Coal-fired boiler furnace arch soot blowing system

Abstract

The invention discloses a soot blowing system for a furnace arch of a coal-fired boiler, in particular to a soot blowing system for the furnace arch and a horizontal flue of the boiler, which measures the temperature and flow field conditions in the furnace arch and the horizontal flue of the boiler in real time according to the operation data of the boiler acquired in real time and by arranging a series of sound wave receiving and transmitting devices at proper positions in the boiler. According to the obtained operation parameters of the boiler and the changes of the temperature and the flow field in the boiler, the starting and operation modes of the soot blower are adjusted in real time, the soot deposition conditions of the furnace arch and the horizontal flue can be monitored and predicted according to the changes of the flow field and the temperature, and the soot blowing period, the soot blowing time every time, the soot blowing strength and the like are optimized. Safe and stable operation of boiler equipment is guaranteed, the operation cost of the boiler is reduced, and meanwhile the operation cost of soot blowing equipment is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of soot blowing in boilers, specifically to the soot blowing technology for the furnace arch and horizontal flue of boilers. Background Art

[0002] Due to changes in boiler fuel, incomplete combustion, and the operation of many current boilers at low loads due to peak shaving and other needs, combined with unreasonable boiler furnace design, furnace arch design, etc., it is easy to cause ash accumulation in the furnace arch and horizontal flue of the boiler. After ash accumulation, it is easy to cause a decrease in boiler thermal efficiency, an increase in energy consumption, and a decrease in boiler safety. It can be prevented or removed by optimizing combustion, improving boiler design, regular soot blowing, etc. However, conventional steam soot blowing increases the water vapor content in the flue gas, causing more serious blockage of the air preheater, and the acoustic soot blower has little effect on adhesive ash. Moreover, there is currently a lack of effective monitoring of the ash accumulation situation, and there is no dynamic monitoring and operation optimization based on boiler operating conditions (such as boiler load, temperature field inside the boiler, resistance change, etc.) and coal combustion changes, and it is impossible to effectively evaluate the soot blowing effect of the soot blower.

[0003] Therefore, we have developed a process for monitoring the flow field and ash accumulation situation of the horizontal flue and furnace arch by sound waves, and an intelligent control model combined with acoustic soot blowing or laminated disc jet soot blowing technology and big data to strengthen the removal of ash accumulation in the horizontal flue and furnace arch of the boiler. Summary of the Invention

[0004] The purpose of the present invention is to propose a soot blowing system for the furnace arch of a coal-fired boiler in view of the above-mentioned existing technical situation, to effectively monitor the ash accumulation situation and soot blowing effect on the horizontal flue and furnace arch in the boiler, and to solve the ash accumulation problem of the furnace arch of the boiler efficiently, safely and economically by combining boiler operation data and historical operation data of the soot blower.

[0005] A soot blowing system for the furnace arch of a coal-fired boiler includes the following:

[0006] Step 1: Obtain the real-time operation data of the boiler, and obtain the historical values of various parameters of the boiler operation, including but not limited to boiler load, coal calorific value analysis, component analysis, boiler coal consumption, temperature distribution inside the boiler, pressure inside the boiler, and resistance inside the boiler, etc. The data is sent to the boiler operation data acquisition unit for obtaining relevant real-time operation data of the boiler operation;

[0007] Step 2: Set a series of acoustic wave transceiver devices at appropriate positions inside the boiler to measure the temperature and flow field situation near the furnace arch and inside the horizontal flue in the boiler in real time.

[0008] Step 3: Obtain the historical data of the operating parameters of the acoustic soot blower or the laminated disc jet soot blower, summarize the obtained historical data and the data obtained from boiler operation, etc., and use neural network methods such as BP, ANN, FNN, CNN, RNN or LSTM, set goals such as ensuring the safe operation of the boiler, preventing soot accumulation at the furnace arch corner of the boiler, and the economic operation of the soot blowing system, to obtain monitoring and operation models of the soot blowing device such as the early warning and prediction model of the soot accumulation system, the abnormal monitoring model, and the optimal soot blowing model, for the safe and economic operation of the soot blower.

