Flue gas extraction type monitoring pretreatment method and system
Through segment extraction and convolutional neural network analysis, the flue gas extraction point and channel direction are dynamically adjusted, which solves the problems of poor data representation and timeliness in the existing flue gas monitoring technology, and achieves high-precision and high-efficiency flue gas monitoring , meets the environmental protection requirements of thermal power plants.
Patent Information
- Application Number
- CN202410958775.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2024-11-15
AI Technical Summary
The existing flue gas monitoring technology has poor data representation, unreasonable sampling point settings, poor timeliness and lack of intelligent analysis in thermal power plants, resulting in unsatisfactory flue gas monitoring results and cannot meet strict environmental protection requirements.
The flue extraction point is set using segment extraction method, the flue gas path extraction channel is designed, the flue gas data is randomly extracted, the flue gas flow characteristics are analyzed through the convolutional neural network, and the position and channel direction of the extraction point are dynamically adjusted to realize the flue gas flow characteristics. intelligent monitoring and optimization.
It significantly improves the accuracy and efficiency of flue gas monitoring, provides more comprehensive data, avoids the misoperation of manual calibration, and meets the environmental protection and production needs of thermal power plants.
Smart Images

Figure CN118961328A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of flue gas monitoring, and in particular to a flue gas extraction monitoring preprocessing method and system. Background Art
[0002] As one of the main ways of electricity production, thermal power plants have long faced an increasingly prominent contradiction between energy demand and environmental protection. With increasingly stringent environmental protection regulations, flue gas emission monitoring in thermal power plants has become an important task and research target.
[0003] Nowadays, the existing flue gas monitoring technology mainly relies on single-point sampling and multi-point fixed sampling technology. The single-point sampling method is simple and easy, but its data representativeness is poor and cannot accurately reflect the flue gas condition of the entire flue. Although the multi-point fixed sampling technology can improve the representativeness of the data to a certain extent, there are still problems such as unreasonable sampling point setting and poor timeliness of sampling data. In addition, the operating conditions of thermal power plants are complex and changeable, and the flue gas flow characteristics will also change with the changes in the operating status. Especially when the flue gas flow speed and direction change, the data of the fixed sampling points often lag behind the actual situation and it is difficult to accurately reflect the dynamic changes of the flue gas. In addition, due to the lack of intelligent analysis of the flue gas path and flow characteristics at this stage, most thermal power plants still use manual monitoring and correction methods, which not only requires professional knowledge reserves but also prevents the possible losses caused by misoperation, so that the automatic adjustment of the flue gas path cannot be fully realized, which in turn affects the accuracy and efficiency of flue gas monitoring. In summary, these shortcomings have led to unsatisfactory flue gas monitoring effects in practical applications and cannot meet the increasingly stringent environmental protection requirements. Summary of the invention
[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.
[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a flue gas extraction monitoring pretreatment method to solve the problems mentioned in the background technology.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:
[0007] In a first aspect, the present invention provides a flue gas extraction monitoring pretreatment method, comprising:
[0008] Use segmented extraction to set extraction points on the flue and record the locations of the extraction points;
[0009] Each extraction point is designed as a smoke path extraction channel, and smoke data is randomly extracted to obtain different smoke distribution data and directions of smoke path extraction channels;
[0010] The different smoke distribution data are monitored, and the position of the extraction point and the direction of the smoke path extraction channel are adjusted according to the monitoring results.
[0011] As a preferred solution of the flue gas extraction monitoring pretreatment method of the present invention, the extraction point of the flue is set by adopting a segmented extraction method, and the position of the current extraction point is recorded, including:
[0012] Determine the length and height of the flue;
[0013] The segment distance of the flue is determined according to the length and height of the flue, and there are at least three sections, namely, the flue inlet section to the middle section of the flue, the middle section of the flue, and the middle section of the flue to the end section of the flue;
[0014] By calculating the height difference of the flue section by section, the position of the extraction point in the flue and the position of the existing branch point are determined.
