Coal powder pipe wind powder leveling method and system based on dynamic sensing and adjustment

Abstract

This invention provides a method and system for pulverized coal pipe air-coal leveling based on dynamic sensing and adjustment. The method collects electrostatic and microwave signals from each pulverized coal pipe, using these two non-contact signals for complementary verification. This avoids the problems of clogging and interference from pulverized coal particles inherent in traditional contact measurements. The data is fused to obtain confidence air velocity and confidence concentration. A benchmark pipe is determined based on confidence parameters and stability assessment, replacing manual experience-based judgment. A multi-objective collaborative optimization algorithm is used to manage both air velocity and concentration deviations, overcoming the limitations of single-parameter adjustment. Furthermore, fuzzy PID composite control is combined to drive the actuator based on the nonlinear relationship between the orifice opening and the air-coal flow, solving the adjustment lag problem. Ultimately, this method achieves real-time dynamic leveling of the air-coal flow, addressing the poor leveling effect of pulverized coal pipes in existing technologies.

Description

Technical Field

[0001] This invention relates to the field of combustion control technology for coal-fired power plant boilers, and in particular to a method and system for pulverized coal pipe air-coal leveling based on dynamic sensing and adjustment. Background Technology

[0002] In the operation system of a coal-fired power plant, pulverized coal ground by a coal mill needs to be transported to the boiler burner through multiple parallel pulverized coal pipelines to achieve complete combustion of the fuel. Under ideal operating conditions, the pulverized coal concentration and air velocity in all pulverized coal pipelines must be kept consistent, that is, to achieve air-coal leveling. This is a key prerequisite for ensuring the efficient, stable, and safe operation of the boiler.

[0003] However, due to various factors such as differences in pipeline layout, long-term wear and tear, coal quality fluctuations, and load variations, the air-coal flow distribution among the pulverized coal pipelines often exhibits severe unevenness during actual operation. This uneven air-coal distribution directly leads to adverse consequences such as unstable combustion in the furnace, flame center deviation, localized high temperatures, boiler coking, and increased NOx emission concentrations. This not only significantly reduces boiler combustion efficiency and wastes energy but may also trigger major safety accidents such as fire extinguishing and deflagration, seriously threatening the stable production and operational safety of coal-fired power plants.

[0004] To address the issue of uneven coal-airflow, existing technologies have developed corresponding measurement and regulation methods. In terms of measurement, traditional methods such as static pressure and differential pressure are primarily used to obtain parameters related to coal powder concentration and air velocity within the pipeline. In terms of regulation, mechanical structures such as adjustable orifices or baffles are often installed on the coal powder pipeline, and the air-coal flow state within the pipeline is adjusted based on offline test data or the operational experience of personnel. From a regulation logic perspective, existing technologies mostly focus on controlling a single parameter, that is, adjusting only the air velocity or optimizing only the coal powder flow rate, without considering air velocity and coal powder concentration as core parameters for coordinated regulation. Furthermore, existing technologies lack support from big data analysis and artificial intelligence technologies, failing to form an intelligent regulation system with self-learning and self-optimization capabilities, and relying entirely on traditional mechanical regulation and manual experience-based judgment. Summary of the Invention

[0005] This invention provides a method and system for leveling pulverized coal pipes based on dynamic sensing and adjustment, in order to solve the problem of poor leveling effect of pulverized coal pipes in the prior art.

[0006] On the one hand, the present invention provides a method for leveling pulverized coal in a pulverized coal pipe based on dynamic sensing and adjustment, comprising: Collect electrostatic and microwave signals from each pulverized coal pipeline; The electrostatic signal and microwave signal are fused and cross-verified to calculate the confidence wind speed and confidence concentration of each pulverized coal pipeline. Based on the confidence velocity and confidence concentration of the pulverized coal pipeline, and combined with stability assessment indicators, the benchmark pipeline under the current operating conditions is identified and determined. Calculate the wind speed deviation and concentration deviation between each coal powder pipeline to be adjusted (excluding the reference pipe) and the reference pipe; With minimizing the wind speed deviation and concentration deviation of all the coal powder pipelines to be adjusted as the optimization objective, the target opening of the electrically adjustable orifice corresponding to the coal powder pipeline to be adjusted is calculated through a multi-objective collaborative optimization algorithm. Based on the target opening, a control signal is generated by a fuzzy PID composite control algorithm to drive each of the electrically adjustable orifices to the target opening.

[0007] Optionally, the step of fusing and cross-verifying the electrostatic signal and microwave signal to calculate the confidence velocity and confidence concentration of each pulverized coal pipeline includes: The electrostatic signals collected by the electrostatic sensor are subjected to spectrum analysis and cross-correlation calculation to obtain the coal powder flow rate and relative concentration values; The coal powder concentration value is calculated based on the signal attenuation measured by the microwave concentration meter. The pulverized coal flow rate, the relative concentration value, and the pulverized coal concentration value are weighted, fused, and cross-validated to remove abnormal data, and the confidence velocity and confidence concentration of each pulverized coal pipeline are output.