[0009] Step 4: According to the relevant models obtained in Step 3, based on the measured data, control the operation mode of the soot blower in real time, such as the operation cycle, the length of the operation time, etc., and adjust the operation of the soot blower using the best operation mode. Adjust the opening and operation mode of the soot blower in real time according to the operating parameters of the boiler and the changes in temperature and flow field in the boiler, especially at positions such as the furnace arch corner and the horizontal flue. Optimize the soot blowing cycle, the time of each soot blowing, and the soot blowing intensity according to the changes in the flow field and temperature, and construct based on the historical data of the actual operating boiler, the data measured by the acoustic measurement device, and the historical data of the operation of the soot blower, etc., and further feedback to the intelligent control model for continuous optimization.

[0010] Step 5: Use the acoustic wave signals between the horizontal flue and the furnace arch corner of the boiler collected by the set acoustic wave transceiver device, through mathematical methods such as correlation function processing, measure the temperature and flow field conditions near the horizontal flue and the furnace arch corner, identify the soot accumulation conditions of the furnace arch corner and the horizontal flue, and set appropriate soot blowing intervals and intensities according to the historical operation data, and set soot accumulation degree alarm measures. When the average soot accumulation thickness reaches 1.0 cm, give a secondary alarm, and when the average soot accumulation thickness reaches 2.5 cm, give a primary alarm. When necessary, conduct manual intervention to strengthen soot blowing.

[0011] The described soot blowing system for the furnace arch corner of a coal-fired boiler mainly includes a data acquisition unit for boiler operation, which is used to obtain the relevant real-time operation data of the boiler operation; an acoustic wave temperature and flow field measurement unit, which measures the temperature and flow field conditions near the horizontal flue and the furnace arch corner of the boiler; a neural network data processing unit, which uses neural network methods such as LSTM to obtain relevant monitoring and operation models; a soot blowing system control and alarm unit, which is used to control the operation mode of the soot blower, such as the operation cycle, the length of the operation time, etc., and adjust the operation of the soot blower using the best operation mode; the described soot blowing unit includes relevant soot blower components, pipelines, valves, etc. of the acoustic soot blower or the laminated disc jet soot blower.

[0012] The soot blowing unit of the described soot blowing system for the arch of a coal-fired boiler is an acoustic soot blower or a laminated disc jet soot blower. The acoustic soot blower includes a compressed air system, an acoustic waveguide, an acoustic emitter, an acoustic sensor, an amplifier, etc. The laminated disc jet soot blower includes components such as jet nozzles, laminated discs, a driving device, and a compressed air system.

[0013] The control and alarm unit of the soot blowing system includes a system control and alarm module and a communication module.

[0014] The described acoustic wave temperature and flow field measurement unit includes an acoustic wave measurement system, a signal conditioning system, a control sub-unit, etc. The control sub-unit includes an A / D conversion module, a communication module, a control module, etc.

[0015] A computer device

[0016] Comprising: a processor for executing a computer program; a computer-readable storage medium storing a computer program which, when executed by the processor, is capable of implementing the described method.

[0017] A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, is capable of implementing the described method.

[0018] A computer program product comprising a computer program which, when executed by a processor, is capable of implementing the described method.

[0019] The beneficial effects of the present invention are:

[0020] The soot blowing system for the arch of a coal-fired boiler provided by the present invention can, through an acoustic wave measurement system, measure in real time the temperature and flow field conditions of the arch and the horizontal flue, etc., monitor the degree of ash accumulation in parts such as the arch, and perform soot blowing on parts such as the arch efficiently, safely and economically. By combining efficient soot blowers such as acoustic soot blowers or laminated disc jet soot blowers, the reliability of the equipment is effectively improved, the operation risk of the equipment is significantly reduced, the operation efficiency of the unit is increased, and thus the safe, economic and stable operation of the boiler equipment is ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a diagram of the soot blowing system for the arch of a coal-fired boiler according to the present invention.

