---

Passive systems are preferred tools for seismic control of buildings challenged by probabilistic nature of the input excitation. However, other types of uncertainty still exist in parameters of the control device even when optimally tuned. The present work concerns optimal design of multiple-tuned-mass-damper embedded on a shear building by a number of meta-heuristics. They include well-known genetic algorithm and particle swarm optimization as well as more recent gray wolf optimizer and its hybrid method embedding swarm intelligence. The study is two-fold: first, optimal designs by different meta-heuristics are compared concerning their reduction in structural seismic responses; second, the effect of uncertainty in Multi-Tuned-Mass-Damper parameters, is studied offering new reliability-based curves. Monte Carlo Simulation is employed to evaluate failure probabilities. A variety of structural responses are assessed against seismic excitation including maximal displacement, velocity and acceleration. It is declared that the best algorithm for efficiency and effectiveness has not coincided the best based on the reliability traces. Such traces also show that in a specific range of limit-states, algorithm selection has a serious effect on the reliability results. It was found even more than 35% and depends on the response type.  

---

Shape optimization of a double-curved dam is formulated using control points for interpolation functions. Every design vector is decoded into the integrated water-dam-foundation rock model. An enhanced algorithm is proposed by hybridizing particle swarm algorithm with ant colony optimization and simulated annealing. The best experiences of the search agents are indirectly shared via pheromone trail deposited on a bi-partite characteristic graph. Such a stochastic search is further tuned by Boltzmann functions in simulated annealing. The proposed method earned the first rank in comparison with six well-known meta‑heuristic algorithms in solving benchmark test functions. It captured the optimal shape design of Morrow Point dam, as a widely addressed case-study, by 21% reduced concrete volume with respect to the common USBR design practice and 16% better than the particle swarm optimizer. Such an optimal design was also superior to the others in stress redistribution for better performance of the dam system.
 

---

Although metaheuristic algorithms are popular tools for global optimization, none of them is reported as the best for all problems. Hybridization is an advanced solution to overcome the shortcomings of individual methods by using the power points of the others. Here, a popular swarm intelligent algorithm with high explorative capability is combined with an exploitative operator of differential evolution and some dynamic parameter variation, as well as a greedy operator to enhance the search refinement. The proposed method is evaluated on a variety of engineering and constrained engineering problems, including the optimal design of Belleville Spring, pressure vessel, car side impact problem, and Morrow point dam. According to the results, considerable improvement is observed with respect to the standard particle swarm optimizer as well as competitive performance with a number of metaheuristic algorithms.