[0008] Optionally, the pulverized coal flow rate, the relative concentration value, and the pulverized coal concentration value are weighted, fused, and cross-validated to remove outlier data, and the confidence velocity and confidence concentration of each pulverized coal pipeline are output, including: Calculate the difference between the relative concentration value and the coal powder concentration value, and determine whether the absolute difference exceeds a preset verification threshold. If the verification threshold is not exceeded, the relative concentration value and the coal powder concentration value are weighted and averaged according to a preset weight to obtain the confidence concentration, and the coal powder flow rate is used as the confidence wind speed. If the verification threshold is exceeded, a data anomaly is determined, and the confidence concentration and confidence wind speed are determined according to the preset anomaly handling logic. The preset exception handling logic is as follows: The relative concentration value and the pulverized coal concentration value with the smaller deviation are selected as the confidence concentration; or a substitute value is calculated by calling the historical concentration data of the pulverized coal pipeline as the confidence concentration. The coal powder flow rate calculated from the electrostatic signal is used as the confidence wind speed.

[0009] Optionally, the process of identifying and determining the benchmark pipe under the current operating conditions based on the confidence velocity and confidence concentration of each pulverized coal pipeline, combined with stability assessment indicators, includes: Calculate the mean and standard deviation of the confidence velocity and confidence concentration for all pulverized coal pipelines; A comprehensive stability scoring function is defined, and the comprehensive stability score of each pulverized coal pipeline is calculated based on the comprehensive stability scoring function. The pipe with the highest comprehensive stability score is selected and identified as the benchmark pipe under the current operating conditions.

[0010] Optionally, a comprehensive stability scoring function is defined, and based on the comprehensive stability scoring function, the comprehensive stability score of each pulverized coal pipeline is calculated, including: Based on the pipeline confidence velocity and confidence concentration, calculate the parameter proximity score of the pulverized coal pipeline; The volatility score of the pulverized coal pipeline is calculated based on the fluctuation range of the pipeline's operating wind speed and confidence concentration. Substitute the parameter proximity score and the volatility score into the comprehensive stability score function to obtain the comprehensive stability score; The comprehensive stability scoring function is: ; in, and The preset weighting coefficients, and .

[0011] Optionally, based on the pipeline confidence velocity and confidence concentration, a parameter proximity score for the pulverized coal pipeline is calculated, including: Calculate the average confidence velocity and the average confidence concentration of the pulverized coal pipeline; Substituting the average confidence wind speed and the average confidence concentration into the parameter proximity scoring function yields the parameter proximity score. The parameter proximity scoring function is as follows: ; in, To be confident about wind speed, For confidence concentrations, The average value of the confidence wind speed. The average of the confidence concentrations. and This is the preset positive adjustment coefficient.

[0012] Optionally, based on the fluctuation range of the pipeline's operating velocity and confidence concentration, a volatility score for the pulverized coal pipeline is calculated, including: Obtain the confidence wind speed sequence and confidence concentration sequence of the pulverized coal pipeline within a preset time window prior to the current moment; Calculate the standard deviations of the confidence wind speed series and the confidence concentration series respectively to obtain the standard deviations of the confidence wind speed series and the confidence concentration series. Substituting the standard deviation of the confidence wind speed series and the standard deviation of the confidence concentration series into the volatility scoring function yields the volatility score; The volatility scoring function is as follows: ; in, To determine the confidence level of the wind speed series standard deviation, The standard deviation of the confidence concentration series. and This is the preset positive adjustment coefficient.

[0013] Optionally, with minimizing the wind speed deviation and concentration deviation of all the pulverized coal pipelines to be adjusted as the optimization objective, a multi-objective collaborative optimization algorithm is used to calculate the target opening of the electrically adjustable orifice corresponding to the pulverized coal pipeline to be adjusted, including: Construct an objective function with the electrically adjustable orifice opening of the pulverized coal pipeline to be adjusted as the decision variable; The objective function constructed by the multi-objective collaborative optimization algorithm is: ; in, and The first The wind speed and concentration deviations between the pipe to be adjusted and the reference pipe are considered. and The weighting coefficients are dynamically adjusted. The total number of units to be adjusted; Solving the objective function yields the result that... The minimum set of optimal openings is taken as the target opening of the electrically adjustable orifice.

[0014] Optionally, based on the target opening, a control signal is generated using a fuzzy PID composite control algorithm to drive each of the electrically adjustable orifices to the target opening, including: Calculate the opening deviation and the rate of change of deviation between the actual opening of the electrically adjustable orifice and the target opening; A first threshold and a second threshold are set, wherein the first threshold is greater than the second threshold; When the absolute value of the opening deviation is greater than the first threshold, a fuzzy control algorithm is adopted: the opening deviation and the deviation change rate are used as inputs, the preset fuzzy control rule base is queried, and the first control signal is obtained and output. When the absolute value of the opening deviation is less than or equal to the second threshold, the system switches to the PID control algorithm, performs proportional, integral, and derivative operations based on the opening deviation, and obtains and outputs the second control signal.

