| publications-4991 |
Conference paper |
2023 |
Wang S.; Wang L.; Wang A.B.; Luo Y. |
Leak Detection for Large Complex Gas Pipelines by Discrepancy Analysis of Simulated-Measured Pressure Profiles |
ACM International Conference Proceeding Series |
10.1145/3639592.3639612 |
|
|
|
While there are currently several methods available for pipeline leak detection, very few can be implemented on large complex gas pipelines in an intuitive and cost-efficient way. This is due to extensive measurements and additional instrumentations being rudimentary for such implementations to reach the expected real-Time performances. This study explores a leak detection technology built for large, complex gas pipelines, created as a virtual simulation and a digital twin for real pipeline systems, that parallels the dynamic behaviors of the transient flows over time and space. The virtual system works as a mirror of the real systems to reveal the occurrences of abnormal events. Thus, leaks can be observed and located by analyzing discrepancies in the simulated-measured pressure profiles of real-Time transient models (PPRTM). The key assumption of this method is that discrepancies arising from the simulated-measured pressure profiles imply signatures of pipeline leaks. Such an assumption is verified by in-lab experiments as well as field trials. The underlying principles, assumptions, experiments, simulations, trials, and implementation of the PPRTM will be discussed in this study in detail. The application of this method on the YUJI natural gas pipeline system demonstrates that PPRTM is suitable as an efficient and effective implementation on large complex pipeline systems. The method provides a new way of continuously monitoring and locating the occurrences of leaks. It overcomes limitations of existing leak detection systems (LDS) since the pipeline system is monitored as whole and no extra measurements and instrumentation are required. Likewise, it is compatible with standard configurations of the supervisory control and data acquisition (SCADA) system and it is also capable of detecting and locating multiple leaks on the same pipeline. Β© 2023 ACM. |
|
|
|
|
| publications-4992 |
Article |
2023 |
Nemoto R.H.; Ibarra R.; Staff G.; Akhiiartdinov A.; Brett D.; Dalby P.; Casolo S.; Piebalgs A. |
Cloud-based virtual flow metering system powered by a hybrid physics-data approach for water production monitoring in an offshore gas field |
Digital Chemical Engineering |
10.1016/j.dche.2023.100124 |
|
|
|
This work presents a cloud-based Virtual Flow Metering (VFM) system powered by a hybrid physics-data approach to estimate the water production per well in a gas field. This hybrid approach, which allows accurate calculations near real-time conditions, is based on the description of the flow through the wellbore using physics-based models pertaining to gas-liquid flows with high gas volume fraction. A data-driven approach is implemented to tune the flow model using well test data. This implementation accounts for changes in the well performance and increase in water production, resulting in a self-calibrating solution. This means that the model will remain accurate and relevant as production and well conditions change. Results from the VFM show good agreement with the well test data for steady-state conditions. The VFM calculations are performed remotely using a cloud-based DataOps platform where results are also stored. This allows continuous access to live sensor data to be used as input to other applications or visualized through a web interface. The VFM system uses a set of readily available sensors installed in the wells. Thus, it represents cost reduction in both capital and operating expenditures when compared to the installation of multiphase flow meters or separators. Β© 2023 Cognite AS |
|
|
|
|
| publications-4993 |
Article |
2023 |
Cancemi S.A.; Lo Frano R.; Santus C.; Inoue T. |
Unsupervised anomaly detection in pressurized water reactor digital twins using autoencoder neural networks |
Nuclear Engineering and Design |
10.1016/j.nucengdes.2023.112502 |
|
|
|
Deep learning (DL), that is becoming quite popular for prediction and analysis of complex patterns in large amounts of data is used to investigate the safety behaviour of the nuclear plant items. This is achieved by using multiple layers of artificial neural networks to process and transform input data, allowing for the creation of highly accurate predictive models. Particularly to the aim the unsupervised machine learning approach and the digital twin concept in form of pressurized water reactor 2-loop simulator are used. This innovative methodology is based on neural network algorithm that makes capable to predict failures of plant structure, system, and components earlier than the activation of safety and emergency systems. Moreover, to match the objective of the study several scenarios of loss of cooling accident (LOCA) of different break size were simulated. To make the acquisition platform realistic, Gaussian noise was added to the input signals. The neural network has been fed by synthetic dataset provide by PCTRAN simulator and the efficiency in event identification was studied. Further, due to the very limited studies on the unsupervised anomaly detection by means of autoencoder neural networks applied for plant monitoring and surveillance, the methodology has been validated with experimental data from resonant test rig designed for fatigue testing of tubular components. The obtained results demonstrate the reliability and the efficiency of the methodology in detecting anomalous events prior the activation of safety system. Particularly, if the difference between the expected readings and the collected data goes beyond the predetermined threshold, then the anomalous event is identified, e.g., the model detected anomalies up to 38 min before the reactor scram intervention. Β© 2023 |
