International Journal of Optimization in Civil Engineering

IMPACT IDENTIFICATION IN FRAMED STRUCTURES USING DEEP LEARNING: A CNN-BASED APPROACH OPTIMIZED BY BAYESIAN OPTIMIZATION

S. Shojaee

Accurate detection and localization of impacts in structural systems are crucial for safety and enabling effective structural health monitoring (SHM). This paper aims to identify multiple consecutive impacts in framed structures with unknown dynamic properties, using time-domain acceleration data. Traditional methods often struggle under complex conditions such as noisy environments and multiple impacts. To overcome these limitations, we propose a deep learning-based framework utilizing Convolutional Neural Networks (CNNs) to extract intricate patterns from acceleration signals. Input data are generated through high-fidelity numerical simulations based on the Finite Element Method (FEM), allowing precise control over impact characteristics and their spatial distribution. A fixed-length sliding window is employed to segment the acceleration time series, enabling the model to perform localized and near-real-time impact detection. To further improve model performance, Bayesian optimization is utilized for hyperparameter tuning, enhancing accuracy and efficiency over traditional grid search. The proposed model is numerically evaluated on two-dimensional structures: a steel pin-jointed camel-back truss and a shear frame. The results reveal that the proposed strategy achieves high accuracy in estimating the location, timing, and magnitude of impacts, even under noisy conditions. The key novelty of this research lies in combining deep learning with advanced optimization techniques to solve the impact detection problem in structures with unknown parameters. These findings establish a robust framework for advancing intelligent, data-driven SHM systems, with direct applications in real-world infrastructure. The proposed methodology demonstrates significant potential to mitigate economic costs and safety risks associated with structural failures under impact loading.

A TWO-PHASE METAMODEL-DRIVEN APPROACH FOR TOPOLOGY AND SIZE OPTIMIZATION OF TRUSS STRUCTURES

M. Ilchi Ghazaan

This paper introduces a novel two-phase metamodel-driven methodology for the simultaneous topology and size optimization of truss structures. The approach addresses critical limitations in computational efficiency and solution quality. The framework integrates the Flexible Stochastic Gradient Optimizer (FSGO) with adaptive sampling and machine learning to minimize the number of structural analyses (NSAs), while achieving lighter, high-performance designs. In Phase One, FSGO employs a dual global-local search strategy governed by Extensive Constraints (EC), a dynamic constraint relaxation mechanism to balance exploration of unconventional topologies and exploitation of optimal member sizes. By creating adaptive margins around design constraints, EC enables broader exploration of the design space while ensuring feasibility. Phase Two focuses on precision size optimization, leveraging pruned metamodels trained on critical regions of the design space to refine cross-sectional areas for the finalized topology. Comparative evaluations on benchmark planar and spatial trusses demonstrate the method’s superiority: it reduces NSAs by 22–79% compared to state-of-the-art approaches and achieves 0.04–0.7% lighter designs while eliminating up to 31% of redundant members. Results validate the framework as a paradigm shift in truss optimization, merging computational efficiency with structural innovation.

OPTIMAL DESIGN OF DOUBLE-TMDI FOR SEISMIC CONTROL OF BUILDINGS UNDER SOIL-STRUCTURE INTERACTION BY OPPOSITION-SWITCHING SEARCH

M. Shahrouzi

The tuned mass damper inerter systems have recently received considerable attention in the field of structural control. The present work offers a practical configuration of such a device, called double tuned mass damper inerter (DTMDI) that connects the inerter into the damper masses rather than be attached to the main structure. Soil-structure interaction is also taken into account for the soft and dense soils as well as for the fixed based condition. The H∞ norm of the transfer functions for the roof response is minimized as the objective function. The parameters of DTMDI are optimized using opposition-switching search as an efficient parameter-less algorithm in comparison with lightning attachment procedure optimization, sine cosine algorithm and particle swarm optimization. The system performance is evaluated in the frequency domain, as well as in the time domain under various earthquakes including far-field records, near-field records with forward directivity and with fling-step. The results show superiority of opposition-switching search for optimal design of the proposed DTMDI so that it can significantly reduce both the roof displacement and acceleration response for all the SSI conditions.

OPTIMIZATION OF THE PARAMETERS OF THE TRIPLE FRICTION PENDULUM BEARING SYSTEMS FOR A THREE-DIMENSIONAL FRAME WITH NONLINEAR BEHAVIOUR

R. Kamgar

This paper utilized the multi-objective cuckoo search (mocs) optimization algorithm to compute the optimum parameters of three-dimensional frame structures controlled by the triple friction pendulum bearing (TFPB) systems. For this purpose, firstly, the maximum capacity of the unisolated structure (uncontrolled structures) is evaluated for six main earthquakes using an incremental dynamic analysis (IDA). Then, the structure is controlled using the TFPB systems and excited using the maximum acceleration calculated from the previous step to calculate the optimal parameters of the TFPB system (i.e., the coefficients of friction and effective radius of curvature) subjected to some constraints in such a way that the maximum local drift ratio and also the Park-Ang damage index ratio minimized. Finally, to evaluate the behavior of the controlled structure, it is excited by main shock-aftershock earthquakes under sequence IDA. The results showed an average seismic improvement of 30% and 40% for the controlled structures according to the Park-Ang damage and drift indices, respectively.

