Reverse osmosis membrane group pressure optimization control method based on double-RBF neural network
A technology of neural network and reverse osmosis membrane, applied in the field of pressure optimization control of reverse osmosis membrane group based on double RBF neural network, can solve the problems of slow pressure tracking speed, membrane pressure shock, large pressure fluctuation, etc., to improve response speed, The effect of reducing system energy consumption and reducing pressure fluctuations
Active Publication Date: 2021-07-13
QUFU NORMAL UNIV
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Due to the large number of membranes in the reverse osmosis membrane group, the parameters change in real time, and the optimal pressure of the system is difficult to achieve the optimum in real time; because the system is affected by the elastic interference of the membrane group and the temperature rise interference of the solenoid valve winding, the total pressure of the system is unstable during operation , causing reverse osmosis membrane damage
Although the traditional state feedback control method can realize optimal pressure tracking, the pressure tracking speed is slow, and because the state feedback control does not have anti-interference ability, the pressure fluctuates greatly when the working conditions change, and the stability of the steady-state operation is poor. The energy consumption of the system is high, and the membrane is subjected to severe pressure shocks
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 Construction
[0118]The invention provides a reverse osmosis membrane group pressure optimization control method based on double RBF neural network, including the acquisition of optimal pressure under variable working conditions, online adjustment of optimal pressure based on RBF neural network, and optimization of self-adaptive compensation using RBF neural network Pressure control. The acquisition of the optimal pressure takes the rated optimal pressure under variable seawater salinity as the initial value of the single-membrane optimal pressure, and constructs an optimization objective function with the goal of comprehensively optimizing the pressure of each section of the membrane, and adopts the Lagrangian multiplier method to obtain the reverse osmosis membrane The optimal pressure value of the membrane system in the first stage of the group; the online adjustment of the optimized pressure takes the reverse osmosis efficiency of the membrane group as the performance evaluation index, a...
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 reverse osmosis membrane module pressure optimization control method based on a double-RBF neural network, which comprises the following steps: constructing a first-section membrane system pressure dynamic model and other-section membrane steady-state models of a reverse osmosis membrane module, establishing a comprehensive optimal optimization objective function considering the membrane pressure of each section of the membrane module, and adjusting a pressure optimization value on line according to the actual thickness of a filter cake pollution layer. An RBF neural network is adopted to carry out online adjustment on a pressure optimization value by taking an actual membrane module reverse osmosis efficiency approaching the optimal reverse osmosis efficiency as a target, and unknown disturbance of a control suppression system is adaptively compensated by the RBF neural network on the basis of a state feedback controller; and the pressure optimization under the dual meanings of the pressure of each section of the membrane group and the reverse osmosis efficiency, the rapid tracking of the optimized pressure under variable working conditions and the stable operation of the reverse osmosis membrane group are realized.
Description
technical field [0001] The present invention proposes a reverse osmosis membrane group pressure optimization control method based on a double RBF neural network, which is a method for real-time pressure optimization and tracking control applied to multi-membrane reverse osmosis membrane group variable working conditions, and solves the problem of system parameter changes And the problem of inaccurate optimized pressure and unstable system operation caused by unknown interference belongs to the control field of reverse osmosis seawater desalination system. Background technique [0002] The multi-membrane reverse osmosis membrane group seawater desalination system is currently the mainstream seawater desalination system, which has the characteristics of many operating parameters, time-varying parameters, strong system coupling, many unknown disturbances, and frequent changes in working conditions. Therefore, on-line optimization of system pressure and reduction of pressure flu...
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 IPC IPC(8): G05B13/04
CPCG05B13/042Y02A20/131
Inventor 褚晓广王恬王铭涛孔英
Owner QUFU NORMAL UNIV