[0015] On the other hand, the present invention also provides a pulverized coal pipe air-coal leveling system based on dynamic sensing and leveling, comprising: The data acquisition module is configured to acquire electrostatic and microwave signals from each pulverized coal pipeline; The data fusion module is configured to perform data fusion and cross-verification on the electrostatic signal and microwave signal, and calculate the confidence wind speed and confidence concentration of each of the pulverized coal pipelines. The reference tube identification module is configured to identify and determine the reference tube under the current operating conditions based on the confidence wind speed and confidence concentration of the pulverized coal pipeline, combined with stability evaluation indicators. The deviation calculation module is configured to calculate the wind speed deviation and concentration deviation between each coal powder pipeline to be adjusted and the reference pipe, excluding the reference pipe. The multi-objective optimization module is configured to minimize the wind speed deviation and concentration deviation of all the coal powder pipelines to be adjusted, and calculate the target opening of the electrically adjustable orifice corresponding to the coal powder pipeline to be adjusted through a multi-objective collaborative optimization algorithm. The control module is configured to generate a control signal based on the target opening using a fuzzy PID composite control algorithm, and drive each of the electrically adjustable orifices to move to the target opening.

[0016] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the pulverized coal pipe air-coal leveling method based on dynamic sensing and leveling as described above.

[0017] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the pulverized coal pipe air-coal leveling method based on dynamic sensing and leveling as described above.

[0018] On the other hand, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the pulverized coal pipe air-coal leveling method based on dynamic sensing and leveling as described above.

[0019] This invention provides a method and system for pulverized coal pipe air-coal leveling based on dynamic sensing and adjustment. The method collects electrostatic and microwave signals from each pulverized coal pipe, using these two non-contact signals for complementary verification. This avoids the problems of clogging and interference from pulverized coal particles inherent in traditional contact measurements. The data is fused to obtain confidence air velocity and confidence concentration. A benchmark pipe is determined based on confidence parameters and stability assessment, replacing manual experience-based judgment. A multi-objective collaborative optimization algorithm is used to manage both air velocity and concentration deviations, overcoming the limitations of single-parameter adjustment. Furthermore, fuzzy PID composite control is combined to drive the actuator based on the nonlinear relationship between the orifice opening and the air-coal flow, solving the adjustment lag problem. Ultimately, this method achieves real-time dynamic leveling of the air-coal flow, addressing the poor leveling effect of pulverized coal pipes in existing technologies. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 This is a schematic flowchart of the coal pulverizer pipe air-coal leveling method based on dynamic sensing and adjustment provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of the pulverized coal pipe air-powder leveling system based on dynamic sensing and adjustment provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0023] Figure 1 This is a schematic flowchart of the coal pulverizer pipe air-coal leveling method based on dynamic sensing and adjustment provided in an embodiment of the present invention.

[0024] like Figure 1 As shown in the embodiment of the present invention, the method for pulverized coal pipe air-coal leveling based on dynamic sensing and adjustment includes the following steps: 101. Collect electrostatic and microwave signals from each pulverized coal pipeline.

[0025] The acquisition of electrostatic and microwave signals can be achieved by installing electrostatic sensors and microwave concentration meters on the pulverized coal pipeline. The electrostatic sensors capture the electrostatic signals generated during the flow of pulverized coal, which include information related to the flow rate and relative concentration of the pulverized coal. The microwave concentration meter utilizes the propagation characteristics of microwaves in pulverized coal to calculate the pulverized coal concentration value by measuring the signal attenuation.

[0026] 102. Perform data fusion and cross-verification of electrostatic and microwave signals to calculate the confidence velocity and confidence concentration of each pulverized coal pipeline.

[0027] Among them, the confidence velocity and confidence concentration are parameters that more accurately and reliably reflect the actual situation inside the pulverized coal pipeline. Since the pulverized coal flow rate and relative concentration values ​​obtained by the electrostatic sensor and the pulverized coal concentration values ​​obtained by the microwave concentration meter may have errors, data fusion and verification can ensure the accuracy of the data to the greatest extent.

[0028] When fusing and verifying the two signals, it is necessary to perform spectral analysis and cross-correlation calculations on the electrostatic signal to obtain relevant parameters, while the concentration of the microwave signal is calculated based on its attenuation characteristics. This is because electrostatic and microwave signals each have their advantages and disadvantages in reflecting the flow characteristics of pulverized coal, and fusing and complementing them can improve the reliability of the data.

[0029] Specifically, the electrostatic and microwave signals are fused and cross-verified to calculate the confidence velocity and confidence concentration for each pulverized coal pipeline, including: The electrostatic signals collected by the electrostatic sensor are subjected to spectrum analysis and cross-correlation calculation to obtain the coal powder flow rate and relative concentration values; The coal powder concentration value is calculated based on the signal attenuation measured by the microwave concentration meter. The coal powder flow rate, relative concentration value and coal powder concentration value are weighted, fused and cross-validated, and abnormal data are removed to output the confidence velocity and confidence concentration of each coal powder pipeline.

[0030] In the process of collecting electrostatic signals and performing spectrum analysis, the characteristic spectrum and fluctuation law of the electrostatic signal generated by the friction of coal powder particles against the pipe wall are extracted. Then, the cross-correlation algorithm is used to process the signal to obtain the coal powder flow rate and relative concentration value in each coal powder pipeline.

[0031] Subsequently, based on the signal attenuation of the microwave emitted by the microwave concentration meter as it passes through the coal powder flow, the coal powder concentration value of the coal powder pipeline is calculated using a preset signal attenuation and coal powder concentration correspondence model.

