Browsing by Author "Starr, Andrew"
Now showing 1 - 20 of 66
Results Per Page
Sort Options
Item Open Access Automated prediction of crack propagation using H2O AutoML(MDPI, 2023-10-12) Omar, Intisar; Khan, Muhammad; Starr, Andrew; Abou Rok Ba, KhaledCrack propagation is a critical phenomenon in materials science and engineering, significantly impacting structural integrity, reliability, and safety across various applications. The accurate prediction of crack propagation behavior is paramount for ensuring the performance and durability of engineering components, as extensively explored in prior research. Nevertheless, there is a pressing demand for automated models capable of efficiently and precisely forecasting crack propagation. In this study, we address this need by developing a machine learning-based automated model using the powerful H2O library. This model aims to accurately predict crack propagation behavior in various materials by analyzing intricate crack patterns and delivering reliable predictions. To achieve this, we employed a comprehensive dataset derived from measured instances of crack propagation in Acrylonitrile Butadiene Styrene (ABS) specimens. Rigorous evaluation metrics, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R2) values, were applied to assess the model’s predictive accuracy. Cross-validation techniques were utilized to ensure its robustness and generalizability across diverse datasets. Our results underscore the automated model’s remarkable accuracy and reliability in predicting crack propagation. This study not only highlights the immense potential of the H2O library as a valuable tool for structural health monitoring but also advocates for the broader adoption of Automated Machine Learning (AutoML) solutions in engineering applications. In addition to presenting these findings, we define H2O as a powerful machine learning library and AutoML as Automated Machine Learning to ensure clarity and understanding for readers unfamiliar with these terms. This research not only demonstrates the significance of AutoML in future-proofing our approach to structural integrity and safety but also emphasizes the need for comprehensive reporting and understanding in scientific discourse.Item Open Access An autonomous rail-road amphibious robotic system for railway maintenance using sensor fusion and mobile manipulator(Elsevier, 2023-08-02) Liu, Haochen; Rahman, Miftahur; Rahimi, Masoumeh; Starr, Andrew; Durazo-Cardenas, Isidro; Ruiz-Carcel, Cristobal; Ompusunggu, Agusmian; Hall, Amanda; Anderson, RobertThe current maintenance of railway infrastructure replies heavily on human involvement, requiring possession of the track section during maintenance, resulting in high costs and inefficient execution. This paper proposes an autonomous rail-road amphibious robotic system for railway inspection and maintenance tasks. By virtue of its road and rail-autonomous mobility, it is able to execute the complete maintenance execution flow in multiple phases. The system provides flexible track job location access, low-cost maintenance execution, and reduced track network possession. The payload mobile manipulator and sensor fusion enhance the system's capabilities for multiple types of inspection and repair. The design of a command and control system was guided by a rule-based expert system strategy to enable remote operation of the whole system. The developed demonstrator of a track wheel accompanied unmanned ground vehicle was integrated and demonstrated in both operational and realistic track environments with multiple testing activities of remote operation, navigation, accurate job detection, inspection, and repair, confirming effective job completion and logical human interaction. The proposed method produces an outstanding hardware-software integrated robotic inspection and repair system with a high level of technological readiness for autonomous railway maintenance and intelligent railway asset management.Item Open Access An autonomous system for maintenance scheduling data-rich complex infrastructure: Fusing the railways' condition, planning and cost(Elsevier, 2018-02-22) Durazo-Cardenas, Isidro; Starr, Andrew; Turner, Christopher J.; Tiwari, Ashutosh; Kirkwood, Leigh; Bevilacqua, Maurizio; Tsourdos, Antonios; Shehab, Essam; Baguley, Paul; Xu, YuchunNational railways are typically large and complex systems. Their network infrastructure usually includes extended track sections, bridges, stations and other supporting assets. In recent years, railways have also become a data-rich environment. Railway infrastructure assets have a very long life, but inherently degrade. Interventions are necessary but they can cause lateness, damage and hazards. Every day, thousands of discrete maintenance jobs are scheduled according to time and urgency. Service disruption has a direct economic impact. Planning for maintenance can be complex, expensive and uncertain. Autonomous scheduling of maintenance jobs is essential. The design strategy of a novel integrated system for automatic job scheduling is presented; from concept formulation to the examination of the data to information transitional level interface, and at the decision making level. The underlying architecture