CN112364562B - Flue gas environment-friendly island cooperative control method and system - Google Patents

Abstract

The invention discloses a smoke environmental protection island cooperative control method and system, which break through the independent operation data island mode of original environmental protection equipment, integrate boiler load, smoke working condition data and environmental protection island upstream and downstream system data, establish a denitration optimizing model, a dedusting optimizing model, a desulfurization optimizing model, a denitration cooperative model, a dedusting cooperative model and a desulfurization cooperative model, determine the optimization strategy of the smoke of the environmental protection island based on the denitration optimizing model, the dedusting optimizing model and the desulfurization optimizing model, and apply the denitration cooperative model, the dedusting cooperative model and the desulfurization cooperative model to realize the cooperative control of the whole environmental protection island, thereby fully playing the advantages of cooperative control of the environmental protection island equipment, effectively improving the comprehensive control operation level of the environmental protection island, optimizing the technical economy of the environmental protection island system to the greatest extent, and reducing the energy consumption, the material consumption and the treatment cost of the operation of the environmental protection island.

Description

Flue gas environment-friendly island cooperative control method and system

Technical Field

The invention relates to the technical field of flue gas treatment, in particular to a flue gas environment-friendly island cooperative control method and system.

Background

At present, pollutants of domestic coal-fired power plants are still in a single treatment stage due to various reasons such as technology, management and operation. Each pollutant treatment subsystem in the ultralow emission environment-friendly island system of the coal-fired unit only considers the treatment of a single pollutant, for example, the desulfurization treatment subsystem is responsible for removing sulfur dioxide, the electric dust removal treatment subsystem is responsible for removing dust, the denitration treatment subsystem is responsible for removing nitrogen oxides, and the like, and each subsystem is equivalent to a data island and has no data correlation with each other.

However, in practice, the subsystems are related and mutually influenced in operation, and one subsystem governs a certain index, and at the same time, the subsystem has some beneficial or adverse effect on the governance index of the adjacent or non-adjacent subsystem. Wherein, adverse effects may increase the difficulty of the affected subsystem in treating the corresponding pollutants, thereby increasing the treatment cost of the environmental protection island system; the synergistic energy-saving effect possibly brought by the beneficial effect is not fully utilized, so that the technical economy of the environment-friendly island system cannot be optimized to the greatest extent.

Disclosure of Invention

In view of the above, the invention discloses a smoke environmental protection island cooperative control method and system, which are used for realizing the cooperative control of the whole environmental protection island, thereby fully playing the advantages of cooperative treatment of environmental protection island equipment, effectively improving the comprehensive control operation level of the environmental protection island, optimizing the technical economy of the environmental protection island system to the greatest extent and reducing the energy consumption, material consumption and treatment cost of the operation of the environmental protection island.

A smoke environment-friendly island cooperative control method comprises the following steps:

Based on boiler load, flue gas working condition data and upstream and downstream system data of an environmental protection island, a denitration optimizing model, a dedusting optimizing model, a denitration cooperative model, a dedusting cooperative model and a desulfurization cooperative model are established, wherein the denitration optimizing model is used for predicting the optimized ammonia injection amount, the dedusting optimizing model is used for providing a corresponding energy-saving efficiency-improving strategy for electric dust removal equipment, the desulfurization optimizing model is used for obtaining an optimized slurry amount and circulating pump combination according to actual desulfurization working condition data and a sulfur dioxide target concentration value of a chimney discharge port, the denitration cooperative model is used for cooperatively controlling a denitration system and a dedusting system, the dedusting cooperative model is used for cooperatively controlling the dedusting system and an ash conveying system, and the desulfurization cooperative model is used for cooperatively controlling the desulfurization system and the dedusting system;

determining an optimization strategy of the environmental protection island flue gas based on the denitration optimization model, the dust removal optimization model and the desulfurization optimization model;

And carrying out cooperative control on the whole environment-friendly island based on the denitration cooperative model, the dedusting cooperative model and the desulfurization cooperative model.

Optionally, the process for establishing the denitration optimizing model includes:

Acquiring historical denitration working condition data of a denitration process;

applying a machine learning regression algorithm to the historical denitration working condition data, establishing nonlinear correlation models of ammonia injection quantity and nitrogen oxide concentration of a chimney discharge port under various working conditions, and marking the nonlinear correlation models as first nonlinear correlation models;

And obtaining the denitration optimization model through target conversion on the first nonlinear correlation model.

Optionally, the process for establishing the dust removal optimization model includes:

Acquiring boiler working condition data and dust removal electric field operation parameters;

Applying a machine learning classification algorithm to the boiler working condition data and the dedusting electric field operation parameters, and establishing nonlinear correlation models of dust concentration and dedusting power of a chimney discharge port of the dedusting electric field operation parameters under various working conditions;

and taking the nonlinear association model as a dust removal optimization model, and providing a corresponding energy-saving efficiency-improving strategy for electric dust removal equipment by adopting an intelligent preferred algorithm for the dust removal optimization model to realize dust removal optimization output.

Optionally, the process for establishing the desulfurization optimization model includes:

Acquiring historical desulfurization working condition data of a desulfurization process;

Applying a machine learning regression algorithm to the historical desulfurization working condition data, and establishing a nonlinear correlation model of slurry volume, slurry circulating pump combination and sulfur dioxide concentration of a chimney discharge port under various working conditions, and marking the nonlinear correlation model as a second nonlinear correlation model;

and obtaining the desulfurization optimization model through target conversion on the second nonlinear correlation model.

Optionally, the process for establishing the denitration cooperative model includes:

Acquiring historical data of denitration cooperative input factors;

applying a machine learning clustering algorithm to the historical data to construct a forward clustering distribution group model among the denitration cooperative input factors;

And taking the forward clustering distribution group model as a denitration cooperative model, screening irregular changes of one or more data in the denitration cooperative input factors, outputting process interference early warning, optimizing ammonia spraying amount through a denitration optimization model under the condition that the concentration of nitrogen oxides at the discharge outlet of a chimney reaches the standard, and enabling a dust removal system at the rear end to carry out corresponding dust removal treatment.

Optionally, the process for establishing the dedusting cooperation model includes:

Acquiring time sequence historical data of a dedusting cooperative input factor;

Applying a machine learning recommendation algorithm to the time sequence historical data, and combining an expert system to establish a nonlinear correlation model of the rapping force and the rapping period, and marking the nonlinear correlation model as a third nonlinear correlation model;

And taking the third nonlinear association model as a dedusting cooperation model, calculating the dedusting efficiency of the desulfurization system through slurry washing according to the difference value of the dust concentration of the dedusting outlet and the dust concentration of the discharge outlet based on the dedusting cooperation model, taking the dust concentration of the discharge outlet of the chimney as a control target, calculating the lowest dust concentration of the dedusting outlet, determining an association control strategy according to the operation parameters of the ash conveying system and the dedusting operation parameters, and carrying out cooperative control on the dedusting system and the ash conveying system.

