Acoustic decoking control system and method for boiler interior

Abstract

The present invention relates to the field of data processing technology, and in particular to an acoustic decoking control system and method for use inside a boiler. The method comprises: real-time collection of coke scale thickness data inside the boiler; optimizing a bat algorithm based on the coke scale thickness data, including: determining the degree of change in the coke scale data within a reference period at the current moment, sequentially determining the fitness value of each solution in each iteration at the current moment, the search frequency range optimization factor, and optimizing the search frequency range upper limit to complete the optimization of the bat algorithm; utilizing the optimized bat algorithm to control the acoustic wave frequency during the acoustic decoking process, so as to achieve acoustic decoking control inside the boiler. The present invention realizes intelligent control of the acoustic wave frequency based on the real-time boiler coke scale status through adaptive optimization of the bat algorithm, thereby significantly improving the intelligence level, control effect, and operating efficiency of the boiler decoking process.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an acoustic decoking control system and method for use inside a boiler. Background Art

[0002] With the promotion of energy conservation and emission reduction in the industrial sector, boilers, as key energy-consuming equipment, have a significant impact on energy consumption and emissions due to their operating efficiency. Coke accumulation within industrial boilers can reduce boiler efficiency and contribute to air pollution. Traditional decoking methods can consume significant amounts of energy and chemicals, while also providing unsatisfactory results. However, acoustic decoking technology can effectively remove boiler scale while also reducing emissions of greenhouse gases such as carbon dioxide, aligning with sustainable development trends.

[0003] As an intelligent optimization algorithm, the bat algorithm imitates the echolocation principle of bats to achieve intelligent adjustment of sound wave frequency. It can automatically adjust the optimal cleaning frequency according to the actual situation of coke accumulation 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 sound wave frequency, the search frequency range of each solution in each round of iteration is a fixed value. The fixed search frequency range cannot be dynamically adjusted according to the iteration process or the quality of the solution. A large-scale exploration is required in the early stage of each iteration process, and a small-scale fine search is required in the later stage. The fixed range will limit the adaptability of the bat algorithm. At the same time, the setting of the fixed search frequency range cannot flexibly control the search breadth and speed of the optimal solution for the sound wave frequency at the current moment according to the coke scale situation in the boiler at each moment. 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 for the sound wave frequency at the current moment, so as to improve the accuracy of the bat algorithm. When the coke scale changes more regularly in a period of time before the current moment, the search frequency range can be appropriately reduced to reduce the search breadth for the optimal solution for the sound wave frequency at the current moment, so as to improve the computational efficiency of the bat algorithm, thereby 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 sound wave frequency, the search frequency range of each solution in each round of iteration is fixed in 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 cannot flexibly control the search breadth and speed of the optimal solution for the sound wave frequency at the current moment according to the coke scale thickness data in the boiler at each moment, thereby affecting the decoking efficiency and accuracy inside the boiler, the present invention provides an acoustic wave decoking control system and method for the inside of the boiler.

[0006] In a first aspect, the present invention provides an acoustic decoking control method for a boiler, which employs the following technical solutions:

[0007] The invention discloses an acoustic decoking control method for a boiler, comprising: optimizing a bat algorithm based on real-time collected coke scale thickness data inside the boiler, and using the optimized bat algorithm to control the acoustic wave frequency during the acoustic decoking process to achieve acoustic decoking control inside the boiler; in the process of optimizing the bat algorithm, determining the degree of change of the coke scale data within the reference period at the current moment according to the information entropy of the coke scale thickness data at all moments within the reference period at the current moment, and the difference between the angle value of the connecting line of the coke scale thickness data at each moment within the reference period at the current moment and the preset reference angle value, and obtaining the optimized search frequency of each solution of each iteration of the bat algorithm at the current moment. Range upper limit, completes the optimization of the bat algorithm, including: determining the fitness value of each solution in the current round of iteration at the current moment according to the energy consumption, coke thickness reduction, and the number of times each solution is selected as the optimal solution in each solution of the current round of iteration at the current moment; determining the search frequency range optimization factor of each solution in the current round of iteration at the current moment according to the degree of change of the coke data, the fitness value, the number of iterations of the current round, and the preset adjustment coefficient; using the search frequency range optimization factor as a weight, weighting the search frequency range upper limit in the bat algorithm, and obtaining the optimized search frequency range upper limit of each solution in the current round of iteration at the current moment.

