Review of Data Processing Methods Used in Predictive Maintenance for Next Generation Heavy Machinery DOI Creative Commons

Ietezaz Ul Hassan,

Krishna Panduru, J. L. Walsh

et al.

Data, Journal Year: 2024, Volume and Issue: 9(5), P. 69 - 69

Published: May 15, 2024

Vibration-based condition monitoring plays an important role in maintaining reliable and effective heavy machinery various sectors. Heavy involves major investments is frequently subjected to extreme operating conditions. Therefore, prompt fault identification preventive maintenance are for reducing costly breakdowns operational safety. In this review, we look at different methods of vibration data processing the context vibration-based machinery. We divided primary approaches related into three categories–signal methods, preprocessing-based techniques artificial intelligence-based methods. highlight importance these improving reliability effectiveness systems, highlighting precise automated detection systems. To improve performance efficiency, review aims provide information on current developments future directions by addressing issues like imbalanced integrating cutting-edge anomaly algorithms.

Language: Английский

Non-contact diagnosis for gearbox based on the fusion of multi-sensor heterogeneous data DOI
Dingyi Sun, Yongbo Li, Sixiang Jia

et al.

Information Fusion, Journal Year: 2023, Volume and Issue: 94, P. 112 - 125

Published: Jan. 26, 2023

Language: Английский

Citations

45
Fuzzy adaptive power optimization control of wind turbine with improved whale optimization algorithm and kernel extreme learning machine DOI
Bangjun Lei, Haihong Tang, Yuxiang Su

et al.

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 126750 - 126750

Published: Feb. 1, 2025

Language: Английский

Citations

2
Evaluation of Wind Turbine Failure Modes Using the Developed SWARA-CoCoSo Methods Based on the Spherical Fuzzy Environment DOI Creative Commons
Saeid Jafarzadeh Ghoushchi, Sepideh Miralizadeh Jalalat, Shabnam Rahnamay Bonab

et al.

IEEE Access, Journal Year: 2022, Volume and Issue: 10, P. 86750 - 86764

Published: Jan. 1, 2022

Accurately recognizing potential failures in the early stages of providing products or services can prevent loss investment and time reduce risk safety hazards. Failure mode effects analysis (FMEA) is a conventional approach for detecting prioritizing probable product's design production process. Nevertheless, traditional priority number (RPN) method has come under criticism its deficiencies. This paper proposes modified FMEA based on fuzzy Multi-Criteria Decision Making (MCDM) techniques to cope with weaknesses previous methodologies improve primary method. The concept spherical sets (SFS) utilized address vagueness impreciseness information that allows experts have more freedom making decisions by including membership, non-membership, hesitation sets. Initially, procedure assigning weights RPN criteria implemented SFS step-wise weight assessment ratio (SWARA). Then, failure modes are ranked combined compromise solution (CoCoSo) effectiveness practicality suggested illustrated through case study Manjil wind farm Iran. Results show model reliable realistic be prioritization than common other integrated MCDM approaches.

Language: Английский

Citations

41
Fault Detection for Motor Drive Control System of Industrial Robots Using CNN-LSTM-based Observers DOI Creative Commons
Tao Wang, Le Zhang, Xuefei Wang

et al.

CES Transactions on Electrical Machines and Systems, Journal Year: 2023, Volume and Issue: 7(2), P. 144 - 152

Published: Jan. 30, 2023

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

Language: Английский

Citations

30
Joint parameter-input estimation for digital twinning of the Block Island wind turbine using output-only measurements DOI Creative Commons
Mingming Song, Babak Moaveni, Hamed Ebrahimian

et al.

Mechanical Systems and Signal Processing, Journal Year: 2023, Volume and Issue: 198, P. 110425 - 110425

Published: May 12, 2023

Language: Английский

Citations

27
Detailed Determination of Delamination Parameters in a Multilayer Structure Using Asymmetric Lamb Wave Mode DOI Creative Commons
Olgirdas Tumšys, Lina Draudvilienė, Egidijus Žukauskas

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(2), P. 539 - 539

Published: Jan. 18, 2025

A signal-processing algorithm for the detailed determination of delamination in multilayer structures is proposed this work. The based on calculating phase velocity Lamb wave A0 mode and estimating dispersion. Both simulation experimental studies were conducted to validate technique. having a diameter 81 mm segment wind turbine blade (WTB) was used verification Four cases study: defect-free, between first second layers, third defect (hole). calculated variation determine location edge coordinates delaminations defects. It has been found that order estimate depth at which is, it appropriate calculate dispersion curves. difference reconstructed curves layers simulated different depths estimated be about 60 m/s. values compared with hole drilled corresponding depth. obtained results confirmed can as delamination. WTB sample study. Using algorithm, parameters obtained. using signals indicated new suitable structure.

Language: Английский

Citations

1
A review of SCADA-based condition monitoring for wind turbines via artificial neural networks DOI
Li Sheng, Chunyu Li, Ming Gao

et al.

Neurocomputing, Journal Year: 2025, Volume and Issue: unknown, P. 129830 - 129830

Published: March 1, 2025

Language: Английский

Citations

1
Applications and Modeling Techniques of Wind Turbine Power Curve for Wind Farms—A Review DOI Creative Commons
Francisco Bilendo, Angela Meyer, Hamed Badihi

et al.

Energies, Journal Year: 2022, Volume and Issue: 16(1), P. 180 - 180

Published: Dec. 24, 2022

In the wind energy industry, power curve represents relationship between “wind speed” at hub height and corresponding “active power” to be generated. It is most versatile condition indicator of vital importance in several key applications, such as turbine selection, capacity factor estimation, assessment forecasting, monitoring, among others. Ensuring an effective implementation aforementioned applications mostly requires a modeling technique that best approximates normal properties optimal turbines operation particular farm. This challenge has drawn attention farm operators researchers towards “state art” technology. paper provides exhaustive updated review on based common anomaly fault types including their root-causes, along with data preprocessing correction schemes (i.e., filtering, clustering, isolation, others), techniques parametric non-parametric) which cover wide range algorithms. More than 100 references, for part selected from recently published journal articles, were carefully compiled properly assess past, present, future research directions this active domain.

Language: Английский

Citations

38
A Review of machine learning techniques for wind turbine’s fault detection, diagnosis, and prognosis DOI
Prince Waqas Khan,

Yung-Cheol Byun

International Journal of Green Energy, Journal Year: 2023, Volume and Issue: 21(4), P. 771 - 786

Published: May 29, 2023

Wind turbines are becoming increasingly important in the generation of clean, renewable energy worldwide. To ensure their dependable and accessible operation, advanced real-time condition monitoring technology must be implemented to guarantee efficient wind power financial viability. Machine learning (ML) has emerged as a crucial technique for systems recent years. This is especially relevant because dedicated systems, primarily focused on vibration measurements, prohibitively expensive. Preventive maintenance most effective way detect address issues before they impact performance. article provides comprehensive up-to-date review latest technologies fault detection, diagnosis, prognosis turbines, with particular focus ML algorithms critical faults failure modes, preprocessing methods, evaluation metrics. Numerous references have been analyzed evaluate past, present, potential future research development trends this field. Most these based journal articles, theses, reports found open literature.

Language: Английский

Citations

23
A digital twin-based framework for damage detection of a floating wind turbine structure under various loading conditions based on deep learning approach DOI
Zohreh Mousavi, Sina Varahram, Mir Mohammad Ettefagh

et al.

Ocean Engineering, Journal Year: 2023, Volume and Issue: 292, P. 116563 - 116563

Published: Dec. 23, 2023

Language: Английский

Citations

22