908results about "Combustion regulation" patented technology

The invention relates to the technical field of boiler combustion control, in particular to a boiler combustion multi-target collaborative optimization control method and system. The method comprises the following steps: firstly, acquiring coal quality parameters in real time through a laser-induced breakdown spectrum analyzer, carrying out qualitative and quantitative analysis on spectral data by utilizing a machine learning algorithm, constructing a boiler combustion digital twinborn model fusing a combustion mechanism model and a data driving model, and predicting combustion characteristics, NOx generation trends and coking risks under different blending schemes; and then, dynamically generating an optimization instruction combination according to a prediction result of the digital twinborn model, establishing a safety interlocking mechanism while executing the optimization instruction, and automatically switching to a manual control mode when detecting that the working condition fluctuates severely or the model prediction deviation exceeds a preset threshold value. According to the method, the problems of coal quality information lag and untimely combustion adjustment caused by traditional manual sampling are effectively solved, and the economical efficiency, the safety and the environmental protection property of boiler operation are improved.

The invention discloses a machine learning multi-objective optimization control method based on coal quality characteristics and combustion state feedback, and belongs to the technical field of industrial process automatic control. According to the method, collaborative optimization control over the combustion efficiency, NOx emission and combustion stability is achieved under the multi-working-condition operation condition of the combustor. According to the method, coal quality characteristic parameters and combustion state data are collected, working condition clustering is carried out after data fusion, and a historical combustion operation data set coupling coal quality characteristics and combustion states is constructed; a combustion state evaluation model and a combustion control model are established by adopting machine learning, on the basis of identifying working conditions in real time and evaluating combustion performance, a control parameter adjustment amount is generated in combination with trend extrapolation and a multi-objective cost function, and a combustion state feedback rolling correction model and a control strategy are utilized to realize combustion control. The self-adaptive closed-loop collaborative optimization control of the combustion process under multiple coal types and multiple working conditions is realized, the boiler efficiency is improved, the NOx emission is reduced, and the operation robustness is enhanced.

The invention provides a combustion optimization method and system for a coal-fired boiler, electronic equipment and a storage medium. The combustion optimization method for the coal-fired boiler comprises the steps that historical operation data and operation condition data of the boiler are obtained; determining the combustion efficiency of the boiler according to the historical operation data of the boiler; working condition division is carried out according to the boiler combustion efficiency and the operation working condition data, and information of all working condition intervals is obtained; constructing a combustion efficiency prediction model driven by time series data according to the information of each working condition interval; the combustion efficiency prediction model is embedded into a deep reinforcement learning method framework for training, and an optimization model is generated; and inputting real-time operation data of the boiler into the optimization model to generate optimization decision data.

The invention relates to the technical field of industrial intelligent control, in particular to a combustion system fault correlation analysis and diagnosis method and system based on a knowledge graph. The method comprises the following steps: constructing a mechanism topological graph of a combustion system, obtaining real-time load data of the combustion system, calculating dynamic conduction lag time of a parent node influencing a child node in the mechanism topological graph based on a fluid mechanics load correction mechanism in combination with a flow resistance correction factor and reference transmission time, performing time sequence alignment based on dynamic conduction delay time, calculating causal association strength of a father node pointing to a child node and performing confidence attenuation processing, performing reverse search on a mechanism topological graph when an abnormal trigger point is monitored, calculating accumulated abnormal energy of each father node based on the causal association strength, and determining the abnormal trigger point according to the accumulated abnormal energy. And determining the father node with the highest accumulated abnormal energy as a fault root cause. According to the scheme of the invention, accurate time sequence alignment under working condition fluctuation can be realized, diagnosis failure can be prevented, and fault root causes can be accurately positioned.

The invention relates to the technical field of boiler combustion optimization, in particular to a group combustion optimization method under flexible peak regulation of a coal-fired boiler, which comprises the following steps of: acquiring characteristic historical operation data of the coal-fired boiler, dividing operation conditions, calculating key operation parameters of the coal-fired boiler under different working conditions, and constructing a coal-fired boiler combustion model; coal loading information and load information of a future operation plan of the coal-fired boiler are read, and a planned operation condition group of the coal-fired boiler is constructed in combination with key operation variable action time; key operation parameter analysis is carried out on the planned operation condition group of the coal-fired boiler, group optimization is carried out based on a combustion model, a key operation variable adjustment scheme is given, and operation of the coal-fired boiler is guided. According to the method, the operation condition of the coal-fired boiler under the flexible peak regulation can be analyzed and judged, group combustion optimization of the coal-fired boiler is comprehensively guided in combination with the key operation variable action time, and the high efficiency and the environmental protection property of the coal-fired boiler under the flexible peak regulation can be greatly improved.

