Combustion balance AI intelligent detection and diagnosis method, system, equipment and product

Abstract

The invention relates to the technical field of heating furnaces, in particular to a combustion balance AI intelligent detection and diagnosis method, system, equipment and product, and the method comprises the steps that when it is judged that combustion is unbalanced, the rated pressure difference, the actual pressure difference and working parameters of a combustor are read, and the working parameters comprise the flow orifice plate diameter, the diameter ratio, the expansion coefficient, the outflow coefficient and the fluid density; standard fuel gas and air flow and actual fuel gas and air flow of the combustor are calculated through a pressure difference method; the method comprises the following steps: collecting and calculating a centralized data set, inputting the collected centralized data set into a fault judgment model, and judging that the fault type of the combustor is electromagnetic valve blockage (a strong correlation fault) when the centralized data set conforms to the fault judgment model. The invention provides a method for rapid prediction based on finite dynamic factor combination for strong correlation faults, so that the fault detection cost can be reduced through rapid prediction of the electromagnetic valve faults, and timely troubleshooting can be carried out at the initial stage of generation of fault hidden dangers.

Description

Technical Field

[0001] The present invention relates to the technical fields of horizontal and vertical heating furnace production line combustion systems with radiation tubes with double cross-proportional regulation and pulse control, and in particular to a combustion balance AI intelligent detection and diagnosis method, system, equipment and product. Background Art

[0002] The radiant tube combustion heating in metallurgical furnace is a heating technology widely used in the metallurgical industry. In the cold rolling continuous annealing furnace, the radiant tube is the key equipment for heating the strip steel in the furnace. The working condition of the radiant tube is directly related to the annealing quality of the strip steel. Its working principle is: the fuel gas (mostly coal gas) and the combustion-supporting gas (air) are fully mixed and burned in the combustion chamber, and the heat generated causes the radiation tube wall to be in a high temperature state. The outer wall of the radiation tube then transfers the heat to the furnace atmosphere and the strip steel in the form of thermal radiation, so as to achieve the purpose of heating the strip steel without oxidation. The exhaust gas generated by the combustion in the radiant tube is discharged through the circulation into the heat exchanger or the exhaust pipe.

[0003] At present, most metallurgical enterprises have been in operation for a long time, and the radiant tube combustion system has been operating under harsh conditions of high temperature, high pressure, high load and strong impact for a long time. Long-term operation leads to an increase in the failure rate of solenoid valves, combustion equipment, radiant tubes, heat exchangers and other equipment in the system, which in turn causes combustion imbalance, which in turn leads to a vicious cycle of equipment failure. In order to solve the above problems, the following automatic fault identification methods are proposed in the prior art:

[0004] 1. Check the result - flame status

[0005] For example, patent application CN118168349A discloses a method and system for monitoring flames in a heating furnace, including obtaining flame information in the heating furnace; performing data filtering and preprocessing based on the flame information; extracting features to distinguish flame states; establishing a flame state model to match feature parameters with known flame states; by obtaining flame information in the heating furnace, the flame state can be continuously monitored to detect abnormal conditions in a timely manner, and data filtering and preprocessing can remove noise and outliers, thereby improving the accuracy and reliability of subsequent data analysis and facilitating accurate extraction of flame feature parameters.

[0006] However, the monitoring of flame-related conditions is easily affected by environmental conditions. Factors such as light and smoke can interfere with the monitoring results, leading to inaccuracy and stability in the monitoring. This places extremely high demands on the environment and the performance of the monitoring equipment. At the same time, this method is difficult to accurately judge the state and characteristic parameters of the flame, and cannot conduct in-depth analysis of the combustion conditions of the flame, resulting in low monitoring accuracy.

[0007] 2. Use AI model to predict faults

[0008] For example, patent application CN117704416A discloses an AI-based automated boiler combustion regulation method, which includes the following steps: real-time collection of boiler operation data, including temperature, pressure, fuel consumption, and emission data; using the algorithm of the AI ​​unit to analyze the collected data and identify the optimal state of boiler operation; based on the analysis results, the AI ​​unit automatically generates combustion regulation decisions; automatically adjusts fuel supply and air flow parameters to achieve combustion optimization; automatically adjusts combustion strategies according to changes in the external environment to solve combustion efficiency and emission problems caused by environmental changes; the AI ​​unit predicts potential failures and maintenance needs based on the performance data of boiler components and historical maintenance records, and plans maintenance activities in advance.

[0009] For example, patent application CN117490091A discloses a fuel-air distribution control method and system, which includes: collecting historical data and preprocessing the collected data; building a deep learning model and training the model; adjusting the parameters or structure of the model to optimize the model performance; deploying the trained model to the actual fuel-air distribution, and dynamically adjusting the fuel-air ratio according to the model's prediction results.

[0010] For another example, patent application CN117144118A also discloses an adaptive control method and related equipment for a continuous annealing furnace. The method includes: constructing a first training sample library and a second training sample library of a target area, wherein the first training sample library includes a single burner gas flow average value and a single burner gas flow measurement value of the target area, and the second training sample library includes a single burner air flow average value and a single burner air flow measurement value of the target area; constructing a regional balanced combustion model based on the first training sample library and the second training sample library; and determining abnormal conditions of gas and air based on the regional balanced combustion model.

[0011] However, the existing AI models are relatively limited in detection accuracy in application implementation, and the application costs are also relatively high. Summary of the invention

[0012] The purpose of the present invention is to provide a combustion balance AI intelligent detection and diagnosis method, system, equipment and product, which can partially solve or alleviate the above-mentioned deficiencies in the prior art and improve the reliability of fault prediction while reducing the real-time monitoring pressure.

