Introducing deep learning algorithms into the field of structural health monitoring (SHM) has contributed to the automatic extraction of damage-sensitive features, but the type and architecture of these algorithms are still in dispute. This paper proposes a hybrid deep learning framework entitled time-distributed one-dimensional convolutional neural network (1D CNN) long short-term memory (LSTM) model, which utilizes raw multisensor time histories to detect structural damages. Using a sliding window that moves along the temporal dimension, the multisensor data are first segmented into subsequences. The 1D CNN layers are simultaneously applied to each subsequence to extract damage-sensitive features from row data samples. These features are then fed into the LSTM layers to extract temporal features between subsequences. As the final step, these extracted features are classified using fully connected layers. In order to assess the performance of this model, a numerical model of a high-rise frame with nonlinear members is used. This hybrid model is assumed to identify the location of damages to this frame. In order to assess the proposed model with a real-world structure, a well-known benchmark building is employed to identify damage patterns by this deep hybrid neural network. A set of metrics related to the performance of the model is measured and evaluated. It is found that the model has an average accuracy of above 96.6% in localizing damage in the numerical structure and above 99.6% in detecting each damage pattern in the experimental building. The results indicate that the proposed model can be applied effectively to the SHM of different structural systems with different damage patterns.

Nowadays, vibration control of structures is considered as a challenging field among scientists and engineers. Structural damage and financial losses due to recent earthquakes in different countries have more than ever before accentuated the importance of controlling earthquake-induced vibrations. In recent years, semi-active control has been introduced as an efficient and reliable type of structural control which provides the reliability of passive control and flexibility of active control systems at the same time. In this study, the performance of a semi-active tuned mass damper (TMD) with adaptive magnetorheological (MR) damper is investigated using type-1 and -2 fuzzy controllers for seismic vibration mitigation of an 11-degree of freedom building model. The TMD is installed on the roof and the MR damper is located on the 11th story. The MR damper has a capacity of producing a 1000 kN control force. The fuzzy system is designed based on the acceleration and velocity of the top floor determining the input voltage needed to produce the control force based on accelerating or decelerating movements of structure. The seismic performance of semi-active type-2 controller, which considers the uncertainties related to input variables, is higher than that of the type-1 fuzzy controller. The type-2 fuzzy controller is capable of reducing further the maximum displacement, acceleration, and base shear of the structure by 11.7, 14, and 11.2%, respectively, compared to the type-1 fuzzy controller.

Because of the occurrence of severe and large magnitude earthquakes each year, earthquake-prone countries suffer considerable financial damages and loss of life. Teaching essential safety measures will lead to a generation that can perform basic procedures during an earthquake, which is an essential and effective solution in preventing the loss of life in this natural disaster. In recent years, Virtual Reality (VR) technology has been a tool used to educate people on safety matters. This paper evaluates the effect of education and premonition on the incorrect decision-making of residents under the stressful conditions of an earthquake. For this purpose, a virtual model has been designed and modeled based on a proposed classroom in a school in the city of Tehran to simulate a virtual learning experience. In contrast, the classroom represents a realistic method of learning. Accordingly, each educational scenario, presented in reality and the virtual model, respectively, was conducted on a statistical sample of 20 students within the range of 20 to 25 years of age. Among the mentioned sample, the first group of 10 students was taught safety measures in a physical classroom. The second group of 10 students participated in a virtual classroom. Evaluation tests on safety measures against earthquakes were distributed after two weeks. Two self-reporting tests of Depression, Anxiety, Stress Scale (DASS) and Beck Anxiety Inventory (BAI) tests were assigned to the second group to evaluate the effect of foresight under two different scenarios. The results indicate that teaching through VR technology yields a higher performance level than the in-person education approach. Additionally, the ability to detect earthquakes ahead is an influential factor in controlling anxiety and determining the right decisions should the event occur.

This research presents designing a control system to reduce seismic responses of structures. Semi-active control of a magnetorheological (MR) damper is used to improve seismic behavior of a 3-story building implementing neural-fuzzy controller made of adaptive neuro-fuzzy inference system (ANFIS) to determine damper input voltage. Both premise and consequent parameters of fuzzy membership and output functions of ANFIS have the ability for training and improvement but most researchers have focused on just consequent parameters. In order to optimize the controller performance, an approach is proposed in this paper where both premise and consequent parameters of fuzzy functions in an ANFIS network are adjusted simultaneously by genetic algorithm (GA). In order to assess the effectiveness of the designed control system, its function is numerically studied on a benchmark 3-story building and is compared to those of a neural network predictive control (NNPC) algorithm, linear quadratic Gaussian (LQG) and clipped optimal control (COC) systems in terms of seismic performance. The results showed desirable performance of the (ANFIS +GA + membership functions + result function) ANFIS–GA–MFR controller in considerably reducing the structure responses under different earthquakes. The proposed controller showed 30 and 39% reductions in peak story drift (J₁) and normed story drift (J₄) respectively compared to the NNPC controller, 32 and 44% reductions in J₁ and J₄ respectively compared to the LQG controller, and 27 and 38% reductions in J₁ and J₄ respectively compared to the COC controller. The proposed controller effectively reduced acceleration and base shear level compared to the uncontrolled state and had a performance relatively similar to those of three other controllers – for instance, it reduced the maximum level acceleration (J₂) 10% higher than COC. Also, the results showed that the ANFIS–GA–MFR controller has more efficiency than the basic ANFIS controller, on average about 20%.