CN111237789A - Boiler soot blowing method, device and computer readable storage medium - Google Patents
Boiler soot blowing method, device and computer readable storage medium Download PDFInfo
- Publication number
- CN111237789A CN111237789A CN202010021122.4A CN202010021122A CN111237789A CN 111237789 A CN111237789 A CN 111237789A CN 202010021122 A CN202010021122 A CN 202010021122A CN 111237789 A CN111237789 A CN 111237789A
- Authority
- CN
- China
- Prior art keywords
- boiler
- soot blowing
- soot
- smoke temperature
- curve
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
- F23J—REMOVAL OR TREATMENT OF COMBUSTION PRODUCTS OR COMBUSTION RESIDUES; FLUES
- F23J1/00—Removing ash, clinker, or slag from combustion chambers
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
- F23J—REMOVAL OR TREATMENT OF COMBUSTION PRODUCTS OR COMBUSTION RESIDUES; FLUES
- F23J3/00—Removing solid residues from passages or chambers beyond the fire, e.g. from flues by soot blowers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
- F23J—REMOVAL OR TREATMENT OF COMBUSTION PRODUCTS OR COMBUSTION RESIDUES; FLUES
- F23J2700/00—Ash removal, handling and treatment means; Ash and slag handling in pulverulent fuel furnaces; Ash removal means for incinerators
- F23J2700/001—Ash removal, handling and treatment means
Abstract
The invention discloses a boiler soot blowing method, a boiler soot blowing device and a computer readable storage medium, and relates to the technical field of thermal power generation. The boiler soot blowing method comprises the following steps: acquiring characteristics representing the current boiler operation state; inputting the acquired characteristics into a pre-trained prediction model to obtain a predicted smoke temperature, wherein the prediction model is used for predicting the smoke temperature of the boiler under the clean working condition in the current boiler operation state; taking the difference between the actual smoke temperature of the current boiler and the predicted smoke temperature as the gray level; and determining an execution strategy of the soot blowing operation according to the gray scale. The method predicts the soot deposition of the current boiler according to the characteristics of the operating state of the boiler and determines a corresponding soot blowing execution strategy. Therefore, soot blowing control is realized in a data driving mode, the accuracy of soot deposition prediction is improved, and the soot blowing effect is optimized.
Description
Technical Field
The invention relates to the technical field of thermal power generation, in particular to a boiler soot blowing method, a boiler soot blowing device and a computer readable storage medium.
Background
Coal-fired power generation is one of the main power generation modes. The coal types used for combustion of many power plants have great difference with the designed coal types, which may cause serious ash deposition and slag bonding on the heating surface of the boiler, and bring great potential safety hazard to the normal operation of the unit. Therefore, large boilers are equipped with sootblowers to sootblow and remove slag. Most power plants develop on-time and quantitative soot blowing modes according to experience.
Disclosure of Invention
After the inventor analyzes the soot blowing mode, most power plants do not reasonably set up the soot blowing mode according to experience due to the lack of visual data of real-time soot deposition in the furnace. Insufficient sootblowing causes a reduction in the heat transfer performance of the heating surface, while excessive sootblowing results in waste of steam and erosion of the heating surface. Therefore, how to establish a soot deposition monitoring model and formulate a reasonable soot blowing scheme based on a real-time monitoring result becomes a difficult problem to be solved by a large-scale thermal power generating unit.
The embodiment of the invention aims to solve the technical problem that: how to provide an effective sootblowing scheme.
According to a first aspect of some embodiments of the present invention, there is provided a boiler soot blowing method, comprising: acquiring characteristics representing the current boiler operation state; inputting the acquired characteristics into a pre-trained prediction model to obtain a predicted smoke temperature, wherein the prediction model is used for predicting the smoke temperature of the boiler under the clean working condition in the current boiler operation state; taking the difference between the actual smoke temperature of the current boiler and the predicted smoke temperature as the gray level; and determining an execution strategy of the soot blowing operation according to the gray scale.
