Method and device for controlling feeding of circulating fluidized bed boiler based on intelligent sensing

Abstract

The present application provides a circulating fluidized bed boiler furnace feeding control method and device based on intelligent sensing, which relates to the technical field of material conveying equipment, including: dynamically monitoring the target boiler through multi-source sensors to obtain boiler operation information, obtaining the target boiler operation characteristics, using the load integrated prediction model to analyze and obtain the target predicted load in a predetermined time period, issuing a feedforward control instruction when the constraints are not met, generating a feeding strategy based on the instruction, and performing feeding control on the double screw feeder of the target boiler in a predetermined time period. This application can solve the problem that the existing technology relies on a single control strategy, the real-time and accuracy of data collection is insufficient, and the prediction accuracy is low, resulting in the inability to dynamically adjust the feeder according to the uniqueness of the material in a timely manner, thereby achieving accurate feeding control, meeting the needs of boiler operation and keeping the load within a predetermined range.

Description

Technical Field

[0001] The present application relates to the technical field of material conveying equipment, and in particular to a method and device for controlling feeding of a circulating fluidized bed boiler furnace based on intelligent sensing. Background Art

[0002] Due to the low calorific value, low bulk density, easy entanglement, poor fluidity and other characteristics of agricultural and forestry biomass fuels, the design of agricultural and forestry biomass boiler furnace feeding equipment should be quite different from the traditional coal-fired boiler feeding system. At present, agricultural and forestry biomass fuels, especially corn straw fuels, are often fed and transported based on the traditional coal-fired boiler feeding system, which leads to frequent shaft breakage, bulky material blockage, uneven feed volume, smoke, fire, and poor adaptability to the type of fuel entering the furnace.

[0003] In summary, the existing technology relies on a single control strategy, the real-time and accuracy of data collection is insufficient, and the prediction accuracy is low, resulting in the inability to dynamically adjust the feeder according to the uniqueness of the material in a timely manner, further affecting the efficiency and stability of boiler load control. Summary of the invention

[0004] The purpose of this application is to provide a circulating fluidized bed boiler furnace feeding control method based on intelligent sensing, in order to solve the problem that the prior art relies on a single control strategy, the real-time and accuracy of data collection is insufficient, the prediction accuracy is low, and the feeder cannot be dynamically adjusted according to the uniqueness of the material in a timely manner.

[0005] In view of the above problems, the present application provides a circulating fluidized bed boiler furnace feeding control method based on intelligent sensing.

[0006] In the first aspect, the present application provides a circulating fluidized bed boiler furnace feeding control method based on intelligent sensing, and the circulating fluidized bed boiler furnace feeding control method based on intelligent sensing is implemented by a circulating fluidized bed boiler furnace feeding control device based on intelligent sensing, wherein the circulating fluidized bed boiler furnace feeding control method based on intelligent sensing includes: obtaining target operation characteristic information, and the target operation characteristic information refers to the boiler operation information obtained by dynamically monitoring the target boiler through multi-source sensors; obtaining a predetermined time period, and calling a load integration prediction model to analyze the target operation characteristic information and the predetermined time period to obtain the target predicted load of the target boiler in the predetermined time period; if the target predicted load does not meet the predetermined load constraint, issuing a feedforward control instruction; based on the feedforward control instruction, reading a predetermined feeding control mechanism, and generating a target feeding strategy according to the predetermined feeding control mechanism; according to the target feeding strategy, feeding and regulating the double screw feeder of the target boiler in the predetermined time period.

[0007] In the second aspect, the present application also provides a circulating fluidized bed boiler furnace feeding control device based on intelligent sensing, which is used to execute the circulating fluidized bed boiler furnace feeding control method based on intelligent sensing as described in the first aspect, wherein the circulating fluidized bed boiler furnace feeding control device based on intelligent sensing includes: a double-screw feeder overall support platform, wherein the double-screw feeder overall support platform includes a support platform; a variable diameter and variable pitch double-screw feeder, wherein the variable diameter and variable pitch double-screw feeder is fixed on the support platform; a drop pipe expansion joint, wherein the drop pipe expansion joint is arranged on the variable diameter The lower end of the feed port of the variable pitch twin-screw feeder; an emergency pneumatic shut-off door, wherein the emergency pneumatic shut-off door is arranged at the upper end of the feed port of the variable pitch twin-screw feeder and is centered with the drop tube expansion joint; an air-cooled sealing sleeve, wherein the first end of the air-cooled sealing sleeve is fixedly connected to the discharge port of the variable pitch twin-screw feeder, and the second end of the air-cooled sealing sleeve is fixedly connected to the uniform feeding sleeve; a uniform feeding sleeve, wherein the uniform feeding sleeve is fixedly connected to the second end of the air-cooled sealing sleeve; a throwing pulse valve, wherein the throwing pulse valve is fixed to the bottom of the uniform feeding sleeve.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] By acquiring target operation characteristic information, the target operation characteristic information refers to the boiler operation information obtained by dynamically monitoring the target boiler through multi-source sensors; acquiring a predetermined time period, and calling a load integrated prediction model to analyze the target operation characteristic information and the predetermined time period, so as to obtain the target predicted load of the target boiler in the predetermined time period; if the target predicted load does not meet the predetermined load constraint, issuing a feedforward control instruction; reading a predetermined feeding regulation mechanism based on the feedforward control instruction, and generating a target feeding strategy according to the predetermined feeding regulation mechanism; according to the target feeding strategy, performing feeding regulation on the double screw feeder of the target boiler in the predetermined time period, effectively solving the problem that the prior art relies on a single regulation strategy, the real-time and accuracy of data collection are insufficient, and the prediction accuracy is low, resulting in the inability to dynamically adjust the feeder according to the uniqueness of the material in a timely manner, thereby achieving accurate feeding regulation, meeting the needs of boiler operation and keeping the load within a predetermined range.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 This is a flow chart of a circulating fluidized bed boiler furnace feeding control method based on intelligent sensing in this application;

