Sound wave decoking control system and method used in boiler

Abstract

The invention relates to the technical field of data processing, in particular to a sound wave decoking control system and method used in a boiler. The method comprises the following steps: collecting coke scale thickness data in a boiler in real time; on the basis of the coke scale thickness data, optimizing the bat algorithm: determining a coke scale data change degree in a reference time period of the current moment, sequentially determining a fitness value of each solution of each round of iteration of the current moment, a search frequency range optimization factor and an optimization search frequency range upper limit, and completing the optimization of the bat algorithm; and the sound wave frequency in the sound wave decoking process is controlled through the optimized bat algorithm, so that sound wave decoking control in the boiler is achieved. Through adaptive optimization of the bat algorithm, intelligent sound wave frequency control based on the real-time boiler coke scale state is achieved, and therefore the intelligent level, the control effect and the operation efficiency of the boiler decoking process are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to an acoustic anti-coking control system and method for the inside of a boiler. Background Art

[0002] With the popularization of energy conservation and emission reduction in the industrial field, as an important energy-consuming device, the operating efficiency of a boiler directly affects energy consumption and emissions. The problem of coke deposition existing inside the boiler in industrial production will cause the boiler efficiency to decline and also cause air pollution. Traditional anti-coking methods may consume a large amount of energy and chemical agents, and at the same time, the cleaning effect is not satisfactory. While using the acoustic anti-coking technology can efficiently remove the scale inside the boiler, and at the same time, it can also reduce the emission of greenhouse gases such as carbon dioxide, which conforms to the trend of sustainable development.

[0003] As an intelligent optimization algorithm, the bat algorithm realizes the intelligent adjustment of the acoustic wave frequency by imitating the echolocation principle of bats, and can automatically adjust the optimal cleaning frequency according to the actual situation of coke deposition inside the boiler. It not only improves the efficiency and accuracy of boiler cleaning, but also promotes the application of intelligent control technology in the energy field, and improves the efficiency of industrial automation and intelligence.

[0004] However, when using the bat algorithm to intelligently control the acoustic wave frequency, the search frequency range of each solution in each iteration process is a fixed-size value. The fixed search frequency range cannot be dynamically adjusted according to the iteration process or the quality of the solution. In the early stage of each iteration process, a large range needs to be explored, and in the later stage, a small range needs to be searched finely. The fixed range will limit the adaptive ability of the bat algorithm. At the same time, the setting of the fixed search frequency range also cannot flexibly control the search breadth and speed for the optimal solution of the acoustic wave frequency at each moment inside the boiler. For example, when the coke scale changes unstably in a period of time before the current moment, it is necessary to increase the search frequency range to increase the search breadth for the optimal solution of the acoustic wave frequency at the current moment to improve the accuracy of the bat algorithm. When the change of the coke scale in a period of time before the current moment is relatively regular, the search frequency range can be appropriately reduced to reduce the search breadth for the optimal solution of the acoustic wave frequency at the current moment to improve the calculation efficiency of the bat algorithm, thus affecting the efficiency and accuracy of boiler cleaning. Summary of the Invention

[0005] In order to solve the problem that when using the bat algorithm to intelligently control the acoustic wave frequency, the search frequency range of each solution in each iteration process is of a fixed size, and the fixed search frequency range cannot be dynamically adjusted according to the iteration process or the quality of the solution. At the same time, the setting of the fixed search frequency range also cannot flexibly control the search breadth and speed for the optimal solution of the acoustic wave frequency at each moment based on the coke scale thickness data in the boiler at each moment, thus affecting the coke removal efficiency and accuracy inside the boiler. The present invention provides an acoustic wave coke removal control system and method for the inside of the boiler.

[0006] In a first aspect, the present invention provides an acoustic wave coke removal control method for the inside of the boiler, adopting the following technical solution: The acoustic wave coke removal control method for the inside of the boiler includes: based on the coke scale thickness data collected in real time inside the boiler, optimizing the bat algorithm, and using the optimized bat algorithm to control the acoustic wave frequency during the acoustic wave coke removal process to achieve the acoustic wave coke removal control inside the boiler; during the process of optimizing the bat algorithm, according to the information entropy of the coke scale thickness data at all moments within the reference period of the current moment, the difference between the included angle value of the connection lines of the coke scale thickness data at each moment within the reference period of the current moment and the preset reference angle value, determining the degree of change of the coke scale data within the reference period of the current moment, and obtaining the upper limit of the optimized search frequency range of each solution in each iteration of the bat algorithm at the current moment, completing the optimization of the bat algorithm, including: determining the fitness value of each solution in each iteration of the current moment according to the energy consumption, the reduction amount of the coke scale thickness, and the number of times each solution is selected as the optimal solution in each solution in each iteration of the current moment; determining the search frequency range optimization factor of each solution in each iteration of the current moment according to the degree of change of the coke scale data, the fitness value, the number of iterations of the current iteration, and the preset adjustment coefficient; using the search frequency range optimization factor as a weight to weight the upper limit of the search frequency range in the bat algorithm to obtain the upper limit of the optimized search frequency range of each solution in each iteration of the current moment.