[0008] By incorporating information about the coke scale thickness variation (information entropy, line angle differences, etc.) within a reference period, the present invention achieves dynamic adaptive adjustment of the search frequency range. This enables the Bat Algorithm to conduct large-scale exploration in the early iterations and small-scale, refined searches in the later stages, improving the algorithm's global search capability and local search accuracy. Based on the varying characteristics of coke scale thickness and the fitness of each solution, the upper limit of the search frequency range is dynamically optimized, enhancing the algorithm's adaptability under different boiler operating conditions and avoiding the search efficiency and accuracy bottlenecks caused by a fixed range. By adjusting the search frequency range in real time, the algorithm effectively balances search speed and breadth, improving the accuracy and computational efficiency of acoustic frequency adjustment, and thus optimizing the decoking effect within the boiler. When coke scale variations are unstable, the search range is increased to ensure search breadth and avoid missing the optimal solution. When coke scale variations are relatively stable, the search range is reduced to ensure that computing resources are focused on fine-tuning, thereby enhancing system stability and the sustainability of the decoking effect. By optimizing acoustic decoking control, the efficiency and accuracy of coke scale removal are improved, effectively reducing the risk of blockage and energy loss during boiler operation, extending equipment life, and reducing maintenance costs.

[0009] Furthermore, the coke scale thickness data is obtained by using an ultrasonic thickness meter to collect initial data of the coke scale thickness inside the boiler, and performing digital conversion on the initial data of the coke scale thickness to obtain the coke scale thickness data.

[0010] Furthermore, the reference time period of the current moment is a time period consisting of several moments before the current moment.

[0011] Furthermore, the degree of data change disorder satisfies:

[0012] Where, is the degree of change of coke scale data in the reference period at the current moment, is the information entropy of the coke thickness data at all times within the reference period at the current moment, is the number of moments in the reference period of the current moment, The time in the reference period of the current moment The angle value of the line connecting the coke thickness data is is the preset reference angle value, is the standard normalization function, is the absolute value symbol.

[0013] The present invention defines an index of the degree of data change chaos and comprehensively considers the weighted sum of information entropy and connection angle deviation, which can accurately reflect the variation amplitude and instability of coke scale thickness data within a reference period, and provide 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, improve the adaptability of the bat algorithm in situations of drastic or irregular changes, and avoid falling into local optimal solutions.

[0014] Furthermore, the method for obtaining the connection angle value is: using the time series as the horizontal coordinate and the coke thickness data as the vertical coordinate, constructing a plane coordinate system of the coke thickness data at each moment in the reference period of the current moment, connecting the corresponding data points of each moment in the reference period of the current moment and the two adjacent moments on the plane coordinate system, and obtaining the connection angle value of the coke thickness data at each moment in the reference period of the current moment.

[0015] The present invention constructs a plane coordinate system by combining the time series and coke scale thickness data, connects the data points at adjacent moments and calculates the angle, which effectively depicts the geometric characteristics of the coke scale thickness changing with time and can reflect the changing speed and trend of the data.

[0016] Furthermore, the fitness value satisfies:

[0017] Where, For the current moment The first iteration The fitness value of a solution, For the current moment The first iteration The energy consumption in the solution is For the current moment The first iteration The reduction in coke thickness in each solution is For the current moment The first iteration The number of times a solution is selected as the optimal solution, is the standard normalization function, is the natural exponential function.