Optionally, the process for establishing the desulfurization cooperative model includes:

acquiring historical data of desulfurization cooperative input factors;

applying a machine learning classification algorithm to the historical data, and establishing a nonlinear classification model of the dust concentration of the discharge outlet and the flushing of the demister under different dust concentrations of the dedusting outlet;

And taking the nonlinear classification model as a desulfurization cooperative model, starting a demister to wash according to the liquid level of the absorption tower under the condition that the dust concentration of a desulfurization inlet is high through the desulfurization cooperative model, reducing the dust concentration of a discharge outlet, and cooperatively controlling a desulfurization system and a dust removal system.

A smoke environmental protection island cooperative control system, comprising:

The system comprises a model building unit, a denitration optimizing model, a dedusting optimizing model, a desulfurization optimizing model, a denitration cooperative model, a dedusting cooperative model and a desulfurization cooperative model, wherein the denitration optimizing model is used for predicting the optimized ammonia spraying amount, the dedusting optimizing model is used for providing a corresponding energy-saving efficiency improving strategy for electric dust removing equipment, the desulfurization optimizing model is used for obtaining the optimized slurry amount and circulating pump combination according to the actual desulfurization working condition data and the sulfur dioxide target concentration value of a chimney discharge port, the denitration cooperative model is used for cooperatively controlling a denitration system and a dedusting system, the dedusting cooperative model is used for cooperatively controlling the dedusting system and an ash conveying system, and the desulfurization cooperative model is used for cooperatively controlling the desulfurization system and the dedusting system;

The strategy determining unit is used for determining an optimization strategy of the environmental protection island flue gas based on the denitration optimization model, the dust removal optimization model and the desulfurization optimization model;

and the cooperative control unit is used for cooperatively controlling the whole environment-friendly island based on the denitration cooperative model, the dedusting cooperative model and the desulfurization cooperative model.

Optionally, the method further comprises: a denitration optimizing model building unit;

the denitration optimizing model building unit is specifically used for:

Acquiring historical denitration working condition data of a denitration process;

applying a machine learning regression algorithm to the historical denitration working condition data, establishing nonlinear correlation models of ammonia injection quantity and nitrogen oxide concentration of a chimney discharge port under various working conditions, and marking the nonlinear correlation models as first nonlinear correlation models;

And obtaining the denitration optimization model through target conversion on the first nonlinear correlation model.

Optionally, the method further comprises: a dust removal optimization model building unit;

the dust removal optimization model building unit is specifically used for:

Acquiring boiler working condition data and dust removal electric field operation parameters;

Applying a machine learning classification algorithm to the boiler working condition data and the dedusting electric field operation parameters, and establishing nonlinear correlation models of dust concentration and dedusting power of a chimney discharge port of the dedusting electric field operation parameters under various working conditions;

and taking the nonlinear association model as a dust removal optimization model, and providing a corresponding energy-saving efficiency-improving strategy for electric dust removal equipment by adopting an intelligent preferred algorithm for the dust removal optimization model to realize dust removal optimization output.

Optionally, the method further comprises: a desulfurization optimization model building unit;

The desulfurization optimization model building unit is specifically configured to:

Acquiring historical desulfurization working condition data of a desulfurization process;

Applying a machine learning regression algorithm to the historical desulfurization working condition data, and establishing a nonlinear correlation model of slurry volume, slurry circulating pump combination and sulfur dioxide concentration of a chimney discharge port under various working conditions, and marking the nonlinear correlation model as a second nonlinear correlation model;

and obtaining the desulfurization optimization model through target conversion on the second nonlinear correlation model.

Optionally, the method further comprises: a denitration cooperative model building unit;

The denitration cooperative model building unit is specifically configured to:

Acquiring historical data of denitration cooperative input factors;

applying a machine learning clustering algorithm to the historical data to construct a forward clustering distribution group model among the denitration cooperative input factors;

And taking the forward clustering distribution group model as a denitration cooperative model, screening irregular changes of one or more data in the denitration cooperative input factors, outputting process interference early warning, optimizing ammonia spraying amount through a denitration optimization model under the condition that the concentration of nitrogen oxides at the discharge outlet of a chimney reaches the standard, and enabling a dust removal system at the rear end to carry out corresponding dust removal treatment.

Optionally, the method further comprises: a dust removal cooperative model building unit;

the dust removal cooperative model building unit is specifically used for:

Acquiring time sequence historical data of a dedusting cooperative input factor;

Applying a machine learning recommendation algorithm to the time sequence historical data, and combining an expert system to establish a nonlinear correlation model of the rapping force and the rapping period, and marking the nonlinear correlation model as a third nonlinear correlation model;

And taking the third nonlinear association model as a dedusting cooperation model, calculating the dedusting efficiency of the desulfurization system through slurry washing according to the difference value of the dust concentration of the dedusting outlet and the dust concentration of the discharge outlet based on the dedusting cooperation model, taking the dust concentration of the discharge outlet of the chimney as a control target, calculating the lowest dust concentration of the dedusting outlet, determining an association control strategy according to the operation parameters of the ash conveying system and the dedusting operation parameters, and carrying out cooperative control on the dedusting system and the ash conveying system.

Optionally, the method further comprises: a desulfurization cooperative model building unit;

the desulfurization cooperative model building unit is specifically configured to:

acquiring historical data of desulfurization cooperative input factors;

applying a machine learning classification algorithm to the historical data, and establishing a nonlinear classification model of the dust concentration of the discharge outlet and the flushing of the demister under different dust concentrations of the dedusting outlet;

And taking the nonlinear classification model as a desulfurization cooperative model, starting a demister to wash according to the liquid level of the absorption tower under the condition that the dust concentration of a desulfurization inlet is high through the desulfurization cooperative model, reducing the dust concentration of a discharge outlet, and cooperatively controlling a desulfurization system and a dust removal system.

