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 8
  • Thumbnail Image
    Item
    Data-driven hydrogeological mapping and its impact on the tunnel infrastructure
    (University College Cork, 2025) Hajighasemi, Zahra; Li, Zili; Visentin, Andrea; The Irish Centre for Applied Geoscience (iCRAG); CERN; SFI Research Centre for Energy, Climate and Marine
    Tunnel maintenance and predicting failures during operation have been heavily investigated. This investigation has led to new methods to improve prediction accuracy and extend the service life of tunnels. Among the many factors affecting tunnel performance, the hydrogeological profile of the tunnel route is widely considered one of the most important factors. Over time, it can cause various types of deterioration, such as deformation, material degradation, water leakage, cracks in the lining, and other subsurface issues. For these reasons, creating subsurface geological maps and studying tunnel infrastructure hydrology is essential. Several traditional methods already exist for building geological maps along tunnels, including spatial interpolation, kriging, and Inverse Distance Weighting (IDW). However, these traditional approaches have notable limitations; they struggle to manage sparsely distributed data, scale poorly with large datasets, and have limited ability to capture complex and nonlinear relationships. As an alternative, Machine Learning (ML) methods have gained popularity because of their precise, fast performance and better handling of the aforementioned drawbacks. Supervised ML techniques can learn the correlations between the input features and predict the appropriate label for the output regarding the training set. In this study, borehole spatial features and lithological information were manually extracted from paper-based reports from multiple sources, then structured, preprocessed, and integrated into a unified dataset. These data sets were used to train different ML algorithms, including Random Forest (RF), Support Vector Machine (SVM), Categorical Boosting (CatBoost), and eXtreme Gradient Boosting (XGBoost); the performance of these models was compared. Each data point has the following attributes: latitude, longitude, altitude, ground level, borehole name, and type of soil/rock. In addition, the neighborhood aggregation was used to add new features to improve the models' accuracy. Among the implemented algorithms, the RF and CatBoost performed better than the others; both algorithms were used to develop a geological map for the Large Hadron Collider (LHC) tunnel in the European Organization for Nuclear Research (CERN) from point 3 to point 4, where leakage data was available. To complete the hydrogeological profile, the hydrological characteristics of the study area were assessed. Comparing the hydrogeological profile and the tunnel’s leakage data, no obvious relationship was noted between the geological characteristics and leakage. Nevertheless, a river near SPM9 (about DCUM 8700) contributes to the high leakage percentage in that section, whilst the terrain map is related to the leakage distribution in the longitudinal direction. Darcy's Law states that groundwater flow is directly proportional to the hydraulic conductivity, the cross-sectional area, and the hydraulic gradient. As the difference in hydraulic head (i.e., the elevation difference between the ground surface and the tunnel level) increases, the discharge per unit of groundwater into the tunnel also increases. Therefore, the greater the tunnel depth, that is, the larger the difference between the altitude of the tunnel and ground level, the higher the groundwater table, and thus, more leakages are likely to occur.
  • Thumbnail Image
    Item
    Advancement of software in the loop system for current simulation in wave tanks
    (University College Cork, 2024) Frawley, Cillian; Murphy, Jimmy; Zabihi Kooykheily, Milad; Ebrahimi Salari, Mahdi
    Model testing in wave tanks is a valuable asset in the preliminary design phase of offshore floating wind turbines. Challenges arise when applying combined wind, wave and current loads in a single test location due to the differing scaling laws of air and water. Hybrid testing overcomes this issue by substituting one working fluid with a real-time numerical simulation using mechanical actuators. In hybrid testing in wave tanks, simulation of wind loads can be achieved using actuators such as cable winches or fans. Simulation of current loading is often overlooked. This thesis advances the Software-in-the-Loop (SIL) system for current simulation in wave tanks, building on the foundational work by Otter (2022). A comparison between tow testing and physical current testing to determine the hydrodynamic drag coefficient was conducted for both the 1/50 scale model of the INNWIND semi-submersible and the 1/30 scale model of the OE Buoy wave energy device. A broad scope of waves and current loads were tested to evaluate the SIL system for the INNWIND model. A winch actuator simulates current loading on a semi-submersible floating wind platform, through real-time simulations, applying drag forces derived from Morison’s equation. The winch actuation is determined by tension signals from a load cell, with motion-tracking cameras enabling dynamic adjustments based on platform velocity. Wave spectra are adjusted to account for wave-current interactions. Though a dual-winch system was planned to simulate various current angles, only single-winch actuation was achieved due to time and logistical constraints. The design of the control system and layout for the dual-winch are presented. Numerical simulations of the moored semi-submersible model in the Deep Ocean Basin (DOB) at the Lir National Ocean Test Facility (NOTF) were conducted in Ansys AQWA to validate the SIL system. The winch control accurately responded to the demanded drag force across tested environmental loads. For current-only tests, a coefficient of variation (CV) difference between demanded and measured tensions was less than 0.15, with this difference reducing at higher current velocities. Average demanded and measured tensions are within 0.5 % of each other for all velocities. For wave and current tests, the CV of the demanded tension increases significantly due to the wave load, however, the difference in CV between the demanded and measured tension remains less than 0.15 which signifies the Qualisys-SIL (QSIL) system’s ability to react dynamically to the environmental loads exerted on the platform in real-time.
  • 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.