Robust control method for asphalt mixing plant batching error

Abstract

The invention discloses a robust control method of burden error of pitch concrete stirring device, which comprises first building an input/output artificial neutral network model of three-layer structure, while the input layer has one neuron, the middle layer has five neurons and the output layer has one neuron, processing dynamic prediction and learning. The invention builds the non-linear model of flux and fly ash amount to be compared with a linear model of fixed parameters via continuous learning and adjustment, to adapt the change of external parameters, thereby effectively controlling the burden error of pitch mixture stirring device, reaching +-2% burden error as maximum and improving the burden accuracy of pitch mixture stirring device.

Description

technical field [0001] The invention belongs to a robust control method, in particular to a robust control method for batching errors of asphalt concrete mixing equipment. Background technique [0002] Asphalt mixture concrete mixing equipment is the key equipment for high-grade highway construction. The quality of the mixture plays a decisive role in the quality of the road surface, and the error of the ingredients plays an important role. According to literature reports, asphalt mixing plant batching due to changes in the amount of flying materials lead to over-tolerance accounted for more than 90%. At present, there are several methods of batching: (1) fixed value correction method, also known as fixed impulse correction method, this correction method is related to various factors such as the amount of material in the warehouse, the stability of the warehouse door action, and the composition change of the material. Related, the batching error is greater than 10%, which c...

AI Technical Summary

Problems solved by technology

However, this method considers the flow rate and the time for the material to completely fall into the scale after the door is closed to be a certain value, and a linear model is adopted. Since Q in the formula is the flow value collected in real time before the door is closed, it is the same as the time for the flying material to completely fall into the silo. The flow value is different in time series, so there is also a difference in value, and the time for the material to completely fall into the scale is also related to the flow rate, which is not a certain value, so the linear model of this method still brings a certain error

Images