Ensuring Correct Sensor Operation and Decisions Under Harsh Environments

NASA seeks to provide a highly flexible instrumentation solution to mitigate the propulsion system risks that are inherent in spaceflight. Alphacore and its Research Partner, Arizona State University, will develop a framework for self-calibrating sensors, backed by artificial intelligence with in-field calibration capabilities. Specifically, Alphacore will develop comprehensive in-field calibration tools, including a low-cost MEMS accelerometer reference chip with thermal sensor calibration that does not require application of physical stimulus. In Phase I we will prove the feasibility of our approach by modeling pressure sensor and a capacitive accelerometer, designing electrical tests to correlate with mechanical characteristics, developing an aging simulation framework for the sensors, and designing the parametrizable self-test IP. In Phase II we will fabricate test and prototype circuits that implement and validate the work done in Phase I, as well as extend the concepts developed in Phase I to other types of sensors.This project will develop methodologies for 2-tier calibration of sensor-based machine learning systems; Front-End Calibration and Software Calibration. The goal of sensor front-end calibration is to maintain highest level of sensor performance throughout the operation. To this end, the sensor hardware is monitored and calibrated continuously in real-time based on the readings built-in self-test monitors. On the software end, there are various mechanisms to continuously monitor and calibrate the machine learning system. Software calibration will be achieved by incorporating the sensor error model into the machine learning system, adaptive boosting, and assigning a confidence level to the decisions made by the machine learning system based on residual error.