Condition-Based Monitoring and Maintenance: State of the Art Review

Manufacturing firms face great pressure to reduce downtime as well as maintenance costs. Condition-based maintenance (CBM) can be used to effectively manage operations and maintenance by monitoring detailed machine health information. CBM policies and the development of the mathematical models have been growing recently. This paper provides a review of the theoretical and practical development in the field of condition-based maintenance and its current advancements. Standard CBM platform could make it effective and efficient in implementation and performance improvement.

Non-Invasive Inspections: A Review on Methods and Tools

Non-Invasive Inspection (NII) has become a fundamental tool in modern industrial maintenance strategies. Remote and online inspection features keep operators fully aware of the health of industrial assets whilst saving money, lives, production and the environment. This paper conducted crucial research to identify suitable sensing techniques for machine health diagnosis in an NII manner, mainly to detect machine shaft misalignment and gearbox tooth damage for different types of machines, even those installed in a hostile environment, using literature on several sensing tools and techniques. The researched tools are critically reviewed based on the published literature. However, in the absence of a formal definition of NII in the existing literature, we have categorised NII tools and methods into two distinct categories. Later, we describe the use of these tools as contact-based, such as vibration, alternative current (AC), voltage and flux analysis, and non-contact-based, such as laser, imaging, acoustic, thermographic and radar, under each category in detail. The unaddressed issues and challenges are discussed at the end of the paper. The conclusions suggest that one cannot single out an NII technique or method to perform health diagnostics for every machine efficiently. There are limitations with all of the reviewed tools and methods, but good results possible if the machine operational requirements and maintenance needs are considered. It has been noted that the sensors based on radar principles are particularly effective when monitoring assets, but further comprehensive research is required to explore the full potential of these sensors in the context of the NII of machine health. Hence it was identified that the radar sensing technique has excellent features, although it has not been comprehensively employed in machine health diagnosis.

Experimental Study of the Effect of Misalignment on Rolling Element Bearing

Any single machine rotary component in the process could result in downtime costs. It is necessary to monitor the overall machine health while it is in use. Bearing failure is one of the primary causes of machine breakdown in industry at high and low speeds. A vibration signature evaluation has historically determined misalignments in shafting systems. These misalignments are also responsible for the bearing increase in temperature. The purpose of this work is to undertake a comparative study to obtain the reliability of the effect of the amount of misalignment on bearing by using thermography measurement. An experimental study was performed in this paper to indicate the existence of machine misalignment at an early stage by measuring the bearing temperature using a thermal imaging camera. The effects of load, velocity, and misalignment on the bearings and their temperature increase have been investigated. The test bench's rolling-element bearing is an NTN UCP213-208 pillow block bearing. It has been observed that by tracking the change of temperature in bearings could lead to misalignment detection and the effect of the amount of misalignment on it.

Machine Health Surveillance System by Using Deep Learning Sparse Autoencoder

Deep learning is a rapidly growing research area having state of art achievement in various applications including but not limited to speech recognition, object recognition, machine translation, and image segmentation. In the current modern industrial manufacturing system, Machine Health Surveillance System (MHSS) is achieving increasing popularity because of the widespread availability of low cost sensors internet connectivity. Deep learning architecture gives useful tools to analyze and process these vast amounts of machinery data. In this paper, we review the latest deep learning techniques and their variant used for MHSS. We used Gearbox Fault Diagnosis dataset in this paper that contains the sets of vibration attributes recorded by SpectraQuest’s Gearbox Fault Diagnostics Simulator. In addition, the authors used the variant of auto encoders for feature extraction to achieve higher accuracy in machine health surveillance. The results showed that the bagging ensemble classifier based on voting techniques achieved 99% accuracy.

Study on the Digital Intelligent Diagnosis of Miniature Machine Tools

Several industries are currently focusing on smart technologies, high customization, and the integration of solutions. This study focuses on the intelligent diagnosis of digital small machine tools. Furthermore, the main technology processes and cases for smart manufacturing for machine tool applications are introduced. Owing to the requirements of automated processing to determine the quality of a process in advance, the health status of a machine should be monitored in real time, and machine abnormalities should be detected periodically. In this study, we captured the real-time signals of temperature, spindle current, and the vibration of three small five-axis machine tools. Moreover, we used a principal component analysis to diagnose and compare the health status of the spindles and machines. We developed a miniature machine tool health monitoring application to avoid time delays and loss from damage, and used the application to monitor the machine health online under an actual application. Therefore, the technology can also be used in an online diagnosis of machine tools through modeling technology, allowing the user to monitor trends in the machine health. This research provides a feasible method for monitoring machine health. We believe that the intelligent functions of machine tools will continue to increase in the future.

