Aimed to the difficult temperature measurement of scrap copper smelting process, this paper proposed a method of dynamic prediction method of furnace temperature based on weighted least squares support vector machine (WLS-SVM). In this method, the main input and output variables of the process squared error is given different weights to overcome the impact of the training sample anomalies, and use PSO for WLS-SVM parameters optimization, enhanced ability to adapt of dynamic model for the nonlinear time-varying characteristics, improved the prediction accuracy of the model. Finally, simulated through actual operating data of scrap copper smelting process, and verified the effectiveness of the method.
In order to eliminate the coupling between the loops for control in the system of scrap copper smelting, we
propose the methods to built the dynamic models of inverter-fan-furnace pressure loop and natural gas and combustion
air flow-air fuel ratio-furnace temperature loop based on data-driven, established the thought of multi-variable control
model with the amount of scrap copper, gas flow and speed of fan as input, temperature and pressure of furnace as output,
then use the method of PID neural network to decouple. Simulation results show that the control system be with the
features of fast response, small overshoot and without static error, and also multi-variable PID neural network adjusts the
connection weights based on the effect produced by the changes of object parameters, achieve the decoupling of the
coupling variables effectively; as with reference to the PID control requirements, making the whole system be simple
and standard.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.