“…The data‐driven approach establishes the causal relationships between cause, symptom, and fault to predict the fault (Jun & Kim, 2017; Sahu & Palei, 2020b). Looking at the importance of fault diagnosis, its applications have been extended from medical sciences to engineering by researchers for wide variety of industrial machines/systems: air‐conditioning equipment (Mirnaghi & Haghighat, 2020), rotating machine (Brito et al, 2022; Liu, Yang, et al, 2018; Nath et al, 2021), bearing fault diagnosis (Cerrada et al, 2018; Zhang, Zhang, et al, 2019), induction motor (Kumar & Hati, 2020), dragline (Sahu & Palei, 2020a; Sahu & Palei, 2020b; Sahu & Palei, 2022), thermal power plant (Ali & Mahdi, 2014; Ricks & Mengshoel, 2014), steam turbine (Ajami & Daneshvar, 2012; Karlsson et al, 2008; Salahshoor et al, 2011), and nuclear power plant (Ayodeji et al, 2018; Jianping & Jiang, 2015; Lu & Upadhyaya, 2005; Sihombing & Torbol, 2018; Wang, Xia, et al, 2021; Wu et al, 2018; You et al, 2021). The fault diagnosis of heavy industrial machinery through DDFD approaches are demonstrated in past studies using Bayesian network (BN) (Sahu & Palei, 2020b), artificial neural network (ANN) (Karlsson et al, 2008; Sahu & Palei, 2020a), fault tree (Gupta et al, 2006; Sihombing & Torbol, 2018), fuzzy inference (Salahshoor et al, 2011), principal component analysis (PCA) (Bakdi et al, 2019; Lu & Upadhyaya, 2005), independent component analysis (Ajami & Daneshvar, 2012), support vector machine (SVM) (Dindarloo & Siami‐Irdemoosa, 2017; Jung, 2019), hidden Markov model (HMM) (Fan et al, 2019), and deep learning (Li, Yao, et al, 2021; Mushtaq et al, 2021; Zhu et al, 2023).…”