Combustion optimization method based on combined cycle unit

Abstract

The invention provides a combustion optimization method based on a combined cycle unit, and belongs to the technical field of combustion engineering.The method comprises the steps that operation parameters of a gas turbine are monitored through a sensor, the operation parameters of the gas turbine are evaluated in combination with a first combustion rule, and important features are extracted from a combustion evaluation result based on a combustion optimization target; acquiring real-time heat value and density data of a combustion source, integrating the real-time heat value and density data with operation parameters of the gas turbine to obtain a first data set, performing feature construction to obtain a derivative feature set, and establishing a combustion model in combination with a second combustion rule; combining the combustion model and historical operation data of the combined cycle unit to construct a prediction model of the optimal opening degree of the premixing valve, and obtaining the optimal opening degree of the premixing valve; the premixing valve is adjusted according to the optimal opening degree, the real-time combustion condition after adjustment of the premixing valve is collected and compared with the predicted combustion condition, a feedback mechanism is formed based on the comparison result, the combustion model is updated, the energy efficiency utilization rate of the combined cycle unit is remarkably increased, and emission of NOx and other harmful substances is effectively reduced.

Description

Technical Field

[0001] The invention relates to the technical field of combustion engineering, and in particular to a combustion optimization method based on a combined cycle unit. Background Art

[0002] In the current context where energy utilization and environmental protection are increasingly valued, combined cycle units, as an efficient and relatively clean way of generating electricity, are relatively mature in technology, but still face the problem of how to further optimize the combustion process to improve efficiency and reduce emissions. The study of combustion optimization is not only related to the effective utilization of energy, but also to reducing the negative impact on the environment. Traditional methods usually rely on fixed parameter settings and cannot adapt to dynamically changing environments. When processing historical data, these data are often not effectively extracted and applied.

[0003] Therefore, the present invention provides a combustion optimization method based on a combined cycle unit. Summary of the invention

[0004] The present invention provides a combustion optimization method based on a combined cycle unit. The method obtains real-time calorific value and density data of a combustion source, integrates the first data set, constructs a feature set, and then combines historical operating data with a combustion model to predict the optimal opening of a premixing valve. In actual operation, the valve opening is adjusted according to the predicted combustion conditions, and data is collected in real time for feedback, thereby significantly improving the energy efficiency utilization rate of the combined cycle unit, effectively reducing harmful emissions such as NOx, dynamically responding to environmental changes and fluctuations in operating conditions, and improving system stability.

[0005] The present invention provides a combustion optimization method based on a combined cycle unit, comprising:

[0006] Step 1: Monitor the operating parameters of the gas turbine through sensors, evaluate the operating parameters of the gas turbine in combination with the first combustion law, and extract important features from the combustion evaluation results based on the combustion optimization goal;

[0007] Step 2: Obtain the real-time calorific value and density data of the combustion source, and integrate them with the operating parameters of the gas turbine to obtain the first data set, and perform feature construction on the first data set to obtain a derived feature set, and combine it with the second combustion law to establish a combustion model;

[0008] Step 3: Combining the combustion model with the historical operation data of the combined cycle unit, a prediction model for the optimal opening of the premixing valve is constructed to obtain the optimal opening of the premixing valve;

[0009] Step 4: adjusting the premixing valve according to the optimal opening, collecting the real-time combustion conditions after the premixing valve is adjusted, and comparing them with the predicted combustion conditions, forming a feedback mechanism based on the comparison results, and updating the combustion model.

[0010] The present invention provides a combustion optimization method based on a combined cycle unit, which monitors the operating parameters of the gas engine through a sensor, evaluates the operating parameters of the gas engine in combination with a first combustion law, and extracts important features from the combustion evaluation results based on the combustion optimization target, including:

[0011] Obtain basic equipment information of the combined cycle unit, and obtain the operating parameters of the gas turbine based on the basic equipment information;

[0012] Establish the combustion relationship between the operating parameters and combustion conditions of different gas engines according to the combustion theory, and evaluate the first combustion law of the combustion relationship under different working conditions in combination with the combustion characteristics to obtain the combustion evaluation result;

[0013] A combustion optimization target is clarified, and important features related to combustion optimization are extracted from the combustion evaluation results based on the combustion optimization target.

[0014] The present invention provides a combustion optimization method based on a combined cycle unit, which obtains real-time calorific value and density data of a combustion source, integrates the data with the operating parameters of a combustion engine, obtains a first data set, performs feature construction on the first data set to obtain a derived feature set, and establishes a combustion model in combination with a second combustion law, including:

[0015] Based on the important features and the first data set, corresponding domain knowledge and combustion theory are applied to perform feature construction to obtain a derived feature set;

[0016] deriving a target variable according to the combustion optimization target, discretizing the derived feature set and the target variable, and randomly combining the discretized derived feature set and the target variable to obtain a category combination, and creating a frequency table based on the category combination;

[0017] Testing the category combinations according to the frequency table, and selecting corresponding category combinations whose correlation between the target variable and the derived feature is higher than a preset correlation from the test results, to generate a significant derived feature set;

[0018] The combustion influence of each significant derivative feature set on each stage of the combustion process is determined in combination with the second combustion law, and a combustion model is constructed based on the combustion influence and the combustion evaluation result.

[0019] The present invention provides a combustion optimization method based on a combined cycle unit. Based on the important features and the first data set, corresponding domain knowledge and combustion theory are applied to perform feature construction to obtain a derived feature set, including:

[0020] Performing a field analysis on the important features and the first data set based on the combustion optimization goal to determine the fields involved in the important features and the first data set;

[0021] In combination with the fields involved, corresponding domain knowledge is obtained from the combustion knowledge base, and combustion theories consistent with the combustion optimization goals are obtained. Based on the important features and the first data set, hierarchical feature construction of the fields involved is performed, and the feature construction results of all the fields involved are integrated to obtain a derived feature set.

