes; Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2016.06.008
• Languages: English
• ISSNs: 0888-3270

Abstract

Abstract: This paper presents a method for detection and characterisation of structural non-linearities from a single frequency response function using the Hilbert transform in the frequency domain and artificial neural networks. A frequency response function is described based on its Hilbert transform using several common and newly introduced scalar parameters, termed non-linearity indexes, to create training data of the artificial neural network. This network is subsequently used to detect the existence of non-linearity and classify its type. The theoretical background of the method is given and its usage is demonstrated on different numerical test cases created by single degree of freedom non-linear systems and a lumped parameter multi degree of freedom system with a geometric non-linearity. The method is also applied to several experimentally measured frequency response functions obtained from a cantilever beam with a clearance non-linearity and an under-platform damper experimental rig with a complex friction contact interface. It is shown that the method is a fast and noise-robust means of detecting and characterising non-linear behaviour from a single frequency response function. Abstract : Highlights: A tool for detection and characterisation of structural non-linearities. Proposed non-linearity indexes describe FRFs based on the Hilbert transform. The neural network is used to classify non-linear behaviour based on the non-linearity indexes. Successful characterisation of several numerical and two experimental test cases is shown.