Optimization method for soot blowing steam pressure control in boiler steam soot blowing system

Abstract

The invention provides an optimization method for soot blowing steam pressure control in a boiler steam soot blowing system, and relates to the technical field of boiler steam soot blowing, and the optimization method comprises the following steps: obtaining real-time operation data of a target boiler, and determining a soot blowing principle based on a real-time soot blowing demand so as to determine a soot blowing sequence and a soot blowing period; boiler steam soot blowing is conducted on the basis of the soot blowing sequence and the soot blowing period, parameter changes are obtained in real time, and a first parameter change set is obtained; acquiring a DCS (Distributed Control System) of the target boiler, and optimizing the DCS in combination with PID (Proportion Integration Differentiation) control logic and pressure change trend prediction to obtain a first optimized DCS; determining a first optimization scheme of the target boiler based on the first optimization DCS system and the first parameter change set, and performing soot blowing steam pressure control to obtain a first control result; boiler operation parameters in the soot blowing steam pressure control process are obtained in real time, and therefore feedback adjustment is conducted on the first optimization scheme. The stability of soot blowing steam pressure can be remarkably improved, and the reliability of the system is enhanced.

Description

Technical Field

[0001] The invention relates to the technical field of boiler steam sootblowing, and in particular to an optimization method for controlling sootblowing steam pressure in a boiler steam sootblowing system. Background Art

[0002] At present, with the continuous increase in the capacity of coal-fired power station boilers, the heat load of the furnace section, the heat load of the water-cooled wall, the maximum temperature in the furnace, and the flue gas temperature in the convection heating surface area are constantly increasing, and the slagging and dust accumulation problems on the heating surface are becoming increasingly prominent. The steam soot blowing equipment is to solve such problems. It uses the blowing effect of high-pressure steam to remove the dust and slagging on the heating surface. The technology is relatively mature, the soot blowing time is short, and the effect is good. It has been widely used in thermal power plants.

[0003] Sootblowing steam pressure is an important parameter in the sootblowing system and must meet a certain range. If the pressure of the sootblower is too high, the risk of wear and damage to the sootblower may increase, and the service life of the sootblower and the boiler may be shortened; if the pressure of the sootblower is too low, the sootblower cleaning effect may be poor, which directly affects the heat transfer efficiency and normal operation of the boiler.

[0004] The current boiler sootblowing steam pressure control system strategy adopts a single-loop feedback control system, which consists of a controlled object, a pressure measurement and transmission device, a PID controller and a sootblowing regulating valve. The deviation between the measured value and the set value of the steam sootblowing pressure is introduced into the conventional PID function block, and the steam pressure control function is optimized by optimizing the P and I parameters in the PID function block, resulting in a simple regulation function and a general regulation effect.

[0005] Therefore, the present invention provides a method for optimizing the sootblowing steam pressure control in a boiler steam sootblowing system. Summary of the invention

[0006] The present invention provides an optimization method for controlling the sootblowing steam pressure in a boiler steam sootblowing system, which is used to realize the integration of PID and DCS systems and optimize the system in combination with pressure change trend prediction, thereby significantly improving the stability of the sootblowing steam pressure, enhancing the system reliability and reducing the economic loss.

[0007] The present invention provides a method for optimizing sootblowing steam pressure control in a boiler steam sootblowing system, comprising:

[0008] Step 1: Acquire the real-time operation data of the target boiler, and determine the sootblowing principle based on the real-time sootblowing demand of the target boiler, thereby determining the sootblowing sequence and sootblowing cycle of the target boiler;

[0009] Step 2: performing boiler steam sootblowing based on the sootblowing sequence and sootblowing cycle of the target boiler, and obtaining real-time parameter changes of the boiler steam sootblowing process in real time to obtain a first parameter change set;

[0010] Step 3: Obtain the DCS system of the target boiler, and optimize the DCS system by combining PID control logic and pressure change trend prediction to obtain the first optimized DCS system;

[0011] Step 4: Determine a first optimization scheme for the target boiler based on the first optimization DCS system and the first parameter change set, thereby controlling the sootblowing steam pressure of the target boiler to obtain a first control result;

[0012] Step 5: Obtain boiler operating parameters of the sootblowing steam pressure control process in real time, and perform data analysis to make feedback adjustments to the first optimization scheme.

[0013] According to the present invention, real-time operation data of a target boiler is obtained, and a sootblowing principle is determined based on the real-time sootblowing demand of the target boiler, thereby determining a sootblowing sequence and a sootblowing cycle of the target boiler, including:

[0014] Step 11: Collecting real-time operation data of the target boiler in real time based on preset sensors and boiler monitoring equipment;

[0015] Step 12: Determine the real-time sootblowing requirement of the target boiler by combining the real-time operation data with the boiler parameters of the target boiler;

[0016] Step 13: based on the real-time sootblowing demand, select the corresponding sootblowing principle from the sootblowing database, so as to obtain the first sootblowing principle of the target boiler;

[0017] Step 14: Based on the first sootblowing principle and the real-time operation status of the target boiler, the sootblowing sequence and sootblowing cycle of the target boiler are formulated.