configures high-level fusion of technical and business drivers; scheduling optimized intervention plans that factor-in cost impact and added value. A proof of concept demonstrator was developed to validate the system principle and to test algorithm functionality. It employs a dashboard for visualization of the system response and to present key information. Real track incident and inspection datasets were analyzed to raise degradation alarms that initiate the automatic scheduling of maintenance tasks. Optimum scheduling was realized through data analytics and job sequencing heuristic and genetic algorithms, taking into account specific cost & value inputs from comprehensive task cost modelling. Formal face validation was conducted with railway infrastructure specialists and stakeholders. The demonstrator structure was found fit for purpose with logical component relationships, offering further scope for research and commercial exploitation.Item Open Access Challenges for a railway inspection and repair system from railway infrastructure(IEEE, 2023-01-16) Rahman, Miftahur; Rahimi, Masoumeh; Starr, Andrew; Durazo-Cardenas, Isidro; Hall, Amanda; Anderson, RobertRobots and automation techniques are used in many industries for a long period because of the economic advantages and efficiency. Though the railway has a long history compared to other transportation systems, it still lacks wide application of modern technologies such as robots and AI. Track maintenance using robotic technologies has gained some attraction from both infrastructure managers and researchers due to safety and cost benefits. A Railway Inspection and Repair System (RIRS) has been proposed using commercially available Unmanned Ground Vehicles (UGV) and an industrial manipulator for the railway track inspection and repair tasks. The use of a specially designed trolley enables the on-track and off-track navigation capability of RIRS. The infrastructure in railway is very diversified and unique in size, shape, and remoteness compared to other industries. This research investigates the unique challenges to the operation of RIRS imposed by the railway infrastructure.Item Open Access Comparative analysis of machine learning models for predicting crack propagation under coupled load and temperature(MDPI, 2023-06-16) Omar, Intisar; Khan, Muhammad; Starr, AndrewCrack propagation in materials is a complex phenomenon that is influenced by various factors, including dynamic load and temperature. In this study, we investigated the performance of different machine learning models for predicting crack propagation in three types of materials: composite, metal, and polymer. For composite materials, we used Random Forest Regressor, Support Vector Regression, and Gradient Boosting Regressor models, while for polymer and metal materials, we used Ridge, Lasso, and K-Nearest Neighbors models. We trained and tested these models using experimental data obtained from crack propagation tests performed under varying load and temperature conditions. We evaluated the performance of each model using the mean squared error (MSE) metric. Our results showed that the best-performing model for composite materials was Gradient Boosting Regressor, while for polymer and metal materials, Ridge and K-Nearest Neighbors models outperformed the other models. We also validated the models using additional experimental data and found that they could accurately predict crack propagation in all three materials with high accuracy. The study’s findings provide valuable insights into crack propagation behavior in different materials and offer practical applications in the design, construction, maintenance, and inspection of structures. By leveraging this knowledge, engineers and designers can make informed decisions to enhance the strength, reliability, and durability of structures, ensuring their long-term performance and safety.Item Open Access Compatibility and challenges in machine learning approach for structural crack assessment(Sage, 2022-03-11) Omar, Intisar; Khan, Muhammad; Starr, AndrewStructural health monitoring and assessment (SHMA) is exceptionally essential for preserving and sustaining any mechanical structure’s service life. A successful assessment should provide reliable and resolute information to maintain the continuous performance of the structure. This information can effectively determine crack progression and its overall impact on the structural operation. However, the available sensing techniques and methods for performing SHMA generate raw measurements that require significant data processing before making any valuable predictions. Machine learning (ML) algorithms (supervised and unsupervised learning) have been extensively used for such data processing. These algorithms extract damage-sensitive features from the raw data to identify structural conditions and performance. As per the available published literature, the extraction of these features has been quite random and used by academic researchers without a suitability justification. In this paper, a comprehensive literature review is performed to emphasise the influence of damage-sensitive features on ML algorithms. The selection and suitability of these features are