IIoT Machine Health Monitoring Models for Education and Training

IoT, IIoT and Industry 4.0 technologies are leading the way for digital transformation in manufacturing, healthcare, transportation, energy, retail, cities, supply chain, agriculture, buildings, and other sectors. Machine health monitoring and predictive maintenance of rotating machines is an innovative IIoT use case in the manufacturing and energy sectors. This chapter covers how machine health monitoring can be implemented using advanced sensor technology as a basis for predictive maintenance in rotating devices. It also covers how sensor data can be collected from the devices at the edge, preprocessed in a microcontroller/edge node, and sent to the cloud or local server for advanced data intelligence. In addition, this chapter describes the design and operation of three innovative models for education and training supporting the accelerated adoption of these technologies in industry sectors.

Big Data Quantitative Risk Analysis Method for Machine Health Indicator Prediction

Various data-driven methods have been applied to predict machine health indicators especially in the field of prognostics. Machine health indicators reveal the condition of equipment and/or its components including bearings by monitoring their operation data such as frequency vibration. To aid the prediction of the machine health indicators, this study applies the BDQRA method to monitor the health of bearings as a component of the machine. The BDQRA method involves applying data compression techniques like feature extraction to the bearing vibration data, to extract the most important features like time-domain, frequency domain, and time–frequency domain features. Due to the complexity of the feature extraction process, this study proposes fast Fourier transformation for the data compression. This is followed by obtaining a time series profile of the bearing vibration data to analyse the health status of component bearing. It the uses change-point analysis to predict the period at which the bearing health deterioration is imminent. Since the bearing health deterioration could be due to the independent operation of a component bearing or through communication between the component bearing and other components (or bearings) within the process machinery, the method also applies the principle of interaction effect to investigate the contributions from the other components of the machinery to the health deterioration of the component bearing detected. The accuracy of the prediction of the point of imminent health deterioration of the component bearing is investigated by comparing the outcome of the BDQRA method with the outcome of other methods published in literature which have been applied to the dataset used in this study. The findings reveal the BDQRA method have comparative advantages to the methods used in the related studies.

Monitoring a Reverse Osmosis Process with Kernel Principal Component Analysis: A Preliminary Approach

The water purification process is becoming increasingly important to ensure the continuity and quality of subsequent production processes, and it is particularly relevant in pharmaceutical contexts. However, in this context, the difficulties arising during the monitoring process are manifold. On the one hand, the monitoring process reveals various discontinuities due to different characteristics of the input water. On the other hand, the monitoring process is discontinuous and random itself, thus not guaranteeing continuity of the parameters and hindering a straightforward analysis. Consequently, further research on water purification processes is paramount to identify the most suitable techniques able to guarantee good performance. Against this background, this paper proposes an application of kernel principal component analysis for fault detection in a process with the above-mentioned characteristics. Based on the temporal variability of the process, the paper suggests the use of past and future matrices as input for fault detection as an alternative to the original dataset. In this manner, the temporal correlation between process parameters and machine health is accounted for. The proposed approach confirms the possibility of obtaining very good monitoring results in the analyzed context.

Using Learned Health Indicators and Deep Sequence Models to Predict Industrial Machine Health

In this paper, we describe a machine learning approach for predicting machine health indicators with a large time horizon into the future. The approach uses state-of-the-art neural network architectures for sequence modelling and can incorporate numerical-sensor and categorical data using entity embeddings. Moreover, we describe an unsupervised labelling approach where classes are generated using continuous sensor values in the training data and a clustering algorithm. To validate our approach, we performed an ablation study to verify the effectiveness of each of our model’s components. In this context, we show that entity embeddings can be used to generate effective features from categorical inputs, that state-of-the-art models, while originally developed for a different set of problems, can nonetheless be transferred to perform industrial asset health classification and provide a performance boost over simpler networks that have been traditionally used, such as relatively shallow recurrent or convolutional networks. Taken together, we present a machine health monitoring system that can accurately generate asset health predictions. This system can incorporate both numerical and categorical information, the current state-of-the-art for sequence modelling, and generate labels in an unsupervised fashion when explicit labels are unavailable.