In some embodiments, the boiler soot blowing method further comprises: extracting features from historical data of the running state of the boiler under a clean working condition to form training data, wherein the marking value of the training data is the smoke temperature of the boiler; and training the machine learning model for regression prediction by adopting the training data to obtain a prediction model.
In some embodiments, the machine learning model is a random forest model, and the decision trees in the random forest model are classification and regression trees CART model.
In some embodiments, determining an execution strategy for a soot blowing operation based on the soot deposition includes: acquiring a curve of the accumulated ash degree along with the change of time and a threshold point on the curve; determining the time length between the time corresponding to the current integral gray scale and the time corresponding to the threshold point on the curve according to the curve; and determining an execution strategy for executing the soot blowing operation after the time length.
In some embodiments, there are multiple threshold points on the curve, each corresponding to a soot blowing mode; determining the duration between the time corresponding to the current integral gray scale and the time corresponding to each threshold point on the curve according to the curve; an execution strategy for executing the corresponding soot blowing operation after each time period is determined.
In some embodiments, the boiler soot blowing method further comprises: acquiring historical data of the operating state of the boiler, and marking the time of each historical data relative to the last soot blowing operation; and fitting the historical data by taking the time relative to the last soot blowing operation as an abscissa and the accumulated soot as an ordinate to obtain a curve of the accumulated soot changing along with the time.
In some embodiments, the boiler soot blowing method further comprises: determining a reduction value of the accumulated ash after executing the soot blowing operation according to the historical data of the operating state of the boiler; and determining the accumulated gray level threshold value according to the average value of the falling values of the accumulated gray levels so as to take the point corresponding to the accumulated gray level threshold value on the curve as a threshold point.
In some embodiments, the characteristics include one or more of boiler wall temperature, load, steam pressure, main steam temperature, reheat steam temperature, desuperheated water flow, furnace suction pressure, oxygen content, flue fly ash carbon content.
According to a second aspect of some embodiments of the present invention, there is provided a boiler sootblower comprising: a characteristic obtaining module configured to obtain a characteristic representing a current boiler operation state; the smoke temperature prediction module is configured to input the acquired characteristics into a pre-trained prediction model to obtain predicted smoke temperature, and the prediction model is used for predicting the smoke temperature of the boiler under the clean working condition in the current boiler operation state; a volume gray level determining module configured to take a difference between an actual smoke temperature of the current boiler and the predicted smoke temperature as a volume gray level; and the strategy determination module is configured to determine an execution strategy of the soot blowing operation according to the soot deposition degree.
According to a third aspect of some embodiments of the present invention, there is provided a boiler sootblower comprising: a memory; and a processor coupled to the memory, the processor configured to perform any of the foregoing boiler soot blowing methods based on instructions stored in the memory.
According to a fourth aspect of some embodiments of the present invention there is provided a computer readable storage medium having a computer program stored thereon, wherein the program when executed by a processor implements any of the boiler soot blowing methods described above.
Some embodiments of the above invention have the following advantages or benefits: the method predicts the soot deposition of the current boiler according to the characteristics of the operating state of the boiler and determines a corresponding soot blowing execution strategy. Therefore, soot blowing control is realized in a data driving mode, the accuracy of soot deposition prediction is improved, and the soot blowing effect is optimized.
Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 illustrates a flow diagram of a boiler soot blowing method according to some embodiments of the invention.
Fig. 2 exemplarily shows a smoke temperature change diagram, a boiler load change diagram, a degree of influence of soot deposition on smoke temperature, and a soot blowing operation execution diagram.
FIG. 3 is a schematic diagram of the change of the smoke temperature at the inlet of the low-temperature superheater, a schematic diagram of the predicted change of the smoke temperature, a schematic diagram of the change of the boiler load, a schematic diagram of the influence degree of the soot deposition on the smoke temperature and a schematic diagram of the soot blowing operation execution.
Fig. 4 exemplarily shows a smoke temperature change diagram, a soot deposition change diagram, a soot blowing mode diagram, and a soot blowing operation execution diagram.