[0022] The present invention provides a combustion optimization method based on a combined cycle unit, which determines the combustion influence of each significant derivative feature set on each stage of the combustion process in combination with the second combustion law, and constructs a combustion model based on the combustion influence and the combustion evaluation result, including:

[0023] The second combustion law is used to establish a connection between the significant derivative feature set and each stage of the combustion process, and to quantify the combustion impact of each significant derivative feature at each stage.

[0024] At the same time, the contribution of significant derivative features to the combustion optimization objectives is quantified;

[0025] A combustion model is constructed based on the combustion influence and contribution combined with the combustion evaluation results.

[0026] The present invention provides a combustion optimization method based on a combined cycle unit, which combines the combustion model with the historical operation data of the combined cycle unit to construct a prediction model for the optimal opening of the premixing valve, and obtains the optimal opening of the premixing valve, including:

[0027] Determine various environmental conditions that affect the opening of the premixing valve by combining the combustion model with historical operating data of the combined cycle unit, obtain baseline data of the opening of the premixing valve of the combined cycle unit under stable operating conditions, and determine the expected value range of the opening of the premixing valve under various environmental conditions based on the baseline data;

[0028] Identify changes in various environmental conditions according to the expected value range, and analyze the causes of the change identification results to obtain the causes of the changes;

[0029] Each environmental condition and the corresponding change identification results are matched with the cause of the change one by one, and the opening of the premixing valve is set according to the corresponding results, so as to obtain a prediction model for the optimal opening of the premixing valve and predict the optimal opening of the premixing valve under different environmental conditions.

[0030] The present invention provides a combustion optimization method based on a combined cycle unit, which corresponds each environmental condition and the corresponding change identification result to the change cause one by one, and sets the opening of the premixing valve according to the corresponding result, thereby obtaining a prediction model to predict the optimal opening of the premixing valve under different environmental conditions, including:

[0031] Setting a first rule for adjusting the opening of the premixing valve according to the change identification result and the change cause;

[0032] A second rule for adjusting the opening of the premixing valve is set according to the environmental conditions and the change identification result;

[0033] A third rule for adjusting the opening of the premixing valve is set according to environmental conditions and reasons for changes;

[0034] Based on the first rule, the second rule and the third rule, the fuel chamber temperature characteristics, the combustion source flow characteristics and the air to combustion source ratio characteristics during the combustion process are determined, and a prediction model is constructed to set the calculation formula for the optimal opening of the premixing valve:

[0035] ;

[0036] Where A represents the weighted sum of the deviations of each environmental condition; m represents the total number of environmental conditions; k represents the kth environmental condition; ω k (t) weight coefficient of the kth environmental condition; X k represents the actual variable of the kth environmental condition; X r,k represents the reference variable of the kth environmental condition; new Indicates the optimal opening of the premixing valve after adjustment under current conditions; Indicates the reference opening of the premixing valve; O i represents the i-th premixing valve opening value in the historical operation data; n represents the number of premixing valve opening values ​​in the historical operation data; F s (t) represents the current performance index of the combustion process; F q (t) represents the ideal performance index output by the combustion model; τ represents the dynamic adjustment factor; HV represents the real-time calorific value of the combustion source; D represents the density of the combustion source; E s represents the supply of the combustion source; β1, β2, and β3 represent the interaction term coefficient, the nonlinear term coefficient, and the exponential correlation coefficient, respectively; X1, X2, and X3 represent the fuel chamber temperature characteristics, the combustion source flow characteristics, and the air to combustion source ratio characteristics during the combustion process, respectively.

[0037] The present invention provides a combustion optimization method based on a combined cycle unit, which adjusts the premixing valve according to the optimal opening, collects the real-time combustion conditions after the premixing valve is adjusted, and compares them with the predicted combustion conditions, forms a feedback mechanism based on the comparison results, and updates the combustion model, including:

[0038] outputting a predicted combustion condition after executing the optimal opening degree based on the prediction model;

[0039] Perform multi-dimensional comparison between the real-time combustion situation and the predicted combustion situation to obtain a multi-dimensional deviation, perform deviation judgment on the multi-dimensional deviation, if the absolute value of the deviation is lower than the deviation threshold, mark it as normal, obtain the optimization effect, and perform positive feedback on the combustion model; if the absolute value of the deviation is higher than the deviation threshold, mark it as abnormal, obtain a negative adjustment result, and perform negative feedback on the combustion model;

[0040] The combustion model is updated according to the feedback mechanism.

[0041] Compared with the prior art, the beneficial effects of the present application are as follows: by acquiring the real-time calorific value and density data of the combustion source, integrating to obtain the first data set, and constructing a feature set, and then combining the historical operating data with the combustion model, the optimal opening of the premixing valve is predicted. In actual operation, the valve opening is adjusted according to the predicted combustion conditions, and data is collected in real time for feedback, which significantly improves the energy efficiency utilization rate of the combined cycle unit, effectively reduces harmful emissions such as NOx, dynamically responds to environmental changes and fluctuations in operating conditions, and improves system stability.

[0042] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0043] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0045] Figure 1 It is a flow chart of a combustion optimization method based on a combined cycle unit provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0047] Embodiment 1:

[0048] The embodiment of the present invention provides a combustion optimization method based on a combined cycle unit, such as Figure 1 As shown, including:

[0049] Step 1: Monitor the operating parameters of the gas turbine through sensors, evaluate the operating parameters of the gas turbine in combination with the first combustion law, and extract important features from the combustion evaluation results based on the combustion optimization goal;

[0050] Step 2: Obtain the real-time calorific value and density data of the combustion source, and integrate them with the operating parameters of the gas turbine to obtain the first data set, and perform feature construction on the first data set to obtain a derived feature set, and combine it with the second combustion law to establish a combustion model;

[0051] Step 3: Combining the combustion model with the historical operation data of the combined cycle unit, a prediction model for the optimal opening of the premixing valve is constructed to obtain the optimal opening of the premixing valve;

[0052] Step 4: adjusting the premixing valve according to the optimal opening, collecting the real-time combustion conditions after the premixing valve is adjusted, and comparing them with the predicted combustion conditions, forming a feedback mechanism based on the comparison results, and updating the combustion model.

