19684 research outputs found
Sort by
Intelligent Diagnosis of Rolling Element Bearings Under Various Operating Conditions Using an Enhanced Envelope Technique and Transfer Learning
No full textRolling element bearings (REBs) are vital in rotating machinery, making fault detection essential for optimal performance and system reliability. This study assesses the effectiveness of a simple convolutional neural network (SCNN) and a transfer learning-based convolutional neural network (TL-CNN) for diagnosing REB faults using time-domain signals, frequency-domain spectra, and envelope frequency spectrum analysis. The study uses diverse datasets, including laboratory and industrial data under various operating conditions, covering fault types like inner race fault (IRF), outer race fault (ORF), rolling element fault (REF), and healthy (H) states. The main innovation is applying Transfer Learning (TL) with fine-tuning to improve model accuracy in identifying REB conditions by leveraging features learned from diverse datasets. An innovative algorithm is also introduced to identify resonance regions for optimal filter selection in envelope analysis, improving fault-related feature extraction and reducing noise. A preprocessing step that removes speed-related variations further enhances model accuracy by isolating fault features and minimizing the impact of rotational speed. The results show that transfer learning with fine-tuning, combined with the resonance region identification algorithm, significantly enhances fault detection accuracy. The TL-CNN model with envelope signal input achieves the highest accuracy across all scenarios, especially under variable operating conditions, and performs reliably on industrial data.</p
I-AM-Birds (ImB-2):Keep Detecting Amazonian Bird Species
No full textAmazon offers many opportunities to apply artificial intelligence to monitor its rich biodiversity. For example, it is possible to use Deep Learning models to detect Amazonian bird species that frequent residential feeders from images. We demonstrated this in a previous study, but without automating data collection. Therefore, in this extended work, we employed webcams connected to low-cost Orange Pi Zero 3 boards to automate the recording of 6 Amazonian bird species that frequent a residential feeder. Given the volume of data collected, we also trained a preliminary Faster R-CNN model with images of a newly observed species known as the Great Kiskadee and those from previous work to partially annotate the birds in the recordings. Finally, 2,200 new images were randomly extracted from the detected recordings, and 3,358 annotations were manually reviewed and adjusted to train a final Faster R-CNN model that achieved mAP of 99.45%, mean precision of 98.47% and mean recall of 99.68% considering IoU threshold at 50%. With this, we intend to keep collecting and detecting new images to build a monitoring system to study and preserve these species in the future
A comprehensive assessment of life cycle environmental impact and economic feasibility of different red raspberry (Rubus idaeus L) cultivation systems
No full textRed raspberry is considered a knowledge- and capital-intensive crop that targets a niche market globally; its quality attributes and enhanced health-promoting properties are highly appreciated by the consumers. In the context of the exponential growth in demand for this specialty crop that suffers from limited shelf life, it is imperative to expand raspberry cultivation by employing sustainably-sourced production models. In the current study, we used Cyprus as a case study that is characterised by increased production costs and lack of year-round production despite the fact that the latter is feasible under different production systems and cultivation methods in different altitude-related meso‑climates. Towards that goal, the current study assessed the life cycle environmental impact and life cycle costs of two different cultivation methods - open-field production that took place from May to November 2022 and protected cultivation in high-tunnels, from August 2023 to April 2024, using in both cases the same cultivar (Kwanza®) and plant type. The results indicated that protected cultivation has better environmental performance (3.7 mPt - milli eco-points - per kg of raspberry produced compared to 7.4 mPt for open-field production). Noteworthy, production cost is excessive and substantially higher compared to other countries; open-field production has a life cycle cost of 22.5 €/kg, while protected cultivation achieved a lower life cycle cost, equal to 14.0 €/kg yet still high. From an output perspective, a key observation is the increased yield of raspberries in protected cultivation as well as the enhanced water use efficiency of the crop, due to a reduction of the water footprint by 76 %. It is also important to highlight the increased harvest efficiency of the crop under high tunnel, with 500 g per plant compared to 350 g on open field cultivation. Hence, it is safe to conclude that despite the increased start-up costs and knowledge-intensive practices, the productivity of the crop is increased during the off-season months, that can be sold for a premium. The results highlight the environmental and economic impact of the two cultivation methods and will be useful for producers and crop advisors seeking to expand the raspberry cultivation in climates that resembles south-eastern Europe and are characterised as vulnerable to adverse climate change scenarios
Challenges of Built Environment’s Stakeholders in Climate Change Adaptation
