The reciprocating pump plays an important role in the petrochemical industry procedure, it is crucial in ensuring the systematic safety and stability. Since the useful feature information of the vibration signal from the reciprocating pump tends to be overwhelmed by the background ingredients, it is tough to realize the recognition on typical modes. Aiming at the extraction of reciprocating mechanical fault features and mode recognition, this paper proposes Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise and LSTM (Long Short-Term Memory) deep neural network algorithm. Firstly, the IMF components are obtained by decomposing the vibration signals from the reciprocating pump with the Improved CEEMDAN algorithm, in which the key parameter β k is improved and redefined, for optimizing SNRs (Signal Noise Ratio) of the IMF (Intrinsic Mode Function) components. Then the corresponding singular spectral entropy is calculated and the feature vector is constructed. The classification modal based on LSTM deep network is developed in the data dividing-training and the final mode recognition process.The study shows that the proposed method can effectively extract the fault features of vibration signal of the reciprocating pump, and the testing modes could be accurately recognized with the developed classification model.

For non-stationary vibration useful information of the impact feature tends to be overwhelmed with strong routine components, which make it difficult to implement pattern recognition. This paper proposes improved signal processing methods of variational mode decomposition (VMD) and singular value decomposition (SVD) for non-stationary impact feature extraction in application to condition monitoring of reciprocating machinery. The impact feature is firstly simulated with the dynamics' analysis of the driving mechanism of a reciprocating pump. Through comparison the merit of the improved VMD method is demonstrated. The singular value of the decomposed modes is extracted with the SVD method. The support vector machine method is used as the classifier for the extracted set of features. The performance of the proposed VMD-based method is validated practically through a set of measured data from the reciprocating pump setup.

As a key component of a mechanical system, the extraction and accurate identification of rolling bearing fault feature information are of great importance to guarantee the normal operation of the mechanical system. Aiming at that the extraction of rolling bearing fault features and traditional support vector machine parameters affects the overall accuracy of pattern classification, the improved CEEMDAN (complete ensemble empirical mode decomposition with adaptive noise) time-domain energy entropy-based model for fault pattern recognition is proposed. The ICEEMDAN method is developed to decompose the signal to obtain the IMF component series. Then, the particular IMF components are selected according to the trend of correlation coefficient and variance contribution rate; meanwhile, the information entropy (power spectral entropy, singular spectral entropy, and time-domain energy entropy) of the screened IMF components is calculated to construct the feature vector sets, respectively. Finally, the feature vector sets are input into the PSO-SVM (particle swarm optimization-support vector machine) based model for training and pattern recognition. The effectiveness of the proposed method of the improved CEEMDAN time-domain energy entropy and PSO-SVM model is testified through numerical simulation and experiments on rolling bearing datasets. The comparison proceeded with the other mainstream intelligent recognition techniques indicates the superiority of the method with the diagnostic accuracy of 100% as for the final validation.

Accurate buried pipeline state recognition based on acoustic signal is a difficult and important issue. This paper proposes a feature extraction method based on acoustic signal frame and principal component analysis (PCA) for condition monitoring in pipes. This method makes use of the property of nonstationary and multivariate data decomposition scales of pipeline acoustic signal. Signal framing is processed on the collected acoustic signals so that the signal frame series is obtained. Then, the sound pressure level of each frame signal is extracted, and the feature vector of the total sound pressure level is established. The PCA method is applied to optimize the extracted feature vector set for detecting the feature parameters. The acoustic signals related to different operating conditions of a pipeline are identified with the support vector machine. Research on a series of experiments shows that the proposed method for acoustic signal analysis can perform effectively for robust feature extraction and pipeline state identification.

No abstract