Intelligent optimization control system for SCR (selective catalytic reduction) denitration of boiler flue gas

Abstract

The invention discloses a boiler flue gas SCR denitration intelligent optimization control system, and relates to the technical field of environmental protection equipment. According to the boiler flue gas SCR denitration intelligent optimization control system, the SCR denitration intelligent optimization control system is provided with an Ai intelligent pressure control system and model prediction, the control scheme of the SCR denitration intelligent optimization control system is that an AOM module and an AIC module are cooperatively controlled, and the surplus part of NOx ammonia reaction of an SCR catalyst in the SCR denitration intelligent optimization control system is adsorbed by SCR. Data can be extracted in real time through the Ai server, real-time learning is carried out, automatic control is achieved, the number of manual intervention times is reduced, environment-friendly emission indexes such as NOx and ammonia escape at a flue gas outlet are stabilized, edge clamping operation is achieved, the ammonia usage amount is reduced, manual intervention can be achieved, and an original operation system can be switched in real time without disturbance.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of environmental protection equipment, in particular to a boiler flue gas SCR denitration intelligent optimization control system. BACKGROUND

[0002] Denitration process technology is a technology for reducing nitrogen oxides (NOx) emissions from fixed pollution sources. This technology is widely used in thermal power plants, industrial boilers and other combustion devices to reduce their impact on the atmospheric environment.

[0003] The basic working principle of the SCR system is to use ammonia (NH3) as a reducing agent to react with nitrogen oxides in the flue gas under the action of a catalyst at a certain temperature to generate nitrogen (N2) and water (H2O). The specific chemical reaction equation is as follows:

[0004] 4NO + 4NH3 + O2 → 4N2 + 6H2O

[0005] 2NO2 + 4NH3 + O2 → 3N2 + 6H2O

[0006] With the increasing environmental protection requirements, the limitations of denitration in flue gas treatment have been exposed. Especially in the process of controlling nitrogen oxides, the risk of ammonia escape exceeding the standard increases, affecting normal production and social image of enterprises.

[0007] The operation status of the denitration device is that the device uses SCR denitration process technology, the denitration agent is urea, and the operation system is DCS

[0008] Specifically, it is characterized by large fluctuations in SCR inlet flue gas NOx, large changes in flue gas flow, small ammonia escape at the flue gas outlet, large fluctuations in oxygen content at the reactor inlet flue, and large fluctuations in NOx concentration at the flue gas outlet. Phenomenon, at the same time, the device is manually operated by the operator, and the workload of the operator is extremely large. SUMMARY

[0009] The purpose of the present application is to provide a boiler flue gas SCR denitration intelligent optimization control system to solve the problem of large fluctuations in various parameters, manual operation and extremely large workload.

[0010] To achieve the above purpose, the present application provides the following technical scheme:

[0011] The boiler flue gas SCR denitration intelligent optimization control system is characterized in that the intelligent optimization control system is provided with an Ai intelligent pressure control system and a model prediction, the control scheme of the intelligent optimization control system is AOM module plus AIC module cooperative control, the excess part of the SCR catalyst NOx ammonia reaction in the intelligent optimization control system is adsorbed by the SCR, and the ammonia gas is adsorbed in the SCR. The model Langmuir equation:

[0012]

[0013] In the formula, qe is the adsorption amount of the biochar to ammonia nitrogen at adsorption equilibrium, mg·g-1; qmax is the maximum adsorption amount, mg·g-1; ce is the equilibrium concentration of the solution after adsorption, mg·L-1; KL, KF and n are adsorption equilibrium constants;

[0014] The AOM module is responsible for learning, predicting, optimizing and scheduling functions of the denitration system, realizes precise ammonia injection according to the denitration reaction mechanism, realizes the edge operation under the condition of qualified NOx emission, reduces the ammonia consumption and prolongs the service life of the SCR catalyst;

[0015] The AIC module is specifically adjusted according to the instruction of the AOM module, prevents over-regulation, stabilizes the NOx index at the smoke outlet, realizes the edge operation under the premise of emission standard, and maximally reduces the operation cost.

