Boiler multi-source fuel blending method and system

Abstract

The invention discloses a boiler multi-source fuel blending method which is used for solving the problems that due to the fact that an existing fuel quality detection scheme is low in detection time efficiency, blending adjustment of multi-source fuel cannot be conducted in real time, the combustion efficiency of a boiler is reduced, pollutant emission exceeds the standard, and even a hearth is coked or extinguished due to heat value unbalance. The method comprises the following steps: acquiring element composition of the multi-source fuel through LIBS, and determining calorific value data corresponding to the multi-source fuel according to the element composition; according to the obtained element composition, position information and weight data of the multi-source fuel, constructing full-flow dynamic flow track data; determining an optimal flow set value of each coal feeding mechanism based on a multi-objective optimization algorithm according to the dynamic flow track data and the heat value data; and according to the optimal flow set value, a blending control strategy corresponding to each coal feeding mechanism is generated, and the blending control strategy is issued to each coal feeding mechanism, so that each coal feeding mechanism adjusts the rotating speed and the baffle opening degree according to the blending control strategy.

Description

Technical Field

[0001] This application relates to the field of thermal power generator technology, and in particular to a method and system for blending multi-source fuels in a boiler. Background Technology

[0002] Biomass circulating fluidized bed (CFB) boiler combustion technology has gradually attracted attention from various countries due to its unique advantages in three aspects: alternative fuels, treatment of various wastes, and environmental protection, which are unmatched by other combustion technologies.

[0003] For fuel-fired boilers, the quality of the fuel fed into the furnace has a significant impact on combustion economy and safety. Current fuel quality testing methods mainly rely on offline sampling and laboratory analysis (such as industrial analysis and elemental analysis), with results lagging by 4-6 hours. However, CFB boilers feed fuel that is dynamically blended from multiple sources, including coal gangue and coal slime, resulting in frequent fluctuations in fuel characteristics. Operators cannot obtain key parameters such as fuel calorific value, sulfur content, and ash content in real time, leading to significant delays in blending adjustments. Sudden changes in fuel characteristics can easily cause a decrease in boiler efficiency, excessive pollutant emissions (such as a sudden surge in SO2 concentration), and even furnace coking or fire suppression accidents due to calorific value imbalances. Summary of the Invention

[0004] This application provides a method for blending multiple fuels in a boiler to solve the problem that existing fuel quality testing schemes have low detection timeliness, which makes it impossible to obtain parameters of multiple fuels in a timely manner, and thus impossible to adjust the blending of multiple fuels in real time. This leads to a decrease in boiler combustion efficiency, excessive pollutant emissions (such as a sudden increase in SO2 concentration), and even furnace coking or flameout due to calorific value imbalance.

[0005] This application also provides a boiler multi-source fuel blending system to solve the problem that the existing fuel quality detection scheme has low detection timeliness, which makes it impossible to obtain multi-source fuel parameters in a timely manner, and thus impossible to make real-time multi-source fuel blending adjustments, resulting in reduced boiler combustion efficiency, excessive pollutant emissions (such as a sudden increase in SO2 concentration), and even furnace coking or flameout due to calorific value imbalance.

[0006] The embodiments of this application adopt the following technical solutions: A method for blending multiple fuels in a boiler includes: acquiring the elemental composition of multiple fuels using a laser-induced breakdown spectrometer (LIBS); determining the calorific value data corresponding to the multiple fuels based on the elemental composition; constructing dynamic flow trajectory data of the multiple fuels from the storage facility to the boiler based on the acquired elemental composition, location information, and weight data; determining the optimal flow rate setpoint for each coal feeding mechanism based on the dynamic flow trajectory data and the calorific value data using a multi-objective optimization algorithm; generating a blending control strategy corresponding to each coal feeding mechanism based on the optimal flow rate setpoint; and distributing the blending control strategy to each coal feeding mechanism so that each coal feeding mechanism adjusts its rotation speed and damper opening according to the blending control strategy to achieve blending of multiple fuels.

