Prof Mahmoud Shafiee

Professor Mahmoud Shafiee

Professor in Energy Resilience; Head of Energy and Environment Research; University REF Lead for Engineering
Fellow of Institute for Sustainability (IfS)
PhD, CEng, MEI, FIMechE, MIET, MInstNDT, SFHEA, PGCHE
+44 (0)1483 682356

Academic and research departments

Centre for Civil Infrastructure Systems and Engineering, Centre for Engineering Materials, School of Engineering, Institute for Sustainability.

About

News

08 JUN 2026

Why study a masters in sustainable energy

The sun glints off some solar panels in front of a blue sky studded with fluffy clouds

17 MAR 2026

New renewable energy solutions could halve carbon emissions from off-grid buildings

08 MAY 2024

Why study a masters in mechanical engineering

In the media

Professor Shafiee will be a member of the Scientific Committee of the Third International Conference on Durability, Repair and Maintenance of Structures (DRMS), to be held at the University of Porto on 11–12 March 2027

Professor Shafiee runs a Special Session on "Adopting remanufacturing strategies for lifetime extension and recovery of renewable energy power plant assets" for the 9th International Workshop on Advanced Remanufacturing (IWAR 2025) in Spain

Plenary Speaker

Professor Shafiee is speaking at the Westminster Energy, Environment and Transport Forum, contributing to the discussion on "Next Steps for Onshore Wind in England". His presentation will explore the current policy landscape, opportunities for growth, and the challenges facing onshore wind development across the country.

Speaker

Professor Shafiee's research, titled “Predicting Energy Consumption in Residential Buildings Using Advanced Machine Learning Algorithms,” received the Best Paper Award 2025. The study introduced innovative machine learning-based algorithms to accurately predict energy consumption in residential buildings under varying indoor and outdoor conditions.

Energies

Professor Shafiee was a featured speaker at the UK’s Clean Energy Roundtable, broadcast by Business Insider, where they discussed the critical role of resilience and security in energy production and transmission

Business Insider
MS

Research

Research interests

Supervision

Postgraduate research supervision

Teaching

Sustainable development goals

My research interests are related to the following:

Affordable and Clean Energy UN Sustainable Development Goal 7 logo

Publications

M. Shafiee, G. Stamelos, M. M. Aziminia, T. Elusakin, T. Adedipe, F. Dinmohammadi (2021)Failure analysis of floating offshore wind turbine technologies, In: Proceedings in Marine Technology and Ocean Engineeringpp. 488-494
DOI: 10.1201/9781003134572-55
Pooya Sajjadi, Fateme Dinmohammadi, Mahmood Shafiee (2025)Fault Detection of Cyber-Physical Systems Using a Transfer Learning Method Based on Pre-Trained Transformers, In: Sensors25(13)4164 MDPI
DOI: 10.3390/s25134164

Highlights What are the main findings? A pre-trained transformer model, fine-tuned with transfer learning, significantly improves fault detection in cyber-physical systems (CPSs) despite limited fault-labeled data. The proposed method achieves a high average F1-score of 93.38% on industrial CPS datasets, outperforming traditional CNN and LSTM models. What is the implication of the main finding? Transformer-based transfer learning enables more reliable fault diagnostics in industrial CPS environments where data scarcity and domain shifts are common. The approach demonstrates practical scalability from controlled lab conditions to real-world industrial applications.Highlights What are the main findings? A pre-trained transformer model, fine-tuned with transfer learning, significantly improves fault detection in cyber-physical systems (CPSs) despite limited fault-labeled data. The proposed method achieves a high average F1-score of 93.38% on industrial CPS datasets, outperforming traditional CNN and LSTM models. What is the implication of the main finding? Transformer-based transfer learning enables more reliable fault diagnostics in industrial CPS environments where data scarcity and domain shifts are common. The approach demonstrates practical scalability from controlled lab conditions to real-world industrial applications.Abstract As industries become increasingly dependent on cyber-physical systems (CPSs), failures within these systems can cause significant operational disruptions, underscoring the critical need for effective Prognostics and Health Management (PHM). The large volume of data generated by CPSs has made deep learning (DL) methods an attractive solution; however, imbalanced datasets and the limited availability of fault-labeled data continue to hinder their effective deployment in real-world applications. To address these challenges, this paper proposes a transfer learning approach using a pre-trained transformer architecture to enhance fault detection performance in CPSs. A streamlined transformer model is first pre-trained on a large-scale source dataset and then fine-tuned end-to-end on a smaller dataset with a differing data distribution. This approach enables the transfer of diagnostic knowledge from controlled laboratory environments to real-world operational settings, effectively addressing the domain shift challenge commonly encountered in industrial CPSs. To evaluate the effectiveness of the proposed method, extensive experiments are conducted on publicly available datasets generated from a laboratory-scale replica of a modern industrial water purification facility. The results show that the model achieves an average F1-score of 93.38% under K-fold cross-validation, outperforming baseline models such as CNN and LSTM architectures, and demonstrating the practicality of applying transformer-based transfer learning in industrial settings with limited fault data. To enhance transparency and better understand the model's decision process, SHAP is applied for explainable AI (XAI).

