Maintenance, Reliability and Condition Monitoring: Table of Contents

Editor’s Letter

2021-06-30T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 1, Issue 1, 2021, p. 1-1.

Crack identification for bridge condition monitoring using deep convolutional networks trained with a feedback-update strategy

Tong, Tong — 2021-08-06T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 1, Issue 2, 2021, p. 37-51.
Tong Tong, Jing Lin, Jiadong Hua, Fei Gao, Han Zhang
Orthotropic steel bridge decks and steel box girders are key structures of long-span bridges. Fatigue cracks often occur in these structures due to coupled factors of initial material flaws and dynamic vehicle loads, which drives the need for automating crack identification for bridge condition monitoring. With the use of unmanned aerial vehicle (UAV), the acquirement of bridge surface pictures is convenient, which facilitates the development of vision-based bridge condition monitoring. In this study, a combination of convolutional neural network (CNN) with fully convolutional network (FCN) is designed for crack identification and bridge condition monitoring. Firstly, 120 images are cropped into small patches to create a basic dataset. Subsequently, CNN and FCN models are trained for patch classification and pixel-level crack segmentation, respectively. In patch classification, some non-crack patches that contain complicated disturbance information, such as handwriting and shadow, are often mistakenly identified as cracks by directly using the CNN model. To address this problem, we propose a feedback-update strategy for CNN training, in which mistaken classification results of non-crack data are selected to update the training set to generate a new CNN model. By that analogy, several different CNN models are obtained and the accuracy of patch classification could be improved by using all models together. Finally, 80 test images are processed by the feedback-update CNN models and FCN model with a sliding window technique to generate crack identification results. Intersection over union (IoU) is calculated as an index to quantificationally evaluate the accuracy of the proposed method.

A numerical study of rotor eccentricity and dynamic load in induction machines for motor current analysis based diagnostics

Li, Haiyang — 2021-08-06T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 1, Issue 2, 2021, p. 71-86.
Haiyang Li, Zhexiang Zou, Xiuquan Sun, Fengshou Gu, Andrew D. Ball
The asymmetry in the manufacturing and assembling is the common issue of rotor systems. Different degrees of errors are inevitable in alternating current (AC) motors, which causes degraded performances. Furthermore, around 80 % of mechanical faults link to rotor eccentricity. The eccentricity faults (EFs) generate excessive mechanical stress and then lead to fatigue in the other parts of the motor. Motor current signal analysis (MCSA) can be used to diagnose induction machine (IM) faults. As the EF leads to an unequal air gap when the rotor rotates, the inductance of IM also responds to the EF. Moreover, the dynamic load is a typical situation due to residual dynamic unbalance and misalignment. To study how EFs and dynamic load affect the stator current. The current model of symmetrical motor, asymmetrical motors with three-level EFs and with dynamic load are investigated numerically. The correctness of models is verified through experimental study. The results show the level of EF affects the sideband peak values significantly in the stator current spectrum. These findings will provide a foundation for the accurate diagnosis of motor health conditions.

Impact of climate change on railway operation and maintenance in Sweden: A State-of-the-art review

Thaduri, Adithya — 2021-08-06T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 1, Issue 2, 2021, p. 52-70.
Adithya Thaduri, Amir Garmabaki, Uday Kumar
Increased intensity and frequency of extreme weather conditions caused by climate change can have a negative impact on rail service performance and also increases total ownership costs. Research has shown that adverse weather conditions are responsible for 5 to 10 % of total failures and 60 % of delays on the railway infrastructure in Sweden. The impact of short-term and long-term effects of climate change and extreme weather events depends on the design characteristics of the railway assets, geographical location, operational profile, maturity of the climate adaptation, etc. These extreme events will have major consequences such as traffic disruption, accidents, and higher maintenance costs during the operation and maintenance (O&M) phase. Therefore, a detailed assessment of the effects of climate change on the O&M phase requires a more comprehensive review of the previous studies reported from different parts of the world. The paper provides a state-of-the-art review of the effects of extreme weather events and their impacts on the operation and maintenance of railway infrastructure. This paper also provides a list of vulnerable railway assets that can have an impact due to extreme weather events.

Classification of a cracked-rotor system during start-up using Deep learning based on convolutional neural networks

Rezazadeh, Nima — 2021-12-15T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 1, Issue 2, 2021, p. 26-36.
Nima Rezazadeh, Mohammad-Reza Ashory, Shila Fallahy
This article addresses an improvement of a classification procedure on cracked rotors through Deep learning based on convolutional neural networks (CNNs). At first, a cracked rotor-bearing system is modeled by the finite element method (FEM), then throughout its start-up, the related time-domain responses are calculated numerically. In the following, as a pre-processing stage, continuous wavelet transform (CWT) and Short-time Fourier transform (STFT) are applied on the three various health conditions, i.e. without crack, shallow-cracked, and relatively deep-cracked shafts. The plots of CWT’s coefficients and STFT’s in these various classes are used as the input dataset in Deep learning based on CNNs and the three classes are introduced as the output. AlexNet with 25 layers is employed as the network. The results of the testing phase demonstrated that not only this expanded method has a reasonable capacity in the classification of cracked and healthy rotors, but it also can classify cracked rotors with different crack depths with a negligible error.