|
|
|
|
| publications-4994 |
Conference paper |
2024 |
Fu Y.; ShouFu S.; ZhiGuo K.; Fang W.; Xin H. |
Research on Testing Platform Based on Electric Driven Digital Twin Model |
Lecture Notes in Electrical Engineering |
10.1007/978-981-97-0252-7_54 |
|
|
|
In order to solve the problem that multiple system integration tests cannot be carried out due to the lack of electric drive systems in the early stage of vehicle development, a virtual reality combination test scheme based on the digital twin model of electric drive systems was proposed, and a method for constructing the digital twin model of electric drive systems was presented. The calculated and measured values of the digital twin model of water outlet temperature of electric drive systems under different operating conditions were compared, with a maximum error of only 4.7%. This digital twin model has the characteristics of accuracy, efficiency, and stability. Based on this model, multiple system integration virtual reality integration testing can be completed in the absence of an electric drive system, and vehicle thermal management performance can be evaluated at the early stage of vehicle development. Β© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. |
|
|
|
|
| publications-4995 |
Article |
2023 |
Alekseev D.I.; Markov P.V. |
Validation of the Numerical Method for Solving the Flow Mixing Problem in the Annular Gap of a Water–Water Energetic Reactor |
Journal of Machinery Manufacture and Reliability |
10.1134/S1052618823070038 |
|
|
|
Abstract: This article is devoted to numerical modeling of the hydrodynamics in the pressure header of a mockup of a VVER-1000 water–water energetic reactor. The mockup is made on a reduced scale and is a part of the hydraulic stand E7-ELEMASh of the Department of Nuclear Reactors and Installations of Bauman Moscow State Technical University. The test stand and the calculation method based on computational fluid dynamics (CFD) are described. The influence of the calculation model parameters on the calculation results is analyzed. The calculation model is validated according to the physical experiments. Recommendations are given on the choice of the calculation method for the analysis of flow in water–water energetic reactors and the creation of digital twins. © 2023, Pleiades Publishing, Ltd. |
|
|
|
|
| publications-4996 |
Conference paper |
2024 |
Protasov Y.A.; Fedorov M.S.; Erofeev D.A. |
Development of a Digital Twin of a Mineral Water Deposit to Improve the Efficiency of Its Operation |
Proceedings of the 2024 Conference of Young Researchers in Electrical and Electronic Engineering, ElCon 2024 |
10.1109/ElCon61730.2024.10468157 |
|
|
|
Every year the demand for mineral waters increases, and therefore mining organizations are forced to increase production volumes. In the context of ever-increasing pressure on aquifers, there is a need to improve the efficiency of production volume management as a means of preventing the deterioration of aquifers. The article discusses the possibilities of using 'digital twin' technology to improve the efficiency of the exploitation process of a mineral water deposit. The development of a virtual representation of the aquifer system solves the problem of predicting the possible production volume using a generalized mathematical model and a data caching system. As a result of the research, an analytical platform is proposed that can predict changes in the state of the field based on specified field parameters. Β© 2024 IEEE. |
|
|
|
|
| publications-4997 |
Article |
2024 |
Manocha A.; Sood S.K.; Bhatia M. |
IoT-digital twin-inspired smart irrigation approach for optimal water utilization |
Sustainable Computing: Informatics and Systems |
10.1016/j.suscom.2023.100947 |
|
|
|
Agriculture industry faces the challenge of increasing productivity by 50% from 2012 to 2050 while reducing water usage, given that it currently consumes 69% of the world's freshwater. To achieve this goal, smart technologies such as Artificial Intelligence (AI), Digital Twins (DT), and Internet of Things (IoT) are being increasingly utilized. However, the use of DT in agriculture is still in its early stages. This study proposes a smart irrigation framework inspired by digital twins in an application domain. The irrigation framework's sensors and actuators are linked to their virtual counterparts to create a digital twin. The IoT platform collects, aggregates, and processes data to determine daily irrigation requirements, and the behavior of the irrigation system is simulated. The proposed framework has two main advantages: evaluating the behavior of the digital twin and IoT platform in the context of agriculture before integrating them into the field and comparing various irrigation methods with current farming methods. By providing farmers with information about soil, weather, and crops, the system has the potential to improve farm operations and reduce water consumption. Β© 2023 Elsevier Inc. |
|
|
|
|
| publications-4998 |
Article |
2023 |
Barimah A.K.; Niculita O.; McGlinchey D.; Cowell A. |
Data-Quality Assessment for Digital Twins Targeting Multi-Component Degradation in Industrial Internet of Things (IIoT)-Enabled Smart Infrastructure Systems |
Applied Sciences (Switzerland) |
10.3390/app132413076 |
|
|
|
