Yuan Zheng

Bio: Yuan Zheng is an academic researcher from Hohai University. The author has contributed to research in topics: Turbine & Turbulence. The author has an hindex of 16, co-authored 130 publications receiving 1210 citations.

Bearing Fault Diagnosis Based on Statistical Locally Linear Embedding.

Abstract: Fault diagnosis is essentially a kind of pattern recognition. The measured signal samples usually distribute on nonlinear low-dimensional manifolds embedded in the high-dimensional signal space, so how to implement feature extraction, dimensionality reduction and improve recognition performance is a crucial task. In this paper a novel machinery fault diagnosis approach based on a statistical locally linear embedding (S-LLE) algorithm which is an extension of LLE by exploiting the fault class label information is proposed. The fault diagnosis approach first extracts the intrinsic manifold features from the high-dimensional feature vectors which are obtained from vibration signals that feature extraction by time-domain, frequency-domain and empirical mode decomposition (EMD), and then translates the complex mode space into a salient low-dimensional feature space by the manifold learning algorithm S-LLE, which outperforms other feature reduction methods such as PCA, LDA and LLE. Finally in the feature reduction space pattern classification and fault diagnosis by classifier are carried out easily and rapidly. Rolling bearing fault signals are used to validate the proposed fault diagnosis approach. The results indicate that the proposed approach obviously improves the classification performance of fault pattern recognition and outperforms the other traditional approaches.

A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals

Abstract: Intelligent fault diagnosis techniques have replaced time-consuming and unreliable human analysis, increasing the efficiency of fault diagnosis. Deep learning models can improve the accuracy of intelligent fault diagnosis with the help of their multilayer nonlinear mapping ability. This paper proposes a novel method named Deep Convolutional Neural Networks with Wide First-layer Kernels (WDCNN). The proposed method uses raw vibration signals as input (data augmentation is used to generate more inputs), and uses the wide kernels in the first convolutional layer for extracting features and suppressing high frequency noise. Small convolutional kernels in the preceding layers are used for multilayer nonlinear mapping. AdaBN is implemented to improve the domain adaptation ability of the model. The proposed model addresses the problem that currently, the accuracy of CNN applied to fault diagnosis is not very high. WDCNN can not only achieve 100% classification accuracy on normal signals, but also outperform the state-of-the-art DNN model which is based on frequency features under different working load and noisy environment conditions.

A review of solar energy driven desalination technologies

Abstract: Water plays an important role in all our day to day activities and its consumption is increasing day by day because of increased living standards of mankind. Some regions of the globe are under severe stress due to water scarcity and pollution. The fresh water needs of mankind can be only satisfied if saline water which is available in plenty is converted to potable water by desalination. Desalination industry has shown increased threats of CO2 emissions and severe environmental impacts. Desalination industry can be made sustainable if they are integrated with renewable energy and if proper brine disposal methods are followed. In this review different desalination units integrated with renewable energy with special emphasis given to solar energy is discussed. The problems associated with desalination units and their remedies have been presented. Apart from this some novel methods of desalination process has also been explained. This review will allow the researchers to choose appropriate desalination technology for further development.

Optimal planning of hybrid renewable energy systems using HOMER: A review

Abstract: World energy consumption is rising due to population growth and increasing industrialization. Traditional energy resources cannot meet these requirements with notice to their challenges, e.g., greenhouse gas emission and high lifecycle costs. Renewable energy resources are the appropriate alternatives for traditional resources to meet the increasing energy consumption, especially in electricity sector. Integration of renewable energy resources with traditional fossil-based resources besides storages creates Hybrid Renewable Energy Systems (HRESs). To access minimum investment and operation costs and also meet the technical and emission constraints, optimal size of HRES׳s equipment should be determined. One of the most powerful tools for this purpose is Hybrid Optimization Model for Electric Renewables (HOMER) software that was developed by National Renewable Energy Laboratory (NREL), United States. This software has widely been used by many researchers around the world. In this paper a review of the state-of-the-art of researches, which use HOMER for optimal planning of HRES, is presented.

Effects of the computational time step on numerical solutions for turbulent flow

Abstract: Effects of large computational time steps on the computed turbulence were investigated using a fully implicit method. In turbulent channel flow computations the largest computational time step in wall units which led to accurate prediction of turbulence statistics was determined. Turbulence fluctuations could not be sustained if the computational time step was near or larger than the Kolmogorov time scale.