[0007] A boiler multi-source fuel blending system includes: an elemental composition detection unit, used to acquire the elemental composition of multi-source fuels using a laser-induced breakdown spectrometer (LIBS), and determine the calorific value data corresponding to the multi-source fuels based on the elemental composition; a flow trajectory data generation unit, used to construct dynamic flow trajectory data of the multi-source fuels from the storage room to the boiler based on the acquired elemental composition, location information, and weight data; a flow rate calculation unit, used to determine the optimal flow rate setpoint for each coal feeding mechanism based on the dynamic flow trajectory data and the calorific value data using a multi-objective optimization algorithm; and a blending strategy generation unit, used to generate a blending control strategy corresponding to each coal feeding mechanism based on the optimal flow rate setpoint, and distribute the blending control strategy to each coal feeding mechanism so that each coal feeding mechanism adjusts its rotation speed and damper opening according to the blending control strategy to achieve multi-source fuel blending.

[0008] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: The boiler multi-source fuel blending method provided in this application has two advantages. First, the boiler multi-source fuel blending system can obtain the elemental composition of multi-source fuels through laser-induced breakdown spectroscopy (LIBS), achieving elemental composition analysis at the second level (≥5 times / second). This reduces the acquisition delay of fuel quality data from 4-6 hours in traditional laboratory analysis to the second level. Furthermore, the system can instantly capture fluctuations in fuel characteristics (such as a sudden decrease in the calorific value or an increase in sulfur content in a batch of coal gangue), providing the possibility for real-time adjustment of the blending ratio and completely avoiding boiler efficiency decline and emission exceedances caused by information lag. Second, the boiler multi-source fuel blending system can construct a system based on the obtained elemental composition, location information, and weight data of the multi-source fuels. The dynamic flow trajectory data of the multi-source fuel from the warehouse to the boiler is used to determine the optimal flow rate setpoint for each coal feeding mechanism based on the dynamic flow trajectory data and the calorific value data, using a multi-objective optimization algorithm. Based on the optimal flow rate setpoint, a blending control strategy is generated for each coal feeding mechanism, and the blending control strategy is distributed to each coal feeding mechanism. This allows each coal feeding mechanism to adjust its rotation speed and damper opening according to the blending control strategy, achieving multi-source fuel blending. Based on the multi-objective optimization algorithm and real-time dynamic flow trajectory data, the calculated blending command simultaneously satisfies calorific value stability, sulfur content constraints, and optimal economic efficiency, achieving multi-objective collaborative optimization. This reduces the calorific value control deviation of the fuel entering the boiler from ±1200 kJ / kg in the traditional method to within ±400 kJ / kg, improving control accuracy by more than 66%, reducing sulfur content fluctuation by 40%, stabilizing the inlet concentration of the desulfurization system, alleviating environmental pressure from the source, and fundamentally solving the monitoring lag and crude control problems existing in boiler fuel blending control schemes in related technologies. Attached Figure Description

[0009] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A schematic diagram of a boiler multi-source fuel blending method provided in this application embodiment; Figure 2 This is a schematic diagram of the specific structure of a boiler multi-source fuel blending system provided in an embodiment of this application. Detailed Implementation

[0010] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0011] This application provides a method for blending multiple fuels in a boiler to solve the problem that existing fuel quality testing schemes have low detection timeliness, which makes it impossible to obtain parameters of multiple fuels in a timely manner, and thus impossible to adjust the blending of multiple fuels in real time. This leads to a decrease in boiler combustion efficiency, excessive pollutant emissions (such as a sudden increase in SO2 concentration), and even furnace coking or flameout due to calorific value imbalance.

[0012] The implementing entity of the boiler multi-source fuel blending method provided in this application embodiment may be, but is not limited to, at least one of a thermal power generation system, a fuel blending system, or a boiler operation system.

[0013] For ease of description, the following description uses a fuel blending system as the implementing entity of this method. It should be understood that using a fuel blending system as the implementing entity is merely an illustrative example and should not be construed as a limitation of the method.

