Rolling bearing fault diagnosis based on feature fusion with parallel convolutional neural network

  • PDF / 1,059,579 Bytes
  • 13 Pages / 595.276 x 790.866 pts Page_size
  • 44 Downloads / 233 Views

DOWNLOAD

REPORT


ORIGINAL ARTICLE

Rolling bearing fault diagnosis based on feature fusion with parallel convolutional neural network Mingxuan Liang 1 & Pei Cao 2 & J. Tang 2 Received: 12 September 2020 / Accepted: 18 November 2020 # Springer-Verlag London Ltd., part of Springer Nature 2020

Abstract Deep learning has seen increased application in the data-driven fault diagnosis of manufacturing system components such as rolling bearing. However, deep learning methods often require a large amount of training data. This is a major barrier in particular for bearing datasets whose sizes are generally limited due to the high costs of data acquisition especially for fault scenarios. When small datasets are employed, over-fitting may occur for a deep learning network with many parameters. To tackle this challenge, in this research, we propose a new methodology of parallel convolutional neural network (P-CNN) for bearing fault identification that is capable of feature fusion. Raw vibration signals in the time domain are divided into non-overlapping training data slices, and two different convolutional neural network (CNN) branches are built in parallel to extract features in the time domain and in the time-frequency domain, respectively. Subsequently, in the merged layer, the time-frequency features extracted by continuous wavelet transform (CWT) are fused together with the time-domain features as inputs to the final classifier, thereby enriching feature information and improving network performance. By incorporating empirical feature extraction such as CWT, this proposed method can effectively enable deep learning even with dataset size limitation in practical bearing diagnosis. The algorithm is validated through case studies on publicly accessible experimental rolling bearing datasets. A wide range of dataset sizes is tested with cross-validation, and influencing factors on network performance are discussed. Compared with existing methods, the proposed approach not only possesses higher accuracy but also exhibits better stability and robustness as training dataset sizes and load conditions vary. The concept of feature fusion through P-CNN can be extended to other fault diagnosis applications in manufacturing systems. Keywords Fault identification . Parallel convolutional network . Wavelet . Reduced dataset . Rolling bearing

1 Introduction Intelligent fault diagnosis of rotating machinery plays an important role in smart manufacturing, and rolling bearings are one type of key components where a small defect may cause catastrophic consequences. The timely and accurate classification of fault conditions of rolling bearings has attracted a lot of research interests in manufacturing community [1–3]. Vibration signals measured by off-the-shelf sensors are commonly used in condition monitoring. However, the anomalies

* J. Tang [email protected] 1

College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou 310018, China

2

Department of Mechanical Engineering, University of Connecticut, Storrs, CT 06269, USA

in