FIG. 5 illustrates a flow diagram of a predictive model training method according to some embodiments of the inventions.
FIG. 6 illustrates a flow diagram of a method of performing policy determination in accordance with some embodiments of the invention.
FIG. 7 is a flow diagram illustrating a method for performing policy determination in accordance with further embodiments of the present invention.
FIG. 8 illustrates a schematic structural diagram of a boiler sootblower according to some embodiments of the present invention.
FIG. 9 illustrates a schematic structural diagram of a boiler sootblower in accordance with other embodiments of the present invention.
FIG. 10 illustrates a schematic structural diagram of a boiler sootblower in accordance with still further embodiments of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
FIG. 1 illustrates a flow diagram of a boiler soot blowing method according to some embodiments of the invention. As shown in FIG. 1, the boiler soot blowing method of this embodiment includes steps S102 to S108.
In step S102, a characteristic representing the current boiler operation state is acquired. The boiler may be used, for example, in a thermal power plant.
The inventors have analyzed historical data including operating conditions of the boiler, soot blowing actions, smoke temperatures, etc. By carrying out data mining on historical data, the distribution of each feature in the operation state is determined, and the feature with high relevance to the occurrence of the soot blowing action is screened for predicting the gray scale. In some embodiments, the characteristics used in the soot level prediction include one or more of boiler wall temperature, load, steam pressure, main steam temperature, reheat steam temperature, de-superheated water flow, furnace negative pressure, oxygen content, flue fly ash carbon content.
Fig. 2 sequentially shows four schematic diagrams of coordinates, wherein the ordinate of each schematic diagram of coordinates respectively represents the influence degree of the smoke temperature, the boiler load, the ash deposition degree on the smoke temperature, and the soot blowing operation, the abscissa of each schematic diagram is time, and the abscissa of each schematic diagram is the same. In the schematic diagram of the execution of the soot blowing operation, the columnar section indicates that the soot blowing operation is executed. As can be seen from fig. 2, the boiler load has an effect on the soot deposition. Therefore, the load can be one of the characteristics.
In step S104, the obtained features are input into a pre-trained prediction model to obtain a predicted smoke temperature, where the prediction model is used to predict the smoke temperature of the boiler under the clean working condition in the current boiler operating state.
In some embodiments, the machine learning model is a random forest model, and the decision Tree in the random forest model is a CART (Classification and Regression Tree) model. The output of the prediction model is the value of the average of the prediction results of each decision tree.
In step S106, the difference between the current actual flue gas temperature of the boiler and the predicted flue gas temperature is used as a gray scale.
The output of the prediction model is the smoke temperature of the cleaned boiler in the current operation state, namely the smoke temperature of the boiler with no or little ash deposition. Therefore, the difference between the actual smoke temperature and the predicted smoke temperature can be used for measuring the current ash deposition degree.
The actual flue gas temperature collected may be collected at a low temperature superheater, a low temperature reheater, an economizer, or an air preheater, for example. Most boilers are provided with conventional temperature sensors at the positions, so that the high-cost sensors do not need to be additionally arranged at the positions in the boiler and the like when the smoke temperature is collected, and the equipment is slightly or even not modified.
Five coordinate schematic diagrams are sequentially shown in fig. 3, the ordinate of each coordinate schematic diagram respectively represents the low-temperature superheater inlet smoke temperature, the smoke temperature predicted value, the boiler operation load, the influence degree of the soot deposition degree on the smoke temperature, and the soot blowing operation, the abscissa is time, and the abscissa axes of the five schematic diagrams are the same. In the schematic diagram of the execution of the soot blowing operation, the columnar section indicates that the soot blowing operation is executed.
Fig. 4 sequentially shows four schematic diagrams of coordinates, in which the ordinate of each schematic diagram of coordinates respectively represents the execution of the smoke temperature, the volume gray level, the soot blowing mode, and the soot blowing operation, the abscissa of each schematic diagram is time, and the abscissa axes of the four schematic diagrams are the same. In the schematic diagram of the execution of the soot blowing operation, the columnar section indicates that the soot blowing operation is executed. Different values of the ordinate, corresponding to the soot blowing modes, indicate different soot blowing modes.
