Skip to content
Log in
Sponsored Artificial Intelligence: A Modern Approach, Global Edition Artificial Intelligence: A Modern Approach, Global Edition Amazon

Similar papers

Open access 2019

Vibration Analysis of High-Speed Rotating Machinery

The saving grace of industrial systems in the present day is high-speed rotating machinery which encompasses turbines, compressors, generators and aerospace propulsion units. The successful performance of such machines largely remains the responsibility of efficient condition monitoring and fault diagnosis methods. Vibration analysis has become one of the most potent and popular in the number of these techniques. A cohesive exploration of the vibration nature of high-speed rotating machinery with its focus on signal acquisition, signal processing, feature extraction, and fault classification techniques is discussed in this paper. The process combines both experimental measurements, mathematical modeling and using advanced signal processing to detect typical mechanical faults including imbalance, misalignment, bearing flaws, shaft cracks and gear mesh anomaly. An elaborate experimental design is crafted based on an accelerometer, data collection apparatus, and spectral analysis apparatus to record the signature of vibrations at varying operation conditions. The time-domain analysis, frequency-domain abasys and time-frequency-domain analysis are used to extract diagnostic features that are usually significant. Short-Time Fourier Transform (STFT), Fast Fourier Transform (FFT), and Wavelet Transform (WT) techniques are adopted to make a fault more detectable. In addition, automated fault recognition is performed with the help of statistical indicators and classifiers based on machine learning. The findings indicate that vibration-based diagnostics have demonstrated high relative accuracy of early fault detection and reliability of the system. Comparative study shows that the hybrid signal processing solutions are better than the conventional methods in complicated operational scenarios. The given methodology has offered a systematic framework of being predictive in maintenance developed in industrial rotating machines. The results of this study help in making the operations safe, minimizing downtime and minimizing costs of maintenance. The research can be used by the researchers and practitioners who wish to adopt modern vibration monitoring systems in the rotating machines that operate at high speed.

Z. Ahmed · 0 citations
Review Open access Jul 2026

Enhanced Rotating Machinery Fault Diagnosis Using Holo-Hilbert Spectrum Analysis and Machine Learning

Reliable fault diagnosis in rotating machinery is challenging due to the nonlinear and non-stationary nature of vibration signals. Although time–frequency analysis is widely used, it cannot capture the cross-scale coupling between amplitude-modulated (AM) and frequency-modulated (FM) components that carry essential diagnostic information. This study applies Holo-Hilbert Spectrum Analysis (HHSA) to extract amplitude–frequency modulation features and integrates them with six machine learning classifiers to identify four fault conditions. Random Forest, K-Nearest Neighbors, and Logistic Regression achieve accuracies of up to 99.95%, yielding higher accuracy than Fast Fourier Transform-based features. The proposed framework employs an HHSA-based feature extraction pipeline that effectively captures AM–FM coupling in nonlinear vibration signals. It also provides higher discriminative capability than traditional spectral approaches and maintains robustness across multiple classifiers. This method offers high diagnostic accuracy and strong potential for industrial predictive maintenance. Future work will focus on improving computational efficiency and evaluating the framework under more diverse and realistic operating conditions. Received: 10 September 2025 | Revised: 20 April 2026 | Accepted: 10 June 2026 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The VBL-VA001 datasets that support the findings of this study are openly available at https://doi.org/10.1007/s42417-023-00959-9, reference number [44]. Author Contribution Statement Van-Trung Nguyen: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data curation, Writing - original draft, Writing - review & editing, Visualization. Ba-Tan Le: Investigation, Data curation, Writing - original draft, Writing - review & editing. Van-Phuong Dao: Methodology, Validation, Writing - review & editing.

Van-Trung Nguyen, Ba-Tan Le, van-Phuong Dao · 0 citations
Open access Aug 2026

A robust multi-class bearing fault diagnosis framework using envelope analysis, cepstrum prewhitening and machine learning

