A low-carbon coal-fired cogeneration system and method

Abstract

The present application belongs to the field of coal-fired cogeneration, and discloses a low-carbon coal-fired cogeneration system and method. The present application collects equipment operation state data, thermal power decoupling characteristic data and carbon emission monitoring data in real time, extracts power supply coal consumption characteristic values and thermal power ratio characteristic values, and then combines preset power supply coal consumption threshold values, preset thermal power ratio threshold values and corresponding allowable deviation threshold values to determine the low-carbon interval of the current operation condition, so as to realize online quantitative evaluation of the low-carbon operation state of the coal-fired cogeneration system and overcome the problem in the prior art that the low-carbon operation state of the coal-fired cogeneration system is mainly dependent on post-accounting, lacks real-time and accurate perception and quantitative determination basis.

Description

Technical Field

[0001] This invention belongs to the field of coal-fired cogeneration, specifically relating to a low-carbon coal-fired cogeneration system and method. Background Technology

[0002] Coal-fired combined heat and power (CHP) systems, as an important form of energy utilization that combines electricity and heat supply, can improve the overall efficiency of primary energy utilization through energy cascade utilization and are widely used in industrial heating, urban district heating, and regional integrated energy supply in my country. While CHP systems remain significant in ensuring a stable energy supply, they still face challenges such as high coal consumption, substantial carbon emissions, and complex and variable operating conditions. Therefore, how to further achieve energy conservation and carbon reduction while ensuring safe and stable heating and power supply has become an urgent technical problem to be solved in this field.

[0003] In existing technologies, the operational evaluation of coal-fired combined heat and power (CHP) systems typically focuses on traditional energy efficiency indicators such as coal consumption for power generation and thermal efficiency. Monitoring of carbon emissions largely relies on post-hoc statistics, empirical estimations, or periodic calculations, lacking the ability to acquire and accurately perceive carbon emission data in real time. Furthermore, existing technologies often lack quantitative criteria for characterizing whether a system is operating in a low-carbon state, making it difficult to establish a unified low-carbon operation evaluation mechanism that combines coal consumption for power generation, the heat-power coupling relationship, and carbon emission status. Therefore, it is impossible to promptly identify abnormal operating conditions with high carbon emissions or high coal consumption during operation.

[0004] Furthermore, existing technologies often analyze combustion, thermoelectric coupling, and carbon emission states in isolation during system optimization, lacking in-depth modeling of the coupling relationship between combustion conditions and carbon emission intensity. When the system experiences increased coal consumption or abnormal carbon emissions, troubleshooting usually still relies on manual experience, making it difficult to accurately identify key anomalies or further trace the specific equipment nodes causing the system's energy efficiency decline. Consequently, subsequent optimization measures lack specificity and data support.

[0005] Meanwhile, most of the optimization control methods in existing technologies rely on manual adjustment or offline analysis. The optimization strategies used are usually relatively static, making it difficult to dynamically generate control commands and execute them in a closed loop based on real-time operating data, thermal-electric decoupling data, and carbon emission data. Therefore, they are difficult to adapt to the complex operating scenarios of coal-fired cogeneration systems under different loads, different heating demands, and different environmental conditions. Summary of the Invention

[0006] The purpose of this invention is to overcome the lack of a technical solution in the prior art that can monitor the carbon emissions and energy consumption status of coal-fired cogeneration systems in real time, evaluate low carbon emissions, diagnose anomalies, trace equipment sources, and achieve closed-loop optimization control, and to provide a low-carbon coal-fired cogeneration system and method.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for low-carbon coal-fired cogeneration, comprising the following steps: Real-time data collection of equipment operating status, thermal-electric decoupling characteristics, and carbon emission monitoring data from coal-fired cogeneration systems; and preprocessing of the collected data. Feature extraction was performed based on preprocessed equipment operating status data, thermoelectric decoupling characteristic data, and carbon emission monitoring data to obtain characteristic values ​​of power supply coal consumption and heat-to-power ratio. The first difference between the characteristic value of coal consumption for power supply and the preset threshold for coal consumption for power supply, and the second difference between the characteristic value of heat-to-electricity ratio and the preset threshold for heat-to-electricity ratio are calculated respectively. Based on the characteristic value of coal consumption for power supply and the characteristic value of heat-to-electricity ratio, the deviation of coal consumption for power supply and the deviation of heat-to-electricity ratio are calculated respectively. The deviation of coal consumption for power supply is compared with the preset allowable deviation threshold for coal consumption for power supply, and the deviation of heat-to-electricity ratio is compared with the preset allowable deviation threshold for heat-to-electricity ratio. Based on the comparison results, it is determined whether the current operating condition is in the low-carbon operating range, and the evaluation result of low-carbon compliance or low-carbon warning is output. When the evaluation result is a low-carbon warning, the equipment operating status data, thermoelectric decoupling characteristic data and carbon emission monitoring data under the best historical low-carbon operating conditions are used as training samples to construct a multidimensional coupled correlation model with the deviation of power supply coal consumption and the deviation of heat-to-power ratio as input variables and carbon emission intensity as output variable. The deviation of power supply coal consumption and the deviation of heat-to-power ratio under the current operating conditions are input into the multidimensional coupled correlation model. The partial derivative values ​​of each input variable with respect to carbon emission intensity are calculated as the weights of the influencing factors. The key energy consumption anomalies that lead to increased carbon emissions are identified, and the operating condition diagnosis results are output. Based on the operating condition diagnosis results, the pre-stored system topology data is called to construct an energy flow topology network including the boiler combustion subsystem, the turbine power subsystem, and the heating and transmission subsystem. The energy flow process under the current operating condition is decoupled and analyzed, and the energy efficiency loss weight of each energy-consuming device is calculated in order to trace and locate the primary equipment node that causes the increase in coal consumption under the current operating condition. Based on the energy efficiency loss weight of the primary equipment node, a preset low-carbon optimization strategy model is invoked for analysis and identification of the corresponding optimization strategy type. When the strategy is identified as a combustion optimization strategy, control commands are generated to adjust the opening of the blower and the frequency of the coal feeder. When the strategy is identified as a thermal power load distribution strategy, control commands are generated to adjust the opening of the heating extraction steam regulating valve and the flow rate of the turbine speed regulating valve. The control commands are then output to the actuator to adjust the operating status of the current operating condition.

