Monitoring system behavior using empirical distributions and cumulative distribution norms

This invention relates to monitoring machines or systems, such as elevators or chillers, using multiple sensor data, treated as a random sequence, to construct a stochastic process model of the machine or system, comprising an empirical distribution of the sequence of discrete data; comparison of empirical distribution of data acquired daily on-line with the base information of the stochastic process model provides quantitative and qualitative indicators of system health; use of a cumulative distribution norm, for each machine or system, allows relative comparison to other machines or systems. Sensors () attached to various parameters of a system (), such as an elevator system or a chiller, provide values () of corresponding parameters which are utilized to build () an empirical distribution of the process, such as by means of bootstrapping methodology using a five-dimensional Markov chain model. In normal operation thereafter, the sensors are read periodically and in response to events, and an abnormality is determined by comparison of current information against the empirical distribution of the process. Deviations from normal behavior provide quantitative measure of system malfunction or abnormality; eliminating data from one or more sensors in each iteration of processing identifies one or more sensors associated with the abnormality. By utilizing cumulative distribution norm of deviation from normal behavior, the relative health of one system can be compared with the relative health of other, similar or dissimilar systems.