[0022] Figure 2 It is a layout diagram of the acoustic wave measurement device according to the present invention.

[0023] Figure 3 It is a framework diagram of the model predictive control according to the present invention

[0024] Figure 4 It is a block diagram of the neural network predictive control according to the present invention

[0025] Figure 5 This is the framework diagram of the model predictive control of the present invention

[0026] Appendix Figure 1 and Appendix Figure 2 Marking description:

[0027] A. Boiler operation data acquisition unit; B. Acoustic wave temperature and flow field measurement unit; C. Neural network data processing unit; C. Soot blowing system control and alarm unit; D. Soot blowing unit; A1. Boiler operation data acquisition module; A2. Communication module; B1. Acoustic wave measurement system; B2. Signal conditioning system; B3. Acoustic wave transmitter control system; B4. A / D conversion module; B5. Communication module; B6. Control module; C1. Neural network data sorting module; C2. Communication module; D1. Control and alarm module; D2. Communication module; E. Soot blowing unit; F1. Acoustic wave generator; F2. Acoustic wave sensor; F3. Reverberation chamber corner

[0028] Appendix Figure 3 Marking description: The framework diagram of the model predictive control mainly consists of parts such as model predictive control and controlled object, and a model predictive controller is used to achieve the control of the controlled object;

[0029] Appendix Figure 4 Marking description: The block diagram of the neural network predictive control mainly includes parts such as a reference model, data preprocessing, a neural network predictive control model, and a controlled object;

[0030] Appendix Figure 5 Marking description: The framework diagram of the model predictive control mainly consists of three parts: X1 signal input, X2 neural network model construction, and X3 soot blowing control; Specific implementation manners

[0031] In the following description, specific details such as specific system structures and technologies are proposed for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0032] It should be understood that when used in the specification and appended claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0033] It should also be understood that the term "and / or" as used in the specification of this application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0034] As used in the specification of this application and the appended claims, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" depending on the context. Similarly, the phrases "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" depending on the context.

[0035] In addition, in the description of the specification of this application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0036] Reference to "one embodiment" or "some embodiments" or the like described in the specification of this application means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0037] The following further describes a sootblowing system for the arch of a coal-fired boiler of the present invention with reference to the accompanying drawings: This embodiment is only used to illustrate the present invention and not to limit the scope of the present invention. Modifications of various equivalent forms of the present invention by those skilled in the art all fall within the scope defined by the appended claims of this application.

[0038] Embodiment 1:

[0039] As Figure 1 , Figure 2 shown, a sootblowing system for the arch of a coal-fired boiler provided in this embodiment includes the following steps:

[0040] Step 1, an acoustic wave measuring device measures the temperature and flow field data of the arch and the horizontal flue inside the boiler, and the measuring positions are as Figure 2 shown;

[0041] Step 2: Acquire real-time boiler operating data and coal quality analysis data. The acquired data includes historical values of various boiler operating parameters, including but not limited to boiler load, coal calorific value analysis, composition analysis, boiler coal usage, boiler temperature distribution, boiler pressure, and boiler resistance. The acquired coal quality analysis data includes parameters such as volatile matter, moisture, ash content, and calorific value.

[0042] Step 3: Use the obtained real-time operation data as the input of the neural network model to obtain the optimal soot blowing method corresponding to the sonic soot blower or the laminated disc jet soot blower; set the soot thickness alarm value according to the actual design and operation of the boiler, set the second-level alarm when the average soot thickness reaches 1.0 cm, and the first-level alarm when the average soot thickness reaches 2.5 cm. When the first-level alarm occurs, manual intervention is required to strengthen soot blowing to prevent the soot accumulation from worsening.

[0043] In this embodiment, to ensure that the input and output data of the neural network prediction model accurately reflect the system characteristics, the collected training data must be ergodic, compatible, and dense. Specifically, the data samples should cover all possible states of the system; similar inputs may correspond to different outputs in overlapping space; and the data sample density must be moderate to fully reflect the system characteristics. The complexity and degree of interference of the system determine the number of training samples. Due to the complexity and strong nonlinearity of the system, a large number of samples is required, but too many samples will weaken the model's ability to improve.