In step S108, the execution strategy of the soot blowing operation is determined according to the integrated gray scale. For example, the execution strategy may be pushed to the terminal for a worker to refer to, or the soot blowing execution part may be controlled to perform the soot blowing operation according to the execution strategy.
Through the embodiment, the soot deposition degree of the current boiler can be predicted according to the characteristics of the operating state of the boiler, and the corresponding soot blowing execution strategy is determined. Therefore, soot blowing control is realized in a data driving mode, the accuracy of soot deposition prediction is improved, and the soot blowing effect is optimized.
An embodiment of the predictive model training method of the invention is described below with reference to FIG. 5.
FIG. 5 illustrates a flow diagram of a predictive model training method according to some embodiments of the inventions. As shown in fig. 5, the training method of this embodiment includes steps S502 to S504.
In step S502, features are extracted from the historical data of the operating state of the boiler under the clean working condition to form training data, wherein the labeled value of the training data is the smoke temperature of the boiler.
In step S504, a machine learning model for regression prediction is trained using training data to obtain a prediction model.
Because the training data is the historical data of the operation state of the boiler under the clean working condition, the trained model can accurately predict the smoke temperature of the clean boiler under the same operation state, the accuracy of soot deposition prediction is improved, and the soot blowing effect is optimized.
The following describes the training process of the prediction model by taking a random forest model as an example.
1. And traversing each feature and each value of the feature. And (c, v) is taken as a dividing point for dividing the data set.
2. And dividing the input space by adopting the segmentation point with the minimum loss to generate a new space. For the new space, the step in 1 is continuously adopted to determine the dividing point in the new space.
The above process is iteratively performed, and finally, a space formed by the features for predicting the integration gray scale is divided into M input regions. The total loss of the model is expressed by formula (1), and the obtained CART model is expressed by formula (2). In the formulas (1) and (2), M represents the number of regions obtained after division, M represents a region identification, and R representsmDenotes the m-th region, cmRepresenting the mean of the output values of all samples in the current region; c represents the selected feature during partitioning, v represents the value of the selected feature, and (c, v) represents the partitioning point of the partitioned data set. x represents an input value; in x ∈ RmIn the case of (1), otherwise, I is 0.
Other training methods may be used by those skilled in the art and are not described in detail herein.
In some embodiments, the historical data may be fitted to obtain a gray scale change curve to predict when to perform a soot blowing operation. An embodiment of the determination method of the execution policy of the present invention is described below with reference to fig. 6.
FIG. 6 illustrates a flow diagram of a method of performing policy determination in accordance with some embodiments of the invention. As shown in fig. 6, the execution policy determination method of this embodiment includes steps S602 to S606.
In step S602, a curve of the accumulated dust with time and a threshold point on the curve are acquired.
In some embodiments, the gray scale prediction method of the present invention may be used to predict the gray scale of the historical data according to the characteristics of the historical data and the smoke temperature, so as to obtain a curve of the change of the gray scale with time.
In some embodiments, historical data of the operating conditions of the boiler is obtained, and each historical data is marked relative to the time of the last soot blowing operation; and fitting the historical data by taking the time relative to the last soot blowing operation as an abscissa and the accumulated soot as an ordinate to obtain a curve of the accumulated soot changing along with the time. Thus, the curve may reflect the change in soot deposition after each soot blowing.
In some embodiments, the data fitting is performed using a least squares method.
In some embodiments, a decreasing value of the soot level after performing the soot blowing operation is determined according to the historical data of the operating state of the boiler; and determining the accumulated gray level threshold value according to the average value of the falling values of the accumulated gray levels so as to take the point corresponding to the accumulated gray level threshold value on the curve as a threshold point. The skilled person may also set the threshold point in other ways, such as according to the turning point of the curve, the safety parameters of the boiler operation, etc., which will not be described in further detail herein.
