Flue gas oxygen content measurement and air leakage prevention interference system and method for thermal power plant and electronic equipment

Abstract

The application relates to the technical field of environmental protection monitoring of thermal power plants, in particular to a flue gas oxygen content measurement and air leakage prevention interference system and method for a thermal power plant and electronic equipment, wherein the system comprises: a dynamic variable-diameter system arranged in a chimney or a flue; a main oxygen content measurement unit arranged in a flue area and used for detecting the oxygen content value of flue gas; and a data processing and control unit, which is in communication connection with the dynamic variable-diameter system and the main oxygen content measurement unit, respectively, and is used for generating a caliber adjustment signal of the dynamic variable-diameter system based on a boiler load or a flue gas flow signal to adjust the caliber, and inputting the oxygen content value into a pre-pretrained correction model to output a corrected oxygen content value used for pollution conversion. Thus, the problems that in the related art, due to low efficiency of artificial searching and plugging of air leakage points, the flow field characteristics under low load cannot be fundamentally solved, the pollution conversion data deviates, and environmental protection pressure is brought to enterprises and the like are solved.

Description

Technical Field

[0001] This application relates to the field of environmental monitoring technology for thermal power plants, and in particular to a system, method and electronic equipment for measuring oxygen content in flue gas and preventing air leakage interference in thermal power plants. Background Technology

[0002] Currently, thermal power plants frequently participate in deep peak shaving of the power grid, resulting in units operating under low-load conditions for extended periods. Under these conditions, the boiler flue gas flow rate is significantly reduced, leading to increased negative pressure inside the flue and chimney. This makes it easy for cold air to be drawn in from leaky areas such as flanges, welds, and expansion joints, resulting in "air leakage." Oxygen measurement probes used for environmental calculations are typically fixed at the chimney outlet or a specific location. The leaked cold air dilutes the flue gas, distorting the oxygen measurement value and thus amplifying the calculated pollutant concentration several times over, creating "false exceedances" and placing enormous environmental pressure on enterprises.

[0003] Among the related technologies, methods such as manually sealing air leaks, optimizing the location and structure of hardware oxygen measurement, employing soft measurement and intelligent algorithms, and using signal processing and correction compensation are used to address interference issues from the perspective of air leak control or measurement optimization.

[0004] However, in related technologies, manual locating and sealing of air leaks is inefficient, and hardware measurements are significantly affected by installation location and flow field changes. Soft measurement models also have insufficient adaptability and limited anti-interference capabilities, making it impossible to fundamentally solve the flow field characteristics problem under low load. Consequently, the measurement distortion problem under low load cannot be effectively solved, resulting in deviations in pollutant conversion data and placing enormous environmental pressure on enterprises, which urgently needs improvement.

[0005] Application content This application provides a system, method, and electronic device for measuring oxygen content in flue gas of thermal power plants and preventing air leakage interference. This addresses the problems in related technologies, such as the inefficiency of manually locating and sealing air leaks, which makes it impossible to completely solve the flow field characteristics problem under low load, thus failing to effectively solve the measurement distortion problem under low load, resulting in deviations in pollutant conversion data and bringing huge environmental pressure to enterprises.

[0006] The first aspect of this application provides a flue gas oxygen measurement and anti-leakage interference system for thermal power plants, comprising: a dynamic diameter adjustment system installed in a chimney or flue; a main oxygen measurement unit installed in the flue area for detecting the oxygen value of the flue gas; and a data processing and control unit, wherein the data processing and control unit is communicatively connected to the dynamic diameter adjustment system and the main oxygen measurement unit, and the data processing and control unit is used to generate a diameter adjustment signal for the dynamic diameter adjustment system based on boiler load or flue gas flow signal to adjust the diameter, and input the oxygen value into a pre-trained calibration model to output a calibrated oxygen value for pollutant conversion.

[0007] Through the aforementioned technical means, the embodiments of this application can dynamically adjust the flue diameter based on boiler load or flue gas flow through the coordinated operation of the dynamic diameter adjustment system, the main oxygen measurement unit, and the data processing control unit. The measured oxygen value is processed using a pre-trained correction model, thereby adapting to changes in boiler load, actively suppressing the impact of air leakage, and calculating the true oxygen content using the correction model. This ensures that the pollutant conversion data is true and accurate, thereby improving the economic efficiency and operational flexibility of the power plant.

[0008] Optionally, in one embodiment of this application, it further includes: an auxiliary oxygen measurement array, the auxiliary oxygen measurement array including at least two auxiliary oxygen sensors disposed at different positions downstream of the dynamic diameter change system, the at least two auxiliary oxygen sensors collecting auxiliary oxygen data.

[0009] Through the above-mentioned technical means, the embodiments of this application can use auxiliary oxygen sensors arranged in multiple locations to capture oxygen distribution information on the cross-section of the flue, enabling the system to sense the oxygen concentration gradient caused by local air leakage or uneven flow field, providing key spatial distribution data for subsequent accurate identification and quantification of air leakage interference.

