Degradation assessment of bearing based on machine learning classification matrix

Abstract

In the broad framework of degradation assessment of bearing, the final objectives of bearing condition monitoring is to evaluate different degradation states and to estimate the quantitative analysis of degree of performance degradation. Machine learning classification matrices have been used to train models based on health data and real time feedback. Diagnostic and prognostic models based on data driven perspective have been used in the prior research work to improve the bearing degradation assessment. Industry 4.0 has required the research in advanced diagnostic and prognostic algorithm to enhance the accuracy of models. A classification model which is based on machine learning classification matrix to assess the degradation of bearing is proposed to improve the accuracy of classification model. Review work demonstrates the comparisons among the available state-of-the-art methods. In the end, unexplored research technical challenges and niches of opportunity for future researchers are discussed.

Comparison of the characteristics of journal bearings determined according to ISO 7902:2020 and obtained by other methods

“…It should be emphasized that in the case of such sensitive machine parts as slide bearings, not only their correct design, but also the proper operation, maintenance and monitoring of the slide bearings are required. [21][22][23][24] The calculation procedures of the bearing design based on the approximate method and hydrodynamic lubrication theory have been presented by Raimondi and Boyd, 25 Rohde and Li, 26 Pinkus 27 and many other more recent books. [28][29][30] The design process usually involves the curve-fitted functions to derive relations of empirical data and enables the steady-state characteristics computation.…”

“…It should be emphasized that in the case of such sensitive machine parts as slide bearings, not only their correct design, but also the proper operation, maintenance and monitoring of the slide bearings are required. 21–24…”

Multi-level health degree analysis of vehicle transmission system based on PSO- Indexed by: BP neural network data fusion

“…Seventekidis [22] studies structural health detection by combining finite element simulation and deep learning methods Jiang [8]proposes a novel framework to fulfill the task of prognostics and health management with a smart sensors, consisting of embedded sensing elements, wireless communication modules and micro-controllers. Kumar [12] proposed a classification model for bearing degradation evaluation based on machine learning classification matrix, which improved the accuracy of the classification model. Yan [25] proposed a health index extraction method, which is better characterize the degree of degradation compared to relying solely on spectral oil data.…”

Effect of Radial Clearance on Ball Bearing’s Dynamics Using a 2-DOF Model

“…rolling-element bearings, gears, shafts, or couplings, that carry the complex load and transfer motion during its operation. Among mentioned elements, bearings demand the most complex manufacturing process including heat-treatment [1,2] and machining [3,4], which has to provide a high quality of rolling surfaces and the best possible bearing's performance [5,6]. The real-time diagnostics of rolling-element bearings is part of the strategy of Industry 4.0, to prevent unexpected damages leading to unscheduled downtime or economical losses.…”