The invention discloses an intelligent optimization operation method for a biomass gas coupling coal-fired boiler, and belongs to the technical field of boiler operation control. Historical operation parameters of a gasification furnace and the coal-fired boiler are collected, a multi-dimensional coordinate system is constructed, historical operation data are mapped into coordinate points, a high-efficiency area boundary, a stable area boundary and a risk area boundary are divided, and a dynamic operation map is formed; meanwhile, the historical operation data are cut into track fragments, and the state evolution process and operation instructions of the coal-fired boiler are recorded; the method comprises the following steps: acquiring gasifier temperature, gas components and boiler temperature data in real time, determining the position of a current state in a dynamic operation map, and predicting a future evolution path of the coal-fired boiler by fitting a motion track and matching a plurality of historical tracks; and when the evolution path reaches the boundary of the risk area, triggering early warning, screening a historical successful track by taking an efficient area as a target, extracting related operation instructions to form a candidate intervention strategy set, selecting the operation instructions according to real-time working conditions, converting the operation instructions into specific adjustment instructions, and sending the specific adjustment instructions to corresponding control equipment.

The invention discloses a self-adaptive optimization control system and method for the combustion process of a biomass generator set. The self-adaptive optimization control system comprises a multi-dimensional sensing array module, an edge calculation module, a self-adaptive decision server, an execution mechanism cluster and a closed-loop verification terminal. The multi-dimensional sensing array module comprises a temperature field monitoring unit, a flue gas component analysis unit and a fuel characteristic detection unit; a data fusion processor is arranged in the edge calculation module; the self-adaptive decision-making server carries a dual-module decision-making engine; the executing mechanism cluster comprises a frequency conversion fan, a precise feeding machine and an adjustable fire grate. Through multi-source sensing data fusion and a self-adaptive decision-making mechanism, real-time response to biomass component fluctuation and load change is achieved, and the combustion efficiency is improved; a deep learning prediction model is combined, the air-coal ratio and the hearth temperature set value are adjusted in advance, and CO emission is reduced; the manual intervention frequency is reduced through an optimization mechanism, and the equipment maintenance period is prolonged.

The invention discloses an ammonia-doped combustion optimization method and device for a coal-fired power plant, a medium and equipment. According to the method, by obtaining the coal type parameter, the air volume parameter and the initial ammonia mixing proportion of the target coal-fired power plant and combining the preset ammonia-doped combustion simulation model, the emission of the nitric oxide at the hearth outlet is accurately predicted. The model is constructed based on a hearth subarea reactor network, covers a preheating area, a main combustion area and a burnout area, and can accurately simulate the combustion process of each area and the generation of nitrogen oxides through nitrogen conversion path training under a deep air classification working condition. And according to the predicted value, the air volume parameter and the ammonia mixing proportion are dynamically adjusted, the combustion process is optimized, nitrogen oxide emission is effectively reduced, the combustion efficiency is improved, the coal-fired power plant is assisted to achieve low-carbon and environment-friendly operation, and the problem that the ammonia-doped combustion process cannot be accurately and efficiently optimized in the prior art is effectively solved.

The invention provides a deep peak regulation method for a coal-fired unit, relates to the technical field of thermal power generation, and can solve the problem of low-load flame shift, stabilize the combustion core and inhibit the fluctuation of NOx emission concentration by dynamically regulating and controlling a combustion field in a boiler. The energy storage system and the boiler are configured for cooperative operation, the energy storage system is used for rapidly transferring / releasing heat energy, the limitation of the heat storage rate of the boiler is broken through, the two-way peak regulation capacity and the regulation speed of the coal-fired unit in the load reducing stage and the load increasing stage can be remarkably improved, and therefore the boiler efficiency is improved under the low load, and the station service power consumption rate is reduced. By constructing an intelligent control system in communication connection with the DCS, automatic control can be realized.

