Sound wave ash removal control method and system in boiler

Abstract

The invention discloses a sound wave ash removal control method and system in a boiler to solve the problem that an existing sound wave ash removal system is poor in ash removal effect. The method comprises the steps of obtaining boiler operation parameters, first monitoring data and second monitoring data when a boiler system operates; determining a dust deposition dynamic factor based on the boiler operation parameters, the first monitoring data and the second monitoring data; determining a target sound wave frequency and a target sound wave power through a target optimization model by taking the sound wave frequency and the sound wave power as optimization variables; wherein the search range of the target optimization model is determined by a dust deposition dynamic factor; and converting the target sound wave frequency and the target sound wave power into a control instruction to drive the sound wave dust remover to work. According to the method, the sound wave frequency and the sound wave power can be adaptively and dynamically adjusted according to the actual operation condition and the ash deposition state of the boiler, and the ash removal effect of the sound wave ash removal system is improved.

Description

Technical Field

[0001] This application relates to the field of boiler soot blowing technology, and in particular to a method and system for controlling acoustic soot blowing in a boiler. Background Technology

[0002] Acoustic cleaning technology, as a novel cleaning method, uses high-energy sound waves generated by an acoustic cleaner to cause ash particles to resonate and fall off. It boasts advantages such as a wide operating range, low energy consumption, and no damage to equipment. However, existing acoustic cleaning systems still have significant shortcomings in practical applications. Most systems currently employ a fixed parameter control mode, meaning they preset fixed sound wave frequencies and power for periodic cleaning, failing to adapt to the actual operating conditions of the boiler and the state of ash accumulation. This "one-size-fits-all" control method often leads to poor cleaning results when operating conditions change: incomplete cleaning when ash accumulation is severe, and energy waste when ash accumulation is slight. Summary of the Invention

[0003] This application provides a method for controlling acoustic cleaning in a boiler, which solves the problem that existing acoustic cleaning systems cannot adaptively and dynamically adjust the acoustic frequency and power according to the actual operating conditions and ash accumulation of the boiler, resulting in poor cleaning effect.

[0004] This application also provides an acoustic ash removal control system for boilers.

[0005] The embodiments of this application adopt the following technical solutions: In a first aspect, this application provides a method for controlling acoustic ash removal in a boiler, comprising: Obtain boiler operating parameters, first monitoring data, and second monitoring data during boiler system operation; Based on boiler operating parameters, first monitoring data, and second monitoring data, the dynamic factor of dust deposition was determined. Using sound wave frequency and sound wave power as optimization variables, the target sound wave frequency and target sound wave power are determined through a target optimization model; wherein, the search range of the target optimization model is determined by the dust deposition dynamic factor. The target acoustic wave frequency and target acoustic wave power are converted into control commands to drive the acoustic wave cleaner to work.

[0006] Optionally, the first monitoring data includes: average flue gas velocity, flow field uniformity index, and temperature gradient value; based on the boiler operating parameters, the first monitoring data, and the second monitoring data, a dynamic factor for dust deposition is determined, including: The ash accumulation risk factor is determined based on the average flue gas velocity, flow field uniformity index, and temperature gradient value. Based on boiler operating parameters, secondary monitoring data, and ash accumulation risk factors, dynamic factors of ash deposition are determined.

[0007] Optionally, the boiler operating parameters include: boiler load, coal calorific value, coal composition content, flue gas temperature, and pressure; the second monitoring data includes: dust thickness data series; based on the boiler operating parameters, the second monitoring data, and ash accumulation risk factors, dynamic factors for dust deposition are determined, including: Based on boiler load, coal calorific value, coal composition content, flue gas temperature, and pressure value, a deposition tendency factor is determined. Determine the deposition fluctuation factor based on the dust thickness data sequence; Based on the deposition tendency factor, deposition fluctuation factor, and ash accumulation risk factor, the dynamic factors of dust deposition are determined.