[0032] Finally, the coal powder flow rate and relative concentration values ​​obtained above are weighted and fused with the coal powder concentration values ​​measured by the microwave method based on the accuracy weight allocation of the two measurement methods. At the same time, the consistency of the two sets of concentration data is compared by cross-validation, and abnormal data caused by instantaneous interference from the sensor is eliminated. Finally, the confidence wind speed and confidence concentration that can truly reflect the state of air-powder flow in the pipeline are output.

[0033] It is understood that cross-correlation algorithms are methods used to analyze the similarity between two signals. In this embodiment of the invention, they are mainly used to process electrostatic signals to obtain the coal powder flow rate and relative concentration values. Through cross-correlation algorithms, the correlation of electrostatic signals at different time points can be found, thereby determining the movement velocity and relative concentration of coal powder particles.

[0034] For spectral analysis, the cross-correlation algorithm mainly transforms the electrostatic signal from the time domain to the frequency domain to analyze the distribution of different frequency components in the signal. The electrostatic signal generated by the friction between pulverized coal particles and the pipe wall during flow contains rich frequency information, and characteristic frequencies related to the flow characteristics of pulverized coal can be extracted through spectral analysis.

[0035] In the data fusion and verification process, the weight allocation for weighted fusion is a crucial step. The weights need to be rationally determined based on factors such as the measurement accuracy and stability of the electrostatic sensor and the microwave concentration meter. For example, the weight of sensors with high measurement accuracy and good stability can be appropriately increased to ensure that the fused data more accurately reflects the actual situation.

[0036] Cross-validation compares concentration data obtained from different measurement methods to determine the consistency of the data. If the deviation between the two sets of data is within the allowable range, the data is considered reliable; if the deviation exceeds a preset threshold, further analysis is needed to determine the cause, which may be due to sensor malfunction, signal interference, or other issues. In this case, abnormal data needs to be removed.

[0037] Furthermore, real-time data processing is crucial in the entire pulverized coal leveling system. Since the pulverized coal flow state within the pipeline is dynamically changing, timely signal acquisition and processing are necessary to ensure the system can respond quickly and make effective adjustments. To achieve real-time data processing, high-performance processors and optimized data processing algorithms can be employed to improve the system's processing speed and efficiency.

[0038] In actual operation, regular maintenance and calibration of the system are also required. This includes checking the working status of the electrostatic sensors and microwave concentration meters to ensure their normal operation; and optimizing and adjusting the data processing algorithms to adapt to different operating conditions and environmental conditions. These measures can further improve the stability and reliability of the pulverized coal pipe air-coal leveling method and system based on dynamic sensing and regulation, achieving long-term stable leveling of the air-coal flow.

[0039] The process involves weighted fusion and cross-validation of pulverized coal flow rate, relative concentration, and pulverized coal concentration, removing outliers, and outputting the confidence velocity and confidence concentration for each pulverized coal pipeline, including: Calculate the difference between the relative concentration value and the coal powder concentration value, and determine whether the absolute difference exceeds the preset verification threshold. If the verification threshold is not exceeded, the relative concentration value and the coal powder concentration value are weighted and averaged according to the preset weight to obtain the confidence concentration, and the coal powder flow rate is used as the confidence wind speed. If the verification threshold is exceeded, a data anomaly is determined, and the confidence concentration and confidence wind speed are determined according to the preset anomaly handling logic. The default exception handling logic is as follows: Choose the relative concentration value with the smaller deviation from the pulverized coal concentration value as the confidence concentration; or use historical concentration data from the pulverized coal pipeline to calculate a substitute value as the confidence concentration. The coal powder flow rate calculated from the electrostatic signal is used as the confidence wind speed.

[0040] Specifically, after processing the electrostatic and microwave signals, the difference between the relative concentration value obtained by the electrostatic sensor and the coal powder concentration value measured by the microwave concentration meter is calculated first, and the absolute value of the difference is compared with the preset verification threshold to complete the cross-validation of the two measurement data.

[0041] If the absolute value of the difference does not exceed the preset verification threshold, it indicates that the two measurement results are in good agreement. At this time, the relative concentration value and the coal powder concentration value are weighted and averaged according to the preset weight to obtain a confidence concentration that can truly reflect the state of coal powder in the pipeline. At the same time, the coal powder flow rate calculated by combining the electrostatic signal with the cross-correlation algorithm is directly used as the confidence wind speed. If the absolute value of the difference exceeds the preset verification threshold, it is determined that there is a data anomaly. In this case, the confidence concentration is determined according to the preset anomaly handling logic. The preset anomaly handling logic is as follows: by comparing the deviations of the two concentration values ​​with the standard concentration under normal operating conditions in the same period of history, the one with the smaller standard concentration deviation is selected as the confidence concentration. In addition, the historical concentration data of the pulverized coal pipeline under the same coal quality and similar load conditions can be called, and the substitute value can be calculated as the confidence concentration through data interpolation or fitting.

[0042] The confidence wind speed still uses the electrostatic signal measurement results to ensure that even if a single measurement signal is abnormal, reliable confidence wind and dust flow parameters can still be output.

[0043] 103. Based on the confidence velocity and confidence concentration of the pulverized coal pipeline, and combined with stability assessment indicators, identify and determine the benchmark pipe under the current operating conditions.

[0044] Among them, determining the reference pipe can effectively reduce the impact of individual differences in pulverized coal pipelines and fluctuations in operating conditions, and provide a reliable reference standard for air-pulverized coal leveling.