[0018] According to the sootblowing sequence and sootblowing cycle of the target boiler provided by the present invention, boiler steam sootblowing is performed, and real-time parameter changes of the boiler steam sootblowing process are obtained in real time to obtain a first parameter change set, including:

[0019] Step 21: starting the sootblowing equipment to perform boiler steam sootblowing on the target boiler based on the sootblowing sequence and sootblowing cycle of the target boiler;

[0020] Step 22: real-time monitoring of boiler operating parameters of the target boiler during the boiler steam soot blowing process;

[0021] Among them, boiler operating parameters include steam pressure, temperature, and flow rate;

[0022] Step 23: Based on the parameter change values ​​of the boiler operating parameters during the boiler steam sootblowing process, a first parameter change set of the target boiler is obtained.

[0023] According to the DCS system of the target boiler provided by the present invention, the DCS system is optimized by combining the PID control logic and the pressure change trend prediction to obtain a first optimized DCS system, including:

[0024] Step 31: Obtain the DCS system of the target boiler and add PID control to the DCS system;

[0025] Step 32: Acquire the real-time operation status of the target boiler, thereby adjusting the PID parameters in real time to obtain the steam pressure range of the target boiler;

[0026] Step 33: Obtain the historical operating parameters of the target boiler, and extract the corresponding machine learning algorithm from the algorithm database based on the boiler parameters of the target boiler, build a pressure change trend prediction model for the target boiler, and integrate it into the DCS system to obtain the first optimized DCS system.

[0027] According to the present invention, the historical operating parameters of the target boiler are obtained, and the corresponding machine learning algorithm is extracted from the algorithm database based on the boiler parameters of the target boiler, a pressure change trend prediction model of the target boiler is constructed, and integrated into the DCS system to obtain a first optimized DCS system, including:

[0028] Step 331: Acquire historical operating parameters of the target boiler, and classify the historical operating parameters according to parameter types to obtain a first classification parameter set;

[0029] Step 332: sorting each sub-parameter set in the first classification parameter set according to the time series to obtain a second sub-parameter set, thereby obtaining a second classification parameter set of the target boiler;

[0030] Step 333: performing data processing on each operating parameter in the second classification parameter set to obtain a first processing parameter set;

[0031] Step 334: extracting a machine learning algorithm matching the target boiler from an algorithm database based on the boiler parameters of the target boiler as an initial learning algorithm;

[0032] Step 335: obtaining an initial pressure change trend prediction model of the target boiler based on the initial learning algorithm, and performing model training based on historical operating parameters to obtain a pressure change trend prediction model;

[0033] Step 336: Integrate the pressure change trend prediction model into the DCS system based on a preset programming program to obtain a first integrated model;

[0034] Step 337: randomly extracting a historical operating parameter at any historical moment from the historical operating parameters as a first verification parameter, and inputting the first verification parameter into a first integrated model to obtain a first prediction result;

[0035] Step 338: determining whether the first prediction result is consistent with the boiler operation result corresponding to the current historical moment;

[0036] If they are consistent, the prediction result is judged to be accurate, and the first integrated model is integrated into the DCS system to obtain a first optimized DCS system;

[0037] Otherwise, it is judged that the prediction result is inaccurate, and the model needs to be retrained to obtain the second integrated model which is integrated into the DCS system to obtain the first optimized DCS system.

[0038] According to the present invention, a first optimization scheme for a target boiler is determined based on a first optimization DCS system and a first parameter change set, so as to control the sootblowing steam pressure of the target boiler and obtain a first control result, including:

[0039] Step 41: formulating a first optimization scheme for the target boiler based on the first optimization DCS system and the first parameter change set;

[0040] Step 42: According to the first optimization scheme, the sootblowing steam pressure of the target boiler is controlled using the first optimization DCS system to obtain a first control result.

[0041] According to the present invention, the boiler operating parameters of the sootblowing steam pressure control process are obtained in real time, and data analysis is performed to feedback and adjust the first optimization scheme, including:

[0042] When the sootblowing steam pressure of the target boiler is controlled, the boiler operation parameters of the target boiler are obtained in real time, so as to judge the change of the sootblowing steam pressure in real time;

[0043] If the sootblowing steam pressure change is within the steam pressure range, it is judged that the sootblowing steam pressure control is qualified;

[0044] Otherwise, it is determined that the sootblowing steam pressure control is unqualified, and feedback adjustment is required to the first optimization scheme.

