Three state-of-the-art methods for condition monitoring

This paper describes and compares three different state-of-the-art conditio n monitoring techniques: first principles, feature extraction, and neural n etworks. The focus of the paper is on the application of the techniques, no t on the underlying theory. Each technique is described briefly and is acco mpanied by a discussion on how it can be applied properly. The discussion i s finished with an enumeration of the advantages and disadvantages of the t echnique. Two condition monitoring cases, taken from the marine engineering field, are explored: condition monitoring of a diesel engine, using only t he torsional vibration of the crank shaft, and condition monitoring of a co mpression refrigeration plant, using many different sensors. Attention is a lso paid to the detection of sensor malfunction and to the user interface, The experience from the cases shows that all techniques are showing promisi ng results and can be used to provide the operator with information about t he monitored machinery on a higher level, The main problem remains the acqu isition of the required knowledge, either from measured data or from analys is.