Transmission Failure Prediction Using AI and Structural Modeling Informed by Distribution Outages

Understanding and quantifying the impact of severe weather events on the electric transmission and distribution system is crucial for ensuring its resilience in the context of the increasing frequency and intensity of extreme weather events caused by climate change. While weather impact models for the distribution system have been widely developed during the past decade, transmission system impact models lagged behind because of the scarcity of data. This study demonstrates a weather impact model for predicting the probability of failure of transmission lines. It builds upon a recently developed model and focuses on reducing model bias, through multi-model integration, feature engineering, and the development of a storm index that leverages distribution system data to aid the prediction of transmission risk. We explored three methods for integrating machine learning with mechanistic models. They consist of: (a) creating a linear combination of the outputs of the two modeling approaches, (b) including fragility curves as additional inputs to machine learning models, and (c) developing a new machine learning model that uses the outputs of the weather-based machine learning model, fragility curve estimates, and wind data to make new predictions. Moreover, due to the limited number of historical failures in transmission networks, a storm index was developed leveraging a dataset of distribution outages to learn about storm behavior to improve model skills. In the current version of the model, we substantially reduced the overestimation in the sum of predicted values of transmission line probability of failure that was present in the previously published model by a factor of 10. This has led to a reduction of model bias from 3352% to 14.46–15.43%. The model with the integrated approach and storm index demonstrates substantial improvements in the estimation of the probability of failure of transmission lines and their ranking by risk level. The improved model is able to capture 60% of the failures within the top 22.5% of the ranked power lines, compared to a value of 34.9% for the previous model. With an estimate of the probability of failure of transmission lines ahead of storms, power system planning and maintenance engineers will have critical information to make informed decisions, to create better mitigation plans and minimize power disruptions. Long term, this model can assist with resilience investments as it highlights areas of the system more susceptible to damage.

View this article on IEEE Xplore

NeRF View Synthesis: Subjective Quality Assessment and Objective Metrics Evaluation

Neural radiance fields (NeRF) are a groundbreaking computer vision technology that enables the generation of high-quality, immersive visual content from multiple viewpoints. This capability has significant advantages for applications such as virtual/augmented reality, 3D modelling, and content creation for the film and entertainment industry. However, the evaluation of NeRF methods poses several challenges, including a lack of comprehensive datasets, reliable assessment methodologies, and objective quality metrics. This paper addresses the problem of NeRF view synthesis (NVS) quality assessment thoroughly, by conducting a rigorous subjective quality assessment test that considers several scene classes and recently proposed NVS methods. Additionally, the performance of a wide range of state-of-the-art conventional and learning-based full-reference 2D image and video quality assessment metrics is evaluated against the subjective scores of the subjective study. This study found that errors in camera pose estimation can result in spatial misalignments between synthesized and reference images, which need to be corrected before applying an objective quality metric. The experimental results are analyzed in depth, providing a comparative evaluation of several NVS methods and objective quality metrics, across different classes of visual scenes, including real and synthetic content for front-face and 360° camera trajectories.

View this article on IEEE Xplore

Diagnosing Grass Seed Infestation: Convolutional Neural Network-Based Terahertz Imaging

Grass seed infestation is a significant issue in the Australian sheep industry. Detecting the seeds when they are in wool or on the surface of the skin could assist with prevention of the grass seed infestation. Terahertz imaging provides a viable option for detecting seeds due to its short wavelength, non-ionizing feature, and penetration ability through wool. Here we demonstrate that accuracy of seeds detection can be improved utilising a Convolutional Neural Network even when the seeds are not visually distinguishable in terahertz images. Our studies reveal accuracies of greater than 95% and 67% can be achieved in identification of seed hidden underneath 1 cm and 2 cm thick wool under normal incidence. Moreover, our analysis finds that terahertz frequencies in the 0.3–0.4 THz range have better overall classification accuracy compared to other frequency bands. The combination of machine learning and terahertz imaging has the potential to be widely implemented in rapid and on-site detection of grass seed infestation with high efficiency.