[0007] The present invention realizes the dynamic adaptive adjustment of the search frequency range by combining the change information (such as information entropy, difference in connection angles, etc.) of the coke scale thickness data within the reference period, enabling the bat algorithm to conduct a large-scale exploration in the early stage of iteration and a small-scale fine search in the later stage, enhancing the global search ability and local search accuracy of the algorithm; based on the change characteristics of the coke scale thickness and the fitness of each solution, the upper limit of the search frequency range is dynamically optimized, enhancing the adaptability of the algorithm under different boiler operating conditions and avoiding the bottlenecks in search efficiency and accuracy caused by a fixed range; by adjusting the search frequency range in real time, the search speed and search breadth are effectively balanced, improving the accuracy and calculation efficiency of the acoustic wave frequency adjustment, thereby optimizing the coke removal effect inside the boiler; when the coke scale changes unstably, the search range is increased to ensure the search breadth and avoid missing the optimal solution; when the coke scale changes relatively stably, the search range is reduced to ensure that the computing resources are concentrated on fine tuning, enhancing the sustainable operation of the system and the coke removal effect; by optimizing the acoustic wave coke removal control, the efficiency and accuracy of coke scale removal are improved, effectively reducing the blockage risk and energy consumption loss during boiler operation, extending the equipment life and reducing the maintenance cost.

[0008] Further, the acquisition method of the coke scale thickness data is as follows: the initial data of the coke scale thickness inside the boiler is collected by using an ultrasonic thickness gauge, and the initial data of the coke scale thickness is digitally converted to obtain the coke scale thickness data.

[0009] Further, the reference period at the current moment is a time period composed of several moments before the current moment.

[0010] Further, the degree of chaos of the data change satisfies: ; in the formula, is the degree of change of the coke scale data within the reference period at the current moment, is the information entropy of the coke scale thickness data at all moments within the reference period at the current moment, is the number of moments within the reference period at the current moment, is the moment within the reference period at the current moment is the value of the connection angle of the coke scale thickness data, is the preset reference angle value, is the standard normalization function, is the absolute value symbol.

[0011] The present invention can accurately reflect the change range and instability of the fouling thickness data during the reference period by defining an index for the degree of chaos in data changes and comprehensively considering the weighted sum of information entropy and the deviation of the connection angle, providing a scientific basis for subsequent dynamic adjustment; due to the integration of information entropy and angle difference, it can effectively capture the complexity and volatility of data, improving the adaptability of the bat algorithm in cases of drastic or irregular changes and avoiding falling into local optimal solutions.

[0012] Further, the method for obtaining the connection angle value is as follows: taking the time sequence as the abscissa and the fouling thickness data as the ordinate, a plane coordinate system of the fouling thickness data at each moment during the reference period of the current moment is constructed. The data points corresponding to each moment and the two adjacent moments during the reference period of the current moment are connected on the plane coordinate system to obtain the connection angle value of the fouling thickness data at each moment during the reference period of the current moment.

[0013] The present invention constructs a plane coordinate system with the time sequence and the fouling thickness data, connects the data points of adjacent moments, and calculates the angle, effectively depicting the geometric characteristics of the change of the fouling thickness over time and being able to reflect the change speed and trend of the data.

[0014] Further, the fitness value satisfies: ; where is the fitness value of the th solution in the th iteration at the current moment, is the energy consumption in the th solution in the th iteration at the current moment, is the fouling thickness reduction in the th solution in the th iteration at the current moment, is the number of times the th solution in the th iteration at the current moment is selected as the optimal solution, is the standard normalization function, is the natural exponential function.

