20505 research outputs found
Sort by
Multi-channel anomaly detection using graphical models
Get PDFAnomaly 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.Engineering and Physical Sciences Research CouncilJournal of Intelligent Manufacturin
Geopolitical disruptions and supply chain structural ambidexterity
Get PDFPurpose
This paper seeks insights into how multinational enterprises restructure their global supply chains to manage the uncertainty caused by geopolitical disruptions. To answer this question, we investigate three significant geopolitical disruptions: Brexit, the US-China trade war and the coronavirus disease 2019 (Covid-19) pandemic.
Design/methodology/approach
The study uses an inductive theory-elaboration approach to build on Organisational Learning Theory and Dunning’s eclectic paradigm of international production. Twenty-nine expert interviews were conducted with senior supply chain executives across 14 multinational manufacturing firms. The analysis is validated by triangulating secondary data sources, including standard operating procedures, annual reports and organisational protocols.
Findings
We find that, when faced with significant geopolitical disruptions, companies develop and deploy supply chain structural ambidexterity in different ways. Specifically, during Covid-19, the US-China trade war and Brexit, companies developed and deployed three distinct types of supply chain structural ambidexterity through (1) partitioning internal subunits, (2) reconfiguring supplier networks and (3) creating parallel supply chains.
Originality/value
The findings contribute to Dunning’s eclectic paradigm by explaining how organisational ambidexterity is extended beyond firm boundaries and embedded in supply chains to mitigate uncertainty and gain exploration and exploitation benefits. During significant geopolitical disruptions, we find that managers make decisions in tight timeframes. Therefore, based on the transition time available, we propose three types of supply chain structural ambidexterity. We conclude with a managerial framework to assist firms in developing supply chain structural ambidexterity in response to geopolitical disruptions.International Journal of Operations and Production Managemen
Interactive effects of deformable wave energy converters operating in close proximity
Get PDFFlexible wave energy converters (FlexWECs) have been gaining increasing research and industrial interest as their deformable nature can potentially remedy the structural issues that limit the development of rigid WECs. To maximise the usage of space and infrastructure and improve energy efficiency, FlexWECs are normally deployed in close proximity, where the wave interaction with one device can influence others, signifying the opportunity to obtain energy efficiency enhancement from the interactions. To investigate the power capture performance of a FlexWEC array, this study employed a validated three-dimensional high-fidelity computational method to simulate the wave interaction with three FlexWECs in various array arrangements including power-take off. Based on systematic simulation cases, the present work analysed the relation between the geometrical characteristics of an isolated FlexWEC's perturbed wave field and the array's overall energy capture efficiency. The constructive interaction of the array was found the strongest when the longitudinal and lateral spacings of the array were 0.6 and 1 times of incident wavelength respectively, with a 15 % enhancement of overall captured energy compared to three devices operating in isolation. Overall, this study provides insights into the fluid-structure interaction of waves with multiple deformable structures, facilitating the modelling and planning of FlexWECs.Innovate UKL.H. acknowledges grants received from Innovate UK (No. 10048187, 10079774, 10081314), the Royal Society (IEC∖NSFC∖223253, RG∖R2∖232462) and UK Department for Transport (TRIG2023 – No. 30066).Energ
Motion prediction and object detection for image-based visual servoing systems using deep learning