[0044] A flue gas soot blowing system is modeled using a dynamic neural network to establish a predictive model for the system. Since neural networks can infinitely approximate nonlinear performance, using neural network models such as LSTM to model the flue gas soot blowing system can effectively reduce the deviations that exist in the system's actual operation. The established flue gas soot blowing system predictive model is used to calculate a predicted value for the soot accumulation thickness in the flue gas soot blowing system, and this predicted value is used to control the soot blowing unit of the flue gas soot blowing system.

[0045] The present invention adopts a numerical comparison method to determine the operation mode of the soot blowing unit: the target value is compared with the predicted value. If the predicted value is greater than the target value and the difference between the two is greater, the corresponding soot blowing frequency and blowing volume will be greater; if the target value is greater than the predicted value, the soot blowing frequency and blowing volume will be reduced.

[0046] Figure 3It is a framework diagram of model predictive control. Among them, the measurable disturbance is the disturbance that can be measured by sensors in the actual system, which directly acts on the controlled object, and this variable is not expected to be output; the set value is the output target value, that is, the ash accumulation thickness; the manipulable variables are the soot blowing frequency and the soot blowing air volume of the flue gas soot blowing system, and its magnitude can be adjusted by the controller so that it acts on the target object to make the output reach the expected value; the unmeasurable disturbance has a certain impact on the target output value; the measured output is the concentration of sulfur dioxide in the flue gas measured at the outlet of the system, which can be used to evaluate whether the actual output value is accurate; the noise represents the factors affecting the measurement accuracy; the actual output value is the ash accumulation thickness at positions such as the horizontal flue and the flame deflecting angle.

[0047] Based on the above predictive control framework, a neural network predictive control block diagram is designed, including parts such as a reference model, data preprocessing, a neural network predictive control model, and a controlled object (see Figure 4 ).

[0048] Based on the principle of neural network predictive control, a block diagram of the control system principle is built, as shown in Figure 5 It shows, and mainly includes three parts: X1 signal input, X2 neural network model building, and X3 soot blowing control.

[0049] During the operation process, the results of the ANN are evaluated, and parameters such as R2, MSE, and RMSE are used to determine a model with better performance, selecting a high (R2) value, as well as a lower root mean square error value. And a lower root mean square error and mean square error. R2 indicates the degree of association between the model and the dependent variable, and the formula is as follows:

[0050]

[0051] Among them, N is the number of measurement data, Dem represents the average value of the actual data, Dp is the predicted value, and De is the actual value. (The same below)

[0052] The RMSE and MSE statistical methods are used for data evaluation. MSE is used as an index of the loss function to quantify the effectiveness of the training algorithm and detect outliers. RMSE is the square root of MSE and is used to evaluate whether the model is suitable for future trend analysis. The formulas are as follows:

[0053]

[0054] Step 4, use the obtained best soot blowing method to control the operation of the soot blower, and collect parameters such as the soot blowing pressure and soot blowing flow rate of the soot blowing medium corresponding to the soot blower in real time;

[0055] Step 5: Continuously feedback the parameters such as soot blowing pressure and soot blowing flow rate collected to the model for continuous optimization. Optimize the soot blowing mode of the soot blower according to the measured parameters to ensure the safe operation of the boiler system and the economic operation of the soot blowing system at the same time.

[0056] Embodiment 2: On the basis of Embodiment 1, a soot blowing system for the arch of a coal-fired boiler provided in this embodiment. In step 2, historical data of boiler operation is obtained. The historical data includes boiler load, coal calorific value analysis, component analysis, boiler coal consumption, temperature distribution in the boiler, pressure in the boiler, resistance in the boiler, etc. After pre-optimizing and processing the relevant data in the communication module, the data is transmitted to the neural network model together with the measurement data obtained in step 1.

