AI-Driven Thermography-based Fault Diagnosis in Single-Phase Induction Motor

Results in Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 103493 - 103493

Published: Nov. 1, 2024

Language: Английский

---

Fault Diagnosis of Rolling Bearings Based on Acoustic Signals in Strong Noise Environments

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(3), P. 1389 - 1389

Published: Jan. 29, 2025

Compared to vibration sensors, microphones offer several advantages, including non-contact detection, high sensitivity, low cost, and ease of installation. To address the challenges posed by complex components significant interference in rolling bearing sound signals, we proposed a fault diagnosis method for acoustic signals based on Secretary Bird Optimization Algorithm (SBOA)-optimized Feature Mode Decomposition (FMD). Initially, microphone is utilized collect data while operates, followed application S-FMD (Secretary Algorithm-optimized Decomposition) decompose signal extract that may contain information related bearing. The SBOA employed adaptively optimize four influencing parameters FMD: mode number n, filter length L, frequency band cutting K, cycle period m. By minimizing envelope entropy as objective function, achieve FMD with assistance SBOA. Additionally, this paper introduces an Integrated Signal Evaluation Index (ISEI) potential failure characteristics from filtered components. Simulation experiments test results indicate that, compared Empirical Decomposition, Complementary Ensemble fixed-parameter FMD, adaptive variational decomposition methods, approach more effectively extracts weak characteristic early faults signals.

Language: Английский

---

Feature extraction of combined failures of rolling bearings based on adaptive variance symplectic geometry model decomposition

Journal of Vibration and Control, Journal Year: 2025, Volume and Issue: unknown

Published: March 20, 2025

Vibration signals of rolling bearings with faults are characterized by strong nonlinearity and non-stationarity, making it difficult to extract fault information. In the engineering practice, bearing is often represented as compound. Compared single fault, more feature information combined faults. Symplectic geometric mode decomposition represents better performance can provide protection geometry structure phase space. However, extraction affected ineffective symplectic geometrical components when processing noise weak failure feature. Meanwhile, there a lack effective standard for component option. To solve these problems, an adaptive variance method proposed. decrease interference strengthen features in original signal, sequence signal constructed. prevent influence improper embedding dimension on decomposition, track matrix adaptively determined maximum margin factor criterion. problem being option, optimal activity parameter. Faults identification accomplished power spectrum component. ascertain efficacy superiority proposed method, was compared method. Results indicate that effectively suppress noise, reduce invalid accomplish option components, enables precise judgment bearings. Furthermore, contrast frequencies distributed lower frequency band, which beneficial real-time monitoring applications.

Language: Английский

---

Enhanced rolling bearing fault diagnosis using a multi-stage attention fusion network

Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science, Journal Year: 2025, Volume and Issue: unknown

Published: March 27, 2025

Fault diagnosis of rolling bearings can promptly identify issues in the operation mechanical equipment, which is crucial for performance and safety equipment. In practical applications, equipment typically faces challenges such as limited sample sizes, high noise levels, complex operating conditions, making it difficult to extract fault features from vibration signals. The introduction attention mechanism has significantly enhanced feature extraction capability neural networks, increasingly being applied task bearings. This paper proposes a bearing method based on multi-stage fusion network. First, GADF used convert one-dimensional time-series signal into an RGB two-dimensional image. Then, global local performed using Swin Transformer Parallelized Patch-Aware Attention, respectively. Finally, Content-Guided Attention employed perform weighted two types features. By integrating mechanisms, improves recognition accuracy. Experimental results demonstrate that proposed outperforms other comparative models terms accuracy, few-shot learning ability, generalization capability, resistance.

Language: Английский

---

Investigation on coaxial pseudo-fault characteristics induced by the outer ring defect in the single-sided axle-box bearing of wheelset in urban rail vehicles

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 28, 2025

An in-depth understanding of vibration characteristics the coaxial pseudo-fault in axle-box bearings installed coaxially on both sides wheelset is essential for distinguishing real fault and bearing condition monitoring. Therefore, a bearing-vehicle-track coupled dynamic model developed, which incorporates an with outer ring defect vehicle-track model. The responses wheelset, considering single-sided defects different widths at vehicle speeds, are obtained through simulation subsequently analyzed. results indicate that effect more pronounced under width 3 mm. amplitude, root mean square (RMS), shock pulse method (SPM) indicators response defective side exceed those healthy side. impulse transmitted to consistently lags behind generated minimum lag time 0.0011 s. frequency components harmonics dispersed decay rapidly. Finally, based amplitude-related features spectral energy dispersion characteristics, criterion identifying proposed using variance (VF) indicator, rationality indicator range demonstrated field test data.

