Search

The use of machine learning (ML) for predicting concrete compressive strength (CCS) has shown promising and accurate results, making it a valuable tool in the field. However, efficient prediction requires not only a robust ML approach but also a comprehensive and well-curated dataset. This study addresses this challenge by investigating an extensive and integrated dataset of (1) concrete compositions (mixture proportions) and (2) testing conditions (mechanical and microstructure properties of concrete testing samples), containing 1525 observations relating to 39 parameters. On algorithms side, this research proposes novel tree-structured parzen estimator based extreme gradient boosting (TPE-xgboost) for accurate and confident CCS predictions. Moreover, SHapley Additive exPlanations (SHAP) analysis was performed to provide a comprehensive understanding of feature importance, dependencies, and interactions. Compared to prior research, this study demonstrates significant improvements in CCS prediction accuracy for separate investigations on concrete compositions (3.77 %) and mechanical and microstructure properties (28.57 %), while maintaining reasonable accuracy for the integrated dataset despite its complexity and sparseness. SHAP analysis reveals key influential factors, including age and water-to-binder ratio in concrete composition, and peak load and height of testing samples, as well as microstructural characteristics such as mean values of global autocorrelation length and its integral range. This research provides valuable insights into model optimization, predictive performance, and feature dependencies and interactions, contributing to the development of more accurate and reliable CCS prediction models. • Predicted compressive strength on enhanced dataset with 39 features. • Proposed xgboost for accurate and confident predictions on sparse dataset. • Used Tree-structured parzen estimator (TPE) approach for optimization of xgboost. • SHAP analysis reveals key influential features and interactions. [ABSTRACT FROM AUTHOR]

The functionality of community buildings not only depends on the damage to individual buildings but also on the interactions with other infrastructure systems. This paper incorporates these interactions by applying the systems thinking approach to analyze community resilience. The proposed framework starts with identifying the physical infrastructure systems and key components in a community. Then, the seismic hazard scenarios are defined, and the component damage and recovery are assessed by utilizing fragility and consequence functions. After that, a network model, considering the interdependencies between the utility networks and the dependency of utility networks on the community buildings, is introduced to evaluate the component-level building functionality. Finally, community resilience is assessed by proposing community-level indicators including inherent resilience, community functionality, and access to essential facilities. The proposed model is illustrated on a community consisting of building portfolios, water, and electric power systems under four hazard scenarios. It is concluded that the systems thinking approach considered at a community level provides important insights into community resilience such as building functionality, utility demand, and supply, and access to essential facilities, among others. [ABSTRACT FROM AUTHOR]

• Develop an intelligent seismic risk optimization framework for building structures. • Leverage deep reinforcement learning for performance enhancements under hazard. • Compare model performance with genetic optimization, policy gradients, and deep Q-networks. • The proposed tool is efficient for complex decision-making problem of high dimension. • Illustrate the proposed methodology on building structures under seismic hazard. Risk management often involves retrofit optimization to enhance the performance of buildings against extreme events but may result in huge upfront mitigation costs. Existing stochastic optimization frameworks could be computationally expensive, may require explicit programming, and are often not intelligent. Hence, an intelligent risk optimization framework is proposed herein for building structures by developing a deep reinforcement learning-enabled actor-critic neural network model. The proposed framework is divided into two parts including (1) a performance-based environment to assess mitigation costs and uncertain future consequences under hazards and (2) a deep reinforcement learning-enabled risk optimization model for performance enhancement. The performance-based environment takes mitigation alternatives as input and provides consequences and retrofit costs as output by utilizing several steps, including hazard assessment, damage assessment, and consequence assessment. The risk optimization is performed by integrating performance-based environment with actor-critic deep neural networks to simultaneously reduce retrofit costs and uncertain future consequences given seismic hazards. For illustration, the proposed framework is implemented on a portfolio with numerous building structures to demonstrate the new paradigm for intelligent risk optimization. Also, the performance of the proposed method is compared with genetic optimization, deep Q-networks, and proximal policy optimization. [ABSTRACT FROM AUTHOR]

Buildings are susceptible to reduced performance due to deterioration and recurrent extreme events. Hence, a life-cycle sustainability and resilience enhancement approach is proposed herein for reinforced concrete structures under environmental deterioration and recurrent extreme events. The framework consists of five parts: (1) extreme event modeling to characterize the occurrence uncertainty of the recurrent extreme events, (2) deterioration modeling to assess deterioration initiation and propagation during the investigated time, (3) structural modeling to assess structural response given deterioration and natural hazards, (4) life-cycle sustainability and resilience assessment to determine the consequences, downtimes and functionality during the investigated time given mitigation alternatives, and (5) decision-making to select the optimal retrofit alternative given life-cycle sustainability and resilience performance by utilizing utility decision theory and multi-criteria decision making. The proposed framework is illustrated on an intermediate moment resisting reinforced concrete frame structure prone to carbonation-induced deterioration and stochastically recurring seismic hazards. The methodology highlights the importance of considering life-cycle sustainability and resilience and provides a tool to effectively manage structures under deterioration and recurring extreme events. • Proposed a renewal process-based seismic hazard arrival methodology. • Integrated sustainability and resilience in a life cycle. • Investigated combined effect of deterioration and recurrent seismic hazards. • Considered socioeconomic and environmental consequences and functionality during the investigated time. • Provide a decision-making tool by leveraging the utility decision theory and multi-criteria decision-making methods. [ABSTRACT FROM AUTHOR]

