An Adaptive Decoupling Control Method for Improved fsrbfd
A technology of decoupling control and decoupling controller, which is applied in the decoupling field of coupling system, can solve the problems that the decoupling adjustment ability of the closed-loop control system cannot be effectively improved, the coupling effect cannot be completely eliminated, and there is no dynamic characteristic, etc., to achieve film production Quality assurance, strong anti-interference ability, precise decoupling effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0110] Such as Figure 6 As shown, an adaptive decoupling control method for improved FSRBFD described in this embodiment is specifically an adaptive decoupling control method for FSRBFD applied to a BOPP film thickness control system, but the decoupling control method does not Limited to the BOPP film thickness control system, it can also be applied to the decoupling control of other multi-channel coupling systems. The adaptive decoupling control method of FSRBFD described in this embodiment includes the following steps:
[0111] Step S1, system modeling: according to the relationship between the control quantity and the output quantity, determine the transfer function matrix model of the system.
[0112] (1) System modeling
[0113] Considering the three-channel film thickness control system, the thickness of each channel is taken as the measured value, and the temperature of the heating bolt is used as the control quantity to form a three-input and three-output control sys...
Embodiment 2
[0228] Embodiment 2, experimental comparative analysis
[0229] (1) System experiment environment
[0230] In order to verify the effect of the FSRBFD decoupling controller described in Embodiment 1 above, this embodiment uses the following four controllers to conduct experimental simulations for the film thickness control model under the MATLAB environment.
[0231] PID: PID controller;
[0232] SFFD: Feedforward-like decoupling controller;
[0233] RBFD: RBF neural network decoupling controller;
[0234] FSRBFD: Fast self-learning RBF decoupling controller.
[0235] The controlled object model in the experiment of this embodiment is the second-order discrete transfer function model described in formulas (2), (3) and (4). Based on the model setting v 1 =v 2 =v 3 =3, when the system is stable, select the following data at time=401:1400 as training samples, such as Figure 7 shown.
[0236] Set the initial clustering number of RBFD to 20 groups, and the clustering resu...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