In step S604, according to the curve, a time duration between a time corresponding to the current gray scale and a time corresponding to the threshold point on the curve is determined.
In step S606, an execution strategy for executing the soot blowing operation after the time period is determined.
For example, in the curved coordinate system, the time corresponding to the current gray scale is t0, the time corresponding to the threshold point is t1, and t0< t1, it may be determined that the soot blowing operation is performed later in the time period of t1-t 0.
Some embodiments of the invention may also determine threshold points for various soot blowing modes, and also determine the soot blowing mode when determining the execution strategy. An embodiment of the determination method of the execution policy of the present invention is described below with reference to fig. 7.
FIG. 7 is a flow diagram illustrating a method for performing policy determination in accordance with further embodiments of the present invention. As shown in fig. 7, the execution policy determination method of this embodiment includes steps S702 to S706.
In step S702, a curve of the soot deposition degree with time and a plurality of threshold points on the curve are obtained, wherein each threshold point corresponds to one soot blowing mode.
In step S704, a time duration between a time corresponding to the current integration level and a time corresponding to each threshold point on the curve is determined according to the curve.
In step S706, an execution strategy for executing the corresponding soot blowing operation after each time period is determined.
Table 1 exemplarily shows the soot deposition threshold and the soot deposition reduction degree after soot blowing for each soot blowing mode obtained by the analysis of the history data.
TABLE 1
Soot blowing mode | Integral gray scale threshold | Average degree of decrease |
Single soot blowing gun for soot blowing | 0.624 | 11.3%-37.5%(32.6%) |
Soot blowing by double soot blowing guns | 0.629 | 15.4%-38.1%(33.7%) |
All soot blowing guns blow soot | 0.831 | 41.6%-78.9%(60.4%) |
As can be seen from table 1, the thresholds for the single soot blowing gun to perform soot blowing, the double soot blowing guns to perform soot blowing, and all the soot blowing guns to perform soot blowing are sequentially increased. The threshold points are set according to the ash deposition threshold values of the three soot blowing modes, and the time values of the corresponding threshold points of the soot blowing of the single soot blowing gun, the soot blowing of the double soot blowing guns and the soot blowing of all the soot blowing guns are t1 ', t 2' and t3 ', and t 1' < t2 '< t 3'.
If the predicted current soot deposition is t0 ', and t0 ' < t1 ', three soot blowing strategies may be determined: strategy 1 is to use a single soot blower gun to perform soot blowing after the duration of t1 '-t 0'; the strategy 2 is to use a double number of soot blowing guns to perform soot blowing after the time length of t2 '-t 0'; strategy 3 is to use all sootblowing guns to sootblow after a time period of t3 '-t 0'. If t1 ' < t0 ' < t2 ', policies 2 and 3 can be determined.
When executed, any one of the policies may be selected, or the policy may be selected according to a pre-configuration or the like.
An embodiment of the boiler sootblower of the present invention is described below with reference to FIG. 8.
FIG. 8 illustrates a schematic structural diagram of a boiler sootblower according to some embodiments of the present invention. As shown in fig. 8, the boiler sootblower 80 of this embodiment includes: a characteristic obtaining module 810 configured to obtain a characteristic representing a current boiler operation state; a smoke temperature prediction module 820 configured to input the obtained characteristics into a pre-trained prediction model to obtain a predicted smoke temperature, wherein the prediction model is used for predicting the smoke temperature of the boiler under the clean working condition in the current boiler operation state; a integral gray level determining module 830 configured to take a difference between an actual smoke temperature of the current boiler and the predicted smoke temperature as an integral gray level; a strategy determination module 840 configured to determine an execution strategy of the soot blowing operation according to the soot deposition.
In some embodiments, the boiler sootblower 80 further comprises: a training module 850, configured to extract features from historical data of the operating state of the boiler under the clean working condition, and form training data, wherein a labeled value of the training data is the smoke temperature of the boiler; and training the machine learning model for regression prediction by adopting the training data to obtain a prediction model.