[0013] Figure 2 This is a schematic diagram of the process of obtaining the target predicted load in the circulating fluidized bed boiler furnace feeding control method based on intelligent sensing in this application. DETAILED DESCRIPTION

[0014] The present application provides a circulating fluidized bed boiler furnace feeding control method and device based on intelligent sensing, which solves the problem that the prior art relies on a single control strategy, the lack of real-time and accuracy of data collection, and the low prediction accuracy, resulting in the inability to dynamically adjust the feeder according to the uniqueness of the material in a timely manner. It realizes accurate feeding control, meets the needs of boiler operation and keeps the load within a predetermined range.

[0015] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0016] For example, please refer to the attached Figure 1The present application provides a circulating fluidized bed boiler furnace feeding control method based on intelligent sensing, wherein the circulating fluidized bed boiler furnace feeding control method based on intelligent sensing is applied to a circulating fluidized bed boiler furnace feeding control device based on intelligent sensing, and the circulating fluidized bed boiler furnace feeding control method based on intelligent sensing specifically includes the following steps:

[0017] S1: Acquire target operation characteristic information, where the target operation characteristic information refers to boiler operation information obtained by dynamically monitoring a target boiler through multi-source sensors.

[0018] Specifically, the target operation characteristic information includes but is not limited to temperature characteristics, which monitor the temperature changes of different parts of the boiler, such as the furnace, superheater, economizer, etc., through temperature sensors to reflect the thermal performance of the boiler; pressure characteristics, which use pressure sensors to monitor the boiler steam pressure, feed water pressure, etc. to ensure that the boiler operates within a safe range; flow characteristics, which monitor the boiler feed water flow, steam flow, etc. through flow sensors to analyze the material balance and energy conversion efficiency of the boiler; vibration characteristics, for large boilers, vibration sensors can monitor the vibration of the boiler body and auxiliary equipment to detect potential mechanical failures in a timely manner; flue gas composition characteristics, which monitor oxygen, carbon dioxide, nitrogen oxides and other components in the flue gas through flue gas analyzers to evaluate the combustion efficiency and environmental performance of the boiler. According to the specific needs and monitoring indicators of the target boiler, select the appropriate sensor type, accuracy and range. Ensure that the sensor can accurately and reliably collect the required data. According to the structural characteristics and monitoring needs of the boiler, reasonably determine the deployment location of the sensor. For example, the temperature sensor should be arranged on the key heating surface of the boiler; the pressure sensor should be installed at the key nodes of the steam pipe and the feed water pipe; the flow sensor should be installed at the outlet of the feed water pump and the steam outlet.

[0019] S2: Obtain a predetermined time period, and call a load integrated prediction model to analyze the target operation characteristic information and the predetermined time period to obtain a target predicted load of the target boiler in the predetermined time period.

[0020] Specifically, the predetermined time period refers to the future time period for which you want to predict and prepare the feeding control strategy in advance. It can be set according to actual needs, such as the next hour, the next shift or the next day. It is set by technical personnel in this field according to factors such as the operation cycle of the boiler, the law of load changes, and the implementation time of the control strategy. According to the operating characteristics and historical data of the boiler, a suitable load integration prediction model is selected, which can be a neural network model. The load integration prediction model is trained using historical data. Specifically, the first record under the first historical period is extracted from the operating record data of the same boiler as the target boiler, and the first training data group is formed based on the first operating characteristic information record and the first load record in the first record. Then, the first training data group is machine-learned based on the principle of neural network, and the prediction performance of the model is evaluated by cross-validation and other methods. When its prediction performance reaches the predetermined performance requirements, the trained intelligent model is used as the load integration prediction model. The target operating characteristic information is used as input data, and the prepared data is input into the load integration prediction model. The model is run and the target predicted load under the predetermined period is obtained based on the current operating characteristic information and the historical load data.

