Self-adaptive intelligent thermal power generation DCS regulation control method
Through the adaptive intelligent thermal power generation DCS regulation and control method, real-time monitoring and dynamic adjustment of fuel and grid loads is solved, and the traditional methods are difficult to cope with fuel and grid changes, improving the efficiency and environmental adaptability of thermal power generation, reducing pollution and costs .
Patent Information
- Application Number
- CN202411071649.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-06
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-08-06
AI Technical Summary
Traditional thermal power DCS control methods lack real-time data processing capabilities, making it difficult to monitor and dynamically optimize key operating parameters in real time, resulting in a decrease in fuel use efficiency and an increase in environmental pollution, and it is impossible to quickly respond to fuel quality fluctuations and grid load changes.
Adaptive intelligent thermal power generation DCS regulation and control method is adopted, and real-time monitoring and data analysis, dynamic fuel quality evaluation, grid load monitoring and automatic adjustment, combined with Gaussian process regression model and convolutional neural network, real-time monitoring of fuel and grid load is achieved. and dynamically adjust to optimize fuel use efficiency and reduce environmental emissions.
It improves the operating efficiency and environmental adaptability of thermal power generation, ensures the continuity and efficiency of the power generation process, reduces operating costs and harmful emissions, and ensures the stable operation and sustainability of the power generation system.
Smart Images

Figure CN119070392A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of thermal power generation, and in particular to a self-adaptive intelligent thermal power generation DCS regulation and control method. Background Art
[0002] In the field of thermal power generation, traditional distributed control systems (DCS) mainly rely on preset control strategies to manage the power generation process. Although these systems can basically meet daily operational needs, in the face of fuel quality fluctuations, grid load changes and increased environmental protection requirements, traditional methods are often not flexible enough and cannot adapt to the complex and changing operating environment in real time. For example, the uncertainty of fuel quality may lead to a decrease in combustion efficiency and an increase in environmental emissions, while the rapid changes in grid load require the power generation system to be able to quickly adjust the output to ensure the stability of the grid. In addition, increasingly stringent environmental regulations also require power stations to reduce pollutant emissions and improve energy efficiency during operation.
[0003] Current DCS control methods for thermal power generation usually lack efficient real-time data processing capabilities, making it difficult to achieve real-time monitoring and dynamic optimization of key operating parameters, which limits the response speed and adaptability of power stations when faced with changes in fuel quality and fluctuations in grid demand. Therefore, there is an urgent need for an intelligent control method that can perform real-time analysis and dynamic adjustment to improve the operational efficiency of thermal power generation, optimize fuel utilization efficiency, and reduce environmental impact. Summary of the invention
[0004] Based on the above purpose, the present invention provides an adaptive intelligent thermal power generation DCS regulation and control method.
[0005] The adaptive intelligent thermal power generation DCS regulation control method comprises the following steps:
[0006] S1, real-time monitoring and data analysis: sensors are used to monitor key parameters in the power station in real time, including fuel flow, steam pressure, temperature and emission data, and key parameters are analyzed to identify the current operating status of thermal power generation;
[0007] S2, Dynamic Fuel Quality Assessment: Based on the output of real-time monitoring and data analysis, dynamic fuel quality assessment is implemented, and the operating parameters of the combustion equipment are automatically adjusted according to the real-time analyzed fuel sample data to adapt to the changes in fuel quality;
[0008] S3, grid load monitoring: Integrate grid load monitoring mechanism to monitor changes in grid demand in real time, capture real-time data of grid load, provide load change information, and provide data support for DCS control strategy adjustment;
[0009] S4, automatic regulation and environmental control: Based on the results of dynamic fuel quality assessment and grid load monitoring, the DCS receives regulation suggestions and automatically adjusts the control strategy to optimize fuel efficiency and reduce environmental emissions;
[0010] S5, effect evaluation and strategy optimization: After the DCS executes the adjustment control strategy, the effect evaluation information after the adjustment control strategy is collected and analyzed, and the adjustment control strategy is adjusted and optimized based on the analysis results of the effect evaluation information;
[0011] S6, Abnormal monitoring and emergency plan: Set up an abnormal situation handling mechanism. When abnormal key parameters are monitored, the emergency plan will be automatically activated to respond quickly and ensure the stable operation of thermal power generation.
[0012] Furthermore, the real-time monitoring and data analysis in S1 includes:
[0013] S11, Sensor deployment and data collection: Various sensors are deployed in the power station to monitor key parameters in real time. The sensors include flow sensors, pressure sensors, temperature sensors and emission monitoring sensors. The flow sensor is used to monitor the fuel flow, the pressure sensor is used to monitor the steam pressure, the temperature sensor is used to record the temperature, and the emission monitoring sensor is used to monitor the environmental emission data;
[0014] S12, Data Analysis: Real-time analysis of key parameters collected from various sensors using linear regression models to identify data patterns and trends;
[0015] S13, operation status diagnosis: Based on the results of data analysis, identify the current operation status of the thermal power plant, including operation efficiency, operation abnormalities and preventive maintenance needs.