According to the technical scheme, the invention discloses a smoke environmental protection island cooperative control method and system, which break through the independent operation data island mode of original environmental protection equipment, integrate boiler load, smoke working condition data and environmental protection island upstream and downstream system data, establish a denitration optimizing model, a dedusting optimizing model, a desulfurization optimizing model, a denitration cooperative model, a dedusting cooperative model and a desulfurization cooperative model, determine the optimizing strategy of the smoke of the environmental protection island based on the denitration optimizing model, the dedusting optimizing model and the desulfurization optimizing model, and apply the denitration cooperative model, the dedusting cooperative model and the desulfurization cooperative model to realize cooperative control of the whole environmental protection island, thereby fully playing the advantages of cooperative control of the environmental protection island equipment, effectively improving the comprehensive control operation level of the environmental protection island, optimizing the technical economy of the environmental protection island system to the greatest extent, and reducing the energy consumption, the material consumption and the control cost of the operation of the environmental protection island.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the disclosed drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a smoke environmental protection island cooperative control method disclosed by the embodiment of the invention;

FIG. 2 is a flowchart of a method for establishing a denitration optimization model, which is disclosed by the embodiment of the invention;

FIG. 3 is a flowchart of a method for establishing a dust removal optimization model according to an embodiment of the present invention;

FIG. 4 is a flowchart of a method for establishing a desulfurization optimization model according to an embodiment of the present invention;

FIG. 5 is a flowchart of a method for establishing a denitration cooperative model according to an embodiment of the present invention;

FIG. 6 is a flowchart of a method for establishing a dust removal cooperative model according to an embodiment of the present invention;

FIG. 7 is a flowchart of a method for establishing a desulfurization co-model according to an embodiment of the present invention;

Fig. 8 is a schematic diagram of an intelligent environment-friendly cloud platform for collaborative control of a smoke environment-friendly island according to an embodiment of the invention;

FIG. 9 is a schematic diagram of hardware connection of a smoke environmental protection island according to an embodiment of the present invention;

Fig. 10 is a schematic structural diagram of a smoke environmental protection island cooperative control system according to an embodiment of the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

The embodiment of the invention discloses a smoke environmental protection island cooperative control method and system, which break through the independent operation data island mode of original environmental protection equipment, integrate boiler load, smoke working condition data and environmental protection island upstream and downstream system data, establish a denitration optimizing model, a dedusting optimizing model, a desulfurization optimizing model, a denitration cooperative model, a dedusting cooperative model and a desulfurization cooperative model, determine the optimization strategy of the smoke of the environmental protection island based on the denitration optimizing model, the dedusting optimizing model and the desulfurization optimizing model, and apply the denitration cooperative model, the dedusting cooperative model and the desulfurization cooperative model to realize the cooperative control of the whole environmental protection island, thereby fully playing the advantages of the cooperative control of the environmental protection island equipment, effectively improving the comprehensive control operation level of the environmental protection island, optimizing the technical economy of the environmental protection island system to the greatest extent, and reducing the energy consumption, the material consumption and the treatment cost of the operation of the environmental protection island.

Referring to fig. 1, a flow chart of a smoke environmental protection island cooperative control method disclosed by an embodiment of the invention comprises the following steps:

Step S101, a denitration optimizing model, a dedusting optimizing model, a desulfurization optimizing model, a denitration cooperative model, a dedusting cooperative model and a desulfurization cooperative model are established based on boiler load, flue gas working condition data and upstream and downstream system data of an environmental protection island;

Step S102, determining an optimization strategy of the environmental protection island flue gas based on the denitration optimization model, the dust removal optimization model and the desulfurization optimization model;

the denitration optimizing model is used for predicting the optimized ammonia spraying amount, the dedusting optimizing model is used for providing a corresponding energy-saving efficiency improving strategy for electric dedusting equipment, and the desulfurization optimizing model is used for obtaining the optimized slurry amount and circulating pump combination according to actual desulfurization working condition data and a sulfur dioxide target concentration value of a chimney discharge outlet.

And step S103, carrying out cooperative control on the whole environment-friendly island based on the denitration cooperative model, the dedusting cooperative model and the desulfurization cooperative model.

The denitration cooperative model is used for cooperatively controlling the denitration system and the dust removal system, the dust removal cooperative model is used for cooperatively controlling the dust removal system and the ash conveying system, and the desulfurization cooperative model is used for cooperatively controlling the desulfurization system and the dust removal system.

In summary, the flue gas environmental protection island cooperative control method disclosed by the invention breaks through the data island mode of independent operation of original environmental protection equipment, integrates boiler load, flue gas working condition data and environmental protection island upstream and downstream system data, establishes a denitration optimization model, a dedusting optimization model, a desulfurization optimization model, a denitration cooperative model, a dedusting cooperative model and a desulfurization cooperative model, determines the optimization strategy of flue gas of the environmental protection island based on the denitration optimization model, the dedusting optimization model and the desulfurization optimization model, and realizes cooperative control of the whole environmental protection island by applying the denitration cooperative model, the dedusting cooperative model and the desulfurization cooperative model, thereby fully playing the advantage of cooperative control of the environmental protection island equipment, effectively improving the comprehensive control operation level of the environmental protection island, optimizing the technical economy of the environmental protection island system to the greatest extent, and reducing the energy consumption, the material consumption and the treatment cost of the operation of the environmental protection island.

In order to further optimize the above embodiment, referring to fig. 2, the embodiment of the present invention discloses a method for establishing a denitration optimization model, which includes the steps of:

step S201, acquiring historical denitration working condition data of a denitration process;

Wherein, the historical denitration working condition data may include: boiler load (x ₁), denitration inlet operating mode flue gas amount (x ₂), denitration inlet oxygen amount (x ₃), denitration inlet temperature (x ₄), denitration inlet nitrogen oxide concentration (x ₅), denitration outlet nitrogen oxide concentration (x ₆), ammonia injection amount (u ₁) and ammonia escape amount (x ₇) are obtained.

Step S202, applying a machine learning regression algorithm to the historical denitration working condition data, and establishing a nonlinear correlation model of ammonia injection quantity (u ₁) and the concentration (y ₁) of nitrogen oxides at a chimney discharge port under various working conditions, wherein the nonlinear correlation model is recorded as a first nonlinear correlation model;

and step 203, obtaining a denitration optimization model from the first nonlinear correlation model through target conversion.

The denitration optimization model can predict the optimized ammonia injection amount according to actual denitration working condition data and a target concentration value of the nitrogen oxides at the discharge port of the chimney, and can obtain denitration optimization output.

The mathematical equation of the denitration optimization model is as follows:

f₁(x₁,x₂,x₃,x₄,x₅,x₆,x₇,y₁)＝u₁.

f ₁ is a correlation function of the variables, and a specific expression cannot be obtained in view of complex working conditions, but the correlation function can be approximated by a series of methods, such as training an AI model which can be comparable to the effect of f ₁ by using a data driving mode.

