Supersonic ejection pulse injection pressure control method and system

Abstract

The present application relates to the technical field of bag type dust removal, and particularly relates to a supersonic injection pulse spraying pressure control method and system, which is used for evaluating the effectiveness of single dust cleaning operation and optimizing subsequent spraying pressure, and the method comprises the following steps: when spraying operation is performed on at least one spraying unit of a bag type dust removal system, a pressure monitoring device arranged on a spraying gas path of the spraying unit is used to collect pressure signals in the spraying gas path, so as to obtain pressure waveform data, and the pressure waveform data represents pressure change at the moment of spraying; at least one preset dynamic characteristic parameter is extracted from the pressure waveform data, and the dynamic characteristic parameter reflects the state of the spraying gas flow or the change of the filter bag air permeability; the spraying pressure is adjusted according to the evaluation of the dust cleaning effectiveness level by collecting the spraying gas path pressure signals and extracting the dynamic characteristic parameters, and the mapping relationship is updated online, so that the problems of extensive dust cleaning control, inability to finely evaluate and adjust in the prior art are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bag type dust removal, and particularly relates to a supersonic injection pulse blowing pressure control method and system. BACKGROUND

[0002] Bag type dust removal is a key equipment in industrial processes such as coal-fired power plants, which uses filter bags to filter flue gas dust. During operation, dust layer accumulates on the surface of the filter bag, reducing the air permeability and increasing the system resistance. Regular dust cleaning (such as pulse blowing technology: instant high-pressure gas is sprayed into the filter bag to make it expand and vibrate to shake off the dust) is needed to maintain efficiency and capacity.

[0003] However, the existing pulse blowing dust cleaning control method is usually rough. For example, a fixed blowing pressure set value may be used, or dust cleaning cycle is started based on the total pressure difference of the dust collector box reaching a certain threshold. This method does not fully consider the differences in actual dust accumulation conditions and dust cleaning difficulty caused by factors such as installation position, flue gas flow field distribution, dust properties (such as humidity, viscosity), and filter bag aging degree. This difference is dynamic and particularly significant in large dust collectors. Rough dust cleaning control may result in incomplete dust cleaning of some filter bags due to insufficient blowing pressure, continuous accumulation of residual dust layer, formation of local high resistance area, affecting the filtration efficiency of this area, and possibly causing flue gas to bypass, increasing the load of other areas, and ultimately reducing the dust removal efficiency and processing capacity of the entire dust removal system. At the same time, for filter bags with less dust accumulation or easy dust cleaning, using uniform high-pressure blowing may cause unnecessary compressed air consumption and increase operating energy consumption; too high blowing pressure and too frequent blowing may also accelerate the fatigue damage of filter bag fibers, shorten the service life of filter bags, and increase the frequency of filter bag replacement and maintenance costs.

[0004] In order to achieve fine management of bag type dust removal system dust cleaning operation, improve dust cleaning effect, reduce energy consumption and prolong filter bag life, it is urgent to develop a method that can accurately evaluate the effectiveness of single or local dust cleaning operation, and adaptively adjust the subsequent blowing parameters, especially the blowing pressure, based on the evaluation results. Traditional methods (such as pressure difference before and after dust cleaning) are difficult to capture dust peeling details and uniformity. Direct monitoring of filter bag dynamic response (such as vibration) is more direct, but it is too costly to install sensors for a large number of filter bags in harsh working conditions.

[0005] Therefore, exploring an evaluation method based on easily accessible physical signals and capable of indirectly reflecting the ash removal effect has become a research direction. In the process of pulse injection, the high-speed airflow causes a sharp pressure change in the injection pipeline and injects the surrounding air into the filter bag, causing the internal pressure of the filter bag to rise and the filter bag to expand and vibrate. The dynamic characteristics of the pressure signals in these processes, such as the shape, peak value, and decay speed of the pressure waveform, are theoretically affected by the degree of filter bag ash deposition, the air permeability, and the dynamic response of the filter bag. How to effectively collect these pressure signals at the moment of injection, extract dynamic characteristic parameters that can represent the state of the cleaning airflow or the change in the air permeability of the filter bag, and establish a reliable correlation model between these parameters and the actual cleaning operation effectiveness to realize real-time evaluation of the cleaning effect of a single injection operation, and based on the evaluation results, online and self-adaptive adjustment of the injection pressure set value of the subsequent injection unit to cope with the dynamic influence of complex working conditions such as changes in coal characteristics, while achieving the goals of optimizing the cleaning effect, reducing energy consumption, and prolonging the service life of the filter bag, is still a technical problem that needs to be solved in the field of bag-type dust removal technology.

[0006] In view of the above problems, the prior art needs to be improved. SUMMARY

[0007] The purpose of the present application is to solve the problems existing in the prior art and to provide a supersonic injection pulse injection pressure control method and system.

[0008] In the first aspect, the present application provides a supersonic injection pulse injection pressure control method for evaluating the effectiveness of a single ash removal operation and optimizing the subsequent injection pressure, characterized in that the method comprises the following steps:

[0009] When at least one injection unit of the bag-type dust removal system performs an injection operation, a pressure monitoring device arranged on the injection gas path of the injection unit is used to collect the pressure signals in the injection gas path, and pressure waveform data is obtained, which represents the pressure change at the moment of injection;

[0010] At least one preset dynamic characteristic parameter is extracted from the pressure waveform data, and the dynamic characteristic parameter reflects the change in the injection airflow state or the air permeability of the filter bag;

[0011] Based on the extracted dynamic characteristic parameters and according to the preset mapping relationship between the dynamic characteristic parameters and the ash removal operation effectiveness level, the ash removal effectiveness level of the current injection operation is determined;

[0012] According to the determined ash removal effectiveness level, the subsequent injection pressure set value of the injection unit or the filter bag area responsible for it is adjusted;

[0013] The mapping relationship between the dynamic characteristic parameters and the ash removal operation effectiveness level is updated online.

[0014] The core innovation of the present application is that the mapping relationship between the dynamic characteristic parameters extracted from the pressure waveform data on the injection gas path and the dust cleaning operation effectiveness level is combined, thereby realizing real-time evaluation of the effectiveness of a single injection operation, and based on the evaluation results, the subsequent injection pressure is adaptively adjusted, achieving the effects of improving dust cleaning efficiency, reducing energy consumption and prolonging the service life of the filter bag.