Reliability of quantitative risk models: a case study from offshore gas production platform

Attia, Mohamed — 2022-06-30T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 2, Issue 1, 2022, p. 1-16.
Mohamed Attia, Jyoti Sinha
In response to the competing factors governing the operation of oil and gas facilities, i.e., the stringent safety and environmental regulations, and the challenging business environment that entails minimizing the running cost, a risk-based inspection (RBI) program became a vital part of all Asset Integrity Management (AIM) frameworks. The objective is to ensure asset mechanical integrity while optimizing the maintenance and inspection resources and minimizing production downtime. There are different risk models being used to manage operational risk for equipment. The decision-maker should be attentive to the subjectivity and reliability of the risk results to establish an adequate risk target that can achieve the ultimate goal of RBI by determining the cost-effective inspection and maintenance plan without compromising plant safety, integrity or reliability. This paper presents evaluations of the most quantitative RBI models through a case study from an offshore gas producing platform. A case study was implemented for topside equipment on an offshore platform. The study analyzed the impact of contributing factors to the probability of failure (PoF) model through a sensitivity analysis to quantify the reliability and subjectivity in the failure probabilities. A sensitivity analysis and comparison between both API consequence modelling methodologies (i.e., CoF level 1 and 2) were performed to manifest the reliability of risk results. The sensitivity analysis revealed the variance in the calculated risk and demonstrated that a risk target/threshold should be established based on the deployed risk model. Using the same risk target for different risk models cannot effectively define all equipment items that actually need more resources to mitigate the risk. And can result in omitting critical equipment which can jeopardize asset integrity and lead to major losses, or spend resources on unnecessary equipment.

Improvement of maintenance management through Lean Philosophy and Industry 4.0

Mendes, David S. F. T. — 2022-06-30T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 2, Issue 1, 2022, p. 17-27.
David S. F. T. Mendes, Helena V. G. Navas, Filipe Didelet, Fernando Charrua-Santos
For companies to be able not only to survive, but also to differentiate themselves in the current global market scenario, all their functional areas must be in line with short, medium, and long-term management objectives and policies. The performance and competitiveness of companies depend on the behaviour of their production system, so an ambitious and adequate maintenance management is necessary. In this way, companies seek to adopt new methodologies and approaches to maintenance management that allow them to prepare maintenance for the challenges of Lean Philosophy and Industry 4.0. The Lean philosophy aims to do more and more with less and less, that is, using less equipment, less human effort, less space, and time, trying to offer customers exactly what they want, at the right time. On the other hand, Industry 4.0 is based on intelligent factories with production processes with a computer interface between people, machines, and resources, through extensive communication networks that combine the virtual and the real world, to obtain all integrated processes generating thus a real-time information system. Thus, an adequate maintenance management system contributes not only to improve maintenance performance as well as the production system. The maintenance management system, when combined with Lean Philosophy and Industry 4.0 concepts, makes it more efficient and effective. To improve maintenance performance, a system that combines these three concepts is proposed.

Experimental investigation of damping characteristics of sandwiched engine isolators using two-way isolator excitation method (TWIEM) and performance evaluation

Bhende, Amit — 2022-09-21T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 2, Issue 2, 2022, p. 28-34.
Amit Bhende
Dynamic properties of engine isolators are of significant importance in determining the performance of the isolator and precise prediction of the dynamic behavior at the design stage. Unfortunately, the damping property can not be deduced deterministically from other structural properties because it is highly dependent on dynamic shear properties such as frequency and temperature of material under application. Generally damping properties are determined from experiments conducted on the desired setup. Many times, designers use the damping property data available in literature. Such data may not be recommended for development of predictive models for dynamic behavior. This paper presents a novel method of determination of damping property of the engine isolator. The method is called two-way isolator excitation method (TWIEM). The damping property is determined by excitation of the isolator for active and passive transmissibility. The purpose of this paper is to analyze the vibration isolation by checking the transmissibility ratio for various engine isolators. Sandwiched engine isolators are designed to blend the good properties of different isolation materials to make it more efficient. The experimentation was carried out using three different isolator designs and compared the performance of the isolator on the basis of isolation percentage. Mild steel plates, polymer foam sheets and natural rubber materials are used as Isolator materials. The results show that low damping ratio isolating material is more effective in isolating the vibration source.