critically reviewed while processing raw data obtained from different materials (metals, composites and polymers). It has been found that an accurate crack prediction is only possible if the selection of damage-sensitive features and ML algorithms is performed based on available raw data and structure material type. This paper also highlights the current challenges and limitations during the mentioned sections.Item Open Access Cost data visualisation(IOS Press, 2021-09-07) Wood, Andrew; Kirkwood, Leigh; Feng, Zijin; Alhaydhal, Sultan; Alomran, Abdullah; Bin Taleb, Rayan; Durazo-Cardenas, Isidro; Starr, AndrewDecision making using the methodologies and analysis generated by the cost engineering function is widely considered good practice across industry, as a way to support both technical engineering decisions and fundamental business decisions. One persistent challenge for the professional cost engineer is to present cost data and information to decision makers and a mix of audiences. Data visualisation is therefore an important element to ensure that data is presented in a clear, effective and convenient format to ensure sufficient insights can be gathered. This work explores different data presentation and visualisation approaches. This review highlighted this topic as a research gap that this paper is novel in addressing. The review findings are further explored through a series of semi-structured interviews with experts in relevant fields to establish effective data visualisation methods, along with the challenges associated with presenting cost data to a variety of audiences. Chart embellishments are one explored area of potential to increase the engagement and understanding of visualisations.Item Open Access A cost estimation approach for IoT modular architectures implementation in legacy systems(Elsevier, 2018-02-08) Tedeschi, Stefano; Emmanouilidis, Christos; Erkoyuncu, John Ahmet; Rodrigues, Duarte Polonia; Roy, Rajkumar; Starr, AndrewIndustry 4.0 has encouraged manufacturing organisations to update their systems and processes by implementing Internet of Things (IoT) technology in legacy systems to provide new services such as autonomous condition monitoring and remote maintenance. However, there is still no literature that guides in realizing the advantages and disadvantages of the fourth industry revolution in terms of complexity, data security, and cost. This paper lays the foundation for the creation of an innovative conceptual model to estimate the cost for implementation of new architectures for legacy systems. The proposed approach considers aspects that impact the cost of different IoT architectures such as: complexity, data gathering and sharing protocols, and cyber security. The authors suggest a further implementation of the cost model, in order to guide the organisations in the most cost-effective architecture for modernisation of their legacy systems.Item Open Access Coupled effects of temperature and humidity on fracture toughness of Al–Mg–Si–Mn alloy(MDPI, 2023-05-30) Alqahtani, Ibrahim; Starr, Andrew; Khan, MuhammadThe combined effect of temperature and humidity on the fracture toughness of aluminium alloys has not been extensively studied, and little attention has been paid due to its complexity, understanding of its behaviour, and difficulty in predicting the effect of the combined factors. Therefore, the present study aims to address this knowledge gap and improve the understanding of the interdependencies between the coupled effects of temperature and humidity on the fracture toughness of Al–Mg–Si–Mn alloy, which can have practical implications for the selection and design of materials in coastal environments. Fracture toughness experiments were carried out by simulating the coastal environments, such as localised corrosion, temperature, and humidity, using compact tension specimens. The fracture toughness increased with varying temperatures from 20 to 80 °C and decreased with variable humidity levels between 40% and 90%, revealing Al–Mg–Si–Mn alloy is susceptible to corrosive environments. Using a curve-fitting approach that mapped the micrographs to temperature and humidity conditions, an empirical model was developed, which revealed that the interaction between temperature and humidity was complex and followed a nonlinear interaction supported by microstructure images of SEM and collected empirical data.Item Open Access Data for the paper "A Dissection and Enhancement Technique for Combined Damage Characterisation in Composite Laminates using Laser-line Scanning Thermography".