[0016] Furthermore, the dynamic fuel quality assessment in S2 includes:
[0017] S21, data preprocessing: obtaining key parameters of real-time fuel samples from sensors and preprocessing the key parameters, including data cleaning and denoising;
[0018] S22, feature extraction: extract features from the preprocessed key parameters and convert the original key data into feature vectors for evaluation;
[0019] S23, model construction and training: constructing a dynamic fuel quality assessment model based on the feature vector, and using known fuel sample data as a training set to train the dynamic fuel quality assessment model;
[0020] S24, real-time evaluation: after the dynamic fuel quality evaluation model is trained, the fuel sample data collected in real time is input into the dynamic fuel quality evaluation model for real-time evaluation to predict the quality characteristics and change trends of the fuel;
[0021] S25, parameter adjustment: automatically adjust the operating parameters of the combustion equipment, including the air-fuel ratio and the injection speed, based on the results of the real-time evaluation.
[0022] Furthermore, the dynamic fuel quality assessment model adopts a Gaussian process regression model (GPR), and the Gaussian process regression model (GPR) includes:
[0023] Define kernel function: Combine radial basis function (RBF) and Matérn function to adapt to different data smoothness and irregularity. The calculation formula is:
[0024]
[0025] Among them, x and x′ are input feature vectors, θ1 and θ3 are the amplitude parameters of the kernel function, and θ2 and θ4 are the length parameters;
[0026] Training and optimizing the model: Use the maximum likelihood estimation method to optimize the parameters of the kernel function. The calculation formula is:
[0027]
[0028] in, K is the kernel matrix, is the noise variance, I is the identity matrix, y is the response variable vector, and X is the input variable matrix;
[0029] Dynamic update: Introduce online learning mechanism, use new data points (new fuel sample data) to update the Gaussian process regression model. new ,y new ) arrives, the calculation formula is:
[0030]
[0031]
[0032] The updated Gaussian process regression model uses K new and new Make predictions;
[0033] Among them, K new is the updated covariance matrix, y new is the updated response variable vector, k(x,x new ) is the covariance vector between the new data point and the existing data points;
[0034] Prediction and error estimation: Use the optimized Gaussian process regression model to make predictions for new input points x * , use the Gaussian process regression model to make predictions and calculate the standard deviation of the predictions. The calculation formula is:
[0035]
[0036]
[0037] Among them, μ(x * ) is the predicted mean, σ 2 (x * ) is the variance of the prediction.
[0038] Furthermore, the grid load monitoring in S3 includes:
[0039] S31, real-time load data collection: real-time monitoring of the load parameters of the power grid, including total load, load fluctuation, and peak demand;
[0040] S32, introduction of grid load monitoring mechanism and data analysis: Integrate the grid load monitoring mechanism into the DCS, process and analyze the collected load parameters in real time, and identify load change trends and patterns;
[0041] S33, load change information and data support provision: Based on the introduction of the grid load monitoring mechanism and the results of data analysis, a grid load change information report is generated to display the current status and future trends of the grid load, and the load change information report is directly provided to the DCS as data support for adjusting power generation output and optimizing control strategies.
[0042] Furthermore, the real-time load data collection in S31 includes:
[0043] Load sensors monitor total load in real time: Use load sensors to monitor the total load of the power grid in real time. Load sensors are installed on transmission lines or power generation equipment to measure current or power, thereby obtaining the total load of the power grid;
[0044] Current sensor monitors load fluctuations: Use current sensors to monitor grid load fluctuations in real time, and perceive dynamic changes in load by monitoring current changes;
[0045] Power sensors detect peak demand: Power sensors are used to detect the maximum power demand of the power grid within a predetermined time period. Power sensors are usually installed in generators, substations or transmission lines to measure the power output of the power grid.
[0046] Furthermore, the introduction of the power grid load monitoring mechanism and data analysis in S32 include:
[0047] S321, collecting load parameters and real-time processing: DCS collects load parameters of the power grid in real time and performs pre-real-time processing on the collected load parameters. The real-time processing includes data cleaning, denoising and correction;
[0048] S322, load data analysis: using a convolutional neural network (CNN) model to analyze load parameters processed in real time;
[0049] S323, identifying load change trends and patterns: Based on the results of load data analysis, the DCS identifies the change trends and patterns of the grid load, including discovering periodic fluctuations of the load, trends of load changes, and sudden load increases or decreases.
