A Reliable Fault Diagnosis Method for a Gearbox System with Varying Rotational Speeds

Abstract

The vibration signals of gearbox gear fault signatures are informative components that can be used for gearbox fault diagnosis and early fault detection. However, the vibration signals are normally non-linear and non-stationary, and they contain background noise caused by data acquisition systems and the interference of other machine elements. Especially in conditions with varying rotational speeds, the informative components are blended with complex, unwanted components inside the vibration signal. Thus, to use the informative components from a vibration signal for gearbox fault diagnosis, the noise needs to be properly distilled from the informational signal as much as possible before analysis. This paper proposes a novel gearbox fault diagnosis method based on an adaptive noise reducer–based Gaussian reference signal (ANR-GRS) technique that can significantly reduce noise and improve classification from a one-against-one, multiclass support vector machine (OAOMCSVM) for the fault types of a gearbox. The ANR-GRS processes the shaft rotation speed to access and remove noise components in the narrowbands between two consecutive sideband frequencies along the frequency spectrum of a vibration signal, enabling the removal of enormous noise components with minimal distortion to the informative signal. The optimal output signal from the ANR-GRS is then extracted into many signal feature vectors to generate a qualified classification dataset. Finally, the OAOMCSVM classifies the health states of an experimental gearbox using the dataset of extracted features. The signal processing and classification paths are generated using the experimental testbed. The results indicate that the proposed method is reliable for fault diagnosis in a varying rotational speed gearbox system.

Frequency Spectra Analysis of Drawbar Pulls Generated by Special Driving Wheels Improving Tractive Performance

“…The support tube connects the blade wheel with the tractor driving wheel by means of three screws (6). Ten blades (4) are fulcrumed around the pivots (8), which are fastened to the support tube (1). A control disc (2) is also fulcrumed and secured from axial movement by means of two opposite stop bars (3).…”

“…Vibrations are a typical demonstration of functionality for many machines. The signal analysis of machine vibrations is often used for diagnostics of technical conditions of various machines or identification of their individual parts’ operation [ 1 ]. Fast Fourier transformation (FFT) is widely used for signal analysis for many applications in engineering, science, mathematics, etc.…”

“…The authors measured signals by an accelerometer, and motors using their original Hall effect encoders yes, the change retains the meaning or rotation speed sensor. In addition to the evaluation of the special driving wheels’ tractive properties, the operation of various driving wheel types was analyzed from the signals of drawbar pull using the fast Fourier transformation [ 1 , 21 , 22 , 23 ]. The signals were obtained from the load cell connected between the test and load tractor.…”

Construction of a Sensitive and Speed Invariant Gearbox Fault Diagnosis Model Using an Incorporated Utilizing Adaptive Noise Control and a Stacked Sparse Autoencoder-Based Deep Neural Network

“…The ANC module then processes the raw vibration signals. Firstly, it performs down-sampling three times along with filtering the signal with a low-pass filter to receive the vibration subbands within the frequency range from 0 to 10 kHz according to the real operating frequency range of the vibration sensor [18]. The expression of multilevel gear defect types on the vibration characteristic is signified by the magnitudes of the principal frequency tones, therefore the main function of the ANC is optimizing vibration subbands for removing the redundant components along with noise while preserving the original fault-related components.…”

Trends in Sensors Fault Diagnosis

“…Here, as in [ 8 ], the methods are applied in the frequency domain. The aforementioned SVM is also a part of the fault diagnosis method proposed in [ 10 ], where the one-against-one multiclass support vector machine is fed by a signal with noise reduced by using the adaptive noise filtering technique. The noise reduction method is based on the LMS filter with Gaussian reference noise generator.…”