[0008] A further improvement of this invention lies in the following specific method for real-time acquisition of equipment operating status data, thermal-electric decoupling characteristic data, and carbon emission monitoring data of a coal-fired combined heat and power system, and for preprocessing the acquired data: Real-time acquisition of equipment operating status data, thermal-electric decoupling characteristic data, and carbon emission monitoring data of coal-fired cogeneration systems; The Laida criterion was used to identify and remove outliers in time series data of equipment operating status data, thermoelectric decoupling characteristic data and carbon emission monitoring data. The arithmetic mean of data at adjacent time points was used to linearly interpolate and fill in the data after outliers were removed. The physical quantities of different dimensions in the filled data are uniformly formatted and encoded, and the non-numerical switch quantities of the device start-stop status are converted into numerical matrices. The data matrix is ​​normalized using the min-max normalization method, which linearly maps the original data to the interval between 0 and 1.

[0009] A further improvement of this invention lies in the following method for extracting features based on preprocessed equipment operating status data, thermoelectric decoupling characteristic data, and carbon emission monitoring data to obtain the characteristic values ​​of coal consumption for power supply and the heat-to-power ratio: Preprocessed equipment operating status data, thermoelectric decoupling characteristic data, and carbon emission monitoring data were acquired and feature extracted to obtain boiler combustion efficiency, main steam pressure, and main steam temperature. The oxygen content of the flue gas, as well as the amount of steam extracted for heating, the back pressure heating power, and the turbine speed; Obtain boiler combustion efficiency, main steam pressure, and main steam temperature. Historical sample data on flue gas oxygen content were used to calculate boiler combustion efficiency, main steam pressure, and main steam temperature. The principal component contribution of oxygen content in flue gas is converted into corresponding weights. Based on boiler combustion efficiency, main steam pressure, and main steam temperature The weight of flue gas oxygen content is used to establish a power supply coal consumption characteristic value model using a weighted fitting method, and the power supply coal consumption characteristic value is calculated using the power supply coal consumption characteristic value model. The matching parameters of heat load and electrical load are obtained by calculating the ratio of the heat extraction steam volume, back pressure heating power and turbine speed, and are used as the characteristic value of the heat-to-power ratio.

[0010] A further improvement of the present invention is that the deviation of power supply coal consumption is the ratio of the difference between the characteristic value of power supply coal consumption and the preset threshold value of power supply coal consumption to the characteristic value of power supply coal consumption. The thermoelectric ratio deviation is the ratio of the difference between the thermoelectric ratio characteristic value and the preset thermoelectric ratio threshold to the thermoelectric ratio characteristic value; When the deviation of coal consumption for power supply is less than or equal to the preset allowable deviation threshold for coal consumption for power supply, and the deviation of the heat-to-power ratio is less than or equal to the preset allowable deviation threshold for the heat-to-power ratio, the current operating condition is determined to be in the low-carbon operating range and the evaluation result of low-carbon compliance is output. When the deviation of coal consumption for power supply exceeds the preset allowable deviation threshold, or the deviation of the heat-to-power ratio exceeds the preset allowable deviation threshold, the current operating condition is determined to be in a non-low-carbon operating range and a low-carbon warning evaluation result is output.

[0011] A further improvement of this invention is that the multidimensional coupling correlation model employs a multivariate nonlinear regression equation:

[0012] in, For the deviation of coal consumption for power supply, Thermoelectric ratio deviation, For carbon emission intensity, For constant terms, The coefficient of the linear term, The coefficient of the quadratic term, These are the interaction term coefficients; each coefficient is solved by fitting the historical training samples using the least squares method.

[0013] A further improvement of this invention is that when the key energy consumption anomaly is the deviation of power supply coal consumption, the deviation of the heat-to-power ratio is kept constant. The required power supply coal consumption correction value is calculated in reverse using a multi-dimensional coupled correlation model with a preset power supply coal consumption threshold as the target. Based on the power supply coal consumption correction value, the boiler combustion efficiency loss area is located, and the working condition diagnosis result of the deterioration of combustion conditions is output. When the key energy consumption anomaly is the deviation of the heat-to-power ratio, the deviation of the power supply coal consumption remains unchanged. The required adjustment parameters for the heating steam extraction volume are calculated in reverse using a multi-dimensional coupled correlation model with the preset heat-to-power ratio threshold as the target. Based on these adjustment parameters, the over-limit situation of the heat-to-power decoupling constraint boundary is judged, and the working condition diagnosis result of the heat-to-power matching imbalance is output.

[0014] A further improvement of the present invention is that when the working condition diagnosis result is that the combustion working condition is deteriorated, the main steam pressure, main steam temperature and flue gas oxygen content are obtained, and combined with the boiler energy efficiency benchmark model generated based on the historical best low carbon operating conditions, the exhaust heat loss, incomplete combustion heat loss and heat dissipation loss are calculated respectively. Calculate the proportion of each loss value to the total loss value as the loss contribution weight, and set the loss contribution weight as the energy efficiency loss weight; Identify the primary equipment node corresponding to the loss type with the largest energy efficiency loss weight, and trace its source to locate the primary equipment node causing the increase in coal consumption.

[0015] A further improvement of the present invention is that when the operating condition diagnosis result is thermoelectric mismatch, thermoelectric decoupling characteristic data is obtained, and the interstage enthalpy drop loss of the steam turbine and the heat transmission heat loss of the heating pipeline are calculated respectively. Calculate the proportion of each loss value to the total loss value as the loss contribution weight, and set the loss contribution weight as the energy efficiency loss weight; The equipment node with the largest energy efficiency loss weight is traced back to the primary equipment node causing the increase in coal consumption.