[0015] The fitness value of the present invention is comprehensively calculated by normalizing the three factors of energy consumption, fouling thickness reduction, and exponential decay of the number of times the optimal solution is selected, fully reflecting the overall advantages and disadvantages of the solution in terms of energy conservation, descaling effect, and historical optimization performance; multiplying the normalized value of energy consumption by the exponential decay of the descaling reduction helps to encourage energy conservation while improving the descaling efficiency, achieving balanced optimization of multiple objectives and effectively promoting the economy and practicality of the solution; combining the historical optimization situation with the current performance, dynamically adjusting the fitness evaluation of each solution, and improving the intelligent adaptability and optimization efficiency of the bat algorithm for the boiler descaling process.

[0016] Further, the energy consumption is the energy consumption generated by the acoustic sootblower within a preset time period when treating the fouling consistent with the fouling thickness data at the current moment in each solution of the current round of iteration at the current moment.

[0017] Further, the fouling thickness reduction amount is the fouling thickness reduction amount within a preset time period when treating the fouling consistent with the fouling thickness data at the current moment in each solution of the current round of iteration at the current moment.

[0018] Further, the search frequency range optimization factor satisfies: ; where is the search frequency range optimization factor of the th solution in the th round of iteration at the current moment, is the degree of change of the fouling data within the reference period at the current moment, is the fitness value of the th solution in the th round of iteration at the current moment, is the minimum value among the fitness values of all solutions in the th round of iteration at the current moment, is the total number of iterations, is the iteration number of the th round of iteration, is a preset adjustment coefficient, is the standard normalization function, is the natural exponential function.

[0019] By combining the degree of change of the fouling data, the ratio of the fitness of the current solution to the minimum value of the global optimal fitness, and the exponential decay of the iteration progress, the obtained search frequency range optimization factor can flexibly adjust the search intensity according to the actual situation; the exponential term decreases with the increase of the iteration number, so that the search frequency range gradually converges from a larger range to a smaller range, improving the global exploration and local development capabilities of the algorithm.

[0020] In a second aspect, the present invention provides an acoustic soot removal control system for the interior of a boiler, adopting the following technical solution: An acoustic soot removal control system for the interior of a boiler includes: a processor and a memory, where the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned acoustic soot removal control method for the interior of a boiler is implemented.

[0021] By adopting the above technical solution, the above-mentioned acoustic soot removal control method for the interior of a boiler is generated into a computer program and stored in the memory, so as to be loaded and executed by the processor, and thus a terminal device is manufactured according to the memory and the processor, which is convenient to use.

[0022] The present invention has the following technical effects: (1) By introducing a dynamic optimization mechanism, the present invention adaptively adjusts the search frequency range of each solution in each iteration according to the historical change trend of the coke scale thickness inside the boiler. Compared with the traditional bat algorithm with a fixed frequency range, it can dynamically adjust the search granularity according to the current working conditions, enabling the algorithm to have strong global search ability in the initial stage and enhancing the local fine search ability in the later stage. It effectively balances the relationship between global exploration and local development, and improves the overall optimization efficiency and stability of the algorithm.

[0023] (2) Through the differential analysis of the information entropy of the coke scale thickness data, the trend included angle and the preset reference angle, the severity of the change in the coke scale thickness can be accurately identified, so as to determine whether it is necessary to expand the search frequency range to increase the search breadth of the optimal frequency or narrow the range to improve the search accuracy, ensuring the accuracy and responsiveness of the acoustic wave frequency control.

[0024] (3) The search frequency range optimization strategy of the present invention enables it to quickly cover more solution spaces when the coke scale fluctuates greatly, and reduce redundant calculations when the coke scale trend is stable, improving the algorithm convergence speed, significantly optimizing the real-time response ability and computational resource utilization efficiency of the boiler acoustic wave coke removal control system, and improving the coke removal efficiency and accuracy inside the boiler.

[0025] (4) Through the adaptive optimization of the bat algorithm, the present invention realizes the intelligent control of the acoustic wave frequency based on the real-time coke scale state of the boiler, thus significantly improving the intelligent level, control effect and operation efficiency of the boiler coke removal process. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is the flowchart of the method for acoustic wave coke removal control inside the boiler in an embodiment of the present invention.

[0027] Figure 2 is the flowchart of step S2 in the method for acoustic wave coke removal control inside the boiler in an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0029] An embodiment of the present invention discloses a method for acoustic wave coke removal control inside a boiler, referring to Figure 1 , including steps S1 - S3: S1: Collect the data of the coke scale thickness inside the boiler in real time.