[0008] Optionally, the objective optimization model employs an improved metaheuristic algorithm, which includes: The search range of the target optimization model is dynamically adjusted based on the dynamic factors of dust deposition. When the dynamic factor of dust deposition increases, the search range of the target optimization model is expanded; When the dust deposition dynamic factor decreases, the search range of the objective optimization model is narrowed.

[0009] Optionally, the improved metaheuristic algorithm is a hybrid gray wolf optimization-particle swarm optimization algorithm, which includes: The position weighting factor is dynamically adjusted and updated based on the dust deposition dynamic factor to obtain the updated weighting factor. Based on the updated weighting factors, at least one set of candidate solutions is determined, each candidate solution including a set of candidate acoustic frequencies and candidate acoustic powers.

[0010] Optionally, the target sound wave frequency and target sound wave power are determined through a target optimization model, using sound wave frequency and sound wave power as optimization variables, including: The target acoustic frequency and target acoustic power are determined from at least one candidate solution set by using a fitness function constructed using cleaning efficiency, energy consumption ratio and equipment life factor.

[0011] Secondly, this application provides a boiler in-situ acoustic ash removal control system, the system comprising: a data acquisition unit, used to acquire boiler operating parameters, first monitoring data and second monitoring data during boiler system operation; The dust deposition dynamic factor calculation unit is used to determine the dust deposition dynamic factor based on boiler operating parameters, first monitoring data, and second monitoring data. The target optimization unit is used to determine the target acoustic frequency and target acoustic power through a target optimization model, using acoustic frequency and acoustic power as optimization variables; wherein, the search range of the target optimization model is determined by the dust deposition dynamic factor. The control command generation unit is used to convert the target acoustic wave frequency and target acoustic wave power into control commands to drive the acoustic wave cleaner to work.

[0012] Optionally, the first monitoring data includes: average flue gas velocity, flow field uniformity index, and temperature gradient value; the dust deposition dynamic factor calculation unit is specifically used for: The ash accumulation risk factor is determined based on the average flue gas velocity, flow field uniformity index, and temperature gradient value. Based on boiler operating parameters, secondary monitoring data, and ash accumulation risk factors, dynamic factors of ash deposition are determined.

[0013] Optionally, the boiler operating parameters include: boiler load, coal calorific value, coal composition content, flue gas temperature, and pressure; the second monitoring data includes: dust thickness data sequence; and a dust deposition dynamic factor calculation unit, specifically used for: Deposition tendency factor is determined based on boiler load, coal calorific value, coal composition content, flue gas temperature and pressure. Determine the deposition fluctuation factor based on the dust thickness data sequence; Based on the deposition tendency factor, deposition fluctuation factor, and ash accumulation risk factor, the dynamic factors of dust deposition are determined.

[0014] Optionally, the objective optimization model employs an improved metaheuristic algorithm, with the objective optimization unit specifically used for: The search range of the target optimization model is dynamically adjusted based on the dynamic factors of dust deposition. When the dynamic factor of dust deposition increases, the search range of the target optimization model is expanded; When the dust deposition dynamic factor decreases, the search range of the objective optimization model is narrowed.

[0015] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: The method provided in this application allows for the acquisition of boiler operating parameters, first monitoring data, and second monitoring data during boiler system operation. Based on these parameters, dynamic factors for dust deposition are determined. Using acoustic frequency and power as optimization variables, a target acoustic frequency and power are determined through a target optimization model. The search range of the target optimization model is determined by the dynamic factors for dust deposition. The target acoustic frequency and power are then converted into control commands to drive the acoustic soot remover. This method can adaptively and dynamically adjust the acoustic frequency and power according to the actual boiler operating conditions and ash accumulation status, improving the soot removal effect of the acoustic soot removal system. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A schematic diagram illustrating the implementation process of a boiler acoustic ash removal control method provided in this application embodiment; Figure 2 This application provides a schematic diagram of the specific structure of an acoustic ash removal control system for a boiler. Detailed Implementation To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0017] As will be known to those skilled in the art, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0018] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application.