[0013] In order to solve the above-mentioned technical problems, the present invention specifically adopts the following technical solutions:

[0014] A first aspect of the present invention is to provide a combustion balance AI intelligent detection and diagnosis method, the intelligent detection method is applied to a combustion system, the combustion system comprises: a heating furnace, and a burner providing a heat source for the heating furnace, and correspondingly, the method comprises the steps of:

[0015] Centralized fault determination of the burner, including:

[0016] S101: Read the serial number of the burner, and centrally read the rated pressure difference, actual pressure difference and working parameters of the burner according to the serial number; the rated pressure difference includes: standard pressure difference of gas and standard pressure difference of air; the actual pressure difference includes: actual pressure difference of gas and actual pressure difference of air; the pressure difference is the pressure difference between the input side pressure and the output side pressure of the flow orifice plate in the pipeline of the burner; the working parameters include: the diameter of the flow orifice plate, the ratio of the diameter of the flow orifice plate to the pipeline, the expansion coefficient, the outflow coefficient, and the fluid density;

[0017] S102: using the pressure difference method to calculate the standard gas flow rate Qgs and the standard air flow rate Qas of the burner respectively through the standard gas pressure difference and the standard air pressure difference;

[0018] S103: using the pressure difference method to calculate the actual gas flow Qg and the actual air flow Qa of the burner through the actual gas pressure difference and the actual air pressure difference;

[0019] S104: judging the equipment type of the heating furnace according to the actual input side pressure and the actual output side pressure, wherein when the fluctuation values ​​of the input side pressure and the output side pressure both belong to the set fluctuation threshold, it is considered that the equipment type is double cross proportional regulation;

[0020] S105: When the device type is double cross ratio regulation, it is considered that the burner meets the centralized prediction condition, and the current centralized data set is collected to input the centralized data set into the fault judgment model, the centralized data set includes: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2, the fault judgment model includes:

[0021] |Qa-Qas|÷Qas<A1;

[0022] |Qg-Qgs|÷Qgs>A2;

[0023] Cco>A3;

[0024] Co2>A4;

[0025] Among them, |Qa-Qas|÷Qas is the first indicator, |Qg-Qgs|÷Qgs is the second indicator, A1, A2, A3, A4 are the first training threshold, the second training threshold, the third training threshold, and the fourth training threshold respectively; correspondingly, a plurality of corresponding training thresholds are obtained through machine learning training;

[0026] S106: When the centralized data set conforms to the fault determination model, it is determined that the fault type of the burner is a solenoid valve blockage.

[0027] In some embodiments, the step of obtaining a plurality of corresponding training thresholds through machine learning training includes:

[0028] Acquire a training sample set, the training sample set comprising: input end training data, the input end training data comprising: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2; output end training data corresponding to the input end training data, the output end training data comprising: solenoid valve blockage data;

[0029] Inputting the training sample set into a setting model to perform at least one iterative training; wherein the setting model is used to learn the intrinsic relationship between the first indicator, the second indicator, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2 and the solenoid valve blockage data;

[0030] After the setting model converges, the setting model outputs the predicted numerical ranges of the first indicator, the second indicator, the exhaust gas carbon monoxide content Cco, and the exhaust gas oxygen content Co2 corresponding to the blockage state of the solenoid valve, and sets corresponding multiple training thresholds according to the predicted numerical ranges.

[0031] In some embodiments, before determining a burner fault, the method further includes the following steps:

[0032] (1) obtaining the historical training threshold value set last time according to the set model;

[0033] (2) using an updated data set formed by the current burner in the first period, the updated data set comprising: input end updated data, which includes: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2; and output end updated data corresponding to the input end updated data, the output end updated data comprising: solenoid valve blockage data;

[0034] (3) collecting a first updated data set from the updated data set and inputting the corresponding input-end updated data into the fault judgment model to obtain a fault prediction result output by the fault judgment model; wherein the fault judgment model uses the historical training threshold to make a judgment;

[0035] (4) Comparing the fault prediction result with the output end update data, calculating the current prediction accuracy of the fault judgment model.

[0036] In some embodiments, the step further includes: when the prediction accuracy is greater than a first set value, collecting a second update data set from the update data set;

[0037] Inputting the second updated data set into the setting model to perform update training on the setting model;

[0038] A new training threshold is set again based on the updated setting model.

[0039] In some embodiments, before determining the burner fault, the method further includes the following steps:

[0040] Determine the combustion equilibrium state; it includes:

[0041] Collect the excess air volume and actual air volume in the exhaust gas to calculate the excess air coefficient; wherein the excess air coefficient is calculated using the following formula: α=1 / [1-(ΔL / La)], α is the excess air coefficient, ΔL is the excess air volume, and La is the actual air volume;

[0042] Determine whether the excess air coefficient is within the set threshold range. If so, execute the steps of: performing a fault determination on the burner; if not, continue to detect the excess air volume and the actual air volume of the exhaust gas.

[0043] The present invention also provides a combustion balance AI intelligent detection and diagnosis system, wherein the intelligent detection method is applied to a combustion system, wherein the combustion system comprises: a heating furnace, and a burner providing a heat source for the heating furnace. Correspondingly, the system comprises: a centralized fault determination subsystem, which comprises:

[0044] A reading module is used to read the serial number of the burner, and centrally read the rated pressure difference, actual pressure difference and working parameters of the burner according to the serial number; the rated pressure difference includes: standard pressure difference of gas and standard pressure difference of air; the actual pressure difference includes: actual pressure difference of gas and actual pressure difference of air; the pressure difference is the pressure difference between the input side pressure and the output side pressure of the flow orifice plate in the pipeline of the burner; the working parameters include: the diameter of the flow orifice plate, the ratio of the diameter of the flow orifice plate to the diameter of the pipeline, the expansion coefficient, the outflow coefficient, and the fluid density;