[0053] In this embodiment, the operating parameters are key indicators that describe the operating status of the combined cycle unit, especially the gas turbine, and reflect the current operating performance and environmental conditions of the equipment, including: gas temperature, pressure, air flow, gas composition, etc., such as temperature: the temperature of the combustion chamber (for example, 900°C), pressure: the pressure in the combustion chamber (for example, 100 kPa).

[0054] In this embodiment, the first combustion law is a summary of the combustion behavior under specific conditions based on combustion theory and analysis results. It usually summarizes the performance of different operating conditions, including: optimal combustion area, combustion rate, etc. For example, combustion stability under stable temperature conditions: when the temperature is in the range of 900°C to 950°C, NOx generation remains at an acceptable level.

[0055] In this embodiment, the combustion optimization goal is to achieve specific performance indicators by adjusting operating parameters, aiming to improve the safety, efficiency and environmental protection level of the combustion process, including: improving combustion efficiency, reducing emissions, increasing energy output, reducing fuel consumption, optimizing combustion stability, reducing noise and vibration, and singing equipment life, for example, maximizing combustion efficiency: the expected combustion efficiency is at least 95%.

[0056] In this embodiment, the density data is the density of the combustion source (such as natural gas, heavy oil, coal, etc.) under specific conditions. For example, liquid fuels such as heavy oil and gasoline are generally denser than gaseous fuels (such as natural gas).

[0057] In this embodiment, the first data set includes measured data related to the operation of the gas turbine, such as operating parameters (temperature, pressure, fuel flow, air flow, etc.) and real-time calorific value and density data. For example, the fuel flow at a certain moment is 100 kg / h, the intake temperature is 600°C, the pressure is 15 bar, etc.

[0058] In this embodiment, the process of determining the derived feature set is to obtain relevant field knowledge and combustion theory from the combustion knowledge base, combine important features with the first data set, implement hierarchical feature construction, comprehensively analyze the feature construction results of different involved fields, and finally obtain the derived feature set.

[0059] In this embodiment, the combustion model is constructed by establishing a quantitative connection between the significant derivative feature set and each stage of the combustion process through the second combustion law, evaluating the impact of each feature on the combustion process, quantifying the contribution of the significant derivative features to the combustion optimization target, and combining the combustion impact and contribution with the combustion evaluation results to construct a combustion model.

[0060] In this embodiment, by combining the combustion model with the historical operating data of the combined cycle unit, the environmental conditions that affect the opening of the premixing valve are identified, and the baseline data under stable operation is obtained. Based on these baseline data, the expected value range of the premixing valve opening under various environmental conditions is determined, and the changes are identified and the causes are analyzed. By corresponding to the environmental conditions and the causes of the changes, the premixing valve opening is set, thereby establishing a prediction model for the optimal opening of the premixing valve.

[0061] In this embodiment, the feedback mechanism is to compare the combustion conditions in real time with the optimal opening output by the prediction model, calculate the multi-dimensional deviation, and determine whether the operation is normal through the set deviation threshold. If the deviation is less than the threshold, it is marked as normal and positive feedback is given to the combustion model to improve the prediction accuracy; if the deviation is greater than the threshold, it is marked as abnormal and negative feedback is given to prompt the combustion model to be adjusted and updated.

[0062] The working principle and beneficial effects of the above technical solution are: by acquiring the real-time calorific value and density data of the combustion source, integrating to obtain the first data set, and constructing a feature set, and then combining the historical operation data with the combustion model, the optimal opening of the premixing valve is predicted. In actual operation, the valve opening is adjusted according to the predicted combustion conditions, and data is collected in real time for feedback, which significantly improves the energy efficiency utilization rate of the combined cycle unit, effectively reduces harmful emissions such as NOx, dynamically responds to environmental changes and fluctuations in operating conditions, and improves system stability.

[0063] Embodiment 2:

[0064] The embodiment of the present invention provides a combustion optimization method based on a combined cycle unit, which monitors the operating parameters of the gas engine through a sensor, evaluates the operating parameters in combination with a first combustion law, and extracts important features from the combustion evaluation results based on a combustion optimization target, including:

[0065] Obtain basic equipment information of the combined cycle unit, and obtain the operating parameters of the gas turbine based on the basic equipment information;

[0066] Establish the combustion relationship between the operating parameters and combustion conditions of different gas engines according to the combustion theory, and evaluate the first combustion law of the combustion relationship under different working conditions in combination with the combustion characteristics to obtain the combustion evaluation result;

[0067] A combustion optimization target is clarified, and important features related to combustion optimization are extracted from the combustion evaluation results based on the combustion optimization target.

[0068] In this embodiment, the basic equipment information is data describing the technical parameters and specifications of each component in the combined cycle unit, including the performance indicators and characteristics of the equipment, such as model and specifications: a certain model of gas turbine, such as "GE LM6000", rated power: the rated output power of the equipment (for example, 40MW).

[0069] In this embodiment, the combustion relationship describes the interaction between different operating parameters and combustion results, including: combustion products and temperature and pressure, for example, temperature and NOx generation: an increase in temperature generally leads to an increase in NOx emissions.

[0070] In this embodiment, the combustion condition refers to the combustion performance produced by the combined cycle unit under specific conditions, which is usually measured by emission data and efficiency, including: combustion mode, combustion stability, flame shape and characteristics, and unfueled monitoring, for example, combustion efficiency: the ratio of the energy generated by actual combustion to the theoretical energy (for example, combustion efficiency = 95%).

[0071] In this embodiment, the combustion evaluation result is the data feedback obtained after analyzing the combustion process, which describes the performance of the system under specific conditions, including: combustion efficiency, emission level, etc. The emission evaluation report describes the results of NOx, CO and other emissions under different working conditions (for example, NOx = 30ppm at 75% load, NOx = 50ppm at 100% load).