[0050] Furthermore, the convolutional neural network (CNN) model includes:
[0051] Data collation: Data collation of real-time monitored load parameters, including normalization and denoising;
[0052] Stacking of convolutional layers and pooling layers: Multiple convolutional layers and pooling layers are stacked to extract the hierarchical features of the load data. The calculation formula is:
[0053] Convolution operation:
[0054] Pooling operation:
[0055] in, is the feature value at position (i, j) in the output feature map of the lth convolutional layer, F is the convolution kernel size, is the parameter of the convolution kernel of the first layer, m and n represent the rows and columns of the convolution kernel respectively, b (l) is the bias term of the lth layer, is the feature value at position (i, j) in the output feature map of the lth pooling layer, and s is the size of the pooling kernel;
[0056] Multi-scale convolution: Multi-scale convolution operation is introduced, and the load change pattern under different time scales is considered at the same time. The calculation formula is:
[0057]
[0058] Among them, K is the scale number of multi-scale convolution, F k is the convolution kernel size of the kth scale, is the parameter of the l-th layer multi-scale convolution kernel, m and n represent the rows and columns of the convolution kernel respectively, b (l) is the bias term of the lth layer;
[0059] Learning time series features: Combined with the attention mechanism, the learning of time series features is introduced to capture the time dependency of load data. The calculation formula is:
[0060] α t =softmax(W α ·h t +b α );
[0061]
[0062] Among them, h t represents the hidden state of each time step, T represents the length of the time series, and α t is the attention weight at time step t, W α is the attention weight parameter, b α is the attention weight bias;
[0063] Fully connected layer and output layer: The output of the convolutional layer and the temporal feature extraction part is connected to the fully connected layer, and the final prediction or classification is performed through the output layer. The calculation formula is:
[0064] y (l) =σ(w (l) ·x (l-1) +b (l) );
[0065] Among them, y (l) is the output of the lth fully connected layer, W (l) is the weight parameter of the lth layer, x (l-1) is the output of layer l-1, b (l) is the bias term of the lth layer.
[0066] Furthermore, the automatic adjustment and environmental control in S4 includes:
[0067] S41, receiving results: the DCS receives result data from dynamic fuel quality assessment and grid load monitoring;
[0068] S42, analyzing adjustment suggestions: Based on the received result data, the DCS analyzes the adjustment suggestions to determine the control strategy, including adjusting the power generation, fuel supply rate and combustion parameters;
[0069] S43, automatic adjustment of control strategy: DCS automatically adjusts the control strategy based on the results of the analysis and adjustment suggestions to optimize fuel efficiency and reduce environmental emissions, including adjusting the fuel blend ratio, changing the combustion temperature or adjusting the operating parameters of the emission treatment equipment;
[0070] S44, real-time monitoring and feedback: DCS continuously monitors the operation of the adjusted thermal power generation and feeds back effect evaluation information based on the key parameters monitored in real time.
[0071] Furthermore, the effect evaluation and strategy optimization in S5 include:
[0072] S51, evaluation information analysis: The collected effect evaluation information is evaluated using the mean absolute error (MAE) to measure the deviation between the predicted value and the actual value;
[0073] S52, strategy optimization: adjust and optimize the control strategy based on the results of the evaluation information analysis;
[0074] S53, real-time optimization: The optimized control strategy is applied to thermal power generation, and key parameters continue to be collected for monitoring and feedback.
[0075] Beneficial effects of the present invention:
[0076] The present invention can effectively cope with fuel quality changes and grid demand fluctuations through real-time monitoring and data analysis, dynamic fuel quality assessment and grid load monitoring. This integrated monitoring and adjustment strategy not only improves the operational efficiency of thermal power generation, but also enhances the system's adaptability to environmental changes. Real-time data analysis ensures the continuity and efficiency of the power generation process. Through dynamic adjustment strategies, the system can respond to any sudden changes in a timely manner and maintain the stability of the power generation process.
[0077] The present invention, by precisely adjusting the fuel mixing ratio and the combustion temperature, and optimizing the operating parameters of the emission treatment equipment, not only reduces the operating cost, but also significantly reduces harmful emissions, makes a positive contribution to environmental protection and resource conservation, and ensures the sustainability of power generation activities.
[0078] The present invention monitors key parameters in real time and initiates emergency plans in a timely manner. The system can respond to various abnormal situations quickly and effectively, thereby ensuring the stable operation of the power generation system. In addition, the implementation of the effect evaluation and strategy optimization stages further improves the operational safety and efficiency of the system. Through continuous learning and optimization, the entire regulation and control method is made more accurate and efficient. BRIEF DESCRIPTION OF THE DRAWINGS
[0079] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0080] Figure 1A schematic diagram of a control method flow chart of an embodiment of the present invention;
[0081] Figure 2 Schematic diagram of dynamic fuel quality assessment according to an embodiment of the present invention. DETAILED DESCRIPTION
[0082] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.
