Search

Rolling bearing fault diagnosis is conventionally performed by vibration-based diagnosis (VBD). However, VBD is restrained in some cases because vibration measurement usually requires the contact with the machine. Acoustical-based fault diagnosis (ABD) has the advantage of non-contact measurement over VBD. However, ABD has received little attention and rarely applied in bearing fault diagnosis. In this paper, a new non-contact ABD method for rolling bearings using acoustic imaging and convolutional neural networks (CNN) is proposed. Firstly, a microphone array is used to acquire the acoustic field radiated by rolling bearings. Then, acoustic imaging is performed with the wave superposition method (WSM). The reconstructed acoustic images can depict the spatial distribution of the acoustic field, which add a new spatial dimension in the acoustic data representation for fault diagnosis and makes it possible to localize the sound sources. Finally, CNN is applied to accomplish bearing fault diagnosis, which can overcome the problems of handcrafted feature extraction in traditional ABD methods. Experimental results verify the effectiveness of the proposed ABD method. Comparisons with peer state-of-the-art ABD methods further validate that the proposed method can mitigate the drawbacks of the existing ABD methods, and obtain more accurate and reliable diagnosis results.

In machinery fault diagnosis, a large amount of monitoring data is often unlabeled, while the number of labeled data is limited. Therefore, learning effective features from massive unlabeled data is a challenging issue for machinery fault diagnosis. In this paper, a simple unsupervised feature learning method, consistency inference-constrained sparse filtering (CICSF), is proposed to learn mechanical fault features with enhanced clustering performance for fault diagnosis. Firstly, inspired by the data augmentation strategy, consistency inference of latent representations for time series (CILRTS) is derived, which infers that training data instances segmented from the same time series should possess consistent latent feature representations. Then, CILRTS is integrated into sparse filtering (SF) as an additional constraint in the latent feature space. The developed CICSF method can optimize the inter-class sparsity and intra-class similarity of the feature distribution simultaneously. Thus, it can learn more effective features from massive unlabeled data. Finally, based on CICSF, a semi-supervised machinery fault diagnosis method is developed. After unsupervised feature learning by CICSF, a softmax regression classifier is trained with limited labeled data to realize machinery fault diagnosis. Experimental results on bearing and gearbox datasets verify the effectiveness of the proposed method. Moreover, comparisons with standard SF and several auto-encoder (AE) variants validate its superiority in unsupervised feature learning and fault diagnosis using limited labeled data.