In manufacturing industry machines and systems become more advanced and complicated. Proper maintenance is crucial to ensure productivity, product quality, on-time delivery, and safe working environment. Recently, the importance of the predictive maintenance has been growing rapidly. Well applied predictive maintenance can be in many cases more cost effective than traditional corrective and preventive approaches to maintenance. Targeting this vibrant field, this paper reviews the literature of Predictive Maintenance (PdM). Published literature is systematically categorised and then methodically reviewed and analysed. Methodology for data acquisition, feature extraction, failure detection and prediction are presented. The connection between Maintenance field and Information Fusion has been highlighted. Statistical analysis based on Elsevier’s Scopus abstract and citation database has been performed. Various emerging trends in the field of Predictive Maintenance are identified to help specifying gaps in the literature and direct research efforts.