View this article on IEEE Xplore

Transformer-Based Optimized Multimodal Fusion for 3D Object Detection in Autonomous Driving

Accurate 3D object detection is vital for autonomous driving since it facilitates accurate perception of the environment through multiple sensors. Although cameras can capture detailed color and texture features, they have limitations regarding depth information. Additionally, they can struggle under adverse weather or lighting conditions. In contrast, LiDAR sensors offer robust depth information but lack the visual detail for precise object classification. This work presents a multimodal fusion model that improves 3D object detection by combining the benefits of LiDAR and camera sensors to address these challenges. This model processes camera images and LiDAR point cloud data into a voxel-based representation, further refined by encoder networks to enhance spatial interaction and reduce semantic ambiguity. The proposed multiresolution attention module and integration of discrete wavelet transform and inverse discrete wavelet transform to the image backbone improve the feature extraction capability. This approach enhances the fusion of LiDAR depth information with the camera’s textural and color detail. The model also incorporates a transformer decoder network with self-attention and cross-attention mechanisms, fostering robust and accurate detection through global interaction between identified objects and encoder features. Furthermore, the proposed network is refined with advanced optimization techniques, including pruning and Quantization-Aware Training (QAT), to maintain a competitive performance while significantly decreasing the need for memory and computational resources. Performance evaluations on the nuScenes dataset show that the optimized model architecture offers competitive results and significantly improves operational efficiency and effectiveness in multimodal fusion 3D object detection.

View this article on IEEE Xplore

Applications of Hybrid Solar Streetlamps: Electrical Performance Measurements and Development of Algorithms for Their Optimal Management

This study examines the electrical performance and management of hybrid solar street lighting systems with the objective of optimizing their operation for sustainable urban development. Hybrid solar streetlights, which integrate photovoltaic panels with additional power sources, offer resilience and reliability that are crucial for urban settings. A hybrid solar streetlamp was installed in a city in central Italy and monitored for over a year to analyze its electrical behavior and the illuminances obtainable under different boundary conditions and operational programs. The measured data permit the development of an optimization algorithm in a Python program for the optimal management of the solar streetlamp and the forecasting of the battery charging/discharging cycles, as well as the electricity taken from the grid. The simulation scenarios permit the development of a novel management algorithm that is capable of optimizing the battery usage with a minimal draw on the grid in order to achieve a state of near self-sufficiency for the solar streetlamp. The results demonstrate that tilted solar panels enhance energy production, while optimized LED power profiles and system management enhance efficiency. The study highlights the importance of maintaining the state of charge (SOC) of the battery above 20% to extend its lifetime and reduce replacement needs. Economic analysis indicates significant potential energy savings, emphasizing the necessity of system optimization for economic viability and environmental sustainability in urban lighting. Despite initial investment costs and challenges, adopting hybrid solar lighting in urban environments presents substantial benefits, paving the way for a more sustainable and energy-efficient urban future.

View this article on IEEE Xplore

Quantifying Passive Biomechanical Stability Using an Industrial Robot: Development and Experimental Validation of a Task Space Motion Framework

This paper presents a methodology and generalized motion framework for quantifying passive biomechanical stability and Range of Motion of human cadaveric specimens, using a position-controlled industrial robot and a wrist-mounted force/torque sensor. Many biomechanical studies on diarthrodial joints using human cadaveric specimens are published in the literature, using various test protocols and machines to apply the loading conditions. In these studies, laxity or mobility of the joints are quantified by measuring the magnitude of translations and rotations with respect to force and torque. The protocols and anatomical motions of the specimens are usually described high-level, textually, and from a medical perspective to a broad audience. The present paper aims to describe, from a technical perspective to a robotics audience, our method to perform biomechanical studies and how existing protocols can be replicated through parameterization using the existing textual descriptions. To accomplish this, we propose a generalized task space motion framework for performing biomechanical studies on diarthrodial joints. The generalization is made by defining the robot Tool Center Point at the cadaveric joint rotation center and aligning the specimen so the anatomical motions can be modeled in world frame or tool frame. The framework was successfully evaluated in a technical pilot study on the shoulder, using one cadaveric shoulder specimen and an established protocol from the literature. The specimen was tested in the intact state and in an injury state, with increased passive instability observed for the injury state compared to intact state.

View this article on IEEE Xplore

Carrier Lifetime Dependence on Temperature and Proton Irradiation in 4H-SiC Device: An Experimental Law

