Self-Powered Wireless Sensor for Fault Diagnosis of Wind Turbine Planetary Gearbox

Li Lu,Bing Li,Yigang He,Tao Wang,Tiancheng Shi

doi:10.1109/access.2019.2925426

Abstract

This paper proposes a wind turbine planetary gearbox (PGB) fault diagnosis method based on a self-powered wireless sensor. The proposed wireless sensor, which consists of a piezoelectric energy harvester, a power management circuit, a microcontroller unit (MCU), a radio-frequency (RF) module, and an accelerometer, can acquire the vibration signals of wind turbine PGB by the accelerometer. The piezoelectric energy harvester utilizing vibration environment is optimized as a power supply for the proposed wireless sensor, including the MCU, RF module, and accelerometer. An ac–dc converter combined with a low-dropout voltage regulator is developed to provide stable dc voltage for the proposed wireless sensor. Stacked denoising autoencoder (SDAE) shows excellent performance in learning robust features from the noised signal. Thus, in this paper, the SDAE method is adopted to learn robust and distinguishable features from measured signals. Then, the least squares support vector machine (LSSVM) is employed to classify features extracted by the SDAE. Both the SDAE and LSSVM are optimized by quantum particle swarm optimization (QPSO). The experimental results show that the presented power supply can generate 3.3-V dc voltage, which ensures regular operation of the rest of the wireless sensor. The proposed wireless sensor can achieve a reliable communication distance of 40.8 m in the test environment. Furthermore, the SDAE approach and LSSVM show excellent performance in feature extraction and fault diagnosis, respectively. The experimental results indicate that the proposed method is effective in terms of fault diagnosis for the wind turbine PGB.

Highlights

Great progress has been made in wind power generation in recent years [1], but compared with traditional power generation system, such as coal and natural gas, the maintenance strategy of wind projects needs more initiative due to the relatively higher operation and maintenance costs [2]
This paper presents a novel approach for fault diagnosis of wind turbine planetary gearbox (PGB) with advantage of no-invasive, compact, efficient and feasible
In this paper, an on-line diagnosis approach for wind turbine PGB faults based on wireless sensor networks (WSNs), Stacked denoising autoencoder (SDAE) and quantum particle swarm optimization (QPSO)-least squares support vector machine (LSSVM) is proposed

Summary

INTRODUCTION

Great progress has been made in wind power generation in recent years [1], but compared with traditional power generation system, such as coal and natural gas, the maintenance strategy of wind projects needs more initiative due to the relatively higher operation and maintenance costs [2]. The fault diagnosis methods used for gearbox condition monitoring are mainly based on vibration monitoring [7]–[9], in which the vibration signals are acquired by sensors, such as accelerometers, mounted on the casing of the gearbox, which is in a high tower and inaccessible during the operation of wind turbine. A novel wireless sensor node, developed for on-line monitoring of wind turbine gearbox, is adopted to obtain vibration signals for subsequent fault diagnosis. Various deep learning methods are employed to process complex vibration signals, such as deep belief network (DBN) [31], sparse filtering [32], sparse autoencoder [33], multilayered extreme learning machine [34], and stacked denoising autoencoder (SDAE) [35], for fault diagnosis.

SYSTEM TOPOLOGY

STACKED DENOISING AUTOENCODER

LEAST SQUARES SVM

MEASUREMENT AND PROCESSING RESULTS

Findings

CONCLUSION