[0010] Optionally, in one embodiment of this application, the data processing and control unit is further configured to calculate the oxygen distribution gradient based on the auxiliary oxygen data and obtain the real-time operating parameters of the boiler, so as to input the oxygen distribution gradient, the real-time operating parameters and the oxygen value into the pre-trained correction model, wherein the real-time operating parameters include total air volume, fuel volume, and the ratio of primary air volume to secondary air volume.

[0011] Through the above-mentioned technical means, the embodiments of this application can combine the oxygen distribution gradient calculated from the auxiliary oxygen data, as well as real-time operating parameters such as total air volume and fuel quantity, and input them together with the measured value of the main oxygen into the calibration model. Through multi-dimensional data fusion, the anti-interference ability and operating condition adaptability of the calibration model are significantly improved, so that the output calibration oxygen value is closer to the actual combustion state than the reading of any single sensor, thus fundamentally solving the problem of "false exceedance".

[0012] Optionally, in one embodiment of this application, the dynamic diameter-changing system is a venturi tube structure, with a movable conical plug or an adjustable guide vane provided at the throat diameter.

[0013] Through the above-mentioned technical means, the embodiments of this application can adopt a venturi tube structure design for a dynamic variable diameter system. The flow can be adjusted by a movable conical plug or an adjustable guide vane at the throat, thereby achieving precise control of the flue gas velocity, further optimizing the negative pressure state of the flue, effectively suppressing air leakage, and reducing the interference of flow field fluctuations on oxygen measurement.

[0014] Optionally, in one embodiment of this application, the dynamic diameter adjustment system is specifically used to determine a diameter reduction value based on the diameter adjustment signal for adjustment when the boiler load is lower than a first preset threshold; and to determine a diameter expansion value based on the diameter adjustment signal for adjustment when the boiler load is higher than a second preset threshold.

[0015] Through the above-mentioned technical means, the embodiments of this application can achieve differentiated diameter adjustment according to the boiler load threshold. At low load, the diameter is reduced to increase flow velocity, enhance dynamic pressure, and suppress air leakage in the rear flue. At high load, the diameter is expanded to reduce resistance. Thus, the system can automatically identify low-load high-risk operating conditions and improve the flow field and suppress air leakage by dynamically changing the diameter, ensuring the stable operation and measurement accuracy of the system under different operating conditions.

[0016] Optionally, in one embodiment of this application, the main oxygen measurement unit has a multi-point matrix sampling probe with full-process heating, and the sampling holes of the multi-point matrix sampling probe are arranged facing the flue gas flow direction.

[0017] Through the above-mentioned technical means, the embodiments of this application can sample from different depths through a multi-point matrix design, eliminate sampling deviations caused by uneven flue gas flow field, prevent data distortion caused by flue gas condensation or component adsorption through full-process heating function, and ensure that the original flue gas is collected without interference by designing the sampling holes to face the incoming flow direction, thereby enhancing the sampling authenticity and reducing dust blockage, thereby further improving the reliability and authenticity of the main oxygen measurement data and providing a high-quality input data source for the calibration model.

[0018] A second aspect of this application provides a method for calculating flue gas pollutants, comprising the following steps: acquiring the boiler load or flue gas flow signal; generating a caliber adjustment signal based on the boiler load or flue gas flow signal to adjust the caliber, detecting the oxygen content of the flue gas, and inputting the oxygen content value into a pre-trained calibration model to output a calibrated oxygen content value for pollutant calculation.

[0019] Through the aforementioned technical means, the embodiments of this application can dynamically adjust the flue diameter based on boiler load or flue gas flow through the coordinated operation of the dynamic diameter adjustment system, the main oxygen measurement unit, and the data processing control unit. The measured oxygen value is processed using a pre-trained correction model, thereby adapting to changes in boiler load, actively suppressing the impact of air leakage, and calculating the true oxygen content using the correction model. This ensures that the pollutant conversion data is true and accurate, thereby improving the economic efficiency and operational flexibility of the power plant.

[0020] Optionally, in one embodiment of this application, it further includes: collecting auxiliary oxygen data.

[0021] Through the above-mentioned technical means, the embodiments of this application can capture oxygen distribution information on the cross-section of the flue, enabling the system to sense the oxygen concentration gradient caused by local air leakage or uneven flow field, providing key spatial distribution data for subsequent accurate identification and quantification of air leakage interference.

[0022] Optionally, in one embodiment of this application, the step of generating a caliber adjustment signal based on the boiler load or flue gas flow signal to adjust the caliber, detecting the oxygen content value of the flue gas, and inputting the oxygen content value into a pre-trained calibration model to output a calibrated oxygen content value for pollutant conversion further includes: calculating the oxygen distribution gradient based on the auxiliary oxygen content data, and obtaining the real-time operating parameters of the boiler, so as to input the oxygen distribution gradient, the real-time operating parameters, and the oxygen content value into the pre-trained calibration model, wherein the real-time operating parameters include total air volume, fuel volume, and the ratio of primary air volume to secondary air volume.