[0016] Further, the Ai model predictor is provided in the model prediction, the Ai model predictor can realize large-lag optimization control, and the Ai model predictor is based on that the NOx at the smoke outlet and the ammonia reaction to the reaction at the SCR outlet NOx measuring instrument are displayed for 300-720 seconds, the dynamic characteristics of the process control under the disturbance are estimated in advance, and pre-compensation is given, so that the delayed controlled variable is ahead of the reaction to the regulator, the regulator is advanced, the over-regulation amount is reduced, and the regulation process is accelerated, and is expressed as:

[0017] Wherein KsGs(s)=KpGp(s)(1-e -ts ),

[0018] Let K=2.2, T=200, t=30,

[0019] KsGs(s)=(2.2 / 200+1)(1-e -30s ).

[0020] Further, the multivariable controller is provided in the Ai model predictor, the overall architecture of the multivariable controller includes a set value and a control interval, a control optimization algorithm, a process model, a control variable, a controlled variable, a disturbance variable and a production process, the set value and the control interval are operated on the soft instrument, the control optimization algorithm is further controlled, the control variable and the controlled variable are selected in the process model, the controlled variable is fed back to the process of the control optimization algorithm for optimization, the content of the early feedback is optimized through the process of the control optimization algorithm, the disturbance variable not confirmed in the early feedback content is listed as the controlled variable in the continuous production process and is fed back to the process of the control optimization algorithm for optimization, so as to form an overall closed loop.

[0021] The application has the beneficial effects that the application can extract data in real time on the Ai server, perform real-time learning, realize automatic control, reduce the number of manual interventions, stabilize environmental emission indexes such as NOx and ammonia escape of flue gas outlet, realize edge cutting operation, reduce the amount of ammonia used, can be manually intervened, and can be switched to the original operation system in real time without disturbance.

[0022] The above description is only a summary of the technical scheme of the present application, in order to more clearly understand the technical means of the present application, and can be implemented according to the content of the specification, the following is a preferred embodiment of the present application and the detailed description is as follows. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 The flow chart of the overall operation shown in an embodiment of the present application.

[0024] Figure 2 The control block schematic diagram shown in an embodiment of the present application.

[0025] Figure 3 The operation flow chart of the multivariable controller shown in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The technical scheme of the present application will be described in detail below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0027] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the purpose of facilitating the description of the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, the terms "first", "second", "third" are only for the purpose of description, and cannot be understood as indicating or implying relative importance.

[0028] In the description of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "mounting", "connection", "linking" should be understood in a broad sense, for example, it can be fixed connection, or detachable connection, or integral connection; it can be mechanical connection, or electrical connection; it can be direct connection, or indirect connection through intermediate medium, or internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances. In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0029] Please refer to Figure 1 The boiler flue gas SCR denitration intelligent optimization control system shown in a preferred embodiment of the present application is characterized in that the intelligent optimization control system is provided with an Ai intelligent pressure control system and model prediction, the control scheme of the intelligent optimization control system is AOM module plus AIC module cooperative control, the excess part of the SCR catalyst NOx ammonia reaction in the intelligent optimization control system is adsorbed by the SCR, and the ammonia gas is adsorbed in the SCR according to the Langmuir equation:

[0030]

[0031] In the formula, qe is the adsorption amount of the biochar to ammonia nitrogen at the adsorption equilibrium, mg·g-1; qmax is the maximum adsorption amount, mg·g-1; ce is the equilibrium concentration of the solution after adsorption, mg·L-1; KL, KF and n are adsorption equilibrium constants;

[0032] The AOM module is responsible for the learning, prediction, optimization and scheduling functions of the denitration system, according to the denitration reaction mechanism, precise ammonia injection is realized, the edge operation is realized under the condition of qualified NOx emission, the ammonia consumption is reduced and the service life of the SCR catalyst is prolonged;

[0033] The AIC module is specifically adjusted according to the instruction of the AOM module, over-regulation is prevented, the NOx index at the flue gas outlet is stabilized, the edge operation is realized under the premise of emission standard, and the operation cost is maximally reduced.

[0034] The Ai model predictor is provided in the model prediction, the Ai model predictor can realize large-lag optimization control, on the basis of the 300-720 second time of the reaction of the flue gas outlet NOx and the ammonia gas to the reaction on the SCR outlet NOx measuring instrument, the Ai model predictor pre-estimates the dynamic characteristics of the process control under disturbance, and gives pre-compensation, so that the delayed controlled variable is ahead of reaction to the regulator, the regulator is ahead of action, the over-regulation amount is reduced and the regulation process is accelerated, which is expressed as:

[0035] Wherein, KsGs(s)=KpGp(s)(1-e -ts ),

[0036] Let K = 2.2, T = 200, t = 30.