From description to code: a method to predict maintenance codes from maintainer descriptions

Anand, Srini — 2022-10-30T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 2, Issue 2, 2022, p. 35-44.
Srini Anand, Rob Keefer
Aircraft maintenance crews enter the actions performed, the time required to complete the actions, and process followed to complete the action into a system of record that may be used to support future important operational decisions such as part inventory and staffing levels. Unfortunately, the actions performed by maintainers may not align with structured, predetermined codes for such actions. This discrepancy combined with an overabundance of structured codes has led to incorrect and polluted maintenance data that cannot be used in decision making. Typically, the unstructured textual fields accurately record the maintenance action, but are inaccessible to common reporting approaches. The textual fields can be used to cleanse the structured fields, thereby making more data available to support operational decision making. This paper introduces a natural language processing pipeline to predict C-17 US Air Force maintenance codes from an unstructured, shorthand text record. This research aims to cleanse problematic structured fields for further use in operational efficiency and asset reliability measures. Novel use of text processing, extraction, clustering, and classification approaches was employed to develop a natural language processing pipeline suited to the peculiarities of short, jargon-based text. The pipeline evaluates the frequency of structured field values within the datase and selects an appropriate machine learning model to optimize the predictive accuracy. Three different predictive methods were investigated to determine an optimal approach: a Logistic Regression Classifier, a Random Forrest Classifier, and Unsupervised techniques. This pipeline predicted structured fields with an average accuracy of 93 % across the five maintenance codes.

Reliability calculation with error tree analysis and breakdown effect analysis for a quadcopter power distribution system

Imani, Kazem — 2022-12-23T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 2, Issue 2, 2022, p. 45-57.
Kazem Imani, Amirhossein Gholami, Mahdi Bagherian Dehaghi
Quadcopters are playing an increasingly important role in a variety of industries due to their numerous advantages over other types of aircraft. Additionally, quadcopters are susceptible to damage, and their repair can be costly. On the other hand, today, reliability is recognized as a critical design feature in most industries. A device's reliability is one of the most important and complex issues in the field of engineering since it provides engineers with an insight into how a device performs. Due to the fact that reliability is a major factor in all industries and can significantly affect the quality and life of products, we analyzed the reliability of a quadcopter using statistical relationships, mathematical models, and previous experiences. After examining the failure modes and their effects on the system, the effects of the quadcopter failures are analyzed using the FMEA method, in order to determine the cause and mode of the failure. Finally, to determine the causes of failure, we have checked the quadcopter by the FTA method to minimize the possibility of failure. The purpose of this article is to discuss definitions and concepts in the field of reliability, followed by an analysis of the quadcopter and its components.

Vibration influence of different types of heavy-duty trucks on road surface damage

Sun, Mingming — 2023-01-18T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 3, Issue 1, 2023, p. 1-9.
Mingming Sun, Vanliem Nguyen
Under the interaction of the wheels of heavy-duty trucks on the random road surface when the vehicles are travelling, their generated vibrations not only affect the driver's ride comfort but also impact the road surface damage. To assess the vibration influence of different types of vehicles on the road surface damage, three dynamic models of the two axle, three axle, and four axle of heavy trucks have been build and computed via the Matlab/Simulink software. The dynamic tire load, dynamic load coefficient, and dynamic load-stress factor are chosen to assess the friendly load of different heavy trucks under the different operating conditions of the vehicle. The obtained result indicates that the dynamics parameters including suspension system, tires, and axle load distributions of heavy trucks have a greater effect on the dynamic tire force than the total weight of the vehicle. In order to ensure the road’s safety, the traffic management should intervene quickly to give a velocity limit for vehicles under the condition of the vehicle moving with the empty loaded on the poor road surface.

Optimizing and reliability analysis by firefly and genetic algorithms for a quadcopter

Gholami, Amirhossein — 2023-06-25T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 3, Issue 1, 2023, p. 10-26.
Amirhossein Gholami, Abolghasem Naghash, Mahdi Bagherian Dehaghi, Kazem Imani
Our study aims to obtain the highest level of reliability for a quadcopter, taking financial and mass limitations into account, to achieve the highest level of reliability with the lowest mass and cost. For this purpose, we first calculated the reliability and the relationships that govern it, and based on these relationships, we determined the reliability of the quadcopter subsystems. In order to achieve the highest level of reliability, we utilized optimization algorithms. It is possible to increase the reliability of a system through several methods, such as enhancing the quality of parts and components, using surplus components, improving the quality of parts and components by always using surplus components, and redesigning the system. This study examines the possibility of increasing quadcopter reliability by using additional parts and optimizing it using the firefly algorithm. Lastly, in order to validate the results obtained from the firefly algorithm, we implemented the problem once again using the genetic algorithm and compared the results obtained from both algorithms. After 20 times of running the algorithms, the optimal reliability values were 0.99925 for the firefly algorithm and 0.99999 for the genetic algorithm.