[0045] Specifically, based on the confidence velocity and confidence concentration of each pulverized coal pipeline, and combined with stability assessment indicators, the benchmark pipeline under the current operating conditions is identified and determined, including: Calculate the mean and standard deviation of the confidence velocity and confidence concentration for all pulverized coal pipelines.

[0046] Specifically, the mean and standard deviation of the confidence wind speed and the mean and standard deviation of the confidence concentration for all pulverized coal pipelines are calculated. The mean is used to measure the overall central level of the pipeline wind speed parameter, and the standard deviation is used to reflect the overall degree of fluctuation of all pipeline parameters.

[0047] A comprehensive stability scoring function is defined, and the comprehensive stability score of each pulverized coal pipeline is calculated based on the comprehensive stability scoring function.

[0048] Specifically, a comprehensive stability scoring function is defined, and based on this function, the comprehensive stability score of each pulverized coal pipeline is calculated, including: Based on the pipeline's confidence velocity and confidence concentration, the parameter proximity score of the pulverized coal pipeline is calculated.

[0049] Among them, the parameter proximity score of the pulverized coal pipeline is calculated based on the pipeline's confidence velocity and confidence concentration, including: Calculate the average confidence velocity and the average confidence concentration of the pulverized coal pipeline.

[0050] Substituting the average confidence wind speed and the average confidence concentration into the parameter proximity scoring function yields the parameter proximity score.

[0051] The parameter proximity scoring function is as follows: ; in, To be confident about wind speed, For confidence concentrations, The average value of the confidence wind speed. The average of the confidence concentrations. and This is the preset positive adjustment coefficient.

[0052] The volatility score of the pulverized coal pipeline is calculated based on the fluctuation range of the pipeline's operating wind speed and confidence concentration.

[0053] Optionally, based on the fluctuation range of the pipeline's operating velocity and confidence concentration, a volatility score for the pulverized coal pipeline is calculated, including: Obtain the confidence wind speed sequence and confidence concentration sequence of the pulverized coal pipeline within a preset time window prior to the current moment.

[0054] Calculate the standard deviations of the confidence wind speed series and the confidence concentration series respectively to obtain the standard deviations of the confidence wind speed series and the confidence concentration series.

[0055] Substituting the standard deviations of the confidence wind speed series and the confidence concentration series into the volatility scoring function yields the volatility score.

[0056] The volatility scoring function is as follows: ; in, To determine the confidence level of the wind speed series standard deviation, The standard deviation of the confidence concentration series. and This is the preset positive adjustment coefficient.

[0057] Substituting the parameter proximity score and volatility score into the comprehensive stability score function yields the comprehensive stability score.

[0058] The overall stability scoring function is: ; in, and The preset weighting coefficients, and .

[0059] The pipe with the highest overall stability score is selected and identified as the benchmark pipe under the current operating conditions.

[0060] Among them, the comprehensive stability scores of all pulverized coal pipelines are ranked, and the pulverized coal pipeline with the highest score is selected as the benchmark pipe under the current operating conditions. The benchmark pipe ensures both the objectivity of the adjustment benchmark and the reliability of the benchmark state, avoiding the subjectivity and experience dependence of manually selecting the benchmark pipe.

[0061] 104. Calculate the wind speed deviation and concentration deviation between each coal powder pipeline to be adjusted and the reference pipeline, except for the reference pipeline.

[0062] Specifically, when calculating wind speed deviation and concentration deviation, the confidence wind speed and confidence concentration corresponding to the established benchmark tube are extracted. These two sets of parameters are standard reference values ​​that are stable and centrally located under the current operating conditions.

[0063] Subsequently, the confidence velocity and confidence concentration of all pulverized coal pipelines to be adjusted, excluding the reference pipeline, were acquired one by one. This ensured that the parameters of the pipelines to be adjusted and the reference pipeline were valid data collected synchronously under the same operating conditions and verified through data fusion, thus avoiding calculation distortions due to fluctuations in operating conditions. Next, the velocity deviation and concentration deviation of each pipeline to be adjusted were calculated separately. For example, under certain operating conditions, the confidence velocity of the reference tube is 26 m / s and the confidence concentration is 0.75 kg / m³, and the confidence velocity of the tube to be adjusted is 23.4 m / s and the confidence concentration is 0.825 kg / m³. Then the wind speed deviation is -2.6 m / s and the relative deviation is -10%.

[0064] By quantifying the differences in parameters between the pulverized coal pipeline to be adjusted and the benchmark pipeline, the leveling direction of each pulverized coal pipeline to be adjusted is clarified, and a precise quantitative basis is provided for the subsequent multi-objective collaborative optimization algorithm.

[0065] 105. With minimizing the wind speed deviation and concentration deviation of all pulverized coal pipelines to be adjusted as the optimization objective, the target opening of the electrically adjustable orifice corresponding to the pulverized coal pipeline to be adjusted is calculated through a multi-objective collaborative optimization algorithm.

