Combustion device state recognition method and system based on physicochemical consistency diagnosis

Abstract

The application relates to the technical field of machinery, in particular to a combustion device state recognition method and system based on physical and chemical consistency diagnosis. The method comprises the following steps: collecting current operation parameters of a target combustion device; determining current physical and chemical constraint conditions based on the type of the target combustion device, and calculating the current violation degree of at least one physical and chemical constraint according to the current operation parameters based on the current physical and chemical constraint conditions; determining a target physical and chemical constraint with a current violation degree greater than a corresponding physical and chemical constraint threshold based on the current violation degree of the at least one physical and chemical constraint, and determining the fault type of the target combustion device according to the target physical and chemical constraint when the number of the target physical and chemical constraint is greater than a first preset number. Thus, the problems that the diagnosis conclusion cannot be traced back, relies on historical fault data and the accuracy of the diagnosis result is insufficient in the related art are solved, and traceable accurate positioning from abnormal phenomena to physical root causes is realized.

Description

Technical Field

[0001] This application relates to the field of mechanical technology, and in particular to a method and system for identifying the condition of a combustion device based on physicochemical consistency diagnosis. Background Technology

[0002] The chemical transformation process of carbon-containing fuels in combustion devices is entirely governed by a set of inviolable laws of conservation of physical and chemical properties. From the exothermic oxidation reaction of the fuel to the reaction of pollutants (… (sulfur dioxide) The formation and removal of nitrogen oxides (NOx) are governed by the law of conservation of elements. The total mass of each chemical element (carbon, sulfur, nitrogen, oxygen, hydrogen) entering the furnace remains unchanged before and after the reaction. The total energy input to the system equals the total energy output from the system (law of conservation of energy). A definite stoichiometric relationship exists between the amount of oxygen consumed and the amount of each combustible element in the fuel (stoichiometric ratio constraint). If a systematic deviation exceeding the measurement uncertainty occurs between the measured operating parameters and the theoretically expected values ​​of these laws, then this deviation is no longer a "measurement error" but a definite diagnostic signal, revealing some undetected anomaly in the system.

[0003] In related technologies, fault diagnosis of combustion devices is mainly divided into two types of schemes: data-driven and mechanism-assisted. The data-driven scheme embeds the mass and energy conservation equations as regularization constraints into the neural network loss function, and realizes fault classification through the adversarial generative network guided by physical knowledge and the diagnostic model. The mechanism-assisted scheme adopts a dual-drive scheme of system-level thermal balance mechanism model combined with operating data to complete the consistency verification of operating data and fault mode matching.

[0004] However, the related technologies have the following drawbacks: the diagnostic potential of physical conservation laws has not been directly utilized, resulting in untraceable diagnostic conclusions and inability to address unknown faults; the lack of multi-constraint collaborative diagnostic capabilities leads to inherent ambiguity in violations of single constraints; the inability to distinguish the causal direction of deviations leads to incorrect strategy selection; and the over-reliance on historical fault data results in failure for fault modes that have not occurred before, all of which urgently need to be addressed. Summary of the Invention

[0005] This application provides a combustion device status identification method and system based on physicochemical consistency diagnosis to solve the problems in related technologies such as the inability to trace diagnostic conclusions, reliance on historical fault data, and insufficient accuracy of diagnostic results, thereby achieving traceable and accurate location from abnormal phenomena to physical root causes.

[0006] To achieve the above objectives, the first aspect of this application proposes a method for identifying the condition of a combustion device based on physicochemical consistency diagnosis, comprising the following steps: Collect the current operating parameters of the target combustion device; Based on the type of the target combustion device, the current physical and chemical constraints are determined, and based on the current physical and chemical constraints, the current degree of violation of at least one physical and chemical constraint is calculated according to the current operating parameters. Based on the current degree of violation of the at least one physical and chemical constraint, a target physical and chemical constraint with a current degree of violation greater than the corresponding physical and chemical constraint threshold is determined, and if the number of the target physical and chemical constraints is greater than a first preset number, the fault type of the target combustion device is determined according to the target physical and chemical constraints.

[0007] According to one embodiment of this application, determining the current physicochemical constraints based on the type of the target combustion device includes: Identify whether the target combustion device is a circulating fluidized bed boiler; If the target combustion device is a circulating fluidized bed boiler, then the current physicochemical constraints are at least one of the following: carbon conservation constraints, sulfur conservation constraints, nitrogen conservation constraints, stoichiometric constraints, energy conservation constraints, solid product mass conservation constraints, working fluid mass conservation constraints, solid material inventory-bed pressure dynamic constraints, and in-furnace desulfurization-combustion coupling constraints. Otherwise, identify whether the target combustion device is a pulverized coal boiler; If the target combustion device is a pulverized coal boiler, then the current physicochemical constraints are at least one of the following: carbon conservation constraint, sulfur conservation constraint, nitrogen conservation constraint, stoichiometric ratio constraint, energy conservation constraint, solid product mass conservation constraint, working fluid side mass conservation constraint, furnace heat transfer distribution constraint, and burner zone stoichiometric zoning constraint.

[0008] According to one embodiment of this application, the target combustion device is a circulating fluidized bed boiler, and determining the fault type of the target combustion device based on the target physicochemical constraints includes: Based on the time-series data of the current operating parameters, calculate the first cross-correlation coefficient between bed pressure difference and bed temperature, and calculate the first directional index based on the first cross-correlation coefficient; The deviation-dominant type of the circulating fluidized bed boiler is determined based on the first directional index, and the fault type is determined based on the deviation-dominant type of the circulating fluidized bed boiler and the target physicochemical constraints.

[0009] According to one embodiment of this application, the target combustion device is a pulverized coal boiler, and determining the fault type of the target combustion device based on the target physicochemical constraints includes: Based on the time-series data of the current operating parameters, the second cross-correlation coefficient between the oxygen concentration field in the burner zone and the furnace outlet temperature is calculated, and the second directional index is calculated based on the second cross-correlation coefficient. The deviation-dominant type of the pulverized coal boiler is determined based on the second directional index, and the fault type is determined based on the deviation-dominant type of the pulverized coal boiler and the target physicochemical constraints.

[0010] According to one embodiment of this application, after determining a target physical and chemical constraint whose current violation degree is greater than the corresponding physical and chemical constraint threshold based on the current violation degree of the at least one physical and chemical constraint, the method further includes: If the number of the target physical and chemical constraints is a second preset number, then the target combustion device is determined to be fault-free. If the number of target physical and chemical constraints is greater than the second preset number and the number of target physical and chemical constraints is less than the first preset number, then the target combustion device is marked as an abnormal state.

[0011] According to one embodiment of this application, after determining the failure type of the target combustion device based on the target physicochemical constraints, the method further includes: Match the corresponding fault handling strategy according to the fault type, and perform fault handling operations on the target combustion device based on the fault handling strategy.

[0012] The combustion device status identification method based on physicochemical consistency diagnosis proposed in this application determines the current physicochemical constraints based on the type of the target combustion device, calculates the current violation degree based on the current physicochemical constraints, identifies target physicochemical constraints whose current violation degree is greater than the corresponding physicochemical constraint threshold, and determines the fault type of the target combustion device when the number of target physicochemical constraints is greater than a first preset number. This solves the problems of untraceable diagnostic conclusions, reliance on historical fault data, and insufficient accuracy of diagnostic results in related technologies, achieving traceable and precise localization from abnormal phenomena to physical root causes.

