Staff publications (SATM)
Permanent URI for this collection
Browse
Recent Submissions
Item Open Access Modulating the properties of brown alga alginate-based fibers using natural cross-linkers for sustainable textile and fashion applications(American Chemical Society (ACS), 2024-09-03) Badruddin, Ishrat J; Silva, Mariana P; Tonon, Thierry; Gomez, Leonardo D; Rahatekar, Sameer SSeaweed-derived alginate shows promise in the textile industry as a sustainable alternative to synthetic and natural materials. However, challenges arise due to its low mechanical strength. We addressed this limitation by sustainably extracting alginates from European brown algae and employing novel manufacturing methods. Using natural cross-linkers, such as chitosan, ferulic acid, and citric acid, we have successfully modulated the mechanical properties of alginate fibers. Mechanical properties of ferulic acid and citric acid-cross-linked alginate solutions were spinnable, producing fibers with a diameter of 73–75 μm. Ferulic acid cross-linked alginate fibers exhibited stiffness, with a tensile strength of 52.97 MPa and a strain percentage of 20.77, mechanical properties comparable to those of wool, polyester, and rayon. In contrast, citric acid-cross-linked fibers showed partial elasticity, with a tensile strength of 14.35 MPa and a strain percentage of 45.53, comparable to those of nylon. This ability to control the mechanical properties of seaweed-derived fibers represents a significant advancement for their application in sustainable textiles and the fashion industry.Item Open Access Performance analyses of active aerodynamic load balancing designs on high-performance vehicles in cornering conditions(AIP Publishing, 2024-08-29) Rijns, Steven; Teschner, Tom-Robin; Blackburn, Kim; Brighton, JamesThis study presents a comprehensive investigation into the impact of active aerodynamic load balancing (AALB) on the cornering performance of high-performance vehicles. The research explores the use of active asymmetric aerodynamic devices, specifically split and tilted rear wing concepts, capable of manipulating vertical wheel loads and counteracting effects of lateral load transfer during cornering. The performance potential of AALB is assessed through quasi-steady static coupling of aerodynamic data with a detailed vehicle dynamics model. The findings show that inside bias operating states of the split rear wing and tilted rear wing concepts, which favor loads on the inside tires, can improve cornering velocities up to 0.5% and 2% compared to high symmetric operating states, respectively. Noteworthy, through effective distribution of aerodynamic loads, the inside bias operating states produce less downforce and drag, thereby reducing the propulsion power required to overcome drag by 15%–20%, depending on the cornering condition. The tilted rear wing concept demonstrates the highest AALB capability and most consistent response to its control strategy, accredited to its ability to generate vertical and horizontal aerodynamic force components. It can, therefore, achieve over 1% higher maximum cornering velocities compared to the split rear wing, while also offering efficiency benefits. Overall, the research highlights the effectiveness of AALB in improving cornering performance and efficiency, offering valuable insights for the development of advanced active aerodynamic solutions in automotive design and paving the way for future advancements in the field.Item Open Access On the chemical composition, microstructure and mechanical properties of a Nitrogen-contaminated Ti-6Al-4V component built by Wire-Arc Additive Manufacturing(IOP Publishing, 2024-08-01) Hu, D; Biswal, R; Sahu, VK; Fellowes, JW; Zadehkabir, A; Williams, SW; Davis, AEAdditive manufacturing (AM) using recycled Ti-6Al-4V (Ti64) feedstock material from wrought waste streams is a novel process that can reduce the overall energy cost and carbon (CO2) footprint when compared to primary-production routes. The potential contamination of recycled feedstock material (e.g. C, O, N and Fe) can affect the microstructure and mechanical properties of the component. In this work, a Ti64 test wall built using wire arc AM (WAAM) was studied, where the top half only was contaminated by N through the shielding gas during deposition. This allowed a direct comparison of Ti64 WAAM material with high and low N content, deposited under otherwise identical conditions, to replicate the worst-case scenario of N contamination from using recycled swarf. The hardness of the N-contaminated section was found to be 25% higher than the uncontaminated section of the wall, demonstrating the N solid solution strengthening in Ti64. The room temperature transformed microstructure was found to have a 25% coarser α-lath thickness, which was proposed to be an effect of the AM cyclical heating and increasing of the β-transus temperature due to a higher level of N. Additionally, the outer layer of the N-contaminated sample section was found to have a refined parent β grain structure.Item