[0015] As a preferred solution of the flue gas extraction monitoring pretreatment method of the present invention, it also includes:
[0016] Determine whether the position of the existing branch point overlaps with the position of the extraction point. If the branch point overlaps with the position of the extraction point, discard the position of the branch point and replace it with the position of the extraction point; otherwise, use the flue gas data collected at the branch point position as the flue gas data collected at the extraction point position.
[0017] As a preferred solution of the smoke extraction monitoring preprocessing method of the present invention, each extraction point is designed as a smoke path extraction channel, and smoke data is randomly extracted to obtain different smoke distribution data and the direction of the smoke path extraction channel, including:
[0018] The smoke path extraction channel includes a plurality of smoke extraction paths, each of which is divided into a neuron, and each neuron includes smoke data whose influencing factors of smoke are different from those of other neurons;
[0019] A convolutional neural network is used to analyze the influencing factors of the smoke and obtain the smoke flow characteristics.
[0020] As a preferred solution of the flue gas extraction monitoring pretreatment method of the present invention, it also includes:
[0021] According to the smoke flow characteristics, the flow velocity, concentration gradient and temperature distribution of the smoke in different extraction paths are determined, and the different smoke distribution data and the direction of the smoke path extraction channel are obtained.
[0022] As a preferred solution of the smoke extraction monitoring preprocessing method of the present invention, wherein: monitoring the different smoke distribution data, adjusting the position of the extraction point and the direction of the smoke path extraction channel according to the monitoring results, including:
[0023] Based on the currently obtained smoke distribution data, a channel direction objective function is established, and the smoke data in the neuron is returned to the channel direction objective function to obtain a new channel direction objective function;
[0024] When the new channel direction objective function exceeds the channel direction objective function, the channel direction objective function is re-established, the direction of the flue gas path extraction channel is modified according to the re-established channel direction objective function, and it is determined whether the direction of the modified flue gas path extraction channel is equal to the recorded position of the initial extraction point; if they are equal, the position of the extraction point is modified at the same time, otherwise no modification is made.
[0025] As a preferred solution of the flue gas extraction monitoring pretreatment method of the present invention, it also includes:
[0026] The current channel direction objective function is trained with the smoke data in each neuron until the number of all neurons reaches the maximum or the positions of the extraction points are traversed.
[0027] In a second aspect, the present invention provides a flue gas extraction monitoring pretreatment system, which comprises:
[0028] The extraction point position selection module is configured to set the extraction point of the flue using a segmented extraction method and record the position of the extraction point;
[0029] The smoke path extraction channel module is configured to design each extraction point as a smoke path extraction channel, randomly extract smoke data, and obtain different smoke distribution data and directions of the smoke path extraction channels;
[0030] The monitoring and adjustment module is configured to monitor the different smoke distribution data and adjust the position of the extraction point and the direction of the smoke path extraction channel according to the monitoring results.
[0031] In a third aspect, the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: the processor implements any step of the above method when executing the computer program.
[0032] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: the computer program implements any step of the above method when executed by a processor.
[0033] Compared with the prior art, the beneficial effects of the invention are as follows: the present invention sets extraction points on the flue by adopting a segmented extraction method, and records the positions of the extraction points, designs each extraction point as a flue path extraction channel, randomly extracts flue gas data, obtains different flue gas distribution data and the directions of the flue gas path extraction channels, monitors the different flue gas distribution data, and adjusts the positions of the extraction points and the directions of the flue gas path extraction channels according to the monitoring results; the method of the present invention overcomes the shortcomings of the prior art, realizes dynamic monitoring and optimization of flue gas flow characteristics, can accurately reflect the real-time status of flue gas, significantly improves the accuracy and efficiency of flue gas monitoring, can not only provide more comprehensive flue gas data, but also can avoid the problem of manual calibration in the later stage through intelligent analysis and automatic adjustment, improves the intelligence of actual flue gas monitoring, reduces the losses caused by misoperation, and better meets the environmental protection requirements and production needs of thermal power plants. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:
[0035] Figure 1 This is an overall flow chart of a flue gas extraction monitoring pretreatment method according to an embodiment of the present invention;
[0036] Figure 2 A diagram showing the relationship between the flow velocity, concentration gradient and temperature distribution in the flue gas of the flue gas extraction monitoring pretreatment method according to an embodiment of the present invention;
[0037] Figure 3 A diagram showing the real-time concentration gradient and temperature distribution change of flue gas in a flue gas extraction monitoring pretreatment method according to an embodiment of the present invention;
[0038] Figure 4 This is a linear fitting diagram of the flue gas concentration gradient and temperature data of the flue gas extraction monitoring pretreatment method described in one embodiment of the present invention. DETAILED DESCRIPTION
[0039] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.
