Estimating parameters in a proportional solenoid valve

Many control schemes, simple or sophisticated, utilize high performance electro-hydraulic components as an interface to mechanical hardware. Failure of an electro-hydraulic component in these applications may impact safety, maintenance schedules and/or productivity of the overall operation. A condition monitoring scheme that would measure the performance or health of critical electro-hydraulic components would be desirable in addressing the above mentioned concerns. Present research at the University of Saskatchewan involves the feasibility of acquiring data from a proportional solenoid valve on-line for the purpose of condition monitoring. Once data have been acquired (specifically spool displacement and spool differential pressure), an algorithm can be implemented to estimate the desired valve parameters. Some of the parameters that affect the performance of the main stage valve spool which may be used in a condition monitoring scheme include area orifice gradient, spring rates, spring pretensions and friction. This paper considers the use of individual 'neuron-like' structures to estimate each valve parameter. Each neuron trains to a specific valve parameter with its output being the estimated parameter. The individual neurons act and train independently; however, their outputs are integrated to compute the main spool differential pressure. This differential pressure calculation is compared to the measured value and the difference is used to train each neural structure. Experimental results are presented which demonstrate the accuracy and feasibility of the procedure.