NUMERICAL STUDY ON DIFFERENT TYPES OF WEIRS TO DETERMINE THEIR OPTIMALITY BASED ON THE HYDRAULIC AND STRUCTURAL CRITERIA

T. Bakhshpoori

In this research, different types of weirs have been numerically investigated to determine the optimal design based on two hydraulic and structural criteria. FLOW 3D and ABAQUS software were utilized for the hydraulic and structural analysis, respectively. The accuracy of the numerical models was verified with the available experimental and numerical results. In the hydraulic investigation, 18 models of different types of weirs including rectangular (6 models), square, triangular (3 models), circular, ogee (3 models), and labyrinth (4 models) weirs were examined. In the structural study of weirs, there are 13 models, including rectangular, square, triangular (3 models), circular, ogee (3 models), and labyrinth (4 models) weirs were analyzed. The results of hydraulic analyzes showed that the dimensions of the rectangular weir significantly affect the output velocity. In triangular weirs, the highest energy dissipation will occur with an apex angle of 45°, and with the increase of the apex angle in the ogee weir, more turbulence is observed in the downstream flow. In labyrinth weirs, by changing the shape of the weir from triangular to rectangular, the output velocity and also turbulence of the flow will be much less. According to the findings of the structural analyses, the increase of the apex angle in triangular weirs, the weir will be more critical, but the situation will be more suitable in ogee weirs. Additionally, the rectangular labyrinth weir performs the best structurally among the labyrinth weirs.

TUNED METAHEURISTIC ALGORITHMS FOR OPTIMAL DESIGN PROBLEMS WITH CONTINUOUS VARIABLES

A. Kaveh

Metaheuristic algorithms mostly consist of some parameters influencing their performance when faced with various optimization problems. Therefore, this paper applies Multi-Stage Parameter Adjustment (MSPA), which employs Extreme Latin Hypercube Sampling (XLHS), Primary Optimizer, and Artificial Neural Networks (ANNs) to a recently developed algorithm called the African Vulture Optimization Algorithm (AVOA) and a well-known one named Particle Swarm Optimization (PSO) for tuning their parameters. The performance of PSO is tested against two engineering and AVOA for two structural optimization problems, and their corresponding results are compared to those of their default versions. The results showed that the employment of MSPA improved the performance of both metaheuristic algorithms in all the considered optimization problems.

OPTIMIZATION OF SLOPE CRITICAL SURFACES USING SA_EVPS ALGORITHM WITH SEEPAGE AND SEISMIC EFFECTS

P. Hosseini

This study presents a novel approach for optimizing critical failure surfaces (CFS) in homogeneous soil slopes by incorporating seepage and seismic effects through the Self-Adaptive Enhanced Vibrating Particle System (SA_EVPS) algorithm. The Finite Element Method (FEM) is employed to model fluid flow through porous media, while Bishop's simplified method calculates the Factor of Safety (FOS). Two benchmark problems validate the proposed approach, with results compared against traditional and meta-heuristic methods. The SA_EVPS algorithm demonstrates superior convergence and accuracy due to its self-adaptive parameter optimization mechanism. Visualizations from Abaqus simulations and comprehensive statistical analyses highlight the algorithm's effectiveness in geotechnical engineering applications. The results show that SA_EVPS consistently achieves lower FOS values with smaller standard deviations compared to existing methods, indicating more accurate identification of critical failure surfaces.

MULTI-MATERIAL TOPOLOGY OPTIMIZATION OF STRUCTURES BY USING THE METHOD OF MOVING ASYMPTOTES

S. M. Tavakkoli

This study aims to deal with multi-material topology optimization problems by using the Methods of Moving Asymptotes (MMA) method. The optimization problem is to minimize the strain energy while a certain amount of material is used. Several types of structures, including plane, plate and shell structures, are considered and optimal materials distribution is investigated. To parametrize the topology optimization problem, the Solid Isotropic Material with Penalization (SIMP) method is utilized. Analytical sensitivity analysis is performed to obtain the derivatives of the objective function and volume constraints with respect to the design variables. Two types of material with different modulus of elasticities are considered and, therefore, each element has two design variables. The first design variable represents the presence or absence of material in an element, while the second design variable determines the type of material assigned to the element. In order to analyze the structures required during the optimization process, the ABAQUS software is employed. To integrate the topology optimization procedure with ABAQUS model, a Python script is developed. The obtained results demonstrate the performance of the proposed method in generating reasonable and effective topologies.