Description: Dual-mode scramjets have the potential to operate efficiently in a variety of flight conditions without requiring complicated variable configurations, thus providing cost-effective access to space and potential for high-speed atmospheric transport. However, the successful design and operation of these systems requires the identification of potential failure modes related to the transition between ramjet and scramjet modes and inlet-isolator-combustor unstart events. High-fidelity computer simulations and detailed diagnostics in a ground-based facility provide invaluable data, but cannot be routinely used for an extensive exploration of design solutions due to cost. Furthermore, it is challenging to formulate efficient design strategies that accommodate performance constraints and guarantee safe operations; as a consequence safety factors (and limitations in vehicle operability) are typically introduced a-posteriori leading to suboptimal systems. Cascade's proposal aims at investigating modern scramjet systems using a combination of computational tools focusing on design strategies that a-priori include safety margins from unstart. The project goal is to combine machine-learning tools, in-house high-fidelity simulation capabilities, and high-throughput low fidelity engineering techniques within a risk-aware optimization framework that can potentially enhance the ability to generate safe and performant design. Machine learning will enable the extraction and categorization of knowledge from in-house high-fidelity data and experiments; the engineering tools afford the exploration of a large set of geometrical configurations and operating scenarios; the QMU (Quantification of Margins and Uncertainties) technique, will provide the optimization framework. Validation of the high-fidelity and low-fidelity tools with data from the HIFiRE experimental campaign will provide an explicit measure of the confidence in the simulations which will explicitly be included within QMU.

Benefits: The unstart prediction technology is applicable to three main areas within NASA. First, the combination of high-fidelity and high-throughput engineering tools employed and validated in this project enables NASA to design and virtually test the impact of various dual-mode scramjet inlet and combustor chamber designs for hypersonic travel and access to space. Finding the most efficient method to transition between subsonic to supersonic combustion speeds, while avoiding unstart is a key requirement to propel scramjet usage into reality. Second, the image-based machine learning tools can be utilized for detecting physical phenomena across a diverse set of applications, possibly not even limited to fluid-dynamics problems, such as the detection of incipient structural failures. Lastly, the Quantification of Margins and Uncertainties (QMU) methodology can be relevant for many complex systems beyond scramjets. The methodology's focus on identifying uncertainty and rigorously assessing their impact on performance to create more accurate operability margins based on prediction can lead to a more comprehensive strategy that directly combines performance criteria and safety into the design process.

The unstart prediction technology can be used to detect the precursors to engine failure in military and commercial aircrafts and spacecrafts developed by companies such as Lockheed, Boeing, SpaceX, BlueOrigin, and Virgin Galactic. It can also be used to detect incipient structural failures in other sectors such as transportation and energy. The image-based machine learning tools can be utilized for detecting physical phenomena across a diverse set of applications, possibly not even limited to fluid-dynamics problems, such as the detection of incipient structural failures in the transportation and energy sector (i.e. failure in a power generation turbine). Lastly, the Quantification of Margins and Uncertainties (QMU) methodology can be applied to any engineering application that is required to adhere to certain safety margins relating to uncertainty. The methodology's focus on identifying uncertainty and rigorously assessing their impact on performance to create more accurate operability margins based on prediction can lead to a more comprehensive design process that optimizes for operational profitability and safety.