[0019] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0020] Example 1 To address the problem that existing acoustic cleaning systems cannot adaptively and dynamically adjust the acoustic frequency and power according to the actual operating conditions and ash accumulation status of the boiler, resulting in poor cleaning performance, this application provides an acoustic cleaning control method for boilers.

[0021] Specifically, the implementation flow of the method provided in this application embodiment is as follows: Figure 1 As shown, it includes the following steps: Step 11: Obtain boiler operating parameters, first monitoring data, and second monitoring data during boiler system operation.

[0022] Specifically, the first set of monitoring data includes: average flue gas velocity, flow field uniformity index, and temperature gradient value, which are obtained and determined through an acoustic measurement device. Boiler operating parameters are selected during boiler operation by screening the system's operating parameters to identify key parameters affecting ash accumulation, including: boiler load, coal calorific value, coal composition, flue gas temperature, and pressure. The second set of monitoring data includes: a dust thickness data sequence, which is obtained by real-time collection of dust thickness data in a designated area inside the boiler using dust sensors installed inside the boiler.

[0023] In this embodiment, in addition to the original dust thickness data, boiler operating parameters such as boiler load, coal calorific value, composition analysis, coal consumption, boiler internal temperature distribution, pressure, and resistance are added, as well as temperature and flow field data obtained by the acoustic wave measurement device. Through multi-dimensional data, the ash accumulation status inside the boiler can be assessed more comprehensively and accurately, thus providing a sufficient guarantee for subsequent dynamic adjustment of acoustic wave frequency and acoustic wave power.

[0024] Step 12: Determine the dynamic factor of dust deposition based on boiler operating parameters, first monitoring data, and second monitoring data.

[0025] In this embodiment, the dust deposition dynamic factors include: dust risk factor, deposition fluctuation factor, and deposition tendency factor. The dust risk factor is calculated and determined from the first monitoring data obtained in step 11, the deposition fluctuation factor is calculated and determined from the dust thickness data sequence obtained in step 11, and the deposition tendency factor is determined from the boiler operating parameters.

[0026] (1) Determine dust risk factors based on the first monitoring data .

[0027] Specifically, key characteristic parameters are extracted from the flow field and temperature field data acquired by the acoustic measurement device, including: Average flue gas velocity (V): The average velocity of flue gas within the measurement cross section (m / s); Flow field uniformity index (U): reflects the degree of uniformity of flow velocity distribution. ,in, The standard deviation of the flow rate, The average flow velocity; Temperature gradient value ( T: Maximum temperature change rate (°C / m) between key monitoring points.

[0028] Next, the extracted key feature parameters are fuzzified to obtain the corresponding fuzzy sets for flow velocity, uniformity index, and temperature gradient. Specifically, they are represented as follows: Fuzzy set of flow velocity V: {very low, lower, normal, higher}, membership function: trapezoidal function, threshold [0.5, 1.0, 2.0, 3.0] m / s; Fuzzy set of uniformity index U: {non-uniform, general, uniform}, membership function: trigonometric function, threshold [0.3, 0.5, 0.7, 0.9]; Temperature gradient The fuzzy set of T is {small, medium, large}, its membership function is a Gaussian function, and its parameters are... .

[0029] Then, based on the fuzzy sets of flow velocity, uniformity index, and temperature gradient obtained after fuzzification, a fuzzy rule base is constructed; the fuzzy rule base includes multiple inference rules.