[0015] In a second aspect, a supersonic injection pulse injection pressure control system is provided for evaluating the effectiveness of a single dust cleaning operation and optimizing the subsequent injection pressure, characterized in that the system comprises:

[0016] A pressure acquisition module is configured to acquire pressure signals in the injection gas path of at least one injection unit of a bag-type dust removal system during an injection operation of the injection unit, and obtain pressure waveform data through a pressure monitoring device arranged on the injection gas path of the injection unit, wherein the pressure waveform data represents the pressure change at the injection moment.

[0017] A feature extraction module is configured to extract at least one preset dynamic characteristic parameter from the pressure waveform data, wherein the dynamic characteristic parameter reflects the state of the injection gas flow or the change in the filter bag permeability.

[0018] An effectiveness evaluation module is configured to determine the dust cleaning effectiveness level of the current injection operation based on the extracted dynamic characteristic parameters and according to a preset mapping relationship between the dynamic characteristic parameters and the dust cleaning operation effectiveness level.

[0019] A pressure adjustment module is configured to adjust the subsequent injection pressure set value of the injection unit or the filter bag area responsible for the injection unit according to the determined dust cleaning effectiveness level.

[0020] A mapping relationship updating module is configured to update the mapping relationship between the dynamic characteristic parameters and the dust cleaning operation effectiveness level online.

[0021] Compared with the prior art, the present application has the following beneficial effects:

[0022] By acquiring the injection gas path pressure signal, extracting the dynamic characteristic parameters, evaluating the dust cleaning effectiveness level, and adjusting the injection pressure accordingly, and updating the mapping relationship online, the problem of extensive dust cleaning control, inability to fine evaluation and adjustment in the prior art is solved, thereby having the advantages of being able to evaluate the effectiveness of a single dust cleaning operation, and adaptively adjusting the injection pressure according to the evaluation results, thereby improving the dust cleaning effect, reducing energy consumption, and prolonging the service life of the filter bag. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 The flowchart of the method of the present application.

[0024] Figure 2 The system structure diagram of the present application.

[0025] In the figure: 201, pressure acquisition module; 202, feature extraction module; 203, effectiveness evaluation module; 204, pressure adjustment module; 205, mapping relationship updating module. DETAILED DESCRIPTION

[0026] Embodiments of the present application are described in detail below with reference to the accompanying drawings, wherein the same or similar notations used throughout the drawings and the specification denote the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary only, and are used only for the purpose of explaining the present application, and should not be understood as limiting the present application.

[0027] The terms "first", "second", etc. are used only for the purpose of description, and should not be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second", etc. can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0028] As Figure 1 A supersonic ejection pulse injection pressure control method for evaluating the effectiveness of a single dust removal operation and optimizing subsequent injection pressure, the method comprising the following steps:

[0029] When a dust injection unit of a bag filter system performs an injection operation, a pressure monitoring device arranged on the injection gas path of the injection unit acquires a pressure signal in the injection gas path, and obtains pressure waveform data, which represents the pressure change at the injection moment;

[0030] At least one preset dynamic characteristic parameter is extracted from the pressure waveform data, and the dynamic characteristic parameter reflects the injection gas flow state or the change in filter bag permeability;

[0031] Based on the extracted dynamic characteristic parameter, and according to a preset mapping relationship between the dynamic characteristic parameter and the dust removal operation effectiveness level, the dust removal effectiveness level of the current injection operation is determined;

[0032] According to the determined dust removal effectiveness level, the subsequent injection pressure set value of the injection unit or the filter bag area responsible for it is adjusted;

[0033] The mapping relationship between the dynamic characteristic parameter and the dust removal operation effectiveness level is updated online.

[0034] The method comprises collecting pressure signal in the injection gas path of the injection unit of the bag type dust removal system by a pressure monitoring device arranged on the injection gas path of the injection unit when the injection operation is performed in at least one injection unit of the bag type dust removal system, and obtaining pressure waveform data. The pressure monitoring device is a sensor or instrument for measuring the gas pressure in the injection gas path in real time, which can be realized by a piezoresistive sensor, a capacitive sensor or a piezoelectric sensor, and is mainly used to obtain the pressure change information in the injection process. The pressure waveform data refers to the pressure signal sequence collected by the pressure monitoring device, which changes with time, and represents the dynamic pressure change process at the injection moment, and is mainly used to capture the dynamic characteristic information in the injection process.

[0035] The preset dynamic characteristic parameter refers to a value or index extracted from the pressure waveform data, which can represent the characteristics of the injection gas flow or the state of the filter bag, which can be realized by peak pressure, pressure drop rate, waveform integral value or frequency spectrum characteristics, and is mainly used to convert the original pressure signal into quantitative information that can be used to evaluate the cleaning effect. The dynamic characteristic parameter reflects the state of the injection gas flow or the change of the filter bag permeability, and refers to the correlation between the extracted dynamic characteristic parameter and the state of the injection gas flow such as intensity, speed and duration, and the change of the filter bag permeability such as dust adhesion amount and pore blockage degree, which is mainly used to evaluate the cleaning effect indirectly.

[0036] The preset mapping relationship between the dynamic characteristic parameter and the cleaning operation effectiveness level refers to the rules, models or lookup tables established for converting the extracted dynamic characteristic parameter into the cleaning effect evaluation result, which can be realized by a rule set based on expert experience, a statistical model or a machine learning model, and is mainly used to realize the quantitative evaluation of the cleaning operation effectiveness. The cleaning operation effectiveness level refers to the evaluation result of the cleaning effect of a single injection operation, which can be realized by grade division or numerical index, and is mainly used to provide basis for subsequent injection pressure adjustment.

[0037] The online update refers to the real-time or periodic adjustment and optimization of the mapping relationship between the dynamic characteristic parameter and the cleaning operation effectiveness level according to the actual operation data or feedback information during the system operation, which is mainly used to adapt the evaluation model to the working condition change and improve the accuracy of the evaluation.