[0045] A first calculation module, for respectively calculating a standard gas flow Qgs and a standard air flow Qas of the burner through the standard gas pressure difference and the standard air pressure difference by using a pressure difference method;

[0046] A second calculation module is used to calculate the actual gas flow Qg and the actual air flow Qa of the burner by using the actual gas pressure difference and the actual air pressure difference using a pressure difference method;

[0047] A type judgment module, used for judging the equipment type of the heating furnace according to the actual input side pressure and the actual output side pressure, wherein when the fluctuation values ​​of the input side pressure and the output side pressure both belong to the set fluctuation threshold, it is considered that the equipment type is double cross proportional regulation;

[0048] A data input module is used for, when the device type is double cross ratio regulation, considering that the burner meets the centralized prediction condition, and collecting the current centralized data set to input the centralized data set into the fault judgment model, wherein the centralized data set includes: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2, and the fault judgment model includes:

[0049] |Qa-Qas|÷Qas<A1;

[0050] |Qg-Qgs|÷Qgs>A2;

[0051] Cco>A3;

[0052] Co2>A4;

[0053] Among them, |Qa-Qas|÷Qas is the first indicator, |Qg-Qgs|÷Qgs is the second indicator, A1, A2, A3, A4 are the first training threshold, the second training threshold, the third training threshold, and the fourth training threshold respectively; correspondingly, a plurality of corresponding training thresholds are obtained through machine learning training;

[0054] The fault determination module is used to determine that the fault type of the burner is a solenoid valve blockage when the centralized data set conforms to the fault determination model.

[0055] In some embodiments, the data input module further comprises:

[0056] A sample acquisition unit is used to acquire a training sample set, wherein the training sample set includes: input end training data, wherein the input end training data includes: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, and the exhaust gas oxygen content Co2; output end training data corresponding to the input end training data, wherein the output end training data includes: solenoid valve blockage data;

[0057] An iteration unit, used for inputting the training sample set into a setting model to perform at least one iteration training; wherein the setting model is used for learning the intrinsic relationship between the first indicator, the second indicator, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2 and the solenoid valve blockage data;

[0058] A threshold setting unit is used to output the predicted numerical range of the first indicator, the second indicator, the exhaust gas carbon monoxide content Cco, and the exhaust gas oxygen content Co2 corresponding to the blockage state of the solenoid valve through the setting model after the setting model converges, and set corresponding multiple training thresholds according to the predicted numerical range.

[0059] In some embodiments, the system further includes: an accuracy prediction subsystem configured to perform the following steps:

[0060] (1) obtaining the historical training threshold value set last time according to the set model;

[0061] (2) using an updated data set formed by the current burner in the first period, the updated data set comprising: input end updated data, which includes: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2; and output end updated data corresponding to the input end updated data, the output end updated data comprising: solenoid valve blockage data;

[0062] (3) collecting a first updated data set from the updated data set and inputting the corresponding input-end updated data into the fault judgment model to obtain a fault prediction result output by the fault judgment model; wherein the fault judgment model uses the historical training threshold to make a judgment;

[0063] (4) Comparing the fault prediction result with the output end update data, calculating the current prediction accuracy of the fault judgment model.

[0064] The present invention also provides an electronic device, comprising: a memory and a processor; the memory is used to store a program; the processor is used to execute the program to implement each step of the intelligent detection method as described in any embodiment.

[0065] The present invention also provides a computer program product, comprising a computer program, which, when executed by one or more processors, causes the one or more processors to execute the intelligent detection method as described in any one of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale. Obviously, the drawings described below are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without paying creative labor.

[0067] Figure 1 is a schematic diagram of a method flow in an exemplary embodiment of the present invention;

[0068] Figure 2 is a system module structure diagram in an exemplary embodiment of the present invention;

[0069] Figure 3 It is a schematic diagram of an interface for gas solenoid valve blockage fault diagnosis in an exemplary embodiment of the present invention;

[0070] Figure 4 It is a schematic diagram of an interface for gas solenoid valve leakage fault diagnosis in an exemplary embodiment of the present invention;

[0071] Figure 5 It is a schematic diagram of the collection result of burner related data in a specific embodiment of the present invention;

[0072] Figure 6 It is a schematic diagram of the module structure of a system in an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0073] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0074] Herein, suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present invention, and have no specific meanings by themselves. Therefore, "module", "component" or "unit" can be used mixedly.

[0075] In this document, the terms "upper", "lower", "inner", "outer", "front", "back", "one end", "the other end" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0076] In this document, unless otherwise clearly specified and limited, the terms "installed", "provided with", "connected", etc. should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0077] Herein "and / or" includes any and all combinations of one or more of the associated listed items.

[0078] Herein, "plurality" means two or more than two, ie, it includes two, three, four, five, etc.

[0079] As used in this specification, the term "about" typically means + / - 5% of the stated value, more typically + / - 4% of the stated value, more typically + / - 3% of the stated value, more typically + / - 2% of the stated value, even more typically + / - 1% of the stated value, even more typically + / - 0.5% of the stated value.

[0080] In this specification, certain embodiments may be disclosed in a format of being in a certain range. It should be understood that such description of "being in a certain range" is merely for convenience and brevity, and should not be interpreted as a rigid limitation on the disclosed range. Therefore, the description of the range should be considered to have specifically disclosed all possible sub-ranges and independent numerical values ​​within this range. For example, the description of the range 1 to 6 should be considered to have specifically disclosed sub-ranges such as from 1 to 3, from 1 to 4, from 1 to 5, from 2 to 4, from 2 to 6, from 3 to 6, etc., as well as individual numbers within this range, such as 1, 2, 3, 4, 5 and 6. Regardless of the breadth of the range, the above rules apply.