Get PDFThis study primarily investigates advanced object detection and time series prediction methods in image-based visual servoing systems, aiming to capture targets better and predict the motion trajectory of robotic arms in advance, thereby enhancing the system’s performance and reliability. The research first implements object detection on the VOC2007 dataset using the Detection Transformer (DETR) and achieves ideal detection scores. The particle swarm optimization algorithm and 3-5-3 polynomial interpolation methods were utilized for trajectory planning, creating a unique dataset through simulation. This dataset contains randomly generated trajectories within the workspace, fully simulating actual working conditions. Significantly, the Bidirectional Long Short-Term Memory (BILSTM) model was improved by substituting its traditional Multilayer Perceptron (MLP) components with Kolmogorov–Arnold Networks (KANs). KANs, inspired by the K-A theorem, improve the network representation ability by placing learnable activation functions on fixed node activation functions. By implementing KANs, the model enhances parameter efficiency and interpretability, thus addressing the typical challenges of MLPs, such as the high parameter count and lack of transparency. The experiments achieved favorable predictive results, indicating that the KAN not only reduces the complexity of the model but also improves learning efficiency and prediction accuracy in dynamic visual servoing environments. Finally, Gazebo software was used in ROS to model and simulate the robotic arm, verify the effectiveness of the algorithm, and achieve visual servoing.Electronic
Long-range hydrological drought forecasting using multi-year cycles in the North Atlantic Oscillation
Get PDFWith global temperatures, populations and ecological stressors expected to rise, hydrological droughts are projected to have progressively severe economic and environmental impacts. As a result, hydrological drought forecasting systems have become increasingly important water resource management tools for mitigating these impacts. However, high frequency behaviours in meteorological or atmospheric conditions often limit the lead times of hydrological drought forecasts to seasonal timescales, either through poorer performance of multi-year meteorological forecasts or the lack of multi-year lags in atmosphere-hydrology systems. By contrast, low frequency behaviours in regionally important teleconnection systems (such as the North Atlantic Oscillation, NAO) offer a novel way to forecast hydrological drought at longer lead times. This paper shows that, by using a data-driven modelling approach, long-term behaviours within the NAO can be skilful predictors of hydrological drought conditions at a four-year forecasting horizon. Multi-year semi-periodic patterns in the NAO were used to forecast regional groundwater drought coverage in the UK (proportion of groundwater boreholes in drought), with the greatest forecast performance achieved for longer duration droughts, and for hydrogeological regions with longer response times. Model errors vary from 14 % (proportion of boreholes, (MAE)) in flashy hydrological regions or short droughts (8 months). Model fits of r2 up to 0.8 were produced between simulated and recorded regional drought coverage. As such our results show that teleconnection indices can be a skilful predictor of hydrological drought dynamics at multi-year timescales, opening new opportunities for long-lead groundwater drought forecasts to be integrated within existing drought management strategies in Europe and beyond.Journal of Hydrolog
Dataset "A Novel Hybrid Electrochemical Equivalent Circuit Model for Online Battery Management Systems"
No full textA Novel Hybrid Electrochemical Equivalent Circuit Model for Online Battery Management System
Searching molecular biomarkers correlating with BSID-III at 24 months in infants with neonatal hypoxic-ischemic encephalopathy
Get PDFAn early prediction of outcomes of neonatal hypoxic-ischemic encephalopathy (NE) is of key importance in reducing neonatal mortality and morbidity. The objectives were (i) to analyze the characteristics of miRNA expression and metabolic patterns of neonates with NE and (ii) to assess their predictive performance for neurodevelopmental outcomes. Plasma samples from moderate/severe NE patients (N = 92) of the HYPOTOP study were collected before, during, and after therapeutic hypothermia (TH) and compared to a control group (healthy term infants). The expression of miRNAs and concentrations of metabolites (hypoxia-related and energy, steroid, and tryptophan metabolisms) were analyzed. Neurodevelopmental outcomes were evaluated at 24 months postnatal age using Bayley Scales of Infant Development, ed. III, BSID-III. Differences in miRNA and metabolic profiles were found between NE vs. control infants, abnormal (i.e., mildly and moderately abnormal and severe) vs. normal, and severe vs. non-severe (i.e., normal and mildly and moderately abnormal) BSID-III. 4-Androstene-3,17-dione, testosterone, betaine, xanthine, and lactate were suitable for BSID-III outcome prediction (receiver operating characteristic areas under the curve (AUCs) ≥ 0.6), as well as 68 miRNAs (AUCs of 0.5–0.9). Significant partial correlations of xanthine and betaine levels and the expression of several miRNAs with BSID-III sub-scales were found.
