Vibration Analysis for Machine Monitoring and Diagnosis: A Systematic Review

Abstract

Untimely machinery breakdown will incur significant losses, especially to the manufacturing company as it affects the production rates. During operation, machines generate vibrations and there are unwanted vibrations that will disrupt the machine system, which results in faults such as imbalance, wear, and misalignment. Thus, vibration analysis has become an effective method to monitor the health and performance of the machine. The vibration signatures of the machines contain important information regarding the machine condition such as the source of failure and its severity. Operators are also provided with an early warning for scheduled maintenance. Numerous approaches for analyzing the vibration data of machinery have been proposed over the years, and each approach has its characteristics, advantages, and disadvantages. This manuscript presents a systematic review of up-to-date vibration analysis for machine monitoring and diagnosis. It involves data acquisition (instrument applied such as analyzer and sensors), feature extraction, and fault recognition techniques using artificial intelligence (AI). Several research questions (RQs) are aimed to be answered in this manuscript. A combination of time domain statistical features and deep learning approaches is expected to be widely applied in the future, where fault features can be automatically extracted from the raw vibration signals. The presence of various sensors and communication devices in the emerging smart machines will present a new and huge challenge in vibration monitoring and diagnosing.

Research and Development of Fault Diagnosis Methods for Liquid Rocket Engines

“…Xu et al [90] used the improved PSO algorithm to optimize the weights of the wavelet neural network (WNN), and established an LRE fault detection model combining the improved PSO algorithm and WNN, the local convergence ability and more accurate fault prediction ability. Wu et al [91] established a fault detection approach using PSO optimized least squares support vector machine (LSSVM), and compared the predicted change value of the detected component obtained by the prediction model with the standard threshold to judge the engine and whether a failure occurs. Li et al [92][93][94] proposed an LRE fault detection approach using the improved PSO optimized BP neural network, and applied the method for the fault detection of the LRE steady-state process.…”

Development of a Reliable Vibration Based Health Indicator for Monitoring the Lubricating Condition of the Toggle Clamping System of a Plastic Injection Molding Machine

“…Time domain is defined as a collection of time-indexed data points collected over a historical time [19]. In practice, time domain signals are generally complex, as they capture a wide range of vibrational responses from other moving components in machine paired with Gaussian noise [20]. This high complexity makes it difficult for the raw signal to be directly used for condition monitoring.…”

Machine Learning Meets Compressed Sensing in Vibration-Based Monitoring

“…Damage detection has a pivotal role in Structural Health Monitoring (SHM) systems as a fundamental means to implement on-condition maintenance. In particular, many novel damage detection procedures are gaining momentum thanks to the recent developments in the Machine Learning (ML) field [ 1 , 2 , 3 , 4 , 5 ]. Indeed, to cope with these continuously evolving requirements, novel Artificial Intelligence (AI) tools have been proposed in the recent literature, which were fostered by the parallel technological advancements in the processing power promoted by the information engineering community.…”