[0066] Specifically, with the optimization objective of minimizing the wind speed and concentration deviations of all pulverized coal pipelines to be adjusted, a multi-objective collaborative optimization algorithm is used to calculate the target opening of the electrically adjustable orifice corresponding to the pulverized coal pipeline to be adjusted, including: Construct an objective function with the electrically adjustable orifice opening of the pulverized coal pipeline to be adjusted as the decision variable; The objective function constructed by the multi-objective collaborative optimization algorithm is: ; in, and The first The wind speed and concentration deviations between the pipe to be adjusted and the reference pipe are considered. and The weighting coefficients are dynamically adjusted. The total number of units to be adjusted; Solve the objective function to obtain the result that makes The minimum set of optimal openings is used as the target opening for each electrically adjustable orifice.

[0067] Specifically, when calculating the target opening of the electrically adjustable orifice using a multi-objective collaborative optimization algorithm, the decision variable is first defined as the electrically adjustable orifice opening corresponding to each pulverized coal pipeline to be adjusted (denoted as θ_i, where i is the pipeline number to be adjusted). Since the orifice opening directly changes the pipeline flow cross-section, it simultaneously affects the air velocity and pulverized coal concentration within the pipeline. Subsequently, an objective function is constructed to minimize the air velocity deviation and concentration deviation of all pulverized coal pipelines to be adjusted.

[0068] and Optimize in real time based on current coal quality, load conditions, and historical regulation effects; for example, increase the speed under high load conditions. Weighting ensures airflow stability; it can be increased when coal quality fluctuates greatly. Weighting ensures complete combustion. This represents the total number of pipes to be adjusted. The objective function amplifies the impact of larger deviations through a squared term, while using dynamic weights to balance the balancing priorities of wind speed and concentration.

[0069] Finally, the total objective value is obtained through numerical iteration. The minimum set of optimal orifice openings is the target opening of the electrically adjustable orifice for each pulverized coal pipe to be adjusted.

[0070] 106. Based on the target opening, a control signal is generated through a fuzzy PID composite control algorithm to drive each electrically adjustable orifice to the target opening.

[0071] Specifically, based on the target opening, a control signal is generated using a fuzzy PID composite control algorithm to drive each electrically adjustable orifice to the target opening, including: Calculate the opening deviation and the rate of change of deviation between the actual opening and the target opening of the electrically adjustable orifice; Set a first threshold and a second threshold, where the first threshold is greater than the second threshold; When the absolute value of the opening deviation is greater than the first threshold, the fuzzy control algorithm is adopted: the opening deviation and the rate of change of deviation are used as input, the preset fuzzy control rule base is queried, and the first control signal is obtained and output. When the absolute value of the opening deviation is less than or equal to the second threshold, the system switches to the PID control algorithm. Based on the opening deviation, it performs proportional, integral, and derivative operations to obtain and output the second control signal.

[0072] Specifically, when generating control signals and driving the electrically adjustable orifice reduction action through the fuzzy PID composite control algorithm, firstly, based on the position feedback device built into the electrically adjustable orifice reduction device, the actual opening degree of each orifice to be adjusted is collected in real time. Combined with the target opening degree calculated in the previous step, the opening degree deviation is calculated. At the same time, the opening degree deviation at adjacent moments is collected at fixed time intervals, and the deviation change rate is calculated. Both are used as input parameters of the fuzzy PID composite control algorithm to realize the dynamic perception of the orifice opening state.

[0073] Subsequently, a first threshold is set according to the response requirements of the coal pulverized pipeline air-coal flow adjustment, such as 5% of the opening range of the first threshold, denoted as Th1, and a second threshold is set, such as 1% of the opening range of the second threshold, denoted as Th2, and Th1 > Th2. The first threshold is used to determine the scenario where a large deviation requires rapid coarse adjustment, and the second threshold is used to determine the scenario where a small deviation requires precise fine adjustment.

[0074] When the absolute value of the opening deviation exceeds Th1, a fuzzy control algorithm is used for coarse adjustment. The opening deviation and the rate of change of deviation are fuzzified, and a preset fuzzy control rule base is queried. The fuzzy control rule base is constructed based on historical adjustment data and simulation results under different coal qualities and load conditions. It includes adjustment logic of large deviation + fast rate of change → large adjustment and medium deviation + slow rate of change → medium adjustment. After fuzzy inference and calculation, the first control signal is output. The first control signal drives the servo motor built into the orifice to move rapidly, quickly reducing the opening deviation in a large step and high response manner, avoiding leveling lag due to excessive deviation.

[0075] When the absolute value of the opening deviation is ≤Th2, the system automatically and smoothly switches to the PID control algorithm for fine-tuning. Based on the current opening deviation, proportional (P), integral (I), and derivative (D) operations are performed respectively. The proportional stage adjusts the adjustment force in real time according to the magnitude of the deviation, quickly responding to the remaining deviation. The integral stage accumulates historical deviations, gradually eliminating static errors and ensuring that the opening accurately matches the target value. The derivative stage predicts the trend of deviation changes and suppresses overshoot and oscillation during the adjustment process. After the three stages are calculated together, a second control signal is output to drive the servo motor to fine-tune in a small step and with high precision. Combined with the self-locking function of the orifice, vibration is avoided to prevent displacement, ensuring that the actual opening is stably maintained near the target value.

[0076] Based on the same inventive concept, this invention also protects a pulverized coal pipe air-powder leveling system based on dynamic sensing and leveling. The pulverized coal pipe air-powder leveling system based on dynamic sensing and leveling provided by this invention will be described below. The pulverized coal pipe air-powder leveling system based on dynamic sensing and leveling described below can be referred to in correspondence with the pulverized coal pipe air-powder leveling method based on dynamic sensing and leveling described above.