[0038] The scheme of the present application obtains the pressure waveform data at the instant of injection by using the pressure monitoring device arranged on the injection gas path when the injection operation is performed in the injection unit of the bag type dust removal system. The data contains the information of the injection gas flow impacting the filter bag and the dynamic response of the filter bag. Since the state of the injection gas flow and the change of the air permeability of the filter bag will affect the specific form of the pressure waveform, the dynamic characteristic parameters extracted from the pressure waveform data can indirectly reflect the cleaning effect. Based on these extracted dynamic characteristic parameters and according to the mapping relationship between the dynamic characteristic parameters and the cleaning operation effectiveness level established in advance, the cleaning effectiveness level of the current injection operation can be determined. For example, a certain pressure peak, a falling rate or a waveform integral value may correspond to different cleaning effects. According to the determined cleaning effectiveness level, the system can judge whether the current injection is sufficient and effective. If the cleaning effect is poor, the injection pressure set value of the subsequent injection unit or the responsible area thereof can be increased accordingly; if the cleaning effect is good or even excessive, the injection pressure can be appropriately reduced, so as to realize the fine and adaptive adjustment of the injection pressure. In addition, in order to cope with the influence of factors such as system working condition change, dust property change or filter bag aging on the evaluation accuracy, the scheme also includes online updating the mapping relationship between the dynamic characteristic parameters and the cleaning operation effectiveness level, so that the evaluation model can be continuously optimized, and the effectiveness of evaluation and adjustment can be maintained. The whole process forms a closed loop control, and the cleaning operation is optimized through real-time monitoring, evaluation and adjustment.

[0039] In some embodiments, the pressure monitoring device can employ a fast-responding pressure sensor installed at the connection between the blowpipe and the plenum. The acquired pressure waveform data can be digitized by a data acquisition card. The dynamic characteristic parameters extracted from the pressure waveform data can include the time to reach the peak pressure after the start of the blow, the peak pressure value, the time required for the pressure to drop from the peak to a certain threshold value, the area integral value of the pressure waveform, etc. The pre-set mapping relationship between the dynamic characteristic parameters and the cleaning effectiveness level can be stored in a lookup table, which maps different ranges of dynamic characteristic parameter combinations to different cleaning effectiveness levels, such as effective, basically effective, and suboptimal. The cleaning effectiveness level can be further subdivided into multiple levels, such as levels 1 to 5, where level 1 represents the best cleaning effect and level 5 represents the worst cleaning effect. According to the determined cleaning effectiveness level, the pressure adjustment module can consult a pre-set adjustment strategy table, which defines how to adjust the subsequent blow pressure set value for different cleaning effectiveness levels, for example, if the evaluation level is suboptimal, the subsequent blow pressure set value is increased by 0.05 MPa; if the evaluation level is effective, the blow pressure is maintained or appropriately reduced. Online updating of the mapping relationship can be achieved by monitoring the correlation between the overall performance indicators of the system after a period of operation and the cleaning effect evaluated based on the current mapping relationship, and when a deviation is found between the evaluation result and the actual system performance, the adjustment algorithm for optimizing the mapping relationship is triggered.

[0040] As an embodiment of the present application, the step of online updating the mapping relationship between the dynamic characteristic parameters and the cleaning effectiveness level includes:

[0041] Obtaining deviation indication information for representing the current accuracy of the mapping relationship between the dynamic characteristic parameters and the cleaning effectiveness level;

[0042] Based on the change of the obtained deviation indication information within a pre-set evaluation period, determining whether the mapping relationship has a trend deviation;

[0043] When it is determined that the mapping relationship has no trend deviation, then the mapping relationship adjustment operation based on the current deviation indication information is inhibited or delayed to maintain the current mapping relationship;

[0044] When it is determined that the mapping relationship has a trend deviation, then the mapping relationship between the dynamic characteristic parameters and the cleaning effectiveness level is adjusted according to the trend deviation.

[0045] The deviation indication information refers to the difference between the actual dust removal effect and the dust removal effect predicted based on the current mapping relationship. It can be represented by the comparison between the actual monitored filter bag resistance change, emission concentration and other indicators and the prediction effectiveness level. The purpose is to quantify the current accuracy of the mapping relationship. The preset evaluation period refers to the time window or the number of dust removal operations used to accumulate and analyze the deviation indication information to determine the trend. The purpose is to provide a stable observation range to avoid making judgments based on instantaneous data. The trend deviation refers to the continuous, non-random systematic change of the deviation indication information within the preset evaluation period. The judgment can be based on statistical analysis methods, such as analyzing whether the mean, variance or change slope of the deviation indication information sequence exceeds the preset threshold. The purpose is to distinguish between accidental fluctuations and systematic deviations that need to be corrected. The mapping relationship adjustment operation is suppressed or delayed. When it is judged that the mapping relationship has not deviated in trend, the mapping relationship modification action triggered by the current deviation indication information is not immediately or delayed. It can be specifically implemented by setting adjustment trigger conditions, allowing adjustment only when the trend deviation condition is met, or putting the adjustment instruction into a waiting queue. The purpose is to enhance the robustness of the system and avoid frequent adjustments caused by random noise. The mapping relationship between the trend deviation adjustment dynamic characteristic parameter and the dust removal operation effectiveness level refers to modifying the mapping relationship according to the detected trend direction and amplitude when it is judged that the mapping relationship has deviated in trend. It can be specifically implemented by modifying the corresponding values in the mapping table or adjusting the parameters in the mapping model. The purpose is to make the mapping relationship approximate the current actual working condition again.

[0046] The scheme of the present application solves the problem of misalignment of the preset mapping relationship under varying working conditions by introducing a mechanism for online updating of the mapping relationship. Specifically, the system continuously acquires deviation indication information, which quantifies the deviation between the prediction result of the current mapping relationship and the actual situation. It is precisely because of the continuous monitoring of this deviation that the system can perceive the accuracy state of the mapping relationship. Further, the system analyzes the changes in these deviation indication information within a preset evaluation period, and distinguishes between accidental fluctuations and systematic deviations by judging whether there is a trend of misalignment. It is precisely because of this trend judgment that the system avoids overreaction to random noise. When there is no trend of misalignment, the system suppresses or delays the mapping relationship adjustment operation that may be triggered, which effectively maintains the stability of the mapping relationship and prevents unnecessary system shock. When there is a trend of misalignment, the system adjusts the mapping relationship between the dynamic characteristic parameter and the cleaning effectiveness level according to the nature of the detected trend of misalignment. It is precisely because of this trend-based adaptive adjustment that the mapping relationship can dynamically adapt to changing working conditions and maintain its accuracy over the long term. This online updating mechanism, combined with the basic method of evaluating cleaning effectiveness based on pressure waveform features and adjusting the blowing pressure, makes the cleaning effectiveness evaluation no longer dependent on static preset relationships, but is dynamically optimized online, thereby ensuring the accuracy of the evaluation results and ensuring the effectiveness and precision of subsequent blowing pressure adjustment. This enables the entire bag-type dust collection system to achieve efficient, energy-saving, and low-loss cleaning operation even in the face of complex and dynamically changing working conditions.