[0013] To achieve the above objectives, a second aspect of this application proposes a combustion device condition identification system based on physicochemical consistency diagnosis, comprising: The acquisition module collects the current operating parameters of the target combustion device; The calculation module determines the current physical and chemical constraints based on the type of the target combustion device, and calculates the current degree of violation of at least one physical and chemical constraint based on the current operating parameters. The determination module determines the target physical and chemical constraints whose current violation degree is greater than the corresponding physical and chemical constraint threshold based on the current violation degree of the at least one physical and chemical constraint, and determines the fault type of the target combustion device according to the target physical and chemical constraints when the number of the target physical and chemical constraints is greater than a first preset number.

[0014] According to one embodiment of this application, the computing module is specifically used for: Identify whether the target combustion device is a circulating fluidized bed boiler; If the target combustion device is a circulating fluidized bed boiler, then the current physicochemical constraints are at least one of the following: carbon conservation constraints, sulfur conservation constraints, nitrogen conservation constraints, stoichiometric constraints, energy conservation constraints, solid product mass conservation constraints, working fluid mass conservation constraints, solid material inventory-bed pressure dynamic constraints, and in-furnace desulfurization-combustion coupling constraints. Otherwise, identify whether the target combustion device is a pulverized coal boiler; If the target combustion device is a pulverized coal boiler, then the current physicochemical constraints are at least one of the following: carbon conservation constraint, sulfur conservation constraint, nitrogen conservation constraint, stoichiometric ratio constraint, energy conservation constraint, solid product mass conservation constraint, working fluid side mass conservation constraint, furnace heat transfer distribution constraint, and burner zone stoichiometric zoning constraint.

[0015] According to one embodiment of this application, the target combustion device is a circulating fluidized bed boiler, and the determining module is specifically used for: Based on the time-series data of the current operating parameters, calculate the first cross-correlation coefficient between bed pressure difference and bed temperature, and calculate the first directional index based on the first cross-correlation coefficient; The deviation-dominant type of the circulating fluidized bed boiler is determined based on the first directional index, and the fault type is determined based on the deviation-dominant type of the circulating fluidized bed boiler and the target physicochemical constraints.

[0016] According to one embodiment of this application, the target combustion device is a pulverized coal boiler, and the determining module is specifically used for: Based on the time-series data of the current operating parameters, the second cross-correlation coefficient between the oxygen concentration field in the burner zone and the furnace outlet temperature is calculated, and the second directional index is calculated based on the second cross-correlation coefficient. The deviation-dominant type of the pulverized coal boiler is determined based on the second directional index, and the fault type is determined based on the deviation-dominant type of the pulverized coal boiler and the target physicochemical constraints.

[0017] According to one embodiment of this application, after determining a target physicochemical constraint whose current violation degree is greater than the corresponding physicochemical constraint threshold based on the current violation degree of the at least one physicochemical constraint, the determining module is further configured to: If the number of the target physical and chemical constraints is a second preset number, then the target combustion device is determined to be fault-free. If the number of target physical and chemical constraints is greater than the second preset number and the number of target physical and chemical constraints is less than the first preset number, then the target combustion device is marked as an abnormal state.

[0018] According to one embodiment of this application, after determining the fault type of the target combustion device based on the target physicochemical constraints, the determining module is further configured to: Match the corresponding fault handling strategy according to the fault type, and perform fault handling operations on the target combustion device based on the fault handling strategy.

[0019] The combustion device status identification system based on physicochemical consistency diagnosis proposed in this application determines the current physicochemical constraints based on the type of the target combustion device, calculates the current violation degree based on the current physicochemical constraints, identifies target physicochemical constraints whose current violation degree is greater than the corresponding physicochemical constraint threshold, and determines the fault type of the target combustion device when the number of target physicochemical constraints is greater than a first preset number. This solves the problems of untraceable diagnostic conclusions, reliance on historical fault data, and insufficient accuracy of diagnostic results in related technologies, achieving traceable and precise localization from abnormal phenomena to physical root causes.

[0020] To achieve the above objectives, a third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the combustion device status identification method based on physicochemical consistency diagnosis as described in the above embodiments.

[0021] To achieve the above objectives, a fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the combustion device status identification method based on physicochemical consistency diagnosis as described in the above embodiments.

[0022] To achieve the above objectives, a fifth aspect of this application provides a computer program product, which, when executed by a processor, implements the combustion device status identification method based on physicochemical consistency diagnosis as described in the above embodiments.

[0023] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0024] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a combustion device condition identification method based on physicochemical consistency diagnosis provided in an embodiment of this application; Figure 2 This is a schematic diagram of a differentiated physicochemical constraint system for two types of coal-fired boilers according to an embodiment of this application; Figure 3 This is a schematic diagram of a multi-constraint collaborative violation determination decision tree provided according to an embodiment of this application; Figure 4 This is a schematic diagram illustrating the principle of time-series causal analysis according to an embodiment of this application; Figure 5 This is a comparative schematic diagram of a diagnostic method provided according to an embodiment of this application; Figure 6 This is a flowchart of a combustion device condition identification method based on physicochemical consistency diagnosis according to an embodiment of this application; Figure 7 This is a block diagram of a combustion device condition identification system based on physicochemical consistency diagnosis provided in an embodiment of this application; Figure 8 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0025] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0026] The following describes, with reference to the accompanying drawings, a method and system for identifying the state of a combustion device based on physicochemical consistency diagnosis, according to embodiments of this application.

[0027] Before introducing the combustion device status identification method based on physicochemical consistency diagnosis according to the embodiments of this application, we will first introduce the fault diagnosis method of combustion device in related technologies.

[0028] For example, a method for diagnosing industrial boiler faults based on physical knowledge generative adversarial networks is disclosed in related technologies. The technical route of this scheme consists of four steps: acquiring and preprocessing historical operating data of industrial boilers; establishing a physical knowledge neural network model containing mass and energy conservation equations to simulate boiler operation; establishing a generative adversarial network to generate training data; and training a diagnostic model to classify faults. In this scheme, the mass and energy conservation equations serve as constraints or regularization terms for training the neural network. They are embedded in the network structure or loss function to guide the network to learn mapping relationships that conform to physical laws. However, the final decision-maker for determining the fault category is still the neural network itself. This leads to three core problems that this application aims to solve: First, the method relies on a large amount of balanced historical fault data to train the model. It lacks diagnostic capabilities for fault patterns that have never appeared in the training data, and newly built combustion devices or old devices with limited operating records often lack sufficient historical fault data. Second, its diagnostic output is in the form of fault category labels, which cannot provide a physical causal chain explanation of "which conservation law was violated, what the direction and magnitude of the violation were, and why this violation pattern uniquely corresponds to this root cause." Third, this scheme is a single-layer diagnostic architecture that only performs fault classification and does not have the ability to cross-validate abnormal root causes from multiple dimensions.

