Method and systems for virtual sensor selection and blending

A method of controlling the operation of an engine of a vehicle, said method comprising:

• receiving data from a plurality of sensors associated with corresponding sensed locations on the engine;
• determining by each of a plurality of engine model modules configured to simulate an operation of the engine, an estimate of a process parameter of a location in the engine where at least one of a sensor for the process parameter is not available, a sensor for the process parameter is not present at the location, a sensor at the location has failed, and a sensor at the location is determined to be inaccurate;
• determining model blending factors using an estimate source selector;
• determining an estimated virtual sensor value using the determined estimates from at least two of the plurality of engine model modules and the model blending factors;
• and
• controlling the operation of the engine using the estimated virtual sensor value.

A system for controlling the operation of a vehicle engine comprising:

• a plurality of sensors configured to output a sensed vehicle parameter value;
• and
• an engine controller comprising:
• a plurality of engine model modules comprising at least one of a physics model, a regression model, and a look-up table model, said plurality of engine model modules executing independently and programmed to receive engine operating condition values from the plurality of sensors, each of said plurality of engine model modules programmed to determine an estimate of a process parameter of a location in the engine where at least one of a sensor for the process parameter is not present at the location and a sensor at the location has failed, said plurality of engine model modules further configured to generate at least one of a model accuracy level and a model validity level, said model accuracy level represents a measure of the accuracy of the determined estimate based on a predetermined assessment of the inputs to the respective model, said model validity level represents a measure of the validity of the model based on a predetermined assessment of the inputs to the respective model;
• a model verifier configured to apply at least one of a range check, a rate check, a drift check, a noise detection, and a prediction on the determined estimates from each of the engine model modules to generate a verification result for the determined estimates of the process parameter from each of the engine model modules, the verification result represents a measure of a validity of the determined estimates of the process parameter from each of the engine model modules;
• an estimate source selector communicatively coupled to said plurality of engine model modules and said model verifier, said estimate source selector configured to determine model blending factors using the model self-confidence levels and results of the reasonableness checks;
• and
• a model blending module configured to determine an estimated virtual sensor value using the determined estimates from at least two of the plurality of engine model modules and the model blending factors.