[0072] The working principle and beneficial effects of the above technical solution are: based on the basic equipment information of the combined cycle unit, by real-time monitoring of the operating parameters of the gas turbine, combined with the combustion theory to evaluate the combustion relationship and characteristics, so as to determine the first combustion law, clarify the combustion optimization goals and extract important features, and finally achieve dynamic optimization of the combustion process, improve power generation efficiency and reduce emissions, adapt to changes in the operating environment, and enhance the flexibility and responsiveness of the system.

[0073] Embodiment 3:

[0074] The embodiment of the present invention provides a combustion optimization method based on a combined cycle unit, which obtains real-time calorific value and density data of a combustion source, integrates the data with the operating parameters of a combustion engine, obtains a first data set, performs feature construction on the first data set to obtain a derived feature set, and establishes a combustion model in combination with a second combustion law, including:

[0075] Based on the important features and the first data set, corresponding domain knowledge and combustion theory are applied to perform feature construction to obtain a derived feature set;

[0076] deriving a target variable according to the combustion optimization target, discretizing the derived feature set and the target variable, and randomly combining the discretized derived feature set and the target variable to obtain a category combination, and creating a frequency table based on the category combination;

[0077] Testing the category combinations according to the frequency table, and selecting corresponding category combinations whose correlation between the target variable and the derived feature is higher than a preset correlation from the test results, to generate a significant derived feature set;

[0078] The combustion influence of each significant derivative feature set on each stage of the combustion process is determined in combination with the second combustion law, and a combustion model is constructed based on the combustion influence and the combustion evaluation result.

[0079] In this embodiment, the domain knowledge includes the basic principles of the combustion process, chemical reaction characteristics, and fluid dynamics; combustion theory provides a theoretical framework for explaining and predicting combustion behavior. For example, based on the Archimedean constant and the reaction rate equation, the effects of different fuel-air mixture ratios on combustion efficiency can be studied.

[0080] In this embodiment, the derived feature set is a new feature set extracted through mathematical calculations or physical models based on the first data set and domain knowledge, such as the ratio of temperature to pressure, the ratio of oxygen to fuel, etc.

[0081] In this embodiment, the target variable is a key indicator determined according to the combustion optimization goal, and is usually an output result that needs to be optimized, such as combustion efficiency (expressed as a percentage) and emission concentration (such as g / kWh of NOx).

[0082] In this embodiment, the category combination is a different category (combination) pair generated by randomly combining the discretized derived feature set and the target variable, for example, the category of the combination formed by the temperature, pressure and mixing ratio of the incoming air, such as (high temperature, high pressure, low mixing ratio).

[0083] In this embodiment, the frequency table is a table that records the frequency of occurrence of category combinations, and is used to detect which combinations are common in the data set. For example, the table lists feature combinations, such as the "high temperature-high pressure" combination that appears 80 times in all test data.

[0084] In this embodiment, the significant derivative feature set is a tested derivative feature set, and its correlation with the target variable is higher than the preset correlation, indicating that it has important influence on the combustion process. For example, a significant correlation between oxygen concentration and NOx emissions is found, and the combination of oxygen concentration = 20% is considered to be a significant feature.

[0085] In this embodiment, the preset correlation is a strength threshold that defines the association between the feature and the target variable. Combinations below this threshold will be eliminated. For example, the preset correlation is set to 0.7, and only feature combinations with a correlation exceeding 0.7 will be considered significant.

[0086] In this embodiment, the combustion impact is the specific impact of significant derivative characteristics on each stage of the combustion process, including the degree of impact on efficiency, stability and emission characteristics. For example, a specific mixture ratio (such as an oxygen to fuel ratio of 1:14) may result in optimal thermal efficiency and lowest NOx emissions.

[0087] The working principle and beneficial effects of the above technical solution are: based on important features and the first data set, using combustion theory to construct features, generate derived feature sets, determine target variables according to combustion optimization goals, discretize and randomly combine the derived feature sets, create category combinations and frequency tables, test the correlation of the combinations, screen significant derived feature sets, and build a combustion model in combination with the second combustion law to achieve optimization and adjustment of each stage of the combustion process, improve power generation efficiency, achieve more efficient energy utilization, optimize combustion characteristics, and reduce exhaust emissions.

[0088] Embodiment 4:

[0089] The embodiment of the present invention provides a combustion optimization method based on a combined cycle unit. Based on the important features and the first data set, corresponding domain knowledge and combustion theory are applied to perform feature construction to obtain a derived feature set, including:

[0090] Performing a field analysis on the important features and the first data set based on the combustion optimization goal to determine the fields involved in the important features and the first data set;

[0091] In combination with the fields involved, corresponding domain knowledge is obtained from the combustion knowledge base, and combustion theories consistent with the combustion optimization goals are obtained. Based on the important features and the first data set, hierarchical feature construction of the fields involved is performed, and the feature construction results of all the fields involved are integrated to obtain a derived feature set.

[0092] In this embodiment, the integration process refers to combining different domain knowledge with combustion theory, and merging multiple feature sets through a systematic feature construction method to form an integrated derived feature set. For example: assuming that there is the following domain knowledge and theory from the combustion knowledge base: the relationship between combustion efficiency and fuel flow rate and air flow rate, the influence of temperature and pressure on the chemical reaction rate. More specifically, combined with the changes in temperature, pressure and flow rate, the feature "Feature 1 = (fuel flow rate / air flow rate) * temperature" is constructed.

[0093] In this embodiment, hierarchical feature construction means that in the feature construction process, features are hierarchically processed according to their characteristics, sources or corresponding physical meanings. For example, in combustion optimization research, the following layers of features may be constructed: first-layer features (original features): features directly obtained from the first data set, such as fuel temperature, pressure, flow, etc., second-layer features (derived features): features obtained by simple formulas, such as "thermal efficiency = output power / fuel flow", third-layer features (composite features): combining multiple secondary features to represent more complex relationships, such as "feature 3 = interaction feature of temperature and flow".

[0094] The working principle and beneficial effects of the above technical solution are: by acquiring relevant field knowledge and combustion theory from the combustion knowledge base, combining important features with the first data set, implementing hierarchical feature construction, and comprehensively analyzing the feature construction results of different involved fields, and finally obtaining a derived feature set, it helps to reveal the complexity of the combustion process, provide data support for optimizing combustion, help reduce harmful gas emissions, meet environmental protection standards, and promote sustainable development.

