A review of vibration analysis and its applications

Vibration Analysis (VA) is the most commonly used technique in predictive maintenance. It allows the diagnosis of faults, especially those in the early stages. The use of VA is important for maintenance costs and downtime savings, making decisions about repair and total replacement. The method has been applied in many industries and proven to be effective. It is applicable to rotating, non-rotating equipment, continuous processes or even construction structure. In this paper, vibration analysis fundamentals as well as many studies on the method's application are reviewed. The purpose is to give an overview of how vibration analysis is used in many industries including petroleum to show its potential in petroleum industry. VA has been used in many areas from transportation, refinery to drilling and production. However, there are still rooms for improvement and implementation. One potential application is detecting faults in Electric Submersible Pump (ESP) system. ESP is located downhole making it susceptible to faults and defects that could be difficult to detect using conventional methods. These faults and defects could lead to reduced pump performance or even complete failure that require replacement. Thus, it is important to monitor and analyze vibration of ESP components, specifically pump and motor. Different studies on the topic are also reviewed and discussed. Some studies have been conducted showing that analyzing ESP vibration data helps predict early problems and identifying the causes. Vibration data were also used in principal component analysis models to predict and identify problems as presented in some works. However, principal component analysis could discharge the data models to be unable to correctly predict and determine the faults. VA is a practical technique to monitor and diagnose machine's health. It is important to research VA further and apply it more in petroleum industry, especially in production system. Applications of VA could increase machine's lifespan, reduce maintenance cost and would be useful in optimization.

Healthcare facilities management: A novel data-driven model for predictive maintenance of computed tomography equipment

BACKGROUND

The breakdown of healthcare facilities is a huge challenge for hospitals. Medical images obtained by Computed Tomography (CT) provide information about the patients' physical conditions and play a critical role in diagnosis of disease. To deliver high-quality medical images on time, it is essential to minimize the occurrence frequencies of anomalies and failures of the equipment.

METHODS

We extracted the real-time CT equipment status time series data such as oil temperature, of three equipment, between May 19, 2020, and May 19, 2021. Tube arcing is treated as the classification label. We propose a dictionary-based data-driven model SAX-HCBOP, where the two methods, Histogram-based Information Gain Binning (HIGB) and Coefficient improved Bag of Pattern (CoBOP), are implemented to transform the data into the bag-of-words paradigm. We compare our model to the existing predictive maintenance models based on statistical and time series classification algorithms.

RESULTS

The results show that the Accuracy, Recall, Precision and F1-score of the proposed model achieve 0.904, 0.747, 0.417, 0.535, respectively. The oil temperature is identified as the most important feature. The proposed model is superior to other models in predicting CT equipment anomalies. In addition, experiments on the public dataset also demonstrate the effectiveness of the proposed model.

CONCLUSIONS

The two proposed methods can improve the performance of the dictionary-based time series classification methods in predictive maintenance. In addition, based on the proposed real-time anomaly prediction system, the model assists hospitals in making accurate healthcare facilities maintenance decisions.

Multi-modal LSTM network for anomaly prediction in piston engine aircraft

An aircraft is a highly intricate system that features numerous subsystems, assemblies, and individual components for which regular maintenance is inevitable. The operational efficiency of an aircraft can be maximised, and its maintenance needs can be reduced using an effective yet automatic AI-based health monitoring systems which are more efficient as compared to designing and constructing expensive and harder to operate engine testbeds. It has been observed that aircraft engine anomalies such as undergoing flameouts can occur due to the rapid change in the temperature of the engine. Engine oil temperature and cylinder head temperature, two measures connected to this issue, might be affected differently depending on flight modes and operational conditions which in turn hamper AI-based algorithms to yield accurate prediction on engine failures. In general, previous studies lack comprehensive analysis on anomaly prediction in piston engine aircraft using modern machine learning solutions. Furthermore, abrupt variation in aircraft sensors' data and noise result in either overfitting or unfavourable performance by such techniques. This work aims at studying conventional machine learning and deep learning models to foretell the possibility of engine flameout using engine oil and cylinder head temperatures of a widely used Textron Lycoming IO-540 six-cylinder piston engine. This is achieved through pre-processing the data extracted from the aircraft's real-time flight data recorder followed by prediction using specially designed multi-modal regularised Long Short-Term Memory network to enhance generalisation and avoid overfitting on highly variable data. The proposed architecture yields improved results with root mean square error of 0.55 and 3.20 on cylinder head and engine oil temperatures respectively averaged over three case studies of five different flights. These scores are significantly better i.e., up to 84% as compared to other popular machine learning predictive approaches including Random Forest, Decision Tree Regression, Artificial Neural Networks and vanilla Long Short-Term Memory networks. Through performance evaluation, it can be established that the proposed system is capable of predicting engine flameout 2 minutes ahead and is suitable for integration with the software system of aircraft's engine control unit.