[0021] S3: If the target predicted load does not satisfy the predetermined load constraint, a feedforward control instruction is issued.

[0022] Specifically, the predetermined load constraints are used to ensure that the boiler operates within a safe and efficient range, including maximum load, minimum load, load change rate, etc. When the load integrated prediction model obtains the target predicted load, it is compared with the predetermined load constraints. If the target predicted load does not meet any one or more conditions in the predetermined load constraints, a feedforward control instruction is issued, including the load amount or load change rate that needs to be adjusted, the direction of adjustment, such as increasing or decreasing the load, and the time requirements for adjustment, such as immediate adjustment or completing the adjustment within a certain period of time.

[0023] S4: Reading a predetermined feeding regulation mechanism based on the feedforward control instruction, and generating a target feeding strategy according to the predetermined feeding regulation mechanism.

[0024] Specifically, the predetermined feeding control mechanism is used to guide how to make adjustments during the feeding process to respond to load changes or keep the boiler in a specific operating state, including the relationship between the feeding rate and the load, the time constant of the feeding adjustment, the limit of the feeding change, etc. When the feedforward control instruction is received, the database or configuration file storing the predetermined feeding control mechanism is accessed, and the relevant rules and strategies are read as the basis for generating the target feeding strategy. Based on the read predetermined feeding control mechanism and the current operating state of the boiler (including the target predicted load, the actual load, the feeding rate, etc.), the target feeding strategy is generated, including how to adjust the feeding amount to achieve the expected load level or keep the boiler in a specific operating state; the specific adjustment value or adjustment ratio of the feeding amount; the adjustment schedule or time constant, that is, how long should the feeding amount reach the new set value; the limit of feeding change, such as the maximum feeding increase rate or the maximum feeding decrease rate.

[0025] S5: According to the target feeding strategy, the double screw feeder of the target boiler is regulated and controlled during the predetermined period of time.

[0026] Specifically, interpret the target feeding strategy, clarify the specific adjustment value or adjustment ratio of the feeding amount, the adjustment schedule or time constant, and the restriction of feeding change and other key information. According to the target feeding strategy, set the feeding amount of the double screw feeder, adjust the speed, pitch and other parameters of the feeder to ensure that the feeding amount meets the strategy requirements; adjust the schedule or time constant, and set the corresponding time parameters in the control system of the double screw feeder to ensure that the adjustment of the feeding amount can be completed within the predetermined time; according to the feeding change restriction in the target feeding strategy, limit the feeding amount change of the double screw feeder.

[0027] Further, if Figure 2 As shown, this application also includes:

[0028] Extract a first predetermined operating indicator, and traverse and match the target operating characteristic information based on the first predetermined operating indicator to obtain the first operating characteristic information; use the first operating characteristic information as input information of the first predictor in the load integrated prediction model to obtain the first predicted load in the predetermined time period, wherein the load integrated prediction model is constructed by the first predictor as the initial prediction layer and the meta-prediction layer; use the first predicted load as input information of the meta-prediction layer in the load integrated prediction model to obtain the target predicted load.

[0029] Specifically, the first predetermined operating index, including temperature, pressure, flow, etc., is extracted from the preset operating index library, and the extracted operating index will be used for matching in the target operating characteristic information. The first operating characteristic information corresponding to the first predetermined operating index is traversed and matched in the target operating characteristic information to find the first operating characteristic information. The target operating characteristic information contains the current operating state and multiple operating parameters of the boiler, and the data related to the first predetermined operating index is screened out. A load integrated prediction model of the first predictor and the meta-prediction layer is constructed, and trained and verified. The load integrated prediction model consists of an initial prediction layer and a meta-prediction layer. The initial prediction layer, that is, the first predictor, can be a neural network model. According to historical load data and influencing factors, appropriate features are selected as input. Based on the selected prediction algorithm and features, a model of the initial prediction layer is established. The meta-prediction layer adopts an integrated learning strategy to synthesize the prediction results of the initial prediction layer. The integrated methods include bagging, boosting, stacking, etc. Multiple initial prediction results are fused into a final prediction result by weighted average, voting, learning fusion weights, etc. Collect a large amount of historical load data and related influencing factor data, and perform preprocessing, such as cleaning and normalization, to ensure the quality and availability of the data. Divide the preprocessed data set into a training set, a validation set, and a test set. The training set is used to train the model, the validation set is used to adjust the model parameters and prevent overfitting, and the test set is used to evaluate the final performance of the model. Use the training set to train the model, and adjust the model parameters, such as learning rate, number of iterations, regularization coefficient, etc., through the validation set. For the meta-prediction layer, train the initial prediction layer model, and use the prediction results as input to train the meta-prediction layer model. Use the test set to evaluate the performance of the trained load integration prediction model. Including root mean square error, mean absolute error, mean absolute percentage error, etc. According to the results of performance evaluation and error analysis, optimize the model, including adjusting feature selection, improving prediction algorithms, optimizing integration strategies, etc. The first operating characteristic information is used as the input information of the first predictor in the load integration prediction model. The first predictor is the initial prediction layer of the load integration prediction model, and the first predicted load under the predetermined period is generated according to the input operating characteristic information. After the first predicted load is obtained, it is used as input information of the meta-prediction layer in the load integrated prediction model, and the first predicted load is further processed and analyzed to obtain the target predicted load.

