Health assessment and health trend prediction of wind turbine bearing based on BO-BiLSTM model

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 17, 2025

During the long-term operation of wind turbines, due to environmental factors and equipment aging, health reliability each component will gradually decline, leading failure. To assess status timely grasp subsequent changes development trends, it is necessary extract degradation characteristics, including time domain, frequency time-frequency domain characteristics. These characteristics can reflect operating equipment, help build indicator curves, evaluate high-speed shaft bearings turbines. Selecting reasonable an important prerequisite for constructing a index curve, using evaluation indicators construct comprehensive function screen The feature fusion method based on self-organizing mapping network used fuse multiple selected features into curve that bearing process. Finally, quantitative analysis performed scientifically bearings. Bearings are one key components Based constructed in this article, appropriate prediction model predict trend A effective trends turbine great practical significance formulating scientific maintenance measures farms. work article be divided following four parts: (1) Extracting vibration signals turbines; (2) Comprehensive monotonicity, correlation, robustness constructs degenerate features; (3) Use network. integrates curve; (4) optimize BiLSTM hyperparameters through Bayesian establish BO-BiLSTM achieve more accurate trend.

Язык: Английский

---

BCSSA-VMD and ICOA-ELM based fault diagnosis method for analogue circuits

Analog Integrated Circuits and Signal Processing, Год журнала: 2025, Номер 123(2)

Опубликована: Март 18, 2025

Язык: Английский

---

An intelligent fault diagnosis model for bearings with adaptive hyperparameter tuning in multi-condition and limited sample scenarios

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 24, 2025

Abstract Bearing fault diagnosis under multiple operating conditions is challenging due to the complexity of changing environments and limited availability training data. To address these issues, this paper presents an advanced method using a hybrid Grey Wolf Algorithm (HGWA)-optimized convolutional neural network (CNN) Bidirectional long short-term memory (BiLSTM) architecture. The proposed model leverages CNN for extracting spatial features BiLSTM capturing temporal dependencies. Through HGWA, hyperparameters are efficiently optimized, achieving 100% diagnostic accuracy across four with CWRU dataset. Additionally, optimized CNN–BiLSTM demonstrated high when applied as pre-trained in new environments, even minimal not only improves performance but also enhances optimization efficiency, faster results within same time frame. This approach mitigates challenges manually tuning effectively addresses bearing constrained sample conditions, representing meaningful contribution field rolling diagnostics.

Язык: Английский

---

Generalized Gaussian Distribution Refined Composite Multiscale Fluctuation Dispersion Entropy and Its Application in Fault Diagnosis of Switch Machine

Structural Control and Health Monitoring, Год журнала: 2025, Номер 2025(1)

Опубликована: Янв. 1, 2025

The switch machine (SM) is an important device for turnout conversion, which of great significance to ensure the safety train operations. Refined composite multiscale dispersion entropy (RCMDE) a formidable nonlinear characterization tool time series signals, has been applied fault diagnosis (FD) machines. In fact, lack mapping ability RCMDE and inability evaluate volatility SM signal affect its extract features. To overcome inherent drawbacks, generalized Gaussian distribution refined fluctuation (GGRCMFDE) proposed measure complexity signal. GGRCMFDE, first, algorithm improved by replacing normal cumulative function (NCDF) with (GGD). theory introduced better adapt phenomenon nonperiodic when fails. Through above improvement, feature extraction capability comprehensively enhanced. Second, FD method used combining features extracted GGRCMFDE support vector (SVM) classification. Finally, algorithm’s performance guaranteed improving dung beetle optimization (IDBO) algorithm, superiority using IDBO optimize SVM; we name this GGRCMFE–IDBO–SVM. It verified actual operation scene experiment shows that compared other algorithms, impact GGRCMFE–IDBO–SVM significant, taller identification precision can be obtained.

Язык: Английский

---

Self-supervised learning for vehicle bearing fault diagnosis based on time–frequency dual-domain contrast and fusion

Nonlinear Dynamics, Год журнала: 2025, Номер unknown

Опубликована: Апрель 4, 2025

Язык: Английский

---