[0023] Through the above-mentioned technical means, the embodiments of this application can combine the oxygen distribution gradient calculated by auxiliary oxygen data, as well as real-time operating parameters such as total air volume and fuel volume, and input them together with the measured value of main oxygen into the correction model. Through multi-dimensional data fusion, the anti-interference ability and working condition adaptability of the correction model are significantly improved, so that the output corrected oxygen value is closer to the actual combustion state, fundamentally solving the problem of "false excess".

[0024] Optionally, in one embodiment of this application, the method further includes: when the boiler load is lower than a first preset threshold, determining a diameter reduction value based on the diameter adjustment signal for adjustment; and when the boiler load is higher than a second preset threshold, determining a diameter expansion value based on the diameter adjustment signal for adjustment.

[0025] Through the above-mentioned technical means, the embodiments of this application can achieve differentiated diameter adjustment according to the boiler load threshold. At low load, the diameter is reduced to increase flow velocity, enhance dynamic pressure, and suppress air leakage in the rear flue. At high load, the diameter is expanded to reduce resistance. Thus, the system can automatically identify low-load high-risk operating conditions and improve the flow field and suppress air leakage by dynamically changing the diameter, ensuring the stable operation and measurement accuracy of the system under different operating conditions.

[0026] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the flue gas pollutant conversion method as described in the above embodiments.

[0027] A fourth aspect of this application provides a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described flue gas pollutant conversion method.

[0028] A fifth aspect of this application provides a computer program product that stores a computer program that, when executed by a processor, implements the above-described method for calculating flue gas pollutants.

[0029] This application embodiment utilizes a dynamic diameter adjustment system, a main oxygen measurement unit, and a data processing and control unit to dynamically adjust the flue gas duct diameter based on boiler load or flue gas flow. It then uses a pre-trained calibration model to process the measured oxygen value, thereby adapting to boiler load changes, actively suppressing the impact of air leakage, and calculating the true oxygen content using the calibration model. This ensures the accuracy and reliability of pollutant conversion data, improving the power plant's economy and operational flexibility. This solves the problems in related technologies where the inefficiency of manually locating and sealing air leaks leads to the inability to fundamentally address flow field characteristics under low loads, resulting in measurement distortion and causing deviations in pollutant conversion data, placing significant environmental pressure on enterprises.

[0030] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0031] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a schematic diagram of a flue gas oxygen measurement and anti-leakage interference system for thermal power plants provided according to an embodiment of this application; Figure 2 This is a schematic diagram of the overall system structure according to an embodiment of this application; Figure 3 This is a flowchart illustrating the training and workflow of an AI oxygenation correction model according to one embodiment of this application. Figure 4 This is a schematic diagram of the overall system structure and a flowchart of the workflow according to an embodiment of this application; Figure 5 This is a flowchart of a flue gas pollutant conversion method provided according to an embodiment of this application; Figure 6 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application.

[0032] Figure label: 10- Flue gas oxygen measurement and anti-leakage interference system for thermal power plants; 100- Dynamic diameter changing system; 200- Main oxygen measurement unit; 300- Data processing and control unit; 601- Memory; 602- Processor; 603- Communication interface. Detailed Implementation

[0033] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0034] The following description, with reference to the accompanying drawings, outlines an embodiment of a flue gas oxygen measurement and anti-leakage interference system, method, and electronic equipment for thermal power plants. Addressing the issues raised in the background section regarding the inefficiency of manually locating and sealing leaks, which fails to fundamentally resolve flow field characteristics under low load conditions and consequently hinders effective measurement distortion, leading to deviations in pollutant conversion data and placing significant environmental pressure on enterprises, this application provides a flue gas oxygen measurement and anti-leakage interference system for thermal power plants. This system utilizes a dynamic diameter adjustment system, a main oxygen measurement unit, and a data processing control unit to dynamically adjust the flue gas duct diameter based on boiler load or flue gas flow. A pre-trained calibration model is used to process the measured oxygen value, enabling adaptive adaptation to boiler load changes, proactive suppression of leak effects, and calculation of the true oxygen content using the calibration model. This ensures accurate and reliable pollutant conversion data, improving the economic efficiency and operational flexibility of the power plant. This solves the problems in related technologies, such as the inefficiency of manually locating and sealing air leaks, which makes it impossible to completely solve the flow field characteristics problem under low load, thus failing to effectively solve the measurement distortion problem under low load, resulting in deviations in pollutant conversion data and bringing huge environmental pressure to enterprises.

[0035] Specifically, Figure 1 This is a schematic diagram of the structure of the flue gas oxygen measurement and anti-leakage interference system for thermal power plants according to an embodiment of this application.

[0036] like Figure 1 As shown, the flue gas oxygen measurement and anti-leakage interference system 10 of the thermal power plant includes: a dynamic diameter changing system 100, a main oxygen measurement unit 200, and a data processing and control unit 300.

[0037] Among them, the dynamic diameter changing system 100 is installed in the chimney or flue.

[0038] It is understood that the dynamic diameter changing system 100 in this application embodiment can be understood as a device that can dynamically adjust the internal flow diameter according to changes in operating conditions, used to optimize flue gas flow field parameters, and can suppress air leakage by changing flue gas velocity and pressure.

