A Comprehensive Review on Signal-Based and Model-Based Condition Monitoring of Wind Turbines: Fault Diagnosis and Lifetime Prognosis

Badihi, Hamed; Zhang, Youmin; Jiang, Bin; Pillay, Pragasen; Rakheja, Subhash

doi:10.1109/jproc.2022.3171691

Cited by 104 publications

(38 citation statements)

References 372 publications

(187 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The approach looks for elements such as rotor motion, rotational inertia, punching deformation, and torque due to power transmission, considering the gyroscopic effect. Specifically, the function that is considered for the vertical movement is [ 19 ]:

…”

Section: Vibration Analysis Datamentioning

confidence: 99%

A Deep Spiking Neural Network Anomaly Detection Method

Liu

Qiu

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Cyber-attacks on specialized industrial control systems are increasing in frequency and sophistication, which means stronger countermeasures need to be implemented, requiring the designers of the equipment in question to re-evaluate and redefine their methods for actively protecting against advanced mass cyber-attacks. The attacks in question have huge motivations, ranging from corporate espionage to political targets, but in any case, they have a substantial financial impact and severe real-world implications. It should also be said that it is challenging to defend against cyber threats because a single point of entry can be enough to destroy an entire organization or put it out of business. This paper examines threats to the digital security of vibration monitoring systems used in petroleum infrastructure protection services, such as pipelines, pumps, and tank farms, where malicious interventions can cause explosions, fires, or toxic releases, with incalculable economic and environmental consequences. Specifically, a deep spiking neural network anomaly detection method is presented, which models the spike sequences and the internal presentation mechanisms of the information to discover with very high accuracy anomalies in vibration analysis systems used in oil infrastructure protection services. This is achieved by simulating the complex structures of the human brain and the way neural information is processed and transmitted. This work uses a particularly innovative form of the Galves–Löcherbach Spiking Model (GLSM) [1], which is a spiking neural network model with intrinsic stochasticity, ideal for modeling complex spatiotemporal situations, which is enhanced with possibilities of exploiting confidence intervals by modeling optimally stochastic variable-length memory chains that have a finite state space.

show abstract

…”

Section: Vibration Analysis Datamentioning

confidence: 99%

A Deep Spiking Neural Network Anomaly Detection Method

Liu

Qiu

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Signal-based methods perform fault detection tasks by analyzing the time-domain signals without modeling. The main disadvantages are time-consuming computation and noise susceptibility [7]. Recently, data-driven methods, which are also known as knowledge-based methods, have been extensively studied due to their powerful modeling ability without any prior known models or parameters [8].…”

Section: Introductionmentioning

confidence: 99%

Fault Detection for Motor Drive Control System of Industrial Robots Using CNN-LSTM-based Observers

Wang

Zhang

Wang

2023

Trans. Electr. Mach. Syst.

View full text Add to dashboard Cite

The complex working conditions and nonlinear characteristics of the motor drive control system of industrial robots make it difficult to detect faults. In this paper, a deep learning-based observer, which combines the convolutional neural network (CNN) and the long short-term memory network (LSTM), is employed to approximate the nonlinear driving control system. CNN layers are introduced to extract dynamic features of the data, whereas LSTM layers perform time-sequential prediction of the target system. In terms of application, normal samples are fed into the observer to build an offline prediction model for the target system. The trained CNN-LSTM-based observer is then deployed along with the target system to estimate the system outputs. Online fault detection can be realized by analyzing the residuals. Finally, an application of the proposed fault detection method to a brushless DC motor drive system is given to verify the effectiveness of the proposed scheme. Simulation results indicate the impressive fault detection capability of the presented method for driving control systems of industrial robots.

show abstract

“…Though today’s CMSs can be used to gain insight into the drivetrain’s condition, they cannot measure GB input loads. According to [ 11 ], several studies have been conducted to measure the torque on the LSS [ 12 , 13 , 14 , 15 , 16 , 17 ]. In [ 18 ], torque measurements were categorized into strain gauges, magnetostrictive, surface acoustic wave, piezoelectric, and optical and inductive twist measurements.…”

Section: Introductionmentioning

confidence: 99%

From Strain to Loads: Development of a Measurement Solution for Wind Turbine Transmission Input Loads during Drivetrain Testing

Bilen

Azzam

Schelenz

et al. 2023

Sensors

View full text Add to dashboard Cite

As wind energy is paving the way for the energy transition from fossil to renewable energy sources, the ongoing trend of increasing the rated power of wind turbines aims to reduce the overall cost of wind energy. The resulting increase in drivetrain loads motivates the need for wind turbine (WT) drivetrain testing in the development phase of critical components such as the WT main gearbox (GB). While several WT system test benches allow for the application of emulated rotor loads in six degrees of freedom (6-DOF), the drivetrain input loads can significantly differ from the GB 6-DOF input loads due to the design of the drivetrain under test. However, currently available load measurement solutions are not capable of sensing GB input loads in 6-DOF. Thus, this work aims to develop a methodology for converging signals from a purposely designed sensor setup and turbine specific design parameters to compute the GB 6-DOF input loads during WT testing. Strain gauges (SG) and accelerometers have been installed on the low-speed shaft (LSS) of a WT drivetrain under test at the 4MW WT system test bench at the Center for Wind Power Drives. Using the data of the aforementioned sensors, a methodology for computing the GB input loads is developed. The methodology is validated through comparison to the applied loads data provided by the aforementioned test bench. The results demonstrate the high promise of the proposed method for estimating the GB input loads during WT drivetrain testing.

show abstract

A Comprehensive Review on Signal-Based and Model-Based Condition Monitoring of Wind Turbines: Fault Diagnosis and Lifetime Prognosis

Abstract: This article reviews the state-of-the-art condition monitoring technologies used for fault diagnosis and lifetime prognosis in wind turbines.

Cited by 104 publications

References 372 publications

A Deep Spiking Neural Network Anomaly Detection Method

A Deep Spiking Neural Network Anomaly Detection Method

Fault Detection for Motor Drive Control System of Industrial Robots Using CNN-LSTM-based Observers

From Strain to Loads: Development of a Measurement Solution for Wind Turbine Transmission Input Loads during Drivetrain Testing

Contact Info

Product

Resources

About