CN-116305648-B - Valve coefficient optimization calculation method, device, equipment and storage medium

CN116305648BCN 116305648 BCN116305648 BCN 116305648BCN-116305648-B

Abstract

The invention provides a valve coefficient optimization calculation method, a device, equipment and a storage medium, wherein the method comprises the steps of obtaining initial valve coefficients of valves in a dust removal system, an optimization strategy and a dust removal pipe network simulation model corresponding to the dust removal system, wherein the optimization strategy at least comprises an objective function and constraint conditions; the method comprises the steps of calculating initial valve coefficients of all valves by utilizing an objective function and constraint conditions to obtain global optimized valve coefficients of all valves, inputting the global optimized valve coefficients into a dust removal pipe network simulation model to carry out simulation calculation to obtain a simulation result set of all the valves, constructing a machine learning model, training the machine learning model according to the simulation result set, and adjusting the valve opening of all the valves through the trained machine learning model. The invention optimizes the initial valve coefficient, improves the accuracy of simulation calculation and ensures the regulation and control effect of the dust removal system.

Inventors

WANG DABIN
WANG YUNPENG
XIE JIAN
HU JUNPENG
LIU ZHIXIANG
SHI CHUNYAN
HU KUN
CHEN CHENG
WANG JING
WU SHAN

Assignees

中冶赛迪信息技术(重庆)有限公司

Dates

Publication Date: 20260508
Application Date: 20230320

Claims (8)

1. A valve coefficient optimization calculation method, comprising: Acquiring initial valve coefficients of valves in a dust removal system, an optimization strategy and a dust removal pipe network simulation model corresponding to the dust removal system, wherein the optimization strategy at least comprises an objective function and constraint conditions, and the constraint conditions comprise an upper limit value of the initial valve coefficients and a lower limit value of the initial valve coefficients; before the initial valve coefficient of each valve in the dust removing system is obtained, a valve model is constructed according to the valve type of the dust removing system to obtain the valve coefficient of each valve, the valve coefficients are divided according to different opening intervals of the valve openings to obtain the valve coefficient to be optimized corresponding to the opening intervals; The method comprises the steps of combining different opening intervals of each valve with different opening intervals of other valves respectively to form an array matrix, wherein each array in the array matrix represents the combination of each valve in any opening interval, the combination of each array representation is not repeated, the initial valve coefficient is determined by the opening interval corresponding to each valve in the array, the accumulated value of the pressure error of each dust removing point corresponding to each array is calculated, and the initial valve coefficient corresponding to the smallest accumulated value is used as the global optimized valve coefficient; Inputting the global optimized valve coefficient into the dust removal pipe network simulation model for simulation calculation to obtain a simulation result set of each valve; And constructing a machine learning model, and training the machine learning model according to the simulation result set so as to adjust the valve opening of each valve through the trained machine learning model.
2. The valve coefficient optimization calculation method according to claim 1, further comprising, before said calculating said initial valve coefficient for each of said valves using said objective function and said constraint condition: obtaining simulation pressure and actual measurement pressure of each dust removing point under each working condition; performing difference operation on the measured pressure and the corresponding simulation pressure to obtain a pressure error of the dust removing point; and carrying out weight distribution on the pressure errors of the dust removing points, and determining the objective function.
3. The method for optimizing and calculating the valve coefficient according to claim 2, wherein said obtaining the simulated pressure of each of said dust removing points under each of the working conditions comprises: acquiring historical working data of the dust removal system; Generating a working condition set comprising a plurality of working conditions based on the historical working data; And carrying out hydraulic calculation on the initial valve coefficient of each valve according to the working condition set and the dust removal pipe network simulation model to obtain the simulation pressure of each dust removal point under each working condition, wherein the valves are in one-to-one correspondence with the dust removal points.
4. The valve coefficient optimization calculation method of claim 1, wherein inputting the global optimized valve coefficient of each valve to the dust removal pipe network simulation model for simulation calculation to obtain a simulation result set comprises: Traversing the valve opening of each valve in any combination of opening intervals; inputting the global optimized valve coefficient corresponding to the combination of the valve opening and the opening interval of each valve into the dust removal pipe network simulation model for hydraulic calculation to obtain a simulation optimization result of each valve, wherein the simulation optimization result at least comprises the simulation flow of each dust removal point and the simulation pressure after the optimization of each dust removal point; and aggregating the simulation flow of each dust removing point, the optimized simulation pressure of each dust removing point and the valve opening of each valve to obtain a simulation result set.
5. The valve coefficient optimization calculation method according to claim 4, wherein the constructing a machine learning model and training the machine learning model according to the simulation result set to adjust the valve opening of each valve by the trained machine learning model includes: Labeling the simulation result set to form a sample data set; Training the machine learning model based on the sample dataset; Obtaining the target flow of each dust removing point; inputting the target flow of each dust removing point to the trained machine learning model so as to output the target valve opening of each valve through the machine learning model; And adjusting the current valve opening of each valve to be the target valve opening.
6. A valve coefficient optimization computing device, comprising: The system comprises an acquisition module, a valve model, a valve coefficient dividing module and a optimizing module, wherein the acquisition module is used for acquiring initial valve coefficients of all valves in a dust removal system, an optimizing strategy and a dust removal pipe network simulation model corresponding to the dust removal system, the optimizing strategy at least comprises an objective function and a constraint condition, the constraint condition comprises an upper limit value of the initial valve coefficients and a lower limit value of the initial valve coefficients, before the initial valve coefficients of all the valves in the dust removal system are acquired, the valve model is constructed according to the valve types of the dust removal system to acquire the valve coefficients of all the valves, the valve coefficients are divided according to different opening intervals of the valve openings to acquire the valve coefficients to be optimized corresponding to the opening intervals, the valve coefficients to be optimized are initialized, and the initial valve coefficients are determined The optimization module is used for calculating the initial valve coefficient of each valve by utilizing the objective function and the constraint condition to obtain a global optimization valve coefficient of each valve, and comprises the steps of respectively combining different opening intervals of each valve with different opening intervals of other valves to form an array matrix, wherein each array in the array matrix represents the combination of each valve in any opening interval, the combination of each array representation is not repeated, the initial valve coefficient is determined by the opening interval corresponding to each valve in the array, the accumulated value of the pressure error of each dust removing point corresponding to each array is calculated, and the initial valve coefficient corresponding to the smallest accumulated value is used as the global optimization valve coefficient; the simulation module is used for inputting the global optimized valve coefficient into the dust removal pipe network simulation model to perform simulation calculation to obtain a simulation result set of each valve; And the training module is used for constructing a machine learning model, and training the machine learning model according to the simulation result set so as to adjust the valve opening of each valve through the trained machine learning model.
7. An electronic device, characterized in that the electronic device comprises; One or more processors; Storage means for storing one or more programs that, when executed by the one or more processors, cause the electronic device to implement the valve coefficient optimization calculation method of any one of claims 1-5.
8. A computer-readable storage medium having stored thereon a computer program for causing a computer to execute the valve coefficient optimization calculation method of any one of claims 1 to 5.