[0039] In actual implementation, the embodiments of this application can be installed in a chimney or flue, and its flow diameter can be adjusted according to the boiler load or flue gas flow signal. The dynamic diameter adjustment system 100 can adjust the effective flow area of ​​its internal channel in real time by receiving the diameter adjustment signal from the data processing and control unit 300.

[0040] The embodiments of this application can dynamically adjust the flue gas flow diameter to change the flue gas velocity and pressure distribution, effectively increasing the flue gas dynamic pressure in the flue under low load, thereby suppressing the problem of cold air leakage caused by increased negative pressure, and creating a stable flow field environment for accurate measurement from a physical perspective.

[0041] Optionally, in one embodiment of this application, the dynamic diameter changing system 100 is a venturi tube structure, and the throat diameter is provided with a movable conical plug or an adjustable guide vane.

[0042] It is understood that the Venturi tube structure in this application embodiment can be understood as a throttling flow field adjustment structure designed based on the Venturi effect. Its throat is the key area for flow field control, and the movable conical plug or adjustable guide vane is the core component for achieving precise diameter changes, which can improve the stability of flow field adjustment.

[0043] For example, in this embodiment, the dynamic diameter adjustment system 100 can be a venturi tube structure, where the throat diameter is adjusted by a movable conical plug or an adjustable guide vane. The actuator precisely controls the forward and backward displacement of the conical plug or the opening and closing angle of the guide vane. For instance, when a diameter adjustment signal is received from the data processing and control unit 300 indicating that a diameter reduction is needed, the conical plug is driven to move towards the center of the throat, reducing the effective flow area; conversely, it moves backward, expanding the effective flow area.

[0044] The embodiments of this application can adopt a venturi tube structure to design a dynamic variable diameter system 100. The flow can be adjusted by a movable conical plug or an adjustable guide vane at the throat, thereby achieving precise control of the flue gas velocity, further optimizing the negative pressure state of the flue, effectively suppressing air leakage, and reducing the interference of flow field fluctuations on oxygen measurement.

[0045] Optionally, in one embodiment of this application, the dynamic diameter adjustment system 100 is specifically used to determine a diameter reduction value based on a diameter adjustment signal for adjustment when the boiler load is lower than a first preset threshold; and to determine a diameter expansion value based on a diameter adjustment signal for adjustment when the boiler load is higher than a second preset threshold.

[0046] It is understood that the first preset threshold and the second preset threshold in the embodiments of this application can be understood as critical values ​​set according to the rated load of the unit, the flow field characteristics and the leakage control requirements. For example, the first threshold can be 30% of the rated load and the second threshold can be 70% of the rated load. It should be noted that the first preset threshold and the second preset threshold can be set by those skilled in the art according to the actual situation, and no specific restrictions are made here.

[0047] In actual implementation, the flow diameter of the dynamic variable diameter system 100 in this embodiment can be infinitely or steppedly adjusted according to the boiler load signal. At low loads, the diameter is reduced to increase flow velocity, enhance dynamic pressure, and suppress air leakage in the rear flue; at high loads, the diameter is expanded to reduce resistance. When the boiler load is below a first preset threshold, the diameter is reduced to increase flue gas velocity; when the boiler load is above a second preset threshold, the diameter is expanded to reduce flue resistance. The system can automatically identify load changes and adjust its operating strategy, achieving a leap from "passive leak sealing" to "active immunity."

[0048] The embodiments of this application can achieve differentiated diameter adjustment according to the boiler load threshold. At low load, it can effectively suppress air leakage caused by excessive negative pressure, and at high load, it can ensure smooth flow field. Thus, the system can automatically identify low load high risk conditions and improve the flow field and suppress air leakage by dynamically changing the diameter, so as to ensure the stable operation and measurement accuracy of the system under different operating conditions.

[0049] The main oxygen measurement unit 200, located in the flue area, is used to detect the oxygen content of the flue gas.

[0050] It is understood that the main oxygen measurement unit 200 in this embodiment can be understood as an oxygen detection component, the core of which can be an oxygen sensor, such as a zirconia sensor, used to convert the oxygen concentration in the flue gas into a transmittable electrical signal, providing the raw input for subsequent data correction.

[0051] In actual implementation, the main oxygen measurement unit 200 in this embodiment can be located in the flue area upstream of the dynamic diameter changing system 100, and can be used to measure the first oxygen value. The main oxygen measurement unit 200 can continuously extract or measure flue gas samples in situ through the oxygen sensor probe, convert the oxygen concentration in the flue gas into a standard electrical signal, and transmit it to the data processing and control unit 300 for subsequent analysis.

[0052] The embodiments of this application can collect raw data of flue gas oxygen in real time and continuously, providing a timely input data source for the calibration model, ensuring the continuity and integrity of data transmission, and laying the foundation for subsequent accurate calibration.

[0053] Optionally, in one embodiment of this application, the main oxygen measurement unit 200 has a multi-point matrix sampling probe with full-process heating, and the sampling holes of the multi-point matrix sampling probe are arranged facing the flue gas flow direction.

