20505 research outputs found
Sort by
Shaping extended product design and development with predictive maintenance capability for digital servitisation
Get PDFTraditional business models of selling a product as a single item can no longer satisfy the growing service-oriented needs of customers. Service-oriented business models, like servitisation or product-service systems (PSS), have been introduced to respond to this market demand. Predictive maintenance (PdM) strategy is regarded as a key element in the development of such business models because of its effective role in maximising the availability and usability of products. The PdM strategy requires technologies including, sensing, data acquisition, data analytics algorithms and decision support tools. In traditional business models, these technologies are typically developed by third parties when products are already commissioned or in service, which is sub-optimal. It can be argued that PdM technologies developed by original equipment manufacturers (OEMs) can significantly reduce development costs and increase competitiveness. This paper proposes a new framework for guiding OEMs to develop and integrate relevant PdM technologies during the development of new products in support of their new journey in a digital servitisation business model. This encompasses the full life cycle of the product from customers’ needs/values analysis to after-sales service. The model-based system engineering (MBSE) approach was adopted to implement the proposed framework using the selected system modelling language (SysML) tool, namely Capella, and to verify it in an industrial case study.34th CIRP Design Conference 2024Procedia CIR
Flight plan optimisation of unmanned aerial vehicles with minimised radar observability using action shaping proximal policy optimisation
Get PDFThe increasing use of unmanned aerial vehicles (UAVs) is overwhelming air traffic controllers for the safe management of flights. There is a growing need for sophisticated path-planning techniques that can balance mission objectives with the imperative to minimise radar exposure and reduce the cognitive burden of air traffic controllers. This paper addresses this challenge by developing an innovative path-planning methodology based on an action-shaping Proximal Policy Optimisation (PPO) algorithm to enhance UAV navigation in radar-dense environments. The key idea is to equip UAVs, including future stealth variants, with the capability to navigate safely and effectively, ensuring their operational viability in congested radar environments. An action-shaping mechanism is proposed to optimise the path of the UAV and accelerate the convergence of the overall algorithm. Simulation studies are conducted in environments with different numbers of radars and detection capabilities. The results showcase the advantages of the proposed approach and key research directions in this field.Drone
Compressive properties and fracture behaviours of Ti/Al interpenetrating phase composites with additive-manufactured triply periodic minimal surface porous structures
Get PDFThe triply periodic minimal surfaces (TPMS) structure is regarded as a highly promising artificial design, but the performance of composites constructed using this structure remains unexplored. Two porosity levels of Ti/Al interpenetrating phase composites (IPCs) were fabricated by infiltrating ZL102-Al melt into additive-manufactured TC4-Ti scaffolds with the TPMS porous in this study. The combination of the two-phase alloys exhibits structural integrity at the interfacial region, as evidenced by microscopic surfaces observed in uncompressed IPCs. Quasi-static compression tests were performed to demonstrate that the Young’s modulus, yield stress and maximum compressive stress of IPCs exhibit significant enhancement when compared to the individual TPMS scaffolds, due to the supporting and strengthening effect of the filling phase. In the compression process of IPCs, defects emerge initially at the interface between the ZL102 phase and TC4 phase, triggering the fracture and slip of the ZL102 phase, eventually propagating to involve fracture in the TC4 phase. The deformation behaviours obtained from numerical simulation were combined to support these experimental phenomena. The results show that the corresponding stress concentration region is the central region of the spiral surface, the maximum stress concentration region of the ZL102 phase is the same as that of the TC4 phase, and the ZL102 phase effectively shares part of the loading. The Ti/Al IPCs achieve equivalent load-bearing capacity through a simplified interpenetration process and the utilisation of lighter materials.The authors wish to gratefully acknowledge the financial support from the National Natural Science Foundation of China (Grant No. 52105418), the Natural Science Foundation of Hunan Province (Grant No. 2023JJ20069), and the key scientific research project of Hunan Provincial Department of Education (Grant No. 23A0001).Metals and Materials Internationa
On hysteresis in a variable pitch fan transitioning to reverse thrust mode and back