[0014] The schematic diagram illustrating the specific implementation process of the boiler multi-source fuel blending method provided in this application is shown below. Figure 1 As shown, the main steps include the following: Step 11: Obtain the elemental composition of the multi-source fuel using a laser-induced breakdown spectroscopy (LIBS) instrument, and determine the corresponding calorific value data of the multi-source fuel based on the elemental composition. It should be noted that, in order to ensure that dynamic flow data of multi-source fuels from the warehouse to the boiler can be obtained in the future, this embodiment of the application also requires the fuel to be coded upon arrival and initial data to be entered.

[0015] Specifically, in this embodiment, when a vehicle carrying multi-source fuels of different qualities, such as coal, coal gangue, and coal slime, enters the site, the system automatically assigns it a unique RFID electronic tag. Staff use a terminal to bind information such as the fuel's supplier, mining location, purchase price, and preliminary laboratory analysis data to this RFID tag and upload it to the fuel blending system's backend data center. Subsequently, the RFID tag can serve as the fuel's "identity card," acting as a data carrier for tracking and differentiation in all subsequent stages.

[0016] During the process of unloading fuel into the coal storage yard or warehouse, the system automatically mixes pre-allocated, high-temperature resistant RFID tags (encapsulated in ceramic or metal shells) corresponding to the batch of fuel into the fuel flow. In this embodiment, a tag can be placed every certain tonnage (e.g., 50 tons) to represent a "fuel batch", thereby associating the virtual RFID code with the physical fuel itself, realizing the mapping between the information world and the physical world, and thus providing technical support for subsequent "dynamic tracking".

[0017] After completing the above preparatory steps, the fuel blending system can use the LIBS installed at the material drop port of the coal conveyor belt transfer station to perform penetrating detection on the multi-source fuel flow falling through the material drop port according to a preset detection frequency, using a pulse airflow self-cleaning and vibration compensation mechanism, to obtain the elemental composition of the multi-source fuel.

[0018] Specifically, in the embodiments of this application, the fuel blending system can obtain the elemental composition of multi-source fuels by means of the following method: continuously monitoring the falling fuel flow through a LIBS online monitoring device installed at the feed inlet or in the middle of the conveyor belt. The LIBS online monitoring device can generate plasma by bombarding the fuel surface with high-energy laser pulses, and analyze its spectral signal with a spectrometer to resolve the elemental composition (carbon, hydrogen, sulfur, ash, etc.) of the current fuel flow in real time and calculate the real-time calorific value, thereby realizing the real-time acquisition of the most critical parameters (calorific value, sulfur content) required for blending decisions.

[0019] Step 12: Based on the obtained elemental composition, location information, and weight data of the multi-source fuel, construct the dynamic flow trajectory data of the multi-source fuel from the warehouse to the boiler. In one implementation, step 12 may include: using a multi-source data fusion algorithm based on Kalman filtering and particle filtering to perform spatiotemporal alignment and integration of the acquired elemental composition, location information and weight data to generate dynamic flow trajectory data of the multi-source fuel from the warehouse to the boiler, which has attributes of composition, weight, location and flow direction.

[0020] Specifically, in this embodiment, RFID readers can be installed at key nodes of the coal conveying system (such as the head and tail of the belt conveyor and the inlet of the blending bin). When tagged fuel flows through, the reader captures the tag ID and its location information. The system fuses the RFID location information, the weight and flow information of the belt scale, and the real-time composition information of LIBS to obtain dynamic flow trajectory data of each batch of fuel from the warehouse to the boiler.

[0021] Step 3: Based on the dynamic flow trajectory data and the calorific value data, determine the optimal flow rate setting value for each coal feeding mechanism using a multi-objective optimization algorithm; In this embodiment of the application, step 12 may be implemented by: based on the dynamic flow trajectory data and the calorific value data, using a multi-objective optimization algorithm to solve for the optimal solution set with multiple objectives of calorific value stability, sulfur emission control, and optimal economic efficiency, and determining the optimal flow rate setpoint for each coal feeding mechanism. Specifically, the fuel blending system can perform multi-objective optimization algorithm calculations based on the real-time data stream obtained by executing steps 1 and 2, according to the objective function shown in the following formula [1]: [1] in, This indicates the deviation in calorific value; , indicating total sulfur content; , representing the total cost.