[0081] Since most metallurgical enterprises have been in operation for a long time, the radiation tube combustion system has been operating under harsh conditions of high temperature, high pressure, high load and strong impact for a long time. Long-term operation leads to an increase in the failure rate of solenoid valves, combustion equipment, radiation tubes, heat exchangers and other equipment in the system, resulting in combustion imbalance, which will seriously affect the stable operation of the combustion system.

[0082] In this regard, the prior art attempts to use AI intelligent detection for fault detection. However, the applicant noted that due to the huge system and complexity of the combustion system, the existing AI intelligent detection technology is actually very limited in its ability to predict maintenance and fault prediction. In particular, the training workload of the model is very large, while the versatility of the model is very limited.

[0083] For example, the adaptive control method of the continuous annealing furnace disclosed in patent application CN117144118A adopts the following technical route: comprehensively predicting faults through a massive parameter library (furnace temperature setting value, strip speed setting value, gas flow setting value, air-fuel ratio setting value, air flow setting value, power load, combustion fan power, combustion air pressure before the burner, gas pressure, flow, negative pressure, flue temperature, etc. series data), such as predicting air leakage, proportional valve failure, pipeline blockage, heat exchanger damage, radiation tube damage, etc. based on massive data learning. However, the applicant found that such massive fault prediction of massive data requires a lot of resources in the training and maintenance process of the model, and is relatively effective in terms of prediction versatility.

[0084] Correspondingly, in order to reduce the pressure of model training on the basis of improving the coverage of fault prediction and the scope of model application, the present application proposes an AI intelligent detection method for centralized prediction of burner blockage faults of heating furnaces with specific adjustment mechanisms. Specifically, the present application proposes a method of using a limited dynamic factor combination (such as the first indicator, the second indicator, the exhaust gas carbon monoxide content Cco, and the exhaust gas oxygen content Co2 as described below) to focus on predicting strongly correlated faults (i.e., solenoid valve blockage). The applicant found that this limited dynamic factor combination can not only predict the fault of solenoid valve blockage more efficiently and accurately for the combustion system based on the double cross-proportional adjustment control mode, but also indirectly predict the possible associated faults through the prediction results of the solenoid valve fault - that is, specific types of faults such as flue damage, excessive air volume, and heat exchanger burnout. That is, for the combustion system with this special adjustment mechanism, the present invention focuses on directly predicting the solenoid valve faults that are strongly correlated with other faults through limited dynamic factors, thereby greatly improving the cost-effectiveness of fault prediction.

[0085] Therefore, the present application not only helps to improve the accuracy and reliability of fault prediction by making targeted predictions for specific strongly correlated faults (this targeted prediction mechanism for strongly correlated faults avoids the technical pressure on model training imposed by the huge system and complexity of the combustion system to a certain extent), but also can at least indirectly judge batch faults through limited workload, thus still being able to reduce the pressure of real-time fault analysis to a large extent.

[0086] In particular, most of the equipment in the heating furnace is in a sealed package state. For the detection devices set inside, the layout, maintenance difficulty and cost are also very high. The smaller number of detection devices used in this application can also reduce the technical difficulty and cost of the detection system in the implementation process. For example, for some small metallurgical enterprises, the cost of the AI ​​supporting equipment layout that they can invest in is relatively limited. This centralized prediction can complete batch fault prediction at a limited cost, thereby combining manpower to manually analyze the predicted faults, which can reduce the cost of fault detection and maintenance to a lower level.

[0087] In other words, the centralized prediction mechanism proposed in the present invention is also conducive to the centralized collection of data. For example, from the perspective of the input end, the pressure of the gas and air in the burner pipeline, and the oxygen and carbon monoxide content in the exhaust gas are centrally collected. The necessary data detection devices required are also relatively small, making the detection system of the present invention easier to implement.

[0088] In summary, the present invention proposes a technical route for centralized prediction of strongly correlated faults based on centralized data.

[0089] Embodiment 1:

[0090] See also Figure 1 As shown, the present invention provides a combustion balance AI intelligent detection and diagnosis method, the combustion system includes: a heating furnace, and a burner providing a heat source for the heating furnace. Correspondingly, the method includes the steps of:

[0091] Centralized fault determination of the burner, including:

[0092] S101: Read the serial number of the burner, and centrally read the rated pressure difference, actual pressure difference and working parameters of the burner according to the serial number; the rated pressure difference includes: standard pressure difference of gas and standard pressure difference of air; the actual pressure difference includes: actual pressure difference of gas and actual pressure difference of air; the pressure difference is the pressure difference between the input side pressure and the output side pressure of the flow orifice plate in the pipeline of the burner; the working parameters include: the diameter of the flow orifice plate, the diameter ratio of the diameter of the flow orifice plate to the diameter of the pipeline, the expansion coefficient, the outflow coefficient, and the fluid density;

[0093] For example, in some embodiments, multiple burners are arranged in the combustion system, and the corresponding rated parameters can be queried through the burner number (such as ID value), such as the rated power of the M3AO burner is Ps = 100kW, and the corresponding rated pressure difference can be calculated according to the current design standard of the combustion system, such as the gas standard pressure difference and air standard pressure difference corresponding to the M3AO burner are both approximately 500Pa.

[0094] Specifically, the series rated pressure difference, actual pressure difference and operating parameters associated with the burner can be automatically read through the number.