Open Access Comparison of Performance of NiCr2O4 and Cr2O3 Formed on the Ni-Based Superalloy RR1000 Under Corrosive Conditions(Springer Science and Business Media LLC, 2024) Gray, S.; Mphahlele, M.; Collins, D. M.; Jackson, C.; Hardy, M. C.; Taylor, M. P.Samples of the Ni-based superalloy, RR1000, were exposed to 98% Na2SO4/2% NaCl salts at 700 °C with a flux of 1.5 µg cm−2 h−1 in flowing air + 300 ppm SO2 for a total of 250 h. Three pre-exposure conditions were studied: a bare reference alloy; fast heating to the test temperature followed by a 100 h hold; heating at a rate of 5 °C min−1 to the test temperature following by a 100 h hold. The surface oxide formed under the latter two conditions were Cr2O3 or NiCr2O4, respectively. The results show corrosion pit formation on the surface of the base, reference sample, and no pits present on the sample with the preformed Cr2O3. Some protection was found for the sample heated at 5 °C min−1 with a delay in the progression to accelerated corrosion attack. Additional testing under moisture containing air was also conducted. This showed no obvious difference in surface oxide morphology under the two tested heating rates for the short-term exposures examined but a difference was noted to be dependent on the moisture content of the air.Item Open Access Meta-analysis of the safety effect of electronic stability control(Elsevier BV, 2024-09-01) af Wåhlberg, A. E.; Dorn, L.Objective: Electronic Stability Control (ESC) is a standard feature on most modern cars, due to its reported efficiency to reduce the number of crashes of several types. However, empirical studies of safety effects of ESC for passenger vehicles have not considered some methodological problems that might have inflated the effects. This includes self-selection of drivers who buy/use ESC and behavioral adaptation to the system over long time periods, but also the dominant method of induced exposure. This study aimed to investigate whether such methodological problems might have influenced the results. Method: A meta-analysis was undertaken to investigate whether there are systematic differences between published studies. Moderators tested included when the study was undertaken, the type of vehicle studied, the percent ESC in the sample, size of sample, the length of the study, whether matched or un-matched vehicles were studied, whether induced exposure was used, and two variants of types of crashes used as controls. Results: The effects found ranged from 38% to 75% reduction of crashes for the main targets of singles, running off road and rollover crashes. However, these effects were heterogeneous, and differed depending on the methods used. Most importantly, information that could have allowed more precise analyses of the moderators were missing in most publications. Conclusions: Although average effects were large and in agreement with previous meta-analyses, heterogeneity of the data was large, and lack of information about important moderators means that firm conclusions about what kind of mechanisms were influencing the effects cannot be drawn. The available data on ESC efficiency are not unanimous, and further investigations into the effects of ESC on safety using different methodologies are warranted.Item Open Access Observer based decentralized load frequency control with false data injection attack for specified network quality and delay(Elsevier BV, 2024-08-01) Panda, Deepak Kumar; Halder, Kaushik; Das, Saptarshi; Townley, StuartLoad frequency control (LFC) aims to stabilize grid frequency fluctuations by countering load disturbances with generation-side controllers. In smart grids, demand response (DR) and electric vehicles (EV) offer alternatives to traditional frequency control, reducing reliance on costly generation-side controllers. These decentralized controls, interconnected through a shared communication medium, form a cyber-physical system, vulnerable to challenges like packet drops and false data injection (FDI) attacks. Additionally, consumer participation in DR introduces significant time delays. This paper derives stability conditions for LFC using a state feedback controller, estimating unobservable states with an observer while accounting for bounded disturbances and noise. This cyber-physical system, involving an observer, controller, and network, is modelled as an observer-based networked control system (NCS) using an asynchronous dynamical system (ADS) approach. The resulting switched system model is used to establish linear matrix inequality (LMI) criteria that ensure stability and determine observer and controller gains under specified packet drop rates, disturbances, and noise. The methodology is tested on various configurations, demonstrating that decentralized EV with LFC and DR improves system response, minimizes frequency fluctuations, and optimizes networked control bandwidth under given conditions.Item Open Access The rising entropy of English in the attention economy(Springer Science and Business Media LLC, 