[0022] In the embodiments of this application, the optimization objective can be set as follows: Objective 1: Stabilize the calorific value so that the predicted calorific value after blending is infinitely close to the set target calorific value under the current boiler load.

[0023] Objective 2: Environmental constraints, ensuring that the predicted total sulfur content after blending is below the safe threshold of the design inlet concentration of the desulfurization system.

[0024] Objective 3: Economic Optimization. Under the above conditions, prioritize the use of lower-cost fuels (such as coal gangue and coal slime) to minimize total fuel costs.

[0025] In this embodiment, constraints can be set based on the maximum / minimum output of each coal feeder, the inventory of each warehouse, the boiler load demand, etc. In one implementation, the constraints set in this embodiment can be: Load demand constraints: ; Blending ratio constraints: ; Sulfur emission constraints: ; Equipment capacity constraints: .

[0026] Based on the above optimization objectives and constraints, the Pareto optimal solution set is obtained by using the improved multi-objective particle swarm optimization (MOPSO) algorithm, thus obtaining the optimal flow rate setpoint for each coal feeding mechanism.

[0027] Step 4: Generate a blending control strategy for each coal feeding mechanism based on the optimal flow rate setpoint obtained by executing Step 3, and distribute the blending control strategy to each coal feeding mechanism so that each coal feeding mechanism adjusts its rotation speed and baffle opening according to the blending control strategy to achieve multi-source fuel blending.

[0028] In one implementation, based on the optimal flow rate setpoints obtained by performing step 3, a set of solutions that best suits the current operational preferences (e.g., a greater emphasis on economy or a greater emphasis on environmental protection) can be selected through fuzzy decision-making. This solution represents the target speed and flow rate setpoints for each coal feeder (corresponding to different fuel bins).

[0029] Based on the optimal flow rate setpoint, a blending control strategy is generated for each of the aforementioned coal feeding mechanisms. This determined blending control strategy is then directly transmitted to the power plant's existing Distributed Control System (DCS) or Programmable Logic Controller (PLC) via standard protocols such as OPC UA. The DCS / PLC then automatically adjusts the inverter speed, silo pump output, or damper opening of the corresponding coal feeder. This achieves precise blending of multiple fuel sources.

[0030] It should also be noted that, in order to dynamically optimize the blending control strategy of the fuel blending system based on the real-time operation of the boiler, in this embodiment of the application, the fuel blending system can also acquire the actual operating data of the boiler; compare the operating data with the predicted values ​​generated based on the preset digital twin model to obtain operating deviation data; and optimize and adjust the blending control strategy based on the operating deviation data.

[0031] Specifically, the fuel blending system can collect the actual operating data of the boiler in real time through the boiler-side monitoring system (such as the flue gas online monitoring system CEMS and thermal efficiency calculation model), which may include: boiler efficiency, main steam flow and pressure, boiler efficiency, flue gas temperature, SO2 and NOx concentration, etc.

[0032] Meanwhile, the fuel blending system can use an LSTM (Long Short-Term Memory) network to construct a digital twin model, and then compare the acquired actual operating data with the predicted data of the digital twin model. If there is a significant deviation (e.g., the actual SO2 concentration is higher than the predicted value), it indicates that some parameters or algorithms used in the model may not match reality. Therefore, the blending control strategy can be optimized and adjusted based on the operating deviation data.