[0030] Furthermore, the present application also includes:

[0031] Obtain a target operation component set, and extract any component in the target operation component set, wherein the target operation component set refers to a collection of multiple operation components corresponding to multiple operation links of the target boiler; obtain historical operation records of the arbitrary component, and the historical operation records include historical operation characteristic information and historical load of the arbitrary component; use the historical operation characteristic information as an independent variable, use the historical load as a dependent variable, and perform correlation analysis on the independent variable and the dependent variable to obtain a correlation analysis result; analyze the correlation analysis result to obtain any predetermined operation indicator of the arbitrary component, and form a component load database according to the mapping relationship between the arbitrary component and the arbitrary predetermined operation indicator; obtain a first component, and match the first predetermined operation indicator corresponding to the first component in the component load database.

[0032] Specifically, the target operation component set refers to a set of multiple operation components corresponding to multiple operation links of the target boiler, including the target returner, target furnace and target separator of the target boiler; collect relevant information of all operation links of the target boiler, including the operation components of each link, and integrate the collected operation components into a set, namely the target operation component set. Randomly select a component from the target operation component set as the analysis object, and obtain detailed information of the selected component, including its function, location, associated operation link, etc. The historical operation record includes the historical operation characteristic information and historical load of the selected component, extract the relevant records of the selected component from the historical operation data of the boiler, perform pre-processing operations such as cleaning, denoising, and normalization on the historical operation characteristic information and historical load data, use statistical methods or machine learning algorithms to analyze the correlation between the historical operation characteristic information and the historical load, output the results of the correlation analysis, including the value of the correlation coefficient, the significance level, etc., and determine any predetermined operation index of the selected component according to the results of the correlation analysis. Determine the mapping relationship between the selected component and its predetermined operation index. Store the selected component, its predetermined operation index and the mapping relationship in the component load database. Select or designate a component as the first component from the target operating component set, search for the first predetermined operating index corresponding to the first component in the component load database, and output the first component and its corresponding first predetermined operating index. By obtaining the operating component set of the target boiler, analyzing the historical operating records of any component, forming a component load database, and matching the predetermined operating index corresponding to a specific component in the database, it provides strong data support for boiler operation optimization and load forecasting.

[0033] Furthermore, the target operation component set includes at least a target returner, a target furnace and a target separator of the target boiler.

[0034] Specifically, the target returner is responsible for returning the burned materials to the furnace for re-combustion to improve combustion efficiency and thermal energy utilization. The target furnace is the fuel combustion site in the boiler, and its operating conditions directly affect the boiler's combustion efficiency and thermal energy output. The target separator is responsible for separating solid particles from flue gas in the boiler, which is crucial to maintaining clean operation and efficient combustion of the boiler.

[0035] Furthermore, the present application also includes:

[0036] The predetermined feeding control mechanism includes a feeder control mechanism and a biomass fuel control mechanism; the first optimal feeding strategy of the double screw feeder is obtained according to the feeder control mechanism; combined with the first optimal feeding strategy, the second optimal feeding strategy is obtained according to the biomass fuel control mechanism; the first optimal feeding strategy and the second optimal feeding strategy constitute the target feeding strategy.

[0037] Specifically, the feeder control mechanism is a control strategy for the feeder, which optimizes the operating parameters of the feeder to improve the accuracy and efficiency of feeding. By analyzing the historical operating data, current operating conditions and preset optimization goals of the feeder, the first optimal feeding strategy of the double screw feeder can be obtained, including the optimal feeding speed, feeding amount, feeding time and other parameters. The biomass fuel control mechanism is a control strategy for the characteristics of biomass fuel, which optimizes the combustion efficiency and environmental performance of the fuel. On the basis of the first optimal feeding strategy, combined with the characteristics of biomass fuel, such as calorific value, ash content, moisture, etc. and combustion requirements, the second optimal feeding strategy can be obtained, including feeding adjustment for specific fuels, combustion control parameters, etc. The target feeding strategy is a comprehensive strategy composed of the first optimal feeding strategy and the second optimal feeding strategy. The target feeding strategy can ensure that the feeder operates in the optimal state, while fully considering the characteristics of biomass fuel to achieve precise control of feeding, improve combustion efficiency and environmental performance. The operating parameters of the feeder and the feeding method of the fuel can be adjusted according to the target feeding strategy to achieve the best combustion effect and environmental emission standards.

