The traditional mathematical model of shape memory alloy (SMA) is complicated and difficult to program in numerical analysis. The artificial neural network is a nonlinear modeling method which does not depend on the mathematical model and avoids the inevitable error in the traditional modeling method. In this paper, an optimized neural network prediction model of shape memory alloy and its application for structural vibration control are discussed. The superelastic properties of austenitic SMA wires were tested by experiments. The material property test data were taken as the training samples of the BP neural network, and a prediction model optimized by the genetic algorithm was established. By using the improved genetic algorithm, the position and quantity of the SMA wires were optimized in a three-storey spatial structure, and the dynamic response analysis of the optimal arrangement was carried out. The results show that, compared with the unoptimized neural network prediction model of SMA, the optimized prediction model is in better agreement with the test curve and has higher stability, it can well reflect the effect of loading rate on the superelastic properties of SMA, and is a high precision rate-dependent dynamic prediction model. Moreover, the BP network constitutive model is simple to use and convenient for dynamic simulation analysis of an SMA passive control structure. The controlled structure with optimized SMA wires can inhibit the structural seismic responses more effectively. However, it is not the case that the more SMA wires, the better the shock absorption effect. When SMA wires exceed a certain number, the vibration reduction effect gradually decreases. Therefore, the seismic effect can be reduced economically and effectively only when the number and location of SMA wires are properly configured. When four SMA wires are arranged, the acceptable shock absorption effect is obtained, and the sum of the structural storey drift can be reduced by 44.51%.

To improve the deformation performance of recycled concrete with tailings (TRC), its carbonization characteristics and deterioration mechanism with different polypropylene fiber content were analyzed macroscopically and microscopically. The results showed that the fiber had little effect on the compressive strength, which increased first and then decreased, with the optimum content being 0.6%. The splitting tensile strength first increased and then tended to be stable, with the optimum dosage ranging from 0.6% to 0.9%. The more the content, the higher the peak strain and the lower the elastic modulus. The rising section of its constitutive curve changed little, while the falling section became more gentle. Carbonization made the relative dynamic elastic modulus change small with a trend of first increasing and then decreasing, and the optimum content was 0.6–0.9%. When the fiber content was small, the influence on the carbonization depth did not remain significant, but when it was large, the depth increased obviously, and this critical content was about 0.6%. Microscopically, through nuclear-magnetic resonance (NMR) and scanning electron microscope (SEM) analysis, due to the strong tensioning effect of the fiber, when a small amount was added, the porosity and pore structure had not been significantly changed, so the impact on its resistance to carbonization was not obvious. However, after excessive addition, the interface transition zone (ITZ) between different materials became larger, resulting in a significant increase of its harmful cracks and a great impact on the anti-carbonization ability, with the optimal content being about 0.6%. This study provides a theoretical reference for the deformation performance improvement measure of TRC, which would be helpful for the rapid promotion and application of green concrete in engineering practice.

To improve the utilization efficiency of iron tailings (IOT) and recycled coarse aggregate (RCA), the mechanical properties, erosion depth and other erosion characteristics of recycled aggregate concrete (RAC) with different IOT amounts were studied in salt spray erosion environments and the erosion mechanisms were analyzed by SEM technology. The results showed that at the same erosion age, IOT caused the compressive strength and splitting tensile strength of RAC to tend to first increase and then decrease, with the optimum mixing amount being approximately 40%. Under the same conditions, the erosion depth of RAC was much higher than that of ordinary concrete. The erosion depth first decreased and then increased with an increasing amount of IOT. When the IOT content was 30–40%, the salt spray erosion depth reached its minimum. The solidification coefficient K₁ first decreased and then increased with the increase in iron tailings content. At its lowest point, the iron tailings content was approximately between 30% and 50%, which demonstrated that the higher the salt spray erosion age, the larger the solidification coefficient. Through SEM microscopic images, it could be seen that the appropriate amount of iron tailings caused the formation of salt spray erosion crystals and that the effect of physical expansion pressure caused a reduction in the porosity of RAC and a slight increase in its mechanical properties and salt spray erosion resistance. When the iron tailings content was large, the optimal mix ratio of the concrete also changed and then harmful pores and cracks were regenerated. Therefore, resistance to salt spray erosion was weakened. The research in this paper provides a theoretical basis for the engineering application of recycled concrete with tailings in salt spray environments.

To better control engineering structures subjected to external disturbances, such as earthquakes of varying magnitudes, a smart compound damper is developed and its performance is investigated in this paper. Unlike devices for passive control systems without adjustable control force, the dynamic responses of the engineering structure can be more effectively suppressed under seismic excitation by using devices for active control systems that feature active input to the actuators. A compound damper designed in this vein consists of shape memory alloy (SMA) wires and a variable-friction damper that can provide an adjustable control force according to the level of ground motion by changing the voltage of piezoelectric ceramic (PZC) actuators. Numerical simulations of a seismically excited two-storey steel frame structure were implemented to evaluate the performance of the proposed SMA/PZC compound damper. A back-propagation neural network model was developed using experimentally obtained data to describe the hysteretic behaviour of the SMA wires. A Takagi–Sugeno (T-S) fuzzy controller was used to determine the command voltage of the PZC actuators, such that the compound damper could perform well when applied to structural control. The resulting solution, hybrid control modulated with a T-S fuzzy control strategy, was found to be more effective than passive control.

Based on the superelasticity of shape memory alloy (SMA) and the electrodeformation of a piezoelectric transition (PZT) ceramic, a novel SMA/PZT composite control device (SPCCD) was designed and its energy dissipation performance and neural network constitutive model investigated. The composite control device is composed of a variable friction unit that contains four rectangular PZT actuators and an SMA unit that includes energy-dissipation and resettable wires. The friction force can be adjusted in real time by applying the voltage to the PZT actuators and the SMA wires can dissipate energy via hysteresis and provide a reset force. This composite control device’s different components participate in energy dissipation at different seismic intensities. Electro-mechanical tests are conducted to evaluate the performance of the SPCCD with different displacement amplitudes, loading/unloading frequencies, and excitation voltages. Correspondingly, the force-displacement curves are acquired, and the influences of the lap hysteretic energy dissipation, equivalent stiffness, and equivalent damping ratio on the energy dissipation capacity of the SPCCD are analyzed. Then, the excitation voltage and loading history are considered as neuronal input to establish a back-propagation (BP) neural network model of the SPCCD. The experimental results show that the hysteresis curves of the SPCCD are approximately symmetrical and the loading/unloading frequency has little effect on the mechanical properties. The maximum control force of the SPCCD linearly increases with an increase in the excitation voltage, and its semiactive PZT unit has a large adjustable range for energy dissipation. Thus, the SPCCD is reasonably designed. Moreover, the BP network constitutive model is able to accurately track the output of the SPCCD, providing an effective means for the establishment and application of the constitutive model to SMA-based composite control devices.