This paper presents a systematic framework for real-time fault-type identification in rolling element bearings using vibration signal analysis. The Case Western Reserve University bearing dataset is employed as the primary data source, comprising vibration signals recorded under different load conditions (0–3 HP). Initially, Envelope Analysis (EA) is applied to extract fault-related characteristic frequencies. While computationally efficient, EA successfully identifies fault features in 66.67% of the signals but shows limitations under noisy and spectrally smeared conditions. To address this, Cepstrum Prewhitening Analysis (CPA) is selectively applied to unresolved signals, achieving a 75% detection success in these cases and improving the overall detection rate to 91.67%. Thereafter, 36 time-domain, frequency-domain, and EA-CPA based features were extracted from segmented vibration signals. A sequential feature optimization strategy comprising variance threshold filtering, correlation analysis, Z-score normalization, ANOVA F-test feature ranking, and Recursive Feature Elimination reduced the feature set to the 10 most discriminative features. To eliminate sample- and group-level information leakage, a leakage-free Nested GroupKFold framework was developed, in which preprocessing, feature selection, and hyperparameter optimization was performed exclusively within the training folds using GridSearchCV. Six machine learning classifiers, namely Random Forest, XGBoost, LightGBM, Support Vector Machine, K-Nearest Neighbors, and Logistic Regression, were comparatively evaluated. XGBoost achieved the highest mean classification accuracy of 97.62%, while RF attained a comparable accuracy of 97.51% with lower fold-to-fold variation, indicating superior robustness and stability. Consequently, RF was selected for independent cross-condition validation, in which it was trained solely on the 0 HP operating condition and evaluated on the unseen 1 HP, 2 HP, and 3 HP datasets, demonstrating strong generalization across varying load conditions. Feature importance analysis further confirmed that the characteristic bearing defect frequencies (BPFO, BPFI, and BSF) are the dominant contributors to classification performance. The proposed framework provides an effective balance between diagnostic accuracy, robustness, interpretability, and computational efficiency, making it a promising solution for intelligent condition monitoring and predictive maintenance of rotating machinery.

Rohit Mishra · 0 citations
Jul 2026

Machine learning-based fault detection in low-speed bearings using a multi-environmental dataset

The near-perfect linear separability indicates that the dataset’s binary, controlled-laboratory labelling rather than intrinsic bearing-degradation physics drives the clean classification, and validation on 500–1000 or more samples with progressive-degradation labelling is essential before any operational claim can be supported.

P. Pugazhendi, Vinoth Vishwanathan, Aadil Arshad Ferhath et al. · 0 citations
Conference Jul 2026

Real-Time Vibration Detection and Signal Analysis of Machines

This work is a condition-based maintenance low-cost real-time vibration monitoring system of industrial machines based on the ESP32 microcontroller and MPU6050 triaxial accelerometer. The axis-wise and overall RMS vibration amplitude is calculated in the system by time domain processing, which offsets them based on a specified threshold that is installed in MATLAB and which is also embedded in the profile parameters per the requirements of vibration severity. The FFT-based real-time spectral analysis is used to detect the vibration frequency components that are predominant in mechanical faults. The machine condition is automatically determined to be safe, warning or dangerous based on quantitative factors such as mean RMS vibration and danger ratio based on time. Multimachine experimental results record values of RMS vibration between 0.02 g and 0.78 g and a predominant low-frequency vibration signal between 0.3 and 3 Hz. The proposed system was implemented with classification accuracy of 91.67%, analysis latency of less than 100ms. The entire self-sacrificing system has a cost of less than 15 USD, making it fit the limited resource-based industrial settings.

Rachana Naik, Raghavendra Devaraddi, Vijet Kutte et al. · 0 citations
Open access Jul 2026

Condition-based monitoring of HCCI engines utilizing vibration signals

Marine transportation moves approximately 80% of the world’s cargo volume, playing a vital role in global logistics. Ever-increasing environmental challenges and fuel economy concerns demand efficient, low-emission engine technologies. Homogeneous charge compression ignition (HCCI) offers improved thermal efficiency at minimum engine-out emissions, but maintaining combustion stability across varying operating conditions limits its widespread adoption. Established in-cylinder pressure-based control systems perform reliably when combustion phasing variations remain small but lack responsiveness under larger deviations, limiting robust real-time combustion state detection and correction. This study presents a vibration-based sensing and classification framework for detecting combustion states in an HCCI engine. Vibration signals recorded from a single-cylinder HCCI research engine were processed to extract a compact set of time- and frequency-domain features, which were used to train supervised classification models based on combustion phasing (CA50). Combustion states were categorized as Normal, Late, or Very Late Combustion. Six machine learning models were evaluated: K-nearest neighbors (KNN), support vector machines (SVM), Artificial neural networks (ANN), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and a convolutional neural network (CNN) as a deep learning benchmark. All models demonstrated high accuracy and robustness, achieving F1-scores exceeding 98% for the Normal and Very Late Combustion classes. The ANN achieved the highest test accuracy of 98.36%, outperforming the CNN benchmark, particularly for the challenging Late Combustion class, demonstrating the effectiveness of the physically informed feature-based approach. The performance for the Late Combustion class was slightly lower, but the method remains promising for real-time applications due to its minimal computational overhead.

Abolfazl Hasanzadeh Shadiani, Amir-Hossein Nasajian Moghaddam, A. Shamekhi et al. · 0 citations