No abstract

This study utilized the multi-channel convolutional neural network (MCNN) and applied it to wind turbine blade and blade angle fault detection. The proposed approach automatically and effectively captures fault characteristics from the imported original vibration signals and identifies their state in multiple convolutional neural network (CNN) models. The result obtained from each model is sent to the output layer, which is a maximum output network (MAXNET), to compute the most accurate state. First, in terms of wind turbine blade state detection, this paper builds blade models based on the normal state and three common fault types, including blade angle anomaly, blade surface damage, and blade breakage. Vibration signals are employed for fault detection. The proposed wind turbine fault diagnosis approach adopts a triaxial vibration transducer and frame grabber to capture vibration signals and then applies the new MCNN algorithm to identify the state. The test results show that the proposed approach could deliver up to 87.8% identification accuracy for four fault types of large wind turbine blades.

Power capacitors are widely used in power systems, and any internal capacitor failures will affect the safe operations of the systems. The most common failures include humidity, partial discharge, aging, or insulating material degradation and structural damage. The purpose of this study is to detect the types of power capacitor failures by using a humanmachine interface diagnostic system in order to determine the real-time status of the power capacitors. Partial discharge data measurement and diagnostic analysis were mainly conducted on power capacitors operating at a low voltage for a long time. Defects were pre-processed before capacitance measurement, and then, an electric testing machine was used to conduct a partial discharge test for capacitor enclosures and to continuously apply voltage until the occurrence of a partial discharge. A high frequency oscillograph was used to capture the voltage and partial discharge signals. Subsequently, the empirical mode decomposition (EMD) was applied to identify the characteristics of the discharge signals and to build the chaos and error scatter map by combining the chaotic synchronization detection and analysis method. Moreover, eyes of chaos were taken as the characteristics of fault diagnosis, and an extension algorithm was used to identify capacitance failures. The advantages of this method are to reduce the characteristics' captured data and to effectively detect the minimum movement of the voltage signal discharged from power capacitors, so that the operating states of the power capacitors can be detected and determined, in order to carry out emergency measures in advance and prevent major disasters. After verification through actual measurement, the proposed method has a detection rate of 84% based on the extension theory, which proves that the method used in this study is applicable to partial discharge detection of power capacitors.

We propose a chaos synchronization detection method combined with an extension neural network to diagnose the state of wind turbine blades. On the basis of a large-scale wind power generation system architecture, a 100 W small-scale wind power generation system simulation platform was first constructed and then a programmable logic controller (PLC) collected vibration sensor information. Through Ethernet and IEC 61850 communication protocols, the measured vibration signals were synchronously transmitted to a remote human-machine interface constructed by LabVIEW to facilitate remote real-time monitoring and analysis. We examined the identification of four different states of wind turbine blades: the normal state, blade rupture, blade screw fly-off, and abnormal blade inclination angle. On the basis of vibration signals in different states, a dynamic error scatter diagram was constructed by the chaos synchronization detection method, and chaos eye coordinates were extracted as eigenvalues for the identification of various state models. Finally, through the extension neural network, the four different states were identified. The measured results show that the proposed method can identify the states of wind turbine blades, and the identification accuracy rate of the proposed method was as high as 88.75%. Therefore, the proposed method effectively detects abnormal vibration signals of wind turbines and identifies different types of blade faults in real time.

No abstract