[0030] Specifically, the method for obtaining the coke scale thickness data is as follows: Use an ultrasonic thickness gauge to collect the initial data of the coke scale thickness inside the boiler. The collection duration is the entire coke removal process. Digitalize the initial data of the coke scale thickness using an analog-to-digital conversion device to obtain the coke scale thickness data.

[0031] Implementers can set the collection frequency according to the specific implementation situation. For example, 100 times / s.

[0032] S2: Optimize the bat algorithm based on the coke scale thickness data. Refer to Figure 2 , in the process of optimizing the bat algorithm, step S2 includes steps S201 - S204, which are specifically as follows: It should be noted that the core purpose of the present invention is to use the bat algorithm to intelligently control the acoustic frequency of the acoustic soot blower during acoustic coke removal. During the process, the optimized search frequency range of each solution in each iteration process when using the bat algorithm to output the optimal solution for the acoustic frequency will be calculated. The main basis is the analysis of the change characteristics of the coke scale thickness data and the characteristics of different solutions during the iteration process of the bat algorithm.

[0033] S201: Determine the degree of change of the coke scale data within the reference period at the current moment.

[0034] It should be noted that the purpose of analyzing the change characteristics of the coke scale thickness data is that when adapting the search frequency range of each solution in the subsequent process, more accurate calculations can be performed according to the coke scale situation (coke scale thickness data) inside the boiler corresponding to each moment. Then, when calculating the degree of change of the coke scale data within the reference period at the current moment, the greater the information entropy of the coke scale thickness data at all moments within the reference period at the current moment, the greater the degree of change chaos can be indicated; however, when the change of the coke scale thickness data shows a characteristic of uniform decrease (this characteristic belongs to the stable change of the coke scale thickness data. In this case, the algorithm can appropriately reduce the search frequency range to reduce the search breadth for the optimal solution of the acoustic frequency at the current moment to improve the calculation efficiency of the algorithm), then the information entropy alone is not sufficient to quantify the degree of change chaos; therefore, it is necessary to continue to analyze the numerical changes of the coke scale thickness data at all adjacent moments within the reference period at the current moment to obtain a more accurate degree of change chaos. When specifically analyzing, the greater the difference between the included angle value of the line connecting the data points corresponding to all moments within the reference period at the current moment and their previous and next moments and 180°, the greater the degree of change of the coke scale data within the reference period at the current moment.

[0035] Determine the degree of change of the fouling data within the reference period of the current moment based on the information entropy of the fouling thickness data at all moments within the reference period of the current moment and the difference between the included angle value of the connection lines of the fouling thickness data at each moment within the reference period of the current moment and the preset reference angle value.

[0036] Specifically, the reference period of the current moment is a time period composed of several moments before the current moment.

[0037] Implementers can set the number of moments before according to the specific implementation situation. For example, a total of 30 seconds are collected, and the collection frequency is 100 times / s, then each period has 3000 moments. At the same time, to ensure that there is a reference period for each moment, the first calculation is performed 31 seconds after the start of defouling.

[0038] Specifically, the degree of chaos of the data change satisfies: ; In the formula, is the degree of change of the fouling data within the reference period of the current moment, is the information entropy of the fouling thickness data at all moments within the reference period of the current moment, is the number of moments within the reference period of the current moment, is the moment within the reference period of the current moment is the included angle value of the connection lines of the fouling thickness data, is the preset reference angle value, is the standard normalization function, is the absolute value symbol.

[0039] Implementers can set the reference angle value according to the specific implementation situation. For example, 180°.

[0040] Among them, The larger, the more times different values appear in the fouling thickness data at all moments within the reference period of the current moment, and the greater the degree of change of the fouling data within the reference period of the current moment. The larger, the greater the sum of the differences between the included angle values of all moments within the reference period of the previous moment and 180°, and the greater the credibility that the information entropy of the fouling thickness data at all moments within the reference period of the current moment is greater, and the greater the degree of change of the fouling data within the reference period of the previous moment.

[0041] Specifically, the method for obtaining the included angle value is: Taking the time sequence as the abscissa and the coke scale thickness data as the ordinate, a plane coordinate system of the coke scale thickness data at each moment within the reference period of the current moment is constructed. Connect the data points corresponding to each moment within the reference period of the current moment and the two adjacent moments at each moment on the plane coordinate system to obtain the included angle value of the connected lines of the coke scale thickness data at each moment within the reference period of the current moment. For the first moment and the last moment within the reference period, connect the data points corresponding to the first moment and the last moment of the previous reference period (for the first moment within the reference period starting from the first moment calculated, connect the data points corresponding to the first moment and the last moment collected at the last second of the start of coke removal), and connect the data points corresponding to the last moment and the current moment.