[0095] Embodiment 5:

[0096] The embodiment of the present invention provides a combustion optimization method based on a combined cycle unit, which determines the combustion influence of each significant derivative feature set on each stage of the combustion process in combination with the second combustion law, and constructs a combustion model based on the combustion influence and the combustion evaluation result, including:

[0097] The second combustion law is used to establish a connection between the significant derivative feature set and each stage of the combustion process, and to quantify the combustion impact of each significant derivative feature at each stage.

[0098] At the same time, the contribution of significant derivative features to the combustion optimization objectives is quantified;

[0099] A combustion model is constructed based on the combustion influence and contribution combined with the combustion evaluation results.

[0100] In this embodiment, the process of establishing a connection is to analyze the relationship between the significant derivative feature set and each stage in the combustion process through the second combustion law, including: preparing the significant derivative feature set and the combustion data of each stage (such as initial combustion, stable combustion, extinction stage, etc.), and using statistical methods (such as linear regression, correlation analysis, causal inference) to study how the significant derivative features affect the specific performance of each combustion stage. For example, the analysis shows that the increase in temperature is significantly correlated with the increase in NOx emissions, and this effect is particularly evident in the stable combustion stage.

[0101] In this embodiment, the process of quantifying the combustion impact is to calculate the specific impact of each significant derivative feature on combustion efficiency, emission level, stability, etc., and quantify the impact of different features into a standard range for easy comparison. For example, standard deviation, percentage change, etc. are used to express the degree of impact.

[0102] In this embodiment, the contribution calculation is to quantify the specific contribution of each significant derivative feature relative to the combustion optimization goal (such as reducing NOx emissions) to evaluate its importance. For example, through regression analysis, it is found that a 1% increase in oxygen concentration leads to a 5% decrease in NOx emissions, while a 10°C increase in temperature leads to an 8% increase in NOx emissions.

[0103] In this embodiment, the process of constructing the combustion model selects a suitable model type (such as a linear model, a nonlinear model, a machine learning algorithm, etc.) to adapt to the data characteristics, uses historical operating data and the influence degree obtained from the quantification process to train the model, and adjusts the model parameters based on the training results to optimize its predictive ability and accuracy. The performance of the model is tested using an independent validation set to ensure its accuracy and reliability under different conditions. For example, a multivariate regression model is established through data fitting, which uses significant derivative features (such as fuel flow, oxygen concentration, and temperature) to predict NOx emissions.

[0104] The working principle and beneficial effects of the above technical solution are: through the second combustion law, a quantitative connection is established between the set of significant derivative features and each stage of the combustion process, the influence of each feature on the combustion process is evaluated, the contribution of the significant derivative features to the combustion optimization target is quantified, and a combustion model is constructed by combining the combustion influence and contribution with the combustion evaluation results to achieve dynamic optimization, improve combustion efficiency and reduce emissions.

[0105] Embodiment 6:

[0106] The embodiment of the present invention provides a combustion optimization method based on a combined cycle unit, which combines a combustion model with historical operation data of the combined cycle unit to construct a prediction model for the optimal opening of a premixing valve, and obtains the optimal opening of the premixing valve, including:

[0107] Determine various environmental conditions that affect the opening of the premixing valve by combining the combustion model with historical operating data of the combined cycle unit, obtain baseline data of the opening of the premixing valve of the combined cycle unit under stable operating conditions, and determine the expected value range of the opening of the premixing valve under various environmental conditions based on the baseline data;

[0108] Identify changes in various environmental conditions according to the expected value range, and analyze the causes of the change identification results to obtain the causes of the changes;

[0109] Each environmental condition and the corresponding change identification results are matched with the cause of the change one by one, and the opening of the premixing valve is set according to the corresponding results, so as to obtain a prediction model for the optimal opening of the premixing valve and predict the optimal opening of the premixing valve under different environmental conditions.

[0110] In this embodiment, environmental conditions include temperature, humidity, air pressure, fuel characteristics, etc.

[0111] In this embodiment, the baseline data is the premix valve opening data collected under stable operating conditions. By collecting the operating history data of the combined cycle unit under various environmental conditions, the standard of stable operation is determined, such as data maintained under the same load and environmental conditions for a long time, and statistical analysis is performed to extract the premix valve opening data under these conditions. For example, the environmental conditions are a temperature of 30°C, a relative humidity of 50%, an air pressure of 1013hPa, and a load of 250MW. The premix valve opening data has an average opening of 30%, and a fluctuation range of 28% to 32% under this environmental condition.

[0112] In this embodiment, the expected value range is determined based on the baseline data, and the expected value range of the premix valve opening under different environmental conditions is calculated by statistical methods. For example, under the same environmental conditions, the following is calculated: mean: 30%, standard deviation: 2%, and expected value range: 28% to 32%.

[0113] In this embodiment, change identification is to detect the deviation between the actual operating data and the expected value range. By real-time monitoring data, the opening value that is far from the expected value range is identified, the opening trend over time is observed, and whether an abnormality occurs; the change cause analysis is to further analyze the cause after the change is identified, compare the current environmental conditions with the historical operating conditions, and judge the difference. For example, the impact of high temperature: the external ambient temperature rises to 40°C, which reduces the combustion efficiency, and the gas flow rate needs to be increased to ensure the output. Humidity impact: it is found that the relative humidity soars to 80%, and the ratio of fuel to air needs to be adjusted to maintain normal combustion.

[0114] In this embodiment, the one-to-one correspondence process is to correspond each environmental condition, change identification result and change reason one by one, relying on a table or matrix form. For example, the environmental condition is high temperature (40°C), the change identification result is a decrease in opening, and the reason for the change is reduced combustion efficiency and the influence of gas density.

[0115] In this embodiment, the optimal opening prediction model is constructed by constructing a prediction model of the premix valve opening through a machine learning algorithm or statistical regression analysis, which can predict the optimal opening setting under different environmental conditions in real time to achieve the best operating efficiency and emission control.