[0018] The fitness value of the present invention is comprehensively calculated through three factors: normalized energy consumption, reduction in coke thickness and exponential decay of the number of times the optimal solution is selected, which fully reflects the comprehensive advantages and disadvantages of the solution in energy saving, descaling effect and historical optimization performance; multiplying the normalized value of energy consumption by the exponential decay of descaling reduction helps to encourage energy conservation while improving descaling efficiency, achieve balanced optimization of multiple objectives, and effectively promote the economy and practicality of the solution; combining historical optimization conditions with current performance, dynamically adjust the fitness evaluation of each solution, and enhance the intelligent adaptability and optimization efficiency of the bat algorithm for the boiler descaling process.

[0019] Furthermore, the energy consumption is the energy consumption generated by the sonic sootblower within a preset time period when processing coke deposits consistent with the coke deposit thickness data at the current moment in each solution of the current iteration.

[0020] Furthermore, the coke deposit thickness reduction amount is the coke deposit thickness reduction amount within a preset time period when processing coke deposits consistent with the coke deposit thickness data at the current moment in each solution of the current iteration at the current moment.

[0021] Furthermore, the search frequency range optimization factor satisfies:

[0022] Where, For the current moment The first iteration The optimization factor of the search frequency range of a solution, is the degree of change of coke scale data in the reference period at the current moment, For the current moment The first iteration The fitness value of a solution, For the current moment The minimum fitness value of all solutions in the round iteration, is the total number of iterations, For the The number of iterations of the round, is the preset adjustment coefficient, is the standard normalization function, is the natural exponential function.

[0023] The present invention combines the degree of change of coke scale data, the ratio of the current solution fitness to the minimum value of the global optimal fitness, and the exponential decay of the iterative progress, so that the search frequency range optimization factor can be obtained and the search intensity can be flexibly adjusted according to actual conditions; the exponential term decreases as the number of iterations increases, so that the search frequency range gradually converges from a larger range to a smaller range, thereby improving the global exploration and local development capabilities of the algorithm.

[0024] In a second aspect, the present invention provides an acoustic decoking control system for use inside a boiler, employing the following technical solutions:

[0025] An acoustic decoking control system for use inside a boiler includes a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, the acoustic decoking control method for use inside a boiler is implemented.

[0026] By adopting the above technical solution, the above-mentioned acoustic decoking control method for the interior of the boiler is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0027] The present invention has the following technical effects:

[0028] (1) The present invention introduces a dynamic optimization mechanism to adaptively adjust 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, the present invention can dynamically adjust the search granularity according to the current working conditions, so that the algorithm has a strong global search capability in the early stage and improves the local fine search capability in the later stage, effectively balancing the relationship between global exploration and local development, and improving the overall optimization efficiency and stability of the algorithm.

[0029] (2) By analyzing the difference between the information entropy and trend angle of the coke scale thickness data and the preset reference angle, the severity of the coke scale thickness change can be accurately identified, thereby deciding 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, thereby ensuring the accuracy and responsiveness of the acoustic wave frequency control.

[0030] (3) The search frequency range optimization strategy of the present invention enables faster coverage of more solution spaces when the coke scale fluctuations are large, reduces redundant calculations when the coke scale trend is stable, improves the algorithm convergence speed, significantly optimizes the real-time response capability and computing resource utilization efficiency of the boiler acoustic decoking control system, and improves the decoking efficiency and accuracy inside the boiler.

[0031] (4) The present invention realizes intelligent control of the acoustic frequency based on the real-time boiler coke and fouling status through adaptive optimization of the bat algorithm, thereby significantly improving the intelligence level, control effect and operating efficiency of the boiler decoking process. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 This is a flow chart of a method for controlling acoustic decoking inside a boiler according to an embodiment of the present invention.

[0033] Figure 2 This is a method flow chart of step S2 in the acoustic decoking control method for a boiler according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0035] The embodiment of the present invention discloses a method for controlling the acoustic decoking inside a boiler, referring to Figure 1 , including steps S1 to S3:

[0036] S1: Real-time collection of coke scale thickness data inside the boiler.