A gas and steam power generation afterburning type heat-electricity decoupling system and a working mechanism thereof, characterized in that the system comprises a gas turbine power generation system, a power transmission and transformation system, a molten salt heat storage system and a steam power generation system; the gas turbine power generation system is connected with the molten salt heat storage system through a flue gas pipeline; the molten salt heat storage system is connected with the power transmission and transformation system through a cable; the gas turbine power generation system is connected with the power transmission and transformation system through a cable; the molten salt heat storage system is connected with the steam power generation system through a main steam pipeline and a backwater pipeline; and the steam power generation system is connected with the power transmission and transformation system through a cable. The system can realize complete heat-electricity decoupling in a green energy storage system, realize the functions of self-supply of external power, storage of green electricity or heat supply, increase the accommodation capacity of a power grid to green electricity, and enhance the stability, flexibility and safety of a new power system.

The application discloses a supplemental combustion type flue gas molten salt heat exchanger and a working mechanism thereof, characterized in that: a supplemental combustion device is added in the upstream of a flue gas molten salt heat exchanger, the supplemental combustion device is connected with the flue gas molten salt heat exchanger through a flue, and a supplemental combustion type flue gas molten salt heat exchange integrated device is formed; the device comprises a supplemental combustion device or a supplemental combustion device, and a first-stage flue gas molten salt heat exchange component. The application can realize the functions of more uniform and efficient supplemental combustion heat transfer in the flue gas, realize a safer ignition mode of the supplemental combustion gas or the mixed body of the atomized supplemental combustion gas and liquid (or gas powder) outside the flue, realize the function of more convenient monitoring of the supplemental combustion, realize the complete decoupling of heat and electricity in the combustion engine power generation heat supply energy storage system, and realize the functions of self-supply of external power, heat storage or heat supply of the system.

The invention discloses an energy-saving dual-fuel heat accumulating type burner usage monitoring control method and system, and relates to the technical field of control and regulation, the energy-saving dual-fuel heat accumulating type burner usage monitoring control system comprises an MEMS multi-parameter sensing array, a tail gas sensor array and a distributed optical fiber temperature sensing module which are deployed in parallel; millisecond-level fuel flow and air flow adjustment is achieved through inner ring flame tensor feedback control, and second-level fuel ratio adjustment is achieved through inner ring tail gas component closed-loop self-adaptive adjustment; and the heat storage regeneration cycle, ash removal triggering and low-speed fuel and air scheduling are achieved through outer ring model predictive control scheduling. The invention provides a multi-layer closed-loop self-adaptive monitoring control method based on flame tensor, tail gas components and a temperature field, and model prediction control is introduced to carry out overall scheduling on a heat storage-combustion coupling process, so that dynamic self-adaption of a fuel ratio, online prediction of heat storage body scaling and multi-time scale coupling optimization are realized.

The invention relates to the technical field of kiln combustion control, and discloses a dynamic tar blending combustion proportion optimization control method and system. Comprising the following steps: collecting kiln system data to obtain a standardized working condition data set; inputting the multi-layer perceptron model to obtain a combustion stability score; when the score is lower than a stable threshold value, triggering risk assessment: extracting kiln load micro fluctuation characteristics from the data set, classifying shutdown risk levels by using a support vector machine algorithm model, and determining a high-risk early warning signal; based on the signal correlation current working condition, a historical optimal blending combustion proportion in a corresponding historical adjustment record is called, a deviation value is calculated in combination with the current blending combustion proportion, and a preliminary proportion adjustment suggestion value is obtained; and iterative correction is started, real-time fuel characteristic change and a combustion state prediction result are fused for step-by-step adjustment, a correction proportion is input into a multi-layer sensor to calculate a stability score, and an optimization control scheme is output after the stability score reaches the standard. According to the method, the tar blending combustion proportion is dynamically optimized, the combustion stability of the kiln is effectively improved, and the shutdown risk is reduced.

The invention relates to a circuit arrangement (12) for which an input voltage U is provided. E to a predetermined output voltage U A to increase. The circuit arrangement (12) comprises an electric charge pump, configured to alternately charge a first capacitor (16) with the input voltage U in a first operating step by means of a switching device (21) at a frequency f. E to charge and in a second step connect the first capacitor (16) to the input voltage U Eto connect in series. A microcontroller (20) is configured to control the switching device (21) and, within the first operating step, to set a capacitor charging time independent of the duration of the first operating step, wherein the capacitor charging time specifies a duty cycle T as the ratio of the capacitor charging time to one period of the frequency f, and the microcontroller (20) is configured to control the output voltage U A by varying the duty cycle T.

