Maryamsadat Tahavori
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Maryamsadat Tahavori has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Hamid Reza Shaker
SDU Center for Energy Informatics, Maersk Mc-Kinney Moeller Institute, The Faculty of Engineering, University of Southern Denmark, 5230 Odense, Denmark
22 shared publications John Leth
Department of Electronic Systems, Aalborg University, Aalborg, Denmark
4 shared publicationsRafael Wisniewski
Department of Electronic Systems, Aalborg University, Aalborg, Denmark
4 shared publications- Rahman Dashti
Clinical-Laboratory Center of Power System & Protection, Faculty of Intelligent Systems Engineering and Data Science, Persian Gulf University, Bushehr 7516913817, Iran
4 shared publications - Agus Hasan
Norwegian University of Science and Technology
2 shared publications Carsten Kallesøe
Grundfos Management A/S, Bjerringbro, Denmark
2 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Elsevier in Energy and AI
- Vol. 26
Time-series foundation models for energy infrastructure: Evidence and requirements for digital-twin-grade integration
- 6 November 2026
- Published by Elsevier in Energy and AI
- Vol. 26
Open AccessTime-series foundation models for energy infrastructure: Evidence and requirements for digital-twin-grade integration
- Open Access
- 23 September 2026
- Published by Elsevier in European Journal of Control
Data-Driven Energy-Aware Controllability and Actuator Placement in Complex Networks: A Response-Based Gramian Framework
- 23 September 2026
- Published by Elsevier in European Journal of Control
Open AccessData-Driven Energy-Aware Controllability and Actuator Placement in Complex Networks: A Response-Based Gramian Framework
- Open Access
Survival Models for Predictive Maintenance and Remaining Useful Life in Sensor-Enabled Smart Energy Networks: A Review
Smart energy networks, including electricity distribution and district heating, are increasingly operated as sensor-enabled infrastructures where maintenance decisions must be made under heterogeneous and time-varying operating conditions. In these settings, time-to-event data are rarely complete; preventive actions and limited observation horizons routinely introduce censoring and truncation, so models and validation procedures must account for partially observed lifetimes to avoid biased inference and misleading performance estimates. This review surveys survival models for predictive maintenance (PdM) and remaining useful life (RUL) estimation, spanning non-parametric, semi-parametric, parametric, and learning-based approaches, with emphasis on censoring-aware formulations and the use of static and time-varying covariates derived from sensor, inspection, and contextual information. A structured taxonomy and a systematic mapping of model families to data types, core assumptions (proportional hazards versus parametric distributional structure), and decision-oriented outputs such as risk ranking, horizon failure probabilities, and RUL distributions are presented. Evaluation practice is also synthesized by covering discrimination metrics, censoring-aware RUL accuracy measures, and probabilistic assessment via proper scoring rules, including the time-dependent Brier score and Integrated Brier Score (IBS). The review provides researchers and practitioners with a practical guide to selecting, fitting, and evaluating survival models for risk-informed maintenance planning in smart energy networks.
Open AccessSurvival Models for Predictive Maintenance and Remaining Useful Life in Sensor-Enabled Smart Energy Networks: A Review
Smart energy networks, including electricity distribution and district heating, are increasingly operated as sensor-enabled infrastructures where maintenance decisions must be made under heterogeneous and time-varying operating conditions. In these settings, time-to-event data are rarely complete; preventive actions and limited observation horizons routinely introduce censoring and truncation, so models and validation procedures must account for partially observed lifetimes to avoid biased inference and misleading performance estimates. This review surveys survival models for predictive maintenance (PdM) and remaining useful life (RUL) estimation, spanning non-parametric, semi-parametric, parametric, and learning-based approaches, with emphasis on censoring-aware formulations and the use of static and time-varying covariates derived from sensor, inspection, and contextual information. A structured taxonomy and a systematic mapping of model families to data types, core assumptions (proportional hazards versus parametric distributional structure), and decision-oriented outputs such as risk ranking, horizon failure probabilities, and RUL distributions are presented. Evaluation practice is also synthesized by covering discrimination metrics, censoring-aware RUL accuracy measures, and probabilistic assessment via proper scoring rules, including the time-dependent Brier score and Integrated Brier Score (IBS). The review provides researchers and practitioners with a practical guide to selecting, fitting, and evaluating survival models for risk-informed maintenance planning in smart energy networks.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- p. 1
Finite-Region Screening of Diagnostic and Intervention Capability in District-Heating Pipe Models
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- p. 1
Open AccessFinite-Region Screening of Diagnostic and Intervention Capability in District-Heating Pipe Models
- Open Access
- 19 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 168893-168902
Predicting Pipe Failures: A Machine Learning Approach to Asset Management in District Heating
As district heating networks (DHNs) across Europe near or surpass their intended service life, the need for proactive, data-driven maintenance and replacement planning is increasing. This paper presents a predictive asset management framework based on machine learning (ML) to assess the fault vulnerability of pipes. To train the ML algorithm, a combined dataset of both geospatial and operational data is implemented. While pressure is often estimated using complex hydraulic simulations, this study proposes and evaluates a lightweight linear pressure approximation method based on expert knowledge. The ML model is applied to a real DHN in Denmark through collaboration with the utility company HOFOR. Due to a significant class imbalance in the data (∼1:215), multiple oversampling (OS) strategies are investigated. Model performance is evaluated using fault capture versus length capture (FCLC) curves and area under the curve (AUC) metrics. The inclusion of pressure data is found to improve the AUC by 4.5%, and the model captures over 40% of failures by inspecting only 10% of the network. These results demonstrate the feasibility of using ML-based fault vulnerability prediction as a tool for predictive maintenance and asset replacement planning in DHNs.