[0029] Another example is a boiler fault diagnosis method and system disclosed in related technologies, which adopts a dual-drive approach of "structural mechanism model plus operational data". Its "structural mechanism" mainly refers to calculations at the thermodynamic system model level, such as verifying the consistency of operational data or estimating internal state variables based on the overall thermal and material balance of the boiler. The structural mechanism constraints of this scheme remain at the system-level thermal balance level, without delving into the material conservation level of individual chemical elements. More importantly, after detecting state deviations, this scheme matches fault modes through a data-driven method, lacking the logic for determining coordinated violations between multiple constraint equations. For example, this scheme cannot distinguish between two completely different anomalies: "carbon conservation violated alone" and "carbon conservation and energy conservation violated simultaneously and in the same direction".

[0030] Therefore, the following are the main drawbacks of the related technologies: First, the diagnostic potential of physical conservation laws is not directly utilized. The related technologies reduce conservation equations to auxiliary conditions for neural network training. Physical laws are misplaced from "unbreakable judgment criteria" to "a trick to make the model more accurate," resulting in untraceable diagnostic conclusions and inability to address unknown faults. Second, there is a lack of multi-constraint collaborative diagnostic capabilities. Violations of a single constraint have inherent ambiguity (for example, a non-closed carbon conservation constraint could be due to either a deviation in coal feed measurement or a change in coal quality). The related technologies all adopt a single-line path of "single constraint deviation calculation and model matching," without distinguishing between carefully labeled single constraint violations and deterministic diagnosis of multi-constraint collaborative violations. Third, the causal direction of deviations cannot be distinguished. In circulating fluidized bed boilers, changes in material flow can cause temperature changes, and changes in combustion intensity can also cause changes in material distribution. The two have similar external manifestations but completely different root causes and control strategies. The related technologies cannot distinguish this difference in causal direction through time-series causal analysis. Fourth, they generally rely on historical fault data. Existing data-driven methods require a large number of balanced historical fault samples and fail for fault modes that have never occurred before.

[0031] Based on the above problems, the technical problem to be solved by the embodiments of this application is: how to use physical conservation laws directly as diagnostic tools without relying on historical fault data and statistical learning models, and achieve traceable and explainable precise location from observed abnormal phenomena to the physical root cause of the abnormality by online determination of the consistency between the real-time operating parameters of carbon fuel combustion devices and the conservation laws that should be satisfied, and be able to distinguish multiple types of deviations that are similar on the surface but have different physical causal directions. This technical problem can be broken down into four sub-problems: how to establish a complete system of physicochemical constraint equations that covers both the conservation of matter at the chemical reaction level (the total amount of elements such as carbon, sulfur, and nitrogen remains unchanged before and after the reaction) and the conservation relationships at the physical process level (energy conservation and mass conservation of solid products), thereby providing a physical benchmark for diagnosing common operational deviations; how to eliminate the inherent ambiguity of single constraint diagnosis through the coordinated violation determination of multiple constraint equations, that is, how to use the combination patterns of violations between different constraints to narrow down the possible root causes from multiple to a single one; when multiple parameters become abnormal almost simultaneously, how to determine the fundamental driving force of the deviation through time-series causal analysis, whether the material flow changes first (material or air distribution deviates first) or the energy flow changes first (combustion intensity or heat transfer state deviates first); and how to make this diagnostic method independent of historical fault data, but based on the universality of the laws of physicochemical conservation.

[0032] Compared with related technologies, the beneficial effects of the embodiments of this application are reflected in the following aspects: It realizes the transformation of the law of conservation of physicochemical properties from a "training aid" to a "diagnostic benchmark." Unlike related technologies that use conservation equations to constrain neural network training, the embodiments of this application directly use the conservation equations themselves as the basis for diagnostic judgment, without going through a neural network or relying on historical data. The diagnosis conclusion is determined by which law is violated, the direction of the violation, and the magnitude of the violation, making the diagnosis completely white-box traceable. It proposes two different criterion levels: "cautious marking of single constraint violation" and "deterministic diagnosis of multi-constraint collaborative violation," utilizing the natural physical coupling relationship between different constraint equations for cross-verification, transforming the diagnosis from "one-to-many" to "many-to-one." It realizes the temporal causal direction discrimination of combustion device operating deviations, using bed pressure difference and bed temperature as indicator variables in CFB boilers, and burner zone oxygen concentration and furnace outlet temperature / … Using the cross-correlation directional index D as an indicator variable, it distinguishes between material flow-dominated and energy flow-dominated deviations; without relying on historical fault data, it has the same diagnostic capability for all operating conditions, including fault modes that have never occurred, based on the universality of conservation laws.

[0033] Specifically, such as Figure 1 As shown, the combustion device condition identification method based on physicochemical consistency diagnosis includes the following steps: In step S101, the current operating parameters of the target combustion device are collected.

[0034] Among them, the current operating parameters refer to the measurement data of the target combustion device's online real-time acquisition and the instantaneous operating status of the reaction equipment.

[0035] Specifically, in this embodiment, five types of operating parameters are acquired from the sensor array at a cycle of 2-5 seconds: fuel input parameters, air-side parameters, flue gas output parameters, working fluid-side parameters, and solid product mass conservation parameters.

[0036] Furthermore, the fuel input parameters include: coal mass flow rate, and elemental analysis data of the coal (based on received carbon content). Sulfur content Nitrogen content Oxygen content Hydrogen content The parameters include: Lower Heating Value (LHV) and Ash Content (as received); Air-side parameters include: Total Air Volume, Primary Air Volume, Secondary Air Volume, and Corresponding Air Temperature; Flue Gas Output Parameters include: Economizer Outlet, Furnace Outlet, and Concentrations of Various Components Before and After SCR (Selective Catalytic Reduction) and FGD (Flue Gas Desulfurization). (Oxygen), CO (carbon monoxide) , ), flue gas temperature field distribution, flue gas pressure, and flue gas flow rate; working fluid side parameters include: main steam temperature, pressure, and flow rate, reheat steam temperature, pressure, and flow rate, and feedwater temperature and pressure; solid product parameters include: fly ash mass flow rate. and its carbon content Bottom ash or slag mass flow rate and its carbon content .

[0037] Furthermore, the sampling locations for flue gas output parameters include the economizer outlet, furnace outlet, before and after the SCR, and before and after the FGD. The sampling locations can be flexibly selected, and each location is an OR selection relationship, so it is not necessary to configure all of them.

[0038] In step S102, based on the type of the target combustion device, the current physical and chemical constraints are determined, and based on the current physical and chemical constraints, the current degree of violation of at least one physical and chemical constraint is calculated according to the current operating parameters.

[0039] Optionally, in some embodiments, the current physicochemical constraints are determined based on the type of the target combustion device, including: identifying whether the target combustion device is a circulating fluidized bed boiler; if the target combustion device is a circulating fluidized bed boiler, then the current physicochemical constraints are at least one of the following: carbon conservation constraints, sulfur conservation constraints, nitrogen conservation constraints, stoichiometric ratio constraints, energy conservation constraints, solid product mass conservation constraints, working fluid side mass conservation constraints, solid material inventory-bed pressure dynamic constraints, and in-furnace desulfurization-combustion coupling constraints; otherwise, identifying whether the target combustion device is a pulverized coal boiler; if the target combustion device is a pulverized coal boiler, then the current physicochemical constraints are at least one of the following: carbon conservation constraints, sulfur conservation constraints, nitrogen conservation constraints, stoichiometric ratio constraints, energy conservation constraints, solid product mass conservation constraints, working fluid side mass conservation constraints, furnace heat transfer distribution constraints, and burner zone stoichiometric zoning constraints.