[0047] As an embodiment of the present application, the step of judging whether the mapping relationship has a trend of misalignment based on the changes in the acquired deviation indication information within the preset evaluation period includes:

[0048] Obtaining a working condition change indication parameter representing the degree of change in the current working condition of the bag-type dust collection system, and adjusting the analysis settings used to analyze the changes in the acquired deviation indication information within the preset evaluation period;

[0049] Based on the changes in the acquired deviation indication information within the preset evaluation period, and applying the adjusted analysis settings to analyze the deviation indication information, to judge whether the mapping relationship has a trend of misalignment.

[0050] Among them, the operating condition change indication parameter refers to a parameter that characterizes the stability of the current operating state of the bag dust removal system, which can be specifically the boiler load change rate, flue gas flow fluctuation amplitude, inlet flue gas temperature change rate, inlet dust concentration change rate, etc. Its purpose is to quantify the degree of operating condition change and provide a basis for subsequent analysis setting adjustments; the analysis setting refers to a set of rules or parameters used to analyze the changes in the obtained deviation indication information within a preset evaluation period, which can be specifically the threshold for judging the trend misalignment of the deviation indication information, the judgment time window, the data smoothing coefficient, the trend judgment algorithm parameters, etc., whose purpose is to define how to interpret the changes in the deviation indication information; adjusting the analysis setting used to analyze the changes in the obtained deviation indication information within the preset evaluation period according to the obtained operating condition change indication parameter refers to the process of modifying the analysis setting according to the operating condition change indication parameter, which can be specifically increasing the judgment threshold or extending the judgment time window when the operating condition changes drastically, and reducing the threshold or shortening the time window when the operating condition is stable, whose purpose is to make the misalignment judgment robust to operating condition changes.

[0051] The solution of the present application obtains operating condition change indication parameters that characterize the severity of the current operating condition changes of the bag dust removal system. These parameters provide information about the stability of the system's external environment or operating status. Based on these operating condition change indication parameters, the analysis settings used to analyze the deviation indication information are dynamically adjusted. For example, if the operating condition changes drastically, the analysis settings will be adjusted to be more relaxed and more tolerant to short-term fluctuations in the deviation indication information. If the operating condition is stable, the analysis settings will be stricter and more sensitive to small changes. Finally, the adjusted analysis settings are used to analyze the changes in the deviation indication information within the preset evaluation period to determine whether the mapping relationship has a trend misalignment. Therefore, the solution of the present application is combined with the basic solution, so that the entire cleaning operation evaluation and injection pressure optimization system can maintain high accuracy and reliability under dynamically changing working conditions. By considering the impact of operating condition changes on the deviation indication information, misjudgments caused by operating condition fluctuations are avoided, and the necessity and timeliness of mapping relationship adjustments are ensured, thereby improving the accuracy of the cleaning effect evaluation, and then optimizing the injection pressure, ultimately achieving the goal of energy saving and consumption reduction and extending the life of the filter bags. This adaptive adjustment mechanism is a key improvement that enables the basic solution to operate stably and effectively under complex actual working conditions.

[0052] As an embodiment of the present invention, the step of adjusting the analysis settings for analyzing changes in the obtained deviation indication information within a preset evaluation period according to the obtained operating condition change indication parameter includes:

[0053] Obtaining at least two types of operating condition change indication parameters, wherein the at least two types of operating condition change indication parameters respectively represent changes in different aspects of the operating condition of the bag dust removal system;

[0054] The adjustment mapping relationship between one or more analysis setting sub-items corresponding to the one or more combinations of the one or more types of working condition change indication parameters and the analysis setting for analyzing the change of the acquired deviation indication information in the preset evaluation period, the analysis setting sub-item being an adjustable constituent part in the analysis setting, and the adjustment mapping relationship defining that when the one or more types of working condition change indication parameters satisfy a preset state, an adjustment instruction of the analysis setting sub-item associated therewith is generated;

[0055] According to the state of the at least two types of working condition change indication parameters currently acquired and according to the preset adjustment mapping relationship, an adjustment instruction of one or more analysis setting sub-items in the analysis setting is determined;

[0056] The adjustment instruction is executed to adjust the corresponding analysis setting sub-item in the analysis setting, so as to realize adjustment of the analysis setting for analyzing the change of the acquired deviation indication information in the preset evaluation period according to the acquired working condition change indication parameters.

[0057] Among them, at least two types of working condition change indication parameters refer to a parameter set that can reflect the change of the bag type dust removal system running state in different dimensions, which can be realized by monitoring the flue gas flow, inlet dust concentration, system temperature, differential pressure of each chamber, dust cleaning frequency, blowing gas source pressure fluctuation and other parameters, and its purpose is to comprehensively capture the complex dynamics of system working condition; Analysis setting refers to a series of configuration parameters or rules for processing and analyzing deviation indication information to judge whether the mapping relationship is inaccurate, which can be realized by setting data smoothing window size, slope threshold of trend judgment, abnormal value elimination standard, evaluation period length and other parameters, and its purpose is to define the specific way and sensitivity of deviation indication information analysis; Analysis setting subitem refers to the smallest constituent unit that can be independently adjusted in analysis setting, which can be realized by one or more of the above data smoothing window size, slope threshold of trend judgment, abnormal value elimination standard, evaluation period length and other parameters, and its purpose is to provide an interface for fine control of the analysis process; Adjusting the mapping relationship refers to the association rule set between the specific combination state of at least two types of working condition change indication parameters and the adjustment instruction of one or more analysis setting subitems in the analysis setting, which can be realized by lookup table, rule set, decision tree or function model, and its purpose is to convert complex working condition changes into explicit and executable adjustment actions of analysis setting; The preset state refers to one or more predefined numerical range, change trend or discrete state of the working condition change indication parameter or its combination, which can be realized by setting parameter threshold, change rate interval, stable / fluctuation / severe change state identifier, and its purpose is to trigger the corresponding analysis setting adjustment logic; Adjustment instruction refers to the specific modification requirement for a specific analysis setting subitem in the analysis setting, which can be realized in the form of increasing / decreasing a certain value, switching to a certain preset mode, enabling / disabling a certain rule, and its purpose is to guide the system how to specifically modify the value or state of the analysis setting subitem.

