Channel shear connectors are known as an appropriate alternative for common shear connectors due to having a lower manufacturing cost and an easier installation process. The behavior of channel connectors is generally determined through conducting experiments. However, these experiments are not only costly but also time-consuming. Moreover, the impact of other parameters cannot be easily seen in the behavior of the connectors. This paper aims to investigate the application of a hybrid artificial neural network–particle swarm optimization (ANN-PSO) model in the behavior prediction of channel connectors embedded in normal and high-strength concrete (HSC). To generate the required data, an experimental project was conducted. Dimensions of the channel connectors and the compressive strength of concrete were adopted as the inputs of the model, and load and slip were predicted as the outputs. To evaluate the ANN-PSO model, an ANN model was also developed and tuned by a backpropagation (BP) learning algorithm. The results of the paper revealed that an ANN model could properly predict the behavior of channel connectors and eliminate the need for conducting costly experiments to some extent. In addition, in this case, the ANN-PSO model showed better performance than the ANN-BP model by resulting in superior performance indices.

Gross calorific value (GCV) is one of the essential parameters for evaluating coal quality. Therefore, accurate GCV prediction is one of the primary ways to improve heating value as well as coal production. A novel evolutionary-based predictive system was proposed in this study for predicting GCV with high accuracy, namely the particle swarm optimization (PSO)-support vector regression (SVR) model. It was developed based on the SVR and PSO algorithms. Three different kernel functions were employed to establish the PSO-SVR models, including radial basis function, linear, and polynomial functions. Besides, three benchmark machine learning models including classification and regression trees (CART), multiple linear regression (MLR), and principle component analysis (PCA) were also developed to estimate GCV and then compared with the proposed PSO-SVR model; 2583 coal samples were used to analyze the proximate components and GCV for this study. Then, they were used to develop the mentioned models as well as check their performance in experimental results. Root-mean-squared error (RMSE), correlation coefficient (R²), ranking, and intensity color criteria were used and computed to evaluate the GCV predictive models developed. The results revealed that the proposed PSO-SVR model with radial basis function had better accuracy than the other models. The PSO algorithm was optimized in the SVR model with high efficiency. These should be used as a supporting tool in practical engineering to determine the heating value of coal seams in complex geological conditions.

The present study aims to design a robust adaptive controller employed in the active tuned mass damper (ATMD) system to overcome undesirable vibrations in multistory buildings under seismic excitations. We propose a novel adaptive type-2 neural-fuzzy controller (AT2NF). All system parameters are taken as unknowns. The MLP neural network is used to extract the Jacobian and estimate the structural model; then, the estimated model is applied to the controller online. To tune the control force applied to the ATMD and achieve the control targets, the controller parameters are adaptively trained using the extended Kalman Filter (EKF) and the error back-propagation algorithm. A PID controller is also included in this method to increase the stability and robustness of the adaptive type-2 neural-fuzzy controller against seismic vibrations. An online simple adaptive controller (OSAC) is studied to demonstrate the suggested controller’s superiority. The OSAC is based on adaptive control of the implicit reference model. In this proposed method, the EKF is used to tune the controller parameters online as a novel feature. The uncertainty associated with identifying the mechanical properties of structures, such as mass and stiffness, is one of the primary challenges in the real-time control of structures. This paper investigates how both controllers cope with parametric uncertainties under far-field and near-field seismic excitation. According to numerical results, the AT2NF controller outperforms OSAC in minimizing the dynamic responses of the structure during an earthquake and accomplishing control objectives when the structure’s characteristics change.

This paper presents a novel metaheuristic algorithm inspired by the actions of stadium spectators affecting behavior of players during a match which will be called stadium spectators optimizer (SSO) algorithm. The mathematical model of the SSO algorithm is presented and the performance and efficiency of the presented method is tested on some of the well-known mathematical test functions and also CEC-BC-2017 functions. The SSO algorithm is a parameter-free optimization method since it doesn't require any additional parameter setup at any point throughout the optimization process. It seems urgently necessary to design a novel metaheuristic algorithm that is parameter-free and capable of solving any optimization problem without taking into account extra parameters, as the majority of metaheuristic algorithms rely on the configuration of extra parameters to solve different problems efficiently. A positive point for the SSO algorithm can be seen in the results of the suggested technique, which indicate a partial improvement in performance. The results are compared with those of golf optimization algorithm (GOA), Tiki taka optimization algorithm (TTA), Harris Hawks optimization algorithm (HHO), the arithmetic optimization algorithm (AOA), CMA-ES and EBOwithCMAR algorithms. The statistical tests are carried out for the obtained results and the tests reveal the capability of the presented method in solving different optimization problems with different dimensions. SSO algorithm performs comparably and robustly with the state-of-the-art optimization techniques in 14 of the mathematical test functions. For CEC-BC-2017 functions with ten dimensions, EBOwithCMAR performs better than the proposed method. However, for most functions of CEC-BC-2017 with ten dimensions, the SSO algorithm ranks second after EBOwithCMAR, which is an advantage of the SSO since the proposed method performs better than the well-known CMA-ES optimization algorithm. The overall performance of the SSO algorithm in CEC-BC-2017 functions with 10 dimensions was acceptable, in dimension of 30, 50 and 100, the performance of the proposed method in some functions decreased.