[0042] S202: Determine the fitness value of each solution for each iteration at the current moment.

[0043] It should be noted that in order to enable the algorithm to output the optimal solution more flexibly and accurately when outputting the optimal solution each time, it is also necessary to dynamically adjust the search frequency range in combination with the iteration process when outputting the optimal solution once and the quality of each solution during each iteration. Before that, it is necessary to construct the calculation formula for the fitness value of each solution during the iteration process to evaluate the quality of each solution. When constructing the calculation formula for the fitness value of each solution, in order to better balance the influence of the larger and smaller acoustic wave frequency values on the quality evaluation of the solution and ensure that the optimal solution can better fit the real-time coke scale thickness situation, the basis for the specific construction is as follows: when a solution (acoustic wave frequency value) is dealing with coke with the same coke scale thickness as the current moment, the greater the energy consumption within one minute (obtained from historical data), the lower the environmental protection value, the worse the preference degree, and the greater the fitness value; when a solution is dealing with coke with the same coke scale thickness as the current moment, the fewer the number of times it is selected as the optimal solution in historical data, the worse the preference degree, and the greater the fitness value; when a solution is dealing with coke with the same coke scale thickness as the current moment, the smaller the change in coke scale thickness within one minute, the worse the preference degree, and the greater the fitness value.

[0044] Determine the fitness value of each solution for each iteration at the current moment according to the energy consumption, the reduction amount of coke scale thickness, and the number of times each solution is selected as the optimal solution in each solution for the current iteration at the current moment.

[0045] Specifically, the fitness value satisfies: ; In the formula, is the fitness value of the th solution for the th iteration at the current moment, is the th iteration at the current moment, and the The energy consumption in a solution is the th scale of the fouling thickness reduction in a solution of the current iteration at the current moment is the th number of times a solution is selected as the optimal solution at the current moment is the standard normalization function is the natural exponential function

[0046] Specifically, the energy consumption is the energy consumption generated by the acoustic soot blower within a preset time period when processing fouling consistent with the fouling thickness data at the current moment in each solution of the current iteration at the current moment

[0047] Specifically, the scale of the fouling thickness reduction is the scale of the fouling thickness reduction within a preset time period when processing fouling consistent with the fouling thickness data at the current moment in each solution of the current iteration at the current moment

[0048] Among them The larger is, the greater the energy consumption generated by the solution when processing fouling consistent with the thickness at the current moment, the lower the environmental protection value, the worse the preference degree, and the larger the fitness value The smaller

[0049] S203: Determine the optimization factor of the search frequency range for each solution in each iteration at the current moment

[0050] It should be noted that after the construction of the fitness value formula, this step will analyze the quality of each solution in each iteration process, and calculate the optimization factor of the search frequency range for each solution in each iteration process when performing intelligent control on the acoustic wave frequency at the current moment in combination with the progress of each solution in the iteration process and the change degree of the fouling data within the reference period at the current moment. Since the greater the change degree of the fouling data, and at the same time the worse the quality of each solution in each iteration at the current moment and the more forward position in the iteration process, then the optimization search frequency range for this solution should be larger to ensure that the algorithm can output the optimal solution more accurately, so the optimization factor of the search frequency range for this solution will be larger; on the contrary, it will be smaller

[0051] Determine the optimization factor of the search frequency range for each solution in the current iteration at the current moment according to the change degree of the fouling data, the fitness value, the number of iterations of the current iteration, and a preset adjustment coefficient

[0052] Specifically, the search frequency range optimization factor satisfies: ; In the formula, is the search frequency range optimization factor of the th solution in the th iteration at the current moment, is the degree of change of fouling data within the reference period at the current moment, is the fitness value of the th solution in the th iteration at the current moment, is the minimum value among the fitness values of all solutions in the th iteration at the current moment, is the total number of iterations, is the number of iterations of the th iteration, is a preset adjustment coefficient, is the standard normalization function, is the natural exponential function.

