Article
Engineering, Electrical & Electronic
T. Manoj, C. Ranga, Sherif S. M. Ghoneim, U. Mohan Rao, Saad A. Mohamed Abdelwahab
Summary: Various fault diagnosis techniques in oil immersed power transformers have been studied for the past two decades and are well documented in the literature. Among these techniques, the Duval triangle method (DTM) is reported to be the most prominent. In this study, a new approach combining three Duval triangles with triangular membership functions (MFs) is proposed for fault diagnosis.
IEEE TRANSACTIONS ON DIELECTRICS AND ELECTRICAL INSULATION
(2023)
Article
Energy & Fuels
Prabhakar Sharma, Zafar Said, Saim Memon, Rajvikram Madurai Elavarasan, Mohammad Khalid, Xuan Phuong Nguyen, Anh Tuan Hoang, Lan Huong Nguyen, Muslum Arici
Summary: This paper presents a metamodel framework to predict the thermophysical parameters of Fe3O4-coated MWCNT hybrid nanofluids. GEP and ANFIS models are used for prediction and are validated and compared. The results show that the GEP model outperforms the ANFIS model in most indicators. The generated metamodel can be used to replace expensive and repetitive laboratory procedures.
INTERNATIONAL JOURNAL OF ENERGY RESEARCH
(2022)
Review
Energy & Fuels
Alcebiades Rangel Bessa, Jussara Farias Fardin, Patrick Marques Ciarelli, Lucas Frizera Encarnacao
Summary: This study reviewed the conventional techniques and failure analysis tendency of Dissolved Gas Analysis (DGA) based on the norms IEC 60599 and IEEE Std C57.104, and analyzed the performance of various techniques using the IEC TC10 database. It aimed to provide relevant information to support students and professionals in the field of failure analysis and assist in the development of new tools in the DGA field.
Article
Computer Science, Artificial Intelligence
Fernando Martinez-Plumed, Pablo Barredo, Sean O. Heigeartaigh, Jose Hernandez-Orallo
Summary: Experimental benchmarks like ImageNet and Atari games are crucial for advancing AI research. An analysis of results and papers linked to 25 popular benchmarks reveals that competition and collaboration dynamics in AI research are still not well understood. The study provides an innovative methodology to explore the behavior of different entrants in challenges, from academia to tech giants, in response to achievements.
NATURE MACHINE INTELLIGENCE
(2021)
Review
Energy & Fuels
Yan Zhang, Yufeng Tang, Yongqiang Liu, Zhaowen Liang
Summary: This paper provides a systematic review of the application of artificial intelligence techniques for DGA-based transformer fault diagnosis. Researchers utilize AI techniques to mine the features of DGA data, select appropriate techniques, or make improvements to enhance diagnostic performance. The paper also reviews diagnostic thinking and methods, such as introducing temporal parameters and extracting optimal features from DGA data.
FRONTIERS IN ENERGY RESEARCH
(2022)
Article
Computer Science, Theory & Methods
Rudresh Dwivedi, Devam Dave, Het Naik, Smiti Singhal, Rana Omer, Pankesh Patel, Bin Qian, Zhenyu Wen, Tejal Shah, Graham Morgan, Rajiv Ranjan
Summary: As the reliance on intelligent machines increases, there is a growing demand for transparent and interpretable models. Explaining the model has become the gold standard for building trust and deploying artificial intelligence systems in critical domains. Explainable artificial intelligence (XAI) aims to provide machine learning techniques that enable human users to understand, trust, and produce explainable models. This survey explores state-of-the-art programming techniques for XAI, categorizes different approaches, and discusses their key differences. Concrete examples are provided and mapped to programming frameworks and software toolkits.
ACM COMPUTING SURVEYS
(2023)
Editorial Material
Biochemistry & Molecular Biology
Zachi I. Attia, Paul A. Friedman
Summary: By applying artificial intelligence to electrocardiograms recorded by patients using Apple watches, we conducted a prospective, digital, remote study to enable large-scale screening for left ventricular dysfunction, a serious and under-detected cardiac disease. The study found that patients engaged with the system and that the watch electrocardiograms effectively screened for the disease.
