DETECTION OF EARLY RUB-IMPACT IN ROTORS VIA HIGHER-ORDER TIME-FREQUENCY ENTROPY

Due to the calculation problem of classical methods (such as Lyapunovexponent) for chaotic behavior, a new method of identifying nonlinear dynamics with higher-ordertime-frequency entropy (HOTFE) based on time-frequency analysis and information theorem is proposed.Firstly, the meaning of HOTFE is defined, and then its validity is testified by numericalsimulation. In the end vibration data from rotors are analyzed by HOTFE. The results demonstratethat it can indeed identify the early rub-impact chaotic behavior in rotors and also is simpler tocalculate than previous methods.

Early Sensor Fault Detection Based on PCA and Clustering Analysis

This paper proposes a novel scoring index for the early sensor fault detection in order to make full use of massive archived spacecraft telemetry data.The early detection of sensor faults is made by using the index constructed by the K-means algorithm and PCA model.The sensor fault detection includes the learning phase and monitoring phase.The amplitude of sensor fault has been always increasing when the performance of sensors deteriorates during a period.The proposed index can detect the smaller sensor faults than the squared prediction error( SPE) index which means it can discover the sensor faults earlier than the later.The simulation results demonstrate the effectiveness and feasibility of the proposed index which can decrease the check-limit as much as 40% than SPE in the same magnitude of bias sensor fault.

Discovery of the Early Devonian Sinistral Shear in the Jiangshan-Shaoxing Fault Zone and its Tectonic Significance

The Jiangshan-Shaoxing fault zone （JSFZ） was formed by the amalgamation of the Yangtze and Cathaysia blocks in the Neoproterozoic.Since the Paleozoic,the JSFZ has experienced three episodes of tectonic activities：the Early Paleozoic ductile strike-slip shear,Early Mesozoic thrust,and the Late Mesozoic extension.

NEW METHOD OF EXTRACTING WEAK FAILURE INFORMATION IN GEARBOX BY COMPLEX WAVELET DENOISING

Because the extract of the weak failure information is always the difficulty and focus of fault detection. Aiming for specific statistical properties of complex wavelet coefficients of gearbox vibration signals, a new signal-denoising method which uses local adaptive algorithm based on dual-tree complex wavelet transform （DT-CWT） is introduced to extract weak failure information in gear, especially to extract impulse components. By taking into account the non-Gaussian probability distribution and the statistical dependencies among wavelet coefficients of some signals, and by taking the advantage of near shift-invariance of DT-CWT, the higher signal-to-noise ratio （SNR） than common wavelet denoising methods can be obtained. Experiments of extracting periodic impulses in gearbox vibration signals indicate that the method can extract incipient fault feature and hidden information from heavy noise, and it has an excellent effect on identifying weak feature signals in gearbox vibration signals.

Weak characteristic information extraction from early fault of wind turbine generator gearboxKeywords wind turbine generator gearbox, B-singular value decomposition, local mean decomposition, weak characteristic information extraction, early fault warning

Given the weak early degradation characteristic information during early fault evolution in gearbox of wind turbine generator, traditional singular value decomposition （SVD）-based denoising may result in loss of useful information. A weak characteristic information extraction based on μ-SVD and local mean decomposition （LMD） is developed to address this problem. The basic principle of the method is as follows： Determine the denoising order based on cumulative contribution rate, perform signal reconstruction, extract and subject the noisy part of signal to LMD and μ-SVD denoising, and obtain denoised signal through superposition. Experimental results show that this method can significantly weaken signal noise, effectively extract the weak characteristic information of early fault, and facilitate the early fault warning and dynamic predictive maintenance.

Deep anomaly detection in horizontal axis wind turbines using GraphConvolutional Autoencoders for Multivariate Time series

Wind power is one of the fastest-growing renewable energy sectors instrumental in the ongoing decarbonizationprocess. However, wind turbines are subjected to a wide range of dynamic loads which can cause more frequentfailures and downtime periods, leading to ever-increasing attention to effective Condition Monitoring strategies.In this paper, we propose a novel unsupervised deep anomaly detection framework to detect anomalies in windturbines based on SCADA data. We introduce a promising neural architecture, namely a Graph ConvolutionalAutoencoder for Multivariate Time series, to model the sensor network as a dynamical functional graph. Thisstructure improves the unsupervised learning capabilities of Autoencoders by considering individual sensormeasurements together with the nonlinear correlations existing among signals. On this basis, we developeda deep anomaly detection framework that was validated on 12 failure events occurred during 20 months ofoperation of four wind turbines. The results show that the proposed framework successfully detects anomaliesand anticipates SCADA alarms by outperforming other two recent neural approaches.