[0030] Example: Rule 1: IF V = very low AND U = uneven AND T = Big THEN =very high Rule 2: IF V = lower AND U = uneven AND T = THEN =Higher Rule 3: IF V = Normal AND U = Normal AND T = small THEN =Medium Rule 4: IF V = Higher AND U = Uniform AND T = small THEN =Very low ... Finally, a Mamdani-type fuzzy inference system is adopted. First, the premise satisfaction of each rule is calculated. Then, the max-min synthesis method is used for fuzzy inference. Finally, the centroid method is used to calculate the centroid position of the output fuzzy set, which is used as the accurate ash accumulation risk factor. .

[0031]

[0032] in, It is the number of points after discretizing the output variable, that is, dividing the output domain (such as [0,1]) into... One point. These are the indices of discrete points, from 1 to... . It is the first Output values ​​at discrete points. It is a fuzzy set at a point Membership degree of a location.

[0033] (2) Determine the sedimentation fluctuation factor based on the second monitoring data .

[0034] In this embodiment, the second monitoring data is a dust thickness data sequence. The deposition fluctuation factor can be determined based on the dust thickness data sequence by calculating the information entropy and the difference in the angle of change trend.

[0035] Specifically, the dust thickness data sequence is represented as follows: By calculating the information entropy of this dust thickness data sequence, the randomness of dust accumulation can be characterized. (Calculating information entropy) At this time, we need to discretize the continuous thickness data, that is, divide it into... Each interval. Correspondingly, its information entropy. The calculation formula is as follows:

[0036] in, This indicates that the thickness value falls within the first... The probability within a given interval, i.e., the frequency. It represents the total number of intervals.

[0037] For dust thickness data sequence Construct a sequence of thickness variation vectors: ,

[0038] in: Indicates from time arrive The thickness change vector has a horizontal component of 1 and a vertical component representing the thickness change amount. .

[0039] After constructing the thickness variation vector, the angle between adjacent thickness variation vectors is calculated. :

[0040] The formulas for calculating the vector dot product and magnitude are as follows:

[0041]

[0042]

[0043] Then, calculate all included angles and their comparison with the preset reference angle. The average absolute difference is used as the angular difference factor. The calculation formula is as follows:

[0044] in, The length of the data sequence. For the preset reference angle, Indicates the first The absolute difference between the included angle and the reference angle.

[0045] To facilitate integration with other factors, the aforementioned angle difference factors are normalized. Larger calculated angle difference factors indicate stronger fluctuations in the depositional process, making control more difficult; conversely, smaller calculated angle difference factors indicate stronger regularity in the depositional process, making prediction and control easier.

[0046] (3) Determine the deposition tendency factor based on boiler operating parameters .

[0047] In this embodiment, the key operating parameters that affect ash accumulation include boiler load, coal calorific value, coal composition content, flue gas temperature, and pressure.

[0048] The relationship between the selected key operating parameters and ash accumulation is as follows: Boiler load The higher the load, the greater the flue gas flow rate and velocity, and the more likely ash accumulation will occur; there is a positive correlation. calorific value of coal The higher the calorific value, the more complete the combustion, and the less ash may be. However, a high calorific value may also mean a high flue gas temperature, which may exacerbate ash accumulation. Assuming a positive correlation. Coal composition content value The higher the ash content, the greater the tendency for ash to accumulate; there is a positive correlation. flue gas temperature The higher the temperature, the greater the tendency for dust to accumulate; this is a positive correlation. pressure The effect of pressure on dust accumulation is complex; we assume a positive correlation.

[0049] In practical applications, correlations and weights should be determined through regression analysis or machine learning methods based on the specific boiler's operating data and historical ash accumulation data.

[0050]

[0051] in, The interaction term coefficients are determined through regression analysis. All the parameter values ​​mentioned above are normalized values. Let be the variance contribution rate of the i-th principal component. The variance contribution rate can be determined through principal component analysis.

[0052] (4) Determine the dynamic factors of dust deposition based on dust risk factors, deposition fluctuation factors and deposition tendency factors.