The invention discloses a power plant boiler waste heat recovery system, and relates to the technical field of boiler waste heat detection. The recovery system comprises a flue gas parameter acquisition and pretreatment module, a waste heat potential evaluation and classification module, a heating power matching and heat exchange path planning module and a dynamic operation optimization and feedback control module which are operated in sequence, wherein the flue gas parameter acquisition and preprocessing module is used for acquiring flue gas related parameters corresponding to a target electric field boiler and performing data preprocessing action; according to the technical key points, a multi-objective optimization model is established, heat recovery is weighted to the maximum degree under the condition that the minimum temperature difference and matching constraints are met, and high-grade waste heat is preferentially supplied to high-value users; meanwhile, the model dynamically generates an optimal heat distribution scheme, and energy depreciation and resource mismatching are avoided, so that the problems of energy level mismatching and low efficiency caused by a traditional fixed connection mode are solved, cascade and economization of waste heat utilization are realized, and the intelligent decision-making capability of system resource allocation is embodied.

A method for differentiating gas sources based on temperature includes transmitting an optical beam through a plume emitted by a combustion system. The method includes detecting the optical beam, after propagating through the plume, to obtain an absorption spectrum. The method includes determining, based on the absorption spectrum, a first path-integrated concentration of a gas species, a first temperature of the first path-integrated concentration, a second path-integrated concentration of the gas species, and a second temperature of the second path-integrated concentration. The second temperature is different from the first temperature. The method may further include performing an inversion to obtain a sampled quantity of the gas species within the plume. The method may be implemented with dual-comb spectroscopy, in which case the optical beam is formed from two frequency combs having slightly different repetition rates.

Aiming at the problems of large flue gas nitrogen oxide generation amount, easy exceeding and serious pollution possibly existing in ammonia gas blending combustion, the invention provides an ammonia gas out-of-furnace bypass combustion blending combustion oxidation method, which comprises the following steps: preparing NO2 by virtue of an ammonia combustion system, generating O.free radicals by virtue of photo-thermal cracking of NO2, oxidizing NO in flue gas into NO2, cracking NO2 into N2, removing NO by virtue of NO2, and performing denitration by virtue of denitration, so that the nitrogen oxide in the flue gas is not easily generated. According to the method, SO2 is oxidized into SO3 through O.free radicals, the SO3 reacts with calcium for desulfurization, CO and VOCs are oxidized into CO2 and H2O, collaborative purification of multiple pollutants is achieved, reduction denitration and wet desulfurization are replaced and used for denitration and desulfurization of combustion flue gas and collaborative treatment of the multiple pollutants, and deep pollution reduction, carbon reduction, energy conservation and efficiency improvement are achieved.

The invention relates to an intelligent combustion monitoring and rapid intervention control method and system for deep peak regulation of a coal-fired boiler. The method comprises the following steps: reconstructing a two-dimensional temperature field of a hearth through regularization optimization modeling by utilizing hearth infrared measuring point data; constructing a coal quality dynamic identification model to realize dynamic monitoring and trend prediction of coal quality fluctuation; a combustion state nonlinear probability fusion model is constructed, on the basis of a probability graph model, information such as flame detection signals, hearth negative pressure, flame images, oxygen amount, steam drum water level, coke falling and coal interruption is fused, joint probability distribution is constructed, time sequence incremental learning is conducted in combination with an XGBoost model, and dynamic recognition and early warning of the combustion state are achieved. Key parameters such as a flame image, temperature field distribution and negative pressure fluctuation are collected in real time by means of a hearth multi-dimensional combustion state recognition model, a decision module is triggered when a combustion state score reaches an early warning threshold value, a quick oil gun is triggered to be put into use, and early warning in advance is changed into quick intervention.

A parameter-setting program operates on an information terminal 50 that may perform wireless communication with a combustion device 10. The parameter-setting program may cause the information terminal 50 to execute: processing to cause, when a parameter is to be set for one combustion device 10, the information terminal 50 or an external storage device to store the parameter inputted into the information terminal 50; processing to cause, when, after the storing, the parameter is to be set for another combustion device, the information terminal 50 to display an option to instruct the information terminal 50 to write the stored parameter into the other combustion device 10; and processing to write the stored parameter into the other combustion device 10 when the option is selected.