Stakeholder dynamics and their impact on value creation for industrial maintenance projects-a literature review

Masarira, Mufaro — 2023-12-30T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 3, Issue 2, 2023, p. 45-56.
Mufaro Masarira, Amir Rahbarimanesh, Kassandra A. Papadopoulou, Jyoti K. Sinha
This paper analyses research developments in the dynamics of stakeholders and their impact mechanisms on the creation of value through a literature review. Three databases, Scopus, Science Direct and Google Scholar are selected to search articles. This study employs a quantitative descriptive analysis and a qualitative thematic analysis to provide a perspective of the data. The findings of the review reveal that stakeholder dynamics management is embedded in project environments and that the dynamic nature of the stakeholder salience attributes can be classified under stakeholder influence and engagement, project lifecycle and dynamics, value creation and framing, and project and stakeholder-associated risk. However, from the characterisation and the drivers of stakeholder dynamics discussed in the literature, the perspective of project risk dynamics has been understudied, with a focus mainly on stakeholder-associated risk to the project, and less on project risk and the stakeholder interactions related to potential losses or gains by stakeholders from such project decisions and activities. Although there is a recognition of the importance of managing stakeholder dynamics within project environments, the factors that affect stakeholder dynamics and their impact on the creation of value for industrial maintenance projects are still unclear. The outcome of the literature review can assist in providing the foundation for the authors’ empirical work of developing a novel conceptual framework for analysing stakeholder dynamics and their impact on maximising value creation in the context of industrial maintenance projects.

Diagnosis of localized defects in floating bush bearings through time-frequency domain analysis

Patil, Hiralal — 2023-12-31T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 3, Issue 2, 2023, p. 27-44.
Hiralal Patil, Dilip Patel
Bearings play a crucial role in the functionality of rotating machinery, and any defects in these components can result in machine failure. Detecting, diagnosing, and prognosing bearing faults are crucial steps in machine failure diagnostics to prevent malfunctions and breakdowns. While various methods exist for fault detection, including acoustic emission analysis, visual inspection, thermography, ultrasonic, motor current analysis, wear-debris analysis, oil analysis, and vibration analysis, the latter stands out as a popular non-destructive method. This paper focuses on time and frequency domain vibration analysis techniques for detecting faults in floating bush bearings. Particularly beneficial for online monitoring, remote and non-human intervention areas, and hazardous locations, the time-frequency domain approach enhances diagnostic capabilities. The vibration data collected during these experiments has been rigorously analyzed using data acquisition system and applied a comprehensive approach that includes evaluating the data in both the time and frequency domains, as well as utilizing advanced signal processing techniques, notably the high-frequency resonance technique. Test results underscore the effectiveness of specific parameters in identifying defects: waveform, form factor, parameter K, and cepstrum excel in pinpointing external defects, while kurtosis, crest factor, and skewness prove adept at identifying internal faults. In the frequency domain, the enveloped spectrum emerges as a robust method for comprehensive defect detection. The vibration data presented in this paper will prove to be an invaluable resource for professionals engaged in the field of vibration measurement and analysis.

Maintenance decision-making and its relevance in engineering asset management

More, Sagar — 2024-03-25T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 4, Issue 1, 2024, p. 1-17.
Sagar More, Rabin Tuladhar, Daniel Grainger, William Milne
Engineering asset management (EAM) has received a lot of attention in the last few decades. Despite this, industries struggle to identify the best strategies for maintaining assets. The decision-making around selecting a relevant maintenance strategy generally considers factors like risk, performance and cost. Risk management is, usually, largely subjective and industries consequently make investments in a subjective manner, making the allocation of budget unstructured and arbitrary. Generally, industries focus only on either overt risks or basic performance of assets, thus creating uncertainties in the decision-making process. Recently, however, maintenance decision-making has evolved from a subjective assessment, chiefly dependent on expert opinions, to utilizing live-data-sensor technology. The attitude towards component failures and how to address them has changed drastically with the evolution of maintenance strategies. Additionally, the emergence and use of several tools and models have assisted the drafting and implementation of effective maintenance strategies. These advancements, however, have only considered discrete parameters while modelling, instead of using an integrated approach. One of the primary factors which can address this shortfall and make the decision-making process more robust is the economic element. To enable an effective decision-making process, it is imperative to consider quantifiable determinants and include economic parameters while drafting maintenance policies. This paper reviews maintenance decision-making strategies in EAM and also highlights its relevance through an economic lens.

An improved semi-supervised prototype network for few-shot fault diagnosis

Lu, Zhenlian — 2024-03-29T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 4, Issue 1, 2024, p. 18-31.
Zhenlian Lu, Kuosheng Jiang, Jie Wu
The collection of labeled data for transient mechanical faults is limited in practical engineering scenarios. However, the completeness of sample determines quality for feature information, which is extracted by deep learning network. Therefore, to obtain more effective information with limited data, this paper proposes an improved semi-supervised prototype network (ISSPN) that can be used for fault diagnosis. Firstly, a meta-learning strategy is used to divide the sample data. Then, a standard Euclidean distance metric is used to improve the SSPN, which maps the samples to the feature space and generates prototypes. Furthermore, the original prototypes are refined with the help of unlabeled data to produce better prototypes. Finally, the classifier clusters the various faults. The effectiveness of the proposed method is verified through experiments. The experimental results show that the proposed method can do a better job of classifying different faults.