[0045] Feedback adjustment of the first optimization scheme provided by the present invention includes:

[0046] Performing a first comparison between the sootblowing steam pressure change and the steam pressure range, thereby extracting the sootblowing steam pressure change that exceeds the steam pressure range, and obtaining a first pressure change set;

[0047] Performing a second comparison based on each sootblowing steam pressure change value in the first pressure change set and a corresponding steam pressure value in the steam pressure range to obtain a second change value set;

[0048] Determine a first adjustment plan for the target boiler based on the difference between each sootblowing steam pressure change value and the corresponding steam pressure value in the second change value set and the type of the corresponding sootblowing steam pressure change situation;

[0049] The first optimization scheme is adjusted based on the first adjustment scheme, and the feasibility of the adjusted scheme is determined. If the adjusted scheme is feasible, the adjusted scheme is used as the second optimization scheme of the target boiler to control the sootblowing steam pressure of the target boiler.

[0050] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention provides an optimization method for controlling the sootblowing steam pressure in a boiler steam sootblowing system, which significantly improves the stability of the sootblowing steam pressure, enhances the system reliability, and reduces economic losses by realizing the integration of PID and DCS systems and combining pressure change trend prediction for system optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 The present invention provides a flowchart of a method for optimizing sootblowing steam pressure control in a boiler steam sootblowing system. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Embodiment 1:

[0055] The embodiment of the present invention provides a method for optimizing the sootblowing steam pressure control in a boiler steam sootblowing system. Figure 1 As shown, including:

[0056] Step 1: Acquire the real-time operation data of the target boiler, and determine the sootblowing principle based on the real-time sootblowing demand of the target boiler, thereby determining the sootblowing sequence and sootblowing cycle of the target boiler;

[0057] Step 2: performing boiler steam sootblowing based on the sootblowing sequence and sootblowing cycle of the target boiler, and obtaining real-time parameter changes of the boiler steam sootblowing process in real time to obtain a first parameter change set;

[0058] Step 3: Obtain the DCS system of the target boiler, and optimize the DCS system by combining PID control logic and pressure change trend prediction to obtain the first optimized DCS system;

[0059] Step 4: Determine a first optimization scheme for the target boiler based on the first optimization DCS system and the first parameter change set, thereby controlling the sootblowing steam pressure of the target boiler to obtain a first control result;

[0060] Step 5: Obtain boiler operating parameters of the sootblowing steam pressure control process in real time, and perform data analysis to make feedback adjustments to the first optimization scheme.

[0061] In this embodiment, the target boiler refers to a specific boiler that needs to be operated or optimized.

[0062] In this embodiment, the real-time operation data is the data currently being generated by the boiler, such as temperature, pressure, flow rate, etc. These data change in real time and reflect the current state of the boiler.

[0063] In this embodiment, the soot blowing requirement is that during the operation of the boiler, ash will be generated due to the combustion of fuel, and the ash will adhere to the heating surface of the boiler, affecting the thermal efficiency of the boiler. The soot blowing requirement is to determine whether the soot blowing operation is required based on the accumulation of ash on the heating surface of the boiler.

[0064] In this embodiment, the sootblowing principle is a series of guiding principles for sootblowing operations, such as the frequency and intensity of sootblowing, formulated based on the sootblowing requirements of the boiler.

[0065] In this embodiment, the sootblowing sequence refers to the order in which sootblowing is performed on each heating surface of the boiler, and the sootblowing cycle refers to the time interval between two sootblowing operations.

[0066] In this embodiment, boiler steam soot blowing uses steam as a medium to blow the heating surface of the boiler to remove ash.

[0067] In this embodiment, the real-time parameter change set is the changes of various parameters (such as temperature, pressure, etc.) recorded in real time during the boiler steam soot blowing process. These data are collected to form the real-time parameter change set.

[0068] In this embodiment, the DCS system is a computer system used for industrial process control, which connects multiple control stations through a network to achieve centralized monitoring and decentralized control of the entire industrial process.

[0069] In this embodiment, PID control logic is a commonly used control algorithm, which adjusts the output of the controller to make the output of the system as close to the set value as possible.

[0070] In this embodiment, the pressure change trend prediction is based on historical data and current data to predict the change trend of boiler steam pressure in the future period of time.

[0071] In this embodiment, the first optimized DCS system is an improved system obtained by optimizing the DCS system, and has better control performance and stability.

[0072] In this embodiment, the first optimization scheme is an optimization scheme for the target boiler formulated based on the optimized DCS system and the real-time parameter change set.

[0073] In this embodiment, the sootblowing steam pressure control is to control the steam pressure during the boiler steam sootblowing process to ensure the sootblowing effect.

[0074] In this embodiment, the first control result is the actual operating state or parameter change of the boiler after the sootblowing steam pressure control is performed.

[0075] In this embodiment, the feedback adjustment is to adjust the first optimization scheme according to the boiler operating parameters and data analysis results obtained in real time to further improve the optimization effect.