[0083] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0084] like Figure 1-Figure 2 As shown, the adaptive intelligent thermal power generation DCS regulation control method includes the following steps:
[0085] S1, real-time monitoring and data analysis: sensors are used to monitor key parameters in the power station in real time, including fuel flow, steam pressure, temperature and emission data, and key parameters are analyzed to identify the current operating status of thermal power generation;
[0086] S2, Dynamic Fuel Quality Assessment: Based on the output of real-time monitoring and data analysis, dynamic fuel quality assessment is implemented, and the operating parameters of the combustion equipment are automatically adjusted according to the real-time analyzed fuel sample data to adapt to the changes in fuel quality;
[0087] S3, grid load monitoring: Integrate grid load monitoring mechanism to monitor changes in grid demand in real time, capture real-time data of grid load, provide load change information, and provide data support for DCS control strategy adjustment;
[0088] S4, automatic regulation and environmental control: Based on the results of dynamic fuel quality assessment and grid load monitoring, the DCS receives regulation suggestions and automatically adjusts the control strategy to optimize fuel efficiency and reduce environmental emissions;
[0089] S5, effect evaluation and strategy optimization: After the DCS executes the adjustment control strategy, the effect evaluation information after the adjustment control strategy is collected and analyzed, and the adjustment control strategy is adjusted and optimized based on the analysis results of the effect evaluation information to improve future operation efficiency and response accuracy;
[0090] S6, abnormal monitoring and emergency plan: set up an abnormal situation handling mechanism. When key parameters are monitored to be abnormal, the emergency plan will be automatically activated to quickly respond and ensure the stable operation of thermal power generation;
[0091] Through the above steps, the operational efficiency and environmental adaptability of thermal power generation are significantly improved. By using real-time data analysis and dynamic adjustment strategies, it is possible to effectively respond to changes in fuel quality and fluctuations in grid demand, ensuring the efficiency and stability of the power generation process. In addition, by implementing effective abnormal monitoring and emergency plans, this method not only enhances the reliability of the system, but also optimizes the environmental impact, ensuring continuous environmental protection and resource conservation.
[0092] Real-time monitoring and data analysis in S1 include:
[0093] S11, Sensor deployment and data collection: Various sensors are deployed in the power station to monitor key parameters in real time. The sensors include flow sensors, pressure sensors, temperature sensors and emission monitoring sensors. The flow sensor is used to monitor the fuel flow, the pressure sensor is used to monitor the steam pressure, the temperature sensor is used to record the temperature, and the emission monitoring sensor is used to monitor the environmental emission data;
[0094] S12, Data Analysis: Real-time analysis of key parameters collected from various sensors using linear regression models to identify data patterns and trends;
[0095] The calculation formula of the linear regression model is:
[0096] y=β0+β1x1+β2x2+…+β n x n +∈;
[0097] Among them, y is the dependent variable, x1, x2, …, x n are independent variables, β0,β1,…,β n are model parameters, and ∈ is the error term;
[0098] S13, operation status diagnosis: based on the results of data analysis, identify the current operation status of the thermal power plant, including operation efficiency, operation abnormalities and preventive maintenance needs;
[0099] Through the above steps, it is possible to timely identify and respond to operational changes in the thermal power plant, thereby improving the operational safety and efficiency of the system.
[0100] Dynamic fuel quality assessment in S2 includes:
[0101] S21, data preprocessing: obtaining key parameters of real-time fuel samples from sensors and preprocessing the key parameters, including data cleaning and denoising;
[0102] S22, feature extraction: extract features from the preprocessed key parameters and convert the original key data into feature vectors for evaluation, such as average temperature, humidity change rate, etc.;
[0103] The feature extraction is calculated as follows:
[0104] Average value: Calculate the average value of key parameter data to reflect the central tendency of the data. The calculation formula is:
[0105]
[0106] Where μ is the mean, N is the number of data samples, and x i is the value of the i-th data sample;
[0107] Standard Deviation: Calculate the standard deviation of key parameter data, which indicates the degree of dispersion or variation of the data. The calculation formula is:
[0108]
[0109] Where σ is the standard deviation, N is the number of data samples, and x i is the value of the i-th data sample, and μ is the mean value of the data;
[0110] Correlation coefficient: Calculate the correlation between key parameter data to explore the correlation between different parameters. The calculation formula is:
[0111]
[0112] Where r is the correlation coefficient, N is the number of data samples, and x i and i are the values of the i-th data sample of the two parameters, and are the average values of the two parameters respectively;
[0113] S23, model construction and training: constructing a dynamic fuel quality assessment model based on the feature vector, and using known fuel sample data as a training set to train the dynamic fuel quality assessment model;
[0114] Fuel sample data includes:
[0115] Fuel composition: includes the content of various chemical components in the fuel, such as carbon, hydrogen, oxygen, sulfur and other elements, usually expressed as percentage or mass fraction;
[0116] Volatile matter content: indicates the content of combustible substances volatilized in the fuel during heating, usually expressed as a percentage;
[0117] Ash content: indicates the amount of non-combustible matter in the fuel, usually expressed as a percentage;
[0118] Calorific value: The energy released by a fuel per unit mass or volume, usually expressed in joules per gram (J / g) or kilojoules per cubic meter (kJ / m 3 )express;
[0119] Density: Indicates the density of the fuel, usually expressed in kg / m3 or g / ml;
[0120] Moisture content: Indicates the amount of water in the fuel, usually expressed as a percentage or absolute humidity;
[0121] Particle size distribution: indicates the size distribution of fuel particles, usually expressed as a percentage of particle diameter or particle size range;
[0122] S24, real-time evaluation: after the dynamic fuel quality evaluation model is trained, the fuel sample data collected in real time is input into the dynamic fuel quality evaluation model for real-time evaluation to predict the quality characteristics and change trends of the fuel;
[0123] S25, parameter adjustment: according to the results of real-time evaluation, the operating parameters of the combustion equipment, including air-fuel ratio and injection speed, are automatically adjusted. The adjustment strategy is based on the output of the dynamic fuel quality evaluation model, aiming to optimize the combustion process and adapt to changes in fuel quality;
[0124] Through the above steps, it is possible to realize a dynamic evaluation of the fuel quality and automatically adjust the operating parameters of the combustion equipment according to the evaluation results, thereby improving the combustion efficiency and the stability of the system.