[0016] A further improvement of the present invention is that, when the combustion optimization strategy is identified, the deviation rate between the real-time energy efficiency loss weight and the preset standard weight is calculated, and the target air distribution correction coefficient is set to 1 minus the product of the deviation rate and the preset air volume response factor. The coal feed rate adjustment bias value is calculated based on the difference between the current coal feed rate, the measured value of flue gas oxygen content and the optimal oxygen content setting value, and the coal feed response coefficient. When a thermoelectric load allocation strategy is identified, the thermoelectric decoupling allocation coefficient is calculated based on the thermoelectric ratio deviation and the thermoelectric load response factor. Based on the target air distribution correction coefficient, coal feed rate adjustment bias value, or thermal-electric decoupling distribution coefficient, corresponding control commands are generated and output to the actuator.

[0017] Secondly, the present invention provides a low-carbon coal-fired cogeneration system, comprising: The data acquisition module is used to collect real-time equipment operation status data, thermal-electric decoupling characteristic data, and carbon emission monitoring data of the coal-fired cogeneration system, and to preprocess the collected data. The feature extraction module is used to extract features based on preprocessed equipment operating status data, thermoelectric decoupling characteristic data and carbon emission monitoring data to obtain power supply coal consumption feature value and heat-to-power ratio feature value. The low-carbon evaluation module is used to calculate the first difference between the characteristic value of coal consumption for power supply and the preset threshold value of coal consumption for power supply, and the second difference between the characteristic value of heat-to-electricity ratio and the preset threshold value of heat-to-electricity ratio. Based on the characteristic value of coal consumption for power supply and the characteristic value of heat-to-electricity ratio, the module calculates the deviation of coal consumption for power supply and the deviation of heat-to-electricity ratio, respectively. The module compares the deviation of coal consumption for power supply with the preset allowable deviation threshold value of coal consumption for power supply and the deviation of heat-to-electricity ratio with the preset allowable deviation threshold value of heat-to-electricity ratio. Based on the comparison results, the module determines whether the current operating condition is in the low-carbon operating range and outputs the evaluation results of low-carbon compliance or low-carbon warning. The correlation analysis module is used to construct a multidimensional coupled correlation model when the evaluation result is a low-carbon warning. It uses equipment operating status data, thermoelectric decoupling characteristic data, and carbon emission monitoring data under the best historical low-carbon operating conditions as training samples. The model has the deviation of power supply coal consumption and the deviation of heat-to-power ratio as input variables and carbon emission intensity as output variable. The deviation of power supply coal consumption and the deviation of heat-to-power ratio under the current operating conditions are input into the multidimensional coupled correlation model. The partial derivative values ​​of each input variable with respect to carbon emission intensity are calculated as the weights of the influencing factors. The key energy consumption anomalies that lead to increased carbon emissions are identified, and the operating condition diagnosis results are output. The energy efficiency traceability analysis module is used to construct an energy flow topology network that includes the boiler combustion subsystem, the turbine power subsystem, and the heating and transmission subsystem based on the operating condition diagnosis results and by calling the pre-stored system topology data. It performs decoupling analysis on the energy flow process under the current operating condition and calculates the energy efficiency loss weight of each energy-consuming device in order to trace and locate the primary equipment node that causes the increase in coal consumption under the current operating condition. The optimization decision module is used to analyze and identify the corresponding optimization strategy type by calling a preset low-carbon optimization strategy model based on the energy efficiency loss weight of the primary equipment node. When the strategy is identified as a combustion optimization strategy, control instructions are generated to adjust the opening of the blower and the frequency of the coal feeder. When the strategy is identified as a thermal power load distribution strategy, control instructions are generated to adjust the opening of the heating extraction steam regulating valve and the flow rate of the turbine speed regulating valve. The control instructions are then output to the actuator to adjust the operating status of the current operating condition.

[0018] Compared with the prior art, the present invention has the following beneficial effects: This invention collects real-time equipment operating status data, thermoelectric decoupling characteristic data, and carbon emission monitoring data, extracts characteristic values ​​of coal consumption for power supply and the heat-to-power ratio, and combines these with preset thresholds for coal consumption for power supply, preset thresholds for the heat-to-power ratio, and corresponding allowable deviation thresholds to determine the low-carbon range of the current operating conditions. This enables online quantitative evaluation of the low-carbon operating status of coal-fired cogeneration systems, overcoming the problems of existing technologies that mainly rely on post-event calculations and lack real-time accurate perception and quantitative judgment basis. When the evaluation result is a low-carbon warning, this invention constructs a multi-dimensional coupled correlation model with the deviation of coal consumption for power supply and the deviation of the heat-to-power ratio as input variables and carbon emission intensity as the output variable. By solving the partial derivative values ​​of each input variable with respect to carbon emission intensity as the weight of the influencing factors, it can identify key energy consumption anomalies that lead to increased carbon emissions, thereby revealing the inherent coupling relationship between coal consumption status, thermoelectric matching relationship, and carbon emission intensity. This overcomes the problem of existing technologies that can only analyze energy consumption indicators or emission indicators in isolation and are difficult to accurately identify the root causes of anomalies. This invention constructs an energy flow topology network based on pre-stored system topology data according to operational condition diagnostic results. It then decouples and analyzes the energy flow process under current operating conditions. By combining the energy efficiency loss weights of each energy-consuming device, it traces and locates the primary equipment node causing increased coal consumption. This allows for further analysis of anomalies down to specific equipment nodes or loss points, overcoming the limitations of existing technologies that rely heavily on manual experience for rough troubleshooting and struggle to accurately pinpoint the source of anomalies. This provides a clear basis for subsequent optimization. Furthermore, this invention uses the energy efficiency loss weights of primary equipment nodes to invoke a pre-set low-carbon optimization strategy model, identifies the corresponding optimization strategy type, and generates corresponding control commands to output to the actuators for online adjustment of the current operating conditions. This overcomes the limitations of existing optimization methods that rely on manual experience, have static strategies, and struggle to respond online to real-time operating conditions. This improves the real-time performance, intelligence, and adaptability of energy-saving and carbon-reduction control in coal-fired cogeneration systems. In summary, this invention can ensure the safe and stable operation of coal-fired cogeneration systems while enabling timely identification, accurate diagnosis, effective source tracing, and targeted optimization of high coal consumption and high carbon emission conditions, thereby achieving the comprehensive technical effect of reducing coal consumption, reducing carbon emissions, and improving energy utilization efficiency. Attached Figure Description

[0019] Figure 1 This is a flowchart of the present invention; Figure 2 This is a system diagram of the present invention. Detailed Implementation

[0020] To further understand the content of this invention, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments are merely illustrative and not limiting of the invention.