[0058] The scheme of the present application can understand the current running state of the bag type dust removal system from multiple dimensions by acquiring at least two types of working condition change indication parameters, and compared with only relying on a single parameter, this multi-parameter acquisition mode provides richer and more comprehensive working condition information. Based on these multi-dimensional working condition information, and according to a preset adjustment mapping relationship, the system can determine the optimal analysis setting adjustment instruction for the current complex working condition. The adjustment mapping relationship associates a specific working condition parameter combination with a specific adjustment action of the analysis setting, so that the system can dynamically adjust the analysis mode of the deviation indication information according to the actual running condition. After executing these adjustment instructions, the analysis setting for judging whether the mapping relationship is misaligned will be more suitable for the current working condition. It is precisely because of this adaptive adjustment based on multiple parameters through the mapping relationship that the analysis of the change of the deviation indication information within the preset evaluation period is more accurate and reliable, thereby improving the accuracy of judging whether the mapping relationship is misaligned. This more accurate judgment further improves the effectiveness of the mapping relationship between the online updated dynamic characteristic parameters and the cleaning operation effectiveness level, and finally optimizes the overall performance of the cleaning operation evaluation and the injection pressure control.

[0059] As an embodiment of the present application, the adjustment mapping relationship between one or more combinations of one or more types of working condition change indication parameters and one or more analysis setting sub-items corresponding to the analysis of the change of the acquired deviation indication information within the preset evaluation period in the analysis setting, the analysis setting sub-item is an adjustable component in the analysis setting, and the adjustment mapping relationship defines that when the one or more combinations of working condition change indication parameters meet the preset state, the step of generating the adjustment instruction of the analysis setting sub-item associated therewith includes:

[0060] Establishing an initial adjustment mapping relationship, the initial adjustment mapping relationship includes a mapping rule between one or more combinations of at least two types of working condition change indication parameters and one or more analysis setting sub-items in the analysis setting, and the mapping rule defines that when the one or more combinations of working condition change indication parameters meet the preset state, the adjustment instruction of the analysis setting sub-item associated therewith is generated;

[0061] Acquiring system performance feedback data representing the system performance of the bag type dust removal system after the adjustment instruction generated based on the current adjustment mapping relationship is applied to the analysis setting sub-item adjustment;

[0062] Based on the acquired system performance feedback data and the preset performance target, judging the applicability state of the current adjustment mapping relationship;

[0063] When judging that the applicability state of the adjustment mapping relationship deviates from the preset performance target, determining the combination of working condition change indication parameters as input in the adjustment mapping relationship that causes the applicability deviation;

[0064] According to the determined combination of the working condition change indication parameters causing the applicability deviation, the mapping rule associated with the combination in the adjustment mapping relationship is modified to update the adjustment mapping relationship.

[0065] Wherein, the adjustment mapping relationship refers to the association rule set between different combination states of the working condition change indication parameters and the adjustment instructions of the adjustable part (i.e. the analysis setting sub-item) in the analysis setting, which can be implemented by a lookup table, a rule base, or a model-based function relationship, and its purpose is to dynamically adjust the analysis method of the deviation indication information according to the current working condition change; the analysis setting sub-item refers to the parameter, threshold or configuration item in the analysis setting that can be independently adjusted for analyzing the change of the deviation indication information in the preset evaluation period, which can specifically include the sensitivity threshold of trend judgment, the evaluation period length, the data smoothing coefficient, etc., and its purpose is to fine-tune the analysis process of the deviation indication information; the mapping rule refers to a specific entry in the adjustment mapping relationship, which defines what kind of adjustment instruction for the associated analysis setting sub-item should be generated when a specific combination of working condition change indication parameters meets the preset condition, which can be implemented by a conditional statement (such as an IF-THEN rule) or a function expression, and its purpose is to map a specific working condition state to a specific analysis setting adjustment action; the system performance feedback data refers to the data reflecting the actual running effect of the bag-type dust collection system after applying the analysis setting adjustment instruction generated by the current adjustment mapping relationship, which can specifically include system total pressure difference, energy consumption, emission concentration, filter bag life prediction, etc., and its purpose is to quantitatively evaluate the effectiveness of the current adjustment mapping relationship; the preset performance target refers to the running performance standard or optimization direction expected to be achieved by the bag-type dust collection system, which can be set as a specific pressure difference range, an upper limit of energy consumption, a lower limit of emission concentration, etc., and its purpose is to provide a benchmark for evaluating the applicability of the adjustment mapping relationship; the applicability state refers to the degree of conformity of the current adjustment mapping relationship to the preset performance target in actual application, which can be judged as conforming, deviating or seriously deviating, etc., and its purpose is to indicate whether the adjustment mapping relationship needs to be optimized; the combination of the working condition change indication parameters causing the applicability deviation, which is used as input in the adjustment mapping relationship, refers to the state combination of the one or more groups of working condition change indication parameters used as input conditions in the current adjustment mapping relationship that causes the system performance feedback data to deviate from the preset performance target, and its purpose is to locate the mapping rule that needs to be optimized.

[0066] The scheme of the present application solves the problem that the initial adjustment mapping relationship may be imperfect or the system performance deviates from the preset performance target due to the change of working conditions by establishing an adaptive and optimized closed-loop feedback mechanism. The present application can achieve this goal because it first establishes an initial adjustment mapping relationship, which provides a starting point for subsequent optimization. Then, by obtaining system performance feedback data, the actual effect after the application of the current adjustment mapping relationship is directly quantified, which makes the evaluation of the effectiveness of the mapping relationship have objective basis. It is because the actual performance feedback can be compared with the preset performance target that the applicability state of the current adjustment mapping relationship can be accurately judged. When the applicability deviation is identified, the scheme further traces back to the specific working condition change indication parameter combination that causes the deviation, which makes the optimization targeted. Finally, by modifying the mapping rule associated with the working condition combination that causes the deviation, the online update and optimization of the adjustment mapping relationship are realized.

[0067] As an embodiment of the present application, the step of modifying the mapping rule associated with the determined working condition change indication parameter combination that causes the applicability deviation in the adjustment mapping relationship to update the adjustment mapping relationship according to the determined working condition change indication parameter combination that causes the applicability deviation comprises:

[0068] Retrieving historical adjustment data related to the determined working condition change indication parameter combination that causes the applicability deviation, the historical adjustment data records the historical mapping rule adjustment action and the system performance feedback after adjustment for the combination;

[0069] Based on the obtained historical adjustment data, determining the adjustment direction and adjustment amount of the mapping rule associated with the determined working condition change indication parameter combination that causes the applicability deviation in the current adjustment mapping relationship;

[0070] According to the determined adjustment direction and adjustment amount, modifying the mapping rule associated with the combination in the adjustment mapping relationship to update the adjustment mapping relationship.

