This study proposes a machine learning (ML) model to predict the displacement response of high-rise structures under various vertical and lateral loading conditions. The study combined finite element analysis (FEA), parametric modeling, and a multi-objective genetic algorithm to create a robust and diverse dataset of loading scenarios for developing a predictive ML model. The ML model was trained using a recurrent neural network (RNN) with Long Short-Term Memory (LSTM) layers. The developed model demonstrated high accuracy in predicting time series of vertical, lateral (X), and lateral (Y) displacements. The training and testing results showed Mean Squared Errors (MSE) of 0.1796 and 0.0033, respectively, with R² values of 0.8416 and 0.9939. The model’s predictions differed by only 0.93% from the actual vertical displacement values and by 4.55% and 7.35% for lateral displacements in the Y and X directions, respectively. The results demonstrate the model’s high accuracy and generalization ability, making it a valuable tool for structural health monitoring (SHM) in high-rise buildings. This research highlights the potential of ML to provide real-time displacement predictions under various load conditions, offering practical applications for ensuring the structural integrity and safety of high-rise buildings, particularly in high-risk seismic areas.

This paper investigates the structural performance of flat double-layer grids with various constitutive units, addressing a notable gap in the literature on diverse geometries. Six common types of flat double-layer grids are selected to provide a comprehensive comparison to understand their structural performance. Parametric models are built using Rhino and Grasshopper plugins. Single- and multi-objective optimization processes are conducted on the considered models to evaluate structural mass and maximum deflection. The number of constitutive units, the structural depth, and the cross-section diameter of the members are selected as design variables. The analysis reveals that the semi-octahedron upon square-grid configuration excels in minimizing structural mass and deflection. Furthermore, models lacking a full pyramid form exhibit higher deflections. Sensitivity analyses disclose the critical influence of the design variables, particularly highlighting the sensitivity of structural mass to the number of constitutive units and cross-section diameter. These findings offer valuable insights and practical design considerations for optimizing double-layer grid space structures.

Modeling complex, non-stationary dynamics remains challenging for deterministic neural networks. We present the Chaos-Integrated Synaptic-Memory Network (CISMN), which embeds controlled chaos across four modules—Chaotic Memory Cells, Chaotic Plasticity Layers, Chaotic Synapse Layers, and a Chaotic Attention Mechanism—supplemented by a logistic-map learning-rate schedule. Rigorous stability analyses (Lyapunov exponents, boundedness proofs) and gradient-preservation guarantees underpin our design. In experiments, CISMN-1 on a synthetic acoustical regression dataset (541 samples, 22 features) achieved R² = 0.791 and RMSE = 0.059, outpacing physics-informed and attention-augmented baselines. CISMN-4 on the PMLB sonar benchmark (208 samples, 60 bands) attained R² = 0.424 and RMSE = 0.380, surpassing LSTM, memristive, and reservoir models. Across seven standard regression tasks with 5-fold cross-validation, CISMN led on diabetes (R² = 0.483 ± 0.073) and excelled in high-dimensional, low-sample regimes. Ablations reveal a scalability–efficiency trade-off: lightweight variants train in 95% peak accuracy, while deeper configurations yield marginal gains. CISMN sustains gradient norms (~2300) versus LSTM collapse (<3), and fixed-seed protocols ensure <1.2% MAE variation. Interpretability remains challenging (feature-attribution entropy ≈ 2.58 bits), motivating future hybrid explanation methods. CISMN recasts chaos as a computational asset for robust, generalizable modeling across scientific, financial, and engineering domains.

This study develops a simulation-based surrogate modeling framework for predicting the structural response of space frame structures under predefined geometric, loading, and damage scenarios. The contribution lies in integrating a space-frame-specific parametric modeling workflow with Grasshopper–Karamba3D finite element analysis to generate 28,297 labelled configurations and evaluate machine-learning models for multi-output response prediction. The input variables include member geometry, loading conditions, and prescribed damage-location/radius parameters, while the outputs are total structural mass and maximum displacement. XGBoost, LightGBM, CNN, LSTM, MLP + LSTM, and a fixed equal-weight CNN–LSTM ensemble were compared using the same held-out test set and consistent metrics. The CNN–LSTM ensemble achieved the strongest overall R² and RMSE performance, predicting mass with R² = 0.9985 and RMSE = 0.9278 tons, and displacement with R² = 0.7542 and RMSE = 1.9997 cm. However, the ensemble did not dominate every metric, and the results show that gradient-boosted tree models are strong baselines for structured tabular finite element data. The high mass accuracy mainly reflects the geometry- and material-governed nature of the mass target, whereas displacement prediction is the more demanding and SHM-relevant task. The framework is positioned as a computational tool for rapid simulation-based scenario assessment, not as an inverse damage-localization or field-deployment-ready SHM system. Operational monitoring and inverse damage identification from measured response data remain subjects for future work.

High-rise buildings face significant challenges in withstanding lateral forces, such as wind and seismic activity, which can cause excessive drift and vibrations. Outriggers, integral to stabilizing these structures, are particularly susceptible to stress under such forces. This paper presents a novel approach utilizing Machine Learning (ML) for the Structural Health Monitoring (SHM) of outrigger systems in tall buildings, with the aim of enhancing damage detection and long-term structural integrity predictions. The proposed ML framework uses data from sensor networks and focuses on key stress indicators, including average maximum stress (sig-max) and maximum shear stress (tau-max), to identify early signs of failure. Through the integration of advanced ML algorithms, such as Long Short-Term Memory (LSTM) networks, the study demonstrates the model's high predictive accuracy in forecasting displacements and stress levels under typical lateral loads. The framework offers a proactive approach for monitoring and maintaining structural health in high-rise buildings, reducing risks and optimizing maintenance schedules. By leveraging real-time sensor data, the proposed system supports a continuous evaluation process, contributing to the development of resilient urban infrastructure. This research underscores the potential of ML to revolutionize SHM practices, ensuring the safety and longevity of critical structural systems in tall buildings.