A method and apparatus for detecting mechanical problems in machinery used in a process. A model of the process is developed using a modeling technique such as advanced pattern recognition and the model is used to generate predicted values for a predetermined number of the operating parameters of the process and vibration parameters of the machinery. Statistical process control methods are used to determine if the difference between the predicted and actual measured values for one or more of the parameters exceeds a configured statistical limit. A rule set is used to indicate an actual or probable fault in the machinery.