| 1. |
- Bragone, Federica
(författare)
-
Physics-Informed Neural Networks and Machine Learning Algorithms for Sustainability Advancements in Power Systems Components
- 2023
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- A power system consists of several critical components necessary for providing electricity from the producers to the consumers. Monitoring the lifetime of power system components becomes vital since they are subjected to electrical currents and high temperatures, which affect their ageing. Estimating the component's ageing rate close to the end of its lifetime is the motivation behind our project. Knowing the ageing rate and life expectancy, we can possibly better utilize and re-utilize existing power components and their parts. In return, we could achieve better material utilization, reduce costs, and improve sustainability designs, contributing to the circular industry development of power system components. Monitoring the thermal distribution and the degradation of the insulation materials informs the estimation of the components' health state. Moreover, further study of the employed paper material of their insulation system can lead to a deeper understanding of its thermal characterization and a possible consequent improvement.Our study aims to create a model that couples the physical equations that govern the deterioration of the insulation systems of power components with modern machine learning algorithms. As the data is limited and complex in the field of components' ageing, Physics-Informed Neural Networks (PINNs) can help to overcome the problem. PINNs exploit the prior knowledge stored in partial differential equations (PDEs) or ordinary differential equations (ODEs) modelling the involved systems. This prior knowledge becomes a regularization agent, constraining the space of available solutions and consequently reducing the training data needed. This thesis is divided into two parts: the first focuses on the insulation system of power transformers, and the second is an exploration of the paper material concentrating on cellulose nanofibrils (CNFs) classification. The first part includes modelling the thermal distribution and the degradation of the cellulose inside the power transformer. The deterioration of one of the two systems can lead to severe consequences for the other. Both abilities of PINNs to approximate the solution of the equations and to find the parameters that best describe the data are explored. The second part could be conceived as a standalone; however, it leads to a further understanding of the paper material. Several CNFs materials and concentrations are presented, and this thesis proposes a basic unsupervised learning using clustering algorithms like k-means and Gaussian Mixture Models (GMMs) for their classification.
|
|
| 2. |
- Bragone, Federica, et al.
(författare)
-
Physics-Informed Neural Networks for Modeling Cellulose Degradation in Power Transformers
- 2022
-
Ingår i: 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA). - : IEEE conference proceedings.
-
Konferensbidrag (refereegranskat)abstract
- Insulation is an essential part of power transformers, which guarantees an efficient and reliable operational life. It mainly consists of mineral oil and insulation paper. Most of the major failures of power transformers originate from internal insulation failures. Monitoring aging and thermal behaviour of the transformer’s insulation paper is achieved by different techniques, which consider the Degree of Polymerization (DP) to evaluate the cellulose degradation and other chemical factors accumulated in mineral oil. Given the physical and chemical nature of the problem of degradation, we couple it with machine learning models to predict the desired parameters for considered equations. In particular, the equation used applies the Arrhenius relation, which comprises parameters like the pre-exponential factor, which depends on the cellulose’s contamination content, and the activation energy, which is connected to the temperature dependence; both of the factors need to be estimated for our problem. For this reason, Physics-Informed Neural Networks (PINNs) are considered for solving the data-driven discovery of the DP equation.
|
|
| 3. |
- Bragone, Federica, et al.
(författare)
-
Physics-informed neural networks for modelling power transformer’s dynamic thermal behaviour
- 2022
-
Ingår i: Electric power systems research. - : Elsevier. - 0378-7796 .- 1873-2046. ; 211, s. 108447-108447
-
Tidskriftsartikel (refereegranskat)abstract
- This paper focuses on the thermal modelling of power transformers using physics-informed neural networks (PINNs). PINNs are neural networks trained to consider the physical laws provided by the general nonlinear partial differential equations (PDEs). The PDE considered for the study of power transformer’s thermal behaviour is the heat diffusion equation provided with boundary conditions given by the ambient temperature at the bottom and the top-oil temperature at the top. The model is one dimensional along the transformer height. The top-oil temperature and the transformer’s temperature distribution are estimated using field measurements of ambient temperature, top-oil temperature and the load factor. The measurements from a real transformer provide more realistic solution, but also an additional challenge. The Finite Volume Method (FVM) is used to calculate the solution of the equation and further to benchmark the predictions obtained by PINNs. The results obtained by PINNs for estimating the top-oil temperature and the transformer’s thermal distribution show high accuracy and almost exactly mimic FVM solution.
|
|
| 4. |
- Hellström, Henrik, et al.