[0038] Furthermore, the present application also includes:

[0039] A control index set of the double screw feeder is obtained, wherein each control index in the control index set has a predetermined index threshold value, so as to form a first feeding control space; a first feeding strategy in the first feeding control space is obtained; the first feeding strategy is traversed in a feeding database to obtain a first most similar feeding strategy, and a first most similar feeding record where the first most similar feeding strategy is located is obtained; when a first combustion efficiency in the first most similar feeding record reaches a predetermined combustion efficiency, the first feeding strategy is used as the first optimal feeding strategy.

[0040] Specifically, the control index set of the double screw feeder is determined, including all parameters that need to be monitored and adjusted, such as feeding speed, feeding amount, motor speed, feeding speed, bed temperature and bed pressure. A predetermined index threshold is set for each control index, which represents the upper and lower limits of the index within the normal operating range. These control indexes and their predetermined index thresholds are combined to form a multidimensional control space, namely the first feeding control space, which contains all possible feeding strategies. According to the current operating conditions and optimization goals, a specific feeding strategy, namely the first feeding strategy, is located in the first feeding control space. The first feeding strategy is traversed in the feeding database, which contains all historical feeding records and corresponding combustion efficiencies. By comparing the first feeding strategy with the feeding records in the database, the most similar feeding strategy is found, namely the first most similar feeding strategy. At the same time, the first most similar feeding record where the first most similar feeding strategy is located is obtained, which contains key information such as the combustion efficiency under the strategy. Check whether the combustion efficiency in the first most similar feeding record meets the predetermined combustion efficiency standard. If the combustion efficiency of the first most similar feeding record reaches a predetermined standard, the first feeding strategy is determined as the first optimal feeding strategy. At this time, the first optimal feeding strategy is a feeding method that can achieve the optimal combustion efficiency under current conditions.

[0041] Furthermore, the control index set includes feed rate, bed temperature and bed pressure.

[0042] Specifically, the feeding speed refers to the amount of fuel that the double screw feeder puts into the boiler per unit time. The feeding speed directly affects the combustion efficiency and heat output of the boiler. Too fast or too slow feeding speed may lead to unstable combustion or reduced thermal efficiency. The feeding speed is a dimension in the first feeding control space, and its predetermined index threshold defines the normal operating range of the feeding speed. The bed temperature refers to the average temperature of the fuel layer in the boiler. The bed temperature is a key parameter in the combustion process and directly affects the combustion speed and combustion efficiency of the fuel. Too high or too low bed temperature may lead to incomplete combustion or boiler coking. The bed temperature is also a dimension in the first feeding control space, and its predetermined index threshold defines the normal operating range of the bed temperature. The bed pressure refers to the pressure of the fuel layer in the boiler on the boiler wall. The bed pressure reflects the accumulation of fuel in the boiler and the gas pressure generated by combustion. Too high or too low bed pressure may affect the stable operation and safety of the boiler. The bed pressure is also a dimension in the first feeding control space, and its predetermined index threshold defines the normal operating range of the bed pressure.

[0043] Furthermore, the present application also includes:

[0044] A second feeding control space is formed according to the biomass fuel control mechanism, and the second feeding control space is used as the optimization space; the first optimal feeding strategy is used as the optimization constraint; the combustion efficiency is used as the optimization evaluation index; the taboo search principle is used to perform global optimization in the optimization space under the optimization constraint and based on the optimization evaluation index to obtain the second optimal feeding strategy.

[0045] Specifically, according to the characteristics of biomass fuel, such as calorific value, ash content, moisture, feed particle size, material layer thickness, feed-wind ratio, etc. and combustion requirements, a set of control indicators for biomass fuel is formed. These control indicators and their predetermined indicator thresholds are combined to form a multidimensional control space, namely the second feed control space, which contains all possible feeding strategies for biomass fuel. The first optimal feeding strategy obtained is used as a constraint in the optimization process. When optimizing in the second feeding control space, parameters such as feed rate, bed temperature and bed pressure in the first optimal feeding strategy are considered to ensure that the new feeding strategy does not deviate too far in these parameters. Combustion efficiency is selected as an evaluation indicator to measure the pros and cons of feeding strategies. In the optimization process, it is necessary to continuously calculate and compare the combustion efficiency under different feeding strategies to find a feeding strategy that can maximize the combustion efficiency. By recording the solutions that have been visited, namely the taboo table, repeated searches are avoided, and specific search strategies and amnesty rules are used to jump out of the local optimal solution, thereby achieving global optimization. In the second feeding control space, the taboo search principle is used for global optimization. The specific process includes initializing the solution space, setting the taboo table, selecting candidate solutions, calculating the combustion efficiency, updating the taboo table, and judging the termination conditions. Through continuous iteration and search, the second optimal feeding strategy that can maximize the combustion efficiency is finally found.

