Neuro-Fuzzy Control of Continious Steel Strip Pickling

Abstract

The paper covers the methods and approaches of intelligent process control of pickling cold rolled steel strip with elements of comparator defect identification, based on the use of radialbasis (RBF) networks with Gaussian activation functions (GRB). The authors offer a criterion for assessing the quality of the process of etching the residual defects of the strip at the exit from the Ilyunin O.O., Gakhov R.P., Shamraev A.A. Neuro-fuzzy control of continious steel strip pickling // р а «На р а ». р я «И р а ».-. , № , 2016. 53 Ы INFORMATION TECHNOLOGIES Series ТЧsЭКХХКЭТШЧ. TСО СвЩОrsЮrПКМО ШП ЭСО ЩrШМОss ЩКrКЦОЭОrs' МСКЧРО ШП ЭСО ОЭМСТЧР sШХЮЭТШЧ КЧН MISO-model stabilization of process parameters in an optimal area for cost criteria are presented. The method of fuzzy color identification of defects on the steel strip by luminance component segmentation and positioning, and the approach to the construction of a fuzzy regulator of pressure in the nozzles of the hydraulic unit prior irrigation strip defects are offered. To study the process and the synthesis of the classifier and controller the authors used the data obtained in the course of the experiment in the production process.

Resource and Energy Saving Neural Network-Based Control Approach for Continuous Carbon Steel Pickling Process

“…The next parameter influencing the TP is the acid concentration C. The concentration of ferrous sulfate n• hydrates in solution (Cn) primarily is considered as a limiting factor of the solution life time until its complete draining (Cn ≤ 16%) or (Cn ≤ 6%), partially refreshing [25], but also accelerates the process for certain intervals of (T, C, Cn) parameters.…”

“…MW is the thermal energy consumption from the heat carrier (steam) . In general, the pickling rate function can be represented as a hypersurface of the model f (T, C, Cn) = tP for which a set of experimental data [25] is known for a set of values (Х; Y).…”