[0095] S102: using the pressure difference method to calculate the standard gas flow rate Qgs and the standard air flow rate Qas of the burner respectively through the standard gas pressure difference and the standard air pressure difference;

[0096] S103: using the pressure difference method to calculate the actual gas flow Qg and the actual air flow Qa of the burner through the actual gas pressure difference and the actual air pressure difference;

[0097] For example, in some embodiments, the calculation formula of the pressure difference method is as follows:

[0098] Among them, Q v is the flow rate of the fluid, β is the diameter ratio, d is the diameter of the flow orifice plate, ε is the expansion coefficient, C is the outflow coefficient, ΔP is the pressure difference of the corresponding fluid, and ρ is the density of the corresponding fluid; the fluid is gas or air;

[0099] For example, when Q vWhen Q is the standard gas flow rate, ΔP is the standard gas pressure difference, and ρ is the gas density. v When is the standard air flow rate, ΔP is the standard air pressure difference, and ρ is the density of the air.

[0100] For example, when Q v When Q is the actual gas flow rate, ΔP is the actual gas pressure difference, and ρ is the gas density. v When is the actual air flow rate, ΔP is the actual air pressure difference, and ρ is the air density.

[0101] See also Figure 2 As shown, Figure 2 The actual measurement data table of the M3AO burner is shown. The standard gas flow rate Qgs≈20m 3 / h, standard air flow Qas≈110m 3 / h.

[0102] In some embodiments, before the centralized data set is input into the fault judgment model, the adaptability of the fault judgment model is evaluated. For example, when it is determined that the heating furnace belongs to double cross-proportional regulation, it is recommended to adopt the current fault judgment model.

[0103] S104: judging the equipment type of the heating furnace according to the actual input side pressure and the actual output side pressure, wherein when the fluctuation values ​​of the input side pressure and the output side pressure both belong to the set fluctuation threshold, it is considered that the equipment type is double cross proportional regulation;

[0104] S105: When the device type is double cross ratio regulation, collect the current centralized data set and input the centralized data set into the fault judgment model, the centralized data set includes: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2, the fault judgment model includes:

[0105] |Qa-Qas|÷Qas<A1;

[0106] |Qg-Qgs|÷Qgs>A2;

[0107] Cco>A3;

[0108] Co2>A4;

[0109] Among them, |Qa-Qas|÷Qas is the first indicator, |Qg-Qgs|÷Qgs is the second indicator, A1, A2, A3, A4 are the first training threshold, the second training threshold, the third training threshold, and the fourth training threshold respectively; correspondingly, multiple corresponding training thresholds are obtained through machine learning training;

[0110] S106: When the centralized data set conforms to the fault determination model, it is determined that the fault type of the burner is a solenoid valve blockage.

[0111] In this embodiment, a method for quickly predicting solenoid valve blockage based on centralized (gas and air flow index, CO and O2 content index in exhaust gas) gas index (or limited dynamic factors) is proposed. This centralized prediction method can not only complete the rapid prediction of strongly correlated faults through limited data, so as to facilitate the rapid mobilization of maintenance resources to repair the solenoid valve fault in a timely manner, or, through the analysis of the solenoid valve blockage situation, batch faults can be manually observed in advance, such as when the flue is damaged, the air volume is too large, the heat exchanger is burned, etc., resources can be allocated in time for investigation, suppressing the "signs" of the fault, and limiting the further expansion of the fault.

[0112] It should be noted that heating furnaces based on double cross-proportional regulation are widely used and usually face the problem of a long production period. At the same time, since most of this type of equipment is in a sealed package, it is difficult to detect faults in time through routine inspections. In addition, due to the complexity of the heating furnace system based on double cross-proportional regulation, the applicant has noticed that traditional AI intelligent detection methods are difficult to apply, especially in the early data collection and model training stages. It requires a lot of resources, and the final fault prediction accuracy is relatively limited. In particular, faults such as burner blockage, flue damage, excessive air volume, and heat exchanger burning have a great impact on the losses caused by the heating furnace with double cross-proportional regulation. Once the fault prediction is wrong, it is very easy to cause the fault to expand and increase economic losses.

[0113] In view of this special application environment, the present invention proposes a method for centralized prediction of burner blockage faults of heating furnaces based on double cross-proportional regulation by using limited dynamic factors. The applicant has found that by centralized prediction of burner faults, it is possible to indirectly predict other faults in heating furnaces with double cross-proportional regulation by virtue of the strong correlation between burner faults and other faults such as flue damage, excessive air volume, and heat exchanger burnout. For example, when it is found that the current burner is blocked (or when the blockage is serious), the staff will manually start the fault detection of flue damage, excessive air volume, and heat exchanger burnout.

[0114] Furthermore, in some embodiments, it also includes:

[0115] The steps of obtaining the corresponding training threshold through machine learning training include:

[0116] Acquire a training sample set, the training sample set comprising: input end training data, the input end training data comprising: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2; output end training data corresponding to the input end training data, the output end training data comprising: solenoid valve blockage data;

[0117] For example, in some embodiments, the solenoid valve blockage data may be an indicator describing the blockage degree. For example, the blockage degree may be classified into low, medium or high levels according to the blockage area. For another example, the blockage degree may be a proportional value describing the size of the blockage area, such as 10%, 20% ... 90%, 100% blockage, etc.

[0118] Correspondingly, in some embodiments, the output result may be blocked or not blocked. Alternatively, the output result may be the degree of blockage.

[0119] Inputting the training sample set into a setting model to perform at least one iterative training; wherein the setting model is used to learn the intrinsic relationship between the first indicator, the second indicator, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2 and the solenoid valve blockage data;

[0120] After the setting model converges, the setting model outputs the predicted numerical ranges of the first indicator, the second indicator, the exhaust gas carbon monoxide content Cco, and the exhaust gas oxygen content Co2 corresponding to the blockage state of the solenoid valve, and sets corresponding multiple training thresholds according to the predicted numerical ranges.