[0116] The working principle and beneficial effects of the above technical solution are: by combining the combustion model with the historical operating data of the combined cycle unit, the environmental conditions that affect the opening of the premixing valve are identified, and the baseline data under stable operation conditions are obtained. Based on these baseline data, the expected value range of the premixing valve opening under various environmental conditions is determined, and the changes are identified and the causes are analyzed. By corresponding the environmental conditions and the causes of the changes, the premixing valve opening is set, thereby establishing a prediction model for the optimal opening of the premixing valve to adapt to the operating requirements under different environmental conditions, optimize the mixing ratio of fuel and air, thereby improving combustion efficiency and reducing fuel consumption.

[0117] Embodiment 7:

[0118] The embodiment of the present invention provides a combustion optimization method based on a combined cycle unit, which corresponds each environmental condition and the corresponding change identification result to the change cause one by one, and sets the opening of the premixing valve according to the corresponding result, thereby obtaining a prediction model to predict the optimal opening of the premixing valve under different environmental conditions, including:

[0119] Setting a first rule for adjusting the opening of the premixing valve according to the change identification result and the change cause;

[0120] A second rule for adjusting the opening of the premixing valve is set according to the environmental conditions and the change identification result;

[0121] A third rule for adjusting the opening of the premixing valve is set according to environmental conditions and reasons for changes;

[0122] Based on the first rule, the second rule and the third rule, the fuel chamber temperature characteristics, the combustion source flow characteristics and the air to combustion source ratio characteristics during the combustion process are determined, and a prediction model is constructed to set the calculation formula for the optimal opening of the premixing valve:

[0123] ;

[0124] Where A represents the weighted sum of the deviations of each environmental condition; m represents the total number of environmental conditions; k represents the kth environmental condition; ω k (t) weight coefficient of the kth environmental condition; X k represents the actual variable of the kth environmental condition; X r,k represents the reference variable of the kth environmental condition; new Indicates the optimal opening of the premixing valve after adjustment under current conditions; Indicates the reference opening of the premixing valve; O i represents the i-th premixing valve opening value in the historical operation data; n represents the number of premixing valve opening values ​​in the historical operation data; F s (t) represents the current performance index of the combustion process; F q (t) represents the ideal performance index output by the combustion model; τ represents the dynamic adjustment factor; HV represents the real-time calorific value of the combustion source; D represents the density of the combustion source; E s represents the supply of the combustion source; β1, β2, and β3 represent the interaction term coefficient, the nonlinear term coefficient, and the exponential correlation coefficient, respectively; X1, X2, and X3 represent the fuel chamber temperature characteristics, the combustion source flow characteristics, and the air to combustion source ratio characteristics during the combustion process, respectively.

[0125] In this embodiment, the first rule is to adjust the premix valve opening according to the changes monitored by the system (such as combustion efficiency, temperature, etc.) and their causes (such as environmental factors, high humidity, etc.). For example, if it is identified that the temperature is too high and causes incomplete combustion, the valve is adjusted, and the situation may be improved by reducing the premix valve opening by 5%.

[0126] In this embodiment, the second rule is to adjust the premix valve opening depending on the current environmental conditions (such as air pressure, humidity) and the change recognition result. For example, when the humidity is increased to 80%, the premix valve opening needs to be increased by 3% to ensure sufficient combustion.

[0127] In this embodiment, the third rule is to combine the environmental conditions and the reasons for the changes to optimize the opening through dynamic adjustment. For example, if the oxygen becomes thin because the air pressure drops to 950 hPa, the premix valve may need to be reduced by 2% to adapt to the lower oxygen environment.

[0128] In this embodiment, the interaction coefficient is used to reflect the influence of the interaction between two or more variables on the model output, and the value range is real numbers. For example, the interaction between the fuel chamber temperature and the combustion source flow rate may have a specific influence on the opening of the premixing valve.

[0129] In this embodiment, the nonlinear term coefficient allows certain variables in the model to affect the output in a nonlinear manner.

[0130] In this embodiment, the exponential correlation coefficient is generally used to describe the exponential relationship between a variable and an output. In a combustion process model, it is used to describe how variables such as temperature and flow rate affect the opening of a premixing valve in an exponential manner.

[0131] In this embodiment, β1, β2, β3∈R.

[0132] In this embodiment, the fuel chamber temperature characteristic refers to the temperature of the fuel before or during combustion, which affects the volatility and combustion efficiency of the fuel, and generally ranges from 20°C to 400°C. For example, if the temperature of the fuel chamber is 50°C, the premix valve may be set to 30%, and if the temperature increases to 70°C, it may need to be increased to 35%.

[0133] In this embodiment, the combustion source flow characteristic refers to the flow rate of the combustion source (gas, liquid or solid) flowing into the combustion chamber, which directly affects the intensity and stability of combustion. The combustion source is gas, and the range is 20m 3 / h--1000m 3 / h, the fuel source is liquid, the range is 10L / h--2000L / h, the fuel source is solid, the range is 10kg / h--1000kg / h, for example, the flow rate is set to 100m 3 / h, if the measured flow rate drops to 80m 3 / h, the premix valve needs to be adjusted to increase the flow rate to ensure efficiency.

[0134] In this embodiment, the air-to-combustion source ratio characteristic is the ratio between air and fuel, which affects the sufficiency of combustion and emissions, and ranges from 1:1 to 10:1. For example, the air-to-fuel ratio is set to 10:1. If the sensor detects that the ratio becomes 8:1, it is necessary to reduce the fuel inflow and adjust the estimated valve opening by 5% to restore the ideal combustion ratio.

[0135] In this embodiment, the ideal performance indicators output by the combustion model are targets set based on optimal combustion theory and historical operating data, including ideal combustion efficiency, temperature, and emission standards. For example, the combustion efficiency in the ideal case is 95%. If the actual result is 90%, the premix valve needs to be adjusted to improve efficiency.

