CN214552435U - SNCR control system based on CFB boiler NOx emission concentration prediction - Google Patents

Abstract

The utility model relates to a SNCR control system based on CFB boiler NOx emission concentration prediction, which belongs to the technical field of intelligent power generation and comprises an external hanging server, a DCS and a communication system; an intelligent prediction system is embedded in the plug-in server, and the plug-in server is connected with the DCS through a communication system; the intelligent prediction system inputs numerical values into a PID controller, the PID controller outputs action signals to an ammonia water pump manual operator, and the ammonia water pump manual operator controls a variable-frequency ammonia water pump to send ammonia water into an SNCR (selective non catalytic reduction) denitration device. The utility model controls the ammonia pump manual operator through the PID controller, and further controls the variable frequency ammonia pump to send ammonia water into the SNCR denitration device; the PID controller receives the numerical value of the NOx emission concentration predicted by the intelligent prediction system, so that the numerical value can be moved in advance, and the delay caused by the traditional dependence on field measurement is overcome; the intelligent prediction system is embedded into an LSTM neural network with memory and forgetting functions, so that the prediction precision is high, and prediction can be carried out 3 minutes in advance.

Description

SNCR control system based on CFB boiler NOx emission concentration prediction

Technical Field

The utility model belongs to the technical field of intelligent power generation, in particular to SNCR control system based on CFB boiler NOx emission concentration prediction.

Background

With the increasingly strict requirements of the national environmental protection agency on the pollutant emission of the thermal power plant, more and more pollutants emitted by the thermal power generating unit cannot reach the standard. In order to enable the pollutant emission to reach the ultralow emission standard, most thermal power generating units complete ultralow emission modification, such as adding an SCR (selective catalytic reduction) denitration device and a wet desulphurization device at the tail of flue gas. In recent years, circulating fluidized bed units have been rapidly developed due to the advantages of good coal adaptability, large load regulation range, low pollutant original concentration discharge and the like. In 2013, the first 600 MW supercritical circulating fluidized bed boiler in the world was put into operation in the Sichuan white horse power plant, and in 2015, the first 350 MW supercritical circulating fluidized bed boiler in the world was put into operation in the Shanxi national gold power plant. By the end of 2018, the total installed capacity of the circulating fluidized bed boiler put into China reaches 82.3GW, the 660MW efficient ultra-supercritical circulating fluidized bed boiler which is currently developed is quickly put into engineering construction, and the circulating fluidized bed boiler which is expected to be built is the circulating fluidized bed boiler with the lowest emission and energy consumption level and the highest capacity and efficiency in the world.

In order to save cost and have the advantage of natural low NOx concentration emission of the circulating fluidized bed unit, an SNCR device is usually additionally arranged at the top of a hearth for denitration of the circulating fluidized bed unit. However, the mode has a great defect that the NOx measuring point cannot resist high temperature, so that the measuring point is generally installed at the position of a desulfurizing tower inlet or a chimney, the NOx concentration monitoring is relatively late, the measured value of an SNCR control system is delayed for 3-5 minutes, and the investment of the SNCR automatic control is greatly influenced, so that the ammonia injection amount or the urea amount for denitration of the circulating fluidized bed unit is manually controlled, and the experience and physical strength of operators are seriously tested. And the output of the ammonia injection pump is also in a large-opening and large-closing control mode, so that the conditions of waste and ammonia escape caused by instantaneous exceeding of NOx emission concentration and excessive ammonia injection are occasionally generated.

In summary, an SNCR control system having a prediction function and capable of automatically controlling the ammonia injection amount needs to be designed to overcome the delay problem caused by the fact that a site measuring point is behind, so that the original SNCR control system is optimized, and the automatic input rate of the SNCR is improved.

SUMMERY OF THE UTILITY MODEL

The utility model discloses a solve the technical problem that exists among the well-known technology and provide a SNCR control system based on CFB boiler NOx emission concentration prediction, it can effectively overcome the lagged difficult problem of SNCR concentration measurement point measurement, and the advanced feedback NOx emission concentration moves in advance and spouts ammonia volume, and stable pollutant discharges and reduces and spouts the ammonia quantity.

The utility model comprises the following technical scheme: an SNCR control system based on CFB boiler NOx emission concentration prediction comprises an external hanging type server, a DCS system and a communication system; an intelligent prediction system is embedded in the plug-in server, and the plug-in server is connected with the DCS through a communication system; the intelligent prediction system inputs numerical values into a PID controller, the PID controller outputs action signals to an ammonia water pump manual operator, and the ammonia water pump manual operator controls a variable-frequency ammonia water pump to send ammonia water into an SNCR (selective non catalytic reduction) denitration device.