The study focuses on analysing the high-level carrier lifetime ( τHL ) in 4H silicon carbide (4H-SiC) PiN diodes under varying temperatures and proton implantation doses. The objective is to identify an empirical law applicable in technology computer-aided design (TCAD) modelling for SiC devices, describing the dependence of carrier lifetime on temperature to gain insights into how irradiation dose may influence the τHL . We electrically characterize diodes of different diameters subjected to different proton irradiation doses and examine the variations in current-voltage (I-V) and ideality factor (n) curves under various irradiation conditions. The effects of proton irradiation on the epitaxial layer are analysed through capacitance-voltage (C-V) measurements. We correlate the observed effects on I-V, n, and C-V curves to the hypothesis of formation of acceptor-type defects related to carbon vacancies, specifically the Z 1/2 defects generated during the irradiation process. The impact of irradiation on carrier lifetime is investigated by measuring τHL using the open circuit voltage decay (OCVD) technique at different temperatures on diodes exposed to various H+ irradiation doses with constant ion energy. This investigation reveals the presence of a proportional relationship between 1/ τHL and the dose of irradiated protons: the proportionality coefficient, referred to as the damage coefficient (K T ), exhibits an Arrhenius-type dependence on temperature. OCVD-measured lifetime on the various diodes demonstrates a power-law dependence of lifetime on temperature. The exponent of this dependence varies with the irradiation dose, notably showing an increase in temperature dependence at the highest H+ ion dose. This suggests a threshold-like dependence on H+ irradiation dose in the τHL -temperature relationship.

View this article on IEEE Xplore

An Optical Design for Interaction With Mid-Air Images Using the Shape of Real Objects

Mid-air images, which are augmented reality (AR) technologies, enable computer graphics (CG) images to be superimposed on a physical space. The mid-air image can be placed side-by-side with real objects, allowing various interactions, such as directly manipulating them to contact the mid-air image on the same plane. In this case, the measurement of the shape of real objects is necessary to realize geometric consistency between the mid-air image and real objects. However, in mid-air image optics, real objects cannot be placed behind the mid-air image (i.e., at a position where they interrupt the light rays that form the mid-air image). This limits the placement of the sensor and may prevent accurate measurement of the shape of the real objects. Consequently, we proposed an optical system for interaction with mid-air images that virtually measures the shape of real objects from behind the mid-air image. In our system, a virtual infrared (IR) sensor is formed behind the mid-air image using a hot mirror that reflects only IR light. The optical system considers the visible area of the mid-air image and the measurable area of the sensor. We evaluated the sharpness, luminance, and chromaticity to assess whether the hot mirror had changed the appearance of the mid-air image. The results confirmed that there was little impact on user perception. Furthermore, we developed four supporting applications for our system to show its efficacy.

View this article on IEEE Xplore

Data-Driven Modeling of Grid-Forming Inverter Dynamics Using Power Hardware-in-the-Loop Experimentation

Recently, there is rapid integration of power electronic converter (PECs) into the power grid. Most of these PECs are grid-following inverters, where weak grid operation becomes an issue. Research is now shifting focus to grid-forming (GFM) inverters, resembling synchronous generators. The shift towards converter-based generation necessitates accurate PEC models for assessing system dynamics that were previously ignored in conventional power systems. Data-driven modeling (DDM) techniques are becoming valuable tools for capturing the dynamic behavior of advanced control strategies for PECs. This paper proposes using power hardware-in-the-loop experiments to capture dynamic GFM data in the application of DDM techniques. Furthermore, the paper derives an analytical approach to obtaining a mathematical model of GFM inverter dynamics and compares it with the DDM. A square-chirp probing signal was employed to perturb the active and reactive power of the load inside an Opal-RT model. The dynamic response of the GFM inverter, including changes in frequency and voltage, was recorded. This data was then used in a system identification algorithm to derive the GFM DDMs. The effectiveness of DDM is cross-validated with an analytical approach through experimental simulation studies, and the goodness-of-fit for both approaches is compared. Both approaches show more than 85% accuracy in capturing the dynamic response of GFM inverters under different loading conditions.

View this article on IEEE Xplore

A Distributed Framework for Minimizing the Asymmetrical Power Request in Multi-Agent Microgrids With Unbalanced Integration of DERs

Microgrids (MGs) are initiated in power systems to speed up the integration of the independently operated distributed energy resources (DERs) into the network. In this regard, in multi-agent microgrids (MAMGs), independent agents aim to operate their resources, while the MG operator (MGO) coordinates independent agents to address the operational issues and ensures reliability of the system. In an MAMG, the high integration of single-phase DERs as well as their independent operational scheduling could result in the asymmetrical power flow in the upper-level system. Respectively, addressing the asymmetrical power request of the MAMGs by exploiting the scheduling of DERs seems to be essential due to the limited flexibility capacity in the upper-level power network, which would finally improve the operating condition of the power system. Consequently, this paper aims to develop a transactive-based scheme to minimize the conceived asymmetrical operation of MAMGs. Accordingly, MGO employs transactive energy signals to minimize the asymmetrical power request of the MAMG by exploiting the scheduling of DERs, while ensuring the privacy of independent agents. Eventually, the proposed framework is applied on an MAMG test system to study its efficacy in alleviating the asymmetrical power request from the upper-level system.

View this article on IEEE Xplore