Soft computing for propulsion control

Abstract

The objective is to explore how soft computing technologies could be employed to improve overall vehicle system safety, reliability, and rocket engine performance by development of a qualitative and reliable engine control system (QRECS). This is addressed by enhancing engine control using soft computing technologies, data mining tools, and sound software engineering practices. Goals for addressing quality are improving software management, development time, maintenance, processor execution, fault tolerance and mitigation, and nonlinear control in power level transitions. The intent is not to discuss any shortcomings of existing engine control methodologies, but to provide alternative design choices for control, implementation, performance, and sustaining engineering, all relative to addressing reliability. The approaches presented require knowledge in rocket engine propulsion, software engineering for embedded flight software systems, and soft computing technologies (e.g., neural networks, fuzzy logic, data mining, and Bayesian belief networks), some of which are briefed. For this effort, the demonstration engine testbed is the MC-1 engine which is simulated with hardware and software. A brief plan of action for design, development, implementation, and testing a Phase One effort for QRECS is given, along with expected results. Phase One focuses on development of a Smart Start Engine Module for proper engine start operations. The final product that this paper proposes is an approach to development of an alternative low cost engine controller that would be capable of performing in unique vision spacecraft vehicles requiring low cost advanced avionics architectures for autonomous operations from engine pre-start to engine shutdown.