[0021] See Figure 1 A low-carbon coal-fired cogeneration method includes the following steps: S1 collects real-time data on equipment operating status, thermal-electric decoupling characteristics, and carbon emission monitoring data from coal-fired cogeneration systems, and preprocesses the collected data.

[0022] S2, based on the preprocessed equipment operating status data, thermoelectric decoupling characteristic data and carbon emission monitoring data, feature extraction is performed to obtain the characteristic values ​​of coal consumption for power supply and the characteristic value of heat-to-power ratio.

[0023] S3 calculates the first difference between the characteristic value of coal consumption for power supply and the preset threshold for coal consumption for power supply, and the second difference between the characteristic value of heat-to-electricity ratio and the preset threshold for heat-to-electricity ratio. Based on the characteristic value of coal consumption for power supply and the characteristic value of heat-to-electricity ratio, it calculates the deviation of coal consumption for power supply and the deviation of heat-to-electricity ratio. It compares the deviation of coal consumption for power supply with the preset allowable deviation threshold for coal consumption for power supply and the deviation of heat-to-electricity ratio with the preset allowable deviation threshold for heat-to-electricity ratio. Based on the comparison results, it determines whether the current operating condition is in the low-carbon operating range and outputs the evaluation result of low-carbon compliance or low-carbon early warning.

[0024] S4. When the evaluation result is a low-carbon warning, the equipment operating status data, thermoelectric decoupling characteristic data, and carbon emission monitoring data under the historical best low-carbon operating conditions are used as training samples to construct a multidimensional coupled correlation model with the deviation of power supply coal consumption and the deviation of thermoelectric ratio as input variables and carbon emission intensity as output variable. The deviation of power supply coal consumption and the deviation of thermoelectric ratio under the current operating conditions are input into the multidimensional coupled correlation model. The partial derivative values ​​of each input variable with respect to carbon emission intensity are solved as the weights of the influencing factors. The key energy consumption anomalies that lead to increased carbon emissions are identified, and the operating condition diagnosis results are output.

[0025] S5, based on the operating condition diagnosis results, calls the pre-stored system topology data to construct an energy flow topology network including the boiler combustion subsystem, the turbine power subsystem, and the heating and transmission subsystem. It performs decoupling analysis on the energy flow process under the current operating condition and calculates the energy efficiency loss weight of each energy-consuming device in order to trace and locate the primary equipment node that causes the increase in coal consumption under the current operating condition.

[0026] S6, based on the energy efficiency loss weight of the primary equipment node, calls the preset low-carbon optimization strategy model to analyze and identify the corresponding optimization strategy type. When identified as a combustion optimization strategy, it generates control instructions for adjusting the opening of the blower and the frequency of the coal feeder. When identified as a thermal power load distribution strategy, it generates control instructions for adjusting the opening of the heating extraction steam regulating valve and the flow rate of the turbine speed regulating valve. The control instructions are then output to the actuator to adjust the operating status of the current operating condition.

[0027] See Figure 2A low-carbon coal-fired cogeneration system, comprising: The data acquisition module is used to collect real-time equipment operation status data, thermal-electric decoupling characteristic data, and carbon emission monitoring data of the coal-fired cogeneration system, and to preprocess the collected data.

[0028] The feature extraction module is used to extract features based on preprocessed equipment operating status data, thermoelectric decoupling characteristic data, and carbon emission monitoring data to obtain power supply coal consumption feature values ​​and heat-to-power ratio feature values.

[0029] The low-carbon evaluation module is used to calculate the first difference between the characteristic value of coal consumption for power supply and the preset threshold value of coal consumption for power supply, and the second difference between the characteristic value of heat-to-electricity ratio and the preset threshold value of heat-to-electricity ratio. Based on the characteristic value of coal consumption for power supply and the characteristic value of heat-to-electricity ratio, the module calculates the deviation of coal consumption for power supply and the deviation of heat-to-electricity ratio, respectively. The module compares the deviation of coal consumption for power supply with the preset allowable deviation threshold value of coal consumption for power supply and the deviation of heat-to-electricity ratio with the preset allowable deviation threshold value of heat-to-electricity ratio. Based on the comparison results, the module determines whether the current operating condition is in the low-carbon operating range and outputs the evaluation results of low-carbon compliance or low-carbon warning.

[0030] The correlation analysis module is used to construct a multidimensional coupled correlation model when the evaluation result is a low-carbon warning. This model uses equipment operating status data, thermoelectric decoupling characteristic data, and carbon emission monitoring data under the best historical low-carbon operating conditions as training samples. The model takes the deviation of power supply coal consumption and the deviation of the thermoelectric ratio as input variables and the carbon emission intensity as output variables. The deviation of power supply coal consumption and the deviation of the thermoelectric ratio under the current operating conditions are input into the multidimensional coupled correlation model. The partial derivatives of each input variable with respect to the carbon emission intensity are calculated as the weights of the influencing factors. The model identifies the key energy consumption anomalies that lead to increased carbon emissions and outputs the operating condition diagnosis results.

[0031] The energy efficiency traceability analysis module is used to construct an energy flow topology network that includes the boiler combustion subsystem, the turbine power subsystem, and the heating and transmission subsystem based on the operating condition diagnosis results and by calling the pre-stored system topology data. It performs decoupling analysis on the energy flow process under the current operating condition and calculates the energy efficiency loss weight of each energy-consuming device in order to trace and locate the primary equipment node that causes the increase in coal consumption under the current operating condition.

[0032] The optimization decision module is used to analyze and identify the corresponding optimization strategy type by calling a preset low-carbon optimization strategy model based on the energy efficiency loss weight of the primary equipment node. When the strategy is identified as a combustion optimization strategy, control instructions are generated to adjust the opening of the blower and the frequency of the coal feeder. When the strategy is identified as a thermal power load distribution strategy, control instructions are generated to adjust the opening of the heating extraction steam regulating valve and the flow rate of the turbine speed regulating valve. The control instructions are then output to the actuator to adjust the operating status of the current operating condition.