[0125] The dynamic fuel quality assessment model adopts the Gaussian process regression model (GPR), which includes:
[0126] Define kernel function: Combine radial basis function (RBF) and Matérn function to adapt to different data smoothness and irregularity. The calculation formula is:
[0127]
[0128] Among them, x and x′ are input feature vectors, representing the features of two different data points, θ1 and θ3 are the amplitude parameters of the kernel function, which determine the amplitude of the function value changing with x and x′, and θ2 and θ4 are length parameters, which control the sensitivity of the function value to the difference between the input x and x′.
[0129] Training and optimizing the model: Use the maximum likelihood estimation method to optimize the parameters of the kernel function. The calculation formula is:
[0130]
[0131] in, K is the kernel matrix, is the noise variance, I is the identity matrix, y is the response variable vector, containing the output values of all observation points, and X is the input variable matrix, containing the eigenvalues of all observation points;
[0132] Dynamic update: In order to adapt to the dynamic changes of fuel parameters over time, the model can be updated online. An online learning mechanism is introduced to update the Gaussian process regression model with new data points (new fuel sample data) without retraining from scratch. new ,y new ) arrives, the calculation formula is:
[0133]
[0134]
[0135] The updated Gaussian process regression model uses K new and new Make predictions;
[0136] Among them, K new is the updated covariance matrix, including the covariance of the new data point, y new is the updated response variable vector, including the response value of the new data point, k(x,x new ) is the covariance vector between the new data point and the existing data points;
[0137] Prediction and Error Estimation: Use the optimized Gaussian process regression model to make predictions and estimate the uncertainty of the predictions for new input points x * , use the Gaussian process regression model to make predictions and calculate the standard deviation of the predictions. The calculation formula is:
[0138]
[0139]
[0140] Among them, μ(x *) is the predicted mean, the predicted response based on the new input point, σ 2 (x * ) is the variance of the prediction, which indicates the uncertainty of the prediction;
[0141] Through the above steps, the GPR model can not only handle complex fuel data characteristics, but also dynamically adapt to new data and provide continuous fuel quality assessment, which makes the model more flexible and effective in practical applications.
[0142] Grid load monitoring in S3 includes:
[0143] S31, real-time load data collection: real-time monitoring of the load parameters of the power grid, including total load, load fluctuation, and peak demand;
[0144] S32, introduction of grid load monitoring mechanism and data analysis: Integrate the grid load monitoring mechanism into the DCS, process and analyze the collected load parameters in real time, and identify load change trends and patterns;
[0145] S33, Load change information and data support provision: Based on the introduction of the grid load monitoring mechanism and the results of data analysis, a grid load change information report is generated to display the current status and future trend of the grid load, and the load change information report is directly provided to the DCS as data support for adjusting the power generation output and optimizing the control strategy, ensuring that the power generation operation responds to the real-time needs of the grid and improving the efficiency and stability of power production;
[0146] Through the above steps, grid load monitoring not only improves the responsiveness to changes in grid demand, but also enhances the flexibility and economic benefits of power station operation, providing important support for the stable operation of the entire power system.
[0147] Real-time load data collection in S31 includes:
[0148] Load sensors monitor total load in real time: Use load sensors to monitor the total load of the power grid in real time. Load sensors are installed on transmission lines or power generation equipment to measure current or power, thereby obtaining the total load of the power grid;
[0149] Current sensor monitoring load fluctuation: Use current sensors to monitor grid load fluctuations in real time, and perceive dynamic changes in load by monitoring current changes, such as sudden load increases or decreases;
[0150] Power sensors detect peak demand: Power sensors are used to detect the maximum power demand of the power grid within a predetermined time period. Power sensors are usually installed in generators, substations or transmission lines to measure the power output of the power grid.
[0151] The introduction of the grid load monitoring mechanism and data analysis in S32 include:
[0152] S321, collecting load parameters and real-time processing: DCS collects the load parameters of the power grid in real time and performs pre-real-time processing on the collected load parameters. The real-time processing includes data cleaning, denoising and correction to ensure the accuracy and reliability of the data;
[0153] S322, load data analysis: using a convolutional neural network (CNN) model to analyze load parameters processed in real time;
[0154] S323, Identify load change trends and patterns: Based on the results of load data analysis, DCS identifies the change trends and patterns of the power grid load, including discovering periodic fluctuations in load, trends in load changes, and sudden increases or decreases in load. Identifying these trends and patterns helps to formulate corresponding regulation strategies to ensure the stability and efficiency of power grid operation.