Review
Engineering, Environmental
Yiqi Liu, Pedram Ramin, Xavier Flores-Alsina, Krist. Gernaey
Summary: Recent advances in AI and DA offer opportunities for fault management and decision-making in urban wastewater treatment systems (UWS). However, the complexity and size of UWS, variations in instrumentation, and poor data quality pose challenges for AI and DA applications. This review critically analyzes previous work on AI-based data-driven methodologies for system-wide fault detection and management, addressing process and instrumentation faults, and explores the interplay among UWS, data, and AI. It provides insights into the strengths and weaknesses of different approaches and discusses opportunities and challenges.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2023)
Article
Computer Science, Artificial Intelligence
Kerstin N. Vokinger, Urs Gasser
Summary: Regulatory frameworks for artificial intelligence are being developed on both sides of the Atlantic, eagerly anticipated by the scientific and industrial community. Commonalities and differences in approaches to AI in medicine are beginning to emerge.
NATURE MACHINE INTELLIGENCE
(2021)
Article
Engineering, Electrical & Electronic
Arnaud Nanfak, Samuel Eke, Fethi Meghnefi, Issouf Fofana, Gildas Martial Ngaleu, Charles Hubert Kom
Summary: Power transformers are crucial for electrical power transmission grids, and dissolved gas analysis (DGA) has proven to be an effective tool for early fault detection. This article proposes a hybrid method that combines traditional and intelligent approaches using a genetic algorithm-based clustering algorithm and human expertise for DGA data interpretation and fault diagnosis. The proposed method outperforms existing traditional, intelligent, and hybrid methods in terms of diagnostic accuracy.
IEEE TRANSACTIONS ON DIELECTRICS AND ELECTRICAL INSULATION
(2023)
Article
Environmental Sciences
Victor O. K. Li, Jacqueline C. K. Lam, Jiahuan Cui
Summary: This article discusses the role and challenges of AI and big data technologies in environmental decision-making, raises a series of important questions, and summarizes the significance and innovation of the articles included in the special issue. It also highlights the important principles of AI for social good.
ENVIRONMENTAL SCIENCE & POLICY
(2021)
Article
Computer Science, Artificial Intelligence
Pat Pataranutaporn, Ruby Liu, Ed Finn, Pattie Maes
Summary: This study explores how changes in a person's mental model of an AI system affect their interaction with the system. It shows that perceiving a caring motive for the AI leads to a perception of greater trustworthiness, empathy, and performance. Initial mental models and priming have a stronger effect on more sophisticated AI models. The research also suggests a feedback loop between users and AI that reinforces the user's mental model over time. Further investigation is needed to understand the long-term effects.
NATURE MACHINE INTELLIGENCE
(2023)
Article
Environmental Sciences
Francesca Larosa, Sergio Hoyas, Javier Garcia-Martinez, J. Alberto Conejero, Francesco Fuso Nerini, Ricardo Vinuesa
Summary: Large language models provide an opportunity to advance climate and sustainability research. We believe that regulating and validating generative artificial intelligence models would benefit society more than stopping development.
NATURE CLIMATE CHANGE
(2023)
Article
Construction & Building Technology
Mohammed Ashfaq, Mudassir Iqbal, Mohsin Ali Khan, Fazal E. Jalal, Majed Alzara, M. Hamad, Ahmed. M. Yosri
Summary: This study evaluated the effect of alkali concentration and duration of curing on the unconfined compressive strength (UCS) of soils, as well as the impact of fly ash addition on the UCS of alkali-contaminated soils. The results showed that alkali contamination reduced the UCS of the soils, while the addition of fly ash increased the UCS. Three factors, including fly ash content, curing period, and alkali concentration, were used to develop models for predicting the UCS of the soils.
