Civil and Environmental Engineering - Masters by Research Theses

Permanent URI for this collection

https://hdl.handle.net/10468/10080

Browse

Recent Submissions

Now showing 1 - 5 of 6
  • Thumbnail Image
    Item
    The development of a data-driven decision support tool to reduce the energy consumption of a manufacturing process
    (University College Cork, 2022-10-07) Morris, Liam; Bruton, Ken; O'Sullivan, Dominic; Horizon 2020
    With an ever-growing urgency to reduce energy consumption in the manufacturing industry, process stakeholders need more visibility and insights into how much energy they consume, or can expect to consume, for production. In industry today and with the use of Industry 4.0, the way data is utilised has evolved, with data collection and analysis performed digitally. With many long-established manufacturing processes, the jump from older empirical practices to digitalised practices can be difficult. Similarly, many process stakeholders use process data for different means such as production efficiency improvements. From this it can be difficult to ascertain what information is recorded on machines. And with various machines performing varying tasks in part production, this may drive high energy consumption. One such example is computer numerically controlled (CNC) machining tools. These tools are a common manufacturing apparatus and are known to consume energy inefficiently. This thesis describes the development of a hybrid methodology to identify and select key data features on a CNC machine in medical devices manufacturing. Subsequently, this data is used in an empirical energy consumption model of a CNC machine which enables the energy consumption to be determined from the number of parts processed by the machine. In using a calibrated approach, the data undergoes initial preparation followed by exploratory data analysis and subsequent model development via iteration. During this analysis, relationships between parameters are explored to identify which have the most significance on energy consumption. A training set of 191 data points yielded a linear correlation coefficient of 0.95 between the power consumption and total units produced. Root Mean Square Error, Mean Absolute Percentage Error and Mean Bias Error validation tests yielded results of 0.198, 6.4% and 2.66%, respectively.
  • Thumbnail Image
    Item
    Automated crack classification for underground tunnel infrastructure using deep learning
    (University College Cork, 2021-11-01) O'Brien, Darragh; Li, Zili; Osborne, John; Irish Centre for Applied Geoscience; CERN
    One early sign of tunnel structure deterioration originates in the form of cracking, and therefore crack detection and resultant classification is integral for tunnel structural inspection and maintenance. Conventionally tunnel cracks are manually recorded and classified by trained professionals, which is costly, time-consuming and inevitably subjective. Recent advances in the deep learning space have allowed for automatic cracks detection algorithms to be developed and subsequently utilized in surface structural health assessment of surface buildings, bridges, roads and other civil infrastructure. Nevertheless, these methods of development underperform when implemented for a tunnel structure in an underground environment due to the disparity of illumination combined with the congested image data caused by pipes, steel mesh, wires, and other tunnel amenities. This thesis develops an intuitive crack directional classification approach that increases the accuracy, reduces time and subjectivity in comparison to traditional inspection methods. The detection of cracks by utilising CNN’s is antiquity investigated by in literature however little of the writings develop the algorithm further for classification purposes. The novel of this research is centred on the development of a crack classification algorithm that adheres to the directional classification rationale. The output information of the crack classification is correlated to the structural movement of the lining providing a deeper understanding of the tunnel behaviors. To surmount these challenges, this thesis constructs a Convolution Neural Network (CNN) image-based crack detection method accompanied by an innovative crack classification for underground infrastructure environment. Conventional CNN’s are developed from scratch, the proposed CNN incorporates transfer learning in the form of the VGG16 model with weights transferred from ImageNet. The transfer model was trained under various scenarios to determine the optimal model for the operational task in the tunnel environment. The various models are trained using over 10’000 images validated on 2’500 images all of which are 256 x 256 pixels in size, these models are all subsequently tested using 30 images 3072 x 4096 pixels in size. The transfer learning model used outperforms that of the traditional CNN training method of training from scratch. The optimum transfer model accomplished testing metrics of 96.6%,87.3%,92.4%,89.3% for Accuracy, Precision, Recall and F1 score respectively. The proposed CNN appraises images regarding the existence and