[0033] Example 1: The specific method for real-time acquisition of equipment operating status data, heat and power decoupling characteristic data, and carbon emission monitoring data of coal-fired cogeneration systems, and the preprocessing of the acquired data, is as follows: S11 collects real-time data on equipment operating status, thermal-electric decoupling characteristics, and carbon emission monitoring data of coal-fired cogeneration systems.

[0034] S12 uses the Raida criterion to identify and remove outliers in the time series data of equipment operating status data, thermoelectric decoupling characteristic data, and carbon emission monitoring data. The arithmetic mean of adjacent time points is used to linearly interpolate and fill in the data after removing outliers.

[0035] S13, uniformly format and encode the physical quantities of different dimensions in the filled data, and convert the non-numerical switch quantities of the device start-stop status into numerical matrices.

[0036] S14 uses the min-max normalization method to normalize the data matrix, linearly mapping the original data to the interval between 0 and 1.

[0037] Specifically, during the operation of a coal-fired combined heat and power (CHP) unit, turbine speed, main steam pressure, main steam temperature, and boiler combustion efficiency are collected as equipment operating status data through a distributed sensor network and data communication interface. Heating extraction steam volume, back pressure heating power, and CHP decoupling constraint boundary are collected as CHP decoupling characteristic data. Flue gas oxygen content, carbon dioxide concentration, and real-time carbon emissions are collected as carbon emission monitoring data. After data collection, the Raida criterion is first used to identify outliers in each time series data. When any sampling point satisfies:

[0038] It was identified as an outlier; among which, This is the average value of the parameter over a preset sampling period. The standard deviation is denoted as . For outlier data after removal, linear interpolation is used to fill in the gaps using the arithmetic mean of data from adjacent time points, i.e.:

[0039] Data of different dimensions, such as pressure, temperature, flow rate, power, and concentration, are uniformly formatted and encoded, and non-numerical switch quantities such as equipment start-up and shutdown status are converted into numerical matrices. Finally, normalization is performed using the maximum-minimum standardization method.

[0040] This linearly maps the original data to the 0-1 interval, resulting in a standardized dataset that provides a unified input for subsequent feature extraction.

[0041] Example 2: The specific method for extracting feature values ​​for power supply coal consumption and heat-to-power ratio based on preprocessed equipment operating status data, thermoelectric decoupling characteristic data, and carbon emission monitoring data is as follows: S21, acquire preprocessed equipment operating status data, thermoelectric decoupling characteristic data, and carbon emission monitoring data for feature extraction, extracting boiler combustion efficiency, main steam pressure, and main steam temperature. The oxygen content of the flue gas, as well as the amount of steam extracted for heating, the back pressure heating power, and the turbine speed.

[0042] S22, obtain boiler combustion efficiency, main steam pressure, and main steam temperature. Historical sample data on flue gas oxygen content were used to calculate boiler combustion efficiency, main steam pressure, and main steam temperature. The principal component contribution of oxygen content in flue gas is converted into corresponding weights.

[0043] S23, based on boiler combustion efficiency, main steam pressure, and main steam temperature. The weight of oxygen content in flue gas is used to establish a characteristic value model of coal consumption for power supply using a weighted fitting method, and the characteristic value of coal consumption for power supply is calculated using the characteristic value model of coal consumption for power supply.

[0044] S24. The matching parameters of heat load and electrical load are obtained by ratio calculation based on the heat extraction steam volume, back pressure heating power and turbine speed, and are used as the characteristic value of heat-to-power ratio.

[0045] Specifically, boiler combustion efficiency, main steam pressure, main steam temperature, and flue gas oxygen content are extracted from the preprocessed standardized dataset. Historical sample data for each parameter are retrieved, and principal component analysis is used to calculate the principal component contribution of each parameter. These principal component contributions are then converted into corresponding weights, denoted as follows: , , and Based on this, a characteristic value model for coal consumption in power supply is established:

[0046] in, The characteristic value of coal consumption for power supply. The normalized boiler combustion efficiency, The normalized main steam pressure, The normalized main steam temperature. This represents the normalized oxygen content of the flue gas. Then, the steam extraction rate for heating is extracted. Back pressure heating power and turbine speed The matching parameters between heat load and electrical load are obtained through ratio calculation, and are used as characteristic values ​​of the heat-to-electricity ratio:

[0047] in, The preset reference power is used. Using the above method, the characteristic values ​​of power supply coal consumption (representing coal consumption level) and the characteristic value of thermoelectric ratio (representing thermoelectric coupling state) can be obtained respectively.

[0048] Example 3: The deviation of power supply coal consumption is the ratio of the difference between the characteristic value of power supply coal consumption and the preset threshold value of power supply coal consumption to the characteristic value of power supply coal consumption; the deviation of heat-to-electricity ratio is the ratio of the difference between the characteristic value of heat-to-electricity ratio and the preset threshold value of heat-to-electricity ratio to the characteristic value of heat-to-electricity ratio; when the deviation of power supply coal consumption is less than or equal to the preset allowable deviation threshold value of power supply coal consumption, and the deviation of heat-to-electricity ratio is less than or equal to the preset allowable deviation threshold value of heat-to-electricity ratio, the current operating condition is determined to be in the low-carbon operating range and a low-carbon compliance evaluation result is output; when the deviation of power supply coal consumption is greater than the preset allowable deviation threshold value of power supply coal consumption, or the deviation of heat-to-electricity ratio is greater than the preset allowable deviation threshold value of heat-to-electricity ratio, the current operating condition is determined to be in the non-low-carbon operating range and a low-carbon warning evaluation result is output.

[0049] Specifically, based on the extracted characteristic values ​​of coal consumption for power supply Thermoelectric ratio characteristic value Combined with preset coal consumption thresholds for power supply and preset thermoelectric ratio threshold Calculate the deviation of coal consumption for power supply Deviation from thermoelectric ratio :

[0050]

[0051] Subsequently, the deviation of coal consumption for power supply was measured. Deviation from the preset allowable threshold for coal consumption for power supply Compare and determine the deviation of the thermoelectric ratio. Deviation threshold from preset thermoelectric ratio Compare. When satisfied...