[0071] Wherein, the historical adjustment data refers to the stored information set about the mapping rule modification attempt in the past for a specific working condition change indication parameter combination, which can include the specific content of each modification, the time when the modification occurs and the change of system running performance after the modification, and its purpose is to provide experience reference for subsequent rule adjustment; the adjustment direction and adjustment amount refer to the specific way and degree of modifying the mapping rule, the adjustment direction can refer to increasing or decreasing a parameter value, selecting a different rule type or switching to a preset standby rule, and the adjustment amount can refer to the specific value or proportion of parameter value change, and its purpose is to accurately control the influence of rule modification on system behavior.

[0072] The scheme of the present application introduces historical adjustment data, so that the modification of the mapping rule in the adjustment mapping relationship is no longer a blind attempt, but is based on the running history and experience accumulation of the system itself. Specifically, when the system detects that the applicability of the adjustment mapping relationship deviates from the preset performance target and determines the working condition change indicator combination that causes the deviation, the system will first query and obtain the historical adjustment data related to the specific combination. These historical data record in detail the rule adjustment operations in the past for the same working condition combination and the actual feedback of system performance after each adjustment. Based on these historical adjustment data, the system can analyze the influence law of different adjustment actions (i.e. historical adjustment direction and adjustment amount) on system performance, for example, identify which adjustments have brought performance improvement and which have caused performance decline. Through the analysis of historical data, the system can determine the adjustment direction and adjustment amount to be taken at present with basis, thereby avoiding repeated failed attempts and learning from successful experiences. Finally, according to the adjustment direction and adjustment amount obtained from the analysis of historical data, the system modifies the mapping rule in the current adjustment mapping relationship associated with the working condition combination, and completes the update of the adjustment mapping relationship. This process forms a self-adaptive optimization closed loop based on historical experience, so that the adjustment mapping relationship can continuously learn and improve with the system running and working condition changes, thereby more accurately guiding the analysis of the set adjustment, and further improving the accuracy and robustness of the ash removal operation evaluation and injection pressure optimization.

[0073] As an embodiment of the present application, based on the obtained historical adjustment data, the step of determining the adjustment direction and adjustment amount of the mapping rule in the current adjustment mapping relationship associated with the determined combination of working condition change indicator parameters causing the applicability deviation comprises:

[0074] trend analysis or statistical analysis is performed on the obtained historical adjustment data;

[0075] According to the trend analysis or statistical analysis result, the change law of system performance feedback under different adjustment directions and adjustment amounts in the historical adjustment data is identified;

[0076] Based on the change law, the adjustment direction and adjustment amount of the mapping rule in the current adjustment mapping relationship associated with the determined combination of working condition change indicator parameters causing the applicability deviation are determined.

[0077] The historical adjustment data refers to information recorded when the mapping rule is adjusted for a specific working condition change indication parameter combination in the past, which can include the mapping rule parameters before and after adjustment, the adjustment direction and amount, and the performance feedback data of the system running for a period of time after adjustment, which can be stored in a database or a log file, and the purpose is to provide experience and basis for subsequent mapping rule adjustment; the trend analysis or statistical analysis refers to a method of processing and mining the historical adjustment data, which can use time series analysis, regression analysis, cluster analysis, variance analysis and other statistical or data analysis techniques, which can reveal the potential correlation between the adjustment behavior and the system performance change, and the purpose is to extract useful knowledge from historical experience; the system performance feedback refers to an index reflecting the running state and effect of the bag type dust removal system, which can include the total pressure difference, energy consumption, emission concentration, filter bag life, etc., which can be provided by system sensors or calculation models, and the purpose is to evaluate the effect of mapping rule adjustment; the change law refers to the correlation pattern between the adjustment direction and adjustment amount and the system performance feedback found by analyzing the historical adjustment data, which can be expressed as the influence trend of a specific adjustment range or direction on the performance, which can be expressed as a mathematical model, a rule set or a visual chart, and the purpose is to guide the current adjustment decision; the adjustment direction and adjustment amount refer to the way and amplitude of modifying a specific parameter in the mapping rule, the direction can be increase or decrease, and the amount can be a specific numerical value or proportion, which can be determined according to the change law, and the purpose is to make the mapping rule better adapt to the current working condition.

[0078] The scheme of the present application solves the problem of blindness of mapping rule adjustment by introducing historical adjustment data analysis. When the system performance deviates from the preset target and the working condition change indication parameter combination causing the deviation is determined, instead of simply trying and error or looking up the table, the historical adjustment record for the specific working condition combination is first called. Trend analysis or statistical analysis is performed on these historical data, for example, which adjustment direction and adjustment amount have brought performance improvement and which have caused deterioration under this working condition in the past is analyzed. Based on the analysis results, the change law between the adjustment direction and adjustment amount and the system performance feedback is identified. For example, it can be found that small adjustments are usually safe, while large adjustments are risky, or the adjustment in a specific direction has performed well in history. Using these laws learned from historical experience, the adjustment direction and adjustment amount to be taken currently can be determined. This decision-making method based on historical experience makes the adjustment process more intelligent and efficient, can converge to the mapping rule adapting to the current working condition more quickly, avoids invalid or harmful adjustment, and thus quickly recovers and optimizes the system performance.

[0079] As an embodiment of the present application, the step of identifying the change law of the system performance feedback under different adjustment directions and adjustment amounts in the historical adjustment data includes:

[0080] analyzing the historical adjustment data to obtain the correlation between the adjustment direction, adjustment amount, and system performance feedback;

[0081] According to the correlation, the change law of the system performance feedback under different adjustment direction and adjustment amount combinations is identified, and the change law includes the adjustment characteristic interval that leads to system performance improvement or deterioration.

[0082] The historical adjustment data refers to the historical record of modifying the adjustment mapping relationship, which can include the adjustment direction, adjustment amount, and feedback data of the system performance after each modification. The adjustment direction refers to the direction of modifying the parameters or rules in the adjustment mapping relationship, which can be represented by increasing, decreasing, positive, negative, etc. The adjustment amount refers to the specific value or amplitude of modifying the parameters or rules in the adjustment mapping relationship, which can be represented by absolute value, percentage, or level, etc. The system performance feedback refers to the running performance indicators of the bag-type dust removal system after applying the adjusted mapping relationship, which can be measured by total pressure difference, dust cleaning effect evaluation level, energy consumption, filter bag life, etc. The correlation refers to the mutual influence relationship between the adjustment direction, adjustment amount, and system performance feedback, which can be quantified by correlation coefficient, regression model, or machine learning model, etc. The change law refers to the specific change trend or pattern of the system performance feedback under different adjustment direction and adjustment amount combinations, which can be described by curve, surface, or rule set, etc. The adjustment characteristic interval refers to the interval within a specific adjustment direction and adjustment amount range, in which the system performance feedback shows a consistent change trend, which can be defined by numerical range, discrete set, or rule condition, etc. The purpose is to identify the adjustment range that has a specific impact on the system performance.

