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.

Simple solenoid plunger type electromagnets are commonly used in devices such as switches, relays, and solenoid valves (to name but a few). In most cases these are on/off applications where the plunger is moved from one extreme position (when turned on) to another (when turned off). In this paper a scheme is presented to enable positioning of a linear actuator based on two simple solenoids, a flat faced electromagnet, and a microprocessor. The paper describes the configuration and performance of such a system which uses pulsed signals from a microprocessor to activate the solenoids and the electromagnet. The plungers connected by a shaft in a push pull arrangement move in an axial direction while an electromagnet orthogonal to the shaft latches it at a desired position. An algorithm to control the input pulses to the solenoids and the electromagnet is developed and experimental results using this control scheme are presented.

Axial piston type pumps are often exposed to severe operating conditions because of the duty cycle, the environment, or, in some situations, poor maintenance and even abuse. The detrimental effects on the pump and the hydraulic system as a result of these adverse conditions are often not known or predictable. In this study, four controlled severe operating conditions were imposed on four identical axial piston type pumps. They included 1) constant high load pressure and normal fluid temperature, 2) constant high load pressure and elevated fluid temperature, 3) cyclic load pressure and normal fluid temperature, and 4) cyclic load pressure and elevated fluid temperature. The tests were long-term; they were run continuously for up to 5000 hours. The pump wear was monitored in all cases using ferrography. In addition, the condition of the fluid was monitored and the circuit filters were examined periodically. The results of the findings are presented in this paper.