[0076] The beneficial effects of the above technical solution are: by realizing the integration of PID and DCS systems and optimizing the system in combination with pressure change trend prediction, the stability of sootblowing steam pressure is significantly improved, the system reliability is enhanced, and economic losses are reduced.

[0077] Embodiment 2:

[0078] Based on Example 1, the soot blowing sequence and soot blowing cycle of the target boiler are determined, including:

[0079] Step 11: Collecting real-time operation data of the target boiler in real time based on preset sensors and boiler monitoring equipment;

[0080] Step 12: Determine the real-time sootblowing requirement of the target boiler by combining the real-time operation data with the boiler parameters of the target boiler;

[0081] Step 13: based on the real-time sootblowing demand, select the corresponding sootblowing principle from the sootblowing database, so as to obtain the first sootblowing principle of the target boiler;

[0082] Step 14: Based on the first sootblowing principle and the real-time operation status of the target boiler, the sootblowing sequence and sootblowing cycle of the target boiler are formulated.

[0083] In this embodiment, the target boiler refers to a specific boiler that needs to be operated or optimized.

[0084] In this embodiment, the real-time operation data is the data currently being generated by the boiler, such as temperature, pressure, flow rate, etc. These data change in real time and reflect the current state of the boiler.

[0085] In this embodiment, boiler parameters refer to various factors that need to be considered in boiler design and operation, such as boiler capacity, pressure, temperature, fuel type, etc.

[0086] In this embodiment, the soot blowing requirement is that during the operation of the boiler, ash will be generated due to the combustion of fuel, and the ash will adhere to the heating surface of the boiler, affecting the thermal efficiency of the boiler. The soot blowing requirement is to determine whether the soot blowing operation is required based on the accumulation of ash on the heating surface of the boiler.

[0087] In this embodiment, the sootblowing principle is a series of guiding principles for sootblowing operations, such as the frequency and intensity of sootblowing, formulated based on the sootblowing requirements of the boiler.

[0088] In this embodiment, the sootblowing sequence refers to the order in which sootblowing is performed on each heating surface of the boiler, and the sootblowing cycle refers to the time interval between two sootblowing operations.

[0089] The beneficial effect of the above technical solution is: by determining the sootblowing sequence and sootblowing cycle of the target boiler, thereby combining it with the DCS system and optimizing the system in combination with the pressure change trend prediction, the stability of the sootblowing steam pressure is significantly improved.

[0090] Embodiment 3:

[0091] Based on Example 2, real-time parameter changes of the boiler steam sootblowing process are obtained in real time to obtain a first parameter change set, including:

[0092] Step 21: starting the sootblowing equipment to perform boiler steam sootblowing on the target boiler based on the sootblowing sequence and sootblowing cycle of the target boiler;

[0093] Step 22: real-time monitoring of boiler operating parameters of the target boiler during the boiler steam soot blowing process;

[0094] Among them, boiler operating parameters include steam pressure, temperature, and flow rate;

[0095] Step 23: Based on the parameter change values ​​of the boiler operating parameters during the boiler steam sootblowing process, a first parameter change set of the target boiler is obtained.

[0096] In this embodiment, boiler steam soot blowing uses steam as a medium to blow the heating surface of the boiler to remove ash.

[0097] In this embodiment, the soot blowing equipment refers to equipment used to perform boiler soot blowing operations, generally including a soot blower, a steam pipe, a control system, etc. The soot blowing equipment removes the soot accumulated on the heating surface by spraying steam or compressed air onto the heating surface of the boiler, thereby improving the thermal efficiency of the boiler.

[0098] In this embodiment, boiler steam soot blowing is a common boiler maintenance operation, which removes soot by spraying steam onto the boiler heating surface. Steam soot blowing can effectively improve the thermal efficiency of the boiler, reduce fuel consumption, and also help to extend the service life of the boiler.

[0099] In this embodiment, the boiler operating parameters refer to various parameters involved in the operation of the boiler, and these parameters reflect the operating status and performance of the boiler.

[0100] In this embodiment, the first parameter change set refers to a set of data obtained based on the change values ​​of boiler operating parameters (such as steam pressure, temperature, flow) monitored in real time during the boiler steam soot blowing process, reflecting the impact of the soot blowing operation on the boiler operating state.

[0101] The beneficial effect of the above technical solution is: by determining the parameter changes of the target boiler, the steam pressure range is judged, and then combined with the DCS system control, the stability of the sootblowing steam pressure is significantly improved.

[0102] Embodiment 4:

[0103] Based on Example 3, a first optimized DCS system is obtained, including:

[0104] Step 31: Obtain the DCS system of the target boiler and add PID control to the DCS system;

[0105] Step 32: Acquire the real-time operation status of the target boiler, thereby adjusting the PID parameters in real time to obtain the steam pressure range of the target boiler;

[0106] Step 33: Obtain the historical operating parameters of the target boiler, and extract the corresponding machine learning algorithm from the algorithm database based on the boiler parameters of the target boiler, build a pressure change trend prediction model for the target boiler, and integrate it into the DCS system to obtain the first optimized DCS system.