[0121] In some embodiments, before determining a fault of the burner, the method further includes the following steps:

[0122] (1) obtaining the historical training threshold value set last time according to the set model;

[0123] (2) using an updated data set formed by the current burner in the first period, the updated data set comprising: input end updated data, which includes: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2; and output end updated data corresponding to the input end updated data;

[0124] (3) collecting a first updated data set from the updated data set, inputting the updated input end training data into the fault judgment model, obtaining a fault prediction result output by the fault judgment model, and the fault judgment model uses the historical training threshold to make a judgment;

[0125] (4) Comparing the fault prediction result with the output end update data, calculating the current prediction accuracy (such as prediction accuracy rate) of the fault judgment model.

[0126] In some embodiments, the step further includes: when the prediction accuracy is greater than a first set value, collecting a second update data set from the update data set;

[0127] inputting the second update data set into the setting model to update the setting model;

[0128] A new training threshold is set again based on the updated setting model.

[0129] In some embodiments, it also includes:

[0130] Before determining the fault of the burner, the following steps are also included:

[0131] Determine the combustion equilibrium state; it includes:

[0132] Collect the excess air volume and actual air volume in the exhaust gas to calculate the excess air coefficient; wherein the excess air coefficient is calculated using the following formula: α=1 / [1-(ΔL / La)], α is the excess air coefficient, ΔL is the excess air volume, and La is the actual air volume;

[0133] Determine whether the excess air coefficient is within the set threshold range. If so, execute the steps of: performing a fault determination on the burner; if not, continue to detect the excess air volume and the actual air volume of the exhaust gas.

[0134] In this embodiment, when the combustion state is unbalanced as detected by the air content in the exhaust gas, the solenoid valve of the burner is preferably tested in detail, which can further reduce the fault monitoring pressure of the heating furnace based on double cross proportional regulation.

[0135] Furthermore, in some embodiments, after the intelligent detection method runs in the combustion system for a period of time, it further comprises the steps of:

[0136] Obtaining the fault prediction results of the burners corresponding to the multiple different numbers output by the fault judgment model;

[0137] Comparing the fault prediction result with the actual fault result (for example, the actual fault result can be found by the staff during the maintenance process); when the fault prediction result is the same as the actual fault result, the corresponding fault prediction result is considered to be accurate; when the fault prediction result is different from the actual fault result, the corresponding fault prediction result is considered to be wrong;

[0138] When the proportion of the number of burners with erroneous fault prediction results to the number of all burners is greater than a first set ratio, a first prompt signal is output to prompt the user to verify the fault judgment model (such as updating the model using the latest updated data set at the end of time);

[0139] When the number of burners whose fault prediction results are erroneous accounts for a proportion of all burners that is greater than a second set ratio and is less than or equal to a first set ratio, a second prompt signal is output to prompt the user to detect the gas detectors associated with the corresponding burners (for example, detectors for detecting fuel gas, air flow, oxygen in exhaust gas, and carbon monoxide content, respectively).

[0140] In the present invention, by using limited gas indicators to centrally predict the blockage fault of the burner, the difficulty of fault prediction can be effectively reduced. Conversely, when the prediction results of the model have errors of varying degrees, this is also more conducive to guiding the staff to timely analyze the real cause of the error.

[0141] For example, in some embodiments, when only a small number of burners have fault prediction results that are false positives, the staff can promptly inspect and repair a small number of gas detectors to perform timely maintenance on the fault detection method.

[0142] Embodiment 2:

[0143] See also Figure 6 As shown, the present invention also provides an intelligent detection and diagnosis system correspondingly, and the intelligent detection and diagnosis system is applied to a combustion system, and the combustion system includes: a heating furnace, and a burner providing a heat source for the heating furnace. Correspondingly, the system includes: a centralized fault judgment subsystem, which includes:

[0144] The reading module 101 is used to read the serial number of the burner, and centrally read the rated pressure difference, actual pressure difference and working parameters of the burner according to the serial number; the rated pressure difference includes: standard pressure difference of gas and standard pressure difference of air; the actual pressure difference includes: actual pressure difference of gas and actual pressure difference of air; the pressure difference is the pressure difference between the input side pressure and the output side pressure of the flow orifice plate in the pipeline of the burner; the working parameters include: the diameter of the flow orifice plate, the ratio of the diameter of the flow orifice plate to the pipeline, the expansion coefficient, the outflow coefficient, and the fluid density;

[0145] A first calculation module 102, for respectively calculating a standard gas flow Qgs and a standard air flow Qas of the burner through the standard gas pressure difference and the standard air pressure difference by using a pressure difference method;

[0146] The second calculation module 103 is used to calculate the actual gas flow Qg and the actual air flow Qa of the burner by using the actual gas pressure difference and the actual air pressure difference using the pressure difference method;

[0147] A type judgment module 104 is used to judge the equipment type of the heating furnace according to the actual input side pressure and the actual output side pressure, wherein when the fluctuation values ​​of the input side pressure and the output side pressure both belong to the set fluctuation threshold, it is considered that the equipment type is double cross proportional regulation;

[0148] The data input module 105 is used to consider that the burner meets the centralized prediction condition when the device type is double cross ratio adjustment, and collect the current centralized data set to input the centralized data set into the fault judgment model, wherein the centralized data set includes: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, and the exhaust gas oxygen content Co2. The fault judgment model includes:

[0149] |Qa-Qas|÷Qas<A1;

[0150] |Qg-Qgs|÷Qgs>A2;

[0151] Cco>A3;

[0152] Co2>A4;

[0153] Among them, |Qa-Qas|÷Qas is the first indicator, |Qg-Qgs|÷Qgs is the second indicator, A1, A2, A3, A4 are the first training threshold, the second training threshold, the third training threshold, and the fourth training threshold respectively; correspondingly, a plurality of corresponding training thresholds are obtained through machine learning training;

[0154] The fault determination module 106 is configured to determine that the fault type of the burner is a solenoid valve blockage when the centralized data set conforms to the fault determination model.