[0037] Specifically, the coke scale thickness data is obtained as follows:

[0038] An ultrasonic thickness meter is used to collect the initial data of the coke scale thickness inside the boiler. The collection time is the entire decoking process. The initial data of the coke scale thickness is digitized using an analog-to-digital conversion device to obtain the coke scale thickness data.

[0039] Implementers can set the collection frequency according to specific implementation conditions, for example, 100 times / s.

[0040] S2: Based on the coke thickness data, optimize the bat algorithm, refer to Figure 2 In the process of optimizing the bat algorithm, step S2 includes steps S201 to S204, which are specifically as follows:

[0041] 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 decoking. During the process, the optimal search frequency range of each solution in each round of iteration when the bat algorithm is used to output the optimal solution for the acoustic frequency will be calculated. This is mainly based on the analysis of the changing characteristics of the coke scale thickness data and the characteristics of different solutions of the bat algorithm during the iteration process.

[0042] S201: Determine the degree of change of coke scale data within a reference period at the current moment.

[0043] It should be noted that the purpose of analyzing the variation characteristics of the coke scale thickness data is to enable more accurate calculations of the coke scale conditions (coke scale thickness data) within the boiler at each moment when the search frequency range for each solution is subsequently adapted. Therefore, when calculating the degree of variation of the coke scale data within the reference period at the current moment in this step, 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 variation chaos. However, if the variation of the coke scale thickness data exhibits a uniform decrease (this characteristic indicates a steady variation 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 for the acoustic wave frequency at the current moment, thereby improving the algorithm's computational efficiency), then information entropy alone is insufficient to quantify the degree of variation chaos. Therefore, it is necessary to continue analyzing the numerical changes in the coke scale thickness data at all adjacent moments within the reference period at the current moment to obtain a more accurate degree of variation chaos. Specifically, the greater the difference between the sum of the angles between the lines connecting the data points corresponding to the previous and next moments within the reference period at the current moment and 180°, the greater the degree of variation of the coke scale data within the reference period at the current moment.

[0044] The degree of change of the coke scale data in the reference period at the current moment is determined based on the information entropy of the coke scale thickness data at all moments in the reference period at the current moment and the difference between the angle value of the line connecting the coke scale thickness data at each moment in the reference period at the current moment and the preset reference angle value.

[0045] Specifically, the reference time period at the current moment is a time period consisting of several moments before the current moment.

[0046] The implementer can set the number of previous moments according to the specific implementation situation. For example, if the data is collected for a total of 30 seconds and the collection frequency is 100 times / s, each period will have 3000 moments. At the same time, to ensure that each moment has a reference period, the first calculation is performed 31 seconds after the start of decoking.

[0047] Specifically, the degree of data change disorder satisfies:

[0048] ;

[0049] Where, is the degree of change of coke scale data in the reference period at the current moment, is the information entropy of the coke thickness data at all times within the reference period at the current moment, is the number of moments in the reference period of the current moment, The time in the reference period of the current moment The angle value of the line connecting the coke thickness data is is the preset reference angle value, is the standard normalization function, is the absolute value symbol.

[0050] Implementers can set the reference angle value according to specific implementation conditions, for example, 180.

[0051] in, The larger the value is, the more times different values ​​appear in the coke scale thickness data at all times in the reference period at the current moment, and the greater the degree of change in the coke scale data in the reference period at the current moment. The larger it is, the greater the sum of the differences between the angle values ​​of the connecting lines at all moments in the reference period of the previous moment and 180°, which means that the greater the information entropy of the coke scale thickness data at all moments in the reference period of the current moment, the greater the credibility, and the greater the degree of change in the coke scale data in the reference period of the previous moment.

[0052] Specifically, the method for obtaining the connecting line angle value is:

[0053] Using the time series as the horizontal axis and the coke thickness data as the vertical axis, a plane coordinate system is constructed for the coke thickness data at each moment within the current reference period. Lines are connected between the data points at each moment within the current reference period and the two adjacent moments on the plane coordinate system to obtain the angle between the lines. For the first and last moments in a reference period, the data points corresponding to the first moment and the last moment of the previous reference period are connected (the data points corresponding to the first moment in the reference period at the start of calculation and the last moment collected at the first second after decoking are connected), and the data points corresponding to the last moment and the current moment are connected.

