Intelligent test selection for machine failure isolation using qualitative physics

A method of using a processor for analyzing machine signals to determine the presence of particular machine faults, comprising the steps of:

• the processor generating a plurality of pending hypotheses wherein each hypothesis has associated therewith a set of confluences using variables and equations to describe operation of components of the machine which are assumed not to have failed;
• the processor forming a type I set of hypothesis variables wherein for each variable of said type I set, every possible value of said variable will render at least one of said hypotheses invalid;
• the processor receiving machine signals indicative of values of machine parameters wherein at least one of said signals corresponds to said type I set of hypothesis variables;
• the processor propagating values indicative of said machine signals through said confluences to produce a set of predictions for values of confluence variables;
• the processor discarding hypotheses which produce an inconsistent set of predictions;
• the processor saving hypotheses which produce a consistent set of predictions;
• and
• the processor indicating the presence of one or more particular machine faults in response to there remaining a single hypothesis corresponding to failure of one or more particular machine components.