[0077] On the other hand, the present invention also provides a pulverized coal pipe air-coal leveling system based on dynamic sensing and leveling, comprising: The data acquisition module 210 is configured to acquire electrostatic and microwave signals from each pulverized coal pipeline; The data fusion module 220 is configured to perform data fusion and cross-verification of electrostatic signals and microwave signals, and calculate the confidence wind speed and confidence concentration of each pulverized coal pipeline. The reference tube identification module 230 is configured to identify and determine the reference tube under the current operating conditions based on the confidence wind speed and confidence concentration of the pulverized coal pipeline, combined with stability evaluation indicators. The deviation calculation module 240 is configured to calculate the wind speed deviation and concentration deviation between each coal powder pipeline to be adjusted and the reference pipe, except for the reference pipe. The multi-objective optimization module 250 is configured to minimize the total wind speed deviation and total concentration deviation of all pulverized coal pipelines to be adjusted, and calculate the target opening of the electrically adjustable orifice corresponding to the pulverized coal pipeline to be adjusted through a multi-objective collaborative optimization algorithm. The control module 260 is configured to generate control signals based on the target opening degree using a fuzzy PID composite control algorithm, and drive each electrically adjustable orifice to move to the target opening degree.

[0078] Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention.

[0079] like Figure 3 As shown, the electronic device may include a processor 310, a communication interface 320, a memory 330, and a communication bus 340. The processor 310, communication interface 320, and memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions from the memory 330 to execute a pulverized coal pipe air-coal leveling method based on dynamic sensing and leveling.

[0080] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0081] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the coal pulverizer pipe air-coal leveling method based on dynamic sensing and leveling provided by the above methods.

[0082] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the pulverized coal pipe air-coal leveling method based on dynamic sensing and leveling provided by the above methods.

[0083] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0084] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0085] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for leveling pulverized coal in a pulverized coal pipe based on dynamic sensing and adjustment, characterized in that, include: Collect electrostatic and microwave signals from each pulverized coal pipeline; The electrostatic signal and microwave signal are fused and cross-verified to calculate the confidence wind speed and confidence concentration of each pulverized coal pipeline. Based on the confidence velocity and confidence concentration of the pulverized coal pipeline, and combined with stability assessment indicators, the benchmark pipeline under the current operating conditions is identified and determined. Calculate the wind speed deviation and concentration deviation between each coal powder pipeline to be adjusted (excluding the reference pipe) and the reference pipe; With minimizing the wind speed deviation and concentration deviation of all the coal powder pipelines to be adjusted as the optimization objective, the target opening of the electrically adjustable orifice corresponding to the coal powder pipeline to be adjusted is calculated through a multi-objective collaborative optimization algorithm. Based on the target opening, a control signal is generated by a fuzzy PID composite control algorithm to drive each of the electrically adjustable orifices to the target opening.

2. The method for leveling pulverized coal pipe air based on dynamic sensing and adjustment according to claim 1, characterized in that, The process of fusing and cross-verifying the electrostatic and microwave signals to calculate the confidence velocity and confidence concentration for each pulverized coal pipeline includes: The electrostatic signals collected by the electrostatic sensor are subjected to spectrum analysis and cross-correlation calculation to obtain the coal powder flow rate and relative concentration values; The coal powder concentration value is calculated based on the signal attenuation measured by the microwave concentration meter. The pulverized coal flow rate, the relative concentration value, and the pulverized coal concentration value are weighted, fused, and cross-validated to remove abnormal data, and the confidence velocity and confidence concentration of each pulverized coal pipeline are output.

3. The method for leveling pulverized coal pipe air based on dynamic sensing and adjustment according to claim 2, characterized in that, The pulverized coal flow rate, relative concentration value, and pulverized coal concentration value are weighted, fused, and cross-validated to remove outlier data, and the confidence velocity and confidence concentration of each pulverized coal pipeline are output, including: Calculate the difference between the relative concentration value and the coal powder concentration value, and determine whether the absolute difference exceeds a preset verification threshold. If the verification threshold is not exceeded, the relative concentration value and the coal powder concentration value are weighted and averaged according to a preset weight to obtain the confidence concentration, and the coal powder flow rate is used as the confidence wind speed. If the verification threshold is exceeded, a data anomaly is determined, and the confidence concentration and confidence wind speed are determined according to the preset anomaly handling logic. The preset exception handling logic is as follows: The relative concentration value and the pulverized coal concentration value with the smaller deviation are selected as the confidence concentration; or a substitute value is calculated by calling the historical concentration data of the pulverized coal pipeline as the confidence concentration. The coal powder flow rate calculated from the electrostatic signal is used as the confidence wind speed.

4. The method for leveling pulverized coal pipe air based on dynamic sensing and adjustment according to claim 1, characterized in that, The process of identifying and determining the benchmark pipe under the current operating conditions based on the confidence velocity and confidence concentration of each pulverized coal pipeline, combined with stability assessment indicators, includes: Calculate the mean and standard deviation of the confidence velocity and confidence concentration for all pulverized coal pipelines; A comprehensive stability scoring function is defined, and the comprehensive stability score of each pulverized coal pipeline is calculated based on the comprehensive stability scoring function. The pipe with the highest comprehensive stability score is selected and identified as the benchmark pipe under the current operating conditions.

