Amani Altarawneh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Amani Altarawneh has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Hiyam Farhat
Department of Mechanical and Nuclear Engineering, Tennessee Technological University, P.O. Box 5014, Cookeville, TN 38505, USA
2 shared publications - S. M. Mostaq Hossain
Department of Computer Science Tennessee Technological University Cookeville Tennessee USA
2 shared publications - Jesse Roberts
University of the Cumberlands Tennessee Tech University Tennessee Tech University
1 shared publication - Maanak Gupta
Tennessee Tech University, Cookeville, TN, USA
1 shared publication S M Mostaq Hossain
1 shared publication
Latest Publications
- Open Access
Physics-Informed Machine Learning for Intelligent Gas Turbine Digital Twins: A Review
This review surveys recent progress in hybrid artificial intelligence (AI) approaches for gas turbine intelligent digital twins, with an emphasis on models that integrate physics-based simulations and machine learning. The main contribution is the introduction of a structured classification of hybrid AI methods tailored to gas turbine applications, the development of a novel comparative maturity framework, and the proposal of a layered roadmap for integration. The classification organizes hybrid AI approaches into four categories: (1) artificial neural network (ANN)-augmented thermodynamic models, (2) physics-integrated operational architectures, (3) physics-constrained neural networks (PcNNs) with computational fluid dynamics (CFD) surrogates, and (4) generative and model discovery approaches. The maturity framework evaluates these categories across five criteria: data dependency, interpretability, deployment complexity, workflow integration, and real-time capability. Industrial case studies—including General Electric (GE) Vernova’s SmartSignal, Siemens’ Autonomous Turbine Operation and Maintenance (ATOM), and the Electric Power Research Institute (EPRI) turbine digital twin—illustrate applications in real-time diagnostics, predictive maintenance, and performance optimization. Together, the classification and maturity framework provide the means for systematic assessment of hybrid AI methods in gas turbine intelligent digital twins. The review concludes by identifying key challenges and outlining a roadmap for the future development of scalable, interpretable, and operationally robust intelligent digital twins for gas turbines.
Open AccessPhysics-Informed Machine Learning for Intelligent Gas Turbine Digital Twins: A Review
This review surveys recent progress in hybrid artificial intelligence (AI) approaches for gas turbine intelligent digital twins, with an emphasis on models that integrate physics-based simulations and machine learning. The main contribution is the introduction of a structured classification of hybrid AI methods tailored to gas turbine applications, the development of a novel comparative maturity framework, and the proposal of a layered roadmap for integration. The classification organizes hybrid AI approaches into four categories: (1) artificial neural network (ANN)-augmented thermodynamic models, (2) physics-integrated operational architectures, (3) physics-constrained neural networks (PcNNs) with computational fluid dynamics (CFD) surrogates, and (4) generative and model discovery approaches. The maturity framework evaluates these categories across five criteria: data dependency, interpretability, deployment complexity, workflow integration, and real-time capability. Industrial case studies—including General Electric (GE) Vernova’s SmartSignal, Siemens’ Autonomous Turbine Operation and Maintenance (ATOM), and the Electric Power Research Institute (EPRI) turbine digital twin—illustrate applications in real-time diagnostics, predictive maintenance, and performance optimization. Together, the classification and maturity framework provide the means for systematic assessment of hybrid AI methods in gas turbine intelligent digital twins. The review concludes by identifying key challenges and outlining a roadmap for the future development of scalable, interpretable, and operationally robust intelligent digital twins for gas turbines.
- Open Access
- 16 September 2025
- Published by MDPI AG in Preprints.org
Physics-Informed Machine Learning for Intelligent Gas Turbine Digital Twins: A Review
Gas turbine digital twins are increasingly critical for real-time diagnostics, predictive maintenance, and performance optimization under both baseload and flexible operations. Advances in hybrid modeling that integrate physics-based simulations with machine learning, offer tremendous opportunities to develop intelligent digital twins that are both physically consistent and computationally efficient. This review surveys current research and industrial practices in hybrid artificial intelligence (AI) models for gas turbines and introduces a classification of four distinct methodologies: (1) ANN-augmented thermodynamic models for enhanced component-level diagnostics; (2) physics-integrated operational architectures combining live sensor data, AI, and modular physics models for system-level optimization; (3) physics-constrained neural networks (PcNNs) and computational fluid dynamic (CFD) surrogates that embed governing equations into learning frameworks for consistent flow and thermal predictions; (4) generative and model-discovery approaches for synthetic data generation and interpretable equation extraction. A comparative maturity framework is presented to evaluate these approaches across five criteria: data dependency, interpretability, deployment complexity, integration with simulation and design workflows, and real-time capability. Industrial implementations by leading OEMs and independent research institutes are analyzed within this context. The review concludes by outlining key challenges and a roadmap toward scalable, interpretable, and operationally robust intelligent digital twin architectures for next generation gas turbines.