[0040] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0041] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.
[0042] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.
[0043] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.
[0044] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0045] Example 1
[0046] Reference Figure 1 , which is the first embodiment of the present invention, provides a flue gas extraction monitoring pretreatment method, comprising:
[0047] S1. Use segmented extraction method to set extraction points on the flue and record the locations of the extraction points;
[0048] Furthermore, the process of segment extraction is as follows:
[0049] First, we need to determine the length and height of the flue. Suppose the length and height of the flue are: F L and F H ;
[0050] Secondly, the distance between the sections of the flue is determined according to the length and height of the flue, and there are at least three sections, namely, from the flue inlet section to the middle section of the flue, the middle section of the flue, and the middle section of the flue to the end section of the flue;
[0051] Specifically, the length of each section of the flue is expressed as:
[0052]
[0053] Wherein, d is the number of sections except the section from the flue inlet to the middle section, the middle section, and the middle section to the end section;
[0054] Specifically, the height of each section of the flue is expressed as:
[0055]
[0056] Finally, the position of the extraction point and the existing branching point in the flue are determined by calculating the height difference of the flue section by section;
[0057] Furthermore, according to the middle section of the flue, the middle section of the flue, and the middle section of the flue to the end section of the flue, the starting position and the ending position of each section of the flue are respectively:
[0058]
[0059]
[0060] Among them, L i is the starting position of the i-th segment, L i+1 is the end position of the i-th segment;
[0061] Specifically, the height difference of the flue is calculated as:
[0062]
[0063] Among them, H i represents the height of the i-th segment, and H0=0;
[0064] Specifically, the position formula of the extraction point in the flue is expressed as:
[0065]
[0066] It should be noted that the location of the extraction point can be in the middle of each segment or at any preset point, determined by calculating the start and end positions of each segment;
[0067] It should be noted that the smoke flow in the smoke duct may change direction and speed due to the existence of branches. If the extraction point is located at these branch points, it will make it difficult for the extracted data to reflect the characteristics of the smoke.
[0068] Furthermore, it is determined whether the position of the existing branch point overlaps (i.e. is equal to) the position of the extraction point. If the branch point overlaps with the position of the extraction point, the position of the branch point is discarded and replaced with the position of the extraction point; otherwise, the smoke data collected at the position of the branch point is used as the smoke data collected at the position of the extraction point;
[0069] Specifically, the position formula of the existing branch points is expressed as:
[0070] P=(B i ≠P i or B i =P i )
[0071] Among them, B i is the branch point, = represents the assignment, and P i The value of B i If B i ≠P i , then P=B i ; otherwise P = P i ;
[0072] Furthermore, if there is no overlap, then branch point B i It can be anywhere in each segment;
[0073] It should be noted that by determining the locations of the branch points and extraction points, the extracted data can more accurately reflect the smoke characteristics of the entire flue, avoiding monitoring errors caused by local flow anomalies;
[0074] S2. Design each extraction point as a smoke path extraction channel, randomly extract smoke data, and obtain different smoke distribution data and directions of smoke path extraction channels;
[0075] Furthermore, the smoke path extraction channel includes a plurality of smoke extraction paths, each of which is divided into a neuron, and each neuron includes smoke data whose influencing factors of smoke are different from those of other neurons;
[0076] Specifically, the smoke extraction channel includes several smoke extraction paths, which are recorded as: P = {P1, P2, ..., P n}, n represents the quantity;
[0077] Specifically, each neuron contains the influencing factors of smoke and different smoke data, and the division relationship is as follows:
[0078] N i =(f i ,D i )for i=1,2,…,n
[0079] Among them, f i represents the impact factor of smoke, for is a traversal operation, D i Indicates different smoke data; N i for neurons;
[0080] Furthermore, convolutional neural network is used to analyze the influencing factors of smoke and obtain the smoke flow characteristics;
[0081] Specifically, the convolutional neural network is used to analyze the factors affecting smoke as follows:
[0082]
[0083] F=X*W+b
[0084] A=σ(F)
[0085] P=pool(A)
[0086] O = flatten(P) × W f +b f
[0087] T=output(O)