[0053] In one embodiment, the first monitoring data includes: average flue gas velocity, flow field uniformity index, and temperature gradient value. Step 12 includes the following steps: The ash accumulation risk factor is determined based on the average flue gas velocity, flow field uniformity index, and temperature gradient value. Based on boiler operating parameters, secondary monitoring data, and ash accumulation risk factors, dynamic factors of ash deposition are determined.

[0054] In another embodiment, the boiler operating parameters include: boiler load, coal calorific value, coal composition content, flue gas temperature, and pressure; the second monitoring data includes: a dust thickness data sequence; based on the boiler operating parameters, the second monitoring data, and the dust accumulation risk factor, a dynamic factor for dust deposition is determined, including: Based on boiler load, coal calorific value, coal composition content, flue gas temperature, and pressure value, a deposition tendency factor is determined. Determine the deposition fluctuation factor based on the dust thickness data sequence; Based on the deposition tendency factor, deposition fluctuation factor, and ash accumulation risk factor, the dynamic factors of dust deposition are determined.

[0055] Specifically, a multi-factor weighted fusion approach is adopted, with the weights of multiple factors determined based on expert experience. Accordingly, the calculation formula for the dust deposition dynamic factor is as follows:

[0056] The sum of the above weights is 1.

[0057] Step 13: Using sound wave frequency and sound wave power as optimization variables, determine the target sound wave frequency and target sound wave power through the target optimization model; wherein, the search range of the target optimization model is determined by the dust deposition dynamic factor.

[0058] In one implementation, the objective optimization model employs an improved metaheuristic algorithm, which includes: The search range of the target optimization model is dynamically adjusted based on the dynamic factors of dust deposition. When the dynamic factor of dust deposition increases, the search range of the target optimization model is expanded; When the dust deposition dynamic factor decreases, the search range of the objective optimization model is narrowed.

[0059] Specifically, using acoustic frequency and acoustic power as optimization variables, the search range of the target optimization model is initialized with the historical maximum and minimum values ​​of acoustic frequency and acoustic power of the current acoustic dust cleaner, and this determined search range serves as the base search range. Then, by incorporating the calculated dust deposition dynamic factor, the search range of the target optimization model is dynamically adjusted. (Dust deposition dynamic factor) This is a comprehensive indicator; a larger value indicates more drastic changes in ash accumulation, requiring a wider search range to quickly track the optimal solution. A smaller value indicates more gradual changes, allowing for a narrower search range for finer analysis. When the dust deposition dynamic factor increases, the search range of the target optimization model is expanded, enhancing global exploration; when the dust deposition dynamic factor decreases, the search range of the target optimization model is narrowed, enhancing local exploration. Since boiler ash removal control is a real-time process, this optimization algorithm needs to be run once in each control cycle (i.e., each time an ash removal decision is made). However, the number of algorithm iterations can be set relatively low to meet real-time requirements.

[0060] In another implementation, the improved metaheuristic algorithm is a hybrid gray wolf optimization-particle swarm optimization algorithm, which includes: The position weighting factor is dynamically adjusted and updated based on the dust deposition dynamic factor to obtain the updated weighting factor. Based on the updated weighting factors, at least one set of candidate solutions is determined, each candidate solution including a set of candidate acoustic frequencies and candidate acoustic powers.

[0061] Specifically, a hybrid gray wolf optimization-particle swarm optimization algorithm is adopted. In this algorithm, each candidate solution represents a set of acoustic cleaning operation parameters, specifically acoustic frequency and acoustic strategy. By adjusting the weights in the position update formula using a dust deposition dynamic factor, the algorithm can balance global search and local exploitation capabilities according to the complexity of the boiler ash accumulation state.

[0062] Accordingly, the position update formula is:

[0063] in: It is a new candidate solution that includes the sound wave frequency and the sound wave power. They represent the current population The wolf's position (i.e., the three best solutions at present). It is the individual's historical best position, the best position that the individual achieved in previous iterations. It is a dynamic weighting factor, determined by the dynamic factor of dust deposition. Decide.