[0033] The boiler multi-source fuel blending method provided in this application has two advantages. First, the boiler multi-source fuel blending system can obtain the elemental composition of multi-source fuels through laser-induced breakdown spectroscopy (LIBS), achieving elemental composition analysis at the second level (≥5 times / second). This reduces the acquisition delay of fuel quality data from 4-6 hours in traditional laboratory analysis to the second level. Furthermore, the system can instantly capture fluctuations in fuel characteristics (such as a sudden decrease in the calorific value or an increase in sulfur content in a batch of coal gangue), providing the possibility for real-time adjustment of the blending ratio and completely avoiding boiler efficiency decline and emission exceedances caused by information lag. Second, the boiler multi-source fuel blending system can construct a system based on the obtained elemental composition, location information, and weight data of the multi-source fuels. The dynamic flow trajectory data of the multi-source fuel from the warehouse to the boiler is used to determine the optimal flow rate setpoint for each coal feeding mechanism based on the dynamic flow trajectory data and the calorific value data, using a multi-objective optimization algorithm. Based on the optimal flow rate setpoint, a blending control strategy is generated for each coal feeding mechanism, and the blending control strategy is distributed to each coal feeding mechanism. This allows each coal feeding mechanism to adjust its rotation speed and damper opening according to the blending control strategy, achieving multi-source fuel blending. Based on the multi-objective optimization algorithm and real-time dynamic flow trajectory data, the calculated blending command simultaneously satisfies calorific value stability, sulfur content constraints, and optimal economic efficiency, achieving multi-objective collaborative optimization. This reduces the calorific value control deviation of the fuel entering the boiler from ±1200 kJ / kg in the traditional method to within ±400 kJ / kg, improving control accuracy by more than 66%, reducing sulfur content fluctuation by 40%, stabilizing the inlet concentration of the desulfurization system, alleviating environmental pressure from the source, and fundamentally solving the monitoring lag and crude control problems existing in boiler fuel blending control schemes in related technologies.

[0034] In one embodiment, this application also provides a boiler multi-source fuel blending system to solve the problem that existing fuel quality detection schemes have low detection timeliness, resulting in the inability to obtain multi-source fuel parameters in a timely manner, and thus the inability to adjust the blending of multi-source fuels in real time. This leads to decreased boiler combustion efficiency, excessive pollutant emissions (such as a sudden increase in SO2 concentration), and even furnace coking or flameout due to calorific value imbalance. A schematic diagram of the specific structure of this boiler multi-source fuel blending system is shown below. Figure 2 As shown, it includes: an element composition detection unit 21, a flow trajectory data generation unit 22, a flow rate calculation unit 23, and a blending strategy generation unit 24.

[0035] The elemental composition detection unit 21 is used to obtain the elemental composition of the multi-source fuel through a laser-induced breakdown spectrometer (LIBS), and determine the calorific value data corresponding to the multi-source fuel based on the elemental composition. The flow track data generation unit 22 is used to construct dynamic flow track data of the multi-source fuel from the warehouse to the boiler based on the obtained elemental composition, position information and weight data of the multi-source fuel. The flow calculation unit 23 is used to determine the optimal flow setting value of each coal feeding mechanism based on the dynamic flow trajectory data and the calorific value data and a multi-objective optimization algorithm. The blending strategy generation unit 24 is used to generate a blending control strategy corresponding to each of the coal feeding mechanisms according to the optimal flow setting value, and to send the blending control strategy to each coal feeding mechanism so that each coal feeding mechanism adjusts its rotation speed and baffle opening according to the blending control strategy to achieve multi-source fuel blending.

[0036] In one embodiment, the elemental composition detection unit 21 is specifically used to: use the LIBS installed at the material drop port of the coal conveyor belt transfer station to perform penetrating detection on the multi-source fuel flow falling through the material drop port according to a preset detection frequency, employing a pulse airflow self-cleaning and vibration compensation mechanism, to obtain the elemental composition of the multi-source fuel.

[0037] In one embodiment, the flow track data generation unit 22 is specifically used to: employ a multi-source data fusion algorithm based on Kalman filtering and particle filtering to perform spatiotemporal alignment and integration of the acquired element composition, position information, and weight data to generate dynamic flow track data of the multi-source fuel from the warehouse to the boiler, which has attributes of composition, weight, position, and flow direction.