CASE STUDIES IN CONSTRUCTION MATERIALS
(2022)
Article
Energy & Fuels
Lucheng Hong, Zehua Chen, Yifei Wang, Mohammad Shahidehpour, Minghe Wu
Summary: This paper proposes a new SVM-based decision framework for Power Transformer Fault Diagnosis (PTFD), which significantly improves training efficiency and diagnosis accuracy through multi-step feature extraction and appropriate multi-classification methods.
Article
Engineering, Electrical & Electronic
Priyatosh Mahish, Sukumar Mishra
Summary: This paper proposes a synchrophasor data based Q-V droop (SQVD) control technique to address the reactive power allocation issues in wind farms integrated to the grid. It uses synchronized droop gain and distributed coordination among DFIGs to optimize the reactive power allocation. The SQVD method is found to be more effective than constant Q-V droop and variable Q-V droop control methods in different dynamic situations.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Vikram Singh, Manoj Fozdar, Hasmat Malik, Fausto Pedro Garcia Marquez
Summary: The emergence of competitive power markets has led to an increase in transactions between producers and consumers, but this has also resulted in congestion on the transmission network. This study aims to mitigate congestion and achieve stable power system operation through generator rescheduling.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2023)
Article
Engineering, Multidisciplinary
Yashi Singh, Bhim Singh, Sukumar Mishra
Summary: This paper presents a modified power control (MPC) method for seamless mode transition in a microgrid and accurate regulation of reference grid current, reducing the complex communication setup and cost. The method achieves power distribution between parallel SPI units and maintains power factor and total harmonics distortion based on the IEEE 519 standard.
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Bharat Bhushan Sharma, Naveen Kumar Sharma, Anuj Banshwar, Hasmat Malik, Fausto Pedro Garcia Marquez
Summary: This paper presents a new method for designing matched digital filters with discrete valued coefficients using the fuzzy particle swarm optimization vector quantization (FPSOVQ) algorithm. The approach utilizes fuzzy inference method and expert particle swarm optimization to generate an optimal codebook for compression of data. The results demonstrate the advantage of the developed algorithm in terms of energy compaction ratio for sampled voice signals when compared to a db4 filter.
INFORMATION SCIENCES
(2023)
Article
Engineering, Electrical & Electronic
Arnab Bhattacharjee, Arnab Kumar Mondal, Ashu Verma, Sukumar Mishra, Tapan K. Saha
Summary: This paper proposes a self-supervised latent space clustering algorithm, which is called Deep Latent Space Clustering, for detecting stealthy false data injection attacks in smart grids. The proposed algorithm is effective in bypassing conventional bad data detection algorithms. It utilizes a stacked autoencoder network and a trainable clustering head to achieve clean clustering of the data. The algorithm is tested on standard test systems and found to perform at par with state-of-the-art algorithms.
IEEE TRANSACTIONS ON SMART GRID
(2023)
Article
Green & Sustainable Science & Technology
Lakshminarayana Gadupudi, Gudapati Sambasiva Rao, Rachakonda Venkata Lakshmi Narayana Divakar, Hasmat Malik, Faisal Alsaif, Sager Alsulamy, Taha Selim Ustun
Summary: This paper investigates the low harmonic distortions of a fifteen-level VSC based STATCOM using a fuzzy logic decoupled control algorithm to balance reactive power and manage voltage stability in transmission systems, reducing harmonic distortions.
Article
Engineering, Electrical & Electronic
Himmat Singh, Yashwant Sawle, Shishir Dixit, Hasmat Malik, Fausto Pedro Garcia Marquez
Summary: This study proposes a swarm intelligence Memory based new Multi-Objective Dragonfly (MMOD) algorithm for optimizing active power loss, total investment on reactive power sources, and total voltage variations in distribution systems. The algorithm uses Pareto-optimal solutions memorized by dragonflies to initialize solutions in each cycle. The usefulness of the algorithm is demonstrated in solving MORPD problem in two cases: IEEE-30 bus test system and IEEE-69 bus radial distribution systems integrated with DGs and RPS units.