[0064] when When the amount of dust is large (and the dust accumulation is complex and variable), Increase, the algorithm tends to rely more on The wolf's guidance allows for rapid location of potentially new areas; when When the dust accumulation is relatively small (stable dust accumulation state), The algorithm relies more heavily on the historical best position of each individual unit for a more refined search. The position update formula combines global exploration and local development through dynamic weights, enabling the algorithm to adapt to changes in boiler ash accumulation and efficiently find the optimal acoustic cleaning parameters.

[0065] In another implementation, the method of determining the target sound wave frequency and target sound wave power through a target optimization model, using sound wave frequency and sound wave power as optimization variables, includes: The target acoustic frequency and target acoustic power are determined from at least one candidate solution set by using a fitness function constructed using cleaning efficiency, energy consumption ratio and equipment life factor.

[0066] Specifically, for multiple candidate solution sets, a fitness function is constructed with cleaning efficiency, energy consumption ratio and equipment availability factor as objectives to select the optimal candidate solution set from multiple candidate solution sets as the final target acoustic frequency and target acoustic power.

[0067] Accordingly, the constructed fitness function is:

[0068] in: The value for dust removal efficiency ranges from 0 to 1, indicating the dust removal effect; the higher the value, the better. Energy efficiency ratio, ranging from 0 to 1, represents the relative magnitude of energy consumption; the lower the better. This is the equipment lifespan factor, with a value between 0 and 1, representing the impact on equipment lifespan. A higher value indicates a more favorable impact on lifespan. , , As the weight, satisfying And all of them are positive numbers.

[0069] Step 14: Convert the target acoustic wave frequency and target acoustic wave power into control commands to drive the acoustic wave cleaner to work.

[0070] The method provided in this application allows for the acquisition of boiler operating parameters, first monitoring data, and second monitoring data during boiler system operation. Based on these parameters, dynamic factors for dust deposition are determined. Using acoustic frequency and power as optimization variables, a target acoustic frequency and power are determined through a target optimization model. The search range of the target optimization model is determined by the dynamic factors for dust deposition. The target acoustic frequency and power are then converted into control commands to drive the acoustic soot remover. This method can adaptively and dynamically adjust the acoustic frequency and power according to the actual boiler operating conditions and ash accumulation status, improving the soot removal effect of the acoustic soot removal system.

[0071] Example 2 To address the problem that existing acoustic cleaning systems cannot adaptively and dynamically adjust the acoustic frequency and power according to the actual operating conditions and ash accumulation status of the boiler, resulting in poor cleaning performance, this application provides an acoustic cleaning control system for boilers. A schematic diagram of the specific structure of this control system is shown below. Figure 2 As shown, it includes a data acquisition unit 21, a dust deposition dynamic factor calculation unit 22, a target optimization unit 23, and a control command generation unit 24. The functions of each unit are as follows: Data acquisition unit 21 is used to acquire boiler operating parameters, first monitoring data and second monitoring data when the boiler system is running; The dust deposition dynamic factor calculation unit 22 is used to determine the dust deposition dynamic factor based on boiler operating parameters, first monitoring data, and second monitoring data. The target optimization unit 23 is used to determine the target sound wave frequency and target sound wave power through a target optimization model, using sound wave frequency and sound wave power as optimization variables; wherein, the search range of the target optimization model is determined by the dust deposition dynamic factor. The control command generation unit 24 is used to convert the target acoustic wave frequency and target acoustic wave power into control commands to drive the acoustic wave cleaner to work.

[0072] Optionally, the first monitoring data includes: average flue gas velocity, flow field uniformity index, and temperature gradient value; the dust deposition dynamic factor calculation unit 22 is specifically used for: The ash accumulation risk factor is determined based on the average flue gas velocity, flow field uniformity index, and temperature gradient value. Based on boiler operating parameters, secondary monitoring data, and ash accumulation risk factors, dynamic factors of ash deposition are determined.

