Knowledge transfer in fault diagnosis of rotary machines

Abstract

Data‐driven fault diagnosis has prevailed in machine condition monitoring in the past decades. However, traditional machine‐ and deep‐learning‐based fault diagnosis methods assumed that the source and target data share the same distribution and ignored knowledge transfer in dynamic working environments. In recent years, knowledge transfer approaches have been developed and have shown promising results in intelligent fault diagnosis and health management of rotary machines. This paper presents a comprehensive review of knowledge transfer approaches and their applications in fault diagnosis of rotary machines. A problem‐oriented taxonomy of knowledge transfer in fault diagnosis is proposed. The knowledge transfer paradigms, approaches, and applications are categorised and analysed. Future research challenges and directions are explored from data, modelling, and application perspectives.

Optimised LightGBM-based health condition evaluation method for the functional components in CNC machine tools under strong noise background

“…The first approach involves traditional health evaluation, primarily reliant on expert knowledge or the establishment of physical models grounded in domain expertise [6]. This method is comprehensible through a physical perspective and enjoys the advantage of leveraging lucid physical theories [7,8]. Nonetheless, this technique mandates specialised insights from researchers within the field, and the quality of modelling remarkably governs the evaluation accuracy [9].…”

A novel approach towards parametric assessment of reliability and resilience of high voltage mica‐based insulation systems by statistical analysis of experimental failure data

“…However, the quantitative method that is outlined in this paper delivers a robust statistical method to calculate the probability of failure rates throughout the lifespan of the HV insulation system. In other words, this method covers the grey areas where the status of the machine is not known. The three‐parameter Weibull when combined with Bayesian allows for the consideration of a priori knowledge available for a specific insulation system [22]. The knowledge that is collected through years of experience significantly enriches the accuracy and reasoning of probabilistic models [23, 24].…”

“…ii. The three-parameter Weibull when combined with Bayesian allows for the consideration of a priori knowledge available for a specific insulation system [22]. The knowledge that is collected through years of experience significantly enriches the accuracy and reasoning of probabilistic models [23,24].…”

A framework and prototype system in support of workflow collaboration and knowledge mining for manufacturing value chains

“…Previous studies have discussed collaborative systems in designing [1,[3][4][5][6], editing [7], caring [8], education [9] etc., some of which focus on knowledge-based engineering frameworks such as collaborative knowledge generation in crowdsourcing [9,10], knowledge reasoning [11], knowledge management [12], and others [13][14][15]. However, even if the CSCW system can share information with others in the workgroup to some extent, there is still a lot of personal knowledge that is generated directly or indirectly that is either too crude to be understood by the computer, or ignored by others and therefore not well recorded.…”