Strain response prediction of offshore wind turbine tower under free vibration

Zhang, Zerong — 2024-10-07T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 4, Issue 2, 2024, p. 32-43.
Zerong Zhang, Wei Zhang, Shiqiang Zhang
Strain monitoring of critical locations in offshore wind turbine tower is essential for fatigue life prediction and safe operation of wind turbine. This paper theoretically analyses the feasibility of predicting tower strain under free vibration using the modal superposition method. A finite element numerical model of the tower is established, and the displacement mode and strain mode parameters of the tower are extracted. The initial displacement and strain of the tower at cut-out wind speed are analyzed, and the first three modal coordinate of the tower are calculated using test points of displacement or strain separately. Subsequently, the full field strain of the tower is predicted using the modal superposition method. Comparative results demonstrate higher accuracy in modal coordinate values calculated using test points of displacement, and the accuracy and errors of strain prediction using different numbers of test points are compared, emphasizing the crucial role of selecting optimal positions and numbers of test points in improving prediction accuracy.

Asset Management decision-making through data-driven Predictive Maintenance – an overview, techniques, benefits and challenges

Krishna Menon, Madhu — 2024-12-26T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 4, Issue 2, 2024, p. 44-63.
Madhu Krishna Menon, Rabin Tuladhar
Over the years, industrial asset management has significantly transformed from being an unavoidable resource consumer to a value creator involving multi-criteria decision-making and optimisation. This is particularly important in the scenario of Industry 4.0, which offers more opportunities for improved maintenance effectiveness. This review examines the literature covering the evolving area of data-driven Predictive Maintenance (PdM) within engineering asset management. The work explores current and emerging practices for managing asset degradation, with emphasis on the domain of Prognostics and Health Management (PHM). Next, it examines the opportunities for data-driven methods, associated techniques, and data sources to incorporate data-driven PdM into the maintenance decision-making portfolio. The text concludes by discussing the opportunities and constraints related to data-driven PdM for three identified asset data streams. The paper offers insights for researchers and practitioners interested in utilising data-driven approaches to improve asset reliability, improve maintenance strategies and manage asset complexities.

Impact analysis of field maintenance practices on reliability metrics

Okirie, Ahiamadu Jonathan — 2025-01-23T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 5, Issue 1, 2025, p. 1-24.
Ahiamadu Jonathan Okirie, Ebigenibo Genuine Saturday, Mathew Izuchukwu Gift, Dickens Ewe
Adhering to the maintenance schedules recommended by the original equipment manufacturer (OEM) is crucial for maximizing gas turbine units’ operational efficiency. Adherence to OEM recommendations helps prevent unexpected breakdowns and downtime, promoting a more reliable operation. Timely maintenance also contributes to extending the turbines' lifespan by identifying and rectifying wear and tear before it escalates, it also enhances safety, reduces operational costs, and maintains warranty and support from the OEM. The consequences of ignoring OEM-recommended maintenance schedules for gas turbine power facilities are investigated in this study. Through gap analysis and MATLAB evaluations, the research determined that gas turbine units with low compliance to the OEM’s maintenance plans demonstrated reduced reliability, compared to units with higher compliance, which showed better reliability. Additionally, the study revealed a clear relationship between critical reliability metrics and the failure to adhere to OEM planned maintenance schedules, underscoring the importance of adhering to inspection schedules for optimal performance in power stations. By highlighting the serious consequences of neglecting these recommendations, the study improves our understanding of how adherence to OEM maintenance standards affects operational efficiency and reliability. It also provides valuable insights and guidance for stakeholders in gas turbine energy generation.

Machine learning-based predictive modeling for surface roughness in abrasive machining

S. Usgaonkar, Gajesh G. — 2025-06-28T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 5, Issue 1, 2025, p. 84-97.
Gajesh G. S. Usgaonkar, Rajesh S. Prabhu Gaonkar
The surface quality of any machined component or product greatly influences its attributes, including wear, corrosion resistance, fatigue strength, and more. Numerous safety-instrumented systems and other essential industrial systems necessitate components with a high-quality surface finish. Surface roughness (Ra) is one of the key measurements that indicate the finishing quality of machined parts. In this paper, we begin by detailing the specifics and Ra data set of an experimental study conducted on a commonly utilized abrasive machine, namely, a surface grinder. Next, machine learning algorithms are utilized for predictive modeling of Ra. The problem is framed using the Design of Experiments (DOE) to measure the Ra of EN 8 steel plates with two types of cutting fluids: a conventional synthetic cutting fluid and an eco-friendly cashew nut shell liquid (CNSL). A total of 19 experiments were performed, with five input variables established at two levels each. In the process of creating a predictive model, various algorithms, including Linear Regression, Decision Tree, Random Forest, Epsilon-Support Vector Regression (ε-SVR), and K-Nearest Neighbors Regression, are utilized on the data obtained through experiments. Computed metrics, including Mean Square Error (MSE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R2), showed that ε-SVR outperformed all other methods. Therefore, further tuning of its hyperparameters was done. With this SVR model, predicted roughness values are displayed through a GUI.