[0073] Optionally, the boiler operating parameters include: boiler load, coal calorific value, coal composition content, flue gas temperature, and pressure; the second monitoring data includes: dust thickness data sequence; the dust deposition dynamic factor calculation unit 22 is specifically used for: Deposition tendency factor is determined based on boiler load, coal calorific value, coal composition content, flue gas temperature and pressure. Determine the deposition fluctuation factor based on the dust thickness data sequence; Based on the deposition tendency factor, deposition fluctuation factor, and ash accumulation risk factor, the dynamic factors of dust deposition are determined.

[0074] Optionally, the objective optimization model employs an improved metaheuristic algorithm, with objective optimization unit 23 specifically used for: The search range of the target optimization model is dynamically adjusted based on the dynamic factors of dust deposition. When the dynamic factor of dust deposition increases, the search range of the target optimization model is expanded; When the dust deposition dynamic factor decreases, the search range of the objective optimization model is narrowed.

[0075] Optionally, the improved metaheuristic algorithm is a hybrid gray wolf optimization-particle swarm optimization algorithm, with objective optimization unit 23 specifically used for: The position weighting factor is dynamically adjusted and updated based on the dust deposition dynamic factor to obtain the updated weighting factor. Based on the updated weighting factors, at least one set of candidate solutions is determined, each candidate solution including a set of candidate acoustic frequencies and candidate acoustic powers.

[0076] Optionally, with acoustic frequency and acoustic power as optimization variables, the target optimization unit 23 is specifically used to: determine the target acoustic frequency and target acoustic power from at least one candidate solution set using a fitness function constructed with cleaning efficiency, energy consumption ratio and equipment life factor.

[0077] The control system provided in this application can acquire boiler operating parameters, first monitoring data, and second monitoring data during boiler system operation; determine the dust deposition dynamic factor based on the boiler operating parameters, first monitoring data, and second monitoring data; determine the target sound wave frequency and target sound wave power through a target optimization model, using sound wave frequency and sound wave power as optimization variables; wherein the search range of the target optimization model is determined by the dust deposition dynamic factor; and convert the target sound wave frequency and target sound wave power into control commands to drive the acoustic soot remover to work. This method can adaptively and dynamically adjust the sound wave frequency and sound wave power according to the actual operating conditions and ash accumulation status of the boiler, thereby improving the soot removal effect of the acoustic soot removal system.

[0078] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0079] The above description is merely a specific implementation example of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0080] Secondly, those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0081] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can 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, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0082] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0083] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0084] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0085] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0086] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0087] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0088] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for controlling soot cleaning by acoustic waves in a boiler, characterized by The method comprises: acquiring a boiler operation parameter, first monitoring data and second monitoring data during operation of a boiler system; determining a dust deposition dynamic factor based on the boiler operation parameter, the first monitoring data and the second monitoring data; determining a target acoustic frequency and a target acoustic power by a target optimization model, with the acoustic frequency and the acoustic power as optimization variables; wherein a search range of the target optimization model is determined by the dust deposition dynamic factor; converting the target acoustic frequency and the target acoustic power into a control instruction to drive an acoustic soot blower to work.

2. The method of claim 1, wherein, The first monitoring data comprises an average flue gas flow rate, a flow field uniformity index and a temperature gradient value; and the determination of the dust deposition dynamic factor based on the boiler operation parameter, the first monitoring data and the second monitoring data comprises: determining a soot deposition risk factor based on the average flue gas flow rate, the flow field uniformity index and the temperature gradient value; determining the dust deposition dynamic factor based on the boiler operation parameter, the second monitoring data and the soot deposition risk factor.