[0155] In some embodiments, the data input module further comprises:

[0156] A sample acquisition unit is used to acquire a training sample set, wherein the training sample set includes: input end training data, wherein the input end training data includes: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, and the exhaust gas oxygen content Co2; output end training data corresponding to the input end training data, wherein the output end training data includes: solenoid valve blockage data;

[0157] An iteration unit, used for inputting the training sample set into a setting model to perform at least one iteration training; wherein the setting model is used for learning the intrinsic relationship between the first indicator, the second indicator, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2 and the solenoid valve blockage data;

[0158] A threshold setting unit is used to output the predicted numerical range of the first indicator, the second indicator, the exhaust gas carbon monoxide content Cco, and the exhaust gas oxygen content Co2 corresponding to the blockage state of the solenoid valve through the setting model after the setting model converges, and set corresponding multiple training thresholds according to the predicted numerical range.

[0159] In some embodiments, the system further includes: an accuracy prediction subsystem configured to perform the following steps:

[0160] (1) obtaining the historical training threshold value set last time according to the set model;

[0161] (2) using an updated data set formed by the current burner in the first period, the updated data set comprising: input end updated data, which includes: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2; and output end updated data corresponding to the input end updated data, the output end updated data comprising: solenoid valve blockage data;

[0162] (3) collecting a first updated data set from the updated data set and inputting the corresponding input-end updated data into the fault judgment model to obtain a fault prediction result output by the fault judgment model; wherein the fault judgment model uses the historical training threshold to make a judgment;

[0163] (4) Comparing the fault prediction result with the output end update data, calculating the current prediction accuracy of the fault judgment model.

[0164] In some embodiments, a linear regression algorithm, a K-means algorithm and a neural network algorithm may be used to complete corresponding model training.

[0165] The present invention also provides an electronic device, comprising: a memory and a processor; the memory is used to store a program; the processor is used to execute the program to implement each step of the intelligent detection method as described in any one of the present invention.

[0166] The present invention also provides a computer program product, comprising a computer program, which, when executed by one or more processors, causes the one or more processors to execute the intelligent detection method as described in any one of the present invention.

[0167] It can be understood that the order of steps described in the present invention is only for illustrative purposes. In fact, the steps in the present invention can be performed according to actual conditions. For example, steps S102, S103, S104, and S105 can be performed simultaneously or in any order.

[0168] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0169] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a computer terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0170] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A combustion balance AI intelligent detection and diagnosis method, characterized in that: The method is applied to a combustion system, which includes a heating furnace and a burner that provides a heat source for the heating furnace. Correspondingly, the method includes the steps of: Centralized fault determination is performed on the burner, which includes: S101: Read the serial number of the burner, and centrally read the rated pressure difference, actual pressure difference and working parameters of the burner according to the serial number; the rated pressure difference includes: standard pressure difference of gas and standard pressure difference of air; the actual pressure difference includes: actual pressure difference of gas and actual pressure difference of air; the pressure difference is the pressure difference between the input side pressure and the output side pressure of the flow orifice plate in the pipeline of the burner; the working parameters include: the diameter of the flow orifice plate, the ratio of the diameter of the flow orifice plate to the pipeline, the expansion coefficient, the outflow coefficient, and the fluid density; S102: using the pressure difference method to calculate the standard gas flow rate Qgs and the standard air flow rate Qas of the burner respectively through the standard gas pressure difference and the standard air pressure difference; S103: using the pressure difference method to calculate the actual gas flow Qg and the actual air flow Qa of the burner through the actual gas pressure difference and the actual air pressure difference; S104: judging the equipment type of the heating furnace according to the actual input side pressure and the actual output side pressure, wherein when the fluctuation values ​​of the input side pressure and the output side pressure both belong to the set fluctuation threshold, it is considered that the equipment type is double cross proportional regulation; S105: When the device type is double cross ratio regulation, it is considered that the burner meets the centralized prediction condition, and the current centralized data set is collected to input the centralized data set into the fault judgment model, the centralized data set includes: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2, the fault judgment model includes: |Qa-Qas|÷Qas<A1; |Qg-Qgs|÷Qgs>A2; Cco>A3; Co2>A4; Among them, |Qa-Qas|÷Qas is the first indicator, |Qg-Qgs|÷Qgs is the second indicator, A1, A2, A3, A4 are the first training threshold, the second training threshold, the third training threshold, and the fourth training threshold respectively; correspondingly, a plurality of corresponding training thresholds are obtained through machine learning training; S106: When the centralized data set conforms to the fault determination model, it is determined that the fault type of the burner is a solenoid valve blockage.

2. The method according to claim 1, characterized in that The steps of obtaining a plurality of corresponding training thresholds through machine learning training include: Acquire a training sample set, the training sample set comprising: input end training data, the input end training data comprising: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2; output end training data corresponding to the input end training data, the output end training data comprising: solenoid valve blockage data; Inputting the training sample set into a setting model to perform at least one iterative training; wherein the setting model is used to learn the intrinsic relationship between the first indicator, the second indicator, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2 and the solenoid valve blockage data; After the setting model converges, the setting model outputs the predicted numerical ranges of the first indicator, the second indicator, the exhaust gas carbon monoxide content Cco, and the exhaust gas oxygen content Co2 corresponding to the blockage state of the solenoid valve, and sets corresponding multiple training thresholds according to the predicted numerical ranges.

