Table 1.

Related articles with a focus on smart maintenance in the industry (including power-generation industry).

Reference	Year	Strategy	Methods	Diagnosis	Prediction	Prescription	Area	Contribution
Sikorska et al. [8]	2011	○	●	●	●	○	Industry	A comprehensive review of methods related to RUL. Classification of algorithms and presentation of their strengths and weaknesses to facilitate the selection of the suitable model for the specific business required.
Gao et al. [9,10]	2015	○	●	●	○	○	Industry	Survey of fault-diagnosis and fault-tolerance techniques. Classification of methods as model-based, signal-based and knowledge-based (data-driven).
Sole et al. [11]	2017	◑	●	●	○	○	Industry	An overview focused on the root cause analysis problem, taking particular account of requirements, performance and scalability aspects.
Diez-Olivan et al. [6]	2019	○	○	●	●	●	Industry	A review of applications of data-driven predictive algorithms in the industry within the I4.0 paradigm (categorization into descriptive, predictive and prescriptive analysis).
Carvalho et al. [5]	2019	◑	●	◑	◑	○	Industry	A review of ML methods applied to predictive maintenance. Focuses on methods, devices and data sources used.
Zhang et al. [15]	2019	○	●	◑	◑	○	Industry	Focuses on data-driven PdM methods and their applications.
Saufi et al. [16]	2019	○	●	●	○	○	Rotating machinery	A review of deep learning-based methods for fault detection and diagnosis.
Merkt [17]	2019	●	◑	●	●	○	Industry	A review of data-driven predictive methods highlighting challenges and benefits with indicated areas of possible applications.
Alcacer and Cruz-Machado [18]	2019	◑	○	○	○	●	Manufact-uring	Overview of I4.0 technology applications in terms of enabling opportunities and use in manufacturing environments.
Ngarayana et al. [14]	2019	●	◑	◑	◑	◑	Nuclear Power Plant	A review of models, methods and strategies for optimizing maintenance at a nuclear power plant. A comparison of scientific studies with real applications.
Soualhi et al. [19]	2019	○	●	●	○	○	Industry	An overview of diagnostic methods used for fault isolation and identification. Classification of methods as model-based, data-driven and hybrid.
Cinar et al. [20]	2020	○	●	◑	◑	○	Industry	An overview of ML applications in PdM. Classifies papers based on methods, data sources, devices used in data acquisition, data size and critical findings.
Chao et al. [13]	2020	●	○	◑	◑	◑	Nuclear Power Plant	An overview of AI applications categorized for typical scenarios in a nuclear power plant; addresses the problem of human–machine interaction.
Fausing et al. [12]	2020	◑	●	●	●	○	Thermal Power Plant	A review of PdM articles with a focus on the pumping system in power plants.
Zonta et al. [7]	2020	○	◑	●	●	◑	Industry	A systematic literature review of PdM in the industry. Categorizes methods, standards and applications. Discusses the limitations and challenges of PdM.
this article	2022	●	●	●	●	◑	Energy Industry	An overview of data-driven and experience-based methods improving maintenance. Shows applications of advanced analytics in the energy sector.
○: not studied ◑: mentioned ●: studied