In some embodiments, the machine learning model is a random forest model, and the decision trees in the random forest model are classification and regression trees CART model.
In some embodiments, the policy determination module 840 is further configured to obtain a curve of the accumulated ash over time and a threshold point on the curve; determining the time length between the time corresponding to the current integral gray scale and the time corresponding to the threshold point on the curve according to the curve; and determining an execution strategy for executing the soot blowing operation after the time length.
In some embodiments, there are multiple threshold points on the curve, each corresponding to a soot blowing mode; the policy determination module 840 is further configured to determine, from the curve, a time duration between a time corresponding to the current gray scale and a time corresponding to each threshold point on the curve; an execution strategy for executing the corresponding soot blowing operation after each time period is determined.
In some embodiments, the boiler sootblower 80 further comprises: a curve fitting module 860 configured to obtain historical data of the operating state of the boiler and mark each historical data with respect to the time of the last soot blowing operation; and fitting the historical data by taking the time relative to the last soot blowing operation as an abscissa and the accumulated soot as an ordinate to obtain a curve of the accumulated soot changing along with the time.
In some embodiments, the boiler sootblower 80 further comprises: a threshold point determination module 870 configured to determine a decrease value of the soot deposition after performing the soot blowing operation according to historical data of the operating state of the boiler; and determining the accumulated gray level threshold value according to the average value of the falling values of the accumulated gray levels so as to take the point corresponding to the accumulated gray level threshold value on the curve as a threshold point.
In some embodiments, the characteristics include one or more of boiler wall temperature, load, steam pressure, main steam temperature, reheat steam temperature, desuperheated water flow, furnace suction pressure, oxygen content, flue fly ash carbon content.
FIG. 9 illustrates a schematic structural diagram of a boiler sootblower in accordance with other embodiments of the present invention. As shown in fig. 9, the boiler sootblower 90 of this embodiment includes: a memory 910 and a processor 920 coupled to the memory 910, the processor 920 being configured to perform a boiler soot blowing method in any of the embodiments described above based on instructions stored in the memory 910.
FIG. 10 illustrates a schematic structural diagram of a boiler sootblower in accordance with still further embodiments of the present invention. As shown in fig. 10, the boiler sootblower 100 of this embodiment includes: the memory 1010 and the processor 1020 may further include an input/output interface 1030, a network interface 1040, a storage interface 1050, and the like. These interfaces 1030, 1040, 1050 and the memory 1010 and the processor 1020 may be connected via a bus 1060, for example. The input/output interface 1030 provides a connection interface for input/output devices such as a display, a mouse, a keyboard, and a touch screen. Network interface 1040 provides a connection interface for various networking devices. The storage interface 1050 provides a connection interface for external storage devices such as an SD card and a usb disk.
Embodiments of the present invention also provide a computer readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements any of the boiler soot blowing methods described above.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (11)
1. A boiler soot blowing method comprising:
acquiring characteristics representing the current boiler operation state;
inputting the acquired characteristics into a pre-trained prediction model to obtain a predicted smoke temperature, wherein the prediction model is used for predicting the smoke temperature of the boiler under the clean working condition in the current boiler operation state;
taking the difference between the actual smoke temperature of the current boiler and the predicted smoke temperature as the gray level;
and determining an execution strategy of the soot blowing operation according to the gray product.
2. The boiler soot blowing method as claimed in claim 1, further comprising:
extracting features from historical data of the running state of the boiler under a clean working condition to form training data, wherein the marking value of the training data is the smoke temperature of the boiler;
and training a machine learning model for regression prediction by adopting the training data to obtain a prediction model.
3. The boiler soot blowing method as claimed in claim 1 or 2, wherein the machine learning model is a random forest model, and the decision tree in the random forest model is a classification and regression tree, CART, model.
4. The boiler soot blowing method as claimed in claim 1, wherein the determining an execution strategy of a soot blowing operation according to the gray scale includes:
acquiring a curve of the accumulated ash degree along with the change of time and a threshold point on the curve;
determining the duration between the time corresponding to the current integral gray scale and the time corresponding to the threshold point on the curve according to the curve;
and determining an execution strategy for executing the soot blowing operation after the time length.