Get PDFA novel hysteresis phenomenon during the transition to and back from the reverse thrust mode in a variable pitch fan (VPF) is identified and characterized in this work. This is done using a three-dimensional fully transient unsteady Reynolds-averaged Navier–Stokes (URANS) with the transitioning fan blade airfoils simulated by an adaptation of the mesh displacement method. A “real-time” simulation of the complete VPF hysteresis loop is achieved by specifying a blade wall motion through an Eulerian rotation matrix in differential, gradual steps, and is combined with a mesh probe-and-update routine for improved numerical accuracy and stability. The VPF is modeled to be transitioning in a modern 40000 lbf geared high bypass ratio turbofan engine architecture at “Approach Idle” engine power setting in a typical twin-engine airframe with the flaps, slats, and spoilers set for an aircraft touchdown airspeed of 140 knots. The transition to reverse thrust mode involves flow starvation into the engine, formation of recirculation zones in the bypass duct and the establishment of the reverse stream, all of which occurs in the opposing presence of the freestream flow at aircraft touchdown velocity. The transition back to forward flow mode involves the gradual reestablishment of the freestream, which is opposed by the presence of the reverse stream within the engine. It is quantified that in the transition to reverse thrust, the blockage develops with a larger time delay than the disappearance of the blockage during the transition back due to the interplay of the temporal dynamics of fan blade motion and flow field response. The details of the changes in the flow field behavior, the effect of engine power setting and aircraft touch-down velocity on the hysteresis behavior are explained in detail in the paper. Additional manifestations of the hysteresis phenomena at reverse thrust involving engine spool-up and down, and aircraft acceleration-deceleration maneuvers are also explored. The hysteresis phenomena described in this work are critical in properly developing control schedules to adapt for potential bistable flow field development during the landing run. The study addresses another part of the puzzle in exploring the feasibility of reverse thrust capable VPF engines for future sustainable aircraft to reach aviation climate neutrality.Rolls Royce plcJournal of Engineering for Gas Turbines and Powe
Federated reinforcement learning enhanced human-robotic systems: a comprehensive review
Get PDFFederated Reinforcement learning (FRL) presents a transformative approach for leveraging Human-robot collaboration (HRC) systems by addressing critical challenges in traditional learning paradigms. This paper provides a comprehensive review of the current state of FRL technology and its potential applications within HRC systems. The adaptation of FRL in HRC system is still in its infancy. This review systematically analyses the development trends, current challenges, and future prospects of various learning approaches within HRC systems. The paper highlights the critical factors of developing a conceptual frame-work for FRL within HRC systems to fully realise the potential of FRL. This paper aims to provide valuable insights and guidance for future research efforts focused on advancing FRL technology for human-robotic collaboration.2024 IEEE International Conference on e-Business Engineering (ICEBE
Named entity recognition in aviation products domain based on BERT
Get PDFThe aviation products' manufacturing industry is undergoing a profound transformation towards intelligence, among which the construction of a knowledge graph specifically for the aviation field has become the core link in achieving cognitive intelligence. In the process of knowledge graph construction, named entity recognition (NER) is a key step and one of the main tasks of knowledge extraction. Given the high degree of specialisation of aviation product text data and the wide span of contextual information, existing models often perform poorly in entity extraction. This paper proposes a new Named Entity Recognition (NER) method specifically tailored for the aviation product field (BBC-Ap), introducing an innovative approach that leverages domain-specific ontologies and advanced deep learning algorithms to significantly enhance the accuracy and efficiency of entity extraction from complex technical documents. The first step of this method is to establish an ontology model of aviation products and annotate the relevant text data to form a dataset for training the named entity model. Next, it adopts a multi-level model structure based on BERT, in which BERT is used to generate word vector representations, a bidirectional long short-term memory network (BiLSTM) is used as an encoder to extract semantic features, and a conditional random field (CRF) is used as a decoder to achieve optimal label assignment. Through experiments on the constructed aviation product dataset, the model achieved a Precision value of 91.74%, a Recall value of 92.46%, and an F1 score of 92.1%, Compared with other baseline models, the F1-score is improved by 0.9% to 1.5%. At the same time, the model also performs well on standard datasets such as CoNLLpp, with a Precision value of 92.87%, a Recall value of 92.54%, and an F1-Score of 92.70%. Finally, the model was used to successfully construct a knowledge graph reflecting the relationships between aviation products in Neo4j, further demonstrating the effectiveness and practicality of the method.Engineering and Physical Sciences Research CouncilEngineering and Physical Sciences Research Council (EPSRC), Grant Number: EP/Z533221/1IEEE Acces
Enhancing pure oscillatory response motion performance: innovative designs for semi-submersible and catamaran floating photovoltaic systems (FPVs) in various sea-state conditions
Get PDFA study approach to the novel design of floating photovoltaic systems has been provided using CFD simulation to determine motion characteristics on irregular waves with the JONSW AP spectrum under various water conditions. The simulation included in the frequency domain, shows that the CFPV model exhibits more stable behavior compared to its alternative model. This is due to the findings that the SFPV model has motion excitation associated with its own RAO against the wave energy spectrum at a frequency of 2.13 rad/sec (SS-2). This leads to a significantly dominant difference in motion quality concerning the significant response motion parameter. The quality difference values can be distinguished as heave with a value of 0.26 meters, roll with a value of 4.19°, and pitch with a value of 1.27°.The authors express their gratitude to the Institut Teknologi Sepuluh Nopember for providing financial support for the study project through the "ITS Center Collaboration Research Scheme" under contract number: 1322/PKS/ITS/2024.2024 International Conference on Sustainable Energy: Energy Transition and Net-Zero Climate Future (ICUE