2024-08-01) Pilgrim, Charlie; Guo, Weisi; Hills, Thomas T.We present evidence that the word entropy of American English has been rising steadily since around 1900. We also find differences in word entropy between media categories, with short-form media such as news and magazines having higher entropy than long-form media, and social media feeds having higher entropy still. To explain these results we develop an ecological model of the attention economy that combines ideas from Zipf’s law and information foraging. In this model, media consumers maximize information utility rate taking into account the costs of information search, while media producers adapt to technologies that reduce search costs, driving them to generate higher entropy content in increasingly shorter formats.Item Open Access Enhancing object detection and localization through multi-sensor fusion for smart city infrastructure(IEEE, 2024-06-26) Syamal, Soujanya; Huang, Cheng; Petrunin, IvanThe rapid advancement in autonomous systems and smart city infrastructure demands sophisticated object detection and localization capabilities to ensure safety, efficiency, and reliability. Traditional single sensor approaches often fall short, especially under complex environmental conditions. This paper introduces the CLR-Localiser, a novel multi-sensor fusion framework that synergistically integrates data from cameras, LiDAR and radar sensors mounted on roadside infrastructure to enhance object detection and 3D localization. Leveraging the complementary strengths of each sensor type, the CLR-Localiser employs an early fusion approach and deep learning techniques, including convolutional neural networks for object detection and regression networks for precise localization. We rigorously validated the performance of the CLR-Localiser against the benchmark Kitti dataset, and a custom dataset specifically designed for this research, demonstrating significant improvements in detection accuracy, localization precision, and object-tracking capabilities under diverse conditions. Our findings highlight the CLR-Localiser's potential to overcome the limitations of conventional monocular and single-sensor methods, offering a robust solution for autonomous driving, robotics, surveillance, and industrial automation applications. The development and validation of the CLR-Localiser not only prove the technical feasibility of early sensor data fusion but also pave the way for future advancements in multi-sensor fusion technology for enhanced environmental perception in autonomous systems.Item Open Access Architecting CubeSat constellations for messaging service, Part I(Elsevier BV, 2024-10-01) Osipova, Ksenia; Camps, Adriano; Golkar, Alessandro; Ruiz-de-Azua, Joan A.; Fernandez, Lara; Garzaniti, NicolaIn today's modern and globalized world, connectivity is a key factor for businesses, production facilities, sensor networks, and ordinary people. However, there are still populated areas which are not covered by ground-based telecommunications infrastructure. This is where telecommunication satellite constellations come in, as they can provide coverage to remote and uninhabited regions and fill existing connectivity gaps to ensure data transfer. LoRa is one of the technologies designed for data transmissions over long distances with low power consumption. Alongside with other technologies of the Low-Power Wide Area Network family, it is widely used for Internet of Things applications. LoRa chirp spread spectrum modulation is robust against the Doppler frequency shifts encountered in low earth orbits, and it has already been used in IoT satellite communications. Due to the low transmitted signal power, the achieved data rate is not high, making it a suitable technology for telecommunications payloads on CubeSat platforms for messaging services. As compared to existing traditional communication satellite systems, CubeSat constellations are low-cost and may offer an affordable connectivity service to developing regions. This study is divided in two parts. In Part I the demand model is built based on the population distribution not covered by cell towers. The LoRa link performance is analyzed, considering the impact of LoRa channel parameters variation, such as spreading factor and channel bandwidth, while satellite orbital height, transmission antenna beamwidth, and transmitter peak power have a direct impact on the payload mass. Among thousands of possible configurations, 73 feasible payload designs have been downselected. In Part II of the study, the satellite mass and the total system cost are estimated based on the payload parameters obtained. Messages transmission simulation via a constellation is conducted in order to identify optimal constellation architectures for messaging service, as well as the main drivers of the system economic profitability. The presented analysis results provide a deeper understanding of LoRa connectivity advantages and limitations together with the performance drivers, which will support the optimization of future LoRa-based satellite