Abstract
With the trend of Industry 4.0, the global machine tool industry is developing towards smart manufacturing. The ball bearing is a key component of the rotary axis of machine tool, and its functionality is to bear the external load on the axis as well as maintain the center position of the axis. A damaged bearing will result in abnormal vibration and noise, and thus will lead to the damage of the machine and produced workpieces. Therefore, inspection and identification of ball bearing failures is particularly important. This paper discusses the fault signals of ball bearings published by the Society for Machinery Failure Prevention Technology (MFPT) and creates a recognition model for the ball bearing state based on different fault states, and then we adopt two different approaches for feature extraction. The first approach implements Finite Impulse Response Filter (FIR) and Approximate Entropy (ApEn) to extract the signal features. The second approach utilizes the Chen-Lee chaotic system for analysis and takes its chaotic attractor as the feature of the state recognition. The comparison of model recognition accuracy for Back Propagation Neural Network (BPNN), Support Vector Machine (SVM), and K Nearest Neighbor (KNN) was conducted after acquiring the features through the two approaches in this paper. The results of the experiments in this paper show that both of the feature extraction approaches enable the state to be recognized easily. The Chen-Lee chaotic system with BPNN not only reaches 100% identification rate and it has the highest overall efficiency; it takes only 0.054 second to complete the feature extraction for 63 sets of data; this study is able to provide timely and precise solution for the failure of key mechanical components.
Highlights
Ball bearings are carriers for supporting the mechanical rotating body, to reduce the coefficient of friction during rotation and ensure the rotational precision of mechanical components
FIR has several merits: finite long-term output digital signals are subject to the limitation by inputting the digital signals, being easier to optimize than Infinite Impulse Response Filter (IIR) [34], as well as that all the polar coordinates are relatively stable within the unit circle after Z transformation, where the relations between input-output are represented as a difference equation (1) shown as below: K
We aim at the open datum in regard to a ball bearing released by Machinery Failure Prevention
Summary
Ball bearings are carriers for supporting the mechanical rotating body, to reduce the coefficient of friction during rotation and ensure the rotational precision of mechanical components. If the equipped ball bearings are damaged, they may cause abnormal noise during machine operation or even cause the machine to stop operating which will affect the production capacity. The researchers focus on the implementation of malfunction inspection and analysis without stopping the machine operation in order to reduce the possible loss of production cost due to the damage of ball bearings. Lin et al.: Inspection on Ball Bearing Malfunction by Chen-Lee Chaos System transform has difficulty to process in real time due to a large amount of computations; and the efficiency and accuracy of signal pre-process will be the key for technology advancement in this stage. This paper discusses the fault signals of ball bearings published by the Society for Machinery Failure Prevention Technology (MFPT) and adopts two different approaches for feature extraction. The classification of accuracy rate and overall efficiency for the Support Vector Machine (SVM) [29], [30] and K Nearest Neighbor (KNN) [31], [32] are compared for further discussion
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
