Power transformers are subjected to electrical currents and temperature fluctuations that, if not properly controlled, can lead to major deterioration of their insulation system. Therefore, monitoring the temperature of a power transformer is fundamental to ensure a long-term operational life. Models presented in the IEC 60076-7 and IEEE standards, for example, monitor the temperature by calculating the top-oil and the hot-spot temperatures. However, these models are not very accurate and rely on the power transformers' properties. This paper focuses on finding an alternative method to predict the top-oil temperatures given previous measurements. Given the large quantities of data available, machine learning methods for time series forecasting are analyzed and compared to the real measurements and the corresponding prediction of the IEC standard. The methods tested are Artificial Neural Networks (ANNs), Time-series Dense Encoder (TiDE), and Temporal Convolutional Networks (TCN) using different combinations of historical measurements. Each of these methods outperformed the IEC 60076-7 model and they are extended to estimate the temperature rise over ambient. To enhance prediction reliability, we explore the application of quantile regression to construct prediction intervals for the expected top-oil temperature ranges. The best-performing model successfully estimates conditional quantiles that provide sufficient coverage.

Our work aims at simulating and predicting the temperature conditions inside a power transformer using Physics-Informed Neural Networks (PINNs). The predictions obtained are then used to determine the optimal placement for temperature sensors inside the transformer under the constraint of a limited number of sensors, enabling efficient performance monitoring. The method consists of combining PINNs with Mixed Integer Optimization Programming to obtain the optimal temperature reconstruction inside the transformer. First, we extend our PINN model for the thermal modeling of power transformers to solve the heat diffusion equation from 1D to 2D space. Finally, we construct an optimal sensor placement model inside the transformer that can be applied to problems in 1D and 2D.

Cellulose Nanofibrils (CNFs), highly present in nature, can be used as building blocks for future sustainable materials, including strong and stiff filaments. A rheo-optical flow-stop technique is used to conduct experiments to characterize the CNFs by studying Brownian dynamics through the CNFs' birefringence decay after stop. As the experiments produce large quantities of data, we reduce their dimensionality using Principal Component Analysis (PCA) and exploit the possibility of visualizing the reduced data in two ways. First, we plot the principal components (PCs) as time series, and by training LSTM networks assigned for each PC time series with the data before the flow stop, we predict the behavior after the flow stop (Bragone et al., 2024). Second, we plot the first PCs against each other to create clusters that give information about the different CNF materials and concentrations. Our approach aims at classifying the CNF materials to varying concentrations by applying unsupervised machine learning algorithms, such as k-means and Gaussian Mixture Models (GMMs). Finally, we analyze the Autocorrelation Function (ACF) and the Partial Autocorrelation Function (PACF) of the first principal component, detecting seasonality in lower concentrations.

Recent works on applying Physics-Informed Neural Networks to traffic density estimation have shown promise for future developments due to their robustness to model errors and noisy data. In this paper, we introduce a methodology for online approximation of the traffic density using measurements from probe vehicles in two settings: one using the Greenshield model and the other considering a high-fidelity traffic simulation. The proposed method continuously estimates the real-time traffic density in space and performs model identification with each new set of measurements. The density estimate is updated in almost real-time using gradient descent and adaptive weights. In the case of full model knowledge, the resulting algorithm performs similarly to the classical open-loop one. However, in the case of model mismatch, the iterative solution behaves as a closed-loop observer and outperforms the baseline method. Similarly, the proposed algorithm correctly reproduces the traffic characteristics in the high-fidelity setting.

Transformers are crucial for reliable and efficient power system operations, particularly in supporting the integration of renewable energy. Effective monitoring of transformer health is critical to maintain grid stability and performance. Thermal insulation ageing is a key transformer failure mode, which is generally tracked by monitoring the hotspot temperature (HST). However, HST measurement is complex, costly, and often estimated from indirect measurements. Existing HST models focus on space-agnostic thermal models, providing worst-case HST estimates. This article introduces a spatio-temporal model for transformer winding temperature and ageing estimation, which leverages physics-based partial differential equations (PDEs) with data-driven Neural Networks (NN) in a Physics Informed Neural Networks (PINNs) configuration to improve prediction accuracy and acquire spatio-temporal resolution. The computational accuracy of the PINN model is improved through the implementation of the Residual-Based Attention (PINN-RBA) scheme that accelerates the PINN model convergence. The PINN-RBA model is benchmarked against self-adaptive attention schemes and classical vanilla PINN configurations. For the first time, PINN based oil temperature predictions are used to estimate spatio-temporal transformer winding temperature values, validated through PDE numerical solution and fiber optic sensor measurements. Furthermore, the spatio-temporal transformer ageing model is inferred, which supports transformer health management decision-making. Results are validated with a distribution transformer operating on a floating photovoltaic power plant.