It is of vital importance to incorporate sustainability and resilience in the performance-based decision-making of civil infrastructure under seismic hazard. However, a performance-based engineering framework utilizing component-level approach, integrating seismic loss, sustainability, and resilience in a multi-criteria decision-making (MCDM) is not yet extensively developed particularly for retrofit selection in a long-term perspective. This paper introduces a framework utilizing performance-based approach to couple seismic loss, sustainability, and resilience in decision-making framework for selection of different retrofit alternatives. A component-based probabilistic approach is developed for the seismic loss, sustainability, and resilience assessment in a long-term perspective. The resulting social, economic, and environmental consequences are converted to expected annual consequences (EACs) by considering the full range of seismic hazards, and are utilized as a multi-criterion in the technique for order preference by similarity to ideal solution (TOPSIS). The proposed long-term performance-based multi-criteria decision-making (PB-MCDM) framework considers five consequences, which include cost, casualties, equivalent carbon emissions, embodied energy, and repair time. Based on the illustrative example, it may be concluded that incorporating seismic sustainability and resilience in PB-MCDM approach in a long-term perspective can provide ideal solutions and better decision-making against retrofit alternatives. [ABSTRACT FROM AUTHOR]

Existing buildings can be at a greater seismic risk due to non-conformance to current design codes and may require structural retrofitting to improve building performance. The performance of buildings is measured in terms of immediate consequences due to direct damage, but the continuing impacts related to recovery are not considered in seismic retrofit assessment. This paper introduces a framework of retrofit selection based on the seismic resilience of deficient buildings retrofitted with the conventional mitigation approaches. The assembly-based methodology is considered for the seismic resilience assessment by compiling a nonlinear numerical model and a building performance model. The collapse fragility is developed from the capacity curve, and the resulting social, economic, and environmental consequences are determined. The seismic resilience of a building is assessed by developing a downtime assessment methodology incorporating sequence of repairs, impeding factors, and utility availability. Five functionality states are developed for the building functionality given investigated time interval, and a functionality curve for each retrofit is determined. It is concluded that seismic resilience can be used as a performance indicator to assess the continuing impacts of a hazard for the retrofit selection. [ABSTRACT FROM AUTHOR]

Recent earthquakes have highlighted additional losses due to the lack of resilience of damaged structures. Environmental impact, as performance indicator, has also received increased attention within performance-based earthquake engineering. In this article, a combined probabilistic framework is proposed to assess seismic risk, sustainability, and resilience of a non-ductile reinforced concrete frame structure. The framework utilizes three-dimensional inelastic fiber-based numerical modeling approach to develop limit states associated with performance levels. The decision variables (i.e. repair cost, downtime, and equivalent carbon emissions) are quantified at both component level and system level and are compared considering seismic risk, sustainability, and resilience. In addition, the proposed approach considers uncertainties in the building performance and consequence functions of structural and non-structural components. Fast-track and slow-track schemes are utilized as a repair strategy and probabilistic resilience is quantified given the investigated time period. The proposed approach can aid the development of the next generation of performance-based engineering incorporating both resilience and sustainability. [ABSTRACT FROM AUTHOR]

• Propose multi-objective optimization and decision-making framework. • Considers risk attitudes of decision-makers under uncertain consequences. • Assess consequences by establishing surrogate-based Gaussian process models. • Illustrates the framework on a community building portfolio. The performance of community building portfolios under extreme events is increasingly been assessed in terms of socioeconomic and environmental consequences. These multiple consequences are expensive to be evaluated, uncertain in nature, and it requires an efficient optimization and decision-making tool for performance enhancements on a community level. In this paper, an efficient multi-objective performance-based optimization and decision-making framework is proposed to assess and enhance the performance of community building portfolios under uncertain consequences. The proposed approach includes (1) performance-based black-box to evaluate the socioeconomic and environmental consequences given community building portfolios by considering all the possible hazard scenarios, (2) surrogate-based multi-objective optimization to efficiently approximate the Pareto-optimal solutions by exploiting Gaussian process models, spectral sampling, non-dominated crowding and sorting, and hyper improvements, among others, and (3) utility theory-based decision-making of a community building portfolios considering multiple performance-objectives over an entire hazard curve and under different risk attitudes. The proposed methodology is illustrated on community building portfolio under seismic hazards of varying intensities and occurrence probabilities. A performance-based black box is utilized along with a proposed optimization technique to assess community-level consequences. Finally, the utility for Pareto-optimal solutions is assessed and discussed for possible performance enhancements and decision-making. [ABSTRACT FROM AUTHOR]

Accurately predicting the payload movement and ensuring efficient control during dynamic tower crane operations are crucial for crane safety, including the ability to predict payload mass within a safe or normal range. This research utilizes deep learning to accurately predict the normal and abnormal payload movement of tower cranes. A scaled-down tower crane prototype with a systematic data acquisition system is built to perform experiments and data collection. The data related to 12 test case scenarios are gathered, and each test case represents a specific combination of hoisting and slewing motion and payload mass to counterweight ratio, defining tower crane operational variations. This comprehensive data is investigated using a novel attention-based deep neural network with Tree-Structured Parzen Estimator optimization (TPE-AttDNN). The proposed TPE-AttDNN achieved a prediction accuracy of 0.95 with a false positive rate of 0.08. These results clearly demonstrate the effectiveness of the proposed model in accurately predicting the tower crane payload moving condition. To ensure a more reliable performance assessment of the proposed AttDNN, we carried out ablation experiments that highlighted the significance of the model's individual components. [ABSTRACT FROM AUTHOR]