[0054] S202: Determine the fitness value of each solution of each iteration at the current moment.

[0055] It should be noted that in order to enable the algorithm to output the optimal solution more flexibly and accurately each time the optimal solution is output, it is also necessary to dynamically adjust the search frequency range based on the iterative process when the optimal solution is output and the quality of each solution in each round of iteration. Prior to this, it is necessary to construct a calculation formula for the fitness value of each solution in the iterative 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 impact of larger and smaller acoustic wave frequency values ​​on the quality assessment of the solution and ensure that the optimal solution can better fit the real-time coke scale thickness conditions, the specific construction is based on the following: when a solution (acoustic wave frequency value) processes coke with the same thickness as the current moment, the greater the energy consumption (obtained from historical data) within one minute, the lower the environmental value, the worse its preference, and the greater the fitness value; when a solution processes coke with the same thickness as the current moment, the fewer times it is selected as the optimal solution in the historical data, the worse its preference, and the greater its fitness value; when a solution processes coke with the same thickness as the current moment, the smaller the change in coke scale thickness within one minute, the worse its preference, and the greater its fitness value.

[0056] The fitness value of each solution in the current iteration is determined according to the energy consumption, the reduction in coke thickness, and the number of times each solution is selected as the optimal solution.

[0057] Specifically, the fitness value satisfies:

[0058] ;

[0059] Where, For the current moment The first iteration The fitness value of a solution, For the current moment The first iteration The energy consumption in the solution is For the current moment The first iteration The reduction in coke thickness in each solution is For the current moment The first iteration The number of times a solution is selected as the optimal solution, is the standard normalization function, is the natural exponential function.

[0060] Specifically, the energy consumption is the energy consumption generated by the sonic sootblower within a preset time period when processing coke deposits consistent with the coke deposit thickness data at the current moment in each solution of the current iteration.

[0061] Specifically, the coke deposit thickness reduction amount is the coke deposit thickness reduction amount within a preset time period when processing coke deposits consistent with the coke deposit thickness data at the current moment in each solution of the current iteration.

[0062] in, The larger the value is, the greater the energy consumption of the solution when processing the coke scale with the same thickness at the current moment, the lower the environmental value is, the worse the preference is, and the larger the fitness value is. The smaller it is, the lower the cleaning efficiency of the solution when dealing with coke deposits with the same thickness as the current moment, the worse its preference, and the larger its fitness value. The smaller it is, the worse the preference of the solution is, the greater the credibility is and the larger the fitness value is.

[0063] S203: Determine the search frequency range optimization factor of each solution in each iteration at the current moment.

[0064] It should be noted that after the fitness value formula is constructed, this step will analyze the quality of each solution in each iteration. Combined with the progress of each solution in the iteration process and the degree of change in the coke scale data within the reference period at the current moment, the search frequency range optimization factor for each solution in each iteration when the acoustic wave frequency is intelligently controlled at the current moment is calculated. Since the greater the degree of change in the coke scale data, and the worse the quality of each solution in each iteration at the current moment, and the earlier the solution in the iteration process, the larger the optimized search frequency range for this solution should be to ensure that the algorithm can more accurately output the optimal solution, the larger the search frequency range optimization factor for this solution will be; conversely, the smaller the search frequency range optimization factor will be.

[0065] The search frequency range optimization factor of each solution of the current iteration is determined according to the degree of change of the coke scale data, the fitness value, the number of iterations of the current iteration, and a preset adjustment coefficient.

[0066] Specifically, the search frequency range optimization factor satisfies:

[0067] ;

[0068] Where, For the current moment The first iteration The optimization factor of the search frequency range of a solution, is the degree of change of coke scale data in the reference period at the current moment, For the current moment The first iteration The fitness value of a solution, For the current moment The minimum fitness value of all solutions in the round iteration, is the total number of iterations, For the The number of iterations of the round, is the preset adjustment coefficient, is the standard normalization function, is the natural exponential function.