communication systems and other IoT satellite constellations.Item Metadata only Integration of renewable energy sources in tandem with electrolysis: a technology review for green hydrogen production(Elsevier BV, 2024) Nnabuife, Somtochukwu Godfrey; Hamzat, Abdulhammed K.; Whidborne, James; Kuang, Boyu; Jenkins, Karl W.The global shift toward sustainable energy solutions emphasises the urgent need to harness renewable sources for green hydrogen production, presenting a critical opportunity in the transition to a low-carbon economy. Despite its potential, integrating renewable energy with electrolysis to produce green hydrogen faces significant technological and economic challenges, particularly in achieving high efficiency and cost-effectiveness at scale. This review systematically examines the latest advancements in electrolysis technologies—alkaline, proton exchange membrane electrolysis cell (PEMEC), and solid oxide—and explores innovative grid integration and energy storage solutions that enhance the viability of green hydrogen. The study reveals enhanced performance metrics in electrolysis processes and identifies critical factors that influence the operational efficiency and sustainability of green hydrogen production. Key findings demonstrate the potential for substantial reductions in the cost and energy requirements of hydrogen production by optimising electrolyser design and operation. The insights from this research provide a foundational strategy for scaling up green hydrogen as a sustainable energy carrier, contributing to global efforts to reduce greenhouse gas emissions and advance toward carbon neutrality. The integration of these technologies could revolutionise energy systems worldwide, aligning with policy frameworks and market dynamics to foster broader adoption of green hydrogen.Item Open Access An enhanced deep autoencoder for flight delay prediction(Embry-Riddle Aeronautical University, 2024-08-01) Bisandu, Desmond B.; Soviani-Sitoiu, Dan Andrei; Moulitsas, IreneAccurate and timely flight delay prediction cannot be overemphasized because of the ever-increasing demand for air travel and its importance in deploying intelligent transportation systems. Nonetheless, there has not been a universal solution to the problem, as more intelligent flight decision systems are required for the aviation industry’s future growth. Existing flight delay classification and prediction approaches are mainly shallow traffic models and do not satisfy many applications in the real world. Our motivation to rethink the deep architecture model for predicting flight delays emanates from the problem. In this research, we proposed a technique that modified stacked autoencoder architecture parameters for training the network and understanding the link between space, time and information gained from the flight on-time data. We developed three different types of autoencoders based on the architecture of the modified stacked autoencoder. The models learn the generic flight delay features, and it’s trained greedily in a layer-wise fashion. To the best of our knowledge, this is the first time these performances of vanilla autoencoder, logistic regression autoencoder and Multilayer perceptron for classification were evaluated based on the developed modified stacked autoencoder architecture. Moreover, our experiment demonstrates that the models achieved varying levels of accuracy in the flight delay classifications task. The deep vanilla autoencoder shows superior accuracy, recall and precision performance compared to logistic regression autoencoder and Multilayer perceptron autoencoders at different parameter settings.Item Open Access Navigating barriers to reverse logistics adoption in circular economy: an integrated approach for sustainable development(Elsevier BV, 2024-09-01) Sonar, Harshad; Dey Sarkar, Bishal; Joshi, Prasad; Ghag, Nikhil; Choubey, Vardhan; Jagtap, SandeepAchievement of sustainability goals is an epic task for developing economies that still strive to fulfil their basic needs. The availability of limited resources in the developing world vis-à-vis the ever-increasing demand poses further challenges to developing economies willing to transition into circular economies. Reverse logistics (RL) can facilitate this transition towards a circular economy (CE) by maximising resource utilisation and minimising waste, contributing to sustainability goals. This paper contributes to emerging literature by analysing the development and comprehensive potential of reverse logistics as a sustainability tool. It explores the significant barriers to the adoption of reverse logistics towards a circular economy, considering long-term sustainability. In the first phase, thirteen barriers have been identified from the past academic literature. Three barriers with a defuzzification number less than the threshold limit are excluded, and the final ten barriers are then prioritised using the decision-making trial and evaluation laboratory (DEMATEL) method. The findings suggest that a lack of