Huangbin Liang

Last Name

Liang

First Name

Huangbin

ORCID

0000-0002-8608-1635

Organisational unit

03890 - Chatzi, Eleni / Chatzi, Eleni

Show all metadata

Search Results

Publications1 - 10 of 10

Resilience-based post disaster recovery optimization for infrastructure system via deep reinforcement learning
Liang, Huangbin; Moya, Beatriz; Chinesta, Francisco; et al. (2026)
Reliability Engineering & System Safety
Infrastructure systems are essential yet vulnerable to natural and man-made disasters. Efficient post-disaster recovery requires repair-scheduling approaches under limited resources shared across the system. Existing approaches like component ranking, greedy algorithms, and data-driven models often lack resilience orientation, adaptability, and require high computational resources when tested within such a context. To tackle these issues, we propose a solution by leveraging Deep Reinforcement Learning (DRL) methods and a specialized resilience metric to lead the recovery optimization. The system topology is represented adopting a graph-based structure, where the system's recovery process is formulated as a sequential decision-making problem. Deep Q-learning algorithms are employed to learn optimal recovery strategies by mapping system states to specific actions, i.e., which component ought to be repaired next, with the goal of maximizing long-term recovery from a resilience-oriented perspective. To demonstrate the efficacy of our proposed approach, we implement this scheme on the example of post-earthquake recovery optimization for an electrical substation system. A comparative analysis against baseline methods reveals the superior performance of the proposed method in terms of both optimization effect and computational cost, rendering this an attractive approach in the context of resilience enhancement and rapid response and recovery.
Seismic resilience assessment and improvement framework for electrical substations
Liang, Huangbin; Blagojević, Nikola; Xie, Qiang; et al. (2023)
Earthquake Engineering & Structural Dynamics
Experience from previous earthquakes shows that electrical substations are the most vulnerable components within the power transmission system. Thus, their disaster resilience is essential for providing electric power to communities in earthquake-prone regions. In this study, a quantitative framework was proposed to assess the seismic resilience of electrical substations. The functionality of a substation was quantified using its maximum allowable transmission capacity that integrates the substation topology, redundancy level, line capacity, and power balance. The network model of the substation was developed to investigate how component damage affects substation's functionality. Substation's recovery was simulated as a time-stepping process, in which at each time step the substation's ability to provide transmission capacity was conditioned on the functionality state of its components, whose recovery depends on the availability of repair crews and spare parts. The uncertainty of the resilience assessment was quantified by considering the uncertainty in the component-level vulnerability and recoverability. The impacts of components' robustness, repair resource constraints, and post-earthquake recovery scheduling on substation resilience were investigated by modifying components' seismic fragility curves, available recovery resources, and repair priorities. A case study was conducted on a real-world 220/110 kV step-down substation, and a parametric analysis was carried out to investigate the effect of various seismic resilience improvement strategies to demonstrate the applicability of the proposed framework in seismic disaster risk reduction and management.
Resilience-based post disaster recovery optimization for infrastructure system via Deep Reinforcement Learning
Liang, Huangbin; Moya, Beatriz; Chinesta, Francisco; et al. (2024)
arXiv
Infrastructure systems are critical in modern communities but are highly susceptible to various natural and man-made disasters. Efficient post-disaster recovery requires repair-scheduling approaches under the limitation of capped resources that need to be shared across the system. Existing approaches, including component ranking methods, greedy evolutionary algorithms, and data-driven machine learning models, face various limitations when tested within such a context. To tackle these issues, we propose a novel approach to optimize post-disaster recovery of infrastructure systems by leveraging Deep Reinforcement Learning (DRL) methods and incorporating a specialized resilience metric to lead the optimization. The system topology is represented adopting a graph-based structure, where the system's recovery process is formulated as a sequential decision-making problem. Deep Q-learning algorithms are employed to learn optimal recovery strategies by mapping system states to specific actions, as for instance which component ought to be repaired next, with the goal of maximizing long-term recovery from a resilience-oriented perspective. To demonstrate the efficacy of our proposed approach, we implement this scheme on the example of post-earthquake recovery optimization for an electrical substation system. We assess different deep Q-learning algorithms to this end, namely vanilla Deep Q-Networks (DQN), Double DQN(DDQN), Duel DQN, and duel DDQN, demonstrating superiority of the DDQN for the considered problem. A further comparative analysis against baseline methods during testing reveals the superior performance of the proposed method in terms of both optimization effect and computational cost, rendering this an attractive approach in the context of resilience enhancement and rapid response and recovery.
Harnessing hybrid digital twinning for decision-support in smart infrastructures
Liang, Huangbin; Moya, Beatriz; Seah, Eugene; et al. (2025)
Data-Centric Engineering