Next-generation predictive maintenance: leveraging blockchain and dynamic deep learning in a domain-independent system

The fourth industrial revolution, often referred to as Industry 4.0, has revolutionized the manufacturing sector by integrating emerging technologies such as artificial intelligence (AI), machine and deep learning, Industrial Internet of Things (IIoT), cloud computing, cyber physical systems (CPSs) and cognitive computing, throughout the production life cycle. Predictive maintenance (PdM) emerges as a critical component, utilizing data analytic to track machine health and proactively detect machinery failures. Deep learning (DL), is pivotal in this context, offering superior accuracy in prediction through neural networks' data processing capabilities. However, DL adoption in PdM faces challenges, including continuous model updates and domain dependence. Meanwhile, centralized DL models, prevalent in PdM, pose security risks such as central points of failure and unauthorized access. To address these issues, this study presents an innovative decentralized PdM system integrating DL, blockchain, and decentralized storage based on the InterPlanetary File System (IPFS) for accurately predicting Remaining Useful Lifetime (RUL). DL handles predictive tasks, while blockchain secures data orchestration. Decentralized storage safeguards model metadata and training data for dynamic models. The system features synchronized two DL pipelines for time series data, encompassing prediction and training mechanisms. The detailed material and methods of this research shed light on the system's development and validation processes. Rigorous validation confirms the system's accuracy, performance, and security through an experimental testbed. The results demonstrate the system's dynamic updating and domain independence. Prediction model surpass state-of-the-art models in terms of the root mean squared error (RMSE) score. Blockchain-based scalability performance was tested based on smart contract gas usage, and the analysis shows efficient performance across varying input and output data scales. A comprehensive CIA analysis highlights the system's robust security features, addressing confidentiality, integrity, and availability aspects. The proposed decentralized predictive maintenance (PdM) system, which incorporates deep learning (DL), blockchain technology, and decentralized storage, has the potential to improve predictive accuracy and overcome significant security and scalability obstacles. Consequently, this system holds promising implications for the advancement of predictive maintenance in the context of Industry 4.0.

Dataset of audio signals from brushless DC motors for predictive maintenance

Predictive Maintenance (PdM) has a main role in the Fourth Industrial Revolution; its goal is to design models that can safely detect failure in systems before they fail, aiming to reduce financial, environmental, and operational costs. A brushless DC (BLDC) electric motors have increasingly become more popular and been gaining popularity in industrial applications, so their analysis for PdM applications is only a natural progression; audio analysis proves to be a useful method to achieve this and rises as a very pragmatic case of study of the characteristics of the motors. The main goal of this paper is to showcase sound-based behavior of BLDC motors in different failure modes as result of an experiment led by researchers at Universidad del Cauca in Colombia. This dataset may provide researchers with useful information regarding signal processing and the development of Machine Learning applications that would achieve an improvement within Predictive Maintenance and I4.0.Predictive Maintenance (PdM) has a main role in the Fourth Industrial Revolution; its goal is to design models that can safely detect failure in systems before they fail, aiming to reduce financial, environmental, and operational costs. A brushless DC (BLDC) electric motors have increasingly become more popular and been gaining popularity in industrial applications, so their analysis for PdM applications is only a natural progression; audio analysis proves to be a useful method to achieve this and rises as a very pragmatic case of study of the characteristics of the motors. The main goal of this paper is to showcase sound-based behavior of BLDC motors in different failure modes as result of an experiment led by researchers at Universidad del Cauca in Colombia. This dataset may provide researchers with useful information regarding signal processing and the development of Machine Learning applications that would achieve an improvement within Predictive Maintenance and I4.0.

