AI-Driven Design Optimization of Engineering Systems: A Case Study on Turboshaft Engines

In the pursuit of optimizing complex engineering systems, the exploration and thorough understanding of the design space become imperative, particularly when dealing with multi-objective systems characterized by an array of independent variables. This paper presents a comprehensive analysis on the design space mapping of such intricate systems, utilizing a turboshaft engine as a representative case study. The initial phase of our methodology involves the employment of a physics-based model to generate a synthetic dataset. This dataset reflects the intricate interplay of various system parameters that underpin the engine's operation. The synthesized data serves as a foundation for the subsequent development of a Machine Learning or Deep Learning-based surrogate model. This surrogate AI model is meticulously crafted to encapsulate the multiple inputs and outputs inherent in the turboshaft engine's functioning, thereby facilitating an efficient and accurate exploration of the design space. The core of our investigation revolves around the utilization of the AI surrogate model for conducting multi-objective optimization. This optimization process is not merely focused on enhancing specific performance metrics but is also geared towards identifying a comprehensive family of feasible design solutions. Such an approach enables the delineation of the entire design space, offering invaluable insights into the trade-offs and synergies among different design objectives. Through this methodology, we can uncover a wide spectrum of viable design alternatives, thereby providing a robust framework for decision-making in the engineering design process.