5. The boiler soot blowing method of claim 1, wherein a plurality of threshold points exist on the curve, each threshold point corresponding to a soot blowing mode;
determining the duration between the time corresponding to the current integral gray scale and the time corresponding to each threshold point on the curve according to the curve;
an execution strategy for executing the corresponding soot blowing operation after each time period is determined.
6. The boiler soot blowing method as claimed in claim 4 or 5, further comprising:
acquiring historical data of the operating state of the boiler, and marking the time of each historical data relative to the last soot blowing operation;
and fitting the historical data by taking the time relative to the last soot blowing operation as an abscissa and the accumulated soot as an ordinate to obtain a curve of the accumulated soot changing along with the time.
7. The boiler soot blowing method as claimed in claim 4 or 5, further comprising:
determining a reduction value of the accumulated ash after executing the soot blowing operation according to the historical data of the operating state of the boiler;
and determining a deposition gray threshold value according to the average value of the drop values of the deposition gray, so as to take the point corresponding to the deposition gray threshold value on the curve as a threshold point.
8. A boiler soot blowing method as claimed in claim 1, wherein said characteristics include one or more of boiler wall temperature, load, steam pressure, main steam temperature, reheat steam temperature, desuperheating water flow, furnace negative pressure, oxygen content, flue fly ash carbon content.
9. A boiler sootblower comprising:
a characteristic obtaining module configured to obtain a characteristic representing a current boiler operation state;
the smoke temperature prediction module is configured to input the acquired characteristics into a pre-trained prediction model to obtain predicted smoke temperature, wherein the prediction model is used for predicting the smoke temperature of the boiler under the clean working condition in the current boiler operation state;
a volume gray level determining module configured to take a difference between an actual smoke temperature of the current boiler and the predicted smoke temperature as a volume gray level;
and the strategy determination module is configured to determine an execution strategy of the soot blowing operation according to the gray scale.
10. A boiler sootblower comprising:
a memory; and
a processor coupled to the memory, the processor configured to perform the boiler soot blowing method of any of claims 1-8 based on instructions stored in the memory.
11. A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the boiler soot blowing method of any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010021122.4A CN111237789A (en) | 2020-01-09 | 2020-01-09 | Boiler soot blowing method, device and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010021122.4A CN111237789A (en) | 2020-01-09 | 2020-01-09 | Boiler soot blowing method, device and computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111237789A true CN111237789A (en) | 2020-06-05 |
Family
ID=70874388
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010021122.4A Pending CN111237789A (en) | 2020-01-09 | 2020-01-09 | Boiler soot blowing method, device and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111237789A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112651182A (en) * | 2021-01-04 | 2021-04-13 | 国家能源集团国源电力有限公司 | Steam temperature adjusting method and device and electronic equipment |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11101430A (en) * | 1997-09-30 | 1999-04-13 | Nkk Corp | Treating method of dust in gasifying and melting furnace |
CN102353720A (en) * | 2011-09-01 | 2012-02-15 | 华北电力大学 | Method and device for monitoring ash dirt on convection heating surface of boiler |
CN103062781A (en) * | 2013-01-08 | 2013-04-24 | 北京世纪源博科技股份有限公司 | Intelligent soot blowing method for heating surfaces of boilers on basis of principle of artificial neural network |
CN106773955A (en) * | 2016-12-15 | 2017-05-31 | 大唐陕西发电有限公司灞桥热电厂 | A kind of boiler soot-blowing optimizes system and its optimization method |