[0057] In step 3, neural network methods such as LSTM are used to obtain relevant monitoring and operation models, and the operation of the soot blower is adjusted by adopting the best operation mode.

[0058] Embodiment 3:

[0059] On the basis of Embodiment 1, the acoustic wave measurement system in step 1 mainly includes modules such as a compressed air system, an acoustic wave duct, an acoustic wave transmitter, an acoustic wave sensor, and an amplifier. The measured data is sent to the signal conditioning system, and the information after being converted by the A / D conversion module is processed and transformed by the control system to obtain relevant temperature and flow field data, and at the same time, relevant acoustic wave emission control information is fed back to the acoustic wave measurement system.

[0060] Embodiment 4:

[0061] On the basis of Embodiment 1, the soot blower in Step 3 uses a laminated disc jet soot blower to blow soot on the furnace arch of the boiler. The laminated disc jet soot blower includes components such as a jet nozzle, a laminated disc, a driving device, and a compressed air system. The core device, the laminated disc, is composed of two to five laminated discs containing soot blowing holes. Each laminated disc contains 6-12 Laval jet soot blowing flat holes. Compressed air is ejected in all directions to form a soot blowing jet. Compressed air with a certain pressure and flow rate rolls up the accumulated ash, destroys the sedimentation equilibrium state of the accumulated ash, forces the accumulated ash to become a turbulent flow and a swirling flow state, and flows away following the flow of the flue gas, thereby achieving the purpose of removing the accumulated ash. According to the boiler conditions and the layout position of the soot blower, etc., anti-blocking settings for the soot blowing holes of the laminated disc are set, and the relative size of the hole diameter is controlled. Generally, the upper several layers are set for anti-blocking settings, and the flow resistance is larger than that of the soot blowing holes in the lower layers. In the non-working state of the laminated soot blower, the sedimented ash in the flue gas will enter the soot blower through the soot blowing holes. When the sedimented ash blocks the soot blowing holes in the upper and lower layers, the pressure increases when the soot blower starts. Since the lower soot blowing holes are blocked and the flow resistance increases, the flow resistance of the upper soot blowing holes becomes smaller instead. At this time, the compressed air sucks and ejects the dust in the soot blower from the upper soot blowing holes, continuously cleaning the dust in the soot blower until the lower laminated soot blowing holes are blown through, thereby achieving the purpose of self-cleaning the accumulated ash inside the soot blower. The jet holes are evenly distributed along the circumference of the laminated disc, and the gas working pressure is preferably 0.05-1.0 Mpa according to the boiler and the actual operating conditions.

Claims

1. A soot blowing system for the arch of a coal-fired boiler, characterized in that: Obtain the real-time operation data of the boiler, and set a series of acoustic wave transceiver devices at appropriate positions inside the boiler to measure the temperature and flow field conditions near the reheat furnace arch and in the horizontal flue in real time; monitor and predict the ash accumulation conditions of the reheat furnace arch and the horizontal flue according to the flow field and temperature changes, and construct a soot blower operation model based on the actual operation historical data and operation conditions of the soot blowing system, and adjust the opening and operation mode of the soot blower in real time to optimize the soot blowing cycle, the time of each soot blowing, and the soot blowing intensity; further feedback the soot blower operation model to the soot blowing system according to the historical data of the actually operating boiler, the data measured by the acoustic wave measuring device, and the historical data of the soot blower operation, etc., to optimize the operation of the soot blowing system.

2. The soot blowing system for the arch of a coal-fired boiler according to claim 1, characterized in that, Obtain the historical values of various parameters of the boiler operation, including but not limited to the boiler load, coal calorific value analysis, component analysis, boiler coal consumption, temperature distribution inside the boiler, pressure inside the boiler, and resistance inside the boiler, etc., and also include the temperature and flow field data measured at positions such as the reheat furnace arch and the horizontal flue obtained by using the acoustic wave measuring device. Process the collected data, and use parameters such as the soot blowing cycle, the time of each soot blowing, and the soot blowing intensity, and take the safe and economic operation of the boiler and the economic operation of the soot blower system as the goals to construct an artificial intelligence control model of the neural network.