[0053] Among them, The larger it is, the more irregular the change in the degree of fouling data within the reference period at the current moment is. Then, for the th solution in the th iteration at the current moment, the optimized search frequency range should be larger to ensure that the algorithm can output the optimal solution more accurately. Then is larger. The larger it is, the worse the quality of the th solution in the th iteration at the current moment is ( The corresponding solution is the optimal solution of the th iteration). The corresponding optimized search frequency range should be larger. Then is larger. The smaller it is, the smaller the number of iterations at the current moment when outputting the optimal solution. It needs to adopt wide-range high-frequency exploration to quickly locate the potential optimal area. Therefore, the corresponding optimized search frequency range should be larger. Then is larger. represents the adjustment coefficient for adjusting the value range of the search frequency range optimization factor. Exemplarily, , through will finally adjust the value of to the interval .

[0054] S204: Obtain the upper limit of the optimized search frequency range of each solution in each iteration at the current moment, and complete the optimization of the bat algorithm.

[0055] It should be noted that in this step, based on the search frequency range optimization factor of each solution in each iteration at the current moment, the upper limit of the optimized search frequency range of each solution in each iteration at the current moment is calculated. The larger the search frequency range optimization factor of each solution in each iteration at the current moment, it indicates that the change of the fouling thickness data in the reference period at the current moment is more irregular. At the same time, the quality of each solution in each iteration at the current moment is worse and it is in a more forward position in the iterative process. Then, the optimized search frequency range for this solution should be larger to ensure that the algorithm can output the optimal solution more accurately. On the contrary, the smaller the search frequency range optimization factor of each solution in each iteration at the current moment, it indicates that the change of the fouling thickness data in the reference period at the current moment is more regular. At the same time, the quality of each solution in each iteration at the current moment is better and it is in a more backward position in the iterative process. Then, the optimized search frequency range for this solution should be smaller to improve the calculation efficiency of the algorithm.

[0056] Specifically, the upper limit of the optimized search frequency range satisfies: ; In the formula, is the upper limit of the optimized search frequency range of the th solution in the th iteration at the current moment, is the search frequency range optimization factor of the th solution in the th iteration at the current moment, is the upper limit of the search frequency range in the bat algorithm, .

[0057] Among them, after the upper limit of the optimized search frequency range of each solution in the current iteration at the current moment, since the lower limit of the search frequency range is a fixed value of 0, the optimized search frequency range of each solution in the current iteration at the current moment is , and the optimization of the bat algorithm is completed.

[0058] S3: Use the optimized bat algorithm to control the acoustic wave frequency in the acoustic wave defouling process to achieve the acoustic wave defouling control inside the boiler.

[0059] After obtaining the optimized search frequency range of each solution in each iteration at the current moment when the bat algorithm performs intelligent control on the acoustic wave frequency (the optimal solution in each iteration is the solution corresponding to the minimum fitness value in each iteration, and the optimal solution at the current moment is the solution corresponding to the minimum fitness value among all the optimal solutions of the iterations), use the optimized bat algorithm to perform intelligent control on the acoustic wave frequency in the acoustic wave defouling process inside the boiler to complete the acoustic wave defouling control for the inside of the boiler.

[0060] Implementers can set the parameters of the bat algorithm according to specific implementation situations. For example, the number of solutions randomly generated in the solution space during each iteration (i.e., the number of bats) is an empirical value of 50; the solution space is an empirical value ; the range of solution-taking for the velocity is an empirical value ; the maximum number of iterations is an empirical value of 60; the initial loudness is an empirical value of 1; the loudness attenuation coefficient is an empirical value of 0.95; the pulse rate is an empirical value of 0.6; the pulse enhancement coefficient is an empirical value of 0.08.

[0061] The embodiment of the present invention also discloses an acoustic de-coking control system for the inside of a boiler, including a processor and a memory. The memory stores computer program instructions, which, when executed by the processor, implement the acoustic de-coking control method for the inside of a boiler according to the present invention.

[0062] The above system also includes other components well-known to those skilled in the art, such as a communication bus and a communication interface. Their settings and functions are known in the art, so they will not be elaborated here.

[0063] The above are all preferred embodiments of the present invention. The protection scope of the present invention is not limited thereby. Therefore, all equivalent changes made according to the structure, shape, and principle of the present invention shall be covered within the protection scope of the present invention.