[0083] The scheme of the present application analyzes the historical adjustment data in depth, first quantifies the mutual influence relationship between the adjustment direction, adjustment amount, and system performance feedback. This quantification process can be realized by using various data analysis techniques, thereby establishing a mathematical model or statistical model between the adjustment input and system response. On this basis, further use of the obtained correlation information identifies the specific change pattern of the system performance feedback under different adjustment direction and adjustment amount combinations. This pattern recognition not only reveals the overall trend, but more importantly, can accurately define the specific adjustment range or condition that leads to system performance improvement or deterioration, i.e. the adjustment characteristic interval. In this way, based on the analysis of historical adjustment data, the present scheme provides a more detailed and guiding change law, so that when determining the adjustment direction and adjustment amount of the mapping rule subsequently, the deterioration interval can be avoided more accurately, and the improvement interval can be preferentially selected, thereby improving the effectiveness and efficiency of the mapping relationship adjustment.

[0084] As an embodiment of the present application, according to the determined combination of the working condition change indicating parameters causing applicability deviation, the step of modifying the mapping rule associated with the combination in the adjustment mapping relationship to update the adjustment mapping relationship comprises:

[0085] Obtaining the adjustable parameters (θ MR current) of the current mapping rule associated with the determined combination (C faulty) of the working condition change indicating parameters causing applicability deviation, and obtaining the historical adjustment data (H data(C faulty)) for the combination (C faulty) of the working condition change indicating parameters, the historical adjustment data (H data(C faulty)) containing a series of historical records, each historical record including a historical mapping rule adjustment action (Δθ MR hist i) on the historical mapping rule parameters and an observed system performance change (E change hist i) after the adjustment action; wherein C faulty is a specific combination of working condition change indicating parameters, θ MR current is a set of adjustable parameters of the current mapping rule associated with C faulty, H data(C faulty) is a historical adjustment data set for C faulty, Δθ MR hist i is the modification amount of the mapping rule parameters in the historical data, and E change hist i is the observed system performance feedback change after the i adjustment in the historical data;

[0086] Based on the historical adjustment data (H data(C faulty)), an efficiency response model (g) is constructed or updated, which is used to predict the expected system performance change (E change pred) according to the input candidate adjustment amount (Δθ MR) of the current mapping rule parameters (θ MR current), wherein E change pred=g(Δθ MR|H data(C faulty)); wherein g is the efficiency response function, Δθ MR is the adjustment amount applied to the current rule parameters θ MR current, and E change pred is the predicted system performance change;

[0087] Obtaining the current system performance feedback data (E sys) and the preset system performance target (E target); wherein E sys is the current running performance index of the bag type dust removal system, and E target is the expected system performance target value;

[0088] Based on the performance response model (g), and combined with the current system performance feedback data (E_sys) and the preset performance target (E_target), the optimal adjustment amount (Δθ_MR_opt) of the current mapping rule parameter (θ_MR_current) is determined by solving an optimization problem, which aims to select a candidate adjustment amount (Δθ_MR) to optimize a preset objective function that comprehensively considers the expected system performance improvement, the closeness to the preset performance target, and the rationality of the adjustment amount; wherein Δθ_MR_opt is the optimal parameter adjustment amount obtained by optimization decision;

[0089] According to the adjustable parameter (θ_MR_current) of the current mapping rule and the calculated optimal adjustment amount (Δθ_MR_opt), the adjustable parameter of the mapping rule is updated to obtain the updated mapping rule parameter (θ_MR_new), and the calculation method is: θ_MR_new=θ_MR_current+Δθ_MR_opt; wherein θ_MR_new is the updated mapping rule parameter;

[0090] The updated mapping rule parameter (θ_MR_new) is used to modify the mapping rule associated with the combination (C_faulty) of the working condition change indication parameter.

[0091] As Figure 2 shown, a supersonic ejection pulse spraying pressure control system for evaluating the effectiveness of a single dust cleaning operation and optimizing subsequent spraying pressure, the system comprises:

[0092] A pressure collection module 201 is configured to collect pressure signals in a spraying gas path of a spraying unit of a bag-type dust removal system during spraying operation of the spraying unit, and obtain pressure waveform data by a pressure monitoring device arranged in the spraying gas path, wherein the pressure waveform data represents pressure changes at the spraying moment.

[0093] A feature extraction module 202 is configured to extract at least one preset dynamic characteristic parameter from the pressure waveform data, wherein the dynamic characteristic parameter reflects the spraying gas flow state or the change of filter bag permeability.

[0094] An effectiveness evaluation module 203 is configured to determine the dust cleaning effectiveness level of the current spraying operation based on the extracted dynamic characteristic parameter and according to a preset mapping relationship between the dynamic characteristic parameter and the dust cleaning effectiveness level.

[0095] A pressure adjustment module 204 is configured to adjust the subsequent spraying pressure set value of the spraying unit or the filter bag area responsible for the spraying unit according to the determined dust cleaning effectiveness level.

[0096] The mapping relationship updating module 205 is configured to update the mapping relationship between the dynamic characteristic parameter and the dust cleaning operation effectiveness grade online.

[0097] The basic principle, main features and advantages of the present application are shown and described above. It should be understood by those skilled in the art that the present application is not limited to the above-mentioned embodiments, and the above-mentioned embodiments and descriptions in the specification are only the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application.

