CN-122019918-A - Real-time measurement method for particulate matter dust removal efficiency of wet dust collector

CN122019918ACN 122019918 ACN122019918 ACN 122019918ACN-122019918-A

Abstract

The invention discloses a real-time measurement method of dust removal efficiency of particles of a wet dust collector, which comprises the steps of selecting liquid level height, inlet airflow velocity, inlet air pressure and inlet dust concentration in the wet dust collector as input parameters, acquiring data sets in the dust removal process of particles with different particle diameters, constructing initial calculation models according to the particles with different particle diameters respectively through a data driving method, training the calculation models respectively through the data sets respectively for the particles with different particle diameters, obtaining respective dust removal efficiency calculation formulas of the particles with different particle diameters after training, selecting corresponding dust removal efficiency calculation formulas according to particle diameters of the particles in a required dust removal environment during real-time measurement, continuously acquiring corresponding input parameters in the dust removal process, substituting the corresponding input parameters into the formulas, and finally obtaining a real-time dust removal efficiency value. The method can ensure measurement accuracy and robustness under the premise of ensuring measurement instantaneity, and realize online continuous dust removal efficiency monitoring.

Inventors

WEI TAO
LI XIAOCHUAN
ZHU LINLING
Fan Simeng
ZHAO HAOSEN
ZHU RUHUA

Assignees

中国安全生产科学研究院

Dates

Publication Date: 20260512
Application Date: 20260116

Claims (7)

1. The real-time measurement method of the dust removal efficiency of the wet dust remover particles is characterized by comprising the following steps of: Firstly, determining input parameters, namely selecting the liquid level height, the inlet airflow velocity, the inlet air pressure and the inlet dust concentration in the wet dust collector to be measured as the input parameters; Step two, training data are obtained, namely dust removal efficiency tests are carried out on the wet dust collector in the environments of the particles with different particle sizes, and input parameters determined in the step one are collected in real time, so that data sets of corresponding relations between respective real-time input parameters and real-time dust removal efficiency in the dust removal process of the particles with different particle sizes are obtained; constructing a calculation model of the particles with different particle diameters, namely constructing an initial calculation model through a data driving method, respectively setting model complexity according to the particles with different particle diameters, and constructing a calculation model of the particles with different particle diameters; Step four, determining a dust removal efficiency calculation formula of the particles with different particle sizes, namely firstly selecting particles with a particle size range, acquiring a corresponding calculation model through the step three, acquiring a corresponding data set through the step two, dividing the data set into a training set and a test set, setting model training parameters, training an initial calculation model through the training set, verifying the initial calculation model through the test set after training, determining a final calculation model if the initial calculation model reaches the standard, acquiring a dust removal efficiency calculation formula of the particles with different particle sizes, which consists of input parameters, adjusting model training parameters and model complexity if the initial calculation formula does not reach the standard, and repeating the steps until the initial calculation formula is verified to reach the standard; measuring the particle size of the particles in the required dust removal environment in real time, selecting a corresponding dust removal efficiency calculation formula from the fourth step, placing the wet dust collector in the required dust removal environment for dust removal, continuously acquiring the real-time input parameters determined in the first step in the dust removal process, substituting the real-time input parameters into the selected dust removal efficiency calculation formula, and finally acquiring the real-time dust removal efficiency predicted value.
2. The method for measuring the particulate matter dedusting efficiency of the wet dust collector according to claim 1, wherein the step three is to select a polygenic genetic programming method to construct an initial calculation model.
3. The method for measuring the dust removal efficiency of the wet dust collector particles according to claim 2, wherein the particles with different particle diameters in the second step are PM 1 particle diameter particles, PM 2.5 particle diameter particles, PM 10 particle diameter particles and total suspended particles, respectively, and the set model complexity is reduced as the particle diameter of the particles is increased.
4. A method for measuring the dust removal efficiency of particulate matters in a wet dust collector according to claim 3, wherein the data set in the third step is composed of all data units of the collection time, and each data unit of the collection time is composed of the dust removal efficiency corresponding to the collection time and each real-time input parameter obtained at the current collection time.
5. The method for measuring the dust removal efficiency of the particulate matters of the wet dust collector in real time according to claim 4, wherein the data set in the fourth step is divided into a training set and a testing set, specifically, the number of data units at the time of collection in the data set is divided into the training set and the testing set according to a ratio of 8:2.
6. The method for measuring the dust removal efficiency of the particulate matters of the wet dust collector according to claim 5, wherein the dust removal efficiency calculation formula of each particulate matter with different particle diameters in the fourth step is specifically as follows: (1) (2) (3) (4) Wherein η PM1 is the dust removal efficiency of PM 1 particle size, η PM2.5 is the dust removal efficiency of PM 2.5 particle size, η PM10 is the dust removal efficiency of PM 10 particle size, η TSP is the dust removal efficiency of total suspended particles, h is the liquid level height, v is the inlet airflow velocity, p is the inlet air pressure, and c is the inlet dust concentration.
7. The method according to claim 5, wherein the model training parameters set in the fourth step include population size, algebra, tournament size, elite ratio, termination value, crossover rate, mutation rate, direct replication rate and function set.