[0088] Among them, the input layer receives the data of all neurons to form the input matrix X, and each row in the matrix X corresponds to a different smoke data, that is, a neuron; the convolution layer uses the weight matrix W to perform a convolution operation on the input matrix X* to extract the feature map F, and b is the bias term; the feature map F is nonlinearly transformed by the activation function σ to obtain the activated feature map A; the activated feature map A is downsampled using the pooling operation pool to obtain the pooled feature map P; the pooled feature map P is flattened and input to the fully connected layer to obtain the feature vector O, W f is the weight matrix of the fully connected layer f, b f is the bias term of the fully connected layer f; the output layer processes the feature vector O output and obtains the smoke flow feature T;
[0089] Furthermore, according to the obtained smoke flow characteristics T, the flow velocity, concentration gradient and temperature distribution of the smoke in different extraction paths are determined, and different smoke distribution data and the direction of the smoke path extraction channel are obtained;
[0090] Specifically, the flow velocity is expressed as:
[0091]
[0092] Among them, f v It is expressed as the current flow velocity of the flue gas. Expressed as the velocity characteristic of smoke flow, k v is the proportionality coefficient between flow velocity and flow characteristics, which determines the relationship between flow velocity and flow characteristics;
[0093] Specifically, the concentration gradient is expressed as:
[0094]
[0095] Among them, f g It is expressed as the current flue gas concentration gradient, Expressed as the concentration gradient characteristic of smoke flow, k g is the proportional coefficient of the concentration gradient, which determines the distribution characteristics of the smoke;
[0096] Specifically, the temperature distribution is expressed as:
[0097]
[0098] Among them, f θ Represented as the current flue gas temperature distribution, Expressed as the temperature characteristic of flue gas flow, k θ It is the proportional coefficient of temperature distribution, which determines the conversion between the temperature characteristics of flue gas and the actual temperature distribution;
[0099] Specifically, different smoke distribution data are expressed as:
[0100] D c =D i =(V i ,G i ,θ i )
[0101] Specifically, the direction of the flue gas extraction channel is expressed as:
[0102]
[0103] in, Indicates the current flue gas path direction. Indicates D c and The relationship between them determines the adjustment of the channel direction;
[0104] It should be noted that by analyzing the flow characteristics of the flue gas, the current distribution of the flue gas can be reflected, thus avoiding the limitation of the data of a single sampling point and improving the accuracy of subsequent monitoring;
[0105] S3. Monitor different smoke distribution data and adjust the position of the extraction point and the direction of the smoke path extraction channel according to the monitoring results;
[0106] Furthermore, based on the currently obtained smoke distribution data, a channel direction objective function is established, and the smoke data in the neuron is returned to the channel direction objective function to obtain a new channel direction objective function;
[0107] Furthermore, when the new channel direction objective function exceeds the channel direction objective function, the channel direction objective function is re-established, the direction of the smoke path extraction channel is modified according to the re-established channel direction objective function, and it is determined whether the modified direction of the smoke path extraction channel is equal to the recorded position of the initial extraction point; if they are equal, the position of the extraction point is modified at the same time, otherwise no modification is made;
[0108] Specifically, the judgment process is expressed as:
[0109] if F new_direction >F direction :
[0110] F direction =F new_direction
[0111]
[0112] ΔP new =P init +ΔP
[0113] Among them, F new-direction is the new channel direction objective function, F direction is the channel direction objective function; is the direction of the modified smoke path extraction channel, h is the moving distance in the channel, is the direction of the initial smoke path extraction channel, ΔP new is the extraction point after displacement, P init is the initial extraction point position, ΔP is the offset of the extraction point position;
[0114] Furthermore, the smoke data in each neuron is used to train the current channel direction objective function until the number of all neurons reaches the maximum or the positions of the extraction points are traversed;
[0115] It should be noted that by continuously updating the channel direction objective function, it is possible to adapt to changes in different working conditions and environments, ensuring that the direction of the flue gas path extraction channel is always optimal; and dynamically adjust according to real-time flue gas data, thereby avoiding the need for manual calibration in the later stage, improving the intelligence of actual flue gas monitoring, reducing losses caused by misoperation, and further improving the efficiency of flue gas flow and the accuracy of monitoring.