[0054] It is understood that the multi-point matrix sampling probe in this application embodiment can be understood as a detection component with multiple sampling holes arranged in a matrix distribution to cover different cross-sectional positions of the flue; the full-process heating function can be used to maintain the probe temperature above the flue gas dew point; the sampling holes facing the incoming flow direction can ensure the collection of undisturbed original flue gas.

[0055] For example, in the embodiments of this application, the sampling holes can be aligned with the flue gas flow direction during probe installation. This allows the kinetic energy of the flue gas itself to be utilized, improving sampling efficiency and providing a self-cleaning effect. The matrix-distributed sampling holes simultaneously collect flue gas samples from different cross-sections and locations of the flue, and output a comprehensive average oxygen signal. The full-process heating device can achieve constant temperature control through electric heating, maintaining the probe temperature above the flue gas dew point and preventing moisture condensation or adsorption of corrosive components.

[0056] This application embodiment can sample from different depths through a multi-point matrix design, eliminating sampling deviations caused by uneven flue gas flow fields. The full-process heating function prevents data distortion caused by flue gas condensation or component adsorption. By designing the sampling holes to face the incoming flow direction, it can ensure that the original flue gas that has not been disturbed is collected, enhancing the authenticity of sampling and reducing dust blockage, thereby further improving the reliability and authenticity of the main oxygen measurement data and providing a high-quality input data source for the calibration model.

[0057] The data processing and control unit 300 is communicatively connected to the dynamic diameter changing system 100 and the main oxygen measurement unit 200. The data processing and control unit 300 is used to generate a diameter adjustment signal for the dynamic diameter changing system 100 based on the boiler load or flue gas flow signal to adjust the diameter, and input the oxygen value into a pre-trained correction model to output a corrected oxygen value for pollutant conversion.

[0058] It is understood that, in the embodiments of this application, the pollutant conversion can be calculated by using the formula C = C_actual * (21 - baseline oxygen content) / (21 - O2_actual).

[0059] In actual implementation, the embodiments of this application can receive data from all sensors and the boiler DCS (Distributed Control System), identify the current operating condition based on the boiler load or flue gas flow signal (e.g., determine whether it is in a low load state that is prone to air leakage), generate a diameter adjustment signal for the dynamic diameter system 100 based on the current operating condition, drive the dynamic diameter system 100 to act, adjust the diameter, and input the oxygen value into the pre-trained correction model to output a corrected oxygen value for pollutant conversion.

[0060] Specifically, the pre-trained calibration model can be obtained by training the boiler with historical data during a preset high-load stable operating condition using a machine learning algorithm. The main oxygen quantity measurement value in the historical data is used as the training label. The machine learning algorithm can be one of random forest, gradient boosting decision tree, or neural network.

[0061] The embodiments of this application can physically improve the flow field and suppress air leakage by generating an aperture adjustment signal, and eliminate air leakage interference from the data through upstream sampling and correction models, forming a dual guarantee to achieve adaptive adjustment of operating conditions, effectively avoid "false exceedances" of pollutant conversion concentrations, reduce environmental assessment pressure and unnecessary treatment costs for enterprises, and at the same time ensure the authenticity and authority of environmental monitoring data.

[0062] Optionally, in one embodiment of this application, the flue gas oxygen measurement and anti-leakage interference system 10 for thermal power plants further includes: an auxiliary oxygen measurement array, which includes at least two auxiliary oxygen sensors disposed at different positions downstream of the dynamic diameter change system 100, and the at least two auxiliary oxygen sensors collect auxiliary oxygen data.

[0063] It is understood that the auxiliary oxygen sensor in this embodiment can be used to collect oxygen data at different locations to supplement the limited cross-sectional coverage of the main measurement unit.

[0064] In practical implementation, this embodiment of the application can install auxiliary oxygen sensors at multiple different height positions downstream of the dynamic diameter changing system 100 to monitor the oxygen distribution after the flue gas mixes with any leaking cold air. The auxiliary oxygen measurement array includes at least two auxiliary oxygen sensors positioned at different locations downstream of the dynamic diameter changing system 100. The input features of the calibration model include at least a first oxygen value and auxiliary oxygen data from the auxiliary oxygen measurement array.

[0065] This application embodiment can utilize auxiliary oxygen sensors arranged in multiple locations to capture oxygen distribution information on the cross-section of the flue, enabling the system to sense the oxygen concentration gradient caused by local air leakage or uneven flow field, providing key spatial distribution data for subsequent accurate identification and quantification of air leakage interference.

[0066] Optionally, in one embodiment of this application, the data processing and control unit 300 is further configured to calculate the oxygen distribution gradient based on the auxiliary oxygen data and obtain the real-time operating parameters of the boiler, so as to input the oxygen distribution gradient, the real-time operating parameters and the oxygen value into a pre-trained calibration model, wherein the real-time operating parameters include the total air volume, the fuel volume, and the ratio of the primary air volume to the secondary air volume.

