Vibration-Based Early Crack Diagnosis With Machine Learning for Spur Gears

Abstract Gear mechanisms are one of the most significant components of the power transmission systems. Due to increasing emphasis on the high-speed, longer working life, high torques, etc. cracks may be observed on the gear surface. Recently, Machine Learning (ML) algorithms have started to be used frequently in fault diagnosis with developing technology. The aim of this study is to determine the gear root crack and its degree with vibration-based diagnostics approach using ML algorithms. To perform early crack detection, the single tooth stiffness and the mesh stiffness calculated via ANSYS for both healthy and faulty (25-50-75-100%) teeth. The calculated data transferred to the 6-DOF dynamic model of a one-stage gearbox, and vibration responses was collected. The data gathered for healthy and faulty cases were evaluated for the feature extraction with five statistical indicators. Besides, white Gaussian noise was added to the data obtained from the 6-DOF model, and it was aimed at early fault diagnosis and condition monitoring with ML algorithms. In this study, the gear root crack and its degree analyzed for both healthy and four different crack sizes (25%-50%-75%-100%) for the gear crack detection. Thereby, a method was presented for early fault diagnosis without the need for a big experimental dataset. The proposed vibration-based approach can eliminate the high test rig construction costs and can potentially be used for the evaluation of different working conditions and gear design parameters. Therefore, catastrophic failures can be prevented, and maintenance costs can be optimized by early crack detection.

Download Full-text

A real-time fault diagnosis system for high-speed power system protection based on machine learning algorithms

International Journal of Electrical and Computer Engineering (IJECE) ◽

10.11591/ijece.v10i6.pp6122-6138 ◽

2020 ◽

Vol 10 (6) ◽

pp. 6122

Author(s):

Elmahdi Khoudry ◽

Abdelaziz Belfqih ◽

Tayeb Ouaderhman ◽

Jamal Boukherouaa ◽

Faissal Elmariami

Keyword(s):

Machine Learning ◽

Fault Diagnosis ◽

Power System ◽

Real Time ◽

High Speed ◽

Learning Algorithms ◽

Time Estimation ◽

Machine Learning Algorithms ◽

Diagnosis System ◽

Fault Diagnosis System

This paper puts forward a real-time smart fault diagnosis system (SFDS) intended for high-speed protection of power system transmission lines. This system is based on advanced signal processing techniques, traveling wave theory results, and machine learning algorithms. The simulation results show that the SFDS can provide an accurate internal/external fault discrimination, fault inception time estimation, fault type identification, and fault location. This paper presents also the hardware requirements and software implementation of the SFDS.

Download Full-text

Mathematical Validation of Experimentally Optimised Parameters Used in a Vibration-Based Machine-Learning Model for Fault Diagnosis in Rotating Machines

Machines ◽

10.3390/machines9080155 ◽

2021 ◽

Vol 9 (8) ◽

pp. 155

Author(s):

Natalia Espinoza Sepulveda ◽

Jyoti Sinha

Keyword(s):

Machine Learning ◽

Fault Diagnosis ◽

Fe Model ◽

Rotating Machines ◽

Fe Method ◽

Industrial Systems ◽

Machine Learning Model ◽

Vibration Responses ◽

Diagnosis Model ◽

Experimental Rig

Mathematical models have been widely used in the study of rotating machines. Their application in dynamics has eased further research since they can avoid time-consuming and exorbitant experimental processes to simulate different faults. The earlier vibration-based machine-learning (VML) model for fault diagnosis in rotating machines was developed by optimising the vibration-based parameters from experimental data on a rig. Therefore, a mathematical model based on the finite-element (FE) method is created for the experimental rig, to simulate several rotor-related faults. The generated vibration responses in the FE model are then used to validate the earlier developed fault diagnosis model and the optimised parameters. The obtained results suggest the correctness of the selected parameters to characterise the dynamics of the machine to identify faults. These promising results provide the possibility of implementing the VML model in real industrial systems.

Download Full-text

Blind Application of Developed Smart Vibration-Based Machine Learning (SVML) Model for Machine Faults Diagnosis to Different Machine Conditions

Journal of Vibration Engineering & Technologies ◽

10.1007/s42417-020-00250-1 ◽

2020 ◽

Cited By ~ 1

Author(s):

Natalia F. Espinoza Sepúlveda ◽

Jyoti K. Sinha

Keyword(s):