[0040] Specifically, the embodiments of this application set seven general physicochemical constraints, namely: carbon element conservation constraint C1, sulfur element conservation constraint C2, nitrogen element conservation constraint C3, stoichiometric ratio constraint C4, energy conservation constraint C5, solid product mass conservation constraint C6, and working fluid side mass conservation constraint C7.

[0041] Furthermore, the current degree of violation of the carbon conservation constraint C1 is: ; in, For coal mass flow rate, The mass fraction of carbon in the received base. In the flue gas Mass flow rate of (carbon dioxide), For carbon in The mass percentage of the molecule, In the flue gas mass flow rate For carbon in The mass percentage of the molecule, The mass flow rate of fly ash. This refers to the carbon content in fly ash. The mass flow rate of the bottom ash. This refers to the carbon content in the bottom ash.

[0042] Furthermore, the current degree of violation of the sulfur conservation constraint C2 is: ; in, To determine the mass fraction of sulfur in the base, In the flue gas Mass flow rate For sulfur in The proportion of quality in This represents the total mass flow rate of fly ash and bottom ash. This represents the mass fraction of calcium sulfate in the ash residue. For sulfur in The percentage of quality in the product.

[0043] Furthermore, the current degree of violation of the nitrogen conservation constraint C3 is: ; in, The mass fraction of nitrogen in the coal received. This refers to the total mass flow rate of air entering the furnace. This represents the mass fraction of nitrogen in the air. This represents the total mass flow rate of the outlet flue gas. This represents the mass fraction of nitrogen in the flue gas.

[0044] Furthermore, the current violation degree of the stoichiometric constraint C4 is: ; in, This refers to the total amount of oxygen fed into the furnace. This refers to the amount of oxygen remaining in the exhaust gas. This is the theoretical oxygen demand calculated based on fuel elemental analysis data and combustion reaction equations.

[0045] Furthermore, the current degree of violation of the energy conservation constraint C5 is: ; in, To receive the low-grade heat of the base, The total mass flow rate of superheated steam (and reheated steam). The increase in the total enthalpy of heat absorbed by the working fluid in the furnace is due to... The heat loss carried away by the flue gas, The heat loss carried away by fly ash and bottom ash, For other heat losses.

[0046] Furthermore, the current degree of violation of the solid product mass conservation constraint C6 is: ; in, The ash content is the mass fraction of the coal received. The mass flow rate of fly ash. The mass flow rate of the bottom ash is denoted as .

[0047] Furthermore, the current degree of violation of the working fluid-side mass conservation constraint C7 is: ; in, The mass flow rate of the boiler feedwater. The mass flow rate of the main steam. The mass flow rate of reheat steam. The mass flow rate for continuous and periodic boiler blowdown.

[0048] Furthermore, for circulating fluidized bed (CFB) boilers, the physical and chemical constraints also include the solid material inventory-bed pressure dynamic constraint C8 and the in-furnace desulfurization-combustion coupling constraint C9.

[0049] Specifically, the solid material inventory-bed pressure dynamic constraint C8 is used to detect abnormalities in the material circulation loop, and the current violation degree is: ; in, The total mass of the bed material inside the furnace. The rate of change of the total mass of the bedding material over time. This refers to the ash mass flow rate that enters the furnace with the fuel. This refers to the mass flow rate of limestone feed. The mass flow rate of fly ash discharged from the furnace. The mass flow rate of bottom ash discharged from the furnace.

[0050] Among them, the rate of change of material inventory Through bed pressure difference Conversion between time derivative and bed cross-sectional area: ; in, For bed pressure differential, The cross-sectional area of ​​the furnace bed is... This represents the rate of change of bed pressure differential over time.

[0051] Furthermore, the in-furnace desulfurization-combustion coupling constraint C9 is used to accurately distinguish S The three root causes of the increase are: low bed temperature leading to decreased desulfurization efficiency, insufficient limestone feed, and limestone particle size being too coarse or having poor activity. The current deviation is: ; in, For the actual measured flue gas Emission concentration; This refers to the actual measured bed temperature; This refers to the actual calcium-sulfur molar ratio during operation. This refers to the actual stock of bed materials. , , and These are reference values ​​under optimal desulfurization conditions. , , and The weighting coefficients and + + + This formula combines the deviations of the four parameters into a single violation index using a weighted sum, and the weights can be adjusted according to the degree of influence of each parameter on the desulfurization efficiency. The current violation of the in-furnace desulfurization-combustion coupling constraint C9 is the normalized Euclidean distance between the current operating condition diagnostic vector and the optimal desulfurization operating condition diagnostic vector.

[0052] Furthermore, for pulverized coal boilers (PC), the physicochemical constraints also include furnace heat transfer distribution constraint C10 and burner zone stoichiometric zoning constraint C11.

[0053] Specifically, the current degree of violation of the furnace heat transfer distribution constraint C10 is: ; Among them, slagging of the water-cooled wall is determined when the proportion of radiative heat absorption decreases significantly from the design value while the proportion of convective heat absorption increases accordingly, through each furnace height section. The main areas where slag is distributed and located are the primary areas. To account for the thermal resistance of the ash-polluted wall, the radiative heat absorption of the water-cooled wall is determined through back-calculation of heat transfer as follows: ; in, The baseline thermal resistance of the heated surface under clean conditions is based on ash and dirt. The water-cooled wall absorbs heat through radiation. The average temperature of the flue gas in the furnace. This refers to the water-cooled wall tube temperature. The thermal resistance is the baseline for cleanroom operation.

[0054] Furthermore, the current violation rate of the burner zone stoichiometric zoning constraint C11 is: ; Specifically, in this embodiment, the furnace is divided along the height direction into... A stoichiometric region, j The first division along the height of the furnace j Each burner zone This represents the target oxygen-to-coal equivalent ratio for this zone under design operating conditions. The value with the largest deviation among all partitions is taken as the final violation degree of the constraint. The oxygen-coal equivalent ratio for each region is given when a certain region... If the CO concentration remains consistently low and a CO concentration peak appears at the corresponding height in that zone, it is determined that there is an uneven distribution of fuel / air volume in the burner of that layer.

[0055] For example, such as Figure 2 As shown, Figure 2 This is a schematic diagram of a differentiated physicochemical constraint system for two types of coal-fired boilers, provided according to an embodiment of this application, as a supplement to the boiler type adaptation of the general conservation constraint: For circulating fluidized bed boilers, a dynamic constraint C8 on solid material inventory-bed pressure and a coupled constraint C9 on in-furnace desulfurization-combustion are set. The former identifies faults such as abnormal return material and poor slag discharge based on the bed material mass change rate and bed pressure change rate, while the latter identifies faults through coupling... Concentration, bed temperature, calcium-to-sulfur ratio, and material circulation characteristics can distinguish between them. Three different root causes of the problem were identified. For pulverized coal PC boilers, furnace heat transfer distribution constraint C10 and burner zone chemimetric zoning constraint C11 were set. The former diagnoses slagging location based on changes in the furnace radiation-convective heat transfer ratio, while the latter determines abnormal air distribution conditions based on the oxygen-coal ratio distribution of the stratified burners. This ensures the accuracy of root cause location and scenario adaptability for different boiler types.