No full textImplementing effective climate change adaptation policies and strategies in the built environment can help mitigate the primary consequences of climate change. The built environment contributes heavily to greenhouse gas emissions, and because of its increased population density and economic activity, it is always extremely susceptible to climate change. However, the built environment is complicated and involves a variety of stakeholders, making it difficult to adopt effective climate change adaptation policies and plans. Identifying the challenges stakeholders face in the built environment regarding climate change adaptation is critical to accelerate the implementation process. Therefore, this study aims to identify the challenges of stakeholders’-built environments in climate change adaptation, focusing on the following stakeholder categories: national and local governments, communities, the private sector, academic and research organisations, civil organisations, and professional bodies. The study examined five cases: the United Kingdom, Sweden, Spain, Sri Lanka, and Malta. The country-level investigations began following the initial scoping review and development of the analytical framework. The primary results show that all stakeholders struggle with financial resources and capacities. Every country still has substantially limited coordination between national and local governments and other stakeholders. On the other hand, community and civil organisations have insufficient chances and capacities to participate in decision-making, although they operate at the grassroots level. Even though the UK, Sweden, Malta and Spain have adequate knowledge and resources, these countries are facing significant challenges with mainstreaming climate change adaptation with other sectors at the implementation level. In Sri Lanka, research organisations are dealing with a lack of financing opportunities, communication, and coordination, resulting in a significant information and knowledge gap among other stakeholders, limiting their actions on climate change adaptation. It is critical to identify solutions to reduce stakeholders’ challenges and prevent the severe consequences of climate change in the short and long term. Consequently, the study’s findings are noteworthy and can be used to develop successful implementation mechanisms for climate change adaptation while embracing inclusive decision-making
Study on the formation mechanism and morphology of edge burrs in radial fly-cutting of triangular pyramid microstructures
No full textThe triangular pyramid microstructures (TPM) have been widely applied in the optical field due to its excellent optical properties, such as refraction and reflection. However, the burrs generated during radial fly-cutting (RFC) will have an adverse effect on product performance. To address this issue, the formation mechanism of edge burrs in TPM is deeply analyzed, and RFC experiments are carried out. By adopting the orthogonal experimental method, the influence of processing parameters on the morphology and size of the edge exit burrs is systematically studied. The results indicate that the formation of edge exit burrs is caused by the plastic lateral flow phenomenon of the material in this region. Additionally, the adhesion of chips that have not been promptly separated from the workpiece further increases burr size. The edge exit burrs can be classified into four types: flaky curled burrs, blocky burrs, slim strip burrs, and filiform (thread-like) burrs. As for the two experimental indicators of the edge exit burr projection area and thickness, the main and secondary influencing factors are cutting depth, fly-cutting speed and feed speed. The projection area and thickness of the burrs decrease with the increase of fly-cutting speed, while they increase with higher feed speeds and finer cutting depths. Based on these findings, the optimized processing parameters are determined as follows: fly-cutting speed of 16.76 m/s, feed speed of 10 mm/min, and fine cutting depth of 2 μm. This study provides valuable insights for minimizing burrs and optimizing subsequent deburring processes
Automated pantograph dynamic testing and defect detection
No full textPantographs are a key component for electric trains, responsible for collecting electrical current from the overhead lines. Maintaining pantographs in good working order is key to efficient current collection, whilst avoiding service disruption and managing safety risks. This work proposes a novel robotic system for testing pantographs. Previous studies have conducted initial investigations into automated pantograph testing, typically focusing on a small number of failure modes. There is also a range of pantograph (not automated) test methods defined in EN50206, which can identify faulty pantographs but not diagnose specific faults. The proposed test assesses contact torques as well as contact forces when raising and lowering a pantograph through its working range. Assessment of contact torques proved to be essential to identify some failure modes. Failures in the pantograph frame and joint, dampers, head suspension and air supply are considered. Test parameters, which are post processed from measured results are defined, and testing confirms that a combination of parameters can effectively diagnose all failure modes considered. The method gives a fast assessment of pantograph condition in an industrial train maintenance environment
Effect of strain on the adsorption of carboxylic acids on the surfaces of cerium oxide
No full textCerium oxide nanoparticles are versatile materials suitable for a wide range of catalytic and biotechnological applications. Controlling morphology and surface characteristics is crucial for enhancing their activity, but they are affected by a complex interplay of temperature and partial pressures of oxygen and any adsorbates involved. Here, we use first-principles calculations alongside a thermodynamic approach to model how carboxylic acids, like formic, carbonic, acetic, glycolic, glyoxylic, and oxalic acids, interact with the stoichiometric and oxygen-deficient strained and unstrained {100}, {110}, and {111} cerium oxide surfaces, and how environmental conditions affect the morphology and surface characteristics of ceria nanoparticles. Our analysis includes monodentate, bidentate, and chelate adsorption for each acid, with bidentate adsorption typically showing the highest stability. The presence of oxygen vacancies enhances the adsorption compared to stoichiometric surfaces. We found that adsorbed carboxylic acids can access different particle morphologies under oxidizing conditions. However, in reduced conditions, octahedral shapes dominated by {111} facets tend to be more stable. Hence, our data may exclude thermodynamics as the predominant factor affecting morphology in the presence of carboxylic acids, inferring that kinetic factors affect the growth of ceria nanoparticles
Access Repository Dashboard
Do you manage Huddersfield Research Portal? Access insider analytics, issue reports and manage access to outputs from your repository in the CORE Repository Dashboard!