Optimized AI methods for rapid crack detection in microscopy images
Get PDFDetecting structural cracks is critical for quality control and maintenance of industrial materials, ensuring their safety and extending service life. This study enhances the automation and accuracy of crack detection in microscopic images using advanced image processing and deep learning techniques, particularly the YOLOv8 model. A comprehensive review of relevant literature was carried out to compare traditional image-processing methods with modern machine-learning approaches. The YOLOv8 model was optimized by incorporating the Wise Intersection over Union (WIoU) loss function and the bidirectional feature pyramid network (BiFPN) technique, achieving precise detection results with mean average precision ([email protected]) of 0.895 and a precision rate of 0.859, demonstrating its superiority in detecting fine cracks even in complex and noisy backgrounds. Experimental findings confirmed the model’s high accuracy in identifying cracks, even under challenging conditions. Despite these advancements, detecting very small or overlapping cracks in complex backgrounds remains challenging. Our future work will focus on optimizing and extending the model’s generalisation capabilities. The findings of this study provide a solid foundation for automatic and rapid crack detection in industrial applications and indicate potential for broader applications across various fields.Electronic
Short-term memory artificial neural network modelling to predict concrete corrosion in wastewater treatment plant inlet chambers using sulphide sensors
Get PDFSulphide accumulation in lengthy rising mains can lead to significant concrete corrosion and odour issues at manholes and wastewater treatment plants (WWTPs). Monitoring dissolved sulphide, typically relies on auto-sampling or grab samples followed by laboratory analysis, remains underdeveloped. This study aimed to identify sources of concrete corrosion sources at a WWTP inlet chamber and develop a sulphide prediction model using artificial intelligence (AI). A dissolved sulphide sensor was installed at three rising mains (RM1 to RM3) and the combined inlet at a full-scale WWTP, providing a 5-minute resolution data that revealed a daily hydrogen sulphide (H2S) pattern that inversely correlated with the flow rate. RM1 exhibited the highest sulphide load, peaking at 3.6 kg/d during cold months and 4.2 kg/d during warm months. RM3 and RM2 recorded loads of 2.96 kg/d and 0.98 kg/d, respectively, during cold months. A long short-term memory (LSTM) artificial neural network (ANN) model was developed to predict H₂S concentrations at RM1, using flow rate, temperature, and time of day as inputs. The model achieved a root mean square error (RMSE) of 0.34 and a Nash-Sutcliffe efficiency (NSE) of 0.57, accurately predicting the daily H2S pattern. This study's main contributions include insights into sulphide dynamics from high-resolution sensor data, which could support corrosion management as part of a septicity warning system or feedforward control for sulphide treatment. Additionally, the AI-based prediction model offers potential for sensor repurposing, saving both capital and operational costs.Engineering and Physical Sciences Research CouncilThe authors gratefully acknowledge financial support from the Engineering and Physical Sciences Research Council (EPSRC) [grant number EP/R512515/1] through their funding of the STREAM Industrial Doctorate Centre, and the Industry project sponsor Thames Water.Journal of Water Process Engineerin
Influence of animal manure extracts on physico-chemical and nutritional quality of tomatoes grown in soilless cultivation
Get PDFIn response to environmental challenges facing the agricultural sector, growers are moving toward innovative and sustainable cultivation methods such as the hydroponic production system. This study evaluated the effect of different sources of manure on the physico-chemical and nutritional qualities of tomatoes (cv. CLX 532) grown under a hydroponic system. The experiment was set up in a completely randomized design with four treatments, which included three types of animal manure-derived hydroponic nutrient extracts, namely, chicken (CHME), cow (CME) and goat (GME), and a commercial fertilizer as a control. Tomato fruit from each treatment were harvested and analysed for macro- and micronutrients, physicochemical attributes such as total soluble solids (TSS), titratable acidity (TA), total soluble solid to titratable acidity ratio (TSS/TA), BrimA, colour index and firmness. The total phenolics and ascorbic acid content were also assessed. The results showed significant differences in physico-chemical and nutritional quality among different treatments. TSS was higher in CHME (6.47 °Brix) compared to other treatments. The TA was higher in both commercial fertilizer and CHME (0.62% and 0.61%) than in GME and CME (0.44% and 0.39%). Both TSS/TA and BrimA were lower in commercial fertilizer and than in animal manure extracts (AME). CHME had a higher colour index (30.32) while GME had higher firmness (316.9 N) than other treatments. The phenolic content was notably higher in GME compared to the commercial fertilizer and AME. Fruit fertigated with commercial fertilizer had more macronutrient content while fruit fertigated with animal manure-based nutrient solutions had high micronutrients. Based on these findings, animal manure extracts, specifically CHME and GME, can be used as a nutrient source in the production of tomatoes as it produces good fruit quality which is comparable to commercial fertilizers.National Research FoundationThis research was funded by the National Research Foundation of South Africa (Grant number: MND210609609843 and PMDS230805140843).Horticultura