For access to this article, please select a purchase option:
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Your recommendation has been sent to your librarian.
In gear fault diagnosis, the signal collected by the sensor is mixed with the vibration signal and a lot of noise of various parts in the gearbox. Independent component analysis is an important method of blind source separation, by which the independent vibration source signals can be separated from mixed signals and the fault characteristics can be extracted effectively. This paper proposes a gear fault extraction method based on improved independent component analysis, replacing Newton iterative method with improved particle swarm optimization, so that it has better adaptability and global search ability. Finally, the analysis results of simulation signals show the effectiveness of the proposed method.
Inspec keywords: blind source separation; condition monitoring; feature extraction; sensors; fault diagnosis; independent component analysis; particle swarm optimisation; vibrational signal processing; search problems; gears
Subjects: Civil and mechanical engineering computing; Mechanical components; Vibrations and shock waves (mechanical engineering); Statistics; Optimisation techniques; Other topics in statistics; Digital signal processing; Optimisation techniques; Other topics in statistics; Signal processing and detection; Optimisation; Mechanical engineering applications of IT; Maintenance and reliability; Inspection and quality control; Mechanical drives and transmissions