According to the invention, the optimal ammonia spraying amount is predicted, so that the ammonia escape rate is reduced as much as possible under the condition of ensuring the environment protection to reach the standard.

Specifically, in practical application, the working condition characteristics required by the input of the denitration optimizing model are determined by preprocessing and characteristic engineering analysis on the historical denitration working condition data, and XGboost in integrated learning is selected as a training model through comprehensive evaluation when model training is performed, wherein the expression of the training model is as follows:

Where K is the number of trees, f (x) is a function in the function space, f _k(x_i) is the prediction of the ith sample under the kth tree, x _i represents the ith sample, To represent the predicted result of sample x _i, F represents all possible trees.

Where F is the total regression tree set, F is one of the regression trees, q (x) represents the division of the sample x onto a leaf node, w is the fraction of the leaf node, R ^T is the real space, R ^d is the range of values of the tree, and w _q(x) represents the prediction value of the regression tree on the sample.

The objective function is:

In the method, in the process of the invention, For the training error of sample x _i, Ω (f _k) represents the regularization term of the kth tree, T is the number of leaf nodes, and i/w is the modulus of the leaf node vector; and gamma and lambda are model hyper-parameters, wherein gamma controls the number of leaf nodes, and lambda is an L2 regularization coefficient.

And solving the objective function by selecting a proper optimization algorithm. And then, continuously iterating the optimization model to approach an ideal effect by repeatedly solving the optimization objective function by utilizing the trained model according to actual denitration working condition data and a target concentration value of the nitrogen oxide at the discharge outlet of the chimney, and predicting the optimal ammonia injection amount (based on historical behavior analysis, the emission standard and the minimum ammonia escape amount are met).

In order to further optimize the above embodiments, referring to fig. 3, a flowchart of a method for establishing a dust removal optimization model according to an embodiment of the present invention is disclosed, where the method includes the steps of:

step S301, acquiring boiler working condition data and dedusting electric field operation parameters;

Wherein, boiler operating mode data includes: boiler load (x ₁), dust removal inlet operating mode flue gas volume (g ₁), dust removal inlet oxygen volume (g ₂), dust removal inlet temperature (g ₃), and the like.

The dust-removing electric field operation parameter is represented by (s ₁,s₂,…,s_n).

Step S302, applying a machine learning classification algorithm to the boiler working condition data and the dedusting electric field operation parameters, and establishing a nonlinear correlation model of the dedusting electric field operation parameters under various working conditions, namely the dust concentration (y ₂) of a chimney discharge outlet and the dedusting power (y ₃);

the mathematical equation of the nonlinear correlation model is as follows:

g₁(x₁,g₁,g₂,g₃,s₁,s₂,…,s_n)＝y₂、y₃;

and step 303, taking the nonlinear association model as a dust removal optimization model, and providing a corresponding energy-saving efficiency improvement strategy for electric dust removal equipment by adopting an intelligent preferred algorithm to the dust removal optimization model so as to realize dust removal optimization output.

The energy-saving efficiency-improving strategy provided by the invention is to reduce the power consumption of the dust removing equipment as much as possible under the condition of ensuring that the environment protection reaches the standard.

In order to further optimize the above embodiment, referring to fig. 4, a flowchart of a method for establishing a desulfurization optimization model according to an embodiment of the present invention is disclosed, where the method includes the steps of:

step S401, obtaining historical desulfurization working condition data of a desulfurization process;

wherein, the historical desulfurization condition data may include: boiler load (x ₁), desulfurization inlet operating mode flue gas volume (h ₂), desulfurization inlet oxygen volume (h ₃), desulfurization inlet temperature (h ₄), slurry circulation pump combination (t ₁,t₂,…,t_n), demister flushing (u ₃), absorber liquid level (a ₂) and absorber inlet sulfur dioxide (h ₆).

Step S402, applying a machine learning regression algorithm to the historical desulfurization working condition data, and establishing a nonlinear correlation model of the slurry amount (u ₂), the slurry circulating pump combination (t ₁,t₂,…,t_n) and the sulfur dioxide concentration (y ₄) of a chimney discharge port under various working conditions, wherein the nonlinear correlation model is recorded as a second nonlinear correlation model;

And S403, obtaining a desulfurization optimization model for the second nonlinear correlation model through target conversion.

The desulfurization optimization model can obtain the combination of the optimized slurry amount and the circulating pump according to actual desulfurization working condition data and a target concentration value of sulfur dioxide at a chimney discharge port, and then the desulfurization optimization output is obtained.

The mathematical equation of the desulfurization optimization model is as follows:

q₁(x₁,h₂,h₃,h₄,h₆,y₄,u₃,a₂)＝u₂、t₁、t₂、…、t_n.

according to the invention, by obtaining the combination of the optimized slurry amount and the circulating pump, the material consumption and the electricity consumption of the slurry amount are saved as much as possible under the condition of ensuring the environment protection to reach the standard.

In order to further optimize the above embodiment, referring to fig. 5, a flowchart of a method for establishing a denitration cooperative model is disclosed in the embodiment of the present invention, and the method includes the steps of:

step S501, acquiring historical data of denitration cooperative input factors;

In the denitration process, excessive ammonia escapes to enable dust collection wires to accumulate dust, so that the electric field capacity is inhibited, and finally the dust collection efficiency is reduced. Based on the correlation characteristic, the invention takes the historical data of denitration inlet nitrogen oxide concentration (x ₅), denitration outlet nitrogen oxide concentration (x ₆), ammonia injection amount (u ₁), ammonia escape amount (x ₇), chimney discharge outlet nitrogen oxide concentration (y ₁) and dedusting operation parameters (s ₁,s₂,…,s_n) in the conventional operation process as denitration cooperative input factors.

Step S502, applying a machine learning clustering algorithm to the historical data to construct a forward clustering distribution group model among the denitration cooperative input factors;

The mathematical equation of the forward clustering distribution group model is as follows:

f₂(x₅,x₆,x₇,y₁,s₁,s₂,…,s_n，)＝0/1；

and S503, taking the forward clustering distribution group model as a denitration cooperative model, screening irregular changes of one or more data in the denitration cooperative input factors, outputting process interference early warning, optimizing ammonia spraying amount through a denitration optimization model under the condition that the concentration of nitrogen oxides at a discharge port of a chimney reaches the standard, and enabling a dust removal system at the rear end to carry out corresponding dust removal treatment.

The denitration cooperative model is used for cooperatively controlling a denitration system and a dust removal system.