Preferably, the DCS system is respectively connected with the primary air meter, the secondary air meter, the coal feeder, the ammonia water flow meter, the bed temperature measuring system, the oxygen meter and the CEMS continuous monitoring system.

Preferably, the primary air gauge and the secondary air gauge both adopt WB-1 integrated Weiba air speed measuring devices, are composed of integrated sensors and differential pressure transmitters, can be connected with a DCS system or other computer systems, and have the advantages of accurate and stable dynamic pressure signals and difficulty in blocking.

Preferably, the coal feeder adopts a weighing type coal feeder, and can transmit a coal quantity signal to the DCS system while conveying fuel to the boiler.

Preferably, the ammonia water flowmeter is an electromagnetic flowmeter, and due to the corrosivity of ammonia water, a specific lining and corrosion resistance are required during selective purchasing.

Preferably, the bed temperature measuring system consists of 32 thermocouples, and the bed temperature transmitted to the DCS by the bed temperature measuring system is an average value of the bed temperature after dead spots are removed.

Preferably, the oxygen meter is a zirconia oxygen meter, two oxygen meters are arranged at the inlet of the air preheater, and the average value of the two oxygen meters is taken when the oxygen meters are transmitted to the DCS system.

Preferably, the intelligent prediction system is embedded with an LSTM neural network, and predicts the NOx emission concentration in advance for 3 minutes according to the information collected by the DCS system.

The utility model has the advantages and positive effect:

1. the utility model controls the ammonia pump manual operator through the PID controller, and further controls the variable frequency ammonia pump to send ammonia water into the SNCR denitration device; the PID controller receives the numerical value of the NOx emission concentration predicted by the intelligent prediction system, so that the numerical value can be moved in advance, and the delay caused by the traditional dependence on field measurement is overcome; meanwhile, the PID controller can prevent the ammonia pump from operating abnormally when the intelligent prediction system fails or predicts large deviation.

2. The utility model discloses an intelligent prediction system prediction NOx emission concentration, intelligent prediction system embedding have memory and forget the LSTM neural network of function, and the prediction precision is high, thereby can predict NOx emission concentration 3 minutes in advance and overcome the delay problem that the on-the-spot measurement station brought by the back to optimize former SNCR control system with this, make the automatic input rate of SNCR improve.

3. The utility model discloses can stabilize circulating fluidized bed boiler NOx emission concentration, reduce and spout ammonia volume, and only need add an outer hanging server, need not increase the on-the-spot operation equipment, reform transform simply with low costs.

Drawings

Fig. 1 is a schematic structural diagram of the present invention.

In the figure, 1, a plug-in server; 2. an intelligent prediction system; 3. a primary air gauge; 4. a secondary air gauge; 5. a coal feeder; 6. an ammonia flowmeter; 7. a bed temperature measuring system; 8, an oxygen meter; 9. a CEMS continuous monitoring system; 10. a DCS system; 11. a communication system; 12. a PID controller; 13. the manual operator of the ammonia pump; 14. a variable frequency ammonia pump; 15. SNCR denitrification facility.

Detailed Description

To further disclose the contents, features and functions of the present invention, the following examples are given in detail with reference to the accompanying drawings.

Example (b): referring to fig. 1, an SNCR control system based on the prediction of NOx emission concentration of a CFB boiler includes an external server 1, a DCS system 10, and a communication system 11; an intelligent prediction system 2 is embedded in the plug-in server 1, and the plug-in server 1 is connected with the DCS system 10 through a communication system 11; the intelligent prediction system 2 is embedded with an LSTM neural network, and the intelligent prediction system 2 predicts the NOx emission concentration 3 minutes in advance according to the information collected by the DCS system 10. The intelligent prediction system 2 inputs numerical values into a PID controller 12, the PID controller 12 outputs action signals to an ammonia pump manual operator 13, and the ammonia pump manual operator 13 controls a variable-frequency ammonia pump 14 to send ammonia water into an SNCR denitration device 15.

The DCS system 10 is respectively connected with a primary air meter 3, a secondary air meter 4, a coal feeder 5, an ammonia water flow meter 6, a bed temperature measuring system 7, an oxygen meter 8 and a CEMS continuous monitoring system 9.