(Cranfield University, 2021-05-27 09:52) Liu, Haochen; Du, Robin; Yazdani, Hamed; Starr, Andrew; Zhao, YifanThis is the dataset for paper "A Dissection and Enhancement Technique for Combined Damage Characterisation in Composite Laminates using Laser-line Scanning Thermography". It contains the the simulation and experimental data for figures, tables and results in paper. The files are marked with related names.Item Open Access Data set for "Data-based Detection and Diagnosis of Faults in Linear Actuators"(Cranfield University, 2018-03-07 08:40) Ruiz Carcel, Cristobal; Starr, AndrewThis data set presents the raw original data used in "Data-based detection & diagnosis of faults in Linear actuators".The data was acquired from a linear actuator rig operated using different loading conditions and motion profiles. In addition, three different faults (lack of lubrication, spalling and backlash) were gradually seeded to the system in order to study fault detection and diagnosis capabilities of different algorithms. The data set includes actuator position and motor current measurements for the different conditions mentioned. In addition to the data, the file "Data description.pdf" contains all the details about the test rig set up, cases studied and data structure.Item Open Access Data-based detection and diagnosis of faults in linear actuators(IEEE, 2018-03-27) Ruiz-Carcel, Cristobal; Starr, AndrewModern industrial facilities, as well as vehicles and many other assets, are becoming highly automated and instrumented. As a consequence, actuators are required to perform a wide variety of tasks, often for linear motion. However, the use of tools to monitor the condition of linear actuators is not widely extended in industrial applications. This paper presents a data-based method to monitor linear electro-mechanical actuators. The proposed algorithm makes use of features extracted from electric current and position measurements, typically available from the controller, to detect and diagnose mechanical faults. The features are selected to characterize the system dynamics during transient and steady-state operation and are then combined to produce a condition indicator. The main advantage of this approach is the independence from a need for a physical model or additional sensors. The capabilities of the method are assessed using a novel experimental linear actuator test rig specially designed to recreate fault scenarios under different operating conditions.Item Open Access Degradation mechanisms associated with metal pipes and the effective impact of LDMs and LLMs in water transport and distribution(SAGE, 2022-11-09) Agala, Alaa; Khan, Muhammad; Starr, AndrewThe effective operation of water management systems is contingent upon leak localization and detecti– a common problem that is more acute in large networks. This paper reviews the salient literature in this context and demonstrates the effectiveness of leakage location methods (LLMs) and leakage detection methods (LDMs). Although there is a significant amount of literature that discusses leakage localization and detection technologies, an academic lacuna still exists concerning the linkage between degradation mechanisms and LDMs and do not cover or connect past efforts from the start of a degradation mechanism that leads to changes in the mechanical strength (such as a reduction in fracture toughness) of pipes and results in crack propagation and leakage. This review focuses on these issues in the context of degradation mechanisms and common detection methods.Item Open Access Detectability evaluation of attributes anomaly for electronic components using pulsed thermography(Elsevier, 2020-09-16) Liu, Haochen; Tinsley, Lawrence; Addepalli, Sri; Liu, Xiaochen; Starr, Andrew; Zhao, YifanCounterfeit Electronic Components (CECs) pose a serious threat to all intellectual properties and bring fatal failure to the key industrial systems. This paper initiates the exploration of the prospect of CEC detection using pulsed thermography (PT) by proposing a detectability evaluation method for material and structural anomalies in CECs. Firstly, a numerical Finite Element Modelling (FEM) simulation approach of CEC detection using PT was established to predict the thermal response of electronic components under the heat excitation. Then, by experimental validation, FEM simulates multiple models with attribute deviations in mould compound conductivity, mould compound volumetric heat capacity and die size respectively considering experimental noise. Secondly, based on principal components analysis (PCA), the gradients of the 1st and 2nd principal components are extracted and identified as two promising classification features of distinguishing the deviation models. Thirdly, a supervised machine learning-based method was applied to classify the features to identify the range of detectability. By defining the 90% of classification accuracy as the detectable threshold, the detectability ranges of deviation in three attributes have been quantitively evaluated respectively. The promising results suggest that PT can act as a concise, operable and cost-efficient tool for CECs screening which has the potential to be embedded in the initial large scale screening stage for anti-counterfeit.Item Open Access Detecting wheel slip from railway operational data through a combined wavelet, long short-term memory and neural network classification method(Elsevier, 2024-11) Namoano, Bernadin; Emmanouilidis, Christos; Starr, Andrew— Detecting wheel slip is important in railway operations, to prevent damage to wheels and tracks, reduce maintenance costs, improve safety and enhance passenger comfort. Slip activity is characterised by reduced adhesion between the wheel and the rail and limits effective braking or acceleration, causing also operational risks. It is influenced by environmental conditions, vehicle load, track and