Claims

1. An acoustic sootblowing control method for the inside of a boiler, characterized in that Including: Based on the coking scale thickness data collected in real time inside the boiler, optimize the bat algorithm, and use the optimized bat algorithm to control the acoustic frequency during the acoustic coke removal process, so as to achieve the acoustic coke removal control inside the boiler. During the process of optimizing the bat algorithm, according to the information entropy of the coking scale thickness data at all times within the reference period of the current moment, and the difference between the included angle value of the connection lines of the coking scale thickness data at each moment within the reference period of the current moment and the preset reference angle value, determine the degree of change of the coking scale data within the reference period of the current moment, and obtain the upper limit of the optimized search frequency range of each solution in each iteration of the bat algorithm at the current moment, thus completing the optimization of the bat algorithm, including: According to the energy consumption, the reduction amount of the coking scale thickness in each solution of the current iteration at the current moment, and the number of times each solution is selected as the optimal solution, determine the fitness value of each solution of the current iteration at the current moment. According to the degree of change of the coking scale data, the fitness value, the number of iterations of the current iteration, and the preset adjustment coefficient, determine the optimization factor of the search frequency range of each solution of the current iteration at the current moment; use the optimization factor of the search frequency range as the weight to weight the upper limit of the search frequency range in the bat algorithm, and obtain the upper limit of the optimized search frequency range of each solution of the current iteration at the current moment.

2. The acoustic sootblowing control method for the interior of a boiler according to claim 1, characterized in that, The acquisition method of the coking scale thickness data is as follows: Use an ultrasonic thickness gauge to collect the initial coking scale thickness data inside the boiler, and perform digital conversion on the initial coking scale thickness data to obtain the coking scale thickness data.

3. The acoustic sootblowing control method for the interior of a boiler according to claim 1, wherein The reference period of the current moment is a time period composed of several moments before the current moment.

4. The acoustic sootblowing control method for the inside of a boiler according to claim 1, wherein The degree of chaos of the data change satisfies: ； In the formula, is the degree of change in fouling data within the reference period at the current moment, is the information entropy of the fouling thickness data at all moments within the reference period at the current moment, is the number of moments within the reference period at the current moment, is the moment within the reference period at the current moment is the included angle value of the connection line of the fouling thickness data, is the preset reference angle value, is the standard normalization function, is the absolute value symbol.

5. The acoustic sootblowing control method for the inside of a boiler according to claim 1 or 4, characterized in that, The acquisition method of the included angle value of the connection lines is as follows: Taking time sequence as the abscissa and the coking scale thickness data as the ordinate, construct a plane coordinate system of the coking scale thickness data at each moment within the reference period of the current moment, connect the data points corresponding to each moment and the two adjacent moments within the reference period of the current moment on the plane coordinate system, and obtain the included angle value of the connection lines of the coking scale thickness data at each moment within the reference period of the current moment.

6. The acoustic sootblowing control method for the inside of a boiler according to claim 1, characterized in that, The fitness value satisfies: ； Wherein, is the fitness value of the -th solution in the -th iteration at the current moment, is the energy consumption in the -th solution in the -th iteration at the current moment, is the reduction amount of fouling thickness in the -th solution in the -th iteration at the current moment, is the number of times the -th solution in the -th iteration at the current moment is selected as the optimal solution, is the standard normalization function, is the natural exponential function.

7. The acoustic sootblowing control method for the interior of a boiler according to claim 1 or 6, characterized in that The energy consumption is the energy consumption generated by the acoustic soot blower within a preset time period when processing the coking scale consistent with the coking scale thickness data at the current moment in each solution of the current iteration at the current moment.

8. The acoustic sootblowing control method for the interior of a boiler according to claim 1 or 6, characterized in that The reduction amount of the coking scale thickness is the reduction amount of the coking scale thickness within a preset time period when processing the coking scale consistent with the coking scale thickness data at the current moment in each solution of the current iteration at the current moment.

9. The acoustic sootblowing control method for the inside of a boiler according to claim 1, wherein The optimization factor of the search frequency range satisfies: ； In the formula, is the search frequency range optimization factor of the th solution in the th iteration at the current moment, is the degree of change of fouling data within the reference period at the current moment, is the fitness value of the th solution in the th iteration at the current moment, is the minimum value among the fitness values of all solutions in the th iteration at the current moment, is the total number of iterations, is the number of iterations of the th iteration, is a preset adjustment coefficient, is the standard normalization function, is the natural exponential function.

10. The acoustic sootblowing control system for the inside of a boiler, characterized in that, Including: A processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the acoustic coke removal control method for the inside of the boiler according to any one of claims 1-9 is implemented.

Images