Recent advancements of signal processing and artificial intelligence in the fault detection of rolling element bearings: a review

Abstract

A rolling element bearing is a common component in household and industrial machines. Even a minor fault in this section has a negative impact on the machinery's overall operation. As a result, the industry suffers significant financial losses, and this damage can potentially result in catastrophic failures. Therefore, even a little fault in the rolling element bearings must be recognized and remedied as soon as possible. Many ways for detecting REB defects have been created in recent years, and new methods are being introduced on a daily basis. This article will provide a summary of such methods, with a focus on vibration analysis techniques. The newest advancements in this field will be recognizable to readers of this article. Anyone interested in defect diagnostics of rolling element bearings can utilize this material.

Research progress on bearing fault diagnosis with signal processing methods for rolling element bearings

“…The wavelet transform is popular due to its adaptability, computational advantages, and ability to be localized in both time and scale. Anwarsha et al 47 published a survey on the advancements of different signal processing methods as well as artificial intelligent methods for the fault diagnosis of rolling element bearings. The authors have clearly narrated the different methods and their major findings with methodology.…”

A Comparative Study and Improved Bearing Fault Classifier Using Raw Vibration Data Under Limited Training Samples

“…Mainstream data acquisition of bearing information, in the form of vibration, is performed during FDD, although other parameters such as motor current, acoustic emission, temperature, and oil analysis can be used to evaluate the bearing conditions [3], [8]. In general, an accelerometer is placed in close proximity to the REB, and raw vibration data in the time series of the interested oscillatory motion body is recorded [1]. With the advancement of computational resources, Artificial Intelligence (AI) is utilized in FDD, either replacing or assisting maintenance professionals [9], [10].…”

“…Raw vibration data typically undergoes signal processing to yield useful or visually presentable forms [1], [3] as illustrated in Table 1. These forms are mainly categorized into three domains: Time, Frequency, and Time-Frequency, where unwanted signals or noise are filtered [10].…”

“…Bearings are commonly used in rotating machinery such as electrical motors, pumps, engines, and fans. They function as crucial components, enabling rotational motion by reducing friction loss, subsequently improving energy consumption, preventing overheating, and minimizing wear and tear effects [1], [2]. Among the many types of bearings, Rolling Element Bearings (REBs) are considerably common, consisting of four major elements: outer race, inner race, cage and ball [3], [4].…”

Highly Reliable Multicomponent MEMS Sensor for Predictive Maintenance Management of Rolling Bearings

“…Nowadays, the management of monitoring and control for early fault diagnosis in equipment and industrial production processes is enormously enhanced, mainly thanks to the development of Machine Learning (ML) [ 1 , 2 , 3 ], Deep Learning (DL) [ 4 , 5 ] and Artificial Intelligence (AI) [ 6 , 7 ]. The possibility to manage huge data flows, in real time, from extensive sensors and multi-sensors networks [ 8 ], allows for monitoring the proper functioning of systems and sub-systems in detail [ 9 , 10 ], early identification of possible malfunctions [ 11 ], precisely localizing failures and planning proper decision making for targeted and timely intervention actions [ 12 ].…”