Abstract
In pneumatic systems the supply and discharge of compressed air can be regulated by various shut-off and control valves. One of the modern decisions in this field is the usage of proportional solenoid valves. Such a valve can be represented like a equivalent throttle. Its effective area depends on the control signal and differential pressure. Pneumatic systems work processes modeling requires the development of mathematical model of this device work. Gas dynamic and electromagnetic processes in proportional valves are complex. An approximation based on an artificial neural network is proposed instead of an analytical description. Is is a three-layer feedforward neural network. Vector including the control signal and differential pressure is used to calculate the effective area. The neural network training was based on experimental data. The laboratory unit for the proportional valve investigation is described. Levenberg-Marquardt algorithm was selected for the training. Neural network model was used for plotting of the surface describing air flow through the proportional valve. Mathematical model works in the range of the differential pressure from 0 to 4 bar and in the range of the control signal from 0 to 100%.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
