Latest innovations in the field of condition-based maintenance of rotatory machinery: a review

Abstract

Health monitoring in rotatory machinery is a process of developing a mechanism to determine its state of deterioration. It involves analysing the presence of damage, locating the fault, determining the severity of the problem, and calculating the amount of time that the machine can still be used effectively by making use of signal processing methods. The journey started to repair when the machine fails and progressed to the modern era, which involves the use of advanced sensors to capture data and conduct on-line signal processing methods to extract relevant features. By seamlessly integrating advanced smart sensing, data collection, and intelligent algorithms, modern technologies have transformed the landscape of condition-based maintenance for rotary machinery, bridging the gap between fundamental understanding and practical engineering applications. In this review paper, first, the roadmap of the condition-based maintenance (CBM) journey for rotary machinery is briefly introduced. Then, CBM task techniques are reviewed in the context of manual identification of defects, applying artificial intelligence (AI) model to identify the defect in the rotary machinery, and AI to carry out defect prognosis and determine the remaining useful life. Finally, the challenges, and issues of signal processing methods to detect faults in rotary machinery, and remedies to overcome such challenges are deeply discussed and future research directions are identified to ensure safe operation for rotary machinery.

Condition Monitoring of Pneumatic Drive Systems Based on the AI Method Feed-Forward Backpropagation Neural Network

“…Mincost is the standard loss function, which is only suitable if the classification results are posterior probabilities (as in this case). It calculates the weighted average of the minimum expected misclassification cost losses, according to Equation (2).…”

“…Maintenance is crucial for manufacturers and operators, as the condition of a plant and machinery must be checked regularly to maintain their performance: only in this way production can meet expectations in terms of quality and economy, and failures during operation do not increase costs and reduce competitiveness. For this reason, diagnostic techniques are constantly evolving in terms of hardware (sensors, networks, processing units, data storage) and software (algorithms for data extraction, processing, and analysis) [ 1 , 2 ]. Since maintenance based on replacing the faulty component does not prevent failures in operation, which in the worst case can be harmful to the equipment or machine, more efficient and economical approaches have long been established [ 3 ].…”

DDAGCN: an unsupervised cross-domain identification method for tie rod bolt loosening in a rod-fastening rotor system under different working conditions

“…At present, the general intelligent diagnosis process mainly includes three parts [31][32][33]: data collection and preprocessing, feature extraction, and model training and testing. Thus far, most of the research methods have mainly focused on feature extraction; especially with the quick advancement of deep learning, feature extraction methods based on deep learning have produced an endless stream of studies [34].…”