System and method for conditional multi-output regression for machine condition monitoring

摘要

A method for predicting sensor output values of a sensor monitoring system, includes providing a set test input values to a system of sensors, and one or more known sensor output values from the sensor system, where other sensor output values are unknown, calculating, for each unknown sensor output value, a predictive Gaussian distribution function from the test input values and the known output sensor values, and predicting each unknown output y_m by integrating over a product of the predictive Gaussian distribution function and a conditional Gaussian distribution of the unknown output sensor values with respect to the test input values and other unknown output sensor values. A mean and covariance of the predictive Gaussian distribution function are determined from a training phase, and a hyperparameter of the conditional Gaussian distribution are determined by another training phase.