3. The method of claim 2, wherein, The boiler operation parameter comprises a boiler load, a coal heat value, a coal component content value, a flue gas temperature and a pressure value; the second monitoring data comprises a dust thickness data sequence; and the determination of the dust deposition dynamic factor based on the boiler operation parameter, the second monitoring data and the soot deposition risk factor comprises: determining a deposition tendency factor based on the boiler load, the coal heat value, the coal component content value, the flue gas temperature and the pressure value; determining a deposition fluctuation factor based on the dust thickness data sequence; determining the dust deposition dynamic factor based on the deposition tendency factor, the deposition fluctuation factor and the soot deposition risk factor.

4. The method of claim 1, wherein, The target optimization model adopts an improved meta-heuristic algorithm, and the improved meta-heuristic algorithm comprises: dynamically adjusting a search range of the target optimization model according to the dust deposition dynamic factor; when the dust deposition dynamic factor increases, expanding the search range of the target optimization model; when the dust deposition dynamic factor decreases, reducing the search range of the target optimization model.

5. The method of claim 4, wherein, The improved meta-heuristic algorithm is a hybrid grey wolf optimization-particle swarm optimization algorithm, and the hybrid grey wolf optimization-particle swarm optimization algorithm comprises: dynamically adjusting a position update weight factor according to the dust deposition dynamic factor to obtain an updated weight factor; determining at least one candidate solution set according to the updated weight factor, wherein each candidate solution comprises a set of candidate acoustic frequencies and candidate acoustic powers.

6. The method of claim 5, wherein, The determination of the target acoustic frequency and the target acoustic power by the target optimization model with the acoustic frequency and the acoustic power as optimization variables comprises: determining the target acoustic frequency and the target acoustic power from the at least one candidate solution set by using a fitness function constructed by a soot removal efficiency, an energy consumption ratio and a device life factor.

7. A soot control system for a boiler, comprising: The method comprises: a data acquisition unit configured to acquire a boiler operation parameter, first monitoring data and second monitoring data during operation of a boiler system; A dust deposition dynamic factor calculation unit is configured to determine a dust deposition dynamic factor based on the boiler operation parameters, the first monitoring data, and the second monitoring data. A target optimization unit is configured to determine a target acoustic wave frequency and a target acoustic wave power by taking the acoustic wave frequency and the acoustic wave power as optimization variables and using a target optimization model, wherein a search range of the target optimization model is determined by the dust deposition dynamic factor. A control instruction generation unit is configured to convert the target acoustic wave frequency and the target acoustic wave power into a control instruction to drive the acoustic wave soot blower to work.

8. The acoustic soot cleaning control system in a boiler as claimed in claim 7, wherein, The first monitoring data includes an average flue gas flow rate, a flow field uniformity index, and a temperature gradient value. The dust deposition dynamic factor calculation unit is specifically configured to: determine a dust deposition risk factor based on the average flue gas flow rate, the flow field uniformity index, and the temperature gradient value; and 9. The acoustic soot cleaning control system for a boiler as claimed in claim 8, wherein, determine the dust deposition dynamic factor based on the boiler operation parameters, the second monitoring data, and the dust deposition risk factor. The boiler operation parameters include a boiler load, a coal heat value, a coal component content value, a flue gas temperature, and a pressure value. The second monitoring data includes a dust thickness data sequence. The dust deposition dynamic factor calculation unit is specifically configured to:

10. The acoustic soot cleaning control system for a boiler as claimed in claim 7, wherein, determine a deposition tendency factor based on the boiler load, the coal heat value, the coal component content value, the flue gas temperature, and the pressure value; determine a deposition fluctuation factor based on the dust thickness data sequence; and determine the dust deposition dynamic factor based on the deposition tendency factor, the deposition fluctuation factor, and the dust deposition risk factor. The target optimization model uses an improved meta-heuristic algorithm. The target optimization unit is specifically configured to: dynamically adjust the search range of the target optimization model according to the dust deposition dynamic factor; expand the search range of the target optimization model when the dust deposition dynamic factor increases; and narrow the search range of the target optimization model when the dust deposition dynamic factor decreases.

Images