[0107] In this embodiment, the DCS system is a computer system used for industrial process control, which connects multiple control stations through a network to achieve centralized monitoring and decentralized control of the entire industrial process.

[0108] In this embodiment, PID control is a commonly used control algorithm, which adjusts the output of the controller to make the output of the system as close to the set value as possible.

[0109] In this embodiment, the steam pressure range refers to the pressure fluctuation range allowed in the boiler steam system. Steam pressure is one of the important indicators of boiler operation, which directly affects the thermal efficiency and safety of the boiler. Through PID control, the steam pressure can be accurately adjusted to keep it within the set range.

[0110] In this embodiment, the historical operating parameters refer to the data recorded during the operation of the boiler in the past period of time, including the values ​​and change trends of key parameters such as steam pressure, temperature, flow rate, etc.

[0111] In this embodiment, the pressure change trend prediction is based on historical data and current data to predict the change trend of boiler steam pressure in the future period of time.

[0112] In this embodiment, the pressure change trend prediction model is a model built based on a machine learning algorithm, which is used to predict the future change trend of boiler steam pressure. By learning and analyzing historical operating parameters, the law and pattern of steam pressure change are discovered, thereby achieving accurate prediction of future steam pressure.

[0113] In this embodiment, the first optimized DCS system is an improved system obtained by optimizing the DCS system, and has better control performance and stability.

[0114] The beneficial effects of the above technical solution are: by realizing the integration of PID and DCS systems and optimizing the system in combination with pressure change trend prediction, the stability of sootblowing steam pressure is significantly improved and the system reliability is enhanced.

[0115] Embodiment 5:

[0116] Based on the fourth embodiment, the first optimized DCS system is obtained by integrating it into the DCS system, including:

[0117] Step 331: Acquire historical operating parameters of the target boiler, and classify the historical operating parameters according to parameter types to obtain a first classification parameter set;

[0118] Step 332: sorting each sub-parameter set in the first classification parameter set according to the time series to obtain a second sub-parameter set, thereby obtaining a second classification parameter set of the target boiler;

[0119] Step 333: performing data processing on each operating parameter in the second classification parameter set to obtain a first processing parameter set;

[0120] Step 334: extracting a machine learning algorithm matching the target boiler from an algorithm database based on the boiler parameters of the target boiler as an initial learning algorithm;

[0121] Step 335: obtaining an initial pressure change trend prediction model of the target boiler based on the initial learning algorithm, and performing model training based on historical operating parameters to obtain a pressure change trend prediction model;

[0122] Step 336: Integrate the pressure change trend prediction model into the DCS system based on a preset programming program to obtain a first integrated model;

[0123] Step 337: randomly extracting a historical operating parameter at any historical moment from the historical operating parameters as a first verification parameter, and inputting the first verification parameter into a first integrated model to obtain a first prediction result;

[0124] Step 338: determining whether the first prediction result is consistent with the boiler operation result corresponding to the current historical moment;

[0125] If they are consistent, the prediction result is judged to be accurate, and the first integrated model is integrated into the DCS system to obtain a first optimized DCS system;

[0126] Otherwise, it is judged that the prediction result is inaccurate, and the model needs to be retrained to obtain the second integrated model which is integrated into the DCS system to obtain the first optimized DCS system.

[0127] In this embodiment, the first classification parameter set is a parameter set obtained by classifying the historical operating parameters according to parameter types (such as steam pressure, temperature, flow rate, etc.).

[0128] In this embodiment, the second sub-parameter set and the second classification parameter set are obtained by sorting each sub-parameter set (i.e., parameters of the same type) according to the time series on the basis of the first classification parameter set. The set of all second sub-parameter sets constitutes the second classification parameter set. Time series sorting helps to capture the changing trend of parameters over time.

[0129] In this embodiment, the first processing parameter set is a parameter set obtained after data processing (such as denoising, normalization, smoothing, etc.) is performed on each operating parameter in the second classification parameter set. Data processing is an important step before building a machine learning model, which helps to improve the prediction performance of the model.

[0130] In this embodiment, the initial learning algorithm is a machine learning algorithm extracted from an algorithm database and matching the target boiler.

[0131] In this embodiment, the initial pressure change trend prediction model is a pressure change trend prediction model constructed based on an initial learning algorithm and a first processing parameter set.

[0132] In this embodiment, the pressure change trend prediction model is an initial pressure change trend prediction model after historical operation parameter training. This model can predict the future change trend of boiler steam pressure.