- 16 September 2025
- Published by MDPI AG in Preprints.org
Open AccessPhysics-Informed Machine Learning for Intelligent Gas Turbine Digital Twins: A Review
Gas turbine digital twins are increasingly critical for real-time diagnostics, predictive maintenance, and performance optimization under both baseload and flexible operations. Advances in hybrid modeling that integrate physics-based simulations with machine learning, offer tremendous opportunities to develop intelligent digital twins that are both physically consistent and computationally efficient. This review surveys current research and industrial practices in hybrid artificial intelligence (AI) models for gas turbines and introduces a classification of four distinct methodologies: (1) ANN-augmented thermodynamic models for enhanced component-level diagnostics; (2) physics-integrated operational architectures combining live sensor data, AI, and modular physics models for system-level optimization; (3) physics-constrained neural networks (PcNNs) and computational fluid dynamic (CFD) surrogates that embed governing equations into learning frameworks for consistent flow and thermal predictions; (4) generative and model-discovery approaches for synthetic data generation and interpretable equation extraction. A comparative maturity framework is presented to evaluate these approaches across five criteria: data dependency, interpretability, deployment complexity, integration with simulation and design workflows, and real-time capability. Industrial implementations by leading OEMs and independent research institutes are analyzed within this context. The review concludes by outlining key challenges and a roadmap toward scalable, interpretable, and operationally robust intelligent digital twin architectures for next generation gas turbines.
- Open Access
Bridging Cloud Convenience and Protocol Transparency: A Hybrid Architecture for Ethereum Node Operations on Amazon Managed Blockchain
As blockchain technologies are increasingly adopted in enterprise and research domains, the need for secure, scalable, and performance-transparent node infrastructure has become critical. While self-hosted Ethereum nodes offer operational control, they often lack elasticity and require complex maintenance. This paper presents a hybrid, service-oriented architecture for deploying and monitoring Ethereum full nodes using Amazon Managed Blockchain (AMB), integrated with EC2-based observability, IAM-enforced security policies, and reproducible automation via the AWS Cloud Development Kit. Our architecture supports end-to-end observability through custom EC2 scripts leveraging Web3.py and JSON-RPC, collecting over 1,000 real-time data points-including gas utilization, transaction inclusion latency, and mempool dynamics. These metrics are visualized and monitored through AWS CloudWatch, enabling service-level performance tracking and anomaly detection. This cloud-native framework restores low-level observability lost in managed environments while maintaining the operational simplicity of managed services. By bridging the simplicity of AMB with the transparency required for protocol research and enterprise monitoring, this work delivers one of the first reproducible, performance-instrumented Ethereum deployments on AMB. The proposed hybrid architecture enables secure, observable, and reproducible Ethereum node operations in cloud environments, suitable for both research and production use.
Open AccessBridging Cloud Convenience and Protocol Transparency: A Hybrid Architecture for Ethereum Node Operations on Amazon Managed Blockchain
As blockchain technologies are increasingly adopted in enterprise and research domains, the need for secure, scalable, and performance-transparent node infrastructure has become critical. While self-hosted Ethereum nodes offer operational control, they often lack elasticity and require complex maintenance. This paper presents a hybrid, service-oriented architecture for deploying and monitoring Ethereum full nodes using Amazon Managed Blockchain (AMB), integrated with EC2-based observability, IAM-enforced security policies, and reproducible automation via the AWS Cloud Development Kit. Our architecture supports end-to-end observability through custom EC2 scripts leveraging Web3.py and JSON-RPC, collecting over 1,000 real-time data points-including gas utilization, transaction inclusion latency, and mempool dynamics. These metrics are visualized and monitored through AWS CloudWatch, enabling service-level performance tracking and anomaly detection. This cloud-native framework restores low-level observability lost in managed environments while maintaining the operational simplicity of managed services. By bridging the simplicity of AMB with the transparency required for protocol research and enterprise monitoring, this work delivers one of the first reproducible, performance-instrumented Ethereum deployments on AMB. The proposed hybrid architecture enables secure, observable, and reproducible Ethereum node operations in cloud environments, suitable for both research and production use.
