Search Results

In many areas, neural network technology has made a successful transition from theory to practical application, primarily due to the advances that have been made in computer technology and digital signal processing. Research at the University of Saskatchewan over the past few years has focused on applying neural network technology to fluid power systems. This paper will examine four projects that have been initiated by the authors and their graduate students which use neural networks for purposes of open loop pattern following, multiple input - multiple output control, indirect measurement of actuator displacement, and hydraulic component identification. A brief introduction to static and dynamic neural networks is given. Descriptions of the individual project objectives, the experimental implementation of neural networks to achieve these objectives, and some typical experimental results are considered.

Most fertilizer application systems are not capable of variable rate adjustments “on-the-fly”. To change the application rate, the farmer must dismount the tractor and change the gear ratio mechanically (i.e. via gears, chains, etc.). Air seeder manufacturers have come up with their own unique solutions to address this problem, usually involving electrohydraulics. At present there are older seeding units that perform adequately, but do not have the variable rate option. A retrofit is therefore very desirable for these units. In this paper, the feasibility of a simple hydraulic proportional valve and variable speed motor circuit is employed to replace the gears and chains. The unit is integrated with a microcontroller to provide compensation to the nonlinear properties of a proportional valve, and in turn provide a very accurate feedrate. In addition, direct user input from the cab of the tractor is possible, allowing on-the-go rate changes.

The rapid advances in computer technology over the past decade have provided the Fluid Power industry with a means of integrating modern control concepts with high performance hydraulic devices such as servo valves. One such concept, pulse width modulation (PWM), has been around for several decades, but it has been only recently that the full potential of the technique has been realized from an application's point of view. This paper shall consider the use of pulse width modulation techniques as a means of driving a two-stage flapper type servovalve and load. This work presents both analytical and experimental open loop responses of the valve and load under conditions in which variations from an operating point are substantial. The effects of signal filtration of the modulated input are traced through the valve and load by placing the modulation signal at various locations in the valve.

There has been considerable interest and activity in the area of application of the artificial neural network (ANN) to hydraulic systems. The pattern recognition capabilities of the ANN has led to an early investigation in areas where the neural networks could be trained using signals that were at least statistically similar to those signals which the trained ANN would be exposed during operation. The dynamic and encompassing nature of hydraulic system signals poses more of a challenge to ANN training and implementation than one of only pattern recognition. However, in the past decade, there has been considerable activity and progress in the application of ANN techniques for hydraulic systems control, identification and condition monitoring. This paper provides an overview of work in this area. The ANN has proven to be a valuable addition to the current existing techniques.