ELECTRIC POWER SYSTEMS RESEARCH
(2023)
Article
Energy & Fuels
Abdulaziz Almutairi, Naif Albagami, Sultanh Almesned, Omar Alrumayh, Hasmat Malik
Summary: With the increase in electrification trends, household energy consumption is expected to rise significantly. Management of the demand side is necessary to reduce electricity bills and different programs can be introduced, such as real-time pricing. An innovative home appliance scheduling method is proposed, considering rooftop solar panels as energy suppliers. The method is compared with other methods and has shown superiority in terms of energy cost, load ratio, and consumer satisfaction.
Article
Green & Sustainable Science & Technology
Neeraj Kumar, Madan Mohan Tripathi, Saket Gupta, Majed A. Alotaibi, Hasmat Malik, Asyraf Afthanorhan
Summary: This paper investigates the impact of wind energy on electricity prices using regression models. The study finds that the Decision Tree model outperforms other models, with the lowest MAE values considering and not considering wind energy generation. The findings of this study are important for the application and development of wind energy in electricity markets.
Article
Mathematics, Interdisciplinary Applications
Andrew A. Manderson, Robert J. B. Goudie
Summary: A challenge for Bayesian inference practitioners is how to incorporate multiple relevant, heterogeneous data sets into a model. We propose chained Markov melding, an extension of Markov melding, to combine the submodels into a joint model. We address the challenges of capturing prior dependence and reconciling differences in priors between adjacent submodels. Additionally, we describe a sampler that utilizes the chain structure to incorporate information from submodels in multiple stages.
Article
Engineering, Electrical & Electronic
Utkarsh Kumar, Sukumar Mishra, Kalyan Dash
Summary: This article proposes a low-cost and less data-intensive methodology for detecting, localizing, and classifying faults in solar photovoltaic (SPV) systems. It utilizes a sensorless electronic circuit, an Internet of things (IoT)-based application, and a deep autoencoder-based semi-supervised learning module, followed by a hybrid support vector machine and logistic regression for fault classification. The methodology is validated in a laboratory-scale real-time setup of a grid-connected SPV system.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Green & Sustainable Science & Technology
Abdulaziz Almutairi, Naif Albagami, Sultanh Almesned, Omar Alrumayh, Hasmat Malik
Summary: Electric vehicles (EVs) have the potential to reduce emissions and enhance energy security, but accurately estimating their load is a challenge for optimizing grid management and integration. This study introduces a tailored three-step solution, focusing on Saudi Arabia, to estimate EV load using real survey data and commercially available EV data. The developed load models facilitate load estimations under different scenarios and building types, providing valuable insights for grid operators and policymakers.
Article
Energy & Fuels
Yawar Irshad Badri, Suresh Kumar Sudabattula, Ikhlaq Hussain, Hasmat Malik, Fausto Pedro Garcia Marquez
Summary: This paper presents a method of integrating ultracapacitors with a regenerative braking system for use in electric drive trains. By combining ultracapacitors and batteries, it improves the vehicle's range and enhances speed control response.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Computer Science, Information Systems
Salwan Tajjour, Shyam Singh Chandel, Majed A. Alotaibi, Hasmat Malik, Fausto Pedro Garcia Marquez, Asyraf Afthanorhan
Summary: This study compares the performance of three deep learning techniques for solar irradiance forecasting. The results show that these models have similar accuracy, but differ in training speed and number of parameters. The study is important for reliable solar irradiance forecasting.
Article
Computer Science, Information Systems
Divya Rishi Shrivastava, Shahbaz Ahmed Siddiqui, Kusum Verma, Satyendra Singh, Majed A. Alotaibi, Hasmat Malik, Fausto Pedro Garcia Marquez
Summary: This article proposes a data-driven unified methodology for enhancing grid stability in solar energy-penetrated power network. This methodology incorporates Prompt Instability Evaluation (PIE) and Decision Assisted Adaptive Control (DAAC) to evaluate and correct system transient instability in real-time.