Vibration Analysis for Machine Monitoring and Diagnosis: A Systematic Review

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.

Unsupervised Detection of Anomalous Sound for Machine Condition Monitoring using Fully Connected U-Net

Anomaly detection in the sound from machines is an important task in machine monitoring. An autoencoder architecture based on the reconstruction error using a log-Mel spectrogram feature is a conventional approach for this domain. However, because of the non-stationary nature of some sounds from the target machine, such a conventional approach does not perform well in those circumstances. In this paper, we propose a novel approach regarding the choice of used features and a new auto-encoder architecture. We created the Mixed Feature, which is a mixture of different sound representations, and a new deep learning method called Fully-Connected U-Net, a form of autoencoder architecture. With experiments on the same dataset as the baseline system, using the same architecture for all types of machines, the experimental results showed that our methods outperformed the baseline system in terms of the AUC and pAUC evaluation metrics. The optimized model achieved 83.38% AUC and 64.51% pAUC on average overall machine types on the developed dataset and outperformed the published baseline by 13.43% AUC and 8.13% pAUC.

Multiple Sound Sensors And Fusion In Modern CNN-Based Machine State Prediction

In the new era of manufacturing with Industry 4.0, Smart Manufacturing (SM) is growing in popularity as a potential for the factory of the future. A critical component of SM is effective machine monitoring. Legacy machines indirect monitoring using Internet of Things (IoT) sensors are preferred instead of modifying hardware directly. Machine tools are composed of rotary components, resulting in machine tools emitting acoustic and vibratory signals. However, sound data cannot easily function as a direct representation for machine status due to its noise, variable time course, and irregular sampling. In this paper, we attempt to bridge this gap through machine learning techniques and auditory monitoring of auxiliary components (i.e., coolant, chip conveyor, and mist collector) as well as the main spindle running state of machine tools. Multi-label classification and Convolutional Neural Network (CNN) were utilized to train models for monitoring machine tools from the sound features. An external microphone and three internal sound sensors were attached to both mill and lathe machines. As a sound feature, Mel-frequency cepstrum (MFCC) features were extracted. The classification task performance was compared between each sensor location and early sensor fusion. The results showed that the sensor fusion approach resulted in the highest F1 score on both machine system.

Evaluation procedure for blowing machine monitoring and predicting bearing SKFNU6322 failure by power spectral density

This work shows the results of the comparative study of characteristic frequencies in terms of Power Spectral Density (PSD) or RMS generated by a blower unit and the SKFNU322 bearing. Data is collected following ISO 10816, using Emonitor software and with speed values in RMS to avoid high and low frequency signal masking. Bearing failure is the main cause of operational shutdown in industrial sites. The difficulty of prediction is the type of breakage and the high number of variables involved. Monitoring and analysing all the variables of the SKFNU322 bearing and those of machine operation for 15 years allowed to develop a new predictive maintenance protocol. This method makes it possible to reduce from 6 control points to one, and to determine which of the 42 variables is the most incidental in the correct operation, so equipment performance and efficiency is improved, contributing to increased economic profitability. The tests were carried out on a 500 kW unit of power and It was shown that the rotation of the equipment itself caused the most generating variable of vibrational energy.

A NEW SIMPLE, FLEXIBLE AND LOW-COST MACHINE MONITORING SYSTEM

The industry 4.0 revolution provides the machines with a sensory and communicational capacity, which allows them to monitor and collect large amounts of information. This kind of data have an impact on planning, maintenance, and management of production, enabling real time reaction, efficiency increase, and the development of predictive and process improvement models. The most recent machines are prepared to communicate with the existing monitoring systems, however, many (around 60%) do not. The objective of this work is to present the proposal of a system for remote monitoring of equipment in real time that meets the requirements of low cost, simplicity, and flexibility. The system monitors the equipment in a simple and agile way, regardless of its sophistication, installation constraints and company resources. A prototype of a system was developed and tested both laboratory conditions and a productive environment. The proposed architecture of the system comprises of a sensor that transmits the machine’s signal wirelessly to a gateway which is responsible of collecting all surrounding signals and send it to the cloud. During the testing and assessment of the tools, the results validated the developed prototype. As main result, the proposed solution offers to the industrial market a new low-cost monitoring system based in mature and tested technology laid upon flexible and scalable solutions. Industry 4.0, Machine Monitoring, Beacon, Bluetooth BLE, Remote Monitoring, Low Cost, SME’s, b-Remote