Bo Peng

The periodic impacts are regarded as the typical characteristics of local defect of wind turbine bearing. For this reason, it is significant to extract the periodic impacts from original measured vibration signal with background noise interferences during the defect identification process. For the purpose of effectively solving this issue, an innovative diagnostic frame based on Lkurtogram guided adaptive empirical wavelet transform (LGAEWT) and purified instantaneous energy operation (PIEO) is put forward. Within this diagnostic frame, the L-kurtosis indicator guided wavelet equivalent filter band mergence is carried out to confirm the optimal filter boundary, then the resonance frequency band containing rich characteristic information can be extracted and the characteristic sensitive component is able to be separated from original vibration signal. In additional, a novel signal processing strategy called purified instantaneous energy operation (PIEO) is presented to inhibit the background interferences and enhance the periodic impact signatures in the sensitive components, and the purified instantaneous energy spectrum is adopted to replace the traditional envelope spectrum for characteristic frequency spectral lines identification. The feasibility of proposed diagnostic frame has been demonstrated by the experimental signals and the actual engineering case, and the results manifest that it is suitable for bearing fault enhance detection under low signal-to-noise ratio (SNR) environment. Furthermore, the comparison results with the widely used Kurtogram, Autogram and DWT methods indicate this innovative diagnostic strategy has more prominent advantages on background interference suppression and weak characteristic intensification.

Feature extraction is an essential process in the intelligent fault diagnosis of rotating machinery. Although existing feature extraction methods can obtain representative features from the original signal, domain knowledge and expert experience are often required. In this article, a novel diagnosis approach based on evolutionary learning, namely, automatic feature extraction and construction using genetic programming (AFECGP), is proposed to automatically generate informative and discriminative features from original vibration signals for identifying different fault types of rotating machinery. To achieve this, a new program structure, a new function set, and a new terminal set are developed in AFECGP to allow it to detect important subband signals and extract and construct informative features, automatically and simultaneously. More important, AFECGP can produce a flexible number of features for classification. Having the generated features, k-Nearest Neighbors is employed to perform fault diagnosis. The performance of the AFECGP-based fault diagnosis approach is evaluated on four fault diagnosis datasets of varying difficulty and compared with 14 baseline methods. The results show that the proposed approach achieves better fault diagnosis accuracy on all the datasets than the competitive methods and can effectively identify different fault conditions of rolling bearing, gear, and rotor.

Aiming at the problem that the weak faults of rolling bearing are difficult to recognize accurately, an approach on the basis of swarm decomposition (SWD), morphology envelope dispersion entropy (MEDE), and random forest (RF) is proposed to realize effective detection and intelligent recognition of weak faults in rolling bearings. The proposed approach is based on the idea of signal denoising, feature extraction and pattern classification. Firstly, the raw signal is divided into a group of oscillatory components through SWD algorithm. The first component has the richest fault information and perceived as the principal oscillatory component (POC). Secondly, the MEDE value of the POC is calculated and used to describe the characteristics of signal. Ultimately, the obtained MEDE values of various states are trained and recognized by being input as the feature vectors into the RF classifier to achieve the automatic identification of rolling bearing fault under different operation states. The dataset of Case Western Reserve University is conducted, the proposed approach achieves recognition accuracy rate of 100%. In summary, the proposed approach is efficient and robust, which can be used as a supplement to the rolling bearing fault diagnosis methods.

The early fault of rolling bearing is weak and may not be readily detected. To overcome this issue, the present paper comes up with a rolling bearing fault‐diagnosing approach based on adaptive asymmetric real Laplace wavelet (ARLW) filtering, which is on the strength of water cycle optimization algorithm (WCA). Firstly, ARLW is introduced to filter the initial vibration signal since its waveform has the same asymmetric structure as the fault impact. Secondly, the optimum center frequency and bandwidth of ARLW is found out adaptively by applying the WCA through the proposed square envelope fault energy ratio (SEFER). Finally, envelope analysis is conducted to the narrowband signal obtained by the optimum ARLW filtering, and its envelope spectrum presents the rolling bearing fault characteristic frequency apparently. The proposed approach and two existing approaches are all tested in four signal analysis cases. The results are analyzed, and the conclusion is that the approach proposed by the present paper can detect the early fault of rolling bearing more accurately. The present research is valuable for diagnosing the early fault of rolling bearing.