- Open Access
Unraveling Ethereum's Mempool: The Impact of Fee Fairness, Transaction Prioritization, and Consensus Efficiency
Ethereum's transaction pool (mempool) dynamics and fee market efficiency critically affect transaction inclusion, validator workload, and overall network performance. This research empirically analyzes gas price variations, mempool clearance rates, and block finalization times in Ethereum's proof-of-stake ecosystem using real-time data from Geth and Prysm nodes. We observe that high-fee transactions are consistently prioritized, while low-fee transactions face delays or exclusion despite EIP-1559's intended improvements. Mempool congestion remains a key factor in validator efficiency and proposal latency. We provide empirical evidence of persistent fee-based disparities and show that extremely high fees do not always guarantee faster confirmation, revealing inefficiencies in the current fee market. To address these issues, we propose congestion-aware fee adjustments, reserved block slots for low-fee transactions, and improved handling of out-of-gas vulnerabilities. By mitigating prioritization bias and execution inefficiencies, our findings support more equitable transaction inclusion, enhance validator performance, and promote scalability. This work contributes to Ethereum's long-term decentralization by reducing dependence on high transaction fees for network participation.
Open AccessUnraveling Ethereum's Mempool: The Impact of Fee Fairness, Transaction Prioritization, and Consensus Efficiency
Ethereum's transaction pool (mempool) dynamics and fee market efficiency critically affect transaction inclusion, validator workload, and overall network performance. This research empirically analyzes gas price variations, mempool clearance rates, and block finalization times in Ethereum's proof-of-stake ecosystem using real-time data from Geth and Prysm nodes. We observe that high-fee transactions are consistently prioritized, while low-fee transactions face delays or exclusion despite EIP-1559's intended improvements. Mempool congestion remains a key factor in validator efficiency and proposal latency. We provide empirical evidence of persistent fee-based disparities and show that extremely high fees do not always guarantee faster confirmation, revealing inefficiencies in the current fee market. To address these issues, we propose congestion-aware fee adjustments, reserved block slots for low-fee transactions, and improved handling of out-of-gas vulnerabilities. By mitigating prioritization bias and execution inefficiencies, our findings support more equitable transaction inclusion, enhance validator performance, and promote scalability. This work contributes to Ethereum's long-term decentralization by reducing dependence on high transaction fees for network participation.
- Open Access
Leveraging Large Language Models and Machine Learning for Smart Contract Vulnerability Detection
As blockchain technology and smart contracts become widely adopted, securing them throughout every stage of the transaction process is essential. The concern of improved security for smart contracts is to find and detect vulnerabilities using classical Machine Learning (ML) models and fine-tuned Large Language Models (LLM). The robustness of such work rests on a labeled smart contract dataset that includes annotated vulnerabilities on which several LLMs alongside various traditional machine learning algorithms such as DistilBERT model is trained and tested. We train and test machine learning algorithms to classify smart contract codes according to vulnerability types in order to compare model performance. Having fine-tuned the LLMs specifically for smart contract code classification should help in getting better results when detecting several types of well-known vulnerabilities, such as Reentrancy, Integer Overflow, Timestamp Dependency and Dangerous Delegatecall. From our initial experimental results, it can be seen that our fine-tuned LLM surpasses the accuracy of any other model by achieving an accuracy of over 90%, and this advances the existing vulnerability detection benchmarks. Such performance provides a great deal of evidence for LLMs ability to describe the subtle patterns in the code that traditional ML models could miss. Thus, we compared each of the ML and LLM models to give a good overview of each models strengths, from which we can choose the most effective one for real-world applications in smart contract security. Our research combines machine learning and large language models to provide a rich and interpretable framework for detecting different smart contract vulnerabilities, which lays a foundation for a more secure blockchain ecosystem.
Open AccessLeveraging Large Language Models and Machine Learning for Smart Contract Vulnerability Detection
As blockchain technology and smart contracts become widely adopted, securing them throughout every stage of the transaction process is essential. The concern of improved security for smart contracts is to find and detect vulnerabilities using classical Machine Learning (ML) models and fine-tuned Large Language Models (LLM). The robustness of such work rests on a labeled smart contract dataset that includes annotated vulnerabilities on which several LLMs alongside various traditional machine learning algorithms such as DistilBERT model is trained and tested. We train and test machine learning algorithms to classify smart contract codes according to vulnerability types in order to compare model performance. Having fine-tuned the LLMs specifically for smart contract code classification should help in getting better results when detecting several types of well-known vulnerabilities, such as Reentrancy, Integer Overflow, Timestamp Dependency and Dangerous Delegatecall. From our initial experimental results, it can be seen that our fine-tuned LLM surpasses the accuracy of any other model by achieving an accuracy of over 90%, and this advances the existing vulnerability detection benchmarks. Such performance provides a great deal of evidence for LLMs ability to describe the subtle patterns in the code that traditional ML models could miss. Thus, we compared each of the ML and LLM models to give a good overview of each models strengths, from which we can choose the most effective one for real-world applications in smart contract security. Our research combines machine learning and large language models to provide a rich and interpretable framework for detecting different smart contract vulnerabilities, which lays a foundation for a more secure blockchain ecosystem.