[0116] Furthermore, this embodiment also provides a flue gas extraction monitoring pretreatment system, comprising:
[0117] The extraction point position selection module is configured to set the extraction point of the flue using a segmented extraction method and record the position of the extraction point;
[0118] The smoke path extraction channel module is configured to design each extraction point as a smoke path extraction channel, randomly extract smoke data, and obtain different smoke distribution data and directions of the smoke path extraction channels;
[0119] The monitoring and adjustment module is configured to monitor the different smoke distribution data and adjust the position of the extraction point and the direction of the smoke path extraction channel according to the monitoring results.
[0120] This embodiment also provides a computer device, which is applicable to the case of the flue gas extraction monitoring pretreatment method, including:
[0121] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the flue gas extraction monitoring preprocessing method proposed in the above embodiment.
[0122] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.
[0123] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the flue gas extraction monitoring preprocessing method proposed in the above embodiment is implemented.
[0124] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.
[0125] Example 2
[0126] Reference Figures 2 to 4 , which is the second embodiment of the present invention, and provides a flue gas extraction monitoring pretreatment method, including: In order to verify the effectiveness of the method for setting the extraction point of the flue using the segmented extraction method, the following test was conducted:
[0127] Select an industrial flue with a length of 15m and a height of 3m, and set it as =3m; determine the segment distance according to the length and height of the flue, and divide the flue into three sections, each with a length of 5m and a height of 1m; set extraction points in different sections of the flue, and record the position of each extraction point;
[0128] The starting and ending positions of each section of the flue are: L1 = 0m, L2 = 5m; L2 = 5m, L3 = 10m; L3 = 10m, L4 = 15m; the height difference of each section of the flue is ΔH i =1m; through monitoring by the scheme of the present invention, the data obtained are shown in Table 1;
[0129] Table 1
[0130] Test subjects Flue section 1 Flue section 2 Flue section 3 Flow velocity (m / s) 2.5 2.8 3.0 Concentration gradient (mg / m3) 150 140 130 Temperature distribution (℃) 220 210 200 Extraction point position (m) 2.5 7.5 12.5
[0131] The flow velocity in different flue sections of the prior art is not uniform, which easily leads to inaccurate extraction data. It can be seen from Table 1 that the extraction points set in the present invention make the flow velocity in different flue sections more uniform; and through reasonable segmented extraction, the problem of overlapping between the extraction points and the flue branch points is avoided, making the concentration gradient of different flue sections more realistic. At the same time, by referring to Figure 2 ,With the increase of flow velocity, the concentration gradient and temperature distribution gradually decrease, indicating that the increased flow velocity enables the heat in the flue gas to be transferred to the surrounding medium or equipment more quickly, which promotes the heat exchange process and avoids local overheating;
[0132] Combination Figure 3 , the real-time flow velocity was fitted with the concentration gradient and temperature distribution using the linear fitting method, and the linear fitting results of concentration gradient and flow velocity were obtained: y = -30.01x + 222.46; the linear fitting results of temperature distribution and flow velocity were obtained: y = -30.01x + 292.46; it can be seen that the fitting results are basically similar, indicating that the influence of flow velocity on concentration gradient and temperature distribution is consistent, proving that Figure 2 This fully illustrates the reliability of the solution of the present invention.