[0046] In summary, the circulating fluidized bed boiler furnace feeding control method based on intelligent sensing provided in this application has the following technical effects:

[0047] By acquiring target operation characteristic information, the target operation characteristic information refers to the boiler operation information obtained by dynamically monitoring the target boiler through multi-source sensors; acquiring a predetermined time period, and calling a load integrated prediction model to analyze the target operation characteristic information and the predetermined time period, so as to obtain the target predicted load of the target boiler in the predetermined time period; if the target predicted load does not meet the predetermined load constraint, issuing a feedforward control instruction; reading a predetermined feeding regulation mechanism based on the feedforward control instruction, and generating a target feeding strategy according to the predetermined feeding regulation mechanism; according to the target feeding strategy, performing feeding regulation on the double screw feeder of the target boiler in the predetermined time period, effectively solving the problem that the prior art relies on a single regulation strategy, the real-time and accuracy of data collection are insufficient, and the prediction accuracy is low, resulting in the inability to dynamically adjust the feeder according to the uniqueness of the material in a timely manner, thereby achieving accurate feeding regulation, meeting the needs of boiler operation and keeping the load within a predetermined range.

[0048] Embodiment 2, based on the same inventive concept as the circulating fluidized bed boiler furnace feeding control method based on intelligent sensing in the aforementioned embodiment, the present application also provides a circulating fluidized bed boiler furnace feeding control device based on intelligent sensing, the circulating fluidized bed boiler furnace feeding control device based on intelligent sensing includes:

[0049] The overall support platform of the double-screw feeder comprises a support platform.

[0050] Specifically, the support platform is the foundation of the entire twin screw feeder system, providing a stable support to ensure that the variable diameter and variable pitch twin screw feeder and other components can operate stably. The support platform can bear the weight of the feeder and the material to prevent vibration and deformation.

[0051] A double-screw feeder with variable diameter and pitch, wherein the double-screw feeder with variable diameter and pitch is fixed on the supporting platform.

[0052] Specifically, the variable diameter and variable pitch double screw feeder is fixed on the support platform. It is the core equipment for material transportation. It can adjust the material conveying volume and speed by changing the diameter and pitch according to the needs. The variable diameter and variable pitch double screw feeder realizes continuous, uniform and quantitative material transportation through the rotation of the double screw. The double screw blades are staggered at a certain angle, and the material is driven in two directions during the transportation process, which improves the stability and efficiency of transportation. The diameter and pitch of the screw can be adjusted according to the material characteristics and transportation requirements to meet the transportation requirements of different materials.

[0053] A blanking pipe expansion joint, wherein the blanking pipe expansion joint is arranged at the lower end of the feed port of the variable diameter and variable pitch double screw feeder.

[0054] Specifically, the expansion joint of the drop pipe is located at the lower end of the feed port of the variable diameter and variable pitch double screw feeder. It can absorb and buffer the slight deformation of the drop pipe caused by temperature changes, pressure fluctuations or mechanical vibrations, thereby protecting the feed port of the feeder from damage. It is made of highly elastic materials such as rubber, metal bellows, etc. to absorb pipe deformation.

[0055] An emergency pneumatic shut-off door, wherein the emergency pneumatic shut-off door is arranged at the upper end of the feed port of the variable diameter and variable pitch double screw feeder and is centered with the drop pipe expansion joint.

[0056] Specifically, the emergency pneumatic shut-off door is arranged at the upper end of the feed port of the variable diameter and variable pitch twin screw feeder and is aligned with the center of the expansion joint of the drop pipe. In emergency situations, such as material blockage, equipment failure or emergency shutdown, it can quickly cut off the material feed channel to ensure safety.

[0057] An air-cooled sealing sleeve, wherein the first end of the air-cooled sealing sleeve is fixedly connected to the discharge port of the variable diameter and variable pitch double-screw feeder, and the second end of the air-cooled sealing sleeve is fixedly connected to the uniform feeding sleeve.

[0058] Specifically, the first end of the air-cooled sealing sleeve is fixedly connected to the discharge port of the variable-diameter and variable-pitch double-screw feeder, and the second end is fixedly connected to the uniform feeding sleeve. A sealing function is provided to prevent material leakage, and the sealing sleeve can be cooled by a built-in air cooling system to reduce the heat generated by material friction and transportation.