[0067] It is understood that the oxygen distribution gradient in this embodiment can be understood as a quantitative index calculated based on the measurement values ​​of the auxiliary oxygen measurement array at different spatial locations in the flue, reflecting the degree of difference in oxygen concentration in different areas of the flue cross section; the real-time operating parameters of the boiler can be understood as core indicators reflecting the combustion conditions, among which the total air volume and fuel volume can represent the oxygen consumption requirements of the combustion reaction, and the ratio of primary air volume to secondary air volume can affect the combustion completeness.

[0068] In actual implementation, this application embodiment can use auxiliary oxygen data and the installation coordinates of the sensors to calculate the ratio of the oxygen difference between adjacent sensors to the physical distance using a spatial difference algorithm, thereby obtaining the oxygen distribution gradient of the flue section. The boiler DCS system can then acquire real-time operating parameters such as total air volume, fuel volume, and the ratio of primary air volume to secondary air volume, and obtain the boiler's real-time operating parameters. The oxygen distribution gradient, real-time operating parameters, and oxygen value are then input into a pre-trained calibration model. The real-time operating parameters include total air volume, fuel volume, and the ratio of primary air volume to secondary air volume.

[0069] Specifically, the calibration model can be trained using machine learning algorithms. Training data can be derived from historical power plant operating data, preferably during stable operating conditions with high load and high flow rate (where air leakage is negligible). During this stage, the primary oxygen measurement can be considered the "true oxygen level." The model's input features can include: primary oxygen value, readings from various points in the auxiliary oxygen array and their calculated spatial gradients, boiler load, total air volume, and fuel quantity. The learning objective of the calibration model is to establish a nonlinear mapping relationship between complex operating parameters and the "true oxygen level." After deployment and operation, the calibration model can infer the "calibrated oxygen level" under the current operating condition, stripped of air leakage effects, based on the same real-time input features. This value is sent to the environmental protection DCS system for pollutant conversion, thereby obtaining concentration data that accurately reflects emission levels.

[0070] The embodiments of this application can combine the oxygen distribution gradient calculated from the auxiliary oxygen data, as well as real-time operating parameters such as total air volume and fuel volume, and input them together with the measured value of the main oxygen into the calibration model. Through multi-dimensional data fusion, the anti-interference ability and operating condition adaptability of the calibration model are significantly improved, making the output calibrated oxygen value closer to the actual combustion state, fundamentally solving problems such as "false exceedance".

[0071] The following examples illustrate the implementation of this application on the chimney of a 660MW coal-fired power unit. First, during a major overhaul of the unit, the system is installed in a suitable vertical section from the desulfurization tower outlet to the chimney. Hardware installation: The dynamic diameter-changing system uses a Venturi tube structure, with the throat diameter adjusted via guide vanes driven by an electric actuator. The diameter variation range is 60% to 100% of the original chimney diameter. The main oxygen measurement unit uses a high-performance zirconium oxygen meter, with a multi-point matrix design using 316L stainless steel sampling probes, and is equipped with a 120℃ full-length heated pipeline and a condensate separator. Three similar oxygen sensors are installed in the auxiliary oxygen measurement array approximately 10 meters, 20 meters, and 30 meters after the diameter-changing device. All sensors are connected to the central data processing and control unit via shielded cables.

[0072] Furthermore, data from all stable operating periods with a load rate greater than 80% over the past year, totaling approximately 5000 hours, were collected to form a training dataset. The data underwent preprocessing including outlier removal and standardization. Using the primary oxygen quantity measurement as the label, and the primary oxygen quantity value, the three auxiliary oxygen quantity values, the maximum difference between auxiliary oxygen quantities (gradient), boiler load, total air volume, and coal feed rate as features, the GBDT (Gradient Boosted Decision Tree) algorithm from the Scikit-learn library was used for model training. After training, the model file was deployed to the industrial computer in the data processing and control unit.

[0073] Furthermore, the system monitors the boiler load in real time. When the load drops below 50%, the control unit instructs the dynamic diameter-reducing system to gradually reduce the diameter to a preset position (e.g., 75% of the original diameter). Simultaneously, data from the main and auxiliary oxygen sensors and boiler DCS parameters are collected in real time and fed into the AI ​​model. The AI ​​model outputs a corrected oxygen value per second, which is transmitted to the power plant's environmental protection DCS system via a communication module (e.g., ModbusTCP). The DCS system uses this corrected oxygen value to calculate the measured concentrations of particulate matter, SO2, and NOx. The results show that during low-load periods, the calculated concentrations no longer exhibit abnormal peaks, accurately reflecting the ultra-low emission operating status.

[0074] Specifically, it can be combined with Figures 2 to 4As shown, the working principle of the flue gas oxygen measurement and anti-leakage interference system of the thermal power plant embodiment in this application is described in detail with a specific embodiment.

[0075] like Figure 2 As shown, the embodiments of this application may include: a main oxygen measurement unit (upstream stable section) capturing "core flue gas", which can collect stable and representative core flue gas samples before the flue gas enters the dynamic diameter change system, providing basic data for subsequent measurements.

