Firstly, various commonly used data acquisition methods are introduced and discussed. To fill this gap, this paper provides a review on predictive monitoring of incipient stage faults following its whole program, i.e., from data acquisition to artificial intelligence implementation. There has been a significant amount of literature available however, lack of a systematic review which encapsulate all four technical processes comprehensively.
Over recent years, a significant amount of research work has been undertaken in each of the four processes. A predictive monitoring program generally consists of four technical processes, i.e., data acquisition, pre-processing (denoising process), feature processing, and artificial intelligence. Due to failure of these elements, whole system can lead to complete shutdown. All rotating machines consisting of rotating elements such as gears, bearings etc are considered as the backbone of any plant and condition based maintenance of these elements is at the top priority to keep them available all the time. Predictive maintenance is one of the major tasks in today’s modern industries. A reliable, automatic fault signature from a motor current is thus analyzed using the fusion of a wavelet-based feature extraction technique and a capable knowledge-based efficient artificial intelligence (AI) approach. Comparing machine learning algorithms such as artificial neural network, random forest, fuzzy logic, neuro-fuzzy logic, K-nearest neighbors is performed, and various performance attributes are quantified. FSA uses real-time stator current data in the time and frequency domain from healthy and faulty induction motors to train the various AI-based machine learning classifiers to identify health conditions using wavelets. The design of an AI-based fault signature analyzer (FSA) has been developed in this paper. Recent advances in computational performance and sensor technology concede advanced systems for achieving these goals. Identifying the current signature at its embryonic stage will effectively improve industrial machinery’s downtime and repair costs. Among various defects, early-stage identification of insulation failure in stator winding is of notable demand as it often occurs and accounts for 37% of the overall motor failures.
Automated continuous condition monitoring of industrial electrical machines to identify internal faults has become one of the critical research areas for the past decade.