[0052] The system determines that the current operating condition is within the low-carbon operating range and outputs an evaluation result indicating compliance with low-carbon standards; when the conditions are met...

[0053] The system determines that the current operating condition is in a non-low-carbon operating range and outputs a low-carbon warning assessment result. By using the aforementioned relative deviation determination method, the influence of parameters with different dimensions on the assessment results can be eliminated, enabling a quantitative judgment of the low-carbon level of the current operating condition.

[0054] Example 4: Using historical data on equipment operating status under optimal low-carbon operating conditions, data on thermoelectric decoupling characteristics, and carbon emission monitoring data as training samples, a multivariate nonlinear regression equation was established using the least squares method:

[0055] in, For the deviation of coal consumption for power supply, Thermoelectric ratio deviation, For carbon emission intensity, For constant terms, , The coefficient of the linear term, , The coefficient of the quadratic term, These are the interaction term coefficients. Then, under the current operating conditions, the deviation of power supply coal consumption and the deviation of heat-to-power ratio are input into the model, and the effect of carbon emission intensity on these coefficients is calculated respectively. and Partial derivatives:

[0056]

[0057] By comparison

[0058] Identify the variables that currently have a greater impact on carbon emission intensity and recognize them as key energy consumption anomalies leading to increased carbon emissions. If the former is larger, then the deviation of coal consumption for power generation is identified as a key energy consumption anomaly; if the latter is larger, then the deviation of the heat-to-power ratio is identified as a key energy consumption anomaly.

[0059] Example 5: When the deviation of power supply coal consumption is identified as a key energy consumption anomaly, the deviation of the heat-to-power ratio is kept constant. The required power supply coal consumption correction value is obtained by reverse calculation using the multi-dimensional coupled correlation model with a preset power supply coal consumption threshold as the target. Based on this correction value and the distribution of boiler combustion efficiency, the boiler combustion efficiency loss area is located, thereby outputting the operational condition diagnosis result of combustion condition deterioration. When the deviation of the heat-to-power ratio is identified as a key energy consumption anomaly, the deviation of the power supply coal consumption remains unchanged, and the required adjustment parameters for the heating steam extraction amount are calculated in reverse using the multi-dimensional coupled correlation model with a preset heat-to-power ratio threshold as the target. Based on the adjustment parameters and the actual operating state of the thermoelectric decoupling constraint boundary, the system judges the over-limit situation and outputs the operating condition diagnosis result of thermoelectric mismatch. Through this implementation method, the abstract deviation anomaly can be directly mapped to a specific operating condition diagnosis conclusion.

[0060] Example 6: The main steam pressure, main steam temperature, and flue gas oxygen content are obtained. Combined with a boiler energy efficiency benchmark model generated based on historical best low-carbon operating conditions, the exhaust heat loss, incomplete combustion heat loss, and heat dissipation loss are calculated. Among these, the exhaust heat loss... It can be represented as:

[0061] in, The enthalpy value of boiler flue gas. This is the enthalpy value of cold air. Fuel consumption Heat is input into the boiler. Heat loss due to incomplete combustion. It can be represented as:

[0062] in, This refers to the volumetric carbon monoxide content in the flue gas. For dry flue gas volume, Let the heat generated by carbon monoxide be . Assume the heat loss is . The total loss is

[0063] The contribution weights for each loss are as follows:

[0064] The loss contribution weight is then directly set as the energy efficiency loss weight. Next, the equipment node corresponding to the loss type with the largest energy efficiency loss weight is identified, and its source is traced back to the primary equipment node causing the increase in coal consumption.

[0065] Example 7: Data on thermoelectric decoupling characteristics were obtained, and the interstage enthalpy drop loss of the steam turbine and the heat transfer loss of the heating network were calculated separately. The interstage enthalpy drop loss of the steam turbine was determined by the difference between the actual enthalpy drop and the ideal isentropic enthalpy drop of each stage; the heat transfer loss of the heating network was calculated separately. It can be represented as:

[0066] in, The enthalpy value at the pipeline inlet. The enthalpy value at the pipeline outlet. Let be the flow rate of the heating medium. Assume the interstage enthalpy drop loss of the turbine is... The total loss is

[0067] The contribution weights for each loss are as follows:

[0068]

[0069] The aforementioned loss contribution weights are then set as energy efficiency loss weights. Finally, the equipment node with the largest energy efficiency loss weight is traced and identified as the primary equipment node causing increased coal consumption, thereby achieving precise location of the source of thermal-electricity mismatch anomalies.

[0070] Example 8: Based on real-time energy efficiency loss weight Compared with preset standard weights Calculate the deviation rate:

[0071] Then, the target air distribution correction factor is set as follows:

[0072] in, The preset airflow response factor is used. Simultaneously, based on the current coal feed rate... Measured value of oxygen content in exhaust gas Optimal oxygen content setting value and coal feeding response coefficient Calculate the coal feed rate adjustment bias value:

[0073] Afterwards, based on and The corresponding air supply unit opening adjustment command and coal feeder frequency adjustment command are generated and output to the actuator. When a heat and power load allocation strategy is identified, the deviation of the heat and power ratio is used as the basis for the adjustment. With thermoelectric load response factor Calculate the thermo-electric decoupling distribution factor:

[0074] Then, based on the thermoelectric decoupling distribution coefficient, the opening adjustment command of the heating extraction steam regulating valve and the flow regulation command of the turbine speed regulating valve are generated and output to the actuator, thereby realizing online optimization control of the current operating conditions.