5. The method for leveling pulverized coal pipe air based on dynamic sensing and adjustment according to claim 4, characterized in that, A comprehensive stability scoring function is defined, and based on the comprehensive stability scoring function, the comprehensive stability score of each pulverized coal pipeline is calculated, including: Based on the pipeline confidence velocity and confidence concentration, calculate the parameter proximity score of the pulverized coal pipeline; The volatility score of the pulverized coal pipeline is calculated based on the fluctuation range of the pipeline's operating wind speed and confidence concentration. Substitute the parameter proximity score and the volatility score into the comprehensive stability score function to obtain the comprehensive stability score; The comprehensive stability scoring function is: ； in, and The preset weighting coefficients, and .

6. The method for leveling pulverized coal pipe air based on dynamic sensing and adjustment according to claim 5, characterized in that, Based on the pipeline's confidence velocity and confidence concentration, a parameter proximity score for the pulverized coal pipeline is calculated, including: Calculate the average confidence velocity and the average confidence concentration of the pulverized coal pipeline; Substituting the average confidence wind speed and the average confidence concentration into the parameter proximity scoring function yields the parameter proximity score. The parameter proximity scoring function is as follows: ； in, To be confident of wind speed, For confidence concentrations, The average value of the confidence wind speed. The average of the confidence concentrations. and This is the preset positive adjustment coefficient.

7. The method for leveling pulverized coal pipe air based on dynamic sensing and adjustment according to claim 5, characterized in that, Based on the fluctuation range of the pipeline's operating velocity and confidence concentration, a volatility score for the pulverized coal pipeline is calculated, including: Obtain the confidence wind speed sequence and confidence concentration sequence of the pulverized coal pipeline within a preset time window prior to the current moment; Calculate the standard deviations of the confidence wind speed series and the confidence concentration series respectively to obtain the standard deviations of the confidence wind speed series and the confidence concentration series. Substituting the standard deviation of the confidence wind speed series and the standard deviation of the confidence concentration series into the volatility scoring function yields the volatility score; The volatility scoring function is as follows: ； in, To determine the confidence level of the wind speed series standard deviation, The standard deviation of the confidence concentration series. and This is the preset positive adjustment coefficient.

8. The method for leveling pulverized coal pipe air based on dynamic sensing and adjustment according to claim 1, characterized in that, With the optimization objective of minimizing the wind speed and concentration deviations of all the pulverized coal pipelines to be adjusted, a multi-objective collaborative optimization algorithm is used to calculate the target opening of the electrically adjustable orifice corresponding to each pulverized coal pipeline to be adjusted, including: Construct an objective function with the electrically adjustable orifice opening of the pulverized coal pipeline to be adjusted as the decision variable; The objective function constructed by the multi-objective collaborative optimization algorithm is: ； in, and The first The wind speed and concentration deviations between the pipe to be adjusted and the reference pipe are considered. and The weighting coefficients are dynamically adjusted. The total number of units to be adjusted; Solving the objective function yields the result that... The minimum set of optimal openings is taken as the target opening of the electrically adjustable orifice.

9. The method for leveling pulverized coal pipe air based on dynamic sensing and adjustment according to claim 1, characterized in that, Based on the target opening, a control signal is generated using a fuzzy PID composite control algorithm to drive each of the electrically adjustable orifices to the target opening, including: Calculate the opening deviation and the rate of change of deviation between the actual opening of the electrically adjustable orifice and the target opening; A first threshold and a second threshold are set, wherein the first threshold is greater than the second threshold; When the absolute value of the opening deviation is greater than the first threshold, a fuzzy control algorithm is adopted: the opening deviation and the deviation change rate are used as inputs, the preset fuzzy control rule base is queried, and the first control signal is obtained and output. When the absolute value of the opening deviation is less than or equal to the second threshold, the system switches to the PID control algorithm, performs proportional, integral, and derivative operations based on the opening deviation, and obtains and outputs the second control signal.

10. A pulverized coal pipe air-coal leveling system based on dynamic sensing and leveling, characterized in that, include: The data acquisition module is configured to acquire electrostatic and microwave signals from each pulverized coal pipeline; The data fusion module is configured to perform data fusion and cross-verification on the electrostatic signal and microwave signal, and calculate the confidence wind speed and confidence concentration of each of the pulverized coal pipelines. The reference tube identification module is configured to identify and determine the reference tube under the current operating conditions based on the confidence wind speed and confidence concentration of the pulverized coal pipeline, combined with stability evaluation indicators. The deviation calculation module is configured to calculate the wind speed deviation and concentration deviation between each coal powder pipeline to be adjusted and the reference pipe, excluding the reference pipe. The multi-objective optimization module is configured to minimize the wind speed deviation and concentration deviation of all the coal powder pipelines to be adjusted, and calculate the target opening of the electrically adjustable orifice corresponding to the coal powder pipeline to be adjusted through a multi-objective collaborative optimization algorithm. The control module is configured to generate a control signal based on the target opening using a fuzzy PID composite control algorithm, and drive each of the electrically adjustable orifices to move to the target opening.

Images