This study builds upon previous research that utilised a vibration-based machine learning (VML) approach for diagnosing rotor-related faults in rotating machinery. The original method used artificial neural networks (ANN) to classify rotor-related faults based on optimised vibration parameters from the time and frequency domains. This study expands the application of this vibration-based machine learning approach to include the anti-friction bearing faults in addition to the rotor faults. The earlier suggested vibration-based parameters, both in time and frequency domains, are further revised to accommodate bearing-related defects. The study utilises the measured vibration data from a laboratory-scale rotating test rig with different experimentally simulated faults in the rotor and bearings. The proposed VML model is developed for both rotor and bearing defects at a rotor speed that is above the first critical speed. To gauge the robustness of the proposed VML model, it is further tested at two different rotating speeds, one below the first critical speed and the other above the second critical speed. The paper presents the methodology, the rig and measured vibration data, the optimised parameters, and the findings.

This study presents an efficient vibration-based fault detection method for rotating machines utilising the poly-coherent composite spectrum (pCCS) and machine learning techniques. pCCS combines vibration measurements from multiple bearing locations into a single spectrum, retaining amplitude and phase information while reducing background noise. The use of pCCS significantly reduces the number of extracted parameters in the frequency domain compared to using individual spectra at each measurement location. This reduction in parameters is crucial, especially for large industrial rotating machines, as processing and analysing extensive datasets demand significant computational resources, increasing the time and cost of fault detection. An artificial neural network (ANN)-based machine learning model is then employed for fault detection using these reduced extracted parameters. The methodology is developed and validated on an experimental rotating machine at three different speeds: below the first critical speed, between the first and second critical speeds, and above the second critical speed. This range of speeds represents the diverse dynamic conditions commonly encountered in industrial settings. This study examines both healthy machine conditions and various simulated fault conditions, including misalignment, rotor-to-stator rub, shaft cracks, and bearing faults. By combining the pCCS technique with machine learning, this study enhances the reliability, efficiency, and practical applicability of fault detection in rotating machines under varying dynamic conditions and different machine conditions.

Purpose: In vibration-based condition monitoring of rotating machinery, machine learning (ML) models have demonstrated significant diagnostic capabilities; however, their efficacy is fundamentally constrained by the selection and quality of input parameters. Current literature highlights a critical limitation: the absence of a unified parametric framework, with researchers consistently employing different vibration parameters and signal processing techniques for individual machine configurations. This inconsistency creates implementation challenges for industrial applications, where standardised methodologies are essential for reliable diagnostics across diverse mechanical systems. Method: This study addresses this fundamental gap by proposing a standardised set of vibration parameters derived from poly-Coherent Composite Spectrum (pCCS) analysis that effectively captures fault signatures across different rotating machine configurations while significantly reducing computational overhead. The methodology integrates carefully selected time-domain parameters with frequency-domain parameters to comprehensively characterise rotor and bearing faults. Result: Experimental validation is conducted on two distinctly different test rigs—a multi-rotor system operating across different speed regimes and a bearing configuration operating at three different speeds—representing completely different machine dynamics. Despite these substantial differences in mechanical configuration, the artificial neural network trained on these standardised parameters accurately classified multiple fault conditions (healthy states, misalignment, unbalance, shaft cracks, rotor-stator rub, and bearing faults) with near-perfect accuracy across all tested speeds and configurations. Conclusion: The results demonstrate that the proposed and properly selected vibration parameters based on rotordynamic principles can serve as standardised diagnostic features applicable to any rotating machine, offering a significant advancement toward unified condition monitoring frameworks for industrial implementation.

In any industry, it is the requirement to know whether the machine is healthy or not to operate machine further. If the machine is not healthy then what is the fault in the machine and then finally its location. The paper is proposing a 3-steps methodology for the machine fault diagnosis to meet the industrial requirements to aid the maintenance activity. The Step-1 identifies whether machine is healthy or faulty, then Step-2 detect the type of defect and finally its location in Step-3. This method is extended further from the earlier study on the 2-Steps method for the rotor defects only to the 3-Steps methodology to both rotor and bearing defects. The method uses the optimised vibration parameters and a simple Artificial Neural Network (ANN)-based Machine Learning (ML) model from the earlier studies. The model is initially developed, tested and validated on an experimental rotating rig operating at a speed above 1st critical speed. The proposed method and model are then further validated at 2 different operating speeds, one below 1st critical speed and other above 2nd critical speeds. The machine dynamics are expected to be significantly different at these speeds. This highlights the robustness of the proposed 3-Steps method. Conflict of Interest Statement The authors declare no conflicts of interest.

In rotating machines, any faults in anti-friction bearings occurring during operation can lead to failures that are unacceptable due to considerable downtime losses and maintenance costs. Hence, early fault detection is essential, and different vibration-based methods (VBMs) are explored to recognise incipient fault signatures. Based on rotordynamics, if a bearing defect causes metal-to-metal (MtM) impacts during shaft rotation, the impacts excite high-frequency resonance responses of the bearing assembly. The defect-related frequencies are modulated with the resonance responses and rely on signal demodulation for fault detection. However, the current study highlights that the bearing fault/faults may not be detected if the defect in a bearing is not causing MtM impacts nor exciting the high-frequency resonance of the bearing assembly. In a roller bearing, a localised defect may maintain persistent contact between rolling elements and raceways, thereby preventing the occurrence of impulse vibration responses. Due to contact persistence, such defects may not generate impact and may not be detected by existing VBMs, and the bearing could behave as healthy. This paper investigates such specific cases by exploring the relationship between roller-bearing defect characteristics and their potential to generate impact loads during operation. Using an experimental bearing rig, different roller and inner-race defects are presented while their fault characteristic frequencies remain undetected by the envelope analysis, fast Kurtogram, cyclic spectral coherence, and tensor decomposition methods. This study highlights the significance of both the dimension and location of defects within bearings on their detectability based on the rotordynamics concept. Further, simple roller-beam experiments are carried out to visualise and validate the reliability of the experimental observations made on the roller bearing dynamics.