Featured Application: The paper highlights the steps taken in checking the required data quality (both real and synthetic) before it is used for the development of services in the context of IIoT-enabled smart infrastructure systems. A case study of a scaled-down version of a water distribution system will be presented in detail and data from healthy and faulty conditions will be used to demonstrate the details of the data qualification process and the impact on various health assessment techniques meant to support fault detection and isolation of single and multi-component degradation scenarios. The paper also proposes an IIoT architecture for the instantiation of measurement system analysis. In the development of analytics for PHM applications, a lot of emphasis has been placed on data transformation for optimal model development without enough consideration for the repeatability of the measurement systems producing the data. This paper explores the relationship between data quality, defined as the measurement system analysis (MSA) process, and the performance of fault detection and isolation (FDI) algorithms within smart infrastructure systems. This research employs a comprehensive methodology, starting with an MSA process for data-quality evaluation and leading to the development and evaluation of fault detection and isolation (FDI) algorithms. During the MSA phase, the repeatability of a water distribution system’s measurement system is examined to characterise variations within the system. A data-quality process is defined to gauge data quality. Synthetic data are introduced with varying data-quality levels to investigate their impact on FDI algorithm development. Key findings reveal the complex relationship between data quality and FDI algorithm performance. Synthetic data, even with lower quality, can improve the performance of statistical process control (SPC) models, whereas data-driven approaches benefit from high-quality datasets. The study underscores the importance of customising FDI algorithms based on data quality. A framework for instantiating the MSA process for IIoT applications is also suggested. By bridging data-quality assessment with data-driven FDI, this research contributes to the design of digital twins for IIoT-enabled smart infrastructure systems. Further research on the practical implementation of the MSA process for edge analytics for PHM applications will be considered as part of our future research. © 2023 by the authors. |
|
|
|
|
| publications-4999 |
Article |
2023 |
Zhang R.; Liu Z.; Wang J.; Zhang W.; Han D.; Li T.; Zou X. |
On-line dynamic simulation and optimization of water-cooled cascade refrigeration system; [ζ°΄ε†·εΌ_x008f_ε¤_x008d_ε_x008f_ ε¶ε†·η³»η»_x009f_η_x009a_„ε_x009c_¨ηΊΏε_x008a_¨ζ€ζ¨΅ζ‹_x009f_δΈ_x008e_δΌε_x008c_–] |
Huagong Jinzhan/Chemical Industry and Engineering Progress |
10.16085/j.issn.1000-6613.2023-1020 |
|
|
|
A rigorous dynamic mechanism model was established using Unisim for a complex heat exchange system (water cooled cascade refrigeration system) coupled with an ethylene propylene cascade refrigeration system and a circulating water cooling system in a certain device. Real time acquisition of on-site data was achieved using OPC technology, resulting in the establishment of an online dynamic simulation system. Through online dynamic simulation, synchronous tracking between the model and the on-site device was achieved. The online dynamic model can reflect the current operating status of the on-site device, thus obtaining a high-precision digital twin model. In addition, to address the issue of high system energy consumption, a global simulation optimization was conducted with the objective function of minimizing total system power consumption and the decision variable of circulating water temperature. Among them, for the calculation of fan power, a prediction model for fan power was obtained through regression using one year's historical data of the factory, thus solving the problem of power calculation in the optimization process. Finally, the optimization results were validated and calculated online in the digital twin model, and the optimization effect was predicted. After optimization, the system saved a total of 772.69MW in power consumption, with a total annual cost savings of 564000CNY, bringing significant economic benefits to the enterprise. Β© 2023 Chemical Industry Press. All rights reserved. |
|
|
|
|
| publications-5000 |
Conference paper |
2023 |
Faluomi V. |
A digital twin application for vineyards sustainable management |
BIO Web of Conferences |
10.1051/bioconf/20236801038 |
|
|
|
Environmental protection and production sustainability are the key actions required to the farming activities, especially to those with higher add value as wine production. Vineyard are one of the most demanding activities in terms of water consumption and environmental impacts, which can be mitigated only with a systematic approach based on smart agriculture to support and optimize vineyard management. This paper proposes a vineyard digital twin (VDT) based on a mathematical model able to predict the vegetative and productive growth of a vineyard (leaf area, shoot length, crop and yield mass), qualitative product parameters (sugar and acid) and the water footprint associated with production. The model implements a soil-atmosphere source-sink model, where water balance across vine is coupled with potential carbon demand functions to estimate water and temperature stresses and, through a mechanistic model for sugar accumulation and acid concentration, will evaluate the expected grape quality. The distinctive trait of this model is the integration and feedback among prediction of grapevine quality and vegetative growth, using a common boundary data set and integrating the agronomical operations on vineyard seasonal development. The VDT prototype will help producers to systematize, formalize, and accumulate knowledge to improve and optimize management processes to achieve sustainable production, increasing products healthy and reducing environmental footprint. Β© The Authors, published by EDP Sciences. This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0 (https://creativecommons.org/licenses/by/4.0/). |
|
|
|
|