Machine Learning ◽

Fault Diagnosis ◽

Condition Monitoring ◽

Operating Conditions ◽

Machine Vibration ◽

Identical Machines ◽

Vibration Responses ◽

Faults Diagnosis ◽

Diagnosis Model ◽

Machine Speed

Abstract Purpose The development and application of intelligent models to perform vibration-based condition monitoring in industry seems to be receiving attention in recent years. A number of such research studies using the artificial intelligence, machine learning, pattern recognition, etc., are available in the literature on this topic. These studies essentially used the machine vibration responses with known machine faults to develop smart fault diagnosis models. These models are yet to be tested for all kinds of machine faults and/or different operating conditions. Therefore, the purpose is to develop a generic machine faults diagnosis model that can be applied blindly to any identical machines with high confidence level in accuracy of the predictions. Methods In this paper, a supervised smart fault diagnosis model is developed. This model is developed using the available measured vibration responses for the different rotor faults simulated on an experimental rotating rig operating at a constant speed. The developed smart vibration-based machine learning (SVML) model is then blindly tested to identify the healthy and faulty conditions of the rig when operating at different speeds. Results and conclusions Several scenarios are proposed and examined during the development of the SVML model. It is observed that scenario of the vibration measurements simultaneously from all bearings from a machine is capable to fully map the machine dynamics in the VML model. Therefore, this developed when applied blindly to the sets of data at a different machine speed, the results are observed to be encouraging. The results clearly show a possibility for a centralised vibration-based condition monitoring (CVCM) model for identical machines operating at different rotating speeds.

Download Full-text

Spatially Resolved Experimental Modal Analysis on High-Speed Composite Rotors Using a Non-Contact, Non-Rotating Sensor

Sensors ◽

10.3390/s21144705 ◽

2021 ◽

Vol 21 (14) ◽

pp. 4705

Author(s):

Julian Lich ◽

Tino Wollmann ◽

Angelos Filippatos ◽

Maik Gude ◽

Juergen Czarske ◽

...

Keyword(s):

High Speed ◽

Natural Frequencies ◽

Mode Shapes ◽

Fiber Reinforced ◽

Structural Dynamic ◽

Spatially Resolved ◽

Glass Fiber Reinforced ◽

Vibration Responses ◽

And Performance

Due to their lightweight properties, fiber-reinforced composites are well suited for large and fast rotating structures, such as fan blades in turbomachines. To investigate rotor safety and performance, in situ measurements of the structural dynamic behaviour must be performed during rotating conditions. An approach to measuring spatially resolved vibration responses of a rotating structure with a non-contact, non-rotating sensor is investigated here. The resulting spectra can be assigned to specific locations on the structure and have similar properties to the spectra measured with co-rotating sensors, such as strain gauges. The sampling frequency is increased by performing consecutive measurements with a constant excitation function and varying time delays. The method allows for a paradigm shift to unambiguous identification of natural frequencies and mode shapes with arbitrary rotor shapes and excitation functions without the need for co-rotating sensors. Deflection measurements on a glass fiber-reinforced polymer disk were performed with a diffraction grating-based sensor system at 40 measurement points with an uncertainty below 15 μrad and a commercial triangulation sensor at 200 measurement points at surface speeds up to 300 m/s. A rotation-induced increase of two natural frequencies was measured, and their mode shapes were derived at the corresponding rotational speeds. A strain gauge was used for validation.

Download Full-text

Aerodynamic and aeroacoustic performance investigations on modified H-rotor Darrieus wind turbine

Wind Engineering ◽

10.1177/0309524x211003963 ◽

2021 ◽

pp. 0309524X2110039

Author(s):

Amgad Dessoky ◽

Thorsten Lutz ◽

Ewald Krämer

Keyword(s):

Wind Turbine ◽

High Speed ◽

Cfd Simulation ◽

Vertical Axis ◽

3D Models ◽

Power Coefficient ◽

Design Parameters ◽

Second Phase ◽

Vertical Axis Wind Turbine ◽

Guide Vanes

The present paper investigates the aerodynamic and aeroacoustic characteristics of the H-rotor Darrieus vertical axis wind turbine (VAWT) combined with very promising energy conversion and steering technology; a fixed guide-vanes. The main scope of the current work is to enhance the aerodynamic performance and assess the noise production accomplished with such enhancement. The studies are carried out in two phases; the first phase is a parametric 2D CFD simulation employing the unsteady Reynolds-averaged Navier-Stokes (URANS) approach to optimize the design parameters of the guide-vanes. The second phase is a 3D CFD simulation of the full turbine using a higher-order numerical scheme and a hybrid RANS/LES (DDES) method. The guide-vanes show a superior power augmentation, about 42% increase in the power coefficient at λ = 2.75, with a slightly noisy operation and completely change the signal directivity. A remarkable difference in power coefficient is observed between 2D and 3D models at the high-speed ratios stems from the 3D effect. As a result, a 3D simulation of the capped Darrieus turbine is carried out, and then a noise assessment of such configuration is assessed. The results show a 20% increase in power coefficient by using the cap, without significant change in the noise signal.

Download Full-text