strategic plans for returns is crucial for RL adoption towards a circular economy, followed by a lack of visibility for recycling/reuse. Organisations can increase customer satisfaction, promote environmental sustainability, and gain a competitive edge in the market by creating a strategic plan for reverse logistics. Organisations may lower costs and contribute to a more sustainable and ecologically responsible supply chain by improving visibility across the reverse logistics process. The results serve as a framework for decision-making in RL towards sustainable development. Managers and policymakers can formulate more robust and realistic decisions that align with “maximising profits,” “saving the planet,” “social concerns,” and, most importantly, “consumer concerns” in the circular economy ecosystem. Several implications are derived, leading to increased competitiveness and resilient business strategies. The novelty of this work lies in the identification of barriers to reverse logistics adoption towards a circular economy using an integrated fuzzy Delphi-DEMATEL approach, considering long-term sustainability. This approach is studied for the first time in a developing economy context, proposing social, economic, and environmental effects and actions to be taken by organisations for sustainable development.Item Open Access Why IoT enablement of agrifood transportation disappoints its stakeholders: unravelling barriers for enhanced logistics(Wiley, 2024-01-01) Joshi, Deepika; Gupta, Sumit; Vishwakarma, Amit; Jagtap, SandeepThe present research work investigates the barriers of weak IoT adoption in agrifood transportation, with special reference to India. It is built on a premise that few barriers upshots from the other more impactful ones. Thus, it is important to identify their linkages and classify them based on their strength of relationship. The data collected from 13 agricultural technology (AgriTech) firms of India were subjected to integrated techniques of M‐TISM and Fuzzy MICMAC. As a result, a unique position of autonomous, dependent, linkage, and independent barriers was obtained which revealed that inadequate Internet connectivity, interoperability, and unclear roadmaps are precarious to the use of IoT in agrifood transportation. They are responsible for creating issues like data processing, vehicle tracking, and data privacy. This study offers a contextual phenomenon of barriers that may assist AgriTech stakeholders in developing appropriate strategies to embrace IoT transformation. It extends the theoretical literature by providing critical connections that aspiring researchers can examine through hypothesis testing or building a hierarchical framework. A sensitivity analysis is suggested to optimise decision‐making and bring out a robust and reliable set of obstacles.Item Open Access Unlocking AI's potential in the food supply chain: a novel approach to overcoming barriers(Elsevier, 2024-12-31) Ghag, Nikhil; Sonar, Harshad; Jagtap, Sandeep; Trollman, HanaThis paper delves into the challenges impeding the seamless integration of artificial intelligence (AI) within the food supply chain (FSC) and introduces a novel methodological framework that combines the NK Model with the Decision-Making Trial and Evaluation Laboratory (DEMATEL) technique. Through an exhaustive literature analysis and expert discussions, the research identifies and categorizes significant obstacles to AI deployment in the FSC. These hurdles include the imperative for a skilled labor force, financial limits, regulatory complexity and technological limitations. The unique DEMATEL-NK approach highlights the interconnected nature of these barriers, pinpointing the most critical impediments. The study's implications extend to the broader domains of AI adoption in agriculture and the food industry, offering a nuanced perspective for policymakers, industry stakeholders, and researchers. The findings underscore the imperative of overcoming these barriers for the successful implementation of AI technologies in the FSC, promising advancements in efficiency, quality, and sustainability. The innovative methodology not only sheds light on the interconnectedness of these barriers but also provides a systematic approach for prioritizing and implementing solutions. This research offers a fresh viewpoint on barrier relationships, guiding decision-makers in crafting effective strategies and interventions to propel AI integration in the FSC forward.Item Open Access Assessment of flyby methods as applied to close encounters among asteroids(MDPI, 2024-08-09) Stronati, Nicolò; Fenucci, Marco; Micheli, Marco; Ceccaroni, MartaOrbital flybys have been extensively studied for spacecraft missions, resulting in effective mathematical and physical models. However, these models’ applicability to natural encounters involving asteroids has not been explored. This paper examines the applicability of two such theories, patched conics (PC) and the Keplerian map (KM), to asteroid encounters. A review of the two methods will be