Measurement of dynamic responses plays an important role in structural health monitoring, damage detection and other fields of research. However, in aerospace engineering, the physical sensors are limited in the operational conditions of spacecraft, due to the severe environment in outer space. This paper proposes a virtual sensor model with partial vibration measurements using a convolutional neural network. The transmissibility function is employed as prior knowledge. A four-layer neural network with two convolutional layers, one fully connected layer, and an output layer is proposed as the predicting model. Numerical examples of two different structural dynamic systems demonstrate the performance of the proposed approach. The excellence of the novel technique is further indicated using a simply supported beam experiment comparing to a modal-model-based virtual sensor, which uses modal parameters, such as mode shapes, for estimating the responses of the faulty sensors. The results show that the presented data-driven response virtual sensor technique can predict structural response with high accuracy.
The aerodynamic heating results in the rapid rise of the surface temperature of hypersonic vehicles. As a key factor that influences the selection and design of thermal structures, equilibrium surface temperatures occur when the aerodynamic heat flux imposed on the surface is balance by thermal radiation from the surface, which are typically utilized in the conceptual and preliminary designs of hypersonic vehicles. Obviously the equilibrium surface temperature is the peak temperature that thermal-structure can achieve, since heat conducted into the structure is not calculated when the surface fluxed are balanced. In order to accurately obtain the temperature environment over specified trajectories, an integrated coupled approach in which the aerodynamic heating, radiative heat transfer and structure heat conduction are all taken into account is proposed. This study aims to develop a coupled analysis methodology for the temperature environment prediction under combined aerodynamic heating, radiative transfer and structure heat conduction. The integrated coupled approach is used to obtain the temperature environment of the typical control surface for a representative hypersonic trajectory. Results illustrate that the temperature environment obtained by integrated coupled approach is obviously lower than that by equilibrium, which regularly leads to 25% maximum percent error on the leading edge, 48% maximum percent error on the other regions. Furthermore, the estimation temperature is associated with the trajectory, which indicates that during climbing phase, the difference of surface temperature obtained by equilibrium and coupled approach is much larger than that during gliding phase.
Nomenclatureaero q = aerodynamic heating flux rad q = radiative heating flux cond q = heat conduction flux h = heat transfer coefficient r h = recover enthalpy w h = wall enthalpy St = Stanton number e = local air density e u = local air velocity f c = local skin friction coefficient r p = Prandtl number Re = Reynolds number x = distance from the top to the point of interest along the surface = air viscosity coefficient * = air density coefficient based on reference enthalpy = air viscosity coefficient based on reference enthalpy N R = radius of curvature at the leading edge = air density u = air velocity c u = velocity at the sea level sl = density at the sea level * h = reference enthalpy = Boltzmann constant, 23 1.3806505 10 / J K = emissivity of surface w T = surface temperature k = thermal conduction coefficient R T = equilibrium temperature trans t = time step of heat conduction aero t = time step of aerodynamic heating
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.