(författare)
-
Software-Defined Wireless Communication for Industrial Control : A Realistic Approach
- 2019
-
Ingår i: IEEE Industrial Electronics Magazine. - : Institute of Electrical and Electronics Engineers Inc.. - 1932-4529 .- 1941-0115. ; 13:4, s. 31-37
-
Tidskriftsartikel (refereegranskat)abstract
- Wireless communication for industrial applications of fers multiple advantages over traditional wired communicat ion, such a s reduced installation and maintenance costs, increased flexibility, and better suitability for harsh conditions and mobile environments. However, many industrial applications feature high-performance requirements for latency and reliability, challenges which are difficult are to meet over the wireless channel. Currently available wireless technologies struggle to achieve these requirements, leaving a gap between industry demands and state-of-the-art performance. To close this gap, traditional solutions that rely on general-purpose chipsets could be replaced with dedicated solutions for industrial applications. In this article, we discuss the feasibility of designing an industrial wireless solution based on software-defined radio (SDR), the obtained results, and the role of softwarization in the future of industrial communication.
|
|
| 5. |
|
|
| 6. |
- Jiang, Xiaolin, et al.
(författare)
-
Delay Optimization for Industrial Wireless Control Systems Based on Channel Characterization
- 2020
-
Ingår i: IEEE Transactions on Industrial Informatics. - : Institute of Electrical and Electronics Engineers (IEEE). - 1551-3203 .- 1941-0050. ; 16:9, s. 5855-5865
-
Tidskriftsartikel (refereegranskat)abstract
- Wireless communication is gaining popularity in the industry for its simple deployment, mobility, and low cost. Ultralow latency and high reliability requirements of mission-critical industrial applications are highly demanding for wireless communication, and the indoor industrial environment is hostile to wireless communication due to the richness of reflection and obstacles. Assessing the effect of the industrial environment on the reliability and latency of wireless communication is a crucial task, yet it is challenging to accurately model the wireless channel in various industrial sites. In this article, based on the comprehensive channel measurement results from the National Institute of Standards and Technology at 2.245 and 5.4 GHz, we quantify the reliability degradation of wireless communication in multipath fading channels. A delay optimization based on the channel characterization is then proposed to minimize packet transmission times of a cyclic prefix orthogonal frequency division multiplexing system under a reliability constraint at the physical layer. When the transmission bandwidth is abundant and the payload is short, the minimum transmission time is found to be restricted by the optimal cyclic prefix duration, which is correlated with the communication distance. Results further reveal that using relays may, in some cases, reduce end-to-end latency in industrial sites, as achievable minimum transmission time significantly decreases at short communication ranges.
|
|
| 7. |
- Jiang, Xiaolin, et al.
(författare)
-
Packet Detection by a Single OFDM Symbol in URLLC for Critical Industrial Control : A Realistic Study
- 2019
-
Ingår i: IEEE Journal on Selected Areas in Communications. - : Institute of Electrical and Electronics Engineers (IEEE). - 0733-8716 .- 1558-0008. ; 37:4, s. 933-946
-
Tidskriftsartikel (refereegranskat)abstract
- Ultra-high reliable and low-latency communication (URLLC)is envisaged to support emerging applications with strict latency and reliability requirements. Critical industrial control is among the most important URLLC applications where the stringent requirements make the deployment of wireless networks critical, especially as far as latency is concerned. Since the amount of data exchanged in critical industrial communications is generally small, an effective way to reduce the latency is to minimize the packet's synchronization overhead, starting from the physical layer (PHY). This paper proposes to use a short one-symbol PHY preamble for critical wireless industrial communications, reducing significantly the transmission latency with respect to other wireless standards. Dedicated packet detection and synchronization algorithms are discussed, analyzed, and tuned to ensure that the required reliability level is achieved with such extremely short preamble. Theoretical analysis, simulations, and experiments show that detection error rates smaller than 10(-6) can be achieved with the proposed preamble while minimizing the latencies.
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
- Jiang, Xiaolin, et al.
(författare)
-
Reliable Minimum Cycle Time of 5G NR Based on Data-Driven Channel Characterization
- 2021
-
Ingår i: IEEE Transactions on Industrial Informatics. - : Institute of Electrical and Electronics Engineers (IEEE). - 1551-3203 .- 1941-0050. ; 17:11, s. 7401-7411
-
Tidskriftsartikel (refereegranskat)abstract
- Wireless communication is evolving to support critical control in automation systems. The fifth-generation (5G) mobile network air interface New Radio adopts a scalable numerology and mini-slot transmission for short packets that make it potentially suitable for critical control systems. The reliable minimum cycle time is an important indicator for industrial communication techniques but has not yet been investigated within 5G. To address such a question, this article considers 5G-based industrial networks and uses the delay optimization based on data-driven channel characterization (CCDO) approach to propose a method to evaluate the reliable minimum cycle time of 5G. Numerical results in three representative industrial environments indicate that following the CCDO approach, 5G-based industrial networks can achieve, in real-world scenario, millisecond-level minimum cycle time to support several hundred nodes with reliability higher than 99.9999%.
|
|
| 11. |
- Jiang, Xiaolin, et al.