provided, highlighting their assumptions and range of applicability. Simulations of asteroid–asteroid encounters will then be performed to evaluate their effectiveness in these scenarios. The simulation parameters are set by collecting data on actual asteroid–asteroid encounters, hereby presented, generally characterised by high close approach distances and small masses of the perturbing bodies, if compared to those used to build the flyby theories. Results show that the PC theory’s effectiveness diminishes with increasing approach distances, aligning with its assumptions. Moreover, the prediction of the model is better in the geometric configurations where the flyby has major effects on the orbital energy change. The KM theory has shown good effectiveness for encounters occurring outside the sphere of influence of the perturbing body, even for very high distances. This research investigates flyby models’ strengths and weaknesses in asteroid encounters, offering practical insights and future directions.Item Open Access Advanced UAV design optimization through deep learning-based surrogate models(MDPI, 2024-08-14) Karali, Hasan; Inalhan, Gokhan; Tsourdos, AntoniosThe conceptual design of unmanned aerial vehicles (UAVs) presents significant multidisciplinary challenges requiring the optimization of aerodynamic and structural performance, stealth, and propulsion efficiency. This work addresses these challenges by integrating deep neural networks with a multiobjective genetic algorithm to optimize UAV configurations. The proposed framework enables a comprehensive evaluation of design alternatives by estimating key performance metrics required for different operational requirements. The design process resulted in a significant improvement in computational time over traditional methods by more than three orders of magnitude. The findings illustrate the framework’s capability to optimize UAV designs for a variety of mission scenarios, including specialized tasks such as intelligence, surveillance, and reconnaissance (ISR), combat air patrol (CAP), and Suppression of Enemy Air Defenses (SEAD). This flexibility and adaptability was demonstrated through a case study, showcasing the method’s effectiveness in tailoring UAV configurations to meet specific operational requirements while balancing trade-offs between aerodynamic efficiency, stealth, and structural weight. Additionally, these results underscore the transformative impact of integrating AI into the early stages of the design process, facilitating rapid prototyping and innovation in aerospace engineering. Consequently, the current work demonstrates the potential of AI-driven optimization to revolutionize UAV design by providing a robust and effective tool for solving complex engineering problems.Item Open Access Multi-channel anomaly detection using graphical models(Springer, 2024-12-31) Namoano, Bernadin; Latsou, Christina; Erkoyuncu, John AhmetAnomaly detection in multivariate time-series data is critical for monitoring asset conditions, enabling prompt fault detection and diagnosis to mitigate damage, reduce downtime and enhance safety. Existing literature predominately emphasises temporal dependencies in single-channel data, often overlooking interrelations between features in multivariate time-series data and across multiple channels. This paper introduces G-BOCPD, a novel graphical model-based annotation method designed to automatically detect anomalies in multi-channel multivariate time-series data. To address internal and external dependencies, G-BOCPD proposes a hybridisation of the graphical lasso and expectation maximisation algorithms. This approach detects anomalies in multi-channel multivariate time-series by identifying segments with diverse behaviours and patterns, which are then annotated to highlight variations. The method alternates between estimating the concentration matrix, which represents dependencies between variables, using the graphical lasso algorithm, and annotating segments through a minimal path clustering method for a comprehensive understanding of variations. To demonstrate its effectiveness, G-BOCPD is applied to multichannel time-series obtained from: (i) Diesel Multiple Unit train engines exhibiting faulty behaviours; and (ii) a group of train doors at various degradation stages. Empirical evidence highlights G-BOCPD's superior performance compared to previous approaches in terms of precision, recall and F1-score.Item Open Access Driving sustainability: assessing KPI effectiveness in the Saudi chemical industry(Springer Science and Business Media LLC, 2024-12-31) Alfarsi, Alaa; Sherif, Ziyad; Jagtap, Sandeep; Gupta, Sumit; Salonitis, KonstantinosThis study explores the relationship between Key Performance Indicators (KPIs) and environmental performance improvement within the Saudi chemical industry. Against the backdrop of global sustainability imperatives and Saudi Arabia’s Vision 2030, which promotes sustainability for economic diversification, this research aims to assess the effectiveness