[0136] In this embodiment, the current performance index refers to the actual performance of the combustion process monitored in real time, including indicators such as combustion efficiency, temperature, and emissions. For example, the currently monitored efficiency is 90%. If it is lower than the ideal value, immediate measures must be taken (such as adjusting the premix valve or flow) to improve the combustion effect.

[0137] The working principle and beneficial effects of the above technical solution are: by setting three adjustment rules, the premix valve opening is dynamically adjusted to cope with different environmental conditions and operating changes. Based on the identification results and causes of changes in environmental conditions, combined with the characteristics of combustion process data, a prediction model is constructed to calculate the optimal premix valve opening, thereby optimizing the combustion process, improving efficiency and reducing emissions. Flexible rules can better respond to environmental changes and ensure that the gas turbine operates in the best state.

[0138] Embodiment 8:

[0139] The embodiment of the present invention provides a combustion optimization method based on a combined cycle unit, which adjusts the premixing valve according to the optimal opening, collects the real-time combustion conditions after the premixing valve is adjusted, and compares them with the predicted combustion conditions, forms a feedback mechanism based on the comparison results, and updates the combustion model, including:

[0140] outputting a predicted combustion condition after executing the optimal opening degree based on the prediction model;

[0141] Perform multi-dimensional comparison between the real-time combustion situation and the predicted combustion situation to obtain a multi-dimensional deviation, perform deviation judgment on the multi-dimensional deviation, if the absolute value of the deviation is lower than the deviation threshold, mark it as normal, obtain the optimization effect, and perform positive feedback on the combustion model; if the absolute value of the deviation is higher than the deviation threshold, mark it as abnormal, obtain a negative adjustment result, and perform negative feedback on the combustion model;

[0142] The combustion model is updated according to the feedback mechanism.

[0143] In this embodiment, the combustion condition is predicted by using a combustion model and data analysis to predict the expected performance of the combustion process at a specific premixing valve opening, including indicators such as temperature, pressure, combustion efficiency and emissions. For example, when the premixing valve opening is set to 30%, the prediction model may output an ideal combustion efficiency of 95%, a temperature of 1200°C, and a NOx emission of 50ppm.

[0144] In this embodiment, the multidimensional deviation refers to the difference between the actual combustion situation and the predicted combustion situation, which is usually a comprehensive comparison of multiple performance indicators. These indicators may include efficiency, temperature, pressure, and emissions, etc., forming a multidimensional space deviation data set. For example, if the actual combustion efficiency is 90%, the temperature is 1250°C, and the NOx emission is 70ppm, and the predicted values ​​are 95%, 1200°C, and 50ppm, respectively, then the deviation is: efficiency deviation = 90%-95% = -5%, temperature deviation = 1250°C-1200°C = +50°C, NOx deviation = 70ppm-50ppm = +20ppm.

[0145] In this embodiment, the deviation threshold is a preset critical value used to determine whether the actual operating conditions are within an acceptable range. If the absolute value of the multi-dimensional deviation exceeds this threshold, the system will be marked as abnormal and trigger negative feedback. For example, the set deviation threshold is 5% (percentage indicator) or 50°C (temperature indicator) and 10ppm (emission indicator). If the deviation in efficiency is 5% or greater, or the temperature deviation exceeds 50°C, an abnormal mark will be triggered.

[0146] In this embodiment, negative feedback refers to the negative adjustment signal applied to the model when there is a large deviation between the performance index output by the combustion model and the actual situation, so as to prompt it to adjust and improve. For example, if the actual operating combustion efficiency deviation is greater than the threshold and is marked as abnormal, the negative feedback to the model may be to require reducing the fuel supply and increasing the air inflow to reduce the temperature, improve the efficiency and reduce emissions.

[0147] In this embodiment, positive feedback refers to a support signal to the model when the performance indicator output by the combustion model is within an acceptable range, so as to promote it to continue to maintain a good operating state. For example, if the actual effect is consistent with the predicted effect and the deviation is less than the threshold, the model will be given positive feedback, such as maintaining the current fuel flow and premix valve settings to ensure efficient operation of the system.

[0148] The working principle and beneficial effects of the above technical solution are: by comparing the combustion situation in real time with the optimal opening output by the prediction model, calculating the multi-dimensional deviation, and judging whether the operation is normal through the set deviation threshold. If the deviation is less than the threshold, it is marked as normal and positive feedback is given to the combustion model to improve the prediction accuracy; if the deviation is greater than the threshold, it is marked as abnormal, and negative feedback is given to prompt the combustion model to adjust and update, thereby optimizing the combustion process, improving efficiency and reducing emissions.

[0149] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A combustion optimization method based on a combined cycle unit, characterized in that: include: Step 1: Monitor the operating parameters of the gas turbine through sensors, evaluate the operating parameters of the gas turbine in combination with the first combustion law, and extract important features from the combustion evaluation results based on the combustion optimization goal; Step 2: Obtain the real-time calorific value and density data of the combustion source, and integrate them with the operating parameters of the gas turbine to obtain the first data set, and perform feature construction on the first data set to obtain a derived feature set, and combine it with the second combustion law to establish a combustion model; Step 3: Combining the combustion model with the historical operation data of the combined cycle unit, a prediction model for the optimal opening of the premixing valve is constructed to obtain the optimal opening of the premixing valve; Step 4: adjusting the premixing valve according to the optimal opening, collecting the real-time combustion conditions after the premixing valve is adjusted, and comparing them with the predicted combustion conditions, forming a feedback mechanism based on the comparison results, and updating the combustion model.

2. The combustion optimization method based on a combined cycle unit according to claim 1, characterized in that: The operating parameters of the gas turbine are monitored by sensors, and the operating parameters are evaluated in combination with the first combustion law. Based on the combustion optimization goal, important features are extracted from the combustion evaluation results, including: Obtain basic equipment information of the combined cycle unit, and obtain the operating parameters of the gas turbine based on the basic equipment information; Establish the combustion relationship between the operating parameters and combustion conditions of different gas engines according to the combustion theory, and evaluate the first combustion law of the combustion relationship under different working conditions in combination with the combustion characteristics to obtain the combustion evaluation result; A combustion optimization target is clarified, and important features related to combustion optimization are extracted from the combustion evaluation results based on the combustion optimization target.