[0075] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for low-carbon coal-fired cogeneration, characterized in that, Includes the following steps: Real-time data collection of equipment operating status, thermal-electric decoupling characteristics, and carbon emission monitoring data from coal-fired cogeneration systems; and preprocessing of the collected data. Feature extraction was performed based on preprocessed equipment operating status data, thermoelectric decoupling characteristic data, and carbon emission monitoring data to obtain characteristic values ​​of power supply coal consumption and heat-to-power ratio. The first difference between the characteristic value of coal consumption for power supply and the preset threshold for coal consumption for power supply, and the second difference between the characteristic value of heat-to-electricity ratio and the preset threshold for heat-to-electricity ratio are calculated respectively. Based on the characteristic value of coal consumption for power supply and the characteristic value of heat-to-electricity ratio, the deviation of coal consumption for power supply and the deviation of heat-to-electricity ratio are calculated respectively. The deviation of coal consumption for power supply is compared with the preset allowable deviation threshold for coal consumption for power supply, and the deviation of heat-to-electricity ratio is compared with the preset allowable deviation threshold for heat-to-electricity ratio. Based on the comparison results, it is determined whether the current operating condition is in the low-carbon operating range, and the evaluation result of low-carbon compliance or low-carbon warning is output. When the evaluation result is a low-carbon warning, the equipment operating status data, thermoelectric decoupling characteristic data and carbon emission monitoring data under the best historical low-carbon operating conditions are used as training samples to construct a multidimensional coupled correlation model with the deviation of power supply coal consumption and the deviation of heat-to-power ratio as input variables and carbon emission intensity as output variable. The deviation of power supply coal consumption and the deviation of heat-to-power ratio under the current operating conditions are input into the multidimensional coupled correlation model. The partial derivative values ​​of each input variable with respect to carbon emission intensity are calculated as the weights of the influencing factors. The key energy consumption anomalies that lead to increased carbon emissions are identified, and the operating condition diagnosis results are output. Based on the operating condition diagnosis results, the pre-stored system topology data is called to construct an energy flow topology network including the boiler combustion subsystem, the turbine power subsystem, and the heating and transmission subsystem. The energy flow process under the current operating condition is decoupled and analyzed, and the energy efficiency loss weight of each energy-consuming device is calculated in order to trace and locate the primary equipment node that causes the increase in coal consumption under the current operating condition. Based on the energy efficiency loss weight of the primary equipment node, a preset low-carbon optimization strategy model is invoked for analysis and identification of the corresponding optimization strategy type. When the strategy is identified as a combustion optimization strategy, control commands are generated to adjust the opening of the blower and the frequency of the coal feeder. When the strategy is identified as a thermal power load distribution strategy, control commands are generated to adjust the opening of the heating extraction steam regulating valve and the flow rate of the turbine speed regulating valve. The control commands are then output to the actuator to adjust the operating status of the current operating condition.

2. The low-carbon coal-fired cogeneration method according to claim 1, characterized in that, The specific method for real-time acquisition of equipment operating status data, heat and power decoupling characteristic data, and carbon emission monitoring data of coal-fired cogeneration systems, and the preprocessing of the acquired data, is as follows: Real-time acquisition of equipment operating status data, thermal-electric decoupling characteristic data, and carbon emission monitoring data of coal-fired cogeneration systems; The Laida criterion was used to identify and remove outliers in time series data of equipment operating status data, thermoelectric decoupling characteristic data and carbon emission monitoring data. The arithmetic mean of data at adjacent time points was used to linearly interpolate and fill in the data after outliers were removed. The physical quantities of different dimensions in the filled data are uniformly formatted and encoded, and the non-numerical switch quantities of the device start-stop status are converted into numerical matrices. The data matrix is ​​normalized using the min-max normalization method, which linearly maps the original data to the interval between 0 and 1.

3. The low-carbon coal-fired cogeneration method according to claim 1, characterized in that, The specific method for extracting feature values ​​for power supply coal consumption and heat-to-power ratio based on preprocessed equipment operating status data, thermoelectric decoupling characteristic data, and carbon emission monitoring data is as follows: Preprocessed equipment operating status data, thermoelectric decoupling characteristic data, and carbon emission monitoring data were acquired and feature extracted to obtain boiler combustion efficiency, main steam pressure, and main steam temperature. The oxygen content of the flue gas, as well as the amount of steam extracted for heating, the back pressure heating power, and the turbine speed; Obtain boiler combustion efficiency, main steam pressure, and main steam temperature. Historical sample data on flue gas oxygen content were used to calculate boiler combustion efficiency, main steam pressure, and main steam temperature. The principal component contribution of oxygen content in flue gas is converted into corresponding weights. Based on boiler combustion efficiency, main steam pressure, and main steam temperature The weight of flue gas oxygen content is used to establish a power supply coal consumption characteristic value model using a weighted fitting method, and the power supply coal consumption characteristic value is calculated using the power supply coal consumption characteristic value model. The matching parameters of heat load and electrical load are obtained by calculating the ratio of the heat extraction steam volume, back pressure heating power and turbine speed, and are used as the characteristic value of the heat-to-power ratio.

4. A low-carbon coal-fired cogeneration method according to claim 1, characterized in that, The deviation of coal consumption for power supply is the ratio of the difference between the characteristic value of coal consumption for power supply and the preset threshold value of coal consumption for power supply to the characteristic value of coal consumption for power supply. The thermoelectric ratio deviation is the ratio of the difference between the thermoelectric ratio characteristic value and the preset thermoelectric ratio threshold to the thermoelectric ratio characteristic value; When the deviation of coal consumption for power supply is less than or equal to the preset allowable deviation threshold for coal consumption for power supply, and the deviation of the heat-to-power ratio is less than or equal to the preset allowable deviation threshold for the heat-to-power ratio, the current operating condition is determined to be in the low-carbon operating range and the evaluation result of low-carbon compliance is output. When the deviation of coal consumption for power supply exceeds the preset allowable deviation threshold, or the deviation of the heat-to-power ratio exceeds the preset allowable deviation threshold, the current operating condition is determined to be in a non-low-carbon operating range and a low-carbon warning evaluation result is output.

5. A low-carbon coal-fired cogeneration method according to claim 1, characterized in that, The multidimensional coupling correlation model employs a multivariate nonlinear regression equation: in, For the deviation of coal consumption for power supply, Thermoelectric ratio deviation, For carbon emission intensity, For constant terms, The coefficient of the linear term, The coefficient of the quadratic term, These are the interaction term coefficients; each coefficient is solved by fitting the historical training samples using the least squares method.