[0155] The Convolutional Neural Network (CNN) model includes:
[0156] Data collation: Data collation of real-time monitored load parameters, including normalization and denoising, to improve the robustness and accuracy of the model;
[0157] Stacking of convolutional layers and pooling layers: Multiple convolutional layers and pooling layers are stacked to extract the hierarchical features of the load data. The calculation formula is:
[0158] Convolution operation:
[0159] Pooling operation:
[0160] in, is the feature value at position (i, j) in the output feature map of the lth convolutional layer, F is the convolution kernel size, is the parameter of the convolution kernel of the first layer, m and n represent the rows and columns of the convolution kernel respectively, b (l) is the bias term of the lth layer, is the feature value at position (i, j) in the output feature map of the lth pooling layer, and s is the size of the pooling kernel;
[0161] Multi-scale convolution: Multi-scale convolution operation is introduced to consider the load change patterns at different time scales to capture more comprehensive feature information. The calculation formula is:
[0162]
[0163] Among them, K is the scale number of multi-scale convolution, F k is the convolution kernel size of the kth scale, is the parameter of the l-th layer multi-scale convolution kernel, m and n represent the rows and columns of the convolution kernel respectively, b (l) is the bias term of the lth layer;
[0164] Learning time series features: Combined with the attention mechanism, the learning of time series features is introduced to capture the time dependency of load data. The calculation formula is:
[0165] α t =softmax(W α ·h t +b α );
[0166]
[0167] Among them, h t represents the hidden state of each time step, T represents the length of the time series, and α t is the attention weight at time step t, W α is the attention weight parameter, b α is the attention weight bias;
[0168] Fully connected layer and output layer: The output of the convolutional layer and the temporal feature extraction part is connected to the fully connected layer, and the final prediction or classification is performed through the output layer. The calculation formula is:
[0169] y (l) =σ(w (l) ·x (l-1) +b (l) );
[0170] Among them, y (l) is the output of the lth fully connected layer, W (l) is the weight parameter of the lth layer, x (l-1) is the output of layer l-1, b (l) is the bias term of the lth layer;
[0171] Through the above content, not only can spatial features be captured, but also the attention mechanism can be used to learn temporal features, which can better adapt to the dynamic changes of real-time load data and more accurately predict the changing trends and patterns of power grid load, thereby providing more effective support for the operation of power stations and ensuring the stability and reliability of the power grid.
[0172] The automatic regulation and environmental control in S4 include:
[0173] S41, receiving results: the DCS receives result data from dynamic fuel quality assessment and grid load monitoring;
[0174] S42, analyzing adjustment suggestions: Based on the received result data, the DCS analyzes the adjustment suggestions to determine the control strategy, including adjusting the power generation, fuel supply rate and combustion parameters;
[0175] S43, automatic adjustment of control strategy: DCS automatically adjusts the control strategy based on the results of the analysis and adjustment suggestions to optimize fuel efficiency and reduce environmental emissions, including adjusting the fuel blend ratio, changing the combustion temperature or adjusting the operating parameters of the emission treatment equipment;
[0176] S44, real-time monitoring and feedback: DCS continuously monitors the operation of the adjusted thermal power generation and feeds back effect evaluation information based on the key parameters monitored in real time;
[0177] Through the above steps, automatic regulation and environmental control can quickly respond to and adjust the control strategy of the power generation system according to real-time changes in dynamic fuel quality and grid load conditions, thereby optimizing fuel utilization efficiency and reducing environmental emissions.
[0178] The effect evaluation and strategy optimization in S5 include:
[0179] S51, evaluation information analysis: The collected effect evaluation information is evaluated using the mean absolute error (MAE) to measure the deviation between the predicted value and the actual value;
[0180] The calculation formula for the mean absolute error MAE is:
[0181]
[0182] Among them, y i is the actual value, is the predicted value, n is the number of samples;
[0183] S52, strategy optimization: adjust and optimize the control strategy based on the results of the evaluation information analysis;
[0184] S53, real-time optimization: The optimized control strategy is applied to thermal power generation to ensure that the system operates in the best condition and continues to collect key parameters for monitoring and feedback;
[0185] Through the above steps, the effect evaluation and strategy optimization stage helps improve the accuracy and response speed of adjusting the control strategy by continuously collecting and analyzing real-time data to adapt to changes in factors such as fuel quality and grid load, thereby optimizing the operating efficiency and stability of the thermal power generation system.
[0186] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention is limited to these examples. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity.
