A new fault diagnosis method using deep belief network and compressive sensing

Abstract

Compressive sensing provides a new idea for machinery monitoring, which greatly reduces the burden on data transmission. After that, the compressed signal will be used for fault diagnosis by feature extraction and fault classification. However, traditional fault diagnosis heavily depends on the prior knowledge and requires a signal reconstruction which will cost great time consumption. For this problem, a deep belief network (DBN) is used here for fault detection directly on compressed signal. This is the first time DBN is combined with the compressive sensing. The PCA analysis shows that DBN has successfully separated different features. The DBN method which is tested on compressed gearbox signal, achieves 92.5 % accuracy for 25 % compressed signal. We compare the DBN on both compressed and reconstructed signal, and find that the DBN using compressed signal not only achieves better accuracies, but also costs less time when compression ratio is less than 0.35. Moreover, the results have been compared with other classification methods.

Adaptive High-Resolution Imaging Method Based on Compressive Sensing

“…where ε is the maximum noise energy limit during reconstruction. The single-pixel camera is an optical computer that sequentially measures the inner products y[m] = x, φ m between an N-pixel sampled version x of the incident light-field from the scene under view and a set of two-dimensional (2-D) test functions {φ m } [9]. The structure of the single-pixel CS camera is shown in Figure 2.…”

“…CS theory transfers the burden of sampling to data processing, it shifts the focus of the imaging system from the traditional design of expensive receiver hardware to the novel design of signal recovery algorithms [5,7]. At present, CS technology has been widely used in three areas-wireless communication, array signal processing, and imaging systems-and plays a major role in fault diagnosis and signal recognition [8,9]. A single-pixel camera is an important application of compressed sensing theory.…”

Using Envelope Analysis and Compressive Sensing Method for Intelligent Fault Diagnosis of Ball Bearing

“…In order to overcome the limitation of the sampling rate and processing of big data acquisition, compressive sensing method has been developed to resample the signal below the Nyquist sampling rate and express reliable sparse signal. The original signal, x(t) is reconstructed and multiplied by a sensing matrix to perform the compressed data, which denoted by y, as [6,[8][9][10][11][12]:…”

“…CS is widely used in various applications such as medical imaging, seismic imaging, communications and networks [9][10][11]. It can reduce the big data by a down-sample strategy with preserving reliable extraction of fault features [12]. The compression approaches can help the measuring of wireless transmission data by reducing its volume, hence significant reduction in energy consumption of wireless communication can be achieved [13][14].…”