[0076] The dynamic variable diameter system, with an adjustable throat, can change the flue gas flow diameter by adjusting the throat structure, thereby optimizing the flue gas flow field and suppressing air leakage.

[0077] The auxiliary oxygen measurement array (downstream, monitoring oxygen distribution) contains multiple sensors that can be used to monitor the oxygen distribution across the flue gas cross section after the flue gas has been adjusted by the dynamic diameter adjustment system, providing multi-dimensional references for data correction.

[0078] like Figure 3 As shown in the embodiments of this application, the training phase includes: high-load historical data, data cleaning, feature engineering, model training, validation, and generation of the AI ​​correction model. The operation phase includes: real-time multi-source data, feature extraction, AI correction model, output of corrected oxygen value, and environmental protection conversion.

[0079] Specifically, during the training phase of the calibration model, historical operating data under high-load and stable conditions of the power plant can be collected first—the impact of air leakage is negligible under these conditions, and the data has reference value for "real oxygen content." The data is then cleaned and preprocessed, including outlier removal and range normalization. Feature engineering is then performed to extract key features such as main oxygen content, oxygen distribution gradient, and boiler operating parameters. The model is then trained using machine learning algorithms such as random forest, gradient boosting decision tree, or neural network. The trained model is then validated and evaluated. If the performance is not up to standard, the model training process is iteratively optimized. Once the model performance meets the standards, a deployable AI calibration model is generated.

[0080] During the inference phase of the calibration model, multi-source data such as main oxygen measurement values, auxiliary oxygen distribution data, and boiler operating parameters can be collected in real time. Feature extraction is performed on the real-time data, and its logic is consistent with the feature engineering in the offline phase. The AI ​​calibration model generated by offline training is loaded, and the model calculates the calibrated oxygen value after removing air leakage interference based on the input features. The calibrated oxygen value is used to convert the pollutant emission concentration of the environmental protection system to ensure that the conversion result truly reflects the actual emission level of the enterprise.

[0081] like Figure 4 As shown, the system flow is as follows: flue gas enters from the original flue, passes through the main oxygen measurement unit, the dynamic diameter change system, and the auxiliary oxygen measurement array in sequence, and is finally discharged from the emission port.

[0082] Specifically, the functions and collaboration logic of each module are as follows: the main oxygen measurement unit is used to collect "core flue gas" in the stable flow field region upstream of the dynamic diameter change system to provide basic measurement samples; the dynamic diameter change system is used to adjust the flow path diameter according to the load signal to optimize the flue gas flow field and suppress air leakage; the auxiliary oxygen measurement array is used to monitor the oxygen distribution gradient downstream to supplement the spatial distribution information of the flow field and oxygen; the control unit is used to integrate the control logic module and the preset algorithm module, coordinate hardware control and data operation, and drive the system to operate collaboratively.

[0083] In the data flow diagram, solid arrows represent hardware control signals (such as orifice adjustment commands and device status feedback), while dashed arrows represent data communication signals (such as main oxygen signal and auxiliary oxygen data transmission). The final output goal is to send the corrected oxygen value to the environmental protection DCS system via data communication to achieve accurate pollutant concentration conversion and ensure the authenticity and reliability of emission data.

[0084] The flue gas oxygen measurement and anti-leakage interference system for thermal power plants proposed in this application can dynamically adjust the flue diameter based on boiler load or flue gas flow through the coordinated operation of a dynamic diameter adjustment system, a main oxygen measurement unit, and a data processing and control unit. It then uses a pre-trained calibration model to process the measured oxygen value, thereby adapting to boiler load changes, actively suppressing the impact of air leakage, and calculating the true oxygen content using the calibration model. This ensures the accuracy and reliability of pollutant conversion data, improving the economic efficiency and operational flexibility of the power plant. This solves the problem in related technologies where the inefficiency of manually locating and sealing leaks leads to an inability to fundamentally address flow field characteristics under low loads, resulting in measurement distortion and causing deviations in pollutant conversion data, thus imposing significant environmental pressure on enterprises.

[0085] Next, the method for calculating flue gas pollutants according to the embodiments of this application is described with reference to the accompanying drawings.

[0086] Figure 5 This is a flowchart illustrating a method for calculating flue gas pollutants provided in an embodiment of this application.

[0087] like Figure 5 As shown, the method for converting flue gas pollutants includes the following steps: In step S501, the boiler load or flue gas flow signal is acquired.

[0088] In step S502, a diameter adjustment signal is generated based on the boiler load or flue gas flow signal to adjust the diameter, and the oxygen content of the flue gas is detected. The oxygen content is then input into a pre-trained calibration model to output a calibrated oxygen content for pollutant conversion.

[0089] Optionally, in one embodiment of this application, it further includes: collecting auxiliary oxygen data.