[0187] The present invention is intended to cover all such substitutions, modifications and variations that fall within the broad scope of the claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. Adaptive intelligent thermal power generation DCS regulation and control method, characterized in that: The following steps are involved: S1, real-time monitoring and data analysis: sensors are used to monitor key parameters in the power station in real time, including fuel flow, steam pressure, temperature and emission data, and key parameters are analyzed to identify the current operating status of thermal power generation; S2, Dynamic Fuel Quality Assessment: Based on the output of real-time monitoring and data analysis, dynamic fuel quality assessment is implemented, and the operating parameters of the combustion equipment are automatically adjusted according to the real-time analyzed fuel sample data to adapt to the changes in fuel quality; S3, grid load monitoring: Integrate grid load monitoring mechanism to monitor changes in grid demand in real time, capture real-time data of grid load, provide load change information, and provide data support for DCS control strategy adjustment; S4, automatic regulation and environmental control: Based on the results of dynamic fuel quality assessment and grid load monitoring, the DCS receives regulation suggestions and automatically adjusts the control strategy to optimize fuel efficiency and reduce environmental emissions; S5, effect evaluation and strategy optimization: After the DCS executes the adjustment control strategy, the effect evaluation information after the adjustment control strategy is collected and analyzed, and the adjustment control strategy is adjusted and optimized based on the analysis results of the effect evaluation information; S6, Abnormal monitoring and emergency plan: Set up an abnormal situation handling mechanism. When abnormal key parameters are monitored, the emergency plan will be automatically activated to respond quickly and ensure the stable operation of thermal power generation.
2. The adaptive intelligent thermal power generation DCS regulation and control method according to claim 1 is characterized in that: The real-time monitoring and data analysis in S1 includes: S11, Sensor deployment and data collection: Various sensors are deployed in the power station to monitor key parameters in real time. The sensors include flow sensors, pressure sensors, temperature sensors and emission monitoring sensors. The flow sensor is used to monitor the fuel flow, the pressure sensor is used to monitor the steam pressure, the temperature sensor is used to record the temperature, and the emission monitoring sensor is used to monitor the environmental emission data; S12, Data Analysis: Real-time analysis of key parameters collected from various sensors using linear regression models to identify data patterns and trends; S13, operation status diagnosis: Based on the results of data analysis, identify the current operation status of the thermal power plant, including operation efficiency, operation abnormalities and preventive maintenance needs.
3. The adaptive intelligent thermal power generation DCS regulation and control method according to claim 1 is characterized in that: The dynamic fuel quality assessment in S2 includes: S21, data preprocessing: obtaining key parameters of real-time fuel samples from sensors and preprocessing the key parameters, including data cleaning and denoising; S22, feature extraction: extract features from the preprocessed key parameters and convert the original key data into feature vectors for evaluation; S23, model construction and training: constructing a dynamic fuel quality assessment model based on the feature vector, and using known fuel sample data as a training set to train the dynamic fuel quality assessment model; S24, real-time evaluation: after the dynamic fuel quality evaluation model is trained, the fuel sample data collected in real time is input into the dynamic fuel quality evaluation model for real-time evaluation to predict the quality characteristics and change trends of the fuel; S25, parameter adjustment: automatically adjust the operating parameters of the combustion equipment, including the air-fuel ratio and the injection speed, based on the results of the real-time evaluation.
4. The adaptive intelligent thermal power generation DCS regulation and control method according to claim 3 is characterized in that: The dynamic fuel quality assessment model adopts a Gaussian process regression model, which includes: Define kernel function: Combine radial basis function and Matérn function to adapt to different data smoothness and irregularity. The calculation formula is: Among them, x and x′ are input feature vectors, θ1 and θ3 are the amplitude parameters of the kernel function, and θ2 and θ4 are the length parameters; Training and optimizing the model: Use the maximum likelihood estimation method to optimize the parameters of the kernel function. The calculation formula is: in, K is the kernel matrix, is the noise variance, I is the identity matrix, y is the response variable vector, and X is the input variable matrix; Dynamic update: Introduce online learning mechanism to update Gaussian process regression model with new data points. new ,y new ) arrives, the calculation formula is: The updated Gaussian process regression model uses K new and new Make predictions; Among them, K new is the updated covariance matrix, y new is the updated response variable vector, k(x, x new ) is the covariance vector between the new data point and the existing data points; Prediction and error estimation: Use the optimized Gaussian process regression model to make predictions for new input points x * , use the Gaussian process regression model to make predictions and calculate the standard deviation of the predictions. The calculation formula is: Among them, μ(x * ) is the predicted mean, σ 2 (x * ) is the variance of the prediction.
5. The adaptive intelligent thermal power generation DCS regulation and control method according to claim 1 is characterized in that: The grid load monitoring in S3 includes: S31, real-time load data collection: real-time monitoring of the load parameters of the power grid, including total load, load fluctuation, and peak demand; S32, introduction of grid load monitoring mechanism and data analysis: Integrate the grid load monitoring mechanism into the DCS, process and analyze the collected load parameters in real time, and identify load change trends and patterns; S33, load change information and data support provision: Based on the introduction of the grid load monitoring mechanism and the results of data analysis, a grid load change information report is generated to display the current status and future trends of the grid load, and the load change information report is directly provided to the DCS as data support for adjusting power generation output and optimizing control strategies.