Description

Real-time measurement method for particulate matter dust removal efficiency of wet dust collector Technical Field The invention belongs to the technical field of dust remover performance monitoring, and particularly relates to a real-time measurement method for dust removal efficiency of wet dust remover particles. Background The wet dust collector is widely used for controlling the emission of indoor particle pollution sources in industrial building workshops, and the real-time accurate measurement of dust collection efficiency is a key for guaranteeing indoor air quality and professional health of operators. Currently, the measurement method of dust removal efficiency mainly comprises two types of direct measurement and indirect measurement: Direct measurement methods such as filter weighing and on-line monitoring by sensors. The filter membrane weighing method is accurate, but needs offline sampling and drying treatment, takes long time, cannot meet the real-time monitoring requirement, and the sensor online monitoring (such as an optical principle sensor) is interfered by high moisture content and liquid drops at the outlet of the dust remover, so that the sensor needs to be frequently corrected to ensure the measurement precision and accuracy. Indirect measurement methods are based on high frequency pressure signal analysis (e.g. wavelet analysis, power spectral density estimation) or image processing techniques (e.g. high speed dynamic imaging). The method indirectly deduces the dust removal efficiency by identifying the gas-liquid two-phase flow pattern, but has the problems of more intermediate links, limited data extraction, large error and the like, and the method based on the optical principle is easily influenced by environmental illumination, is feasible in laboratory environment, but the industrial field application faces the challenges of economy, system complexity and robustness. In addition, the existing data driving method (such as traditional regression and neural network) has the problem of 'black box', the model is unexplained, and engineers are difficult to understand and trust, so that the method is not beneficial to on-site debugging and optimization. And the three-phase coupling mechanism of gas-liquid-dust in the wet dust collector is complex, strong coupling and multiple collinearity exist between input variables, and the existing model is difficult to establish an accurate and steady input-output mapping relation. Meanwhile, the measurement result is influenced by the factors of complicated gas-liquid two-phase flow in the interior, high moisture content in the outlet and the like, so that the dust remover is always in an inefficient and uncontrollable running state. Therefore, how to provide a new real-time measurement method, and also ensure the measurement accuracy and the robustness thereof on the premise of ensuring the measurement real-time performance, thereby realizing the online continuous monitoring, and being the direction of the research required by the invention. Disclosure of Invention Aiming at the problems existing in the prior art, the invention provides a real-time measurement method for the dust removal efficiency of the wet dust collector particles, which can ensure the measurement accuracy and the robustness thereof on the premise of ensuring the measurement instantaneity by selecting specific input parameters and establishing calculation formulas of particles with different particle diameters, thereby realizing the online continuous dust removal efficiency monitoring. In order to achieve the purpose, the technical scheme adopted by the invention is that the real-time measurement method for the dust removal efficiency of the particulate matters of the wet dust collector comprises the following steps: The method comprises the steps of firstly, determining input parameters, namely selecting the liquid level height, the inlet airflow velocity, the inlet air pressure and the inlet dust concentration in the wet dust collector to be measured as the input parameters, wherein the combination effectively avoids information redundancy among variables, and comprehensively represents the core state of the gas-liquid-dust coupling process by using the minimum sensing dimension. And step two, acquiring training data, namely testing the dust removal efficiency of the wet dust collector in the environments of the particles with different particle sizes, and collecting the input parameters determined in the step one in real time, so as to obtain data sets of corresponding relations between the respective real-time input parameters and the real-time dust removal efficiency in the dust removal process of the particles with different particle sizes. And thirdly, constructing calculation models of the particles with different particle diameters, namely constructing an initial calculation model through a data driving method, respectively setting model complexity according to the p