FASTory assembly line power consumption data

Machine learning (ML) techniques are widely adopted in manufacturing systems for discovering valuable patterns in shopfloor data. In this regard, machine learning models learn patterns in data to optimize process parameters, forecast equipment deterioration, and plan maintenance strategies among other uses. Thus, this article presents the dataset collected from an assembly line known as the FASTory assembly line. This data contains more than 4,000 data samples of conveyor belt motor driver's power consumption. The FASTory assembly line is equipped with web-based industrial controllers and smart 3-phase energy monitoring modules as an expansion to these controllers. For data collection, an application was developed in a timely manner. The application receives a new data sample as JavaScript Object Notation (JSON) every second. Afterwards, the application extracts the energy data for the relevant phase and persists it in a MySQL database for the purpose of processing at a later stage. This data is collected for two separate cases: static case and dynamic case. In the static case, the power consumption data is collected under different loads and belt tension values. This data is used by a prognostic model (Artificial Neural Network (ANN)) to learn the conveyor belt motor driver's power consumption pattern under different belt tension values and load conditions. The data collected during the dynamic case is used to investigate how the belt tension affects the movement of the pallet between conveyor zones. The knowledge obtained from the power consumption data of the conveyor belt motor driver is used to forecast the gradual behavioural deterioration of the conveyor belts used for the transportation of pallets between processing workstations of discrete manufacturing systems.

Ball bearing vibration data for detecting and quantifying spall faults

Ball bearings are essential components of electromechanical systems, and their failures significantly affect the service lifetime of these systems. For highly reliable and safety-critical electromechanical systems in energy and aerospace sectors, early bearing fault detection and quantification are crucial. The vibration measurements of bearing fatigue faults, i.e., spalls, are typically induced by multiple excitation mechanisms depending on the fault size and the operating conditions. This data article contains vibration datasets for faulty ball bearings, including the common vibration excitation mechanisms for various fault sizes and operating conditions. These faults are artificially seeded on bearing races by a precise machining process to emulate realistic fatigue faults. This data article is beneficial for better understanding the vibration signal characteristics under different fault sizes and for validating condition monitoring methods for various industrial and aerospace applications.

A machine learning-based workflow for automatic detection of anomalies in machine tools

Despite the increased sensor-based data collection in Industry 4.0, the practical use of this data is still in its infancy. In contrast, academic literature provides several approaches to detect machine failures but, in most cases, relies on simulations and vast amounts of training data. Since it is often not practical to collect such amounts of data in an industrial context, we propose an approach to detect the current production mode and machine degradation states on a comparably small data set. Our approach integrates domain knowledge about manufacturing systems into a highly generalizable end-to-end workflow ranging from raw data processing, phase segmentation, data resampling, and feature extraction to machine tool anomaly detection. The workflow applies unsupervised clustering techniques to identify the current production mode and supervised classification models for detecting the present degradation. A resampling strategy and classical machine learning models enable the workflow to handle small data sets and distinguish between normal and abnormal machine tool behavior. To the best of our knowledge, there exists no such end-to-end workflow in the literature that uses the entire machine signal as input to identify anomalies for individual tools. Our evaluation with data from a real multi-purpose machine shows that the proposed workflow detects anomalies with an average F1-score of almost 93%.

Causal augmented ConvNet: A temporal memory dilated convolution model for long-sequence time series prediction

A number of deep learning models have been proposed to capture the inherent information in multivariate time series signals. However, most of the existing models are suboptimal, especially for long-sequence time series prediction tasks. This work presents a causal augmented convolution network (CaConvNet) and its application for long-sequence time series prediction. First, the model utilizes dilated convolution with enlarged receptive fields to enhance global feature extraction in time series. Secondly, to effectively capture the long-term dependency and to further extract multiscale features that represent different operating conditions, the model is augmented with a long-short term memory network. Thirdly, the CaConvNet is further optimized with a dynamic hyperparameter search algorithm to reduce uncertainties and the cost of manual hyperparameter selection. Finally, the model is extensively evaluated on a predictive maintenance task using the turbofan aircraft engine run-to-failure prognostic benchmark dataset (C-MAPSS). The performance of the proposed CaConvNet is also compared with four conventional deep learning models and seven different state-of-the-art predictive models. The evaluation metrics show that the proposed CaConvNet outperforms other models in most of the prognostic tasks. Moreover, a comprehensive ablation study is performed to provide insights into the contribution of each sub-structure of the CaConvNet model to the observed performance. The results of the ablation study as well as the performance improvement of CaConvNet are discussed in this paper.