Pooya Sajjadi, Fateme Dinmohammadi, Mahmood Shafiee (2025)Machine Learning in Prognostics and Health Management of Cyber-Physical Systems: A Review, In: IEEE Access13pp. 162320-162354 Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/ACCESS.2025.3605553

The digital transformation of industries within the framework of Industry 4.0 has accelerated the adoption of Cyber-Physical Systems (CPS), which integrate physical processes with computational and communication technologies. While these systems offer numerous advantages in monitoring and control, their complexity creates challenges in ensuring reliability and resilience. To address these challenges, Prognostics and Health Management (PHM) frameworks use modern sensor technologies and machine learning (ML) to anticipate faults, extend asset life, and improve operational efficiency. This paper presents a comprehensive review of ML methodologies applied to PHM within the domain of CPS, while exploring key advancements, existing challenges, and future prospects. A novel taxonomy is proposed to classify existing research based on hardware and software fault types, PHM stages, data characteristics, ML techniques, and performance metrics, with the aim of guiding researchers and practitioners in selecting appropriate ML methods for end-to-end PHM tasks spanning data collection, preprocessing, model development, and validation. The review also identifies emerging trends, including the growing adoption of deep learning techniques such as transformers and large language models. Additionally, it underscores the need for more holistic approaches that address the deeper integration of physical and cyber systems, the complexity of cascading fault scenarios, and the persistent gap between academic research and industrial applications. The findings of this study provide a valuable foundation for advancing PHM strategies and supporting their effective implementation within the evolving landscape of CPS.

Farzad Ghafoorian, Seyed Reza Mirmotahari, Shayan Farajyar, Mehdi Mehrpooya, Mahmood Shafiee (2025)Performance Optimization of Savonius VAWTs Using Wind Accelerator and Guiding Rotor House for Enhanced Rooftop Urban Energy Harvesting, In: Machines (Basel)13(9)838 Mdpi
DOI: 10.3390/machines13090838

Savonius drag-based rotors, a type of vertical-axis wind turbine (VAWT), are well-suited for urban environments-particularly residential rooftops-owing to their compact design and ability to capture wind from all directions. However, their relatively low efficiency and narrow operational range pose significant challenges, such as limited energy output under variable wind conditions and reduced performance across a broad range of tip speed ratios. To address these issues, this study explores flow augmentation using strategically placed deflectors, referred to as Wind Accelerators and Guiding Rotor Houses (WAG-RHs). Four different configurations, including double, triple, oblique, and straight designs, were evaluated against both omni-directional guide vanes (ODGVs) and a conventional rotor. The findings show that the ODGV configuration successfully extends the operational range from a tip speed ratio of 0.5 to 0.6-termed the extended performance point (EPP)-and increases the power coefficient (Cp) by up to 300% compared to the conventional design. Among all setups, the straight WAG-RH configuration proved most effective, not only achieving the EPP but also delivering a 385% and 264.3% increase in local and AVE Cp values, respectively compared to the conventional rotor. It also outperformed the ODGV-equipped rotor by 25%, thanks to its radial and dual-plane arrangement.

Mohammad Hemmati, Behnam Mohammadi-Ivatloo, Mehdi Abapour, Mahmood Shafiee (2021)Thermodynamic modeling of compressed air energy storage for energy and reserve markets, In: Applied Thermal Engineering193116948 PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.applthermaleng.2021.116948

Compressed air energy storage (CAES) system is one of the highly efficient and low capital cost energy storage technologies, which is used on a large scale. However, due to multiple operational and technical limitations, the CAES operation should be incorporated with thermodynamic characteristics. Therefore, in this paper, novel thermodynamic modeling of CAES facility integrated with the hybrid thermal, wind, and photovoltaic (PV) farms to participate in energy and reserve markets is investigated. Considering the thermodynamic characteristics makes the proposed scheduling more realistic, while imposes multiple constraints on the optimal operation of the hybrid system. The operation of the CAES facility during charging and discharging modes, considering thermodynamic characteristics are analyzed simultaneously, and the state of charge of the cavern is calculated for both modes. In addition to taking into account the thermodynamic characteristics, the recovery cycle capability is embedded for the CAES facility to recover heat from the turbine in the preheater results in increased turbine efficiency. The proposed scheduling of the hybrid system is exposed by high-level uncertainty caused by energy and reserve market prices, as well as wind and PV farms power fluctuation. Hence, the scenario-based stochastic approach is applied based on real historical data of the KHAF station in IRAN to handle existing uncertainties. Numerical results are provided for different cases. The major conclusions of the numerical results show the effectiveness of the recovery cycle from profit improvement and burned fuel reduction up to 11.36% and 11.33%, respectively, while the thermodynamical constraints in the CAES performance make the realistic model, compared with the conventional CAES.