The primary air gauge 3 and the secondary air gauge 4 both adopt WB-1 integrated Weiba air speed measuring devices, are composed of integrated sensors and differential pressure transmitters, can be connected with a DCS (distributed control system) 10 or other computer systems, and have the advantages that dynamic pressure signals are accurate and stable and are not easy to block; the coal feeder 5 adopts a weighing type coal feeder, and can transmit a coal feeding quantity signal to the DCS system 10 while conveying fuel to a boiler; the ammonia water flowmeter 6 is an electromagnetic flowmeter, and due to the corrosivity of ammonia water, a specific lining and corrosion resistance are required during purchasing; the bed temperature measuring system 7 consists of 32 thermocouples, and the bed temperature transmitted to the DCS 10 by the bed temperature measuring system 7 is an average value after dead spots are removed; the oxygen meter 8 is a zirconia type oxygen meter, is arranged at the inlet of the air preheater, has two oxygen meters in total, and takes the average value of the two oxygen meters when transmitting to the DCS system 10.

The working principle is as follows: due to measuring point lag and measurement reasons, the feedback of the SNCR control system cannot reflect the current SNCR outlet NOx concentration value in time, so the control quality is poor. Taking the increase of the NOx emission concentration as an example, when the NOx concentration is fed back by a measuring point to rise, the actual rising time is before 3min, but the SNCR control system only starts to act to increase the ammonia injection amount at the moment, the actual NOx concentration obtained after the reaction still needs 3min to be monitored by the measuring point again, the NOx emission concentration in the 3min is not controlled by the current ammonia injection amount, the NOx concentration emission exceeds the standard, if the NOx concentration is reduced in the 3min, the ammonia injection amount is too high, waste is caused, and meanwhile, the excessive ammonia injection amount can cause ammonia to escape, secondary pollution is caused, and the corrosion of the air preheater is aggravated. The ammonia injection amount required to be increased can be calculated in advance by utilizing the result of model prediction, and the variable-frequency ammonia pump 14 is operated in advance, so that the effects of stabilizing NOx emission and reducing the ammonia injection amount are achieved.

The utility model discloses a LSTM neural network intelligent prediction system 2, history operational data (once the amount of wind, the secondary amount of wind, the volume of coal feeding, aqueous ammonia flow, the bed temperature, air preheater entry oxygen volume and flue gas flow) through gathering in the DCS system 10 trains the model, then utilize the input value of current model to predict the emission concentration of NOx after 3min, and carry numerical value for PID controller 12, PID controller 12 controls ammonia pump hand operator 13 and moves in advance and makes frequency conversion ammonia pump send 14 aqueous ammonia into SNCR denitrification facility 15, optimize SNCR control system with this.

Although the preferred embodiments of the present invention have been described, the present invention is not limited to the above-mentioned embodiments, which are only illustrative and not restrictive, and those skilled in the art can make many forms without departing from the spirit and scope of the present invention. All of which fall within the scope of the present invention.

Claims (6)

1. The utility model provides a SNCR control system based on CFB boiler NOx discharges concentration prediction, includes hanging server, DCS system and communication system outward, the embedded intelligent prediction system of external server, its characterized in that: the plug-in server is connected with the DCS through a communication system; the intelligent prediction system inputs numerical values into a PID controller, the PID controller outputs action signals to an ammonia water pump manual operator, and the ammonia water pump manual operator controls a variable-frequency ammonia water pump to send ammonia water into an SNCR (selective non catalytic reduction) denitration device; and the DCS is respectively connected with a primary air gauge, a secondary air gauge, a coal feeder, an ammonia water flowmeter, a bed temperature measuring system, an oxygen meter and a CEMS continuous monitoring system.

2. The SNCR control system based on prediction of NOx emission concentration from a CFB boiler according to claim 1, wherein: the primary air gauge and the secondary air gauge both adopt WB-1 integrated Weiba air speed measuring devices, are composed of integrated sensors and differential pressure transmitters, and can be connected with a DCS system or other computer systems in a network.

3. The SNCR control system based on prediction of NOx emission concentration from a CFB boiler according to claim 1, wherein: the coal feeder adopts a weighing type coal feeder, and can transmit a coal quantity signal to a DCS system while conveying fuel to a boiler.

4. The SNCR control system based on prediction of NOx emission concentration from a CFB boiler according to claim 1, wherein: the ammonia water flowmeter is an electromagnetic flowmeter.

5. The SNCR control system based on prediction of NOx emission concentration from a CFB boiler according to claim 1, wherein: the bed temperature measuring system consists of 32 thermocouples, and the bed temperature transmitted to the DCS is the average value of the bed temperature after dead spots are removed.

6. The SNCR control system based on prediction of NOx emission concentration from a CFB boiler according to claim 1, wherein: the oxygen meter is a zirconia type oxygen meter and is arranged at the inlet of the air preheater.

Images