In this paper, a novel similarity classifier which synthesizes the adaptive resonance theory (ART) and the similarity classifier based on the Yu’s norm is proposed. The proposed ART-similarity classifier can not only carry out training without forgetting previously trained patterns but also be adaptive to changes in the environment. In order to test the proposed classifier, it is applied to the fault diagnosis of rolling element bearings. Before application to the fault diagnosis of bearings, considering computation burden principal component analysis (PCA) is proposed to reduce the number of features. The PCs are input the proposed classifier to diagnose the faulty bearings. The experiment results testify that the proposed classifier can identify the faults accurately. Furthermore, in order to validate the effectiveness of the proposed classifier further, it compares with other neural networks, such as the fuzzy ART, self-organising feature maps (SOFMs) and radial basis function (RBF) neural network through diagnosing the bearings under the same conditions. The comparison results confirm the superiority of the proposed method.
In the fault diagnosis of a machine, frequencies of its vibration are important indicators to show conditions of the machine. There are two main categories of methods to estimate frequency. One is based on the fast Fourier transform, and the other is on the signal subspace decomposition. Using FFT directly to estimate frequency may introduce larger estimation error, several approaches are proposed to correct or decrease the error, which comprise phase difference, energy centrobaric, interpolation and search method. The signal subspace decomposition method (SSDM) consists of Pisarenko harmonic decomposition, multiple signal classification. In order to assess the performance of these methods, the Cramer-Rao bound is used to compare with the error variance of difference frequency estimation methods, and simulations are based on Monte Carlo experiments for various record sizes and signal-to-noise ratios (SNR’s). The results show that there is a turning point about 25 dB for FFT based methods, above which FFT based methods are less sensitive to the noise, and SSDM achieves higher precision estimation at higher SNR and for the short time series, but produces poor accuracy at lower SNR’s.
In this paper, the acoustic Helmholtz boundary integral equation is solved using Coiflet scaling functions with interpolation approximation property. The scaling functions are utilized as base and test functions in Galerkin method and the expanded coefficients are the values of the function in sampling points, so the number of numerical integral is reduced. Two numerical examples are given and the calculation results agree well with the theoretical results, which show the high accuracy of the estimation and demonstrate validity and applicability of the method.
There are lots of practical problems which are related to the solution of Fredholm integral equations of the second kind. The present work proposes intervallic Coiflets for solving the equations. Illustrative problem involving dynamic stress and electric fields of a cracked piezoelectric excited by anti-plane shear wave is addressed. Permeable boundary condition has been used to obtain a pair of dual integral equations of the symmetric and antisymmetric parts which can be reduced to the solutions of two Fredholm integral equations of the second kind. The dynamic stress intensity factor is expressed in terms of the right-end values of two unknown functions in Fredholm integral equations. The two unknown functions are solved by intervallic Coiflets which have less the endpoints error. And intervallic Coiflets have low calculation cost and high accuracy due to the wavelet expansion coefficients are exactly obtained without calculating the wavelet integrations. The calculation results agree well with the existing method, which show the high accuracy of the estimation and demonstrate validity and applicability of the method.
During machining some ultra-intense and special-shaped parts, unstability and surface ablation often turn up. Some large and heavy parts are often machined with heavy duty NC machine tool. For avoiding the processing defects of the above parts, an online monitoring, diagnosis and control system is designed for heavy duty NC machine tool. The system can online monitor the operation condition of heavy duty NC machine tool and real-time control the processing. Some methods of signal analysis and processing are adopted such as spectrum analysis, wavelet analysis, Wigner-Ville distribution and Artificial Neural Network etc. The system is developed with C language and Qt based on Linux operation system. Optical fiber communication is adopted between industrial computer and NC system. Experiment platform of the system is machining an aircraft landing gear with five-axis NC machine tool. The scheme is verified feasible after preliminary test.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.