of KPIs in driving environmental sustainability practices. The motivation for this study stems from the identified gaps in the systematic implementation and utilisation of KPIs and the lack of awareness regarding certain aspects of environmental impact management within the industry in the Kingdom. The methodology involved a structured survey administered to a diverse range of chemical manufacturing companies, followed by rigorous data analysis using descriptive evaluation, Analysis of Variance (ANOVA), reliability analysis, and t-tests. The results revealed insights into pollution areas, KPI utilisation, methods for pollution assessment, alignment with strategic goals, and governance regulations. Descriptive analysis highlighted air quality management as a priority, with notable attention to water and land pollution, while quantitative analysis confirmed the significance of KPIs in driving environmental performance improvement in the area. However, it also unveiled the absence of a systematic approach to implementing and utilising KPIs effectively, coupled with a lack of awareness regarding certain aspects of environmental impact management, consequently leading to uncertainty. Overall, this study contributes to advancing sustainability efforts within the Saudi chemical sector, providing actionable insights for industry stakeholders and policymakers.Item Open Access Application of CNN for multiple phase corrosion identification and region detection(Elsevier BV, 2024-10-30) Oyedeji, Oluseyi Ayodeji; Khan, Samir; Erkoyuncu, John AhmetCorrosion is a significant issue that contributes negatively to the degradation of materials most especially metals. To ensure proper maintenance, enhance reliability and prevent breakdown, it is very essential to not only effectively detect corrosion but to also understand its locations and distributions on the materials. A Multiple phase Convolutional Neural Network (CNN) model is created for this purpose. The Multiple phase CNN model consists of custom designed deep learning algorithms at various stages. This created the opportunity to make use of binary classification, multi-label classification and patch distribution algorithm to detect and identify corrosion regions on metallic materials. Six (6) different labels of corrosion were modelled to represent different levels of degradation using 600 anonymized images. The images were used in the various stages of the framework for training the respective models. Results at the binary level shows 94.87 % of corrosion detection. The multiclass stage of the Multiple phase CNN records the highest accuracy of 92.1 %. The patch distribution stage recorded a highest accuracy of 96.5 % and 94.6 % for the Average Image and Average Pixel ROCAUC (Region of Concentration Area Under Cover). It also shows a region segment average accuracy detection of 91.5 % (image level) and 89.2 %(pixel level) for 9 distinct regions. The research provides a comprehensive and detailed reliability and maintenance information for Aerospace, Transport and Manufacturing Materials experts and non-experts. The framework shows a robust approach to detecting corrosion which is essential for critical and safety applications as well as preventing economic loss due to corrosion. This can also be extended to other domains beyond the corrosion case study.Item Open Access Strategic flood impact mitigation in developing countries’ urban road networks: application to Hanoi(Elsevier BV, 2024-12-16) Phouratsamay, Siao-Leu; Scaparra, Maria Paola; Tran, Trung Hieu; Laporte, GilbertDue to climate change, the frequency and scale of flood events worldwide are increasing dramatically. Flood impacts are especially acute in developing countries, where they often revert years of progress in sustainable development and poverty reduction. This paper introduces an optimization-based decision support tool for selecting cost-efficient flood mitigation investments in developing countries’ urban areas. The core of the tool is a scenario-based, multi-period, bi-objective Mixed Integer Linear Programming model which minimizes infrastructure damage and traffic congestion in urban road networks. The tool was developed in collaboration with Vietnamese stakeholders (e.g., local communities and government authorities), and integrates data and inputs from other disciplines, including social science, transport economics, climatology and hydrology. A metaheuristic, combining a Greedy Randomized Adaptive Search Procedure with a Variable Neighborhood Descent algorithm, is developed to solve large scale problem instances. An extensive computational campaign on randomly generated instances demonstrates the efficiency of the metaheuristic in solving realistic problems with hundreds of interdependent flood mitigation interventions. Finally, the applicability of the interdisciplinary approach is demonstrated on a real case study to generate a 20-year plan of mitigation investments for the urban area of Hanoi. Policy implications and impacts of the study are also discussed.