[0133] In this embodiment, the first integrated model refers to a model obtained by integrating the pressure change trend prediction model into the DCS system. The integrated model realizes the seamless connection between the prediction function and the control system.

[0134] In this embodiment, the first verification parameter is an operating parameter of any historical moment randomly extracted from historical operating parameters.

[0135] In this embodiment, the first prediction result is a prediction result obtained after the first verification parameter is input into the first integrated model.

[0136] In this embodiment, the boiler operation result is the actual operation result of the boiler at a historical moment corresponding to the first verification parameter.

[0137] In this embodiment, the first optimized DCS system is an optimized system obtained by integrating the verified integrated model into the DCS system.

[0138] In this embodiment, model training is a process of training an initial learning algorithm using historical operating parameters to optimize model parameters and improve prediction performance.

[0139] In this embodiment, the second integrated model is an integrated model obtained by retraining the model when the prediction result is inaccurate. This model may be trained based on different learning algorithms or more abundant historical operating parameters.

[0140] The beneficial effects of the above technical solution are: by realizing the integration of PID and DCS systems and optimizing the system in combination with pressure change trend prediction, the stability of sootblowing steam pressure is significantly improved and the system reliability is enhanced.

[0141] Embodiment 6:

[0142] Based on Example 4, a first control result is obtained, including:

[0143] Step 41: formulating a first optimization scheme for the target boiler based on the first optimization DCS system and the first parameter change set;

[0144] Step 42: According to the first optimization scheme, the sootblowing steam pressure of the target boiler is controlled using the first optimization DCS system to obtain a first control result.

[0145] In this embodiment, the first optimization scheme is an optimization scheme for the target boiler formulated based on the optimized DCS system and the real-time parameter change set.

[0146] In this embodiment, the sootblowing steam pressure control is to control the steam pressure during the boiler steam sootblowing process to ensure the sootblowing effect.

[0147] In this embodiment, the first control result is the actual operating state or parameter change of the boiler after the sootblowing steam pressure control is performed.

[0148] The beneficial effect of the above technical solution is: by using the optimized DCS system to determine the optimization plan for optimization control, the stability of the sootblowing steam pressure is significantly improved, the system reliability is enhanced, and the economic loss is reduced.

[0149] Embodiment 7:

[0150] Based on Example 6, the boiler operating parameters of the sootblowing steam pressure control process are obtained in real time, and data analysis is performed to feedback and adjust the first optimization scheme, including:

[0151] When the sootblowing steam pressure of the target boiler is controlled, the boiler operation parameters of the target boiler are obtained in real time, so as to judge the change of the sootblowing steam pressure in real time;

[0152] If the sootblowing steam pressure change is within the steam pressure range, it is judged that the sootblowing steam pressure control is qualified;

[0153] Otherwise, it is determined that the sootblowing steam pressure control is unqualified, and feedback adjustment is required to the first optimization scheme.

[0154] In this embodiment, the boiler operating parameters include steam pressure, temperature, and flow rate.

[0155] In this embodiment, the feedback adjustment is to adjust the first optimization scheme according to the boiler operating parameters and data analysis results obtained in real time to further improve the optimization effect.

[0156] The beneficial effect of the above technical solution is: by real-time monitoring of the boiler operating parameters of the target boiler, timely feedback adjustment of the first optimization solution can be made, so as to make the sootblowing steam pressure control of the target boiler more timely and accurate, enhance system reliability and reduce economic losses.

[0157] Embodiment 8:

[0158] Based on Example 7, feedback adjustment is performed on the first optimization scheme, including:

[0159] Performing a first comparison between the sootblowing steam pressure change and the steam pressure range, thereby extracting the sootblowing steam pressure change that exceeds the steam pressure range, and obtaining a first pressure change set;

[0160] Performing a second comparison based on each sootblowing steam pressure change value in the first pressure change set and a corresponding steam pressure value in the steam pressure range to obtain a second change value set;

[0161] Determine a first adjustment plan for the target boiler based on the difference between each sootblowing steam pressure change value and the corresponding steam pressure value in the second change value set and the type of the corresponding sootblowing steam pressure change situation;

[0162] The first optimization scheme is adjusted based on the first adjustment scheme, and the feasibility of the adjusted scheme is determined. If the adjusted scheme is feasible, the adjusted scheme is used as the second optimization scheme of the target boiler to control the sootblowing steam pressure of the target boiler.

[0163] In this embodiment, the sootblowing steam pressure change refers to the change of steam pressure over time during the boiler sootblowing process. These changes may be caused by various factors, such as the operation of the sootblower, the change of boiler load, etc.

[0164] In this embodiment, the steam pressure range refers to the pressure fluctuation range allowed by the boiler steam system. The steam pressure must be maintained within this range to ensure safe and efficient operation of the boiler.

[0165] In this embodiment, the first comparison is a process of comparing the sootblowing steam pressure variation with the steam pressure range, with the purpose of finding out the sootblowing steam pressure variation that exceeds the steam pressure range.