[0037] KsGs(s) = (2.2 / 200+1)(1-e -30s ).

[0038] The AI ​​model predictor incorporates a multivariable controller. The overall architecture of the multivariable controller includes setpoints and control ranges, a control optimization algorithm, a process model, control variables, controlled variables, disturbance variables, and the production process. Setpoint and control range operations are performed on the software instrumentation, and the control optimization algorithm further filters out control variables and controlled variables from the process model. The controlled variables are fed back to the control optimization algorithm for optimization. The previously fed-back content is optimized through the control optimization algorithm. Disturbance variables that were not identified in the previously fed-back content are listed as controlled variables in the continued production process and fed back to the control optimization algorithm for optimization, thus forming an overall closed loop.

[0039] In summary, this invention provides an intelligent optimization control system for boiler flue gas SCR denitrification. This system can extract data in real time through an AI server, perform real-time learning, achieve automatic control, reduce the number of manual interventions, stabilize environmental emission indicators such as NOx and ammonia escape at the flue gas outlet, achieve edge operation, reduce ammonia usage, allow for manual intervention, and can switch the original operating system in real time without disturbance.

[0040] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0041] The embodiments described above are merely illustrative of implementation methods of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A boiler flue gas SCR denitrification intelligent optimization control system, characterized in that, The intelligent optimization control system includes an AI intelligent pressure control system and model prediction. The control scheme of the intelligent optimization control system is a collaborative control using an AOM module and an AIC module. In the intelligent optimization control system, the excess NOx from the SCR catalyst reacting with ammonia is adsorbed by the SCR. The ammonia adsorption model in the SCR is based on the Langmuir equation. In the formula, qe is the amount of ammonia nitrogen adsorbed by biochar at adsorption equilibrium, mg·g⁻¹; qmax is the maximum adsorption amount, mg·g⁻¹; ce is the equilibrium concentration of the solution after adsorption, mg·L⁻¹; KL, KF and n are adsorption equilibrium constants. The AOM module is responsible for learning, predicting, optimizing and scheduling the denitrification system. Based on the denitrification reaction mechanism, it can achieve precise ammonia injection, enabling edge operation while ensuring NOx emissions meet standards, reducing ammonia consumption and extending the service life of the SCR catalyst. The AIC module adjusts according to the instructions of the AOM module to prevent over-adjustment, stabilize the NOx index at the flue gas outlet, and achieve edge operation under the premise of meeting emission standards, thereby minimizing operating costs.

2. The intelligent optimization control system for boiler flue gas SCR denitrification as described in claim 1, characterized in that, The model prediction includes an AI model predictor, which can achieve large lag optimization control. Based on the reaction time of NOx and ammonia at the flue gas outlet (300-720 seconds from the reaction point displayed on the SCR outlet NOx meter), the AI ​​model predictor pre-estimates the dynamic characteristics of the process control under disturbances and provides pre-compensation, causing the delayed controlled variable to react ahead of the regulator, thus enabling the regulator to act earlier, reducing over-regulation and accelerating the regulation process. This can be expressed as: Where KsGs(s) = KpGp(s)(1-e -ts ), Let K = 2.2, T = 200, t = 30. KsGs(s)=(2.2 / 200+1)(1-e -30s )。 3. The intelligent optimization control system for boiler flue gas SCR denitrification as described in claim 2, characterized in that, The AI ​​model predictor is equipped with a multivariate controller. The overall architecture of the multivariate controller includes setpoints and control ranges, control optimization algorithms, process models, control variables, controlled variables, disturbance variables, and production processes. Setpoint and control range operations are performed on the software instrument, and the control optimization algorithm further filters out control variables and controlled variables from the process model. The controlled variables are fed back to the control optimization algorithm for optimization. The content fed back in the early stage is optimized through the control optimization algorithm. Disturbance variables that were not identified in the early stage of feedback are listed as controlled variables in the continued production process and fed back to the control optimization algorithm for optimization, thus forming an overall closed loop.

Images