subsequent location of cracks. Detected cracks are subjected to the secondary classification CNN where the crack is categorized into one of the four crack classes which include the three directional classes of Horizontal, vertical and diagonal with the last crack classes incorporated to represent complex crack regions. The secondary classification CNN attains an Accuracy of 92.3% a Precision of 83.9% a Recall value of 82.3 % and an F1 score of 81.5%. The performance of the manufactured integrated detection and classification method is analysed by performing a field test to evolve the research from a controlled theoretical setting into a realistic tunnel environment. The field test is performed on three separate tunnel sections with an amassed distance of 150 meters with the section testing the robustness, speed and ultimately prospect of application in the CERN inspection scenario. The outcome from this testing demonstrates that the established CNN crack detector/classifier can effectively overwhelm the unfavourable tunnel environment and accomplish results to a high standard.
  • Thumbnail Image
    Item
    Feasibility study of reusing concrete gravity-based foundations designed for tidal energy converters
    (University College Cork, 2022) Dineen, Kate; Li, Zili; Ryan, Paraic; European Regional Development Fund
    Tidal energy converter devices have been developed to capture the enormous energy potential of the tides. These devices rely on robust mooring and foundation systems to ensure efficient energy extraction in operational conditions, and stability in extreme environmental conditions. Gravity-based foundations (GBF) are currently the most commonly used foundation type within the tidal energy industry. While tidal turbines are typically supported using bespoke carbon-steel tripod structures, concrete gravity-based foundations have been put forward by a number of studies as an alternative support solution. Several novel concrete GBF concepts exist and the developers of such concrete structures state that these foundations may be reused or relocated following decommissioning. Reuse of these massive concrete structures would greatly reduce construction and demolition (C&D) waste, and the need for new concrete GBFs for future devices, thus contributing significantly to the sustainability of the tidal energy industry. However, the concept of reusing concrete gravity-based foundations following long periods of deployment underwater has not been tested in real-world scenarios due to the nascent nature of the industry and long commissioning time periods. As highlighted from a related concept in the oil and gas industry, several safety issues may arise from reusing and relocating concrete GBFs, including geotechnical hazards and concrete degradation due to corrosion. Therefore, this study assessed the practicalities of reusing concrete foundations following decommissioning by designing a concrete GBF from first principles to be used for further analysis. This representative GBF was then extensively tested using Plaxis geotechnical software to investigate soil subsidence and differential settlement, assessing their impact on GBF relocation feasibility. Subsequently, the risk of corrosion to the steel reinforcement in the GBF was examined by, firstly, modelling the chloride concentration profile of the concrete, and secondly, investigating the interrelationship between oxygen availability and water saturation level. Thorough investigation into these study considerations can significantly contribute to the determination of whether it is practicable to reuse or relocate concrete gravity-based foundations in the tidal industry. The findings from the geotechnical analysis supports the possibility of reusing and relocating concrete GBFs for tidal turbines as both the total settlement and the tilt were significantly less than the allowable total settlement and tilt tolerance in a deployment site for which the GBF was designed and a contrasting site for which it was not. However, the findings from the concrete degradation analysis does not support the feasibility of reusing concrete GBFs. A chloride ingress analysis encapsulating three datasets indicated that the critical chloride threshold would be surpassed during a GBFs deployment period, meaning that the protective passive layer on the steel would be compromised leaving it vulnerable to corrosion should sufficient oxygen and water be present.
  • Thumbnail Image
    Item
    An experimental investigation into the most prominent sources of uncertainty in wave tank testing of floating offshore wind turbines
    (University College Cork, 2022-08-30) Lyden, Eoin; Murphy, Jimmy; Judge, Frances