3. The method according to claim 2, characterized in that Before determining the fault of the burner, the method further comprises the following steps: (1) obtaining the historical training threshold value set last time according to the set model; (2) using an updated data set formed by the current burner in the first period, the updated data set comprising: input end updated data, which includes: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2; and output end updated data corresponding to the input end updated data, the output end updated data comprising: solenoid valve blockage data; (3) collecting a first updated data set from the updated data set and inputting the corresponding input-end updated data into the fault judgment model to obtain a fault prediction result output by the fault judgment model; wherein the fault judgment model uses the historical training threshold to make a judgment; (4) Comparing the fault prediction result with the output end update data, calculating the current prediction accuracy of the fault judgment model.

4. The method according to claim 3, characterized in that: The method further comprises the steps of: when the prediction accuracy is greater than a first set value, collecting a second update data set from the update data set; Inputting the second updated data set into the setting model to perform update training on the setting model; A new training threshold is set again based on the updated setting model.

5. The method according to claim 1, characterized in that Before determining the fault of the burner, the following steps are also included: Determine the combustion equilibrium state; It includes: Collect the excess air volume and actual air volume in the exhaust gas to calculate the excess air coefficient; wherein the excess air coefficient is calculated using the following formula: α=1 / [1-(ΔL / La)], α is the excess air coefficient, ΔL is the excess air volume, and La is the actual air volume; Determine whether the excess air coefficient is within the set threshold range. If so, execute the steps of: performing a fault determination on the burner; if not, continue to detect the excess air volume and the actual air volume of the exhaust gas.

6. A combustion balance AI intelligent detection and diagnosis system, characterized in that: The AI ​​intelligent detection and diagnosis system is applied to a combustion system, which includes a heating furnace and a burner that provides a heat source for the heating furnace. Correspondingly, the system includes a centralized fault determination subsystem, which includes: A reading module is used to read the serial number of the burner, and centrally read the rated pressure difference, actual pressure difference and working parameters of the burner according to the serial number; the rated pressure difference includes: standard pressure difference of gas and standard pressure difference of air; the actual pressure difference includes: actual pressure difference of gas and actual pressure difference of air; the pressure difference is the pressure difference between the input side pressure and the output side pressure of the flow orifice plate in the pipeline of the burner; the working parameters include: the diameter of the flow orifice plate, the ratio of the diameter of the flow orifice plate to the diameter of the pipeline, the expansion coefficient, the outflow coefficient, and the fluid density; A first calculation module, for respectively calculating a standard gas flow Qgs and a standard air flow Qas of the burner through the standard gas pressure difference and the standard air pressure difference by using a pressure difference method; A second calculation module is used to calculate the actual gas flow Qg and the actual air flow Qa of the burner by using the actual gas pressure difference and the actual air pressure difference using a pressure difference method; A type judgment module, used for judging the equipment type of the heating furnace according to the actual input side pressure and the actual output side pressure, wherein when the fluctuation values ​​of the input side pressure and the output side pressure both belong to the set fluctuation threshold, it is considered that the equipment type is double cross proportional regulation; A data input module is used for, when the device type is double cross ratio regulation, considering that the burner meets the centralized prediction condition, and collecting the current centralized data set to input the centralized data set into the fault judgment model, wherein the centralized data set includes: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2, and the fault judgment model includes: |Qa-Qas|÷Qas<A1; |Qg-Qgs|÷Qgs>A2; Cco>A3; Co2>A4; Among them, |Qa-Qas|÷Qas is the first indicator, |Qg-Qgs|÷Qgs is the second indicator, A1, A2, A3, A4 are the first training threshold, the second training threshold, the third training threshold, and the fourth training threshold respectively; correspondingly, a plurality of corresponding training thresholds are obtained through machine learning training; The fault determination module is used to determine that the fault type of the burner is a solenoid valve blockage when the centralized data set conforms to the fault determination model.

7. The system according to claim 6, characterized in that The data input module further comprises: A sample acquisition unit is used to acquire a training sample set, wherein the training sample set includes: input end training data, wherein the input end training data includes: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, and the exhaust gas oxygen content Co2; output end training data corresponding to the input end training data, wherein the output end training data includes: solenoid valve blockage data; An iteration unit, used for inputting the training sample set into a setting model to perform at least one iteration training; wherein the setting model is used for learning the intrinsic relationship between the first indicator, the second indicator, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2 and the solenoid valve blockage data; A threshold setting unit is used to output the predicted numerical range of the first indicator, the second indicator, the exhaust gas carbon monoxide content Cco, and the exhaust gas oxygen content Co2 corresponding to the blockage state of the solenoid valve through the setting model after the setting model converges, and set corresponding multiple training thresholds according to the predicted numerical range.

8. The system according to claim 7, characterized in that Also includes: The accuracy prediction subsystem performs the following steps: (1) obtaining the historical training threshold value set last time according to the set model; (2) using an updated data set formed by the current burner in the first period, the updated data set comprising: input end updated data, which includes: the standard gas flow Qgs, the standard air flow Qas, the actual gas flow Qg, the actual air flow Qa, the exhaust gas carbon monoxide content Cco, the exhaust gas oxygen content Co2; and output end updated data corresponding to the input end updated data, the output end updated data comprising: solenoid valve blockage data; (3) collecting a first updated data set from the updated data set and inputting the corresponding input-end updated data into the fault judgment model to obtain a fault prediction result output by the fault judgment model; wherein the fault judgment model uses the historical training threshold to make a judgment; (4) Comparing the fault prediction result with the output end update data, calculating the current prediction accuracy of the fault judgment model.

9. An electronic device, characterized in that: include: A memory and a processor; the memory is used to store a program; the processor is used to execute the program to implement each step of the combustion balance AI intelligent detection and diagnosis method as described in any one of claims 1 to 5.

10. A computer program product, characterized in that It includes a computer program, which, when executed by one or more processors, causes the one or more processors to execute the combustion balance AI intelligent detection and diagnosis method as described in any one of claims 1 to 5.

Images