Application of artificial neural networks for detecting compressor fouling in industrial gas turbines: a case study of an aero-derivative unit at an oil and gas facility in the Niger Delta, Nigeria

Agbadede, Roupa — 2025-06-29T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 5, Issue 1, 2025, p. 42-52.
Roupa Agbadede, Tosin Folorunsho, Cornelius Sunday Omoniabipi
This study investigates the application of artificial neural networks for the detection of compressors fouling degradation in industrial gas turbines during operation to mitigate the loss in engine performance. An Artificial Neural Network (ANN)-based model was developed to monitor and predict compressor fouling degradation in an aero-derivative gas turbine derived from the Siemens SGT 400 class of gas turbines. Performance data from a Siemens SGT 400 gas turbine unit were obtained and used for the investigation. The obtained engine data represent all faults indicative of compressor performance. For the baseline, data were collected after maintenance actions had taken place, while the degraded case covers historical engine performance from 01 January 2013 to 28 February 2013, accounting for approximately 1,392 Equivalent Operating Hours (EOH). The dataset, encompassing variables such as temperature, pressure, gas flow, power, compressor discharge temperature, and compressor discharge pressure, was processed to eliminate irrelevant and redundant parameters before usage. A Multi-Layer Perceptron (MLP) was chosen as the architecture for the ANN. The outcomes of the training phase showed that the ANN achieved a classification accuracy of 96.2 % in proficiently distinguishing between “fouling” and "other factors" conditions. Additionally, the validation performance plot demonstrates that the network achieved its best performance with a value of 0.077507 at 18 epochs out of 24 training iterations. Finally, the confusion matrix demonstrates the model's capability to predict both fouling and non-fouling scenarios with a minimal rate of misclassification.

Sensor data fusion and cutting tool status recognition by k-means clustering

Hasanlu, M. — 2025-06-29T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 5, Issue 1, 2025, p. 25-41.
M. Hasanlu, M. Danesh
In this study, a novel multi-sensory data fusion approach is developed for real-time tool wear condition monitoring during the turning process, addressing the limitations of single-sensor systems that often suffer from noise and uncertainty. By integrating data from four distinct sensors – machine vision, electrical current, accelerometer, and strain gauge – this method enhances the reliability and robustness of wear state identification. Key features extracted include the entropy of the workpiece’s surface texture via stationary wavelet transform, the time-frequency marginal integral of the motor current, and the Shannon entropy of both the cutting tool’s bending strain and acceleration signals. These features are fused using K-means clustering with Lloyd’s algorithm to classify tool wear into three distinct categories: low (0-0.1 mm), medium (0.1-0.2 mm), and high (> 0.2 mm). Experimental results demonstrate that this approach achieves a classification accuracy of 95 %, significantly outperforming traditional single-sensor methods, which typically yield accuracies below 80 %. This scalable and efficient technique is well-suited for intelligent manufacturing, offering precise tool replacement decisions with minimal computational overhead.

Bearing defects classification using wavelet time scattering features and machine learning techniques

Khan, Heena — 2025-06-29T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 5, Issue 1, 2025, p. 98-108.
Heena Khan, Nitin Upadhyay, Vaibhav Shivhare
Rolling element bearings (REBs) are critical components used in almost all rotating machinery. Small defects, such as pits and spalls, are formed on bearing surfaces due to cyclic loading, results in failure in these rotating machinery and sometime production downtime. Early detection of these small defects is essential to avoid such failure in machinery. In this work, a technique for bearing fault classification using the Wavelet Scattering Transform (WST) and machine learning is proposed. The proposed technique is based on principles of signal processing i.e. wavelet transforms, extracts features that are stable under small deformations and invariant to time shifts. These features are captured automatically from the WST images and are used to train conventional machine learning techniques such as Support Vector Machine, Artificial Neural Network and Decision Tree. The proposed methodology is validated using experimental data from the Case Western Reserve University Bearing Data Centre. Results indicate that WST-based feature extraction, with various classification algorithms, significantly improves the accuracy of bearing fault diagnosis, offering a robust solution for early defect detection.