[0090] Optionally, in one embodiment of this application, a caliber adjustment signal is generated based on the boiler load or flue gas flow signal to adjust the caliber, and the oxygen content of the flue gas is detected. The oxygen content is then input into a pre-trained calibration model to output a calibrated oxygen content value for pollutant conversion. The method further includes: calculating the oxygen distribution gradient based on auxiliary oxygen content data, and obtaining the real-time operating parameters of the boiler, so as to input the oxygen distribution gradient, real-time operating parameters, and oxygen content value into the pre-trained calibration model. The real-time operating parameters include the total air volume, fuel volume, and the ratio of primary air volume to secondary air volume.

[0091] Optionally, in one embodiment of this application, the method further includes: when the boiler load is lower than a first preset threshold, determining a diameter reduction value based on a diameter adjustment signal for adjustment; and when the boiler load is higher than a second preset threshold, determining a diameter expansion value based on a diameter adjustment signal for adjustment.

[0092] It should be noted that the explanation of the above-mentioned embodiment of the flue gas oxygen measurement and anti-leakage interference system for thermal power plants also applies to the flue gas pollutant conversion method of this embodiment, and will not be repeated here.

[0093] The flue gas pollutant conversion method proposed in this application can dynamically adjust the flue diameter based on boiler load or flue gas flow rate, and use a pre-trained calibration model to process the measured oxygen value. This allows for adaptive adaptation to boiler load changes, proactive suppression of air leakage, and calculation of the true oxygen content using the calibration model, thereby ensuring the accuracy and reliability of the pollutant conversion data and improving the power plant's economic efficiency and operational flexibility. This solves the problem in related technologies where the inefficiency of manually locating and sealing air leaks leads to an inability to fundamentally address flow field characteristics under low loads, resulting in measurement distortion and causing deviations in pollutant conversion data, thus imposing significant environmental pressure on enterprises.

[0094] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.

[0095] When the processor 602 executes the program, it implements the flue gas pollutant conversion method provided in the above embodiments.

[0096] Furthermore, electronic devices also include: Communication interface 603 is used for communication between memory 601 and processor 602.

[0097] The memory 601 is used to store computer programs that can run on the processor 602.

[0098] The memory 601 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0099] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0100] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0101] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0102] This application also provides a non-volatile computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described method for calculating flue gas pollutants.

[0103] This application also provides a computer program product storing a computer program that, when executed by a processor, implements the above-described method for calculating flue gas pollutants.

[0104] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0105] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0106] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0107] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, system, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, system, or device). For the purposes of this specification, "computer-readable medium" can be any system that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, system, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic system), a portable computer disk drive (magnetic system), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic systems, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0108] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0109] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0110] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0111] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A system for measuring oxygen content in flue gas and preventing air leakage interference in thermal power plants, characterized in that, include: Dynamic diameter changing system installed in chimneys or flues; The main oxygen measurement unit, located in the flue area, is used to detect the oxygen content of the flue gas. The data processing and control unit is communicatively connected to the dynamic diameter changing system and the main oxygen measurement unit. The data processing and control unit is used to generate a diameter adjustment signal for the dynamic diameter changing system based on the boiler load or flue gas flow signal to adjust the diameter, and input the oxygen value into a pre-trained correction model to output a corrected oxygen value for pollutant conversion. The dynamic diameter changing system is a Venturi tube structure, and the throat diameter is provided with a movable conical plug or an adjustable guide vane. The dynamic diameter adjustment system is specifically used to determine the diameter reduction value according to the diameter adjustment signal for adjustment when the boiler load is lower than the first preset threshold. When the boiler load is higher than the second preset threshold, the diameter expansion value is determined according to the diameter adjustment signal for adjustment.

2. The system according to claim 1, characterized in that, Also includes: An auxiliary oxygen measurement array, comprising at least two auxiliary oxygen sensors disposed at different locations downstream of the dynamic diameter change system, wherein the at least two auxiliary oxygen sensors collect auxiliary oxygen data.

3. The system according to claim 2, characterized in that, The data processing and control unit is also used to calculate the oxygen distribution gradient based on the auxiliary oxygen data and obtain the real-time operating parameters of the boiler, so as to input the oxygen distribution gradient, the real-time operating parameters and the oxygen value into the pre-trained correction model, wherein the real-time operating parameters include total air volume, fuel volume and the ratio of primary air volume to secondary air volume.

4. The system according to claim 1, characterized in that, The main oxygen measurement unit has a multi-point matrix sampling probe with full-process heating, and the sampling holes of the multi-point matrix sampling probe are set facing the flue gas flow direction.

5. A method for calculating flue gas pollutants using the flue gas oxygen measurement and anti-leakage interference system for thermal power plants according to any one of claims 1-4, characterized in that, Includes the following steps: Obtain the boiler load or flue gas flow signal; A caliber adjustment signal is generated based on the boiler load or flue gas flow signal to adjust the caliber, and the oxygen content of the flue gas is detected. The oxygen content is then input into a pre-trained calibration model to output a calibrated oxygen content for pollutant conversion.

6. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, the processor executing the program to implement the flue gas pollutant conversion method as described in claim 5.

7. A non-volatile computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the flue gas pollutant conversion method as described in claim 5.

8. A computer program product, comprising a computer program, characterized in that, The computer program is executed to implement the flue gas pollutant conversion method as described in claim 5.

Images