[0069] in, The larger the value is, the more irregular the change of the coke scale data in the reference period at the current moment is. The first iteration The larger the optimized search frequency range of a solution should be, the larger the search frequency range should be to ensure that the algorithm can output the optimal solution more accurately. The bigger it is. The larger the value, the more The first iteration The worse the quality of the solution ( The corresponding solution is The optimal solution of the round iteration), the larger the corresponding optimized search frequency range should be, the The bigger it is. The smaller it is, the smaller the number of iterations at the current moment when outputting the optimal solution is. It is more necessary to use a wide range and high frequency exploration to quickly locate the potential optimal area. Therefore, the corresponding optimized search frequency range should be larger. The bigger it is. represents an adjustment coefficient for adjusting the value range of the search frequency range optimization factor, exemplarily, ,pass Eventually it will Adjust the value to the range .

[0070] S204: Obtain the upper limit of the optimization search frequency range of each solution in each iteration at the current moment, and complete the optimization of the bat algorithm.

[0071] It should be noted that this step is based on the search frequency range optimization factor of each solution of each iteration at the current moment, and calculates the upper limit of the optimized search frequency range of each solution of each iteration at the current moment. The larger the search frequency range optimization factor of each solution of each iteration at the current moment, the more irregular the change of the coke scale thickness data in the reference period at the current moment, and the worse the quality of each solution of each iteration at the current moment and the earlier the position in the iterative process, then the larger the optimized search frequency range for this solution should be, 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 of each iteration at the current moment, the more regular the change of the coke scale thickness data in the reference period at the current moment, and the better the quality of each solution of each iteration at the current moment and the later the position in the iterative process, then the smaller the optimized search frequency range for this solution should be, to improve the computational efficiency of the algorithm.

[0072] Specifically, the upper limit of the optimization search frequency range satisfies:

[0073] ;

[0074] Where, For the current moment The first iteration The upper limit of the optimal search frequency range for a solution, For the current moment The first iteration The optimization factor of the search frequency range of a solution, is the upper limit of the search frequency range in the bat algorithm, .

[0075] Among them, after the upper limit of the optimized search frequency range of each solution of this round of 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 of this round of iteration at the current moment is , complete the optimization of the bat algorithm.

[0076] S3: The optimized bat algorithm is used to control the acoustic frequency during the acoustic decoking process to achieve acoustic decoking control inside the boiler.

[0077] 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 sound 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 the optimal solutions of all iterations), the optimized bat algorithm is used to intelligently control the sound wave frequency during the sound wave decoking process inside the boiler, thereby completing the sound wave decoking control inside the boiler.

[0078] The implementer can set the parameters of the bat algorithm according to the specific implementation situation. For example, the number of solutions (i.e., the number of bats) randomly generated in the solution space in each iteration is an empirical value of 50; the solution space is an empirical value ; The range of the speed solution space is the empirical value The maximum number of iterations is 60, which is an empirical value. The initial loudness is 1, which is an empirical value. The loudness attenuation coefficient is 0.95, which is an empirical value. The pulse rate is 0.6, and the pulse enhancement coefficient is 0.08.

[0079] An embodiment of the present invention further discloses an acoustic decoking control system for use inside a boiler, comprising a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, an acoustic decoking control method for use inside a boiler according to the present invention is implemented.

