In continuous-process systems, failures of rolling-element bearings typically cause accidents, reduced productivity, and production-related financial losses. Therefore, predicting both the lifespan of rolling-element bearings and their replacement time is crucial for preventing machine system failures. Accordingly, numerous studies have reported various machine and deep learning classifiers for predicting the lifespan of bearings. However, these studies did not consider degradation trends of bearings. Thus, this study aimed to develop an algorithm to predict the lifespan of a bearing by considering its degradation trend. A vibration dataset of bearings was obtained at low and high speeds. Using a second-order curve-fitting model, various degradation patterns in the dataset were classified. Appropriate time-domain or frequency-domain feature variables applicable to the design of a classifier were determined according to classified patterns. In addition, the classifier was trained using multiple bidirectional long short-term memories. Finally, the performance of the developed classifier was verified experimentally.

A Continuous Ship Unloader (CSU) is a facility in which multiple buckets rotate to excavate cargo from a ship to land. It is typically designed to have a lifespan of 20 years. However, fatigue damage is likely to occur before the end of its designated lifespan. This study aims to examine the possibility of extending the component"s lifespan by evaluating the remaining useful life of L-holder, a part of CSU, that has been in use for 20 years. Fatigue load history was predicted by measuring the strain with or without strain at the L-holder part requiring periodic replacement. Through tensile and fatigue tests, the remaining life was evaluated when cracks were not present. In addition, the remaining life in the presence of cracks was evaluated through destructive toughness test and fatigue crack propagation test. Life prediction results based on test cycles were obtained. The proposed guidelines are expected to be helpful for preventing CSU accidents.