- 19 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 168893-168902
Open AccessPredicting Pipe Failures: A Machine Learning Approach to Asset Management in District Heating
As district heating networks (DHNs) across Europe near or surpass their intended service life, the need for proactive, data-driven maintenance and replacement planning is increasing. This paper presents a predictive asset management framework based on machine learning (ML) to assess the fault vulnerability of pipes. To train the ML algorithm, a combined dataset of both geospatial and operational data is implemented. While pressure is often estimated using complex hydraulic simulations, this study proposes and evaluates a lightweight linear pressure approximation method based on expert knowledge. The ML model is applied to a real DHN in Denmark through collaboration with the utility company HOFOR. Due to a significant class imbalance in the data (∼1:215), multiple oversampling (OS) strategies are investigated. Model performance is evaluated using fault capture versus length capture (FCLC) curves and area under the curve (AUC) metrics. The inclusion of pressure data is found to improve the AUC by 4.5%, and the model captures over 40% of failures by inspecting only 10% of the network. These results demonstrate the feasibility of using ML-based fault vulnerability prediction as a tool for predictive maintenance and asset replacement planning in DHNs.
- 20 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 162-166
Asset Management Strategies for District Heating Networks
District Heating (DH) became widely adopted in European cities during the 20th century to meet demand for heating from a growing urban population. Today, the desire to decarbonize Europe's heat consumption has lead to an renewed interest in increasing the adoption of DH. To meet this end, DH has to be a price competitive alternative to other heating technologies. Over time the underground heat distribution network that DH companies operate suffers from faults that require replacement of pipes. On-demand replacement is more expensive than planned large scale replacement projects. The only question is, when is the optimal time to renew the pipes? In this article this question will be formulated using Reliability Theory. Our approach is to use historical records of time to failure and a bounding result to estimate the optimal time for replacement. The method can be used by DH companies with historical fault records to form an Asset Management strategy on the question of when to renew which pipes.
- 20 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 162-166
Asset Management Strategies for District Heating Networks
District Heating (DH) became widely adopted in European cities during the 20th century to meet demand for heating from a growing urban population. Today, the desire to decarbonize Europe's heat consumption has lead to an renewed interest in increasing the adoption of DH. To meet this end, DH has to be a price competitive alternative to other heating technologies. Over time the underground heat distribution network that DH companies operate suffers from faults that require replacement of pipes. On-demand replacement is more expensive than planned large scale replacement projects. The only question is, when is the optimal time to renew the pipes? In this article this question will be formulated using Reliability Theory. Our approach is to use historical records of time to failure and a bounding result to estimate the optimal time for replacement. The method can be used by DH companies with historical fault records to form an Asset Management strategy on the question of when to renew which pipes.
- Open Access
- 2 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 2250-2258
Model-Based Fault Diagnosis Algorithms for Robotic Systems
In this paper, three model-based fault diagnosis algorithms for robotic systems are designed, compared, simulated, and implemented. The first algorithm is based on a nonlinear adaptive observer (NLAO), where a sufficient condition for the convergence of the estimator is derived in terms of linear matrix inequality (LMI) under persistence of excitation condition. The second algorithm is based on an adaptive extended Kalman filter (AEKF). Unlike traditional approaches, where the fault parameters are considered as augmented state variables, the AEKF directly estimates the fault parameters from measurement data. The third algorithm is based on a cascade of a nonlinear observer (NLO) and a linearized adaptive Kalman filter (LAKF), called the adaptive exogenous Kalman filter (AXKF). The pros and cons for each algorithm are discussed. The performance of the algorithms is compared in a single-link joint robot system. Furthermore, the algorithms are implemented in a ball-balancing robot to detect and estimate the magnitude of the actuator faults.