6. The adaptive intelligent thermal power generation DCS regulation and control method according to claim 5 is characterized in that: The real-time load data collection in S31 includes: Load sensors monitor total load in real time: Use load sensors to monitor the total load of the power grid in real time. Load sensors are installed on transmission lines or power generation equipment to measure current or power, thereby obtaining the total load of the power grid; Current sensor monitors load fluctuations: Use current sensors to monitor grid load fluctuations in real time, and perceive dynamic changes in load by monitoring current changes; Power sensors detect peak demand: Power sensors are used to detect the maximum power demand of the power grid within a predetermined time period. Power sensors are usually installed in generators, substations or transmission lines to measure the power output of the power grid.
7. The adaptive intelligent thermal power generation DCS regulation and control method according to claim 6 is characterized in that: The introduction of the power grid load monitoring mechanism and data analysis in S32 include: S321, collecting load parameters and real-time processing: DCS collects load parameters of the power grid in real time and performs pre-real-time processing on the collected load parameters. The real-time processing includes data cleaning, denoising and correction; S322, load data analysis: using a convolutional neural network model to analyze load parameters for real-time processing; S323, identifying load change trends and patterns: Based on the results of load data analysis, the DCS identifies the change trends and patterns of the grid load, including discovering periodic fluctuations of the load, trends of load changes, and sudden load increases or decreases.
8. The adaptive intelligent thermal power generation DCS regulation and control method according to claim 7 is characterized in that: The convolutional neural network model includes: Data collation: Data collation of real-time monitored load parameters, including normalization and denoising; Stacking of convolutional layers and pooling layers: Multiple convolutional layers and pooling layers are stacked to extract the hierarchical features of the load data. The calculation formula is: Convolution operation: Pooling operation: in, is the feature value at position (i, j) in the output feature map of the lth convolutional layer, F is the convolution kernel size, is the parameter of the convolution kernel of the lth layer, m and n represent the rows and columns of the convolution kernel respectively, b(l) is the bias term of the lth layer, is the feature value at position (i, j) in the output feature map of the lth pooling layer, and s is the size of the pooling kernel; Multi-scale convolution: Multi-scale convolution operation is introduced, and the load change pattern under different time scales is considered at the same time. The calculation formula is: Among them, K is the scale number of multi-scale convolution, F k is the convolution kernel size of the kth scale, is the parameter of the multi-scale convolution kernel of the lth layer, m and n represent the rows and columns of the convolution kernel respectively, and b(l) is the bias term of the lth layer; Learning time series features: Combined with the attention mechanism, the learning of time series features is introduced to capture the time dependency of load data. The calculation formula is: a t =softmax(W α ·h t +b α ); Among them, h t represents the hidden state of each time step, T represents the length of the time series, and α t is the attention weight at time step t, W α is the attention weight parameter, b α is the attention weight bias; Fully connected layer and output layer: The output of the convolutional layer and the temporal feature extraction part is connected to the fully connected layer, and the final prediction or classification is performed through the output layer. The calculation formula is: y (l) =σ(W (l) ·x (l-1 )+b (l) ); Among them, y (l) is the output of the lth fully connected layer, W (l) is the weight parameter of the lth layer, x (l-1) is the output of layer l-1, b (l) is the bias term of the lth layer.
9. The adaptive intelligent thermal power generation DCS regulation and control method according to claim 1 is characterized in that: The automatic adjustment and environmental control in S4 include: S41, receiving results: the DCS receives result data from dynamic fuel quality assessment and grid load monitoring; S42, analyzing adjustment suggestions: Based on the received result data, the DCS analyzes the adjustment suggestions to determine the control strategy, including adjusting the power generation, fuel supply rate and combustion parameters; S43, automatic adjustment of control strategy: DCS automatically adjusts the control strategy based on the results of the analysis and adjustment suggestions to optimize fuel efficiency and reduce environmental emissions, including adjusting the fuel blend ratio, changing the combustion temperature or adjusting the operating parameters of the emission treatment equipment; S44, real-time monitoring and feedback: DCS continuously monitors the operation of the adjusted thermal power generation and feeds back effect evaluation information based on the key parameters monitored in real time.
10. The adaptive intelligent thermal power generation DCS regulation and control method according to claim 9 is characterized in that: The effect evaluation and strategy optimization in S5 include: S51, evaluation information analysis: The collected effect evaluation information is evaluated using the mean absolute error (MAE) to measure the deviation between the predicted value and the actual value; S52, strategy optimization: adjust and optimize the control strategy based on the results of the evaluation information analysis; S53, real-time optimization: The optimized control strategy is applied to thermal power generation, and key parameters continue to be collected for monitoring and feedback.
Citation Information
Patent Citations
Cooperative control method and system for furnace rear environmental protection equipment
CN113031552A
Automatic boiler combustion adjusting method based on AI
CN117704416A
Intelligent monitoring system for urban infrastructure
CN118348883A
Method and system for data analysis and synthesis
US20110035346A1