The invention discloses a thermal power generating unit boiler wall temperature early warning method and device, and the method comprises the steps: determining a steady-state working condition according to boiler operation parameters; the boiler operation parameters comprise coal feeding quantity, water feeding quantity, primary air quantity and secondary air quantity; calculating the wall temperature change rate of each monitoring point in a preset time window; the time window is set according to a data smooth filtering requirement and an early warning response timeliness requirement, and the monitoring points comprise a superheater, a reheater and a water cooling wall; and if the wall temperature change rate of at least one monitoring point is greater than or equal to a preset early warning threshold value and the duration is greater than or equal to a corresponding time threshold value, executing a corresponding early warning strategy. Whether the boiler is in the steady-state operation state or not is recognized before early warning is triggered, so that wall temperature fluctuation interference in the normal dynamic process such as unit load adjustment and combustion working condition fine adjustment is eliminated, it is avoided that the normal working condition is misjudged to be abnormal, the early warning timeliness of the wall temperature of the boiler is improved, meanwhile, the misjudgment rate is reduced, and the early warning accuracy is improved.

The utility model provides a primary air powder concentration measuring device and a heat supply system, and belongs to the technical field of concentration measurement, and the device comprises an electrostatic loading system which is used for carrying out charge loading treatment on electrostatic ions on the surfaces of all pulverized coal particles when a power plant is in a low load state, so that all the electrostatic ions reach a saturated state; each electric charge quantity measuring sensor is used for measuring the total electric charge quantity of the static ions reaching the saturation state; each signal detection sensor is used for detecting charges generated when the static ions reaching the saturation state flow through and generating electric signals; and the controller is used for calculating the pulverized coal mass flow according to the electric signal generated by the signal detection sensor, and calculating the primary pulverized coal concentration in the pulverized coal pipeline according to the total charge quantity of the electrostatic ions and the pulverized coal mass flow. According to the scheme, the primary air powder concentration can be accurately measured under the condition of low load of the power plant.

The invention discloses a coal-fired boiler combustion optimization method, system and equipment based on machine learning and a medium, and belongs to the technical field of boiler operation optimizing.The method comprises the steps that operation parameter data and generated fly ash carbon content data are collected; constructing a machine learning model, and performing primary training on the machine learning model; the number of operation parameter data is reduced, secondary training is performed on the machine learning model, and the optimal parameter number is determined according to the fitting effect; screening the operation parameter data, and reserving the operation parameter data of which the quantity accords with the optimal parameter quantity; the method comprises the following steps: constructing a fly ash carbon content prediction model, optimizing an extreme value of the fly ash carbon content prediction model through an optimization algorithm, and determining an optimal boiler combustion operation parameter, and solves the problems that the actual measurement workload is large and the lowest fly ash carbon content cannot be obtained by only depending on a thermal-state multi-working-condition test and easily deviating from the optimal working condition; the existing prediction method has the problems that a local optimal solution is easy to generate and the generalization ability of a model is low.

The invention provides a combustion control system for an industrial kiln. The combustion control system comprises a data acquisition and preprocessing module; the BP neural network module is used for operating three parallel BP neural network models which are respectively used for flame temperature control, flame length control and pollutant emission control, and each BP neural network model is provided with an input layer, a hidden layer and an output layer; the PID parameter adjusting module is used for dynamically adjusting the proportionality coefficient Kp, the integral coefficient Ki and the differential coefficient Kd of the PID controller module according to the output of the BP neural network module; the PID controller module is used for calculating a control quantity according to the parameters provided by the PID parameter adjusting module and outputting a control signal; and the execution mechanism module is used for receiving the control signal of the PID controller module and adjusting the mixing proportion and the flow of the first fuel and the second fuel. According to the invention, the PID control loop is optimized through the three parallel BP neural networks, and cooperative control based on flame temperature, flame length and pollutant discharge is realized.

The present application relates to a kind of belt roaster pellet sintering fine control method, belong to belt roaster technical field.The process parameters in prior art rely on experience setting, dynamic interference compensation lag and the problem of insufficient control precision of multivariable coupling, by process mechanism model, determine the controlled variable parameter range of drum dry section, dry section, preheating section, roasting section, soaking section and cooling section, utilize transfer function matrix to establish the dynamic correlation of controlled variable and fan frequency, air valve opening degree, in combination with production data, real-time correction operation variable set value, and based on feedforward compensation model, predict the influence of green ball conveyor speed, material layer thickness and moisture content on process parameters.The method is used to improve the control precision of pellet sintering process, reduce energy consumption and process fluctuation.