According to the invention, when one or more data in the denitration cooperative input factors are subjected to irregular change, the denitration cooperative model can rapidly screen out a process interference phenomenon, and under the condition that the concentration of nitrogen oxides at the discharge port of a chimney reaches the standard, the ammonia spraying amount is optimized through the denitration optimization model, so that the denitration and dedusting cooperative control purpose is achieved, and the dedusting system at the rear end is informed to carry out corresponding dedusting treatment.

In order to further optimize the above embodiment, referring to fig. 6, a flowchart of a method for establishing a dust removal cooperative model according to an embodiment of the present invention is disclosed, where the method includes the steps of:

step S601, acquiring time sequence historical data of a dedusting collaborative input factor;

Wherein the time sequence history data includes: the method comprises the steps of dedusting operation parameters (s ₁,s₂,…,s_n), dedusting outlet dust concentration (c ₁), chimney discharge outlet dust concentration (y ₂), ash conveying system operation parameters (v ₁,v₂..,v_n) and ammonia escape quantity (m ₁) output by a denitration cooperative model.

Step S602, applying a machine learning recommendation algorithm to the time sequence historical data, and combining an expert system to establish a nonlinear correlation model of the rapping force (y ₅) and the rapping period (y ₆), and recording the nonlinear correlation model as a third nonlinear correlation model;

the expert system is an intelligent computer program system, which contains a large amount of knowledge and experience of expert level in a certain field, and can use the knowledge of human expert and a method for solving the problem to process the problem in the field.

The invention applies a machine learning recommendation algorithm to the time sequence historical data, and can optimize dedusting vibration output parameters including vibration force (y ₅) and vibration period (y ₆) by combining an expert system, so as to reduce the influence of ammonia escape on the dedusting process.

The mathematical equation for the non-linear correlation model of the rapping force (y ₅) and the rapping period (y ₆) is as follows:

g₂(s₁,s₂,…,s_n,v₁,v₂,..,v_n,m₁,c₁,y₂)＝y₅、y₆.

Step S603, taking the third nonlinear association model as a dedusting cooperation model, based on the dedusting cooperation model, calculating the dedusting efficiency of the desulfurization system through slurry washing according to the difference value of the dedusting outlet dust concentration (c ₁) and the discharge outlet dust concentration (y ₂), taking the dust concentration of the chimney discharge outlet as a control target, calculating the lowest dust concentration of the dedusting outlet, determining an association control strategy according to the operation parameters of the ash conveying system and the dedusting operation parameters, and performing cooperative control on the dedusting system and the ash conveying system.

According to the invention, the dust removal efficiency of the desulfurization system through slurry washing is calculated through the difference value of the dust concentration of the dust removal outlet and the dust concentration of the discharge outlet, the dust removal efficiency of the desulfurization system is quantitatively analyzed, the discharge outlet of the chimney is taken as a control target, the minimum concentration to be achieved by the dust removal outlet is calculated, the dust removal output power is properly reduced, and the energy-saving effect is achieved. And according to the deep excavation of the operation parameters of the ash conveying system and the dedusting operation parameters, outputting a related control strategy, reducing the influence of the faults of the ash conveying system on the short circuit of the electric dedusting field, and completing the cooperative control of the dedusting system and the ash conveying system.

In order to further optimize the above embodiment, referring to fig. 7, a flowchart of a method for establishing a desulfurization cooperative model according to an embodiment of the present invention is disclosed, where the method includes:

step S701, obtaining historical data of desulfurization cooperative input factors;

dust at the dust removal outlet interferes with the quality of the desulfurization slurry, and excessive dust can cause slurry poisoning, ultimately reducing desulfurization efficiency.

Wherein the desulfurization co-input factor comprises: dust removal outlet dust concentration (c ₁), vent dust concentration (y ₂), vent sulfur dioxide concentration (y ₄), slurry circulation pump combination (t ₁,t₂,…,t_n), mist eliminator rinse (u ₃) and absorber liquid level (a ₂).

Step S702, applying a machine learning classification algorithm to the historical data, and establishing a nonlinear classification model of discharge outlet dust concentration (y ₂) and demister flushing (u ₃) under different dust concentration of a dust removing outlet;

The mathematical equation for the nonlinear classification model of the discharge outlet dust concentration (y ₂) and demister flushing (u ₃) is as follows:

p₂(c₁,y₂,y₄,t₁,t₂,…,t_n)＝u₃；

Wherein c ₁ is dust concentration of a dust removal outlet, y ₂ is dust concentration of a chimney discharge outlet, y ₄ is sulfur dioxide concentration of the chimney discharge outlet, and (t ₁,t₂,…,t_n) is a slurry circulating pump combination.

And step 703, taking the nonlinear classification model as a desulfurization cooperative model, and starting a demister to wash according to the liquid level of the absorption tower under the condition that the dust concentration of a desulfurization inlet is high through the desulfurization cooperative model, so as to reduce the dust concentration of a discharge outlet and cooperatively control a desulfurization system and a dust removal system.

According to the invention, under the condition of high dust concentration at the desulfurization inlet, the demister is started to flush according to the liquid level of the absorption tower through the desulfurization cooperative model, so that the dust concentration at the discharge port is reduced, the desulfurization efficiency is improved, and the cooperative control of the desulfurization system and the dust removal system is realized.

It should be noted that, the association relationship among the denitration optimizing model, the dedusting optimizing model, the desulfurization optimizing model, the denitration cooperative model, the dedusting cooperative model and the desulfurization cooperative model can be referred to the schematic diagram of the intelligent environment-friendly cloud platform during the cooperative control of the flue gas environment-friendly island shown in fig. 8.

It should be noted that, when implementing the smoke environmental protection island cooperative control, the hardware configuration adopted in the present invention is shown in fig. 9, where the hardware configuration includes: the intelligent environment-friendly cloud platform, the front-end data acquisition machine 1, the front-end data acquisition machine 2, a power plant site environment-friendly island monitoring center, a one-way net gate, an electrostatic dust collection IPC (intelligent control system), an SIS (factory level monitoring information system) PI database, a DCS (distributed control system) and a GPS (Global Positioning System ) network time server.

The intelligent environment-friendly cloud platform is connected with the front-end data acquisition machine 1, the front-end data acquisition machine 2 and the power plant field environment-friendly island monitoring center through a private network.

The front-end data acquisition machine 1 is used for acquiring electric dust removal data.

The front-end data acquisition machine 2 is used for acquiring boiler working condition data and desulfurization, denitration and ash conveying system data through an SIS system;

the unidirectional gatekeeper is a network security device, and data only allows reading and does not allow writing;

The intelligent environment-friendly cloud platform is used for outputting an optimization strategy and transmitting the optimization strategy to a power plant field environment-friendly island monitoring center.