6. A low-carbon coal-fired cogeneration method according to claim 1, characterized in that, When the key energy consumption anomaly is the deviation of power supply coal consumption, the deviation of the heat-to-power ratio is kept constant. The required power supply coal consumption correction value is calculated in reverse by using a multi-dimensional coupled correlation model with the preset power supply coal consumption threshold as the target. Based on the power supply coal consumption correction value, the boiler combustion efficiency loss area is located, and the working condition diagnosis result of the deterioration of combustion conditions is output. When the key energy consumption anomaly is the deviation of the heat-to-power ratio, the deviation of the power supply coal consumption remains unchanged. The required adjustment parameters for the heating steam extraction volume are calculated in reverse using a multi-dimensional coupled correlation model with the preset heat-to-power ratio threshold as the target. Based on these adjustment parameters, the over-limit situation of the heat-to-power decoupling constraint boundary is judged, and the working condition diagnosis result of the heat-to-power matching imbalance is output.

7. A low-carbon coal-fired cogeneration method according to claim 1, characterized in that, When the operating condition diagnosis result is that the combustion condition is deteriorated, the main steam pressure, main steam temperature and flue gas oxygen content are obtained, and combined with the boiler energy efficiency benchmark model generated based on the historical best low carbon operating conditions, the exhaust heat loss, incomplete combustion heat loss and heat dissipation loss are calculated respectively. Calculate the proportion of each loss value to the total loss value as the loss contribution weight, and set the loss contribution weight as the energy efficiency loss weight; Identify the primary equipment node corresponding to the loss type with the largest energy efficiency loss weight, and trace its source to locate the primary equipment node causing the increase in coal consumption.

8. A low-carbon coal-fired cogeneration method according to claim 1, characterized in that, When the operating condition diagnosis result is thermoelectric mismatch, obtain the thermoelectric decoupling characteristic data and calculate the interstage enthalpy drop loss of the steam turbine and the heat transmission heat loss of the heating network respectively. Calculate the proportion of each loss value to the total loss value as the loss contribution weight, and set the loss contribution weight as the energy efficiency loss weight; The equipment node with the largest energy efficiency loss weight is traced and identified as the primary equipment node causing the increase in coal consumption.

9. A low-carbon coal-fired cogeneration method according to claim 1, characterized in that, When identified as a combustion optimization strategy, the deviation rate between the real-time energy efficiency loss weight and the preset standard weight is calculated, and the target air distribution correction coefficient is set to 1 minus the product of the deviation rate and the preset air volume response factor. The coal feed rate adjustment bias value is calculated based on the difference between the current coal feed rate, the measured value of flue gas oxygen content and the optimal oxygen content setting value, and the coal feed response coefficient. When a thermoelectric load allocation strategy is identified, the thermoelectric decoupling allocation coefficient is calculated based on the thermoelectric ratio deviation and the thermoelectric load response factor. Based on the target air distribution correction coefficient, coal feed rate adjustment bias value, or thermal-electric decoupling distribution coefficient, corresponding control commands are generated and output to the actuator.

10. A low-carbon coal-fired cogeneration system, characterized in that, include: The data acquisition module is used to collect real-time equipment operation status data, thermal-electric decoupling characteristic data, and carbon emission monitoring data of the coal-fired cogeneration system, and to preprocess the collected data. The feature extraction module is used to extract features based on preprocessed equipment operating status data, thermoelectric decoupling characteristic data and carbon emission monitoring data to obtain power supply coal consumption feature value and heat-to-power ratio feature value. The low-carbon evaluation module is used to calculate the first difference between the characteristic value of coal consumption for power supply and the preset threshold value of coal consumption for power supply, and the second difference between the characteristic value of heat-to-electricity ratio and the preset threshold value of heat-to-electricity ratio. Based on the characteristic value of coal consumption for power supply and the characteristic value of heat-to-electricity ratio, the module calculates the deviation of coal consumption for power supply and the deviation of heat-to-electricity ratio, respectively. The module compares the deviation of coal consumption for power supply with the preset allowable deviation threshold value of coal consumption for power supply and the deviation of heat-to-electricity ratio with the preset allowable deviation threshold value of heat-to-electricity ratio. Based on the comparison results, the module determines whether the current operating condition is in the low-carbon operating range and outputs the evaluation results of low-carbon compliance or low-carbon warning. The correlation analysis module is used to construct a multidimensional coupled correlation model when the evaluation result is a low-carbon warning. It uses equipment operating status data, thermoelectric decoupling characteristic data, and carbon emission monitoring data under the best historical low-carbon operating conditions as training samples. The model has the deviation of power supply coal consumption and the deviation of heat-to-power ratio as input variables and carbon emission intensity as output variable. The deviation of power supply coal consumption and the deviation of heat-to-power ratio under the current operating conditions are input into the multidimensional coupled correlation model. The partial derivative values ​​of each input variable with respect to carbon emission intensity are calculated as the weights of the influencing factors. The key energy consumption anomalies that lead to increased carbon emissions are identified, and the operating condition diagnosis results are output. The energy efficiency traceability analysis module is used to construct an energy flow topology network that includes the boiler combustion subsystem, the turbine power subsystem, and the heating and transmission subsystem based on the operating condition diagnosis results and by calling the pre-stored system topology data. It performs decoupling analysis on the energy flow process under the current operating condition and calculates the energy efficiency loss weight of each energy-consuming device in order to trace and locate the primary equipment node that causes the increase in coal consumption under the current operating condition. The optimization decision module is used to analyze and identify the corresponding optimization strategy type by calling a preset low-carbon optimization strategy model based on the energy efficiency loss weight of the primary equipment node. When the strategy is identified as a combustion optimization strategy, control instructions are generated to adjust the opening of the blower and the frequency of the coal feeder. When the strategy is identified as a thermal power load distribution strategy, control instructions are generated to adjust the opening of the heating extraction steam regulating valve and the flow rate of the turbine speed regulating valve. The control instructions are then output to the actuator to adjust the operating status of the current operating condition.

Images