[0059] A uniform feeding sleeve, wherein the uniform feeding sleeve is fixedly connected to the second end of the air-cooled sealing sleeve.

[0060] Specifically, the uniform feeding sleeve is fixedly connected to the second end of the air-cooled sealing sleeve to ensure that the material output from the double-screw feeder can enter the next process or equipment evenly and stably, so that the material can be evenly distributed during the transportation process and the impact and wear of the material on the downstream equipment can be reduced.

[0061] A material throwing pulse valve, wherein the material throwing pulse valve is fixed on the bottom of the uniform feeding sleeve.

[0062] Specifically, the material throwing pulse valve is fixed at the bottom of the uniform feeding sleeve, and the material throwing is controlled by pulse signals, which helps to achieve uniform distribution and stable transportation of materials.

[0063] Furthermore, the overall support platform of the double-screw feeder also includes a spring hanger, the variable diameter and variable pitch double-screw feeder includes a screw shaft, a variable frequency speed regulation motor and a driving reducer, the air-cooled sealing sleeve includes an inner wall, an outer wall, an annular cavity, a gas channel, an air inlet pipe and an adjusting damper, and the throwing pulse valve includes a main air duct, a bypass air duct, a main rotary valve and a bypass damper.

[0064] Specifically, the spring hanger is mainly used to support and fix the variable diameter and variable pitch double screw feeder, and can absorb and alleviate the vibration and impact generated by the equipment during operation, protecting the feeder and its connecting parts from damage. The spring hanger has good shock absorption performance and can effectively reduce the impact of equipment vibration on the support platform and the surrounding environment. The screw shaft is equipped with two sections of spiral blades with opposite spiral directions, left-handed and right-handed, which push the material forward through rotation. The variable frequency speed regulation motor provides power for the screw shaft. The speed of the screw shaft can be accurately controlled by the variable frequency speed regulation technology, so as to achieve accurate adjustment of the material conveying amount. The drive reducer is connected between the motor and the screw shaft to reduce the output speed of the motor and increase the torque to meet the driving force requirements of the screw shaft. The inner wall and the outer wall form the inner and outer layers of the sealing sleeve to isolate the material from the external environment. The annular cavity is located between the inner wall and the outer wall to accommodate the cooling gas. The gas channel connects the air inlet pipe and the annular cavity to ensure that the cooling gas can flow smoothly. The air inlet pipe and the damper are used to introduce cooling gas into the annular cavity, and the damper is used to control the flow rate and velocity of the cooling gas. The main air duct and the bypass air duct are used to control the main and bypass air flow channels respectively. The main rotary valve controls the on-off and flow rate of the main air flow through the rotation action; the bypass damper is used to control the on-off of the bypass air flow.

[0065] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The circulating fluidized bed boiler furnace feeding control method based on intelligent sensing and the specific examples in the first embodiment are also applicable to the circulating fluidized bed boiler furnace feeding control device based on intelligent sensing in this embodiment. Through the above detailed description of the circulating fluidized bed boiler furnace feeding control method based on intelligent sensing, those skilled in the art can clearly know the circulating fluidized bed boiler furnace feeding control device based on intelligent sensing in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0066] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0067] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A circulating fluidized bed boiler furnace feeding control method based on intelligent sensing, characterized in that: include: Acquiring target operation characteristic information, wherein the target operation characteristic information refers to boiler operation information obtained by dynamically monitoring the target boiler through multi-source sensors; Obtaining a predetermined time period, and calling a load integrated prediction model to analyze the target operation characteristic information and the predetermined time period, to obtain a target predicted load of the target boiler in the predetermined time period; If the target predicted load does not satisfy the predetermined load constraint, issuing a feedforward control instruction; Reading a predetermined feeding regulation mechanism based on the feedforward control instruction, and generating a target feeding strategy according to the predetermined feeding regulation mechanism; According to the target feeding strategy, the double screw feeder of the target boiler is regulated and controlled during the predetermined period of time; Extracting a first predetermined operation indicator, and traversing and matching the target operation characteristic information based on the first predetermined operation indicator to obtain first operation characteristic information; Using the first operating characteristic information as input information of a first predictor in the load integrated prediction model to obtain a first predicted load in the predetermined time period, wherein the load integrated prediction model is constructed by the first predictor as an initial prediction layer and a meta-prediction layer; The first predicted load is used as input information of a meta-prediction layer in the load integrated prediction model to obtain the target predicted load.