Digital Twinning (DT) has become a main instrument for Industry 4.0 and the digital transformation of manufacturing and industrial processes. In this statement paper, we elaborate on the potential of DT as a valuable tool in support of the management of intelligent infrastructures throughout all stages of their life cycle. We highlight the associated needs, opportunities, and challenges and discuss the needs from both the research and applied perspectives. We elucidate the transformative impact of digital twin applications for strategic decision-making, discussing its potential for situation awareness, as well as enhancement of system resilience, with a particular focus on applications that necessitate efficient, and often real-time, or near real-time, diagnostic and prognostic processes. In doing so, we elaborate on the separate classes of DT, ranging from simple images of a system, all the way to interactive replicas that are continually updated to reflect a monitored system at hand. We root our approach in the adoption of hybrid modeling as a seminal tool for facilitating twinning applications. Hybrid modeling refers to the synergistic use of data with models that carry engineering or empirical intuition on the system behavior. We postulate that modern infrastructures can be viewed as cyber-physical systems comprising, on the one hand, an array of heterogeneous data of diversified granularity and, on the other, a model (analytical, numerical, or other) that carries information on the system behavior. We therefore propose hybrid digital twins (HDT) as the main enabler of smart and resilient infrastructures.
Seismic performance improvement of ±800 kV UHV DC wall busing using friction ring spring dampers
Xie, Qiang; Liang, Huangbin; Wang, Xiaoyou (2021)
Earthquake Spectra
Wall bushings that connect converter valves within hall buildings and other electric facilities in a direct current (DC) field are indispensable in substations but vulnerable to earthquakes. A finite element model was developed to evaluate the seismic performance of a real ultra-high-voltage (UHV) DC wall bushing. The numerical results show that the maximum stress of the wall bushing during seismic activity does not satisfy the strength safety factor provisions within Chinese regulations. To improve the seismic performance of the wall bushing, an energy dissipation device composed of eight friction ring spring dampers (FRSDs) was proposed to be installed between the connection plate on which the bushing is mounted and a steel wall frame. In addition, optimum parameters of the FRSDs were researched and determined, then the seismic responses of the wall bushing with and without the FRSDs were compared to evaluate the energy dissipation effects. Full-scale shaking table tests were conducted on a wall bushing with the designed energy dissipation device. The validity of the numerical simulations and effectiveness of the proposed energy dissipation device of the wall bushing were verified by the experimental results in terms of seismic response mitigation.
An analytical model for seismic response analysis of electrical equipment-steel support structure
Xie, Qiang; Liang, Huangbin (2024)
Journal of Constructional Steel Research
Electrical equipment mounted on supporting structures is typical in a substation but vulnerable to earthquakes from previous field investigations. To evaluate the seismic performance of such an electrical equipment-support coupling system, a modal space analytical model was developed using the vibration partial differential equation (PDE) with distributed parameters and joint nodes. In the analytical model, resonant frequencies and mode shapes were obtained through numerical algorithms based on the boundary condition of each segmented beam. Then seismic responses of the coupling system can be attained by the modal decomposition method and superposition principle. A full-scale shaking table test was conducted on a 550 kV bushing-support coupling structure, and the accuracy of the analytical model was verified by the experimental results. Furthermore, a ceramic breakage inside the connecting flange at the base cross-section of the bushing specimen was observed after the seismic qualification test, which means its seismic performance can not meet the demand in the IEC seismic design specifications. To figure out this problem, parametric analysis was carried out using the analytical model to study the influence of parameters of the supporting structure and flange connection on the seismic responses of the equipment. In light of the analytical results, halving the original flange's flexural rigidity can reduce the bottom stress of the bushing by about 20% without over-magnifying its top displacement for this bushing-support coupling system. Application of the presented analytical modelling method can assist in the seismic optimization design of other equipment-support coupling systems in substations.
Quantifying the value of seismic structural health monitoring for post-earthquake recovery of electric power system in terms of resilience enhancement
Liang, Huangbin; Moya, Beatriz; Chinesta, Francisco; et al. (2026)
Reliability Engineering & System Safety
Post-earthquake recovery of electric power networks (EPNs) is critical to community resilience. Traditional recovery processes often rely on prolonged and imprecise manual inspections for damage diagnosis, leading to suboptimal repair prioritization and extended service disruptions. Seismic Structural Health Monitoring (SSHM) offers the potential to expedite post-earthquake recovery by enabling more accurate and timely damage assessment. However, the deployment of SSHM comes with a cost and the quantifiable benefit of SSHM in terms of system-level resilience remains underexplored. This study develops an integrated probabilistic simulation framework to quantify the system-level value of SSHM in enhancing EPN resilience. The framework incorporates damage simulations based on EPN configuration, seismic hazard, fragility function, and damage-functionality mapping models, along with recovery simulations considering repair scheduling, resource constraints, transfer and repair durations. System functionality is evaluated via graph-based island detection and optimal power flow analysis under electrical constraints. Resilience is quantified using the Lack of Resilience (LoR) metric derived from the time-evolution functionality restoration curve. The effect of SSHM is incorporated by altering the quality of damage information used to create repair schedules. Specifically, different monitoring scenarios (e.g., no-SSHM baseline, partial SSHM, and full SSHM with various assessing accuracy levels) are modelled using observation matrices that simulate misclassification of component damage states. The results demonstrate that improved damage awareness enabled by SSHM significantly accelerates recovery and reduces LoR by up to 21%. This study provides a quantitative foundation for evaluating the system-level resilience benefits of SSHM and guiding evidence-based sensor investment decisions for critical infrastructures.