Conclusion: We have identified metabolites/miRNAs that might be useful to support the prediction of middle-term neurodevelopmental outcomes of NE.This study has been funded by Instituto de Salud Carlos III (ISCIII) through the project “RD21/0012/0015” and co-funded by the European Union—NextGenerationEU.European Journal of Pediatric
A modular UAV hardware platform for aerial indoor navigation research and development
Get PDFThis study introduces a specialised hardware plat-form designed for indoor navigation, featuring a quadrotor equipped with either a NVIDIA Jetson Nano or a Z-turn Zynq onboard computer. The onboard computer communicates via ROS2 with the flight controller, the Inertial Measurement Unit (IMU), Ultra-WideBand (UWB) localisation system, stereo camera, Light Detection and Ranging (LiDAR), and ultrasonic sensors. The focus is on creating a low-cost modular Unmanned Aerial Vehicle (UAV) system adaptable to various indoor navigation applications. The modular design encompasses different onboard computer platforms and sensor configurations, allowing for easy adaptation to research experiment setups. The objective is to facilitate the transition from simulated and simplified laboratory experiments to deploying aerial robots in challenging real-world conditions. The paper explores the hardware architecture and Robot Operating System 2 (ROS2)-based communication system of the UAV and provides a weight analysis and power estimation.2024 International Conference on Unmanned Aircraft Systems (ICUAS
A comprehensive educational App for propulsion systems
Get PDFThis paper presents the development of a multi-platform application for rapid aeroengine performance simulation which aims to reshape conventional educational processes in aerospace propulsion taught courses. This is facilitated by enhancing students’ interaction with a broad spectrum of propulsion concepts, ranging from subsonic to hypersonic regimes. The motivation of this app draws upon the ever-increasing use of smartphone apps among the student community. It is envisaged that this phenomenon could be beneficial to widen students’ knowledge. The user of the app can rapidly extract the thermodynamic and performance parameters at different operating conditions for several propulsion concepts, including conventional turbojets and turbofans, as well as ramjets, turboramjets and advanced, pre-cooled, combined cycle engines. The development process of the application as well as the built-in models are described in detail herein. The app is employed in an aeroengine technology course in Greece and used by the students to investigate the fundamental operating principles of advanced propulsion systems. These include a turboramjet, a hydrogen-powered ramjet as well as a hybrid, pre-cooled, air-breathing rocket-cycle concept. This is facilitated through the use of the app for the performance modeling of each one of the propulsive architectures. Results show that the impact of the app on the educational process is beneficial, with the vast majority of the students providing positive feedback. It is found that the app has far increased their interest and level of knowledge related to propulsion systems, in comparison to traditional teaching techniques. This would have been impossible in the time frame of an academic semester without the implementation of the app.ASME Turbo Expo 2024: Turbomachinery Technical Conference and Expositio
Destination and time-series inference of moving objects via conditionally Markov process
Get PDFThis paper presents a destination and time-series inference algorithm for tracking moving targets. The destination of the object is considered the intent, and inference and state estimation are performed in the Bayesian framework. To describe the destination-aware target motion, we construct the state transition model using a conditionally Markov process. We introduce a multiple model to achieve simultaneous intent and time-series inferences. Given finite destination candidates, the maximum a posteriori hypothesis is chosen as the destination. For time-series inference, local estimates obtained from Kalman filters are fused to yield target state estimates. To address unspecified terminal conditions, the proposed algorithm incorporates parameter correction techniques based on relative geometry. Numerical simulations are performed to validate the proposed inference algorithm.National Research Foundation of Korea, Ministry of Science and ICTThis work was supported by the National Research Foundation of Korea (NRF) Grant funded by the Korea government (no. 2023K2A9A1A01098669).CEAS Aeronautical Journa