[0038] In one embodiment, the flow calculation unit 23 is specifically used to: determine the optimal flow setting value for each coal feeding mechanism by using a multi-objective optimization algorithm to solve for the optimal solution set based on the dynamic flow trajectory data and the calorific value data, with multiple objectives of calorific value stability, sulfur emission control and economic optimization.

[0039] In one embodiment, the system further includes a strategy adjustment unit, specifically configured to: acquire actual boiler operating data; compare the operating data with predicted values ​​generated based on a preset digital twin model to obtain operating deviation data; and optimize and adjust the blending control strategy based on the operating deviation data.

[0040] In one implementation, the preset digital twin model is constructed using an LSTM (Long Short-Term Memory) network; the actual operating data of the boiler includes: boiler efficiency, sulfur dioxide concentration, and nitrogen oxide concentration.

[0041] The boiler multi-source fuel blending system provided in this application has two advantages. First, it can acquire the elemental composition of multi-source fuels using a laser-induced breakdown spectroscopy (LIBS) instrument, achieving elemental composition analysis at the second level (≥5 times / second). This reduces the acquisition delay of fuel quality data from 4-6 hours in traditional laboratory analysis to the second level. Furthermore, the system can instantly capture fluctuations in fuel characteristics (such as a sudden decrease in the calorific value or an increase in sulfur content in a batch of coal gangue), providing the possibility for real-time adjustment of the blending ratio and completely avoiding boiler efficiency degradation and emission exceedances caused by information lag. Second, the boiler multi-source fuel blending system can construct a system based on the acquired elemental composition, location information, and weight data of the multi-source fuels. The dynamic flow trajectory data of the multi-source fuel from the warehouse to the boiler is used to determine the optimal flow rate setpoint for each coal feeding mechanism based on the dynamic flow trajectory data and the calorific value data, using a multi-objective optimization algorithm. Based on the optimal flow rate setpoint, a blending control strategy is generated for each coal feeding mechanism, and the blending control strategy is distributed to each coal feeding mechanism. This allows each coal feeding mechanism to adjust its rotation speed and damper opening according to the blending control strategy, achieving multi-source fuel blending. Based on the multi-objective optimization algorithm and real-time dynamic flow trajectory data, the calculated blending command simultaneously satisfies calorific value stability, sulfur content constraints, and optimal economic efficiency, achieving multi-objective collaborative optimization. This reduces the calorific value control deviation of the fuel entering the boiler from ±1200 kJ / kg in the traditional method to within ±400 kJ / kg, improving control accuracy by more than 66%, reducing sulfur content fluctuation by 40%, stabilizing the inlet concentration of the desulfurization system, alleviating environmental pressure from the source, and fundamentally solving the monitoring lag and crude control problems existing in boiler fuel blending control schemes in related technologies.

[0042] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0043] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0044] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0045] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0046] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0047] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0048] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0049] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0050] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0051] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for blending multiple fuel sources in a boiler, characterized in that, include: The elemental composition of the multi-source fuel was obtained by laser-induced breakdown spectroscopy (LIBS), and the calorific value data of the multi-source fuel was determined based on the elemental composition. Based on the obtained elemental composition, location information, and weight data of the multi-source fuel, construct dynamic flow trajectory data of the multi-source fuel from the warehouse to the boiler. Based on the dynamic flow trajectory data and the calorific value data, the optimal flow rate setting value for each coal feeding mechanism is determined using a multi-objective optimization algorithm. Based on the optimal flow rate setting value, a blending control strategy is generated for each of the coal feeding mechanisms. The blending control strategy is then distributed to each coal feeding mechanism so that each coal feeding mechanism adjusts its rotation speed and baffle opening according to the blending control strategy to achieve multi-source fuel blending.