axle quality, contaminants, inclines, rail oxidation, and braking forces. This paper introduces an innovative method for wheel slip detection in operational trains, utilizing wavelet analysis combined with Long-Short Term Memory (LSTM) modelling. This method analyzes operational data to effectively identify wheel slip, showing promising results when compared to traditional classification-based machine learning methods such as decision trees, forests, logistic regression, naïve Bayes, and support vector machines. This novel approach addresses the complexities of wheel slip detection and is capable of identifying the conditions leading to slip several seconds prior to the commencement of the slip event, offering a practical solution for real-world railway systems.Item Open Access Develop a framework for engineering change management in an aircraft manufacturing company(Cranfield University, 2014-08) Zhu, Lin; Xu, Yuchun; Starr, AndrewThe purpose of this research project is to develop a framework for engineering change management (ECM) in an aircraft manufacturing company. ECM is vital for manufacturers to manage changes efficiently and effectively. As an effective change control technique, ECM has been widely practiced in different industrial sectors. However, adopting an ECM process does not always guarantee the agility of the manufacturing process of the manufacturer. The performance of ECM could be affected by the actual practice followed by the ECM practitioner. The research was conducted in four phases. In the first phase an extensive literature review was carried out to understand the critical success factors related to the ECM and Configuration Management (CM) activities. The second phase was to model the current ECM practice in the aircraft manufacturing company by using IDEF0 approach. The actual ECM practice was understood and some gaps were identified in this part. In the third phase, a survey was carried out to identify the best practices in aerospace and automobile companies. A list of best practices that could promote the performance of the ECM was identified by analysing the result of the survey. In the last phase of the research, a framework was developed from the model of current ECM process in the company. The best ECM practices identified in the third part of the research were integrated into the model to refine the current ECM process. The framework was validated by experts in the aircraft manufacturing company. The outcome of this research shows the correlation between the performance of the ECM process and the actual ECM practices. And the framework developed in this thesis can provide benefits for the further improvement of the current ECM process in the aircraft company. The framework also offers a benchmarking reference for other companies with a similar background to examine their own ECM process and initiate improvement.Item Open Access Development of a context-aware internet of things framework for remote monitoring services(Cranfield University, 2020-12) Al-Shdifat, Ali M. A.; Emmanouilidis, Christos; Starr, AndrewAsset management is concerned with the management practices necessary to maximise the value delivered by physical engineering assets. Internet of Things (IoT)-generated data are increasingly considered as an asset and the data asset value needs to be maximised too. However, asset-generated data in practice are often collected in non-actionable form. Moreover, IoT data create challenges for data management and processing. One way to handle challenges is to introduce context information management, wherein data and service delivery are determined through resolving the context of a service or data request. This research was aimed at developing a context awareness framework and implementing it in an architecture integrating IoT with cloud computing for industrial monitoring services. The overall aim was achieved through a methodological investigation consisting of four phases: establish the research baseline, define experimentation materials and methods, framework design and development, as well as case study validation and expert judgment. The framework comprises three layers: the edge, context information management, and application. Moreover, a maintenance context ontology for the framework has developed focused on modelling failure analysis of mechanical components, so as to drive monitoring services adaptation. The developed context-awareness architecture is expressed business, usage, functional and implementation viewpoints to frame concerns of relevant stakeholders. The developed framework was validated through a case study and expert judgement that provided supporting evidence for its validity and applicability in industrial contexts. The outcomes of the work can be used in other industrially-relevant application scenarios to drive maintenance service adaptation. Context adaptive services can help manufacturing companies in better managing the value of their assets, while ensuring that they continue to function properly over their lifecycle.Item Open Access Diagnostic and prognostic of intermittent faults (by use of machine learning).