Abstract
The gear fault signal under different working conditions is non-linear and non-stationary, which makes it difficult to distinguish faulty signals from normal signals. Currently, gear fault diagnosis under different working conditions is mainly based on vibration signals. However, vibration signal acquisition is limited by its requirement for contact measurement, while vibration signal analysis methods relies heavily on diagnostic expertise and prior knowledge of signal processing technology. To solve this problem, a novel acoustic-based diagnosis (ABD) method for gear fault diagnosis under different working conditions based on a multi-scale convolutional learning structure and attention mechanism is proposed in this paper. The multi-scale convolutional learning structure was designed to automatically mine multiple scale features using different filter banks from raw acoustic signals. Subsequently, the novel attention mechanism, which was based on a multi-scale convolutional learning structure, was established to adaptively allow the multi-scale network to focus on relevant fault pattern information under different working conditions. Finally, a stacked convolutional neural network (CNN) model was proposed to detect the fault mode of gears. The experimental results show that our method achieved much better performance in acoustic based gear fault diagnosis under different working conditions compared with a standard CNN model (without an attention mechanism), an end-to-end CNN model based on time and frequency domain signals, and other traditional fault diagnosis methods involving feature engineering.
Highlights
As a one of the most important components in transmission systems, gears are widely used in many types of machinery, such as wind turbines, construction machinery, automobiles, and other fields [1], thanks to their unique merits, such as large transmission ratio, high efficiency, and heavy load capacity [2,3]
The experimental results show that our method achieved much better performance in acoustic based gear fault diagnosis under different working conditions compared with a standard convolutional neural network (CNN) model, an end-to-end CNN model based on time and frequency domain signals, and other traditional fault diagnosis methods involving feature engineering
In order to verify the hypothesis that the multi-scale convolutional learning structure is superior to the single-scale convolutional structure in for gear fault diagnosis tasks, we first compared the performance of our multi-scale convolutional neural network with that of a low-scale convolutional neural network, mid-scale convolutional neural network, and high-scale convolutional neural network with no attention mechanism
Summary
As a one of the most important components in transmission systems, gears are widely used in many types of machinery, such as wind turbines, construction machinery, automobiles, and other fields [1], thanks to their unique merits, such as large transmission ratio, high efficiency, and heavy load capacity [2,3]. Vibration signals are masked in some special environments, such as high humidity, high temperature, and high corrosion; the application of vibration signal analysis methods for gear fault diagnosis under variable conditions is limited due to the requirement of contacted measuring Those studies that adopt vibration analysis methods, usually rely on signal processing technology to decompose raw vibration signals into several proper signal components to extract valuable features for distinguishing gear fault patterns under different working conditions. In this paper, we propose a novel ABD method for gear fault diagnosis under different working conditions based on a multi-scale convolutional learning structure and attention mechanism. It outperformed a single-scale network and multi-scale network without attention mechanism, and achieved favorable results relative to other methods using manual feature engineering based on the function of multi-scale structure and an attention mechanism
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
