Moisture on-line prediction system of dryer based on neural networks

摘要

The research about on-line prediction system of moisture of feed is put forward to solve a variety of problems that restrict the controlling and prediction of moisture during feed processing. After analyzing of the process of feed, finding that dryingis the key process to moisture control of feed. Then moisture On-line prediction model of dryer based on BP neural networks was established, the upper hot air temperature, the lower hot air temperature, the upper conveyer belt speed, the lower conveyerbelt speed, and the inlet pellet moisture content, while taking the pellet moisture content after drying as output. The linear equation between prediction output and true value is above 0.92 which indicates that prediction model is available. It can be an operation guidance of the moisture control during drying process, and provide a new way of modeling to feed processing industry.