Morteza Zare Oskouei, Behnam Mohammadi-Ivatloo, Mehdi Abapour, Mahmood Shafiee, Amjad Anvari-Moghaddam (2021)Techno-Economic and Environmental Assessment of Coordinated Operation of Regional Grid-Connected Energy Hubs Considering High Penetration of Wind Power, In: Journal of Cleaner Production280(1)124275 Elsevier
DOI: 10.1016/j.jclepro.2020.124275

Nowadays, the high penetration of renewable energy sources (RESs) with non-uniformly distributed patterns has created unprecedented challenges for regional power systems to maintain system flexibility and reliability. These technical challenges obligate power system operators to curtail part of the produced renewable energy at various scheduling intervals. Motivated by these challenges, grid-connected energy hubs are seen as a way forward to boost system flexibility, decrease the rate of renewable power curtailment, and increase energy efficiency. However, simplified models may significantly affect the performance of the grid-connected energy hubs in practice. Hence, this paper proposes a holistic structure to determine the optimal coordinated operation of the grid-connected energy hubs and the regional power system by relying on the high penetration of wind power. In this regard, various fundamental challenges that have not yet been addressed in an integrated manner, including the CO2 emission rate and the amount of curtailed renewable energy along with total operating costs of the integrated energy system, are among the main objectives of the optimization problem. The proposed structure is developed in the form of tractable mixed-integer nonlinear programming (MINLP) problem to handle the day-ahead security-constrained unit commitment (SCUC). The information-gap decision theory (IGDT)-based robust model is used for accurate modeling of wind power uncertainty. The characteristics of the proposed IGDT-based robust SCUC model and its benefits are investigated through several technical case studies conducted on the modified 6-bus and 24-bus test systems. The simulation results validate the effectiveness and feasibility of the proposed structure. According to the obtained results for the 6-bus test system, networked energy hubs can help the system operator to reduce the total operating cost, wind power curtailment cost, and CO2 emission cost by 16.62%, 100%, and 30.44%, respectively, through utilizing up-to-date energy conversion facilities and energy storage systems as well as managing energy demands. It can be seen that the proposed strategy is a very effective step towards achieving a 100% renewable energy system

Tobi Elusakin, Mahmood Shafiee, Tosin Adedipe, Fateme Dinmohammadi (2021)A Stochastic Petri Net Model for O&M Planning of Floating Offshore Wind Turbines, In: Energies14(4)1134 MDPI
DOI: 10.3390/en14041134

With increasing deployment of offshore wind farms further from shore and in deeper waters, the efficient and effective planning of operation and maintenance (O&M) activities has received considerable attention from wind energy developers and operators in recent years. The O&M planning of offshore wind farms is a complicated task, as it depends on many factors such as asset degradation rates, availability of resources required to perform maintenance tasks (e.g., transport vessels, service crew, spare parts, and special tools) as well as the uncertainties associated with weather and climate variability. A brief review of the literature shows that a lot of research has been conducted on optimizing the O&M schedules for fixed-bottom offshore wind turbines; however, the literature for O&M planning of floating wind farms is too limited. This paper presents a stochastic Petri network (SPN) model for O&M planning of floating offshore wind turbines (FOWTs) and their support structure components, including floating platform, moorings and anchoring system. The proposed model incorporates all interrelationships between different factors influencing O&M planning of FOWTs, including deterioration and renewal process of components within the system. Relevant data such as failure rate, mean-time-to-failure (MTTF), degradation rate, etc. are collected from the literature as well as wind energy industry databases, and then the model is tested on an NREL 5 MW reference wind turbine system mounted on an OC3-Hywind spar buoy floating platform. The results indicate that our proposed model can significantly contribute to the reduction of O&M costs in the floating offshore wind sector.