3. A soot blowing system for the arch of a coal-fired boiler according to claim 1, characterized in that, The soot blower used is an acoustic wave soot blower or a laminated disc jet soot blower, and the soot blowing mode is adjusted in real time according to the temperature, pressure and other parameters collected at positions such as the horizontal flue and the reheat furnace arch according to the preset soot blowing cycle, soot blowing interval, soot blowing mode, etc.

4. A sootblowing system for the arch of a coal-fired boiler according to claim 1, wherein Use the acoustic wave signals between the horizontal flue and the reheat furnace arch of the boiler collected by the set acoustic wave transceiver device, and through mathematical methods such as correlation function processing, measure the temperature and flow field conditions near the horizontal flue and the reheat furnace arch, identify the ash accumulation conditions of the reheat furnace arch and the horizontal flue, and set appropriate soot blowing intervals and intensities according to the historical operation data, and set ash accumulation degree alarm measures. When the average ash accumulation thickness reaches 1.0 cm according to the flow field measurement situation, a secondary alarm is given, and when the average ash accumulation thickness reaches 2.5 cm, a primary alarm is given.

5. A sootblowing system for the arch of a coal-fired boiler according to claim 1, wherein, Obtain the historical data of the operation parameters of the acoustic wave soot blower or the laminated disc jet soot blower, summarize the obtained historical data and the data obtained from the boiler operation, etc., and use neural network methods such as BP, ANN, FNN, CNN, RNN or LSTM, and set goals such as ensuring the safe operation of the boiler, preventing ash accumulation on the reheat furnace arch of the boiler, and the economic operation of the soot blowing system, etc., to obtain an intelligent control model of the ash accumulation system (including but not limited to early warning, prediction model, abnormal monitoring, optimal soot blowing model, etc.) for the safe and economic operation of the soot blower..

6. The soot blowing system for the arch of a coal-fired boiler according to claim 1, wherein, Including: A data boiler operation data acquisition unit for acquiring relevant real-time operation data of the boiler operation; The acoustic wave temperature and flow field measurement unit measures the temperature and flow field conditions near the horizontal flue and the retort angle of the boiler; the neural network data processing unit uses neural network methods such as LSTM to obtain relevant monitoring, operation and other models; the soot blower system control and alarm unit is used to control the operation mode of the soot blower, such as the operation cycle, the length of the operation time, etc., and adjusts the operation of the soot blower by adopting the best operation mode; the soot blowing unit includes relevant soot blower components such as acoustic soot blowers or laminated disc jet soot blowers, as well as relevant pipelines, valves, etc.

7. A sootblowing system for the arch of a coal-fired boiler according to claim 6, characterized in that, The soot blower system control and alarm unit includes a system control alarm module and a communication module.

8. The soot blowing unit of a retort angle soot blowing system for a coal-fired boiler according to claim 6 is an acoustic soot blower or a laminated disc jet soot blower. The acoustic soot blower includes components such as an acoustic wave generator, a compressed air system, an acoustic wave duct, and an acoustic wave emitter head. The laminated disc jet soot blower includes components such as a jet nozzle, a laminated disc, a driving device, and a compressed air system.

9. The acoustic wave temperature and flow field measurement unit of a retort angle soot blowing system for a coal-fired boiler according to claim 6 includes an acoustic wave measurement system, a signal conditioning system, a control sub-unit, etc. The control sub-unit includes an A / D conversion module, a communication module, a control module, etc.

10. A computer device, characterized in that, Comprising: a processor for executing a computer program; a computer-readable storage medium storing a computer program which, when executed by the processor, is capable of implementing the method according to any one of claims 1 to 9.

11. A computer-readable storage medium storing a computer program, characterized in that, The computer program, when executed by the processor, implements the method according to any one of claims 1-9.

12. A computer program product, characterized in that, The computer program product contains a computer program which, when executed by the processor, is capable of implementing the method according to any one of claims 1 to 9.

Images