Description

Valve coefficient optimization calculation method, device, equipment and storage medium Technical Field The invention relates to the technical field of optimization calculation, in particular to a valve coefficient optimization calculation method, a device, equipment and a storage medium. Background The dust removing system is generally mainly composed of a dust remover and a fan and is widely applied to various industries, such as the steel industry and chemical enterprises. The dust removal pipe network is used as an important link of a dust removal system and mainly comprises a regulating valve and a dust removal pipeline, the design of the dust removal pipe network is complex, a plurality of dust removal points are connected, and each dust removal point is provided with a regulating valve for controlling the air quantity of the dust removal point. However, because the dust amounts to be treated are different at different dust removing points, the air quantity to be distributed is different, and the mutual influence exists between each dust removing point, the regulating valve is difficult to dynamically regulate according to the actual dust condition. If the air distribution of the dust removing points is too small, dust can be dissipated, and if the air distribution of the dust removing points is too large, useful materials can be sucked. In the related art, the valve coefficient of the valve in each regulating valve is mainly regulated, so that the fluid flow or pressure of a dust removing pipeline is regulated, the output of the opening degree of the valve is controlled, the reasonable purpose of air distribution of each dust removing point is achieved, simulation calculation is carried out on modeling of a dust removing pipe network, and the dynamic regulation and control of the valve are realized according to the simulation calculation result. However, under the conditions of production stage change and equipment operation aging, the valve coefficient can deviate from the design value, so that the simulation calculation result is separated from the actual working condition, the error between the measured value measured by the instrument and the calculated value corresponding to the instrument in the simulation model is overlarge, and the problems of low calculation accuracy of the simulation model and poor dynamic regulation effect of the dust removal system exist. In addition, when the dust removal point changes to the air quantity demand, the valve can not respond to the changed air quantity rapidly, the valve can not be regulated and controlled automatically, the correction is not timely, and the dust removal system is low in working efficiency and high in energy consumption. Disclosure of Invention In view of the above-mentioned drawbacks of the prior art, the present invention provides a valve coefficient optimization calculation method, apparatus, device and storage medium, so as to solve at least one of the above-mentioned technical problems. In a first aspect, the present invention provides a valve coefficient optimization calculation method, including: Acquiring initial valve coefficients of valves in a dust removal system, an optimization strategy and a dust removal pipe network simulation model corresponding to the dust removal system, wherein the optimization strategy at least comprises an objective function and constraint conditions; Calculating the initial valve coefficient of each valve by using the objective function and the constraint condition to obtain a global optimized valve coefficient of each valve; Inputting the global optimized valve coefficient into the dust removal pipe network simulation model for simulation calculation to obtain a simulation result set of each valve; And constructing a machine learning model, and training the machine learning model according to the simulation result set so as to adjust the valve opening of each valve through the trained machine learning model. In an embodiment of the present invention, before said calculating said initial valve coefficient of each of said valves using said objective function and said constraint, further comprises: obtaining simulation pressure and actual measurement pressure of each dust removing point under each working condition; performing difference operation on the measured pressure and the corresponding simulation pressure to obtain a pressure error of the dust removing point; and carrying out weight distribution on the pressure errors of the dust removing points, and determining the objective function. In an embodiment of the present invention, the obtaining the simulated pressure of each dust removing point under each working condition includes: Obtaining actual measurement pressure and simulation pressure of each dust removing point under each working condition; performing difference operation on the measured pressure and the corresponding simulation pressure to obtain a pressure error of the dust removing poin