(Cranfield University, 2020-02) Sedighi, Tabassom; Foote, Peter D.; Starr, AndrewThis thesis investigates novel intermittent fault detection and prediction techniques for complex nonlinear systems. Aerospace and defence systems are becoming progressively more complex, with greater component numbers and increasingly complicated components and subcomponents. At the same time, faults and failures are becoming more challenging to detect and isolate, and the time that operators and maintenance technicians spend on faults is rising. Moreover, a serious problem has recently attracted a lot of attention in health diagnostics of these complex systems. Detecting intermittent faults that persist for very short durations and manifest themselves intermittently have become troublesome and sometimes impossible (also known as “no fault found”). In response to the above challenges, this thesis focuses on the development of a novel methodology to detect intermittent faults of these complex systems. It further investigates various probabilistic approaches to develop efficient fault diagnostic and prognostic methods. In the first stage of this thesis, a novel model (observer)-based intermittent fault detection filter is presented that relies on the creation of a mathematical model of a laboratory scale aircraft fuel system test rig to predict the output of the system at any given time. Comparison between this prediction of output and actual output reveals the presence of a fault. Later, the simulation results demonstrate that the performance of the model (observer)-based fault detection techniques decrease significantly as system complexity increases. In the second stage of this research, a probabilistic data-driven method known as a Bayesian network is presented. This is particularly useful for diverse problems of varying size and complexity, where uncertainties are inherent in the system. Bayesian networks that model sequences of variables are called dynamic Bayesian networks. To introduce the time variable in the framework of probabilistic models while dealing with both discrete and continuous variables in the fuel rig system, a hybrid dynamic Bayesian network is proposed. The presented results of data-driven fault detection show that the hybrid dynamic Bayesian network is more effective than the static Bayesian network or model (observer)- based methods for detecting intermittent faults. Furthermore, the second stage of the research uses all the information captured from the fault diagnostic techniques for intermittent fault prediction by using a probabilistic non-parametric Bayesian method called Gaussian process regression, which is an aid for decision-making using uncertain information.Item Open Access A dissection and enhancement technique for combined damage characterisation in composite laminates using laser-line scanning thermography(Elsevier, 2021-05-24) Liu, Haochen; Du, Weixiang; Yazdani Nezhad, Hamed; Starr, Andrew; Zhao, YifanImpact induced combined damage in composite laminates attracts great attention due to its significant degradation of the structural integrity. However, the provision of the quantitative analysis of each damage portion is challenging due to its bare visibility and structural mixture complexity, so-called barely visible impact damage (BVID), which is referred to as inter-laminar delamination, and is inherently coupled with in-plane transverse and matrix damage also known as combined damage. Instead of focusing on one type of damage in most of the existing studies, this paper proposes a decomposition and targeted enhancement technique based on Stationary Wavelet Transform (SWT) for such coupled BVID in composite laminates using laser-line scanning thermography. Firstly, a combined damage model composed of in-plane damage and inter-laminar delamination is established by finite element numerical modelling to predict the thermal response pattern in the laser scanning thermography. Then, a feature separation and targeted enhancement strategy based on SWT in the frequency domain is proposed to improve the contrast of the matrix crack and delamination in combined damage scenarios induced by low-velocity rigid impact via drop-tower tests, meanwhile eliminating noise and suppressing the laser pattern background. The enhanced images of in-plane damage and delamination are furtherly processed by Random Sample Consensus (RANSAC) method and confidence map algorithms to calibrate the damage profile. The proposed technique is validated through inspecting a group of unidirectional carbon fibre-reinforced polymer composite samples, impacted by a variety of energy levels, in fibre-parallel (0°), 45° and orthogonal scanning modes. The results demonstrate that the proposed technique can pertinently isolate, enhance and characterise the inspected in-plane crack and inter-laminates delamination in a flexible manner. The proposed methodology paves the way towards automated infrared thermography data analysis for quantitative dissection of actual combined damage in composite laminates.Item Open Access Doors datasets(Cranfield University, 2020-08-18 11:55) Namoano, Bernadin; Starr, Andrew; Emmanouilidis, Christos; Ruiz Carcel, CristobalData represents urban train condition monitoring raw data. Data contains, current and door motions during opening and closing periods.