3. The combustion optimization method based on a combined cycle unit according to claim 2, characterized in that: The real-time calorific value and density data of the combustion source are obtained and integrated with the operating parameters of the gas turbine to obtain the first data set, and the first data set is subjected to feature construction to obtain a derived feature set, and the combustion model is established in combination with the second combustion law, including: Based on the important features and the first data set, corresponding domain knowledge and combustion theory are applied to perform feature construction to obtain a derived feature set; deriving a target variable according to the combustion optimization target, discretizing the derived feature set and the target variable, and randomly combining the discretized derived feature set and the target variable to obtain a category combination, and creating a frequency table based on the category combination; Testing the category combinations according to the frequency table, and selecting corresponding category combinations whose correlation between the target variable and the derived feature is higher than a preset correlation from the test results, to generate a significant derived feature set; The combustion influence of each significant derivative feature set on each stage of the combustion process is determined in combination with the second combustion law, and a combustion model is constructed based on the combustion influence and the combustion evaluation result.

4. The combustion optimization method based on a combined cycle unit according to claim 3 is characterized in that: Based on the important features and the first data set, corresponding domain knowledge and combustion theory are applied to perform feature construction to obtain a derived feature set, including: Performing a field analysis on the important features and the first data set based on the combustion optimization goal to determine the fields involved in the important features and the first data set; In combination with the fields involved, corresponding domain knowledge is obtained from the combustion knowledge base, and combustion theories consistent with the combustion optimization goals are obtained. Based on the important features and the first data set, hierarchical feature construction of the fields involved is performed, and the feature construction results of all the fields involved are integrated to obtain a derived feature set.

5. The combustion optimization method based on a combined cycle unit according to claim 3, characterized in that: The combustion influence of each significant derivative feature set on each stage of the combustion process is determined in combination with the second combustion law, and a combustion model is constructed based on the combustion influence and the combustion evaluation result, including: The second combustion law is used to establish a connection between the significant derivative feature set and each stage of the combustion process, and to quantify the combustion impact of each significant derivative feature at each stage. At the same time, the contribution of significant derivative features to the combustion optimization objectives is quantified; A combustion model is constructed based on the combustion influence and contribution combined with the combustion evaluation results.

6. The combustion optimization method based on a combined cycle unit according to claim 1, characterized in that: Combining the combustion model with the historical operation data of the combined cycle unit, a prediction model for the optimal opening of the premixing valve is constructed to obtain the optimal opening of the premixing valve, including: Determine various environmental conditions that affect the opening of the premixing valve by combining the combustion model with historical operating data of the combined cycle unit, obtain baseline data of the opening of the premixing valve of the combined cycle unit under stable operating conditions, and determine the expected value range of the opening of the premixing valve under various environmental conditions based on the baseline data; Identify changes in various environmental conditions according to the expected value range, and analyze the causes of the change identification results to obtain the causes of the changes; Each environmental condition and the corresponding change identification results are matched with the cause of the change one by one, and the opening of the premixing valve is set according to the corresponding results, so as to obtain a prediction model for the optimal opening of the premixing valve and predict the optimal opening of the premixing valve under different environmental conditions.

7. The combustion optimization method based on a combined cycle unit according to claim 6, characterized in that: Each environmental condition and the corresponding change identification results are matched with the change causes one by one, and the opening of the premixing valve is set according to the corresponding results, so as to obtain a prediction model to predict the optimal opening of the premixing valve under different environmental conditions, including: Setting a first rule for adjusting the opening of the premixing valve according to the change identification result and the change cause; A second rule for adjusting the opening of the premixing valve is set according to the environmental conditions and the change identification result; A third rule for adjusting the opening of the premixing valve is set according to environmental conditions and reasons for changes; Based on the first rule, the second rule and the third rule, the fuel chamber temperature characteristics, the combustion source flow characteristics and the air to combustion source ratio characteristics during the combustion process are determined, and a prediction model is constructed to set the calculation formula for the optimal opening of the premixing valve: ； Where A represents the weighted sum of the deviations of each environmental condition; m represents the total number of environmental conditions; k represents the kth environmental condition; ω k (t) weight coefficient of the kth environmental condition; X k represents the actual variable of the kth environmental condition; X r,k represents the reference variable of the kth environmental condition; new Indicates the optimal opening of the premixing valve after adjustment under current conditions; Indicates the reference opening of the premixing valve; O i represents the i-th premixing valve opening value in the historical operation data; n represents the number of premixing valve opening values ​​in the historical operation data; F s (t) represents the current performance index of the combustion process; F q (t) represents the ideal performance index output by the combustion model; τ represents the dynamic adjustment factor; HV represents the real-time calorific value of the combustion source; D represents the density of the combustion source; E s represents the supply of the combustion source; β1, β2, and β3 represent the interaction term coefficient, the nonlinear term coefficient, and the exponential correlation coefficient, respectively; X1, X2, and X3 represent the fuel chamber temperature characteristics, the combustion source flow characteristics, and the air to combustion source ratio characteristics during the combustion process, respectively.

8. The combustion optimization method based on a combined cycle unit according to claim 1, characterized in that: The premixing valve is adjusted according to the optimal opening, the real-time combustion condition after the premixing valve is adjusted is collected, and the real-time combustion condition is compared with the predicted combustion condition, a feedback mechanism is formed based on the comparison result, and the combustion model is updated, including: outputting a predicted combustion condition after executing the optimal opening degree based on the prediction model; Perform multi-dimensional comparison between the real-time combustion situation and the predicted combustion situation to obtain a multi-dimensional deviation, perform deviation judgment on the multi-dimensional deviation, if the absolute value of the deviation is lower than the deviation threshold, mark it as normal, obtain the optimization effect, and perform positive feedback on the combustion model; if the absolute value of the deviation is higher than the deviation threshold, mark it as abnormal, obtain a negative adjustment result, and perform negative feedback on the combustion model; The combustion model is updated according to the feedback mechanism.

Images