[0166] In this embodiment, the first pressure change set is a set of sootblowing steam pressure change conditions that are beyond the steam pressure range and are obtained through the first comparison.

[0167] In this embodiment, the second comparison is a process of comparing each sootblowing steam pressure change value with a corresponding steam pressure value in the steam pressure range in the first pressure change set.

[0168] In this embodiment, the second change value set is a set of differences between the sootblowing steam pressure change values ​​obtained by the second comparison and the corresponding steam pressure values.

[0169] In this embodiment, the difference of the sootblowing steam pressure variation value refers to the specific difference between each sootblowing steam pressure variation value and the corresponding steam pressure value in the second variation value set. This difference indicates the actual deviation degree of the steam pressure.

[0170] In this embodiment, the types of sootblowing steam pressure change conditions are classified into different types according to the characteristics and causes of the sootblowing steam pressure change, which may include sudden pressure increase or decrease, continuous pressure fluctuation, etc.

[0171] In this embodiment, the first adjustment plan refers to a preliminary adjustment plan formulated based on the difference between each sootblowing steam pressure change value in the second change value set and the type of the corresponding sootblowing steam pressure change situation.

[0172] In this embodiment, the scheme adjustment is a process of modifying and improving the first optimization scheme based on the first adjustment scheme.

[0173] In this embodiment, the feasibility of the scheme is to judge whether the adjusted scheme is feasible, that is, whether it can be implemented without affecting the safe and stable operation of the boiler. This judgment is usually based on factors such as engineering experience, technical standards and safety regulations.

[0174] In this embodiment, the second optimization scheme is an optimization scheme for controlling the sootblowing steam pressure of the target boiler that is finally determined after scheme adjustment and feasibility judgment. This scheme aims to achieve accurate control of steam pressure and improve the operating efficiency and safety of the boiler.

[0175] The beneficial effect of the above technical solution is: by real-time monitoring of the boiler operating parameters of the target boiler, timely feedback adjustment of the first optimization solution can be made, so as to make the sootblowing steam pressure control of the target boiler more timely and accurate, enhance system reliability and reduce economic losses.

[0176] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing the sootblowing steam pressure control in a boiler steam sootblowing system, characterized in that: include: Step 1: Acquire the real-time operation data of the target boiler, and determine the sootblowing principle based on the real-time sootblowing demand of the target boiler, thereby determining the sootblowing sequence and sootblowing cycle of the target boiler; Step 2: performing boiler steam sootblowing based on the sootblowing sequence and sootblowing cycle of the target boiler, and obtaining real-time parameter changes of the boiler steam sootblowing process in real time to obtain a first parameter change set; Step 3: Obtain the DCS system of the target boiler, and optimize the DCS system by combining PID control logic and pressure change trend prediction to obtain the first optimized DCS system; Step 4: Determine a first optimization scheme for the target boiler based on the first optimization DCS system and the first parameter change set, thereby controlling the sootblowing steam pressure of the target boiler to obtain a first control result; Step 5: Obtain boiler operating parameters of the sootblowing steam pressure control process in real time, and perform data analysis to make feedback adjustments to the first optimization scheme.

2. The method for optimizing the sootblowing steam pressure control in a boiler steam sootblowing system according to claim 1, characterized in that: Obtain the real-time operation data of the target boiler, and determine the sootblowing principle based on the real-time sootblowing demand of the target boiler, so as to determine the sootblowing sequence and sootblowing cycle of the target boiler, including: Step 11: Collecting real-time operation data of the target boiler in real time based on preset sensors and boiler monitoring equipment; Step 12: Determine the real-time sootblowing requirement of the target boiler by combining the real-time operation data with the boiler parameters of the target boiler; Step 13: based on the real-time sootblowing demand, select the corresponding sootblowing principle from the sootblowing database, so as to obtain the first sootblowing principle of the target boiler; Step 14: Based on the first sootblowing principle and the real-time operation status of the target boiler, the sootblowing sequence and sootblowing cycle of the target boiler are formulated.

3. The method for optimizing the sootblowing steam pressure control in a boiler steam sootblowing system according to claim 2, characterized in that: Based on the sootblowing sequence and sootblowing cycle of the target boiler, steam sootblowing of the boiler is performed, and real-time parameter changes of the steam sootblowing process of the boiler are obtained in real time to obtain a first parameter change set, including: Step 21: starting the sootblowing equipment to perform boiler steam sootblowing on the target boiler based on the sootblowing sequence and sootblowing cycle of the target boiler; Step 22: real-time monitoring of boiler operating parameters of the target boiler during the boiler steam soot blowing process; Among them, boiler operating parameters include steam pressure, temperature, and flow rate; Step 23: Based on the parameter change values ​​of the boiler operating parameters during the boiler steam sootblowing process, a first parameter change set of the target boiler is obtained.