[0056] In step S103, based on the current violation degree of at least one physical and chemical constraint, target physical and chemical constraints with a current violation degree greater than the corresponding physical and chemical constraint threshold are determined. If the number of target physical and chemical constraints is greater than a first preset number, the fault type of the target combustion device is determined according to the target physical and chemical constraints. It should be noted that... The physicochemical constraint threshold can be a user-preset threshold, a threshold obtained through a finite number of experiments, or a threshold obtained through a finite number of computer simulations. The first preset quantity can be a user-preset quantity, a quantity obtained through a finite number of experiments, or a quantity obtained through a finite number of computer simulations.

[0057] Specifically, for a general target combustion device, the root cause is uniquely determined only when two or more constraints are violated simultaneously in a specific combination in a particular direction.

[0058] For example, such as Figure 3 As shown, Figure 3 This is a schematic diagram of a multi-constraint collaborative violation decision tree provided according to an embodiment of this application. If only one physicochemical constraint exceeds the threshold, it is marked as abnormal, with no root cause conclusion. If the carbon conservation constraint C1 and the energy conservation constraint C5 are violated simultaneously, and the violation direction is that the right side is less than the left side (theoretical values ​​are both greater than measured values), then the two constraints are violated in the same direction. Since both carbon and energy are proportional to the coal feed rate, they must deviate in the same direction. Therefore, the only determination is that the coal feed rate measurement system is too high, excluding changes in coal quality. If the stoichiometric ratio constraint C4 is violated (actual oxygen consumption is less than theoretical oxygen demand), and the carbon conservation constraint C1 is normal but the CO concentration is increased, then the oxygen consumption is insufficient, but the carbon balance is closed, indicating that the total air volume is sufficient, but some fuel has not been in sufficient contact with oxygen. Therefore, it is determined that the fuel and air are not mixed evenly. If the working fluid mass conservation constraint C7 and the energy conservation constraint C5 are violated simultaneously in the same direction, the working fluid mass loss is accompanied by energy loss. Therefore, the only determination is that there is a leak in the heating surface, excluding the measurement deviation of the sewage flow rate. It should be noted that... Figure 3 This is merely an illustrative demonstration of some typical scenarios of multi-constraint collaborative violation judgment logic. In this application embodiment, all 22 violation modes are organized into a data structure of a violation propagation directed graph. By using directed edges to carry the causal propagation relationship between constraint violations, the root cause mode of the fault can be quickly matched and traversed, which greatly improves the computational efficiency and root cause localization accuracy of multi-constraint collaborative diagnosis.

[0059] Optionally, in some embodiments, the target combustion device is a circulating fluidized bed boiler. Determining the fault type of the target combustion device based on the target physicochemical constraints includes: calculating a first cross-correlation coefficient between bed pressure difference and bed temperature based on time-series data of current operating parameters, and calculating a first directional index based on the first cross-correlation coefficient; determining the deviation-dominant type of the circulating fluidized bed boiler based on the first directional index; and determining the fault type based on the deviation-dominant type of the circulating fluidized bed boiler and the target physicochemical constraints.

[0060] Optionally, in some embodiments, the target combustion device is a pulverized coal boiler. Determining the fault type of the target combustion device based on the target physicochemical constraints includes: calculating a second cross-correlation coefficient between the oxygen concentration field in the burner zone and the furnace outlet temperature based on time-series data of the current operating parameters, and calculating a second directional index based on the second cross-correlation coefficient; determining the deviation-dominant type of the pulverized coal boiler based on the second directional index; and determining the fault type based on the deviation-dominant type of the pulverized coal boiler and the target physicochemical constraints.

[0061] Among them, bed temperature refers to the average temperature of the gas-solid two-phase flow within the bed material layer in the dense phase zone of the furnace. The oxygen concentration field in the burner zone refers to the spatial distribution field of oxygen concentration along the furnace height and the radial and circumferential directions of the cross-section within the main combustion zone of the furnace (the axial interval where the nozzles of each burner layer are located).

[0062] Specifically, when the current combustion device is a circulating fluidized bed boiler, the bed pressure difference... With bed temperature There is a bidirectional coupling problem in determining the causal direction. When both factors deviate from their normal values ​​almost simultaneously, simply relying on constraint violation cannot determine which changed first and which changed later, while the causal direction directly determines the control strategy. This application's embodiment calculates the bed pressure difference. With bed temperature The first cross-correlation coefficient between With lag time The changes, among which, For bed pressure differential, For bed temperature, a first directional index is defined based on the first cross-correlation coefficient. : ; Specifically, if A value greater than 1.5 indicates that the peak correlation in the positive lag direction is significantly stronger than that in the negative lag direction, suggesting... Change precedes Changes, i.e., deviations dominated by material flow, should prompt priority inspection of the return and slag removal systems; if Less than 0.67 indicates Change precedes Changes in combustion intensity, leading to deviations, should prompt a priority check of fuel and airflow.

[0063] Furthermore, when the current combustion device is a PC boiler, the burner zone... Concentration field (characterizing air distribution / mixing state) is Furnace outlet temperature or Concentration (characterizing combustion products and energy release) is Calculate the second cross-correlation coefficient and define the second directional index. Based on the second directional index, determine the causal direction of analogy.

[0064] For example, such as Figure 4 As shown, Figure 4 This is a schematic diagram of the time-series causal analysis principle provided according to an embodiment of this application. The CFB on the left uses bed pressure difference and bed temperature as analysis parameters, while the PC boiler on the right uses oxygen concentration in the burner zone and furnace outlet temperature as analysis parameters, with directional indicators... Defined as the ratio of the maximum absolute values ​​of the cross-correlation coefficients in the positive and negative lag directions, it is used to quantify the causal lag relationship of parameter fluctuations. When the CFB... When the value is greater than 1.5, it is judged as a flow-dominant deviation, indicating that the abnormal flow state of the material in the bed is the root cause of the deviation; the air distribution-dominant deviation of the PC boiler is manifested by the oxygen concentration change leading the temperature fluctuation, indicating that the air distribution imbalance is the main cause, thus realizing the differentiation of the root cause of the fault.

[0065] Therefore, based on the type of the target combustion device, the current physicochemical constraints are determined, the current violation degree is calculated based on the current physicochemical constraints, and the target physicochemical constraints with a current violation degree greater than the corresponding physicochemical constraint threshold are identified. When the number of target physicochemical constraints is greater than a first preset number, the fault type of the target combustion device is determined. This solves the problems in related technologies such as the inability to trace diagnostic conclusions, reliance on historical fault data, and insufficient accuracy of diagnostic results, achieving traceable and precise localization from abnormal phenomena to physical root causes.

[0066] Furthermore, in order to improve the distinguishability of fault diagnosis and the timeliness of early warning, the embodiments of this application have implemented a graded judgment.

[0067] Optionally, in some embodiments, after determining a target physicochemical constraint whose current violation degree is greater than the corresponding physicochemical constraint threshold based on the current violation degree of at least one physicochemical constraint, the method further includes: determining that the target combustion device is fault-free in response to the number of target physicochemical constraints being a second preset number; and marking the target combustion device as abnormal in response to the number of target physicochemical constraints being greater than the second preset number and less than the first preset number.

[0068] The second preset quantity can be a quantity pre-set by the user, a quantity obtained through a limited number of experiments, or a quantity obtained through a limited number of computer simulations.