(författare)
-
Using a Large Data Set to Improve Industrial Wireless Communications Latency, Reliability, and Security
- 2019
-
Ingår i: IEEE Industrial Electronics Magazine. - : Institute of Electrical and Electronics Engineers (IEEE). - 1932-4529 .- 1941-0115. ; 13:1, s. 6-12
-
Tidskriftsartikel (refereegranskat)abstract
- Trealize the Industry 4.0 vision and enable mobile connectivity and flexible deployment in harsh industrial environments, wireless communication is essential. But before wireless communications technology can be widely deployed for critical control applications, first it must be assessed, and that requires a comprehensive characterization of the wireless channel. This can be done by analyzing large amounts of wireless data collected from different industrial environments. In this article, we discuss the possibilities offered by a recently published industrial wireless data set. This data set is more exhaustive than measurements previously reported. We show two cases of how those data have been applied to improve latency performance and to investigate the feasibility of physical-layer security techniques for wireless communication in industrial environments.
|
|
| 12. |
- Laneryd, Tor, et al.
(författare)
-
Physics Informed Neural Networks for Power Transformer Dynamic Thermal Modelling
- 2022
-
Ingår i: IFAC Papersonline. - : Elsevier BV. - 2405-8963. ; , s. 49-54
-
Konferensbidrag (refereegranskat)abstract
- The emerging methodology of Physics Informed Neural Networks (PINNs) promises to combine available data and physical knowledge to achieve high accuracy and fast evaluation. Dynamic thermal modelling of power transformers is an application specifically set to benefit from these characteristics. Data collected during typical operation is not representative of extreme loading scenarios and the number of thermal sensors is limited. The detailed geometry is often not known by the asset owner which creates high uncertainty for physics-based simulation models. In this study, the transformer is modeled by the one-dimensional heat diffusion equation. PINN is constructed with a loss function including both data-based and physics-based terms. A time-dependent source term from a time series of measurement is also part of the PINN. The result is compared with a finite volume solution demonstrating good agreement. The PINN approach will be useful for further development in thermal modelling for power transformers. Copyright
|
|
| 13. |
- Oueslati, Khaoula, et al.
(författare)
-
Physics-Informed Neural Networks for modelling insulation paper degradation in Power Transformers
- 2022
-
Ingår i: 2022 IEEE International Conference on Electrical Sciences and Technologies in Maghreb (CISTEM).
-
Konferensbidrag (refereegranskat)abstract
- Power transformer’s insulation is an integral part of the health and performance of this power component. This paper uses Physics-Informed Neural Networks (PINNs) for predicting the lifetime and health indicator of the power transformer’s insulation material, which is expressed as the Degree of Polymerization (DP) of the polymeric material (in this case kraft paper). PINNs are a promising deep learning technique for solving scientific computing problems and are designed to incorporate prior knowledge of physical or chemical systems and to respect any symmetries, invariances, and conservation laws. The dynamics of the degradation process is modeled using ordinary differential equations. One major challenge in analyzing kraft paper degradation is estimating the unknown model parameters (e.g. rate constants) and thus predicting model dynamics. For this work, we aim to solve the data-driven discovery of the degradation process, infer the hidden kinetic parameters and predict the degree of polymerization. The final discussion also addresses the advantages and limitations of PINNs for solving this type of problems.
|
|
| 14. |
- Pan, Fei, et al.
(författare)
-
Physical-Layer Security for Industrial Wireless Control Systems
- 2018
-
Ingår i: IEEE Industrial Electronics Magazine. - : IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC. - 1932-4529 .- 1941-0115. ; 12:4, s. 18-27
-
Tidskriftsartikel (refereegranskat)abstract
- Wireless networks for industrial control systems are promising because of their reduced cost, flexible structure, and improved long-term reliability. However, wireless control systems are vulnerable to probing-free attacks (PFAs), which are not possible in wired control systems. Thus, wireless control systems must be made as secure as wired systems. Physical (PHY)-layer security technology (PHY-Sec) may be a new strategy for securing industrial wireless control systems. Among all PHY-Sec technologies, PHY-layer authentication is the first step for PHYSec in industrial wireless control systems. This article discusses the principles of PHY-Sec, its application to wireless control systems, and potential research directions.
|
|
| 15. |
- Pan, Fei, et al.