The power plant field environmental protection island monitoring center is used for monitoring the operating parameters of the environmental protection island and issuing the parameters of the optimization strategy.

The GPS clock synchronizes electrostatic dust collection IPC and SIS PI database time unification, so that time clusters of data are aligned.

Corresponding to the embodiment of the method, the invention also discloses a smoke environment-friendly island cooperative control system.

Referring to fig. 10, a schematic structural diagram of a smoke environmental protection island cooperative control system disclosed in an embodiment of the present invention includes:

The model building unit 801 is configured to build a denitration optimization model, a dedusting optimization model, a desulfurization optimization model, a denitration cooperative model, a dedusting cooperative model and a desulfurization cooperative model based on boiler load, flue gas working condition data and upstream and downstream system data of the environmental protection island;

the denitration optimizing model is used for predicting the optimized ammonia spraying amount, the dedusting optimizing model is used for providing a corresponding energy-saving efficiency improving strategy for electric dust removing equipment, the desulfurization optimizing model is used for obtaining the combination of optimized slurry amount and a circulating pump according to actual desulfurization working condition data and a sulfur dioxide target concentration value of a chimney discharge outlet, the denitration cooperative model is used for cooperatively controlling a denitration system and a dedusting system, the dedusting cooperative model is used for cooperatively controlling the dedusting system and an ash conveying system, and the desulfurization cooperative model is used for cooperatively controlling the desulfurization system and the dedusting system.

A policy determining unit 802, configured to determine an optimization policy of the environmental protection island flue gas based on the denitration optimization model, the dust removal optimization model, and the desulfurization optimization model;

and a cooperative control unit 803, configured to cooperatively control the entire environmental protection island based on the denitration cooperative model, the dedusting cooperative model, and the desulfurization cooperative model.

In summary, the flue gas environmental protection island cooperative control system disclosed by the invention breaks through the data island mode of independent operation of original environmental protection equipment, integrates boiler load, flue gas working condition data and environmental protection island upstream and downstream system data, establishes a denitration optimization model, a dedusting optimization model, a desulfurization optimization model, a denitration cooperative model, a dedusting cooperative model and a desulfurization cooperative model, determines the optimization strategy of flue gas of the environmental protection island based on the denitration optimization model, the dedusting optimization model and the desulfurization optimization model, and realizes cooperative control of the whole environmental protection island by applying the denitration cooperative model, the dedusting cooperative model and the desulfurization cooperative model, thereby fully playing the advantage of cooperative control of the environmental protection island equipment, effectively improving the comprehensive control operation level of the environmental protection island, optimizing the technical economy of the environmental protection island system to the greatest extent, and reducing the energy consumption, the material consumption and the treatment cost of the operation of the environmental protection island.

To further optimize the above embodiment, the flue gas environmental protection island cooperative control system may further include: a denitration optimizing model building unit;

the denitration optimizing model building unit is specifically used for:

Acquiring historical denitration working condition data of a denitration process;

applying a machine learning regression algorithm to the historical denitration working condition data, establishing nonlinear correlation models of ammonia injection quantity and nitrogen oxide concentration of a chimney discharge port under various working conditions, and marking the nonlinear correlation models as first nonlinear correlation models;

And obtaining the denitration optimization model through target conversion on the first nonlinear correlation model.

The specific working principle of the denitration optimizing model building unit is shown in the corresponding part of the embodiment shown in fig. 2, and will not be described herein.

To further optimize the above embodiment, the flue gas environmental protection island cooperative control system may further include: a dust removal optimization model building unit;

the dust removal optimization model building unit is specifically used for:

Acquiring boiler working condition data and dust removal electric field operation parameters;

Applying a machine learning classification algorithm to the boiler working condition data and the dedusting electric field operation parameters, and establishing nonlinear correlation models of dust concentration and dedusting power of a chimney discharge port of the dedusting electric field operation parameters under various working conditions;

and taking the nonlinear association model as a dust removal optimization model, and providing a corresponding energy-saving efficiency-improving strategy for electric dust removal equipment by adopting an intelligent preferred algorithm for the dust removal optimization model to realize dust removal optimization output.

The specific working principle of the dust removal optimization model building unit is shown in the corresponding parts of the embodiment shown in fig. 3, and will not be described herein.

To further optimize the above embodiment, the flue gas environmental protection island cooperative control system may further include: a desulfurization optimization model building unit;

The desulfurization optimization model building unit is specifically configured to:

Acquiring historical desulfurization working condition data of a desulfurization process;

Applying a machine learning regression algorithm to the historical desulfurization working condition data, and establishing a nonlinear correlation model of slurry volume, slurry circulating pump combination and sulfur dioxide concentration of a chimney discharge port under various working conditions, and marking the nonlinear correlation model as a second nonlinear correlation model;

and obtaining the desulfurization optimization model through target conversion on the second nonlinear correlation model.

The specific working principle of the desulfurization optimization model building unit is shown in the corresponding portion of the embodiment shown in fig. 4, and will not be described herein.

To further optimize the above embodiment, the flue gas environmental protection island cooperative control system may further include: a denitration cooperative model building unit;

The denitration cooperative model building unit is specifically configured to:

Acquiring historical data of denitration cooperative input factors;

applying a machine learning clustering algorithm to the historical data to construct a forward clustering distribution group model among the denitration cooperative input factors;

And taking the forward clustering distribution group model as a denitration cooperative model, screening irregular changes of one or more data in the denitration cooperative input factors, outputting process interference early warning, optimizing ammonia spraying amount through a denitration optimization model under the condition that the concentration of nitrogen oxides at the discharge outlet of a chimney reaches the standard, and enabling a dust removal system at the rear end to carry out corresponding dust removal treatment.

The specific working principle of the denitration cooperative model building unit is referred to the corresponding parts of the embodiment shown in fig. 5, and will not be described herein.

To further optimize the above embodiment, the flue gas environmental protection island cooperative control system may further include: a dust removal cooperative model building unit;

the dust removal cooperative model building unit is specifically used for:

Acquiring time sequence historical data of a dedusting cooperative input factor;

Applying a machine learning recommendation algorithm to the time sequence historical data, and combining an expert system to establish a nonlinear correlation model of the rapping force and the rapping period, and marking the nonlinear correlation model as a third nonlinear correlation model;

And taking the third nonlinear association model as a dedusting cooperation model, calculating the dedusting efficiency of the desulfurization system through slurry washing according to the difference value of the dust concentration of the dedusting outlet and the dust concentration of the discharge outlet based on the dedusting cooperation model, taking the dust concentration of the discharge outlet of the chimney as a control target, calculating the lowest dust concentration of the dedusting outlet, determining an association control strategy according to the operation parameters of the ash conveying system and the dedusting operation parameters, and carrying out cooperative control on the dedusting system and the ash conveying system.