[0080] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0081] The above are all preferred embodiments of the present invention, and are not intended to limit the scope of protection of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. An acoustic decoking control method for a boiler, characterized in that: include: Based on the real-time data on the thickness of coke deposits inside the boiler, the bat algorithm is optimized and used to control the frequency of the acoustic wave decoking process, thereby achieving acoustic decoking control inside the boiler. In the process of optimizing the bat algorithm, the degree of change of the coke scale data in the reference period at the current moment is determined based on the information entropy of the coke scale thickness data at all moments in the reference period at the current moment, and the difference between the angle value of the connecting line of the coke scale thickness data at each moment in the reference period at the current moment and the preset reference angle value. The upper limit of the optimization search frequency range of each solution of each iteration of the bat algorithm at the current moment is obtained to complete the optimization of the bat algorithm, including: Determining the fitness value of each solution in the current iteration at the current moment according to the energy consumption, the reduction in coke thickness, and the number of times each solution is selected as the optimal solution in the current iteration; According to the degree of change of the coke scale data, the fitness value, the number of iterations of this round, and the preset adjustment coefficient, the search frequency range optimization factor of each solution of this round of iteration at the current moment is determined; the search frequency range optimization factor is used as a weight to weight the search frequency range upper limit in the bat algorithm to obtain the optimized search frequency range upper limit of each solution of this round of iteration at the current moment.

2. The method for controlling the acoustic decoking inside a boiler according to claim 1, wherein: The method for obtaining the coke scale thickness data is as follows: An ultrasonic thickness meter is used to collect initial data of coke scale thickness inside the boiler, and the initial data of coke scale thickness is digitally converted to obtain coke scale thickness data.

3. The method for controlling the sonic decoking inside a boiler according to claim 1, wherein: The reference time period at the current moment is a time period consisting of several moments before the current moment.

4. The method for controlling the acoustic decoking inside a boiler according to claim 1, wherein: The degree of data change disorder meets the following requirements: ； Where, is the degree of change of coke scale data in the reference period at the current moment, is the information entropy of the coke thickness data at all times within the reference period at the current moment, is the number of moments in the reference period of the current moment, The time in the reference period of the current moment The angle value of the line connecting the coke thickness data is is the preset reference angle value, is the standard normalization function, is the absolute value symbol.

5. The method for controlling the sonic decoking inside a boiler according to claim 1 or 4, characterized in that: The method for obtaining the connecting line angle value is as follows: With the time series as the horizontal coordinate and the coke thickness data as the vertical coordinate, a plane coordinate system of the coke thickness data at each moment in the reference period of the current moment is constructed, and the corresponding data points at each moment in the reference period of the current moment and the two adjacent moments at each moment on the plane coordinate system are connected to obtain the angle value of the connecting line of the coke thickness data at each moment in the reference period of the current moment.

6. The method for controlling the acoustic decoking inside a boiler according to claim 1, wherein: The fitness value satisfies: ； Where, For the current moment The first iteration The fitness value of a solution, For the current moment The first iteration The energy consumption in the solution is For the current moment The first iteration The reduction in coke thickness in each solution is For the current moment The first iteration The number of times a solution is selected as the optimal solution, is the standard normalization function, is the natural exponential function.

7. The method for controlling the sonic decoking inside a boiler according to claim 1 or 6, wherein: The energy consumption is the energy consumption generated by the sonic sootblower within a preset time period when processing coke deposits consistent with the coke deposit thickness data at the current moment in each solution of the current iteration.

8. The method for controlling the sonic decoking inside a boiler according to claim 1 or 6, wherein: The coke scale thickness reduction amount is the coke scale thickness reduction amount within a preset time period when processing coke scale consistent with the coke scale thickness data at the current moment in each solution of the current iteration at the current moment.

9. The method for controlling the sonic decoking inside a boiler according to claim 1, wherein: The search frequency range optimization factor satisfies: ； Where, For the current moment The first iteration The optimization factor of the search frequency range of a solution, is the degree of change of coke scale data in the reference period at the current moment, For the current moment The first iteration The fitness value of a solution, For the current moment The minimum fitness value of all solutions in the round iteration, is the total number of iterations, For the The number of iterations of the round, is the preset adjustment coefficient, is the standard normalization function, is the natural exponential function.

10. The acoustic decoking control system used in boilers is characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the acoustic decoking control method for the interior of a boiler according to any one of claims 1 to 9 is implemented.

Images