Quantitative assessment of RAM driven risk matrix of offset printing machine

Pal, Arun Kiran — 2025-06-30T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 5, Issue 1, 2025, p. 53-83.
Arun Kiran Pal, Avijit Kar
Quantitative assessment of risk matrix through analysis of reliability, availability and maintainability (RAM) is used as quick visual tool for managing potential risk in any continuous production system which can be used for further improved maintenance planning. Fault tree analysis along with failure mode and effect analysis support in assessing risk of minor or major failures associated with different consequences of human impact, production loss, maintenance loss etc. For developing risk matrix, scoring of likelihood and severity are necessary to identify the potential risk zone. An attempt has been made in the present study to assess overall failure scenario of offset-printing machine by analysing reliability of different machine component. Different types of failure frequencies and corresponding failure probability of the machine are set as a value representative likelihood failure data. The critical consequences of these failures are discussed for estimation of actual risk and risk index. Matrix of risk and risk priority number is developed here on the basis of likelihood scores of each kind of failure probability and severity scores by considering different types of breakdown and their associated responsible machine component. Moreover, prioritization of different failure types is validated by MonteCarlo simulation. Based on the risk matrix developed, maintainability and maintenance interval time has been determined which seems to be a novel approach for reduction of risk and breakdown time. Finally, maintenance and safety recommendation on the basis of corresponding risk level and maintainability indicator rating are discussed.

Performance assessment and optimization of multi-rotor versus single-rotor turbine in Norwegian offshore wind farm’s

Aarstein, Johannes — 2025-07-10T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 5, Issue 2, 2025, p. 144-158.
Johannes Aarstein, Rami Knudsen Aboujamous, Jonas Bryde Hagen, Tricole Sienes, Arvind Keprate
With Europe’s aim for significant renewable energy expansion by 2050, optimizing wind farm performance is critical. This paper investigates the optimization of wind farm layouts using Multi-Rotor (MR) and Single-Rotor (SR) turbines along the Norwegian coast, focusing on the Utsira Nord and Sørlige Nordsjø II sites. The study utilizes Python-based tools, including PyWake and TopFarm, to model and simulate wake effects and turbine performance. MR turbine systems, with their modular configuration, offer advantages in terms of maintenance and uptime. However, SR turbines outperformed MR systems in terms of annual energy production (AEP), yielding at least 11 % more energy. The paper concludes that further optimization strategies, particularly for MR turbines, are needed to realize their full potential, particularly with more advanced wake models and lifecycle cost assessments.

Multi-stage quantitative risk assessment of a critical system in mining industry

More, Sagar — 2025-07-19T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 5, Issue 2, 2025, p. 172-195.
Sagar More, William Milne, Rabin Tuladhar
Engineering Asset Management (EAM) is a strategic approach focused on the optimal management of physical assets throughout their lifecycle. By integrating engineering principles with financial and operational strategies, EAM aims to enhance asset performance, reliability, and longevity while minimizing risks and costs. This holistic methodology ensures that machinery, equipment, and infrastructure operate efficiently, thereby reducing failures and maximizing productivity. A critical component of EAM is understanding the criticality of each asset within a system. Criticality analysis evaluates the potential impact of different failure modes, considering factors such as failure likelihood, consequences, system interdependencies, cost implications, and associated risks. This analysis is essential for prioritizing maintenance efforts and allocating resources effectively. Risk assessment plays a pivotal role in this context, involving the systematic identification, analysis, evaluation, and management of potential risks associated with asset failures. However, traditional risk assessment methods often face challenges due to subjectivity and variability in evaluations, which can lead to inconsistencies in maintenance decision-making. To address these challenges, this paper proposes a novel multi-stage quantitative Failure Modes, Effects, and Criticality Analysis (FMECA) framework. This approach systematically analyses failure rates, downtime, and cost implications, providing a comprehensive understanding of each failure mode's impact. By integrating these quantitative parameters, the framework enhances objectivity in risk assessment and supports more informed decision-making. It enables organisations to systematically prioritize maintenance activities and optimize resource allocation. This approach not only mitigates operational risks but also aligns asset management practices with overarching business objectives, leading to improved efficiency and reduced costs. The proposed methodology is particularly beneficial in industries such as mining, manufacturing, and aerospace, where unplanned downtime and maintenance costs can have significant operational and financial repercussions. By adopting this multi-dimensional approach, organizations can improve asset performance, enhance safety, and achieve more sustainable operations.

A structured approach for shifting from TBM to CBM in the maintenance of freight locomotives

Alaswed, Mohamed Ali Mohamed — 2025-08-24T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 5, Issue 2, 2025, p. 159-171.
Mohamed Ali Mohamed Alaswed, Jyoti K. Sinha
This paper presents findings from a survey into locomotive and train maintenance professionals’ insights about their current maintenance approaches and a short review of existing research literature to help provide greater understanding of why Time-based-maintenance (TBM) approaches are still dominant in the industry. Following that, a structured Condition-based-Maintenance (CBM) approach for freight locomotives’ maintenance that can be implemented to either complement or completely replace conventional TBM approaches adopted by the rail freight industry today is proposed. The foundation and most significant component of this approach is the critical review of the existing TBM regime, and the historical failure data using techniques such as Pareto Analysis and FMEA (Failure Mode & Effect Analysis). Once the critical review is completed, the structured approach experimentation and implementation stages can begin, which consist of the deployment of sensors and CBM techniques to detect problems on the locomotive by monitoring parameters such as vibration. An example of the structured approach application in the critical review stage is included in this paper using real failure data. The paper concludes with suggested future work to enable transition from TBM to CBM with a focus on components with the greatest impact on the maintenance organizational profitability.