The specific working principle of the dust removal cooperative model building unit is shown in the corresponding parts of the embodiment shown in fig. 6, and will not be described herein.

To further optimize the above embodiment, the flue gas environmental protection island cooperative control system may further include: a desulfurization cooperative model building unit;

the desulfurization cooperative model building unit is specifically configured to:

acquiring historical data of desulfurization cooperative input factors;

applying a machine learning classification algorithm to the historical data, and establishing a nonlinear classification model of the dust concentration of the discharge outlet and the flushing of the demister under different dust concentrations of the dedusting outlet;

And taking the nonlinear classification model as a desulfurization cooperative model, starting a demister to wash according to the liquid level of the absorption tower under the condition that the dust concentration of a desulfurization inlet is high through the desulfurization cooperative model, reducing the dust concentration of a discharge outlet, and cooperatively controlling a desulfurization system and a dust removal system.

The specific working principle of the desulfurization co-model building unit is shown in the corresponding portion of the embodiment shown in fig. 7, and will not be described herein.

Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (8)

1. The smoke environment-friendly island cooperative control method is characterized by comprising the following steps of:

Based on boiler load, flue gas working condition data and upstream and downstream system data of an environmental protection island, a denitration optimizing model, a dedusting optimizing model, a denitration cooperative model, a dedusting cooperative model and a desulfurization cooperative model are established, wherein the denitration optimizing model is used for predicting the optimized ammonia injection amount, the dedusting optimizing model is used for providing a corresponding energy-saving efficiency-improving strategy for electric dust removal equipment, the desulfurization optimizing model is used for obtaining an optimized slurry amount and circulating pump combination according to actual desulfurization working condition data and a sulfur dioxide target concentration value of a chimney discharge port, the denitration cooperative model is used for cooperatively controlling a denitration system and a dedusting system, the dedusting cooperative model is used for cooperatively controlling the dedusting system and an ash conveying system, and the desulfurization cooperative model is used for cooperatively controlling the desulfurization system and the dedusting system;

determining an optimization strategy of the environmental protection island flue gas based on the denitration optimization model, the dust removal optimization model and the desulfurization optimization model;

based on the denitration cooperative model, the dedusting cooperative model and the desulfurization cooperative model, the whole environmental protection island is cooperatively controlled;

The denitration cooperative model establishing process comprises the following steps:

acquiring historical data of denitration cooperative input factors, wherein the historical data of the denitration cooperative input factors comprise denitration inlet nitrogen oxide concentration, denitration outlet nitrogen oxide concentration, ammonia injection amount, ammonia escape amount, chimney discharge outlet nitrogen oxide concentration and dedusting operation parameters;

applying a machine learning clustering algorithm to the historical data to construct a forward clustering distribution group model among the denitration cooperative input factors;

Taking the forward clustering distribution group model as a denitration cooperative model, screening irregular changes of one or more data in the denitration cooperative input factors, outputting process interference early warning, optimizing ammonia spraying amount through a denitration optimization model under the condition that the concentration of nitrogen oxides at a discharge outlet of a chimney reaches the standard, and enabling a dust removal system at the rear end to carry out corresponding dust removal treatment;

the dust removal cooperative model building process comprises the following steps:

Acquiring time sequence historical data of a dedusting cooperative input factor, wherein the time sequence historical data comprises a dedusting operation parameter, a dedusting outlet dust concentration, a chimney discharge outlet dust concentration, an ash conveying system operation parameter and a denitration cooperative model output ammonia escape amount;

Applying a machine learning recommendation algorithm to the time sequence historical data, and combining an expert system to establish a nonlinear correlation model of the rapping force and the rapping period, and marking the nonlinear correlation model as a third nonlinear correlation model;

Taking the third nonlinear association model as a dedusting cooperation model, calculating the dedusting efficiency of the desulfurization system through slurry washing according to the difference value of the dust concentration of a dedusting outlet and the dust concentration of a chimney discharge outlet based on the dedusting cooperation model, taking the dust concentration of the chimney discharge outlet as a control target, calculating the lowest dust concentration of the dedusting outlet, determining an association control strategy according to the operation parameters of the ash conveying system and the dedusting operation parameters, and carrying out cooperative control on the dedusting system and the ash conveying system;

the desulfurization cooperative model building process comprises the following steps:

Acquiring historical data of desulfurization cooperative input factors, wherein the historical data of the desulfurization cooperative input factors comprise dust concentration of a dust removal outlet, dust concentration of a discharge outlet, sulfur dioxide concentration of the discharge outlet, slurry circulating pump combination, demister flushing and absorption tower liquid level;

applying a machine learning classification algorithm to the historical data, and establishing a nonlinear classification model of the dust concentration of the discharge outlet and the flushing of the demister under different dust concentrations of the dedusting outlet;

And taking the nonlinear classification model as a desulfurization cooperative model, starting a demister to wash according to the liquid level of the absorption tower under the condition that the dust concentration of a desulfurization inlet is high through the desulfurization cooperative model, reducing the dust concentration of a discharge outlet, and cooperatively controlling a desulfurization system and a dust removal system.

2. The smoke environmental protection island cooperative control method according to claim 1, wherein the process for establishing the denitration optimization model comprises the following steps:

Acquiring historical denitration working condition data of a denitration process;

applying a machine learning regression algorithm to the historical denitration working condition data, establishing nonlinear correlation models of ammonia injection quantity and nitrogen oxide concentration of a chimney discharge port under various working conditions, and marking the nonlinear correlation models as first nonlinear correlation models;

And obtaining the denitration optimization model through target conversion on the first nonlinear correlation model.

3. The smoke environmental protection island cooperative control method according to claim 1, wherein the dust removal optimization model building process comprises the following steps:

Acquiring boiler working condition data and dust removal electric field operation parameters;

Applying a machine learning classification algorithm to the boiler working condition data and the dedusting electric field operation parameters, and establishing nonlinear correlation models of dust concentration and dedusting power of a chimney discharge port of the dedusting electric field operation parameters under various working conditions;

and taking the nonlinear association model as a dust removal optimization model, and providing a corresponding energy-saving efficiency-improving strategy for electric dust removal equipment by adopting an intelligent preferred algorithm for the dust removal optimization model to realize dust removal optimization output.