Aviation and maritime shipping are hard-to-abate transport sectors that are heavily dependent on fossil fuels. They jointly account for nearly 10 % of global greenhouse gas emissions, while infrastructure and investments are locked into high-carbon pathways for decades. Fuels and technologies to decarbonize include advanced biofuels, electrofuels, hydrogen and electric propulsion. This research aims to analyse the decarbonization strategies for maritime shipping and aviation from a comparative perspective, and analyzing the role of different actors for disruption to break through carbon lock-in and path dependency. The research uses Sweden as a case study and applies qualitative methods, including expert interviews, focus group discussions and site visits. Our research finds that aviation and maritime shipping are slowly changing, albeit with different dynamics. Both sectors show that incumbent regime actors play a major role in shaping transition pathways and disrupting the (quasi)equilibrium, while niche innovation is often developed together by incumbents and niche players.

Dynamic rating of the transformer is a promising technology, which is suitable for various applications. Using dynamic rating for connecting renewable energy is believed to be beneficial for the economy and flexibility of the power system. However, to safely deploy such operation strategies, it is important to have more precise estimates for the total costs of owning such units and determine how effective such operation method is for a solar power plant. This study proposes a method for calculating total ownership costs (TOC) of dynamically rated transformers used for the connection of the solar power plant to the grid as well as analyzes its efficiency. The sensitivity analysis looks into the change in TOC and peak efficiency index (PEI) after considering reactive power dispatch. Results of this study also show how TOC, PEI, and load and no-load losses change depending on the transformer size.

Dynamic Transformer Rating (DTR) allows unlocking extra capacity of power transformers using real-time weather data and has been proven to be specifically attractive for application to wind farm substation transformers. In this work, we explore an extreme case where the wind farm expanded to 150% of its original rated power while being connected to the grid with the same transformer to simulate a 1:1.5 ratio between rated generation and rated transformer capacity. The focus of the study is to explore the operational challenges of using such a system in a framework of day-ahead dispatch planning, which is done by building a combined forecasting model for 36-hour ahead prediction of wind farm generation and the transformer capacity as well as their match together. The goal is to estimate how often the wind farm generation would exceed the available capacity at the substation and would be required to curtail as well as assign accuracy to the curtailment decision. The results indicate that the model shows sufficient prediction accuracy for exceeding the maximum allowable transformer temperature. Main indication of the model accuracy is the ability to correctly predict instances of transformer overheating, which in this case are below 3.5%. However, since the accuracy of correctly ordered curtailment is at 85% for the lower transformer hot spot temperature limit, future studies should focus on improving current results by possibly integrating other time series forecasting models.

As the quest for more sustainable and environmentally friendly materials has increased in the last decades, cellulose nanofibrils (CNFs), abundant in nature, have proven their capabilities as building blocks to create strong and stiff filaments. Experiments have been conducted to characterize CNFs with a rheo-optical flow-stop technique to study the Brownian dynamics through the CNFs’ birefringence decay after stop. This paper aims to predict the initial relaxation of birefringence using Principal Component Analysis (PCA) and Long Short-Term Memory (LSTM) networks. By reducing the dimensionality of the data frame features, we can plot the principal components (PCs) that retain most of the information and treat them as time series. We employ LSTM by training with the data before the flow stops and predicting the behavior afterward. Consequently, we reconstruct the data frames from the obtained predictions and compare them to the original data.

An increase in electricity demand and renewable penetration requires electrical utilities to improve and optimize the grid infrastructure. Fundamental components in this grid infrastructure are transformers, which are designed conservatively based on static rated power. However, load and weather change continuously and hence, transformers are not used most efficiently. For this reason, new technology has been developed: Dynamic transformer rating (DTR). Applying DTR makes it possible to load transformers above the nameplate rating without affecting their lifetime expectancy. This study uses DTR for short-term and long-term wind farm planning. The optimal wind farm is designed by applying DTR to the power transformer and using it as an input to a Mixed-Integer Linear Programming (MILP) model. Regarding the transformer thermal analysis, the linearized top oil model of IEEE Clause 7 is selected. The model is executed for 4 different types of power transformers: 63 MVA, 100 MVA, 200 MVA and 400 MVA. As a result, it is obtained that the net present value for the investment and the capacity of the wind farm increase linearly with respect to the size of the transformer. Then, a sensitivity analysis is carried out by modifying the wind speed, the electricity price, the lifetime of the transformer and the selected weather data. From this sensitivity analysis, it is possible to conclude that wind resources and electricity price are critical parameters for the wind farm’s feasibility.