[0069] Specifically, if the current violation degree of all physical and chemical constraints is less than the respective diagnostic threshold, i.e. If the violation of only one constraint exceeds the threshold, for example, if only the current violation of the carbon conservation constraint is greater than the corresponding physicochemical constraint threshold, then the target combustion device is determined to be operating normally. The other six constraints are all within the normal range. Since a single constraint violation is ambiguous, a violation of carbon conservation alone may be due to a deviation in the coal feed measurement, a change in the carbon content of the coal, or simply an accidental deviation in fly ash sampling. Therefore, the embodiments of this application only mark "an anomalies that need attention" without outputting a definite root cause.

[0070] This clearly distinguishes between three states: no fault, abnormal warning, and fault diagnosis, effectively improving the differentiation of fault diagnosis and the timeliness of warning, and reducing the risk of misjudgment and missed diagnosis.

[0071] Furthermore, in order to achieve closed-loop management of fault diagnosis and handling, the embodiments of this application match targeted handling strategies and execute controls based on the diagnosed fault type.

[0072] Optionally, in some embodiments, after determining the fault type of the target combustion device based on the target physicochemical constraints, the method further includes: matching the corresponding fault handling strategy according to the fault type, and performing fault handling operations on the target combustion device based on the fault handling strategy.

[0073] Specifically, in this application embodiment, a targeted control scheme is matched according to the confirmed fault type. It can be sent to the unit control system to complete the automatic adjustment of operating parameters, or it can be pushed to the operation and maintenance terminal to trigger the manual handling process.

[0074] This effectively shortens the fault response cycle and reduces equipment safety risks and maintenance costs.

[0075] Therefore, the conservation equation itself is used directly as the basis for diagnosis and judgment, without going through neural networks or relying on historical data, realizing the transformation of the physical and chemical conservation law from a "training aid" to a "diagnostic benchmark"; it proposes two different criterion levels to distinguish between "cautionary marking of single constraint violation" and "deterministic diagnosis of multi-constraint cooperative violation", fundamentally eliminating the ambiguity of single diagnosis through multi-constraint cooperative violation judgment; it realizes the discrimination of temporal causal direction; it does not rely on historical fault data; and the general and adaptive two-layer constraint architecture takes into account both protection width and depth.

[0076] To help those skilled in the art to further understand the combustion device status identification method based on physicochemical consistency diagnosis proposed in the embodiments of this application, further explanation is provided below in conjunction with specific embodiments.

[0077] For example, a 300MW subcritical circulating fluidized bed boiler with a rated evaporation capacity of 1025t / h has a bed pressure difference... The pressure initially rose slowly from 9.0 kPa, reaching 10.2 kPa after approximately two hours (an increase of about 13%). About eight minutes after the bed pressure began to rise, the bed temperature... The temperature slowly decreased from 860℃ to 835℃. Time-series causal analysis: The most recent 600 seconds of data were used as a time window. for , for Calculate the cross-correlation coefficient at lag time. Appears at +120 seconds A significant positive correlation peak of +0.72 ( The rise is ahead of The descent lasts approximately 120 seconds), with the maximum negative hysteresis in the direction of lag. | Only 0.21. Directional indicator =0.72 / 0.21=3.43, which is much greater than the judgment threshold of 1.5, thus clearly indicating a material flow-dominated deviation. Simultaneously, constraint violation calculation: the degree of violation of the dynamic constraint C8 of solid material inventory - bed pressure. =0.09 exceeds the threshold of 0.06 (confirming net change in material inventory), indicating a violation of energy conservation constraint C5. =0.03 is within the normal range (confirming normal energy balance on the combustion side). The diagnosis is an abnormality in the material circulation loop, with obstructed material flow in the return leg or poor bottom ash discharge leading to net accumulation of bed material. It is recommended to prioritize checking the fluidizing air volume of the return leg, the opening of the return valve, and the ash discharge status of the bottom ash cooler, rather than adjusting the fuel or air volume.

[0078] Another example is a 600MW supercritical tangential pulverized coal boiler. During operation, the flue gas temperature at the furnace outlet was 25°C higher than that under clean operating conditions at the same load. The heat flux density calculated from the water-cooled wall temperature measurement data was approximately 18% lower than under clean operating conditions, indicating a violation of energy conservation constraint C5. =0.06, exceeding the diagnostic threshold of 0.05. Further analysis of furnace heat transfer distribution constraint C10: The average radiative heat absorption ratio of the entire furnace decreased from the design value of 48% to 37%, while the convective heat absorption ratio correspondingly increased from 52% to 63%. The thermal resistance of ash and sludge in each zone was calculated according to the furnace height. The upper zone front wall showed the largest decrease in radiative heat absorption, down approximately 28% from the design value. This violation of mode matching was identified as slagging on the water-cooled wall, with the primary slagging area located on the upper front wall of the furnace (elevation 35-45m). The rate of increase in thermal resistance due to ash fouling was also observed. If the value is greater than 0 and the second derivative is positive, it is predicted that the heat transfer degradation will reach a level requiring mandatory intervention after approximately 48 hours. The diagnostic output will trigger the sootblower in the upper area of ​​the front wall to start in the programmed sequence.

[0079] Another example is a 300MW CFB boiler in operation. The emission concentration suddenly increased from the normal 50 mg / Nm³ to 180 mg / Nm³. This represents a violation of the sulfur conservation constraint (C₂). =0.07 exceeds the threshold of 0.05. Joint analysis of four parameters of in-furnace desulfurization-combustion coupling constraint C9: bed temperature 835℃, lower than the optimal desulfurization temperature window of 850-870℃; calcium-sulfur molar ratio Ca / S = 2.5, within the normal range of 2.0-3.0; limestone feed is sufficient; material inventory (via...) The characteristics (of the samples) are within the normal range. The conclusion is that the low bed temperature is the main reason for the decreased desulfurization efficiency; specifically, at 835℃, both the limestone calcination rate and the desulfurization reaction rate are significantly reduced, and even with a sufficient calcium-to-sulfur ratio, effective desulfurization cannot be achieved. This application's embodiments suggest prioritizing restoring the bed temperature to the 850-870℃ range, rather than blindly increasing the limestone feed rate.

[0080] Another example is a 600MW supercritical pulverized coal boiler. The working fluid-side mass conservation constraint C7 consistently showed a violation. The difference between the total feedwater mass flow rate and the main steam and reheat steam flow rates gradually increased from approximately 5 tons per hour (normal value) to approximately 12 tons per hour, with the violation rate rising from 0.02 to 0.08, exceeding the threshold of 0.05. During the same period, the violation rate of the energy conservation constraint C5 also increased from 0.02 to 0.05. The coordinated and simultaneous violation of the working fluid-side mass conservation constraint C7 and the energy conservation constraint C5 indicates that the leaking high-temperature, high-pressure water / steam caused both a loss of working fluid mass and an unmetered loss of energy. Excluding blowdown flow rate metering deviations (if it were only a metering deviation, C5 should not change synchronously), the only reasonable physical cause is a continuously expanding micro-leak at the heating surface, with a leakage rate of approximately 7 tons per hour and continuously increasing. Upon assessment, a high-priority alarm was immediately issued, and a boiler shutdown for inspection was recommended.