Examining the impact of deep learning technology capability on manufacturing firms: moderating roles of technology turbulence and top management support

Data science can create value by extracting structured and unstructured data using an appropriate algorithm. Data science operations have undergone drastic changes because of accelerated deep learning progress. Deep learning is an advanced process of machine learning algorithm. Its simple process of presenting data to the system is sharply different from other machine learning processes. Deep learning uses advanced analytics to solve complex problems for accurate business decisions. Deep leaning is considered a promising area for creating additional value in firms' productivity and sustainability as they develop their smart manufacturing activities. Deep learning capability can help a manufacturing firm's predictive maintenance, quality control, and anomaly detection. The impact of deep learning technology capability on manufacturing firms is an underexplored area in the literature. With this background, the purpose of this study is to examine the impact of deep learning technology capability on manufacturing firms with moderating roles of deep learning related technology turbulence and top management support of the manufacturing firms. With the help of literature review and theories, a conceptual model has been prepared, which is then validated with the PLS-SEM technique analyzing 473 responses from employees of manufacturing firms. The study shows the significance of deep learning technology capability on smart manufacturing systems. Also, the study highlights the moderating impacts of top management team (TMT) support as well as the moderating impacts of deep learning related technology turbulence on smart manufacturing systems.

Deep learning-based anomaly-onset aware remaining useful life estimation of bearings

Remaining Useful Life (RUL) estimation of rotating machinery based on their degradation data is vital for machine supervisors. Deep learning models are effective and popular methods for forecasting when rotating machinery such as bearings may malfunction and ultimately break down. During healthy functioning of the machinery, however, RUL is ill-defined. To address this issue, this study recommends using anomaly monitoring during both RUL estimator training and operation. Essential time-domain data is extracted from the raw bearing vibration data, and deep learning models are used to detect the onset of the anomaly. This further acts as a trigger for data-driven RUL estimation. The study employs an unsupervised clustering approach for anomaly trend analysis and a semi-supervised method for anomaly detection and RUL estimation. The novel combined deep learning-based anomaly-onset aware RUL estimation framework showed enhanced results on the benchmarked PRONOSTIA bearings dataset under non-varying operating conditions. The framework consisting of Autoencoder and Long Short Term Memory variants achieved an accuracy of over 90% in anomaly detection and RUL prediction. In the future, the framework can be deployed under varying operational situations using the transfer learning approach.

Artificial intelligence-based human-centric decision support framework: an application to predictive maintenance in asset management under pandemic environments

Pandemic events, particularly the current Covid-19 disease, compel organisations to re-formulate their day-to-day operations for achieving various business goals such as cost reduction. Unfortunately, small and medium enterprises (SMEs) making up more than 95% of all businesses is the hardest hit sector. This has urged SMEs to rethink their operations to survive through pandemic events. One key area is the use of new technologies pertaining to digital transformation for optimizing pandemic preparedness and minimizing business disruptions. This is especially true from the perspective of digitizing asset management methodologies in the era of Industry 4.0 under pandemic environments. Incidentally, human-centric approaches have become increasingly important in predictive maintenance through the exploitation of digital tools, especially when the workforce is increasingly interacting with new technologies such as Artificial Intelligence (AI) and Internet-of-Things devices for condition monitoring in equipment maintenance services. In this research, we propose an AI-based human-centric decision support framework for predictive maintenance in asset management, which can facilitate prompt and informed decision-making under pandemic environments. For predictive maintenance of complex systems, an enhanced trust-based ensemble model is introduced to undertake imbalanced data issues. A human-in-the-loop mechanism is incorporated to exploit the tacit knowledge elucidated from subject matter experts for providing decision support. Evaluations with both benchmark and real-world databases demonstrate the effectiveness of the proposed framework for addressing imbalanced data issues in predictive maintenance tasks. In the real-world case study, an accuracy rate of 82% is achieved, which indicates the potential of the proposed framework in assisting business sustainability pertaining to asset predictive maintenance under pandemic environments.

Dataset of distribution transformers for predictive maintenance

In electricity sector is possible to collect large quantities of data that contain information on relevant processes and events that occur in a given period. It gives a knowledge of the different operation conditions of the electrical network and its components. Through the treatment and analysis of these data is possible to propose market, cost reduction, reduction of failures and repairs in machines and inventory decrease strategies. Grid operator can implement strategies to improve indicators of reliability and quality of service. From a maintenance point of view, the equipment operating time is a relevant aspect to identify and solve failures without service suspensions. This paper aims to show distribution transformers failures characteristics data using historical data collected by the grid operator (Compañia Energética de Occidente) at Cauca Department (Colombia), under the cooperation of the Universidad del Cauca and Universidad del Valle. The dataset could be helpful to researchers and data scientists who use machine learning to develop applications that help engineers in predictive maintenance.