The invention relates to the technical field of boiler combustion control, in particular to a through-flow boiler ultra-low nitrogen combustion control system based on multistage flue gas recirculation. Comprising a flue gas grading circulation unit; the low-nitrogen combustion regulation and control unit is used for realizing staged mixed combustion of fuel and circulating flue gas, and a staged combustion structure is matched with an air-fuel ratio dynamic regulation technology; the working condition parameter sensing unit is used for acquiring boiler combustion and flue gas state parameters in real time, integrating a multi-source sensor module and constructing a multi-dimensional operation parameter set; and the intelligent cooperative control unit is used for coordinating dynamic control of the ultra-low nitrogen combustion process. High-temperature and low-temperature independent flue gas circulation branches are arranged through the flue gas staged circulation unit, and a staged combustion structure of a main combustion section and a re-combustion section of the low-nitrogen combustion regulation and control unit is combined, so that the problem of non-uniform distribution of a hearth temperature field caused by compact combustion space and dramatic change of a flow field of the through-flow boiler can be solved; therefore, the generation of thermal nitrogen oxides is inhibited.

The invention provides a low-emission and wide-load coal-fired boiler system based on wall-type wind and ammonia-doped combustion, and the system comprises a combustion environment sensing module which is used for deploying a sensing equipment network and obtaining basic combustion characteristic parameters; the combustion state recognition module is used for carrying out flame stability index extraction, combustion trend prediction and fuzzy reasoning to obtain real-time working condition characteristics; the wall type wind configuration module is used for designing a wall type wind jet flow CFD simulation model and obtaining wall type wind optimal configuration parameters; the differential ammonia doping module is used for constructing an ammonia combustion chemical kinetic model and a three-dimensional mapping query table to obtain a differential graded ammonia doping scheme; the collaborative optimization module is used for comprehensively optimizing the wall type wind optimal configuration parameter differentiation grading ammonia doping scheme; and the performance evaluation module is used for comprehensive performance evaluation and equipment prediction maintenance. According to the invention, environmental data in the boiler can be sensed comprehensively, ultralow emission of pollutants such as NOX and the like is realized, the boiler is kept stable and reaches the standard under large-load fluctuation, and the safety, economic and environment-friendly values of boiler operation are improved.

Systems and methods include a computer-implemented method for monitoring emissions in real time. Flaring emissions are determined in real time for a flare stack based on: 1) a flaring volume in conjunction with heat and material balances of systems that discharge to a flare system, and 2) a composition of each relief source that discharges to the flare system. A molar balance around the flare stack is performed in real time using the flaring emissions to determine the emissions.

The embodiment of the invention provides a low-emission and high-efficiency boiler combustion control and management system, relates to the technical field of low-emission and high-efficiency boiler combustion control and management systems, and aims to solve the problems that the combustion efficiency is reduced and the emission of nitrogen oxides is increased due to poor air-coal matching synergism. The system comprises a sensor array, a data acquisition and preprocessing module, a multivariable coupling analysis engine, a combustion state collaborative decision center and an actuator driving array, and an optimal air-coal ratio set point is generated in real time through deep neural network modeling and a multi-target dynamic optimization algorithm. And the actuating mechanism is driven to cooperatively adjust air supply, fuel and flue gas recirculation, so that cooperative control of high efficiency and low emission is realized.

A fuel control system for a turbine engine includes a mixer for mixing first and second fuels to obtain a fuel blend, a fuel blend analyzer, a combustor operable with the fuel blend, and a knock sensor coupled to the combustor. The system also includes a controller configured to: receive a measurement indicative of a composition of the fuel blend; compare the fuel blend measurement to an operational model of the combustor; determine, based on the comparison, a predicted combustion condition in the combustor associated with the fuel blend measurement; control, based on the predicted combustion condition, flow of the first fuel or the second fuel; receive a combustion signal indicative of combustion behavior in the combustor; compare the predicted combustion condition to the combustion signal; and update the operational model if the predicted combustion condition does not match the indicated combustion behavior.

The invention relates to the technical field of thermal energy engineering and industrial artificial intelligence crossing, in particular to a boiler combustion multi-target cooperative control method based on PINN and reinforcement learning, which comprises the following steps: collecting boiler combustion related data through a multi-source sensor network, and fusing edge data; based on physical information neural network modeling training, predicting a key physical field in the boiler; constructing and training a reinforcement learning model based on PINN state embedding; and a multi-target cost function is constructed based on the reinforcement learning model, the multi-target cost function is continuously evaluated through the reinforcement learning model, the weight is automatically adjusted, and multi-target cooperative control over boiler combustion is achieved. The method is obviously superior to a traditional scheme in the aspects of physical consistency, adaptive capacity, real-time performance and multi-target cooperation, and a reproducible theory-engineering integrated new normal form is provided for efficient, clean and flexible operation of a coal-fired power plant boiler combustion system under the double-carbon background.