Rotating machines are pivotal to the achievement of core operational objectives within various industries. Recent drives for developing smart systems coupled with the significant advancements in computational technologies have immensely increased the complexity of this group of critical physical industrial assets (PIAs). Vibration-based techniques have contributed significantly towards understanding the failure modes of rotating machines and their associated components. However, the very large data requirements attributable to routine vibration-based fault diagnosis at multiple measurement locations has led to the quest for alternative approaches that possess the capability to reduce faults diagnosis downtime. Initiatives aimed at rationalising vibration-based condition monitoring data in order to just retain information that offer maximum variability includes the combination of coherent composite spectrum (CCS) and principal components analysis (PCA) for rotor-related faults diagnosis. While there is no doubt about the potentials of this approach, especially that it is independent of the number of measurement locations and foundation types, its over-reliance on manual classification made it prone to human subjectivity and lack of repeatability. The current study therefore aims to further enhance existing CCS capability in two facets—(1) exploration of the possibility of automating the process by testing its compatibility with various machine learning techniques (2) incorporating spectrum energy as a novel feature. It was observed that artificial neural networks (ANN) offered the most accurate and consistent classification outcomes under all considered scenarios, which demonstrates immense opportunity for automating the process. The paper describes computational approaches, signal processing parameters and experiments used for generating the analysed vibration data.

The feasibility and usefulness of frequency domain fusion of data from multiple vibration sensors installed on typical industrial rotating machines, based on coherent composite spectrum (CCS) as well as poly-coherent composite spectrum (pCCS) techniques, have been well-iterated by earlier studies. However, all previous endeavours have been limited to rotor faults, thereby raising questions about the proficiency of the approach for classifying faults related to other critical rotating machine components such as gearboxes. Besides the restriction in scope of the founding CCS and pCCS studies on rotor-related faults, their diagnosis approach was manually implemented, which could be unrealistic when faced with routine condition monitoring of multi-component industrial rotating machines, which often entails high-frequency sampling at multiple locations. In order to alleviate these challenges, this paper introduced an automated framework that encompassed feature generation through CCS, data dimensionality reduction through principal component analysis (PCA), and faults classification using artificial neural network (ANN). The outcomes of the automated approach are a set of visualised decision maps representing individually simulated scenarios, which simplifies and illustrates the decision rules of the faults characterisation framework. Additionally, the proposed approach minimises diagnosis-related downtime by allowing asset operators to easily identify anomalies at their incipient stages without necessarily possessing vibration monitoring expertise. Building upon the encouraging results obtained from the preceding part of this approach that was limited to well-known rotor-related faults, the proposed framework was significantly extended to include experimental and open-source gear fault data. The results show that in addition to early established rotor-related faults classification, the approach described here can also effectively and automatically classify gearbox faults, thereby improving the robustness.