4. The method for optimizing the sootblowing steam pressure control in a boiler steam sootblowing system according to claim 3, characterized in that: The DCS system of the target boiler is obtained, and the DCS system is optimized by combining the PID control logic and the pressure change trend prediction to obtain the first optimized DCS system, including: Step 31: Obtain the DCS system of the target boiler and add PID control to the DCS system; Step 32: Acquire the real-time operation status of the target boiler, thereby adjusting the PID parameters in real time to obtain the steam pressure range of the target boiler; Step 33: Obtain the historical operating parameters of the target boiler, and extract the corresponding machine learning algorithm from the algorithm database based on the boiler parameters of the target boiler, build a pressure change trend prediction model for the target boiler, and integrate it into the DCS system to obtain the first optimized DCS system.

5. The method for optimizing the sootblowing steam pressure control in a boiler steam sootblowing system according to claim 4, characterized in that: The historical operating parameters of the target boiler are obtained, and the corresponding machine learning algorithm is extracted from the algorithm database based on the boiler parameters of the target boiler, and a pressure change trend prediction model of the target boiler is constructed and integrated into the DCS system to obtain the first optimized DCS system, including: Step 331: Acquire historical operating parameters of the target boiler, and classify the historical operating parameters according to parameter types to obtain a first classification parameter set; Step 332: sorting each sub-parameter set in the first classification parameter set according to the time series to obtain a second sub-parameter set, thereby obtaining a second classification parameter set of the target boiler; Step 333: performing data processing on each operating parameter in the second classification parameter set to obtain a first processing parameter set; Step 334: extracting a machine learning algorithm matching the target boiler from an algorithm database based on the boiler parameters of the target boiler as an initial learning algorithm; Step 335: obtaining an initial pressure change trend prediction model of the target boiler based on the initial learning algorithm, and performing model training based on historical operating parameters to obtain a pressure change trend prediction model; Step 336: Integrate the pressure change trend prediction model into the DCS system based on a preset programming program to obtain a first integrated model; Step 337: randomly extracting a historical operating parameter at any historical moment from the historical operating parameters as a first verification parameter, and inputting the first verification parameter into a first integrated model to obtain a first prediction result; Step 338: determining whether the first prediction result is consistent with the boiler operation result corresponding to the current historical moment; If they are consistent, the prediction result is judged to be accurate, and the first integrated model is integrated into the DCS system to obtain a first optimized DCS system; Otherwise, it is judged that the prediction result is inaccurate, and the model needs to be retrained to obtain the second integrated model which is integrated into the DCS system to obtain the first optimized DCS system.

6. The method for optimizing the sootblowing steam pressure control in a boiler steam sootblowing system according to claim 4, characterized in that: A first optimization scheme for the target boiler is determined based on the first optimization DCS system and the first parameter change set, so as to control the sootblowing steam pressure of the target boiler and obtain a first control result, including: Step 41: formulating a first optimization scheme for the target boiler based on the first optimization DCS system and the first parameter change set; Step 42: According to the first optimization scheme, the sootblowing steam pressure of the target boiler is controlled using the first optimization DCS system to obtain a first control result.

7. The method for optimizing the sootblowing steam pressure control in a boiler steam sootblowing system according to claim 6, characterized in that: The boiler operating parameters of the sootblowing steam pressure control process are obtained in real time, and data analysis is performed to provide feedback and adjust the first optimization scheme, including: When the sootblowing steam pressure of the target boiler is controlled, the boiler operation parameters of the target boiler are obtained in real time, so as to judge the change of the sootblowing steam pressure in real time; If the sootblowing steam pressure change is within the steam pressure range, it is judged that the sootblowing steam pressure control is qualified; Otherwise, it is determined that the sootblowing steam pressure control is unqualified, and feedback adjustment is required to the first optimization scheme.

8. The method for optimizing the sootblowing steam pressure control in a boiler steam sootblowing system according to claim 7, characterized in that: Feedback adjustment is made to the first optimization plan, including: Performing a first comparison between the sootblowing steam pressure change and the steam pressure range, thereby extracting the sootblowing steam pressure change that exceeds the steam pressure range, and obtaining a first pressure change set; Performing a second comparison based on each sootblowing steam pressure change value in the first pressure change set and a corresponding steam pressure value in the steam pressure range to obtain a second change value set; Determine a first adjustment plan for the target boiler based on the difference between each sootblowing steam pressure change value and the corresponding steam pressure value in the second change value set and the type of the corresponding sootblowing steam pressure change situation; The first optimization scheme is adjusted based on the first adjustment scheme, and the feasibility of the adjusted scheme is determined. If the adjusted scheme is feasible, the adjusted scheme is used as the second optimization scheme of the target boiler to control the sootblowing steam pressure of the target boiler.

Images