- 2 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 2250-2258
Open AccessModel-Based Fault Diagnosis Algorithms for Robotic Systems
In this paper, three model-based fault diagnosis algorithms for robotic systems are designed, compared, simulated, and implemented. The first algorithm is based on a nonlinear adaptive observer (NLAO), where a sufficient condition for the convergence of the estimator is derived in terms of linear matrix inequality (LMI) under persistence of excitation condition. The second algorithm is based on an adaptive extended Kalman filter (AEKF). Unlike traditional approaches, where the fault parameters are considered as augmented state variables, the AEKF directly estimates the fault parameters from measurement data. The third algorithm is based on a cascade of a nonlinear observer (NLO) and a linearized adaptive Kalman filter (LAKF), called the adaptive exogenous Kalman filter (AXKF). The pros and cons for each algorithm are discussed. The performance of the algorithms is compared in a single-link joint robot system. Furthermore, the algorithms are implemented in a ball-balancing robot to detect and estimate the magnitude of the actuator faults.
- 21 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A Multi-Objective Constrained Robust Optimization Based on NSGA-II Algorithm
In designing engineering systems, definitive solutions can hardly be applied to actual scenarios. This issue is mainly originated from production constraints and the environmental conditions of the actual systems under exploitation. Therefore, a small change in the design variables vector may lead to a significant change in the optimal design that minimizes the objective functions. Hence, it is important to develop methods that provide optimal (or even sub-optimal) solutions with less sensitivity to the uncertainty of the design variables. This is the focus of this paper. We present a robust Non-dominated-Sorting Genetic Algorithm II (NSGA-II)-based multi-objective constrained optimization algorithm. To further illustrate the method, the proposed algorithm is used in the robust and constrained optimal design of a sample engineering system. Evaluation of the obtained results shows that multi-objective engineering problems can be solved by the multi-objective robust optimization (MORO) through finding Pareto solutions, so that by changing the problem parameters, the changes of the solutions will be within an acceptable range.
- 21 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A Multi-Objective Constrained Robust Optimization Based on NSGA-II Algorithm
In designing engineering systems, definitive solutions can hardly be applied to actual scenarios. This issue is mainly originated from production constraints and the environmental conditions of the actual systems under exploitation. Therefore, a small change in the design variables vector may lead to a significant change in the optimal design that minimizes the objective functions. Hence, it is important to develop methods that provide optimal (or even sub-optimal) solutions with less sensitivity to the uncertainty of the design variables. This is the focus of this paper. We present a robust Non-dominated-Sorting Genetic Algorithm II (NSGA-II)-based multi-objective constrained optimization algorithm. To further illustrate the method, the proposed algorithm is used in the robust and constrained optimal design of a sample engineering system. Evaluation of the obtained results shows that multi-objective engineering problems can be solved by the multi-objective robust optimization (MORO) through finding Pareto solutions, so that by changing the problem parameters, the changes of the solutions will be within an acceptable range.
- 1 December 2020
- Published by Elsevier in Aerospace Science and Technology
- Vol. 107
Fault recoverability for nonlinear systems with application to fault tolerant control of UAVs
- 1 December 2020
- Published by Elsevier in Aerospace Science and Technology
- Vol. 107
Fault recoverability for nonlinear systems with application to fault tolerant control of UAVs
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
A New Matching Algorithm for Fault Section Estimation in Power Distribution Networks
Distribution networks are important components of power and energy infrastructure. Today's distribution networks are vulnerable to different types of faults. To make the electric grid more resilient, it is important to detect and locate faults in distribution lines quickly and accurately. Impedance methods are the most common ways used to locate the faults. In this paper, first possible fault locations are identified using the improved impedance method. Then, its natural frequencies are determined. Since there are more than one possible fault locations, it is necessary to identify the fault section in order to determine the fault location accurately. The fault section and its main location are determined through simulating the fault in each section of possible locations. This is done by small steps and through accommodating the determined frequency to the existing natural frequency registered in the original fault voltage form. The proposed method is applied in Salim's 11-node network in which effect of fault inception angles, effect of different resistors and fault type are tested. Accuracy and efficiency of the proposed method has been verified.
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
A New Matching Algorithm for Fault Section Estimation in Power Distribution Networks
Distribution networks are important components of power and energy infrastructure. Today's distribution networks are vulnerable to different types of faults. To make the electric grid more resilient, it is important to detect and locate faults in distribution lines quickly and accurately. Impedance methods are the most common ways used to locate the faults. In this paper, first possible fault locations are identified using the improved impedance method. Then, its natural frequencies are determined. Since there are more than one possible fault locations, it is necessary to identify the fault section in order to determine the fault location accurately. The fault section and its main location are determined through simulating the fault in each section of possible locations. This is done by small steps and through accommodating the determined frequency to the existing natural frequency registered in the original fault voltage form. The proposed method is applied in Salim's 11-node network in which effect of fault inception angles, effect of different resistors and fault type are tested. Accuracy and efficiency of the proposed method has been verified.