A New Strategy for Bearing Health Assessment with a Dynamic Interval Prediction Model

Abstract

Bearing is the critical basic component of rotating machinery and its remaining life prediction is very important for mechanical equipment’s smooth and healthy operation. However, fast and accurate bearing life prediction has always been a difficult point in industry and academia. This paper proposes a new strategy for bearing health assessment based on a model-driven dynamic interval prediction model. Firstly, the mapping proportion algorithm is used to determine whether the measured data are in the degradation stage. After finding the starting point of prediction, the improved annealing algorithm is used to determine the shortest data interval that can be used for accurate prediction. Then, based on the bearing degradation curve and the information fusion inverse health index, the health index is obtained from 36 general indexes in the time domain and frequency domain through screening, fusion, and inversion. Finally, the state space equation is constructed based on the Paris-DSSM formula and the particle filter is used to iterate the state space equation parameters with the minimum interval data to construct the life prediction model. The proposed method is verified by XJTU-SY rolling bearing life data. The results show that the prediction accuracy of the proposed strategy for the remaining life of the bearing can reach more than 90%. It is verified that the improved simulated annealing algorithm selects limited interval data, reconstructs health indicators based on bearing degradation curve and information fusion, and updates the Paris-DSSM state space equation through the particle filter algorithm. The bearing life prediction model constructed on this basis is accurate and effective.

Research on online anomaly detection methods for bearing degradation

“…During the whole life cycle of bearings, various factors such as harsh working environment, external interference and performance degradation may lead to abnormal vibration signals collected, so the monitoring of vibration data is of great significance for the online abnormal detection of bearings [25].The health stage of a bearing constitutes 80%-90% of its entire lifespan [2,26]. During the health stage, the vibration data generally exhibits a long-term, small, and stable fluctuation trend.…”

“…Therefore, research on bearing anomaly detection is essential. However, the performance of bearings is not constant throughout the entire industrial operation process [2]. With the accumulation of operating time, the performance of bearings gradually degrades.…”

Health Management of Bearings Using Adaptive Parametric VMD and Flying Squirrel Search Algorithms to Optimize SVM

“…SSA is used to optimize the decomposition level k and penalty factor α in VMD, where the value range of k and α is [2,10], [200,4000], the population size is set to 30, the maximum iteration number is set to 40, and the optimal value of vibration signal samples is tested for 5 times. VMD initialization parameters, the convex function optimization parameter τ is 0, the first center frequency update parameter DC is 0, the center frequency initialization parameter init is 1, and the precision parameter ε is 10 Genetic Algorithm (GA) is used to search for the optimal solution by simulating evolutionary selection, hybridization, variation, etc., has a good effect on dealing with complex combination multi-objective problems.…”

“…As a crucial component of rotating mechanical equipment, working in a long-term operating state, there will be a tendency to degradation, which has a significant impact on the overall performance of the mechanical system [1,2]. Consequently, the health management of bearings directly impacts equipment performance, service life, production capacity, and operational efficiency of the entire manufacturing system.…”

Online Condition Monitoring of Industrial Loads Using AutoGMM and Decision Trees

“…CM approaches can be divided into two basic categories: physics-based methodologies and data-driven methodologies [1,9]. In order to identify the corresponding defects, physicsbased approaches exploit explicit mathematical modeling and machinery/equipment specifications [10,11]. For instance, the estimation of parameters of the mathematical model of electrical motors can be useful to detect faults and monitor the health state [12,13].…”