The Air Cushion Headbox Intelligent Decoupling Control System

Air-cushioned headbox, the key component of the high-speed paper-making machine, is the hinge of "delivering" and"forming". Since its naissance in 1940s, the air-cushioned headbox's design method, manufacture technology and control strategy has been highly valued by paper making industry. The air-cushioned headbox has become one of the fastest growing components in paper-making machines.In order to meet the urgent demands of the advanced air-cushioned headboxes with high performance, low cost and adaptation to sustainable development in China, this subject will develop an advanced control system for air-cushioned headboxes according to its internal mechanism.Analyzing the previous theoretical achievements about the air-cushioned headboxes, a double variable decoupled controller based on a BP network PID is presented with completely new idea and perspective in this paper. The controller improves the structure of traditional neural network PID and modifies the parameters: proportion ( k_p), integral ( k_i), and differential coefficient ( k_d) of a PID itself on line using the neural network's capability for non-linear description, in order to find the best PID parameters, which can reduce the influence between total pressure and liquid level of an air-cushioned headbox. The results of simulations using linear and nonlinear models indicate that the controller has the characteristics of simple realization and high control and practical value. However, this controller also has the disadvantages of having initial control overshoot and long control time, so an improved decoupling controller based on BP neural network PID with predictive compensation function is designed to solve these shortcomings.The controller based on BP neural network PID with predictive compensation function is designed to reduce the influence between the variables in multivariable, nonlinear and strong-coupling system. The results of simulations using the nonlinear model of air-cushioned headbox indicate that the control variables gain real-time compensation using predictive compensation controller, which can accelerate the decoupling control speed and reduce the initial control overshoot effectively. It can be regarded as an innovation and improvement for the traditional decoupling algorithm.The hardware equipment of the air-cushioned headbox control system mainly consists of a SIEMENS S7-200 PLC and an industrial computer IPC-610; the software system consists of the programming software (STEP 7-Micro/Win32) and the upper-computer monitoring software (KINGVIEW 6.5). Judged from the performance of the practical operation, the control scheme is reasonable and the control algorithm is available. The system performance is improved further and the anticipated goal has been achieved.