    There is an urgent need to replace carbon-based energy sources with renewable energy sources, and floating offshore wind is seen as a critical component in the drive towards energy diversification. Floating offshore wind facilitates accessing a far vaster wind resource that exists in deeper waters, further offshore. Floating offshore wind platforms must undergo wave tank testing in the early stages of development to assess model responses to different wave and wind conditions. Wave tank testing, while highly beneficial, is liable to errors arising throughout the testing campaign. Errors can arise during wave tank setup, testing, and analysis of results. Some of the primary sources of error include errors in the model location within the tank, errors in model parameters like mass, inertia and CoG, and errors due to incorrect replication of mooring forces and aerodynamic forces from the turbine. Scaling wind turbine blade properties can be challenging; this is because aerodynamic forces are scaled using Reynolds scaling, but all hydrodynamic forces are scaled using Froude scaling. For this reason, wind emulation systems are used to replicate the aerodynamic forces from the turbine only. Testing was completed using two very different floating offshore wind concepts. A sensitivity analysis was completed by conducting variations to the wind emulation system used, the model inertia and centre of gravity, and the mooring stiffness of the model. The magnitudes of the variations to the inertia, centre of gravity and mooring stiffness were based on the uncertainty in the values of each of the parameters. Three wind emulation systems of varying complexity were used for this comparison, a simple weighted pulley system, a constant thruster and the software in the loop system developed by CENER. The comparison was conducted to assess the influence of wind emulation systems on the uncertainty of platform response It was found that the effects of each variation conducted were magnified at resonance, and the magnitude of platform response was affected to a greater extent than the period of resonance response. Of all the variations to the model properties conducted, the inertia about the y-axis and location of the centre of gravity along the x-axis affected pitch response to the greatest extent. A 7% change in the inertia about the y-axis coupled with an 8.57% resulted in a 10% change in the period of resonance response for pitch, Tr, and 52% decrease in the magnitude of resonance respsonse for pitch, Tr, mag. Changes in the wind emulation system affected the pitch response most significantly, while the period of resonance response Tr, was mostly unaffected , the magnitude of resonance response Tr, mag, was reduced by nearly 90% when a pulley system was used in lieu of a conventional thruster for a semi-submersible model. Changes in mooring stiffness did not influence the period of resonance response but did affect the magnitude of resonance response, particularly in surge. For a linear horizontal mooring system applied to a semi-submersible model, a 1% decrease in the spring stiffness resulted in a 9% decrease in the magnitude of resonance response for surge, Tr, mag.
  • Thumbnail Image
    Item
    A case-study in the introduction of a digital-twin in a large-scale manufacturing facility
    (University College Cork, 2020-11-02) O'Sullivan, Jamie; O'Sullivan, Dominic; Bruton, Ken; Science Foundation Ireland
    The exponential increase in data produced in recent times has had a profound impact in all areas of society. In the field of industrial engineering, the knowledge produced by this newly obtained data is driving business forward. Automating the process of capturing data from industrial machines, analyzing it and using the knowledge gained to make better decisions for the machines is the crux of the digital twin. Digital twins uncover a wealth of knowledge about the physical asset they duplicate. Sensor technology, Internet of Things platforms, information and communication technology and smart analytics allow the digital twin to transform a physical asset into a connected smart item that is now part of a cyber physical system and that is far more valuable than when it existed in isolation. The digital twin can be adopted by the maintenance engineering industry to aid in the prediction of issues before they occur thus creating value for the business. This thesis discusses the introduction of a maintenance digital twin to a large-scale manufacturing facility. Issues that hamper such work are discovered and categorized to highlight the difficulty of the practical installation of this concept. The work here highlights the difficulties when working on digital systems in manufacturing facilities and how this isn’t discussed in journal articles and the disconnect between academia and industry on this topic. To aid in the installation, a digital twin framework is created that simplifies the digital twin development process into steps that can be completed independently. Work on implementing this framework is commenced and early successes highlight the benefit of sensoring critical assets. The payback of the initial practical work is immediate, and it presents a promising outlook for the iterative development of a maintenance digital twin using the framework. The thesis’ work highlights the benefit in reducing project scale and complexity and hence risk for digital systems in manufacturing facilities by following the framework developed. The later part of the thesis discusses machine learning and how this AI topic can be integrated into the digital twin to allow the digital asset to fulfill its potential.