2. The method for controlling the feeding of circulating fluidized bed boiler furnace based on intelligent sensing according to claim 1 is characterized in that: include: Obtain a target operation component set, and extract any component in the target operation component set, wherein the target operation component set refers to a collection of multiple operation components corresponding to multiple operation links of the target boiler; Acquire a historical operation record of the arbitrary component, wherein the historical operation record includes historical operation characteristic information and a historical load of the arbitrary component; Taking the historical operation characteristic information as an independent variable and the historical load as a dependent variable, and performing a correlation analysis on the independent variable and the dependent variable to obtain a correlation analysis result; Analyzing the correlation analysis result to obtain any predetermined operating index of the arbitrary component, and forming a component load database according to a mapping relationship between the arbitrary component and the arbitrary predetermined operating index; A first component is obtained, and the first predetermined operating indicator corresponding to the first component is matched in the component load database.

3. The method for controlling the feeding of circulating fluidized bed boiler furnace based on intelligent sensing according to claim 2 is characterized in that: The target operation component set includes at least a target returner, a target furnace and a target separator of the target boiler.

4. The method for controlling the feeding of circulating fluidized bed boiler furnace based on intelligent sensing according to claim 1 is characterized in that: include: The predetermined feeding control mechanism includes a feeder control mechanism and a biomass fuel control mechanism; Obtaining a first optimal feeding strategy of the double screw feeder according to the feeder control mechanism; In combination with the first optimal feeding strategy, a second optimal feeding strategy is obtained according to the biomass fuel regulation mechanism; The first optimal feeding strategy and the second optimal feeding strategy constitute the target feeding strategy.

5. The method for controlling the feeding of circulating fluidized bed boiler furnace based on intelligent sensing according to claim 4 is characterized in that: include: Acquire a control index set of the double screw feeder, wherein each control index in the control index set has a predetermined index threshold, so as to form a first feeding control space; Obtaining a first feeding strategy in the first feeding control space; Traversing the first feeding strategy in the feeding database to obtain a first most similar feeding strategy, and obtaining a first most similar feeding record where the first most similar feeding strategy is located; When the first combustion efficiency in the first most similar feeding record reaches a predetermined combustion efficiency, the first feeding strategy is used as the first optimal feeding strategy.

6. The method for controlling the feeding of circulating fluidized bed boiler furnace based on intelligent sensing according to claim 5 is characterized in that: The control index set includes feed rate, bed temperature and bed pressure.

7. The method for controlling the feeding of circulating fluidized bed boiler furnace based on intelligent sensing according to claim 6 is characterized in that: include: Forming a second feedstock control space according to the biomass fuel control mechanism, and using the second feedstock control space as an optimization space; Using the first optimal feeding strategy as an optimization constraint; Combustion efficiency is used as the optimization evaluation index; The second optimal feeding strategy is obtained by performing global optimization in the optimization space based on the optimization evaluation index and under the optimization constraints by utilizing the taboo search principle.

8. A circulating fluidized bed boiler furnace feeding control device based on intelligent sensing, characterized in that: The circulating fluidized bed boiler furnace feeding control device based on intelligent sensing is used to execute the circulating fluidized bed boiler furnace feeding control method based on intelligent sensing as claimed in any one of claims 1 to 7, and the circulating fluidized bed boiler furnace feeding control device based on intelligent sensing includes: The overall support platform of the double screw feeder, wherein the overall support platform of the double screw feeder comprises a support platform; A variable diameter and variable pitch double screw feeder, wherein the variable diameter and variable pitch double screw feeder is fixed on the supporting platform; A blanking pipe expansion joint, wherein the blanking pipe expansion joint is arranged at the lower end of the feed port of the variable diameter and variable pitch double screw feeder; An emergency pneumatic shut-off door, wherein the emergency pneumatic shut-off door is arranged at the upper end of the feed port of the variable diameter and variable pitch double screw feeder and is centrally aligned with the drop pipe expansion joint; An air-cooled sealing sleeve, wherein a first end of the air-cooled sealing sleeve is fixedly connected to a discharge port of the variable-diameter and variable-pitch double-screw feeder, and a second end of the air-cooled sealing sleeve is fixedly connected to a uniform feeding sleeve; A uniform feeding sleeve, wherein the uniform feeding sleeve is fixedly connected to the second end of the air-cooled sealing sleeve; A material throwing pulse valve, wherein the material throwing pulse valve is fixed on the bottom of the uniform feeding sleeve.

9. The circulating fluidized bed boiler furnace feeding control device based on intelligent sensing according to claim 8 is characterized in that: The overall support platform of the double-screw feeder also includes a spring hanger, the variable diameter and variable pitch double-screw feeder includes a screw shaft, a variable frequency speed regulating motor and a driving reducer, the air-cooled sealing sleeve includes an inner wall, an outer wall, an annular cavity, a gas channel, an air inlet pipe and an adjusting damper, and the throwing pulse valve includes a main air duct, a bypass air duct, a main rotary valve and a bypass damper.

Images