Tosin Adedipe, Mahmood Shafiee (2021)An economic assessment framework for decommissioning of offshore wind farms using a cost breakdown structure, In: The International Journal of Life Cycle Assessment26(2)pp. 344-370 Springer
DOI: 10.1007/s11367-020-01793-x

Abstract Purpose As wind power generation increases globally, there will be a substantial number of wind turbines that need to be decommissioned in the coming years. It is crucial for wind farm developers to design safe and cost-effective decommissioning plans and procedures for assets before they reach the end of their useful life. Adequate financial provisions for decommissioning operations are essential, not only for wind farm owners but also for national governments. Economic analysis approaches and cost estimation models therefore need to be accurate and computationally efficient. Thus, this paper aims to develop an economic assessment framework for decommissioning of offshore wind farms using a cost breakdown structure (CBS) approach. Methods In the development of the models, all the cost elements and their key influencing factors are identified from literature and expert interviews. Similar activities within the decommissioning process are aggregated to form four cost groups including: planning and regulatory approval, execution, logistics and waste management, and post-decommissioning. Some mathematical models are proposed to estimate the costs associated with decommissioning activities as well as to identify the most critical cost drivers in each activity group. The proposed models incorporate all cost parameters involved in each decommissioning phase for more robust cost assessment. Results and discussion A case study of a 500 MW baseline offshore wind farm is proposed to illustrate the models’ applicability. The results show that the removal of wind turbines and foundation structures is the most costly and lengthy stage of the decommissioning process due to many requirements involved in carrying out the operations. Although inherent uncertainties are taken into account, cost estimates can be easily updated when new information becomes available. Additionally, further decommissioning cost elements can be captured allowing for sensitivity analysis to be easily performed. Conclusions Using the CBS approach, cost drivers can be clearly identified, revealing critical areas that require attention for each unique offshore wind decommissioning project. The CBS approach promotes adequate management and optimisation of identified key cost drivers, which will enable all stakeholders involved in offshore wind farm decommissioning projects to achieve cost reduction and optimal schedule, especially for safety-critical tasks.

Arif Hussain, Amir Hosein Sakhaei, Mahmoud Shafiee (2024)Machine learning-based constitutive modelling for material non-linearity: A review, In: Mechanics of Advanced Materials and StructuresAhead of Print(Ahead of Print)pp. 1-19 Taylor & Francis
DOI: 10.1080/15376494.2024.2439557

Machine learning (ML) models are widely used across numerous scientific and engineering disciplines due to their exceptional performance, flexibility, prediction quality, and ability to handle highly complex problems if appropriate data are available. One example of such areas which has attracted a lot of attentions in the last couple of years is the integration of data-driven approaches in material modeling. There has been several successful researches in implementing ML-based constitutive models instead of classical phenomenological models for various materials, particularly those with non-linear mechanical behaviors. This review paper aims to systematically investigate the literature on ML-based constitutive models for materials and classify these models based on their suitability for material non-linearity including Non-linear elasticity (hyperelasticity), plasticity, visco-elasticity, and visco-plasticity. Furthermore, we also reviewed and compared the ML-based approaches that have been applied for architectured materials as these groups of materials are designed to represent specific material behaviors that might not exist in classical and conventional material categories. The other goal of this review paper is to provide initial steps in understanding of various ML-based approaches for material modeling, including artificial neural networks (ANN), Gaussian processes, random forests (RF), generated adversarial networks (GANs), support vector machines (SVM), different regression models and physics-informed neural networks (PINN). This paper also outlines different data collection methods, types of data, data processing approaches, the theoretical background of the ML models, advantage and limitations of various models, and potential future research directions. This comprehensive review will provide researchers with the knowledge necessary to develop high-fidelity, robust, adaptable, flexible, and accurate data-driven constitutive models for advanced materials.

Fateme Dinmohammadi, Y Han, M Shafiee (2023)Predicting Energy Consumption in Residential Buildings Using Advanced Machine Learning Algorithms, In: Energies16(9)3748 MDPI
DOI: 10.3390/en16093748

The share of residential building energy consumption in global energy consumption has rapidly increased after the COVID-19 crisis. The accurate prediction of energy consumption under different indoor and outdoor conditions is an essential step towards improving energy efficiency and reducing carbon footprints in the residential building sector. In this paper, a PSO-optimized random forest classification algorithm is proposed to identify the most important factors contributing to residential heating energy consumption. A self-organizing map (SOM) approach is applied for feature dimensionality reduction, and an ensemble classification model based on the stacking method is trained on the dimensionality-reduced data. The results show that the stacking model outperforms the other models with an accuracy of 95.4% in energy consumption prediction. Finally, a causal inference method is introduced in addition to Shapley Additive Explanation (SHAP) to explore and analyze the factors influencing energy consumption. A clear causal relationship between water pipe temperature changes, air temperature, and building energy consumption is found, compensating for the neglect of temperature in the SHAP analysis. The findings of this research can help residential building owners/managers make more informed decisions around the selection of efficient heating management systems to save on energy bills.

Additional publications