An integrated machine learning model for aircraft components rare failure prognostics with log-based dataset

Predictive maintenance is increasingly advancing into the aerospace industry, and it comes with diverse prognostic health management solutions. This type of maintenance can unlock several benefits for aerospace organizations. Such as preventing unexpected equipment downtime and improving service quality. In developing data-driven predictive modelling, one of the challenges that cause model performance degradation is the data-imbalanced distribution. The extreme data imbalanced problem arises when the distribution of the classes present in the datasets is not uniform. Such that the total number of instances in a class far outnumber those of the other classes. Extremely skew data distribution can lead to irregular patterns and trends, which affects the learning of temporal features. This paper proposes a hybrid machine learning approach that blends natural language processing techniques and ensemble learning for predicting extremely rare aircraft component failure. The proposed approach is tested using a real aircraft central maintenance system log-based dataset. The dataset is characterized by extremely rare occurrences of known unscheduled component replacements. The results suggest that the proposed approach outperformed the existing imbalanced and ensemble learning methods in terms of precision, recall, and f1-score. The proposed approach is approximately 10% better than the synthetic minority oversampling technique. It was also found that by searching for patterns in the minority class exclusively, the class imbalance problem could be overcome. Hence, the model classification performance is improved.

Predictive maintenance and safety operation by device integration on the QUEST large experimental device

As technology has improved in recent years, it has become possible to create new valuable functions by combining various devices and sensors in a network. This concept is referred to as the Internet of Things (IoT), and predictive maintenance is a new valuable function associated with the IoT. In large-scale experimental facilities with many researchers, it is not desirable that experiments cannot be performed due to sudden failure of equipment. For this reason, it is important to predict the failure in advance based on the measurement results of sensors and to perform repairs in a planned manner. On the Q-shu University experiment with steady-state spherical tokamak (QUEST) large experimental device, it is necessary to drive a large current of 50 kA, and the diagnosis of its power line deterioration is well performed as predictive maintenance through the evaluation of its contact resistances of several micro ohms order on the network. In addition, as an example of the IoT, mechanisms to assist safe operation, such as a sound alarm system and an entrance management system, are built by sharing experimental information between devices via the network.

Data on the first endurance activity of a Brushless DC motor for aerospace applications

This article describes the data acquired during the first test activity carried out in the Reliable Electromechanical actuator for PRImary SurfacE with health monitoring (REPRISE) H2020 project. The data consist of a set of measures from an Electro-Mechanical Actuator (EMA) employed in small aircrafts, such as phase currents, positions, temperature and loads. A test bench was developed to perform endurance sessions in various loads and working conditions. Specifically, two datasets are provided: (i) measurements used to monitor the EMA degradation through time; (ii) measurements that characterize the EMA closed-loop dynamic behaviour in healthy condition. The data are helpful to develop and test system identification methods and condition monitoring approaches.

A model for preemptive maintenance of medical linear accelerators-predictive maintenance

Background

Unscheduled accelerator downtime can negatively impact the quality of life of patients during their struggle against cancer. Currently digital data accumulated in the accelerator system is not being exploited in a systematic manner to assist in more efficient deployment of service engineering resources. The purpose of this study is to develop an effective process for detecting unexpected deviations in accelerator system operating parameters and/or performance that predicts component failure or system dysfunction and allows maintenance to be performed prior to the actuation of interlocks.

Methods

The proposed predictive maintenance (PdM) model is as follows: 1) deliver a daily quality assurance (QA) treatment; 2) automatically transfer and interrogate the resulting log files; 3) once baselines are established, subject daily operating and performance values to statistical process control (SPC) analysis; 4) determine if any alarms have been triggered; and 5) alert facility and system service engineers. A robust volumetric modulated arc QA treatment is delivered to establish mean operating values and perform continuous sampling and monitoring using SPC methodology. Chart limits are calculated using a hybrid technique that includes the use of the standard SPC 3σ limits and an empirical factor based on the parameter/system specification.

Results

There are 7 accelerators currently under active surveillance. Currently 45 parameters plus each MLC leaf (120) are analyzed using Individual and Moving Range (I/MR) charts. The initial warning and alarm rule is as follows: warning (2 out of 3 consecutive values ≥ 2σ _hybrid) and alarm (2 out of 3 consecutive values or 3 out of 5 consecutive values ≥ 3σ _hybrid). A customized graphical user interface provides a means to review the SPC charts for each parameter and a visual color code to alert the reviewer of parameter status. Forty-five synthetic errors/changes were introduced to test the effectiveness of our initial chart limits. Forty-three of the forty-five errors (95.6 %) were detected in either the I or MR chart for each of the subsystems monitored.

Conclusion

Our PdM model shows promise in providing a means for reducing unscheduled downtime. Long term monitoring will be required to establish the effectiveness of the model.