(författare)
-
Threshold-Free Physical Layer Authentication Based on Machine Learning for Industrial Wireless CPS
- 2019
-
Ingår i: IEEE Transactions on Industrial Informatics. - : IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC. - 1551-3203 .- 1941-0050. ; 15:12, s. 6481-6491
-
Tidskriftsartikel (refereegranskat)abstract
- Wireless industrial cyber-physical systems are increasingly popular in critical manufacturing processes. These kinds of systems, besides high performance, require strong security and are constrained by low computational capabilities. Physical layer authentication (PHY-AUC) is a promising solution to meet these requirements. However, the existing threshold-based PHY-AUC methods only perform ideally in stationary scenarios. To improve the performance of PHY-AUC in mobile scenarios, this article proposes a novel threshold-free PHY-AUC method based on machine learning (ML), which replaces the traditional threshold-based decision-making with more adaptive classification based on ML. This article adopts channel matrices estimated by the wireless nodes as the authentication input and investigates the optimal dimension of the channel matrices to further improve the authentication accuracy without increasing too much computational burden. Extensive simulations are conducted based on a real industrial dataset, with the aim of tuning the authentication performance, then further field validations are performed in an industrial factory. The results from both the simulations and validations show that the proposed method significantly improves the authentication accuracy.
|
|
| 16. |
|
|
| 17. |
- Welin Odeback, Oliver, et al.
(författare)
-
Physics-Informed Neural Networks for prediction of transformer’s temperature distribution
- 2022
-
Ingår i: 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA). - : IEEE.
-
Konferensbidrag (refereegranskat)abstract
- Physics-Informed Neural Networks (PINNs) are a novel approach to the integration of physical models into Neural Networks when solving supervised learning problems. PINNs have shown potential in mapping spatio-temporal input and the solution of a partial differential equation (PDE). However, despite their advantages for many applications, they often fail to train when target PDEs contain high frequencies or multi-scale features. Thermal modelling of power transformers is fundamental for improving their efficiency and extending their lifetime. In this work, we investigate the performance of different PINN architectures applied to a 1D heat diffusion equation with a specific heat source representing the heat distribution inside a transformer. Measurements, which include the top-oil temperature, the ambient temperature and the load factor are taken from a transformer in service. We demonstrate the limitations of PINNs, propose possible remedies, and provide an overall assessment of the potential of using PINNs for transformer thermal modelling.
|
|
| 18. |
- Yan, H., et al.
(författare)
-
Temperature prediction intelligent system based on BP neural network in wireless industrial IoT
- 2019
-
Ingår i: Proceedings - 2019 IEEE International Conference on Smart Internet of Things, SmartIoT 2019. ; , s. 50-55
-
Konferensbidrag (refereegranskat)abstract
- With the development of industrial Internet of Things, manual production in the factory has gradually changed to automated production, and the temperature requirements in many aspects of the production process are very strict. In order to control temperature more intelligently, reduce errors and improve production efficiency, through the study of BP neural network, this paper designs and implements an intelligent temperature prediction system based on BP neural network for wireless industrial Internet of Things. Through the selection of intelligent algorithms, the establishment of the model and the realization of the system, a temperature prediction system suitable for the actual production environment of the industrial Internet of Things and improving the accuracy according to the intelligent algorithm is finally realized. The system is relatively complete in function. Temperature prediction and error correction can accurately predict the change of temperature. It can meet the requirements of industrial production control and make the temperature control more stable.
|
|
| 19. |
- Zhan, Ming, et al.
(författare)
-
Wireless High-Performance Communications Improving Effectiveness and Creating Ultrahigh Reliability with Channel Coding
- 2018
-
Ingår i: IEEE Industrial Electronics Magazine. - : Institute of Electrical and Electronics Engineers (IEEE). - 1932-4529 .- 1941-0115. ; 12:3, s. 32-37
-
Tidskriftsartikel (refereegranskat)abstract
- To meet a set of stringent requirements for wireless control in critical applications, the described wireless high-performance (WirelessHP) communication system represents a breakthrough regarding microsecondlevel latency, but the proof of ultrahigh reliability is still lacking. To this aim, we propose the incorporation of channel coding in its physical layer. Building on a customized protocol stack and a hardware demonstrator, we prove the effectiveness of channel coding and suggest further research in this area.
|
|