System Vulnerability Analysis Simulation Model for Substation Subjected to Earthquakes
Liang, Huangbin; Xie, Qiang (2022)
IEEE Transactions on Power Delivery
To evaluate the earthquake-resistance capability of an entire substation, which is a complex multi-input-multi-output system (MIMOS) composed of many various types of electrical equipment interconnected by conductors, a flow-based analysis model integrating the merit of the flow block diagram and state tree method was introduced. Two performance indicators of a substation were defined from different stakeholders, one is the expected total power transmission capacity and the other is the power accessibility to the targeted users from the substation. And directed graph logic system analysis models were developed on the Simulink platform based on the original internal logic relationship among distributed components and the power delivery path in the substation with different function types. Afterward, the defined reliability indicators associated with the overall system under a certain seismic intensity level can be obtained by combining the seismic vulnerability curve at the equipment level through the Monte Carlo simulation method. The feasibility and accuracy of the proposed system vulnerability analysis model were verified by comparison with the analytical solution through the illustrative simple MIMOS. Then A case study on a practical 220/110 kV substation was conducted, the analysis results can assist decision-makers in seismic optimization of different retrofitting measures and distribution plans for substations.
A multi-model probabilistic framework for seismic risk assessment and retrofit planning of electric power networks
Liang, Huangbin; Moya, Beatriz; Chinesta, Francisco; et al. (2026)
Reliability Engineering & System Safety
Electric power networks are critical lifelines, and their disruption during earthquakes can lead to severe cascading failures and significantly hinder post-disaster recovery. Enhancing their seismic resilience requires identifying and strengthening vulnerable components in a cost-effective and system-aware manner. However, existing studies often overlook the systemic behavior of power networks under seismic loading. Common limitations include isolated component analyses that neglect network-wide interdependencies, oversimplified damage models assuming binary states or damage independence, and the exclusion of electrical operational constraints. These simplifications can result in inaccurate risk estimates and inefficient retrofit decisions. This study proposes a multi-model probabilistic framework for seismic risk assessment and retrofit planning of electric power systems. The approach integrates: (1) regional seismic hazard characterization with ground motion prediction and spatial correlation models; (2) component-level damage analysis using fragility functions and multi-state damage–functionality mappings; (3) system-level cascading impact evaluation through graph-based island detection and constrained optimal power flow analysis; and (4) retrofit planning via heuristic optimization to minimize expected annual functionality loss (EAFL) under budget constraints. Uncertainty is propagated throughout the framework using Monte Carlo simulation. The methodology is demonstrated on the IEEE 24-bus Reliability Test System, showcasing its ability to capture cascading failures, identify critical components, and generate effective retrofit strategies. Results underscore the framework’s potential as a scalable, data-informed decision-support tool for enhancing the seismic resilience of power infrastructure.
Post-earthquake rapid assessment of interconnected electrical equipment based on hybrid modelling
Moya, Beatriz; Liang, Huangbin; Chinesta, Francisco; et al. (2025)
Materials Research Proceedings ~ Structural Health Monitoring – 10APWSHM
Electrical substations play an indispensable role in the power grid for adjusting power voltage and controlling power flow, ensuring normal power transmission and distribution. However, substation equipment is particularly vulnerable to seismic events due to the use of brittle porcelain materials and highly slender structures, increasing the risk of structural failure and cascading effects. While significant research has focused on seismic performance and innovative damping techniques for different standalone equipment, critical gaps remain, particularly in accounting for the interconnected nature of substation equipment and post-earthquake emergency response. This study addresses these gaps by proposing a hybrid post-earthquake rapid assessment model that utilizes monitored ground motion signals. Hybrid modeling combines physics-based models with data-driven approaches, leveraging the strengths of both to overcome their individual limitations. Specifically, the study integrates Graph Neural Networks (GNN) with mechanistic models of standalone equipment to capture the dynamic behavior and interaction forces of interconnected equipment under seismic loads. The spatial relationships of the interconnected equipment are represented through a graph structure, and temporal dependencies are learned through recurrent computations. Thus, this approach circumvents the need for costly and impractical sensor installations on every piece of equipment, offering a cost-effective and accurate assessment method. The efficacy of the proposed hybrid modelling technique is demonstrated with a case study on combinations of 800 kV post insulators interconnected by busbars. By providing a rapid assessment of each equipment’s post-earthquake condition, the proposed model can be applied to inform emergency repair actions and enhance the resilience of power infrastructure.

Publications1 - 10 of 10

Huangbin Liang

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results