Criticality mapping of a system in the mining industry using Bayesian network

More, Sagar — 2025-12-18T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 5, Issue 2, 2025, p. 109-128.
Sagar More, Rabin Tuladhar, Sourav Das, William Milne
Effective evaluation of equipment criticality is a key concern in Engineering Asset Management, particularly in operationally intensive industries such as mining. While the concept of criticality is often subjective, it can be assessed more objectively using quantifiable indicators such as cost, downtime, and failure rate. This paper presents a data-driven approach to assess equipment-level criticality by analysing the impact of individual equipment downtimes on overall system performance. Focusing on a case study from a gold mining operation in Australia, the study demonstrates how equipment-level performance can be used to prioritise maintenance efforts and support more informed decision-making. One of the key contributions of this work lies in its integration of statistical modelling and probabilistic analysis to identify critical equipment within a system. Unlike conventional methods that often overlook uncertainty or assume uniform equipment influence, this approach quantifies the impact of individual equipment failures on system-level outcomes. The analysis treats subsystems independently, acknowledging the absence of interdependency data while still capturing meaningful insights about their relative importance. By leveraging a combination of platforms – Excel for data preprocessing, R for simulation, and Netica for network-based evaluation – the study offers a replicable and scalable methodology for criticality assessment. Sensitivity analysis within the Bayesian Network model further enhances the framework by highlighting components with the highest influence on system reliability. The outcome is a transparent, objective, and practically applicable tool for maintenance prioritisation, offering significant value in data-intensive and reliability-critical environments like mining. This paper contributes to the growing body of research focused on integrating operational data with advanced modelling techniques to improve asset performance management.

Advancing industrial gas turbine field performance testing: a review of procedures and key considerations with emerging technologies

Agbadede, Roupa — 2025-12-20T00:00:00Z

Maintenance, Reliability and Condition Monitoring, Vol. 5, Issue 2, 2025, p. 129-143.
Roupa Agbadede, Biweri Kainga
This review explores the possibility of enhancing the efficiency and accuracy of Industrial Gas turbine Performance testing by critically assessing the traditional methods, their limitations, and how modern technologies can be used to complement the existing traditional testing approaches, optimize data acquisition, and predict operational failures. A systematic and comprehensive search strategy was employed to identify relevant academic and industry literature. Studies on traditional testing practices were reviewed to highlight their constraints, while researches involving the application of emerging technologies for performance diagnostics were also reviewed to illustrate their benefits. Findings show that measured data such as turbine inlet temperature, compressor pressure ratio, exhaust temperature, fuel flow, shaft speed, and vibration remain essential for both traditional and AI-enhanced methods. These parameters, typically obtained through standardized testing procedures, provide the foundational input for AI models such as machine learning algorithms and digital twins. The study revealed that AI technologies thrive in data-rich, repeatable environments by enhancing processes like instrumentation, data logging, and normalization. The study also revealed that machine learning, deep learning, artificial neural networks, and digital twins can be used for more effective planning, reduce redundant testing, and mitigate delays caused by variable factors like weather or load conditions.

Optimization of online compressor washing frequency for enhanced performance and profitability of industrial gas turbines

Agbadede, Roupa — 2026-02-19T00:00:00Z

Maintenance, Reliability and Condition Monitoring, (in Press).
Roupa Agbadede, Biweri Kainga
This study investigates the optimization of online compressor washing frequency for enhanced performance and profitability of industrial gas turbines. Two representative engines: an aero-derivative LM2500 and a heavy-duty V94.3A (also designated SGT5-4000F) were simulated in GasTurb software under varying washing intervals of one day and ten days. Experimental data were applied to model reductions in compressor isentropic efficiency and mass-flow capacity due to fouling. The results indicate that extending the washing interval from daily to every ten days for one year causes significant performance deterioration. For the LM2500, power output decreased from 7 % to 16 %, thermal efficiency from 2.6 % to 6 %, and heat rate rose from 2.7 % to 6.6 %. Corresponding changes for the V94.3A were smaller, confirming that the aero-derivative turbine is more sensitive to fouling than the heavy-duty unit. Economic evaluation showed that while more frequent washing increased wash fluid consumption and operational costs, it provides substantial financial benefits. Daily washing produced additional annual net profits of approximately £11.69 million for the V94.3A and £4.6 million for the LM2500 compared with ten-day intervals. Overall, the findings demonstrate that optimizing compressor washing frequency is essential to sustain turbine performance, improve fuel efficiency, and maximize profitability. Frequent online washing mitigates the adverse effects of fouling and ensures cost-effective, reliable, and energy-efficient gas-turbine operation.