A closed-loop modeling method for industrial process multi-order inertial closed-loop systems
A closed-loop system, industrial process technology, applied in general control systems, control/regulation systems, instruments, etc., can solve the problems of complex excitation signals and low accuracy of object models, and achieve the effect of improving control quality
Active Publication Date: 2022-03-15
ELECTRIC POWER RES INST OF STATE GRID ZHEJIANG ELECTRIC POWER COMAPNY +2
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] At present, the identification of the object model characteristics of the multi-order inertial closed-loop system usually adopts the conventional least squares identification algorithm, but the conventional least squares identification algorithm needs to add more complex excitation signals, and the accuracy of the identified object model is not high.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0023] For multi-order inertial closed-loop systems in industrial processes, such as figure 1 As shown, this embodiment proposes a closed-loop modeling method based on two DNN models. The training data are the input and output data of closed-loop system objects. One is a deep learning fully connected neural network, and the other is a deep learning random deactivation neural network. network. First, add forward and reverse step perturbations to the control variables of the closed-loop system, use a deep learning fully connected neural network based on various inertial filters, and obtain the first DNN model after training; then on the set value of the closed-loop system Add forward and reverse step perturbation, and use the output data of the first DNN model and the output data of the controlled object as the input of the deep learning random inactivation neural network for training. After training, the second DNN model is obtained, and the two DNN The models form a closed-lo...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a closed-loop modeling method of an industrial process multi-order inertia closed-loop system. The closed-loop modeling method of the present invention includes: first, adding forward and reverse step disturbances to the control quantity of the multi-order inertial closed-loop system, and obtaining the first DNN after training with a deep learning fully connected neural network based on various inertial filters model; then add forward and reverse step disturbances to the set value of the multi-order inertial closed-loop system, and use the output data of the first DNN model and the output data of the controlled object as the input of the deep learning random deactivation neural network for training , after training, the second DNN model is obtained, and the two DNN models form a closed-loop system model to effectively identify the characteristics of the controlled object model. The present invention is based on two DNN models, only needs to adopt relatively simple forward and reverse step excitation signals in the modeling process, can easily and accurately identify the model of the controlled object, and effectively improves the control quality of this type of closed-loop system.
Description
technical field [0001] The invention relates to an industrial process control system, in particular to a closed-loop modeling method for an industrial process multi-order inertia closed-loop system. Background technique [0002] A common type of controlled object in the industrial process is the multi-order inertial closed-loop system, which has the characteristics of large delay and large inertia. In order to obtain good control performance, it is often necessary to identify the characteristics of the object in a closed-loop manner. [0003] At present, the identification of the object model characteristics of the multi-order inertial closed-loop system usually adopts the conventional least squares identification algorithm, but the conventional least squares identification algorithm needs to add more complex excitation signals, and the accuracy of the identified object model is not high. Contents of the invention [0004] The technical problem to be solved by the present ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G05B13/04
CPCG05B13/042
Inventor 苏烨李泉尹峰丁俊宏吕洪坤孙坚栋蔡钧宇
Owner ELECTRIC POWER RES INST OF STATE GRID ZHEJIANG ELECTRIC POWER COMAPNY