2. The method according to claim 1, characterized in that, The elemental composition of the multi-source fuel obtained by laser-induced breakdown spectroscopy (LIBS) specifically includes: The LIBS installed at the material drop outlet of the coal conveyor belt transfer station uses a pulsed airflow self-cleaning and vibration compensation mechanism to perform penetrating detection on the multi-source fuel flow falling through the material drop outlet at a preset detection frequency, thereby obtaining the elemental composition of the multi-source fuel.

3. The method according to claim 1, characterized in that, The step of constructing dynamic flow trajectory data for the multi-source fuel from the warehouse to the boiler based on the obtained elemental composition, location information, and weight data of the multi-source fuel specifically includes: A multi-source data fusion algorithm based on Kalman filtering and particle filtering is used to perform spatiotemporal alignment and integration of the acquired elemental composition, location information and weight data to generate dynamic flow trajectory data of the multi-source fuel from the warehouse to the boiler, which has attributes of composition, weight, location and flow direction.

4. The method according to claim 1, characterized in that, The step of determining the optimal flow rate setpoint for each coal feeding mechanism based on the dynamic flow trajectory data and the calorific value data using a multi-objective optimization algorithm specifically includes: Based on the dynamic flow trajectory data and the calorific value data, with multiple objectives of calorific value stability, sulfur emission control, and optimal economy, a multi-objective optimization algorithm is used to solve for the optimal solution set and determine the optimal flow rate set value for each coal feeding mechanism.

5. The method according to claim 1, characterized in that, Also includes: Obtain actual boiler operating data; The operational data is compared with the predicted values ​​generated based on a preset digital twin model to obtain operational deviation data; Based on the operational deviation data, the blending control strategy is optimized and adjusted.

6. The method according to claim 5, characterized in that, The preset digital twin model is constructed using an LSTM (Long Short-Term Memory) network. The actual operating data of the boiler includes: boiler efficiency, sulfur dioxide concentration, and nitrogen oxide concentration.

7. A boiler multi-source fuel blending system, characterized in that, include: The elemental composition detection unit is used to obtain the elemental composition of multi-source fuels through laser-induced breakdown spectroscopy (LIBS) and determine the calorific value data of the multi-source fuels based on the elemental composition. The flow track data generation unit is used to construct dynamic flow track data of the multi-source fuel from the warehouse to the boiler based on the obtained elemental composition, location information and weight data of the multi-source fuel. The flow calculation unit is used to determine the optimal flow setting value of each coal feeding mechanism based on the dynamic flow trajectory data and the calorific value data and a multi-objective optimization algorithm. The blending strategy generation unit is used to generate a blending control strategy corresponding to each of the coal feeding mechanisms based on the optimal flow rate setting value, and to distribute the blending control strategy to each coal feeding mechanism so that each coal feeding mechanism adjusts its rotation speed and baffle opening according to the blending control strategy to achieve multi-source fuel blending.

8. The boiler multi-source fuel blending system according to claim 7, characterized in that, The elements form a detection unit, specifically used for: The LIBS installed at the material drop outlet of the coal conveyor belt transfer station uses a pulsed airflow self-cleaning and vibration compensation mechanism to perform penetrating detection on the multi-source fuel flow falling through the material drop outlet at a preset detection frequency, thereby obtaining the elemental composition of the multi-source fuel.

9. The boiler multi-source fuel blending system according to claim 7, characterized in that, The flow trajectory data generation unit is specifically used for: A multi-source data fusion algorithm based on Kalman filtering and particle filtering is used to perform spatiotemporal alignment and integration of the acquired elemental composition, location information and weight data to generate dynamic flow trajectory data of the multi-source fuel from the warehouse to the boiler, which has attributes of composition, weight, location and flow direction.

10. The boiler multi-source fuel blending system according to claim 7, characterized in that, The flow calculation unit is specifically used for: Based on the dynamic flow trajectory data and the calorific value data, with multiple objectives of calorific value stability, sulfur emission control, and optimal economy, a multi-objective optimization algorithm is used to solve for the optimal solution set and determine the optimal flow rate set value for each coal feeding mechanism.

Images