[0133] Those skilled in the art will appreciate that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program codes. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.
[0134] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0135] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0136] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0137] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.
[0138] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.
Claims
1. A flue gas extraction monitoring pretreatment method, characterized in that: include: Use segmented extraction to set extraction points on the flue and record the locations of the extraction points; Each extraction point is designed as a smoke path extraction channel, and smoke data is randomly extracted to obtain different smoke distribution data and directions of smoke path extraction channels; The different smoke distribution data are monitored, and the position of the extraction point and the direction of the smoke path extraction channel are adjusted according to the monitoring results.
2. The flue gas extraction monitoring pretreatment method according to claim 1, characterized in that: Use segmented extraction to set extraction points on the flue and record the current extraction point locations, including: Determine the length and height of the flue; The segment distance of the flue is determined according to the length and height of the flue, and there are at least three sections, namely, the flue inlet section to the middle section of the flue, the middle section of the flue, and the middle section of the flue to the end section of the flue; By calculating the height difference of the flue section by section, the position of the extraction point in the flue and the position of the existing branch point are determined.
3. The flue gas extraction monitoring pretreatment method according to claim 2, characterized in that: Also includes: Determine whether the position of the existing branch point overlaps with the position of the extraction point. If the branch point overlaps with the position of the extraction point, discard the position of the branch point and replace it with the position of the extraction point; otherwise, use the flue gas data collected at the branch point position as the flue gas data collected at the extraction point position.
4. The flue gas extraction monitoring pretreatment method according to claim 2 or 3, characterized in that: Each extraction point is designed as a smoke path extraction channel, and smoke data is randomly extracted to obtain different smoke distribution data and directions of smoke path extraction channels, including: The smoke path extraction channel includes a plurality of smoke extraction paths, each of which is divided into a neuron, and each neuron includes smoke data whose influencing factors of smoke are different from those of other neurons; A convolutional neural network is used to analyze the influencing factors of the smoke and obtain the smoke flow characteristics.
5. The flue gas extraction monitoring pretreatment method according to claim 4, characterized in that: Also includes: According to the smoke flow characteristics, the flow velocity, concentration gradient and temperature distribution of the smoke in different extraction paths are determined, and the different smoke distribution data and the direction of the smoke path extraction channel are obtained.
6. The flue gas extraction monitoring pretreatment method according to claim 5, characterized in that: The different smoke distribution data are monitored, and the position of the extraction point and the direction of the smoke path extraction channel are adjusted according to the monitoring results, including: Based on the currently obtained smoke distribution data, a channel direction objective function is established, and the smoke data in the neuron is returned to the channel direction objective function to obtain a new channel direction objective function; When the new channel direction objective function exceeds the channel direction objective function, the channel direction objective function is re-established, the direction of the flue gas path extraction channel is modified according to the re-established channel direction objective function, and it is determined whether the direction of the modified flue gas path extraction channel is equal to the recorded position of the initial extraction point; if they are equal, the position of the extraction point is modified at the same time, otherwise no modification is made.
7. The flue gas extraction monitoring pretreatment method according to claim 6, characterized in that: Also includes: The current channel direction objective function is trained with the smoke data in each neuron until the number of all neurons reaches the maximum or the positions of the extraction points are traversed.
8. A flue gas extraction monitoring pretreatment system, based on the flue gas extraction monitoring pretreatment method according to any one of claims 1 to 7, characterized in that: include: The extraction point position selection module is configured to set the extraction point of the flue using a segmented extraction method and record the position of the extraction point; The smoke path extraction channel module is configured to design each extraction point as a smoke path extraction channel, randomly extract smoke data, and obtain different smoke distribution data and directions of the smoke path extraction channels; The monitoring and adjustment module is configured to monitor the different smoke distribution data and adjust the position of the extraction point and the direction of the smoke path extraction channel according to the monitoring results.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