CN108278625A (en) * | 2018-01-19 | 2018-07-13 | 华能国际电力股份有限公司上海石洞口第电厂 | A kind of coal-burning boiler high temperature reheater ash-blowing method |
CN109654517A (en) * | 2018-12-05 | 2019-04-19 | 中北大学 | A kind of boiler soot-blowing optimization method based on the prediction of heating surface health status |
CN109654518A (en) * | 2018-12-05 | 2019-04-19 | 中北大学 | A kind of soot blowing and optimal method of coal-fired plant boiler heating surface |
-
2020
- 2020-01-09 CN CN202010021122.4A patent/CN111237789A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11101430A (en) * | 1997-09-30 | 1999-04-13 | Nkk Corp | Treating method of dust in gasifying and melting furnace |
CN102353720A (en) * | 2011-09-01 | 2012-02-15 | 华北电力大学 | Method and device for monitoring ash dirt on convection heating surface of boiler |
CN103062781A (en) * | 2013-01-08 | 2013-04-24 | 北京世纪源博科技股份有限公司 | Intelligent soot blowing method for heating surfaces of boilers on basis of principle of artificial neural network |
CN106773955A (en) * | 2016-12-15 | 2017-05-31 | 大唐陕西发电有限公司灞桥热电厂 | A kind of boiler soot-blowing optimizes system and its optimization method |
CN108278625A (en) * | 2018-01-19 | 2018-07-13 | 华能国际电力股份有限公司上海石洞口第电厂 | A kind of coal-burning boiler high temperature reheater ash-blowing method |
CN109654517A (en) * | 2018-12-05 | 2019-04-19 | 中北大学 | A kind of boiler soot-blowing optimization method based on the prediction of heating surface health status |
CN109654518A (en) * | 2018-12-05 | 2019-04-19 | 中北大学 | A kind of soot blowing and optimal method of coal-fired plant boiler heating surface |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112651182A (en) * | 2021-01-04 | 2021-04-13 | 国家能源集团国源电力有限公司 | Steam temperature adjusting method and device and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108052007B (en) | Thermal power generating unit operation optimization method, device and equipment and computer storage medium | |
EP2729891B1 (en) | Automatic identification of operating parameters for power plants | |
CN109960873B (en) | Soft measurement method for dioxin emission concentration in urban solid waste incineration process | |
CN101393436B (en) | Dual model approach for boiler section cleanliness calculation | |
JP6884078B2 (en) | Plant abnormality monitoring system | |
GB2462214A (en) | Method of detecting permanent slagging | |
CN107817840B (en) | Device for analyzing the degree of influence of combustibles | |
CN110601185B (en) | Unified power flow model-based comprehensive energy system weak point identification method | |
CN109359428B (en) | Modeling method for boiler combustion efficiency and nitrogen oxide emission | |
CN103699514A (en) | Method for detecting steady state and judging operation condition of water treatment process in thermal power plant | |
CN112417764A (en) | K nearest neighbor regression prediction method for boiler special equipment steam flow prediction | |
CN113515049A (en) | Operation regulation and control system and method for gas-steam combined cycle generator set | |
CN111237789A (en) | Boiler soot blowing method, device and computer readable storage medium | |
JPWO2018179937A1 (en) | Risk assessment device, risk assessment method, and risk assessment program | |
CN116688754A (en) | Ship flue gas desulfurization automatic control system and method thereof | |
US11475186B2 (en) | Apparatus and method for deriving boiler combustion model | |
Bakar et al. | Flexible and operable heat exchanger networks | |
CN107944066B (en) | Waste heat boiler energy-saving potential analysis method based on big data | |
CN109140474A (en) | A kind of coal-fired power station boiler manually intelligent sootblowing | |
Ismail et al. | Adoption of intelligent computational techniques for steam boilers tube leak trip | |
WO2015060158A1 (en) | Method of monitoring and operating heat exchangers for fuels containing carbon | |
EP4160343A1 (en) | Display device, evaluation method, and evaluation system | |
CN104238516B (en) | A kind of steam generator system equipment condition monitoring method | |
JP5203763B2 (en) | Coal-fired boiler type identification device and coal-fired boiler type identification method | |
CN114053848A (en) | Method and system for co-processing multiple pollutants in flue gas in waste incinerator |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200605 |
|
RJ01 | Rejection of invention patent application after publication |