4. The smoke environmental protection island cooperative control method according to claim 1, wherein the process for establishing the desulfurization optimization model comprises the following steps:

Acquiring historical desulfurization working condition data of a desulfurization process;

Applying a machine learning regression algorithm to the historical desulfurization working condition data, and establishing a nonlinear correlation model of slurry volume, slurry circulating pump combination and sulfur dioxide concentration of a chimney discharge port under various working conditions, and marking the nonlinear correlation model as a second nonlinear correlation model;

and obtaining the desulfurization optimization model through target conversion on the second nonlinear correlation model.

5. The utility model provides a flue gas environmental protection island cooperative control system which characterized in that includes:

The system comprises a model building unit, a denitration optimizing model, a dedusting optimizing model, a desulfurization optimizing model, a denitration cooperative model, a dedusting cooperative model and a desulfurization cooperative model, wherein the denitration optimizing model is used for predicting the optimized ammonia spraying amount, the dedusting optimizing model is used for providing a corresponding energy-saving efficiency improving strategy for electric dust removing equipment, the desulfurization optimizing model is used for obtaining the optimized slurry amount and circulating pump combination according to the actual desulfurization working condition data and the sulfur dioxide target concentration value of a chimney discharge port, the denitration cooperative model is used for cooperatively controlling a denitration system and a dedusting system, the dedusting cooperative model is used for cooperatively controlling the dedusting system and an ash conveying system, and the desulfurization cooperative model is used for cooperatively controlling the desulfurization system and the dedusting system;

The strategy determining unit is used for determining an optimization strategy of the environmental protection island flue gas based on the denitration optimization model, the dust removal optimization model and the desulfurization optimization model;

the cooperative control unit is used for cooperatively controlling the whole environment-friendly island based on the denitration cooperative model, the dedusting cooperative model and the desulfurization cooperative model;

wherein the system further comprises: a denitration cooperative model building unit;

The denitration cooperative model building unit is specifically configured to:

acquiring historical data of denitration cooperative input factors, wherein the historical data of the denitration cooperative input factors comprise denitration inlet nitrogen oxide concentration, denitration outlet nitrogen oxide concentration, ammonia injection amount, ammonia escape amount, chimney discharge outlet nitrogen oxide concentration and dedusting operation parameters;

applying a machine learning clustering algorithm to the historical data to construct a forward clustering distribution group model among the denitration cooperative input factors;

Taking the forward clustering distribution group model as a denitration cooperative model, screening irregular changes of one or more data in the denitration cooperative input factors, outputting process interference early warning, optimizing ammonia spraying amount through a denitration optimization model under the condition that the concentration of nitrogen oxides at a discharge outlet of a chimney reaches the standard, and enabling a dust removal system at the rear end to carry out corresponding dust removal treatment;

wherein the system further comprises: a dust removal cooperative model building unit;

the dust removal cooperative model building unit is specifically used for:

Acquiring time sequence historical data of a dedusting cooperative input factor, wherein the time sequence historical data comprises a dedusting operation parameter, a dedusting outlet dust concentration, a chimney discharge outlet dust concentration, an ash conveying system operation parameter and a denitration cooperative model output ammonia escape amount;

Applying a machine learning recommendation algorithm to the time sequence historical data, and combining an expert system to establish a nonlinear correlation model of the rapping force and the rapping period, and marking the nonlinear correlation model as a third nonlinear correlation model;

Taking the third nonlinear association model as a dedusting cooperation model, calculating the dedusting efficiency of the desulfurization system through slurry washing according to the difference value of the dust concentration of a dedusting outlet and the dust concentration of a chimney discharge outlet based on the dedusting cooperation model, taking the dust concentration of the chimney discharge outlet as a control target, calculating the lowest dust concentration of the dedusting outlet, determining an association control strategy according to the operation parameters of the ash conveying system and the dedusting operation parameters, and carrying out cooperative control on the dedusting system and the ash conveying system;

Wherein the system further comprises: a desulfurization cooperative model building unit;

the desulfurization cooperative model building unit is specifically configured to:

Acquiring historical data of desulfurization cooperative input factors, wherein the historical data of the desulfurization cooperative input factors comprise dust concentration of a dust removal outlet, dust concentration of a discharge outlet, sulfur dioxide concentration of the discharge outlet, slurry circulating pump combination, demister flushing and absorption tower liquid level;

applying a machine learning classification algorithm to the historical data, and establishing a nonlinear classification model of the dust concentration of the discharge outlet and the flushing of the demister under different dust concentrations of the dedusting outlet;

And taking the nonlinear classification model as a desulfurization cooperative model, starting a demister to wash according to the liquid level of the absorption tower under the condition that the dust concentration of a desulfurization inlet is high through the desulfurization cooperative model, reducing the dust concentration of a discharge outlet, and cooperatively controlling a desulfurization system and a dust removal system.

6. The smoke and environmental protection island cooperative control system of claim 5, further comprising: a denitration optimizing model building unit;

the denitration optimizing model building unit is specifically used for:

Acquiring historical denitration working condition data of a denitration process;

applying a machine learning regression algorithm to the historical denitration working condition data, establishing nonlinear correlation models of ammonia injection quantity and nitrogen oxide concentration of a chimney discharge port under various working conditions, and marking the nonlinear correlation models as first nonlinear correlation models;

And obtaining the denitration optimization model through target conversion on the first nonlinear correlation model.

7. The smoke and environmental protection island cooperative control system of claim 5, further comprising: a dust removal optimization model building unit;

the dust removal optimization model building unit is specifically used for:

Acquiring boiler working condition data and dust removal electric field operation parameters;

Applying a machine learning classification algorithm to the boiler working condition data and the dedusting electric field operation parameters, and establishing nonlinear correlation models of dust concentration and dedusting power of a chimney discharge port of the dedusting electric field operation parameters under various working conditions;

and taking the nonlinear association model as a dust removal optimization model, and providing a corresponding energy-saving efficiency-improving strategy for electric dust removal equipment by adopting an intelligent preferred algorithm for the dust removal optimization model to realize dust removal optimization output.

8. The smoke and environmental protection island cooperative control system of claim 5, further comprising: a desulfurization optimization model building unit;

The desulfurization optimization model building unit is specifically configured to:

Acquiring historical desulfurization working condition data of a desulfurization process;

Applying a machine learning regression algorithm to the historical desulfurization working condition data, and establishing a nonlinear correlation model of slurry volume, slurry circulating pump combination and sulfur dioxide concentration of a chimney discharge port under various working conditions, and marking the nonlinear correlation model as a second nonlinear correlation model;

and obtaining the desulfurization optimization model through target conversion on the second nonlinear correlation model.