[0081] In another example, during the operation of a 350MW CFB boiler, the carbon content in fly ash gradually increased from the recent normal value of approximately 2.5% to 4.8%, but the CO emission concentration did not increase significantly at the same time. Simultaneously, the carbon conservation constraint C1 and the stoichiometric constraint C4 were both within the normal range, indicating a closed total carbon balance. However, the increased carbon proportion in fly ash suggested insufficient combustion time for complete combustion. Based on the combined constraint analysis of C1 and C4, the analysis concluded that the coal powder fineness was too coarse or the average particle size of the bed material in the circulating fluidized bed boiler was too large.

[0082] Furthermore, such as Figure 5 As shown, Figure 5This is a comparative schematic diagram of the diagnostic method provided according to an embodiment of this application. The results of 13 typical operating deviation verification tests carried out on a 3MWthCFB test bench show that the proposed physicochemical consistency diagnostic method has a diagnostic accuracy of up to 93%, which is significantly better than the 62% diagnostic level of the traditional single-parameter threshold method. In terms of fault response performance, the method can complete the automatic transition judgment of fault level within 45s, which is much faster than the 4 minutes and 20 seconds required for manual judgment. It can also achieve an early trend warning 5 to 15 minutes before the fault occurs. For two types of composite deviations not included in historical operating conditions, the method can make correct diagnoses. The accuracy of determining the causal direction of flow-dominated and combustion-dominated deviations is 100% (all 5 tests were repeated under the same conditions and all were correct). It effectively overcomes the defect of data-driven methods in generally misjudging unknown faults and shows better generalization ability and engineering application value.

[0083] Furthermore, such as Figure 6 As shown, Figure 6 The flowchart below illustrates a combustion device state identification method based on physicochemical consistency diagnosis according to an embodiment of this application. This method includes: acquiring real-time operating data of a carbon-containing fuel combustion device, including fuel input parameters, flue gas output parameters, and solid product parameters, through a data acquisition unit; calculating the real-time violation degree of each constraint equation based on a pre-established set of physicochemical constraint equations, including at least the carbon conservation equation, sulfur conservation equation, stoichiometric equation, and energy conservation equation, through a multi-constraint collaborative violation determination unit; determining the number and direction combination of violated constraints, and marking an anomaly when only one constraint is violated without providing a root cause diagnosis conclusion; matching the corresponding physical root cause from a violation pattern library when two or more constraints are violated simultaneously in a preset specific direction combination, through a violation pattern matching unit; and outputting diagnostic results, including the abnormal root cause, through a diagnostic output unit.

[0084] Therefore, this application directly uses the laws of conservation of physicochemical properties as a diagnostic tool, no longer using conservation equations as auxiliary conditions for neural network training. Instead, it uses the conservation equations themselves for diagnostic judgment, establishing a diagnostic system covering seven general physicochemical constraint equations: conservation of the three main elements (carbon, sulfur, and nitrogen), stoichiometry of oxidation, energy conservation, conservation of solid-phase product mass, and conservation of working fluid mass. The core innovation lies in the multi-constraint collaborative violation judgment method. A deterministic root cause diagnosis is only given when two or more constraints are violated simultaneously in a specific direction combination. When a single constraint is violated, only an anomaly is marked without a diagnostic conclusion. At the same time, the causal direction of the deviation is determined through time-series cross-correlation analysis. All embodiments of this application are based on the universal laws of conservation of physicochemical properties in nature, naturally independent of historical fault data, and are particularly suitable for online condition monitoring, anomaly root cause diagnosis, and auxiliary decision-making scenarios for large power plant boilers and industrial heating boilers in the power industry.

[0085] It should be noted that the above description is merely a preferred embodiment of this application and does not limit the patent scope of this application. Any equivalent modifications made based on the content of this specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

[0086] Furthermore, the embodiments of this application do not rely on machine learning, artificial neural networks, or any form of historical fault data to train the model. Each step of the diagnosis is completed by direct calculation of the physicochemical conservation equations, from the degree of violation. From computation to multi-constraint collaborative violation determination to temporal causal direction analysis, the entire process does not require any intermediate steps such as statistical models or neural networks.

[0087] The combustion device status identification method based on physicochemical consistency diagnosis proposed in this application determines the current physicochemical constraints based on the type of the target combustion device, calculates the current violation degree based on the current physicochemical constraints, identifies target physicochemical constraints whose current violation degree is greater than the corresponding physicochemical constraint threshold, and determines the fault type of the target combustion device when the number of target physicochemical constraints is greater than a first preset number. This solves the problems of untraceable diagnostic conclusions, reliance on historical fault data, and insufficient accuracy of diagnostic results in related technologies, achieving traceable and precise localization from abnormal phenomena to physical root causes.

[0088] Next, referring to the accompanying drawings, a combustion device status identification system based on physicochemical consistency diagnosis is described according to an embodiment of this application.

[0089] Figure 7 This is a block diagram of a combustion device status identification system based on physicochemical consistency diagnosis according to an embodiment of this application.

[0090] like Figure 7As shown, the combustion device status identification system 10 based on physicochemical consistency diagnosis includes: a data acquisition module 100, a calculation module 200, and a determination module 300, wherein, Acquisition module 100 acquires the current operating parameters of the target combustion device; The calculation module 200 determines the current physical and chemical constraints based on the type of the target combustion device, and calculates the current degree of violation of at least one physical and chemical constraint based on the current operating parameters. The determination module 300 determines the target physical and chemical constraints whose current violation degree is greater than the corresponding physical and chemical constraint threshold based on the current violation degree of at least one physical and chemical constraint, and determines the fault type of the target combustion device based on the target physical and chemical constraints when the number of target physical and chemical constraints is greater than a first preset number.

[0091] According to one embodiment of this application, the calculation module 200 is specifically used for: Identify whether the target combustion device is a circulating fluidized bed boiler; If the target combustion device is a circulating fluidized bed boiler, then the current physical and chemical constraints are at least one of the following: carbon conservation constraint, sulfur conservation constraint, nitrogen conservation constraint, stoichiometric ratio constraint, energy conservation constraint, solid product mass conservation constraint, working fluid mass conservation constraint, solid material inventory-bed pressure dynamic constraint, and in-furnace desulfurization-combustion coupling constraint. Otherwise, identify whether the target combustion device is a pulverized coal boiler; If the target combustion device is a pulverized coal boiler, then the current physicochemical constraints are at least one of the following: carbon conservation constraint, sulfur conservation constraint, nitrogen conservation constraint, stoichiometric ratio constraint, energy conservation constraint, solid product mass conservation constraint, working fluid side mass conservation constraint, furnace heat transfer distribution constraint, and burner zone stoichiometric zoning constraint.

[0092] According to one embodiment of this application, the target combustion device is a circulating fluidized bed boiler, and the determining module 300 is specifically used for: Based on the time-series data of the current operating parameters, the first cross-correlation coefficient between the bed pressure difference and the bed temperature is calculated, and the first directional index is calculated based on the first cross-correlation coefficient. The dominant deviation type of the circulating fluidized bed boiler is determined based on the first directional index, and the fault type is determined based on the dominant deviation type of the circulating fluidized bed boiler and the target physicochemical constraints.

