Conventional vacuum control in a milking system is accomplished by using a vacuum pump, sized for the maximum air flows into the milking system, running at a full speed. The difference between the pump capacity and th...Conventional vacuum control in a milking system is accomplished by using a vacuum pump, sized for the maximum air flows into the milking system, running at a full speed. The difference between the pump capacity and the necessary flow of air is compensated by allowing air to enter the system through a regulator. The solution presented in this paper uses a VFD （variable frequency driver） in order to drive the vacuum pump at a controlled speed, so that the air removed equals the air entering the milking system. The VFD technology is able to adjust the rate of air removal from the milking system, by changing the speed of the vacuum pump motor. The VFD is controlled by a computer using a virtual instrument in order to emulate a PID （proportion integration differentiation） regulator. The tests aimed to evaluate the vacuum regulator characteristics and vacuum stability. A statistical analysis of the experimental results was performed and it showed that there was a significant difference between the experimental results obtained for the two methods of vacuum regulation （with vacuum regulator and VFD controller respectively）. The experimental results proved that the used of the VFD controller led to a higher vacuum stability in terms of the error between the set vacuum value and the achieved values.展开更多
The cohort intelligence （CI） method has recently evolved as an optimization method based on artificial intelligence. We use the CI method for the first time to optimize the parameters of the fractional proportional-...The cohort intelligence （CI） method has recently evolved as an optimization method based on artificial intelligence. We use the CI method for the first time to optimize the parameters of the fractional proportional- integral-derivative （PID） controller. The performance of the CI method in designing the fractional PID controller was validated and compared with those of some other popular algorithms such as particle swarm optimization, the genetic algorithm, and the improved electromagnetic algorithm. The CI method yielded improved solutions in terms of the cost function, computing time, and function evaluations in comparison with the other three algorithms. In addition, the standard deviations of the CI method demonstrated the robustness of the proposed algorithm in solving control problems.展开更多
文摘Conventional vacuum control in a milking system is accomplished by using a vacuum pump, sized for the maximum air flows into the milking system, running at a full speed. The difference between the pump capacity and the necessary flow of air is compensated by allowing air to enter the system through a regulator. The solution presented in this paper uses a VFD （variable frequency driver） in order to drive the vacuum pump at a controlled speed, so that the air removed equals the air entering the milking system. The VFD technology is able to adjust the rate of air removal from the milking system, by changing the speed of the vacuum pump motor. The VFD is controlled by a computer using a virtual instrument in order to emulate a PID （proportion integration differentiation） regulator. The tests aimed to evaluate the vacuum regulator characteristics and vacuum stability. A statistical analysis of the experimental results was performed and it showed that there was a significant difference between the experimental results obtained for the two methods of vacuum regulation （with vacuum regulator and VFD controller respectively）. The experimental results proved that the used of the VFD controller led to a higher vacuum stability in terms of the error between the set vacuum value and the achieved values.
文摘The cohort intelligence （CI） method has recently evolved as an optimization method based on artificial intelligence. We use the CI method for the first time to optimize the parameters of the fractional proportional- integral-derivative （PID） controller. The performance of the CI method in designing the fractional PID controller was validated and compared with those of some other popular algorithms such as particle swarm optimization, the genetic algorithm, and the improved electromagnetic algorithm. The CI method yielded improved solutions in terms of the cost function, computing time, and function evaluations in comparison with the other three algorithms. In addition, the standard deviations of the CI method demonstrated the robustness of the proposed algorithm in solving control problems.