Language: Английский

---

Multi-scale bidirectional transformer network for rolling bearing fault diagnosis

Journal of the Brazilian Society of Mechanical Sciences and Engineering, Journal Year: 2025, Volume and Issue: 47(5)

Published: April 7, 2025

Language: Английский

---

Multi scale convolutional neural network combining BiLSTM and attention mechanism for bearing fault diagnosis under multiple working conditions

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 15, 2025

Language: Английский

---

Fault Diagnosis of Rolling Element Bearing Based on BiTCN-Attention and OCSSA Mechanism

Actuators, Journal Year: 2025, Volume and Issue: 14(5), P. 218 - 218

Published: April 28, 2025

This paper proposes a novel fault diagnosis framework that integrates the Osprey–Cauchy–Sparrow Search Algorithm (OCSSA) optimized Variational Mode Decomposition (VMD) with Bidirectional Temporal Convolutional Network-Attention mechanism (BiTCN-Attention). To address limitations of empirical parameter selection in VMD, OCSSA adaptively optimizes decomposition parameters (penalty factor α and mode number K) through hybrid strategy combines chaotic initialization, Osprey-inspired global search, Cauchy mutation. Subsequently, BiTCN captures bidirectional temporal dependencies from vibration signals, while attention dynamically filters critical features, constructing an end-to-end diagnostic model. Experiments on CWRU dataset demonstrate proposed method achieves average accuracy 99.44% across 10 categories, outperforming state-of-the-art models (e.g., VMD-TCN: 97.5%, CNN-BiLSTM: 84.72%).

Language: Английский

---

A novel feature extraction method of compound faults of bearing based on ITD and information fusion

Noise & Vibration Worldwide, Journal Year: 2025, Volume and Issue: unknown

Published: May 13, 2025

A method combining signal decomposition and information fusion is proposed to solve the difficulty in extracting compound fault features of rolling bearing. Firstly, decomposes homologous signals into sum a series proper rotational components, which are obtained by sensors horizontal vertical directions with intrinsic time scale (ITD). Secondly, autocorrelation noise reduction normalization processing performed for component obtained; weight coefficients adaptively determined according normalized function (AF) components. Thirdly, functions all weighted blended coefficient obtained. Finally, feature frequency bearing extracted power spectrum blended. Equally, failure types bearings judged. To verify effectiveness method, data corresponds different analyzed verified; meanwhile, other methods compared presented method. The result indicates that can be precisely, type judged accurately

Language: Английский

---

Influence of the typical operating conditions of urban rail vehicles on vibration and contact characteristics of the axle-box bearing with an outer ring defect

Journal of Vibration and Control, Journal Year: 2025, Volume and Issue: unknown

Published: May 14, 2025

This paper aims to explore the influence of typical operation conditions variable speeds and different loads on contact force vibration response axle-box bearing with an outer ring defect in urban rail vehicles, thereby providing meaningful guidance for fault diagnosis based signals reliability assessments through under working vehicles. Therefore, a double-row cylindrical roller (DCRB)-vehicle-track coupling dynamic model was established, which includes DCRB complete rigid-flex vehicle-track spatial model. Its feasibility validated bench tests theoretical comparison. It subsequently employed simulate 2 mm width various loads, as well loads. The roller-raceway, properties axle-box, variation tendency stability statistical indicators were analysed. results indicate that changes speed load have greater defective row, is greater, maximum fluctuation difference between two rows being 0.316 kN. root mean square (RMS), amplitude (SRA), peak-to-peak value (PPV) increase monotonically speed. Regarding indicators, shape factor (SF) variance frequency (RVF) are relatively stable. skewness (SV) indicator worst.

Language: Английский

---