Claims

1. A supersonic jet pulse injection pressure control method for evaluating the effectiveness of a single dust cleaning operation and optimizing subsequent injection pressure, characterized in that: The method comprises the following steps: When at least one blowing unit of the bag dust removal system performs a blowing operation, a pressure signal in the blowing air path is collected by a pressure monitoring device provided on the blowing air path of the blowing unit to obtain pressure waveform data, wherein the pressure waveform data represents the instantaneous pressure change of the blowing; Extracting at least one preset dynamic characteristic parameter from the pressure waveform data, the dynamic characteristic parameter reflecting the state of the jet airflow or the change in the air permeability of the filter bag; Determining the cleaning effectiveness level of the current blowing operation based on the extracted dynamic characteristic parameters and a preset mapping relationship between the dynamic characteristic parameters and the cleaning effectiveness level; Adjust the subsequent blowing pressure setting value of the blowing unit or the filter bag area it is responsible for according to the determined cleaning effectiveness level; Online update of the mapping relationship between dynamic characteristic parameters and cleaning operation effectiveness level; The step of online updating the mapping relationship between the dynamic characteristic parameters and the dust cleaning operation effectiveness level includes: Obtaining deviation indication information for characterizing the current accuracy of the mapping relationship between the dynamic characteristic parameters and the dust cleaning operation effectiveness level; Based on changes in the obtained deviation indication information within a preset evaluation period, determining whether a trend misalignment occurs in the mapping relationship; When it is determined that the mapping relationship does not have a trend of misalignment, suppressing or delaying the mapping relationship adjustment operation based on the current deviation indication information to maintain the current mapping relationship; When it is determined that the mapping relationship has a trend misalignment, the mapping relationship between the dynamic characteristic parameter and the dust cleaning operation effectiveness level is adjusted according to the trend misalignment; The step of judging whether a trend misalignment occurs in the mapping relationship based on a change in the obtained deviation indication information within a preset evaluation period includes: Obtaining an operating condition change indication parameter that characterizes the severity of the change in the current operating condition of the bag dust removal system, and adjusting an analysis setting for analyzing changes in the obtained deviation indication information within the preset evaluation period; Based on the change of the obtained deviation indication information within the preset evaluation period, the deviation indication information is analyzed by applying the adjusted analysis setting to determine whether the mapping relationship has a trend misalignment.

2. A supersonic ejection pulse jet pressure control method according to claim 1, characterized in that: The step of adjusting, based on the acquired operating condition change indication parameter, an analysis setting for analyzing changes in the acquired deviation indication information within the preset evaluation period includes: Obtaining at least two types of operating condition change indication parameters, wherein the at least two types of operating condition change indication parameters respectively represent changes in different aspects of the operating condition of the bag dust removal system; Presetting an adjustment mapping relationship between one or more combinations of the at least two types of operating condition change indication parameters and one or more corresponding analysis setting sub-items in an analysis setting for analyzing changes in the obtained deviation indication information within the preset evaluation period, wherein the analysis setting sub-items are adjustable components of the analysis setting, and the adjustment mapping relationship defines generating an adjustment instruction for the associated analysis setting sub-items when the one or more combinations of operating condition change indication parameters meet a preset state; Determining, based on the currently acquired states of the at least two types of operating condition change indication parameters and according to a preset adjustment mapping relationship, an adjustment instruction for one or more analysis setting sub-items in the analysis setting; The adjustment instruction is executed to adjust the corresponding analysis setting sub-item in the analysis setting, thereby adjusting the analysis setting for analyzing the change of the obtained deviation indication information within the preset evaluation period according to the obtained working condition change indication parameter.

3. A supersonic ejection pulse jet pressure control method according to claim 2, characterized in that: The step of presetting an adjustment mapping relationship between one or more combinations of the at least two types of operating condition change indication parameters and one or more corresponding analysis setting sub-items in the analysis setting for analyzing the change of the obtained deviation indication information within the preset evaluation period, wherein the analysis setting sub-items are adjustable components in the analysis setting, and the adjustment mapping relationship defines that when the operating condition change indication parameters of the one or more combinations meet a preset state, the step of generating an adjustment instruction for the associated analysis setting sub-items includes: Establishing the initial adjustment mapping relationship; Acquiring system performance feedback data representing the operation of the bag filter system after the adjustment instruction generated based on the current adjustment mapping relationship is applied to the analysis setting sub-item adjustment; Based on the obtained system performance feedback data and the preset performance target, determine the applicability of the current adjustment mapping relationship; When it is determined that the applicability state of the adjustment mapping relationship deviates from the preset performance target, determining the combination of the operating condition change indication parameters used as input in the adjustment mapping relationship that causes the applicability deviation; According to the determined combination of the operating condition change indication parameters that causes the applicability deviation, the mapping rule associated with the combination in the adjustment mapping relationship is modified to update the adjustment mapping relationship.

4. A supersonic ejection pulse jet pressure control method according to claim 3, characterized in that: The initial adjustment mapping relationship includes a mapping rule between one or more combinations of the at least two types of operating condition change indication parameters and one or more corresponding analysis setting sub-items in the analysis setting. The mapping rule defines that when the operating condition change indication parameters of the one or more combinations meet the preset state, an adjustment instruction for the associated analysis setting sub-item is generated.

5. A supersonic ejection pulse jet pressure control method according to claim 4, characterized in that: The step of modifying the mapping rule associated with the combination of the operating condition change indication parameters that causes the applicability deviation in the adjustment mapping relationship to update the adjustment mapping relationship includes: Retrieving historical adjustment data related to the determined combination of the operating condition change indication parameters causing the applicability deviation, the historical adjustment data recording historical mapping rule adjustment actions for the combination and feedback on the adjusted system performance; Based on the acquired historical adjustment data, determining an adjustment direction and an adjustment amount for a mapping rule associated with the combination of the operating condition change indication parameters that causes the applicability deviation in the current adjustment mapping relationship; According to the determined adjustment direction and adjustment amount, the mapping rule associated with the combination in the adjustment mapping relationship is modified to update the adjustment mapping relationship.

6. A supersonic ejection pulse jet pressure control method according to claim 5, characterized in that: The step of determining, based on the acquired historical adjustment data, an adjustment direction and an adjustment amount of a mapping rule associated with the combination of the operating condition change indication parameters that causes the applicability deviation in the current adjustment mapping relationship includes: Conduct trend analysis or statistical analysis on the acquired historical adjustment data; Based on the trend analysis or statistical analysis results, identifying the changing patterns of system performance feedback under different adjustment directions and adjustment amounts in the historical adjustment data; Based on the change rule, an adjustment direction and an adjustment amount of a mapping rule associated with the combination of the operating condition change indication parameters that causes the applicability deviation in the current adjustment mapping relationship are determined.

7. A supersonic ejection pulse jet pressure control method according to claim 6, characterized in that: The step of identifying the changing rules of system performance feedback under different adjustment directions and adjustment amounts in the historical adjustment data includes: Analyze historical adjustment data to obtain the correlation between adjustment direction, adjustment amount and system performance feedback; According to the correlation, a variation pattern of system performance feedback under different adjustment directions and adjustment amounts in the historical adjustment data is identified, wherein the variation pattern includes an adjustment feature interval that causes improvement or deterioration of the system performance.

Images