We present TIDES, a text informed design approach for generating physically sound designs based on a textual description and a set of physical constraints. TIDES jointly optimizes structural (topology) and visual properties. A pre-trained text-image model is used to measure the design's visual alignment with a text prompt and a differentiable physics simulator is used to measure its physical performance. We evaluate TIDES on a series of structural optimization problems operating under different load and support conditions, at different resolutions, and experimentally in the lab by performing the 3-point bending test on 2D beam designs that are extruded and 3D printed. We find that it can jointly optimize the two objectives and return designs that satisfy engineering design requirements (compliance and density) while utilizing features specified by text.

Fatigue crack growth propagation in critical rotorcraft structures is much more complex than fixed-wing aircrafts in part due to the random and vibratory nature of the rotorcraft flight load spectrum. Existing physical damage models, which are originally developed for the uniform cyclic loads of fixed-wing platforms, are not accurate enough for rotorcraft structures. Such inaccuracy often results in increased risk of operation and higher cost of maintenance. The goal of this paper is to present an integrated diagnostic framework for accurate fatigue life estimation of critical rotorcraft structures by combining the predictions of a physical damage model and evidence from real-time diagnostic sensor data. The diagnostic framework obtains the most probable crack size at each inspection interval using a sequential Monte Carlo method known as particle filters. To validate the framework, three representative rotorcraft principal structural elements were tested using an actual rotorcraft flight load spectrum. Results show that the crack size estimation error of the method presented here is much lower than any of the currently available physical damage models.