[0093] According to one embodiment of this application, the target combustion device is a pulverized coal boiler, and the determining module 300 is specifically used for: Based on the time-series data of the current operating parameters, the second cross-correlation coefficient between the oxygen concentration field in the burner zone and the furnace outlet temperature is calculated, and the second directional index is calculated based on the second cross-correlation coefficient. The dominant deviation type of the pulverized coal boiler is determined based on the second directional index, and the fault type is determined based on the dominant deviation type of the pulverized coal boiler and the target physicochemical constraints.

[0094] According to one embodiment of this application, after determining a target physicochemical constraint whose current violation degree is greater than the corresponding physicochemical constraint threshold based on the current violation degree of at least one physicochemical constraint, the determining module 300 is further configured to: If the number of target physical and chemical constraints is the second preset number, then the target combustion device is determined to be fault-free. If the number of target physical and chemical constraints is greater than the second preset number and less than the first preset number, the target combustion device is marked as an abnormal state.

[0095] According to one embodiment of this application, after determining the fault type of the target combustion device based on the target physicochemical constraints, the determining module 300 is further configured to: Match the corresponding fault handling strategy according to the fault type, and perform fault handling operations on the target combustion device based on the fault handling strategy.

[0096] It should be noted that the foregoing explanation of the combustion device condition identification method based on physicochemical consistency diagnosis also applies to the combustion device condition identification system based on physicochemical consistency diagnosis in this embodiment, and will not be repeated here.

[0097] The combustion device status identification system based on physicochemical consistency diagnosis proposed in this application determines the current physicochemical constraints based on the type of the target combustion device, calculates the current violation degree based on the current physicochemical constraints, identifies target physicochemical constraints whose current violation degree is greater than the corresponding physicochemical constraint threshold, and determines the fault type of the target combustion device when the number of target physicochemical constraints is greater than a first preset number. This solves the problems of untraceable diagnostic conclusions, reliance on historical fault data, and insufficient accuracy of diagnostic results in related technologies, achieving traceable and precise localization from abnormal phenomena to physical root causes.

[0098] Figure 8 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. The electronic device may include: The memory 801, the processor 802, and the computer program stored on the memory 801 and capable of running on the processor 802.

[0099] When the processor 802 executes the program, it implements the combustion device status identification method based on physicochemical consistency diagnosis provided in the above embodiments.

[0100] Furthermore, electronic devices also include: Communication interface 803 is used for communication between memory 801 and processor 802.

[0101] The memory 801 is used to store computer programs that can run on the processor 802.

[0102] The memory 801 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0103] If the memory 801, processor 802, and communication interface 803 are implemented independently, then the communication interface 803, memory 801, and processor 802 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 8 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0104] Optionally, in a specific implementation, if the memory 801, processor 802, and communication interface 803 are integrated on a single chip, then the memory 801, processor 802, and communication interface 803 can communicate with each other through an internal interface.

[0105] The processor 802 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention.

[0106] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described combustion device status identification method based on physicochemical consistency diagnosis.

[0107] This application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps in any of the above embodiments of the combustion device state identification method based on physicochemical consistency diagnosis.

[0108] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0109] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0110] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for identifying the condition of a combustion device based on physicochemical consistency diagnosis, characterized in that, include: Collect the current operating parameters of the target combustion device; Based on the type of the target combustion device, the current physical and chemical constraints are determined, and based on the current physical and chemical constraints, the current degree of violation of at least one physical and chemical constraint is calculated according to the current operating parameters. Based on the current degree of violation of the at least one physical and chemical constraint, a target physical and chemical constraint with a current degree of violation greater than the corresponding physical and chemical constraint threshold is determined, and if the number of the target physical and chemical constraints is greater than a first preset number, the fault type of the target combustion device is determined according to the target physical and chemical constraints.

2. The method according to claim 1, characterized in that, The determination of the current physicochemical constraints based on the type of the target combustion device includes: Identify whether the target combustion device is a circulating fluidized bed boiler; If the target combustion device is a circulating fluidized bed boiler, then the current physicochemical constraints are at least one of the following: carbon conservation constraints, sulfur conservation constraints, nitrogen conservation constraints, stoichiometric constraints, energy conservation constraints, solid product mass conservation constraints, working fluid mass conservation constraints, solid material inventory-bed pressure dynamic constraints, and in-furnace desulfurization-combustion coupling constraints. Otherwise, identify whether the target combustion device is a pulverized coal boiler; If the target combustion device is a pulverized coal boiler, then the current physicochemical constraints are at least one of the following: carbon conservation constraint, sulfur conservation constraint, nitrogen conservation constraint, stoichiometric ratio constraint, energy conservation constraint, solid product mass conservation constraint, working fluid side mass conservation constraint, furnace heat transfer distribution constraint, and burner zone stoichiometric zoning constraint.

3. The method according to claim 1 or 2, characterized in that, The target combustion device is a circulating fluidized bed boiler. Determining the fault type of the target combustion device based on the target physicochemical constraints includes: Based on the time-series data of the current operating parameters, calculate the first cross-correlation coefficient between bed pressure difference and bed temperature, and calculate the first directional index based on the first cross-correlation coefficient; The deviation-dominant type of the circulating fluidized bed boiler is determined based on the first directional index, and the fault type is determined based on the deviation-dominant type of the circulating fluidized bed boiler and the target physicochemical constraints.

4. The method according to claim 1 or 2, characterized in that, The target combustion device is a pulverized coal boiler. Determining the fault type of the target combustion device based on the target physicochemical constraints includes: Based on the time-series data of the current operating parameters, the second cross-correlation coefficient between the oxygen concentration field in the burner zone and the furnace outlet temperature is calculated, and the second directional index is calculated based on the second cross-correlation coefficient. The deviation-dominant type of the pulverized coal boiler is determined based on the second directional index, and the fault type is determined based on the deviation-dominant type of the pulverized coal boiler and the target physicochemical constraints.

5. The method according to claim 1, characterized in that, After determining the target physical and chemical constraint whose current violation degree is greater than the corresponding physical and chemical constraint threshold based on the current violation degree of the at least one physical and chemical constraint, the method further includes: If the number of the target physical and chemical constraints is a second preset number, then the target combustion device is determined to be fault-free. If the number of target physical and chemical constraints is greater than the second preset number and the number of target physical and chemical constraints is less than the first preset number, then the target combustion device is marked as an abnormal state.

6. The method according to claim 1, characterized in that, After determining the fault type of the target combustion device based on the target physicochemical constraints, the method further includes: Match the corresponding fault handling strategy according to the fault type, and perform fault handling operations on the target combustion device based on the fault handling strategy.

7. A combustion device status identification system based on physicochemical consistency diagnosis, characterized in that, include: The acquisition module collects the current operating parameters of the target combustion device; The calculation module determines the current physical and chemical constraints based on the type of the target combustion device, and calculates the current degree of violation of at least one physical and chemical constraint based on the current operating parameters. The determination module determines the target physical and chemical constraints whose current violation degree is greater than the corresponding physical and chemical constraint threshold based on the current violation degree of the at least one physical and chemical constraint, and determines the fault type of the target combustion device according to the target physical and chemical constraints when the number of the target physical and chemical constraints is greater than a first preset number.

8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the combustion device status identification method based on physicochemical consistency diagnosis as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the combustion device status identification method based on physicochemical consistency diagnosis as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the combustion device status identification method based on physicochemical consistency diagnosis as described in any one of claims 1-6.

Images