Thermal power plant emission monitoring method and device, electronic equipment and storage medium

Abstract

The invention discloses a thermal power plant emission monitoring method and device, electronic equipment and a storage medium. According to the main technical scheme, the method comprises the steps of obtaining thermal power plant emission monitoring data at a first moment and environmental parameters at the first moment; inputting the thermal power plant emission monitoring data at the first moment and the real-time environmental parameters at the first moment into a pre-trained environmental protection index model to obtain thermal power plant emission prediction data at a second moment output by the pre-trained environmental protection index model; and when the thermal power plant emission prediction data at the second moment exceeds a preset emission threshold value, triggering an alarm and generating a rectification suggestion. Compared with the prior art, according to the embodiment of the invention, the pollutant emission trend is effectively pre-judged by collecting the pollutant data and the environmental parameters discharged by the thermal power plant, extracting the nonlinear features by using the pollutant emission data and the environmental parameters and combining the time sequence analysis, and the possible standard exceeding risk is recognized in advance.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a method and apparatus for monitoring emissions from thermal power plants, electronic equipment, and storage medium. Background Technology

[0002] Thermal power plants are one of the main methods of electricity production, but they emit large amounts of pollutants during operation, such as sulfur dioxide (SO2), nitrogen oxides (NOx) and soot. The emission of these pollutants is one of the important causes of air pollution.

[0003] Real-time and accurate monitoring of pollutants emitted by thermal power plants and the implementation of effective control measures are crucial for environmental protection. Traditional monitoring systems are limited by the accuracy of data acquisition equipment and environmental interference. Especially under complex operating conditions such as high temperature and high humidity, the acquired data may contain noise, making it difficult to accurately reflect the level of pollutant emissions. Existing systems are mostly based on simple data processing methods, unable to predict pollutant emission trends or provide timely warnings of potential exceedances. Traditional systems typically only provide alarm functions, but lack targeted rectification suggestions for different types and degrees of exceedances, making it difficult to efficiently address complex pollution problems. Historical data is mostly stored in a simple manner, failing to fully utilize data for multi-dimensional statistical analysis, which is detrimental to decision-making support for environmental management and regulatory departments of thermal power plants. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, and storage medium for monitoring emissions from thermal power plants. Its main objective is to enhance the pollutant emission monitoring capabilities of thermal power plants.

[0005] According to a first aspect of this disclosure, a method for monitoring emissions from a thermal power plant is provided, comprising:

[0006] Acquire the first-time emission monitoring data of the thermal power plant and the first-time environmental parameters;

[0007] The emission monitoring data of the thermal power plant at the first moment and the real-time environmental parameters at the first moment are input into the pre-trained environmental protection index model to obtain the emission prediction data of the thermal power plant at the second moment output by the pre-trained environmental protection index model.

[0008] When the predicted emissions data of the thermal power plant at the second time point exceeds the preset emission threshold, an alarm is triggered and rectification suggestions are generated.

[0009] Optionally, after triggering an alarm and generating rectification suggestions when the predicted emissions data of the thermal power plant at the second time point exceeds a preset emission threshold, the method further includes:

[0010] The emission prediction data of the thermal power plant at the second time point is stored, and the Dolby result of the emission prediction data of the thermal power plant and the preset emission threshold is stored, and the compliance rate of the emission prediction data of the thermal power plant is calculated.

[0011] Optionally, the preset emission thresholds include a first preset emission threshold, a second preset emission threshold, and a third preset emission threshold; triggering an alarm and generating rectification suggestions when the predicted emission data of the thermal power plant at the second time exceeds the preset emission thresholds further includes:

[0012] When the predicted emissions data of the thermal power plant at the second moment exceeds the first preset emission threshold, a minor exceedance alarm is triggered, and rectification suggestions are generated, including adjusting the operating parameters of the desulfurization equipment and increasing the amount of desulfurizing agent sprayed.

[0013] When the predicted emissions data of the thermal power plant at the second time point exceeds the second preset emission threshold, a moderate exceedance alarm is triggered, and rectification suggestions are generated, including conducting inspections of desulfurization equipment, optimizing the flow distribution in the absorption tower, and adjusting the boiler coal ratio.

[0014] When the predicted emissions data of the thermal power plant at the second moment exceeds the third preset emission threshold, a serious exceedance alarm is triggered, and rectification suggestions are generated, including immediately shutting down the plant to inspect the desulfurization equipment and switching the flue gas treatment process to the backup equipment.

[0015] Among them, the different rectification suggestions have different priorities.

[0016] Optionally, the step of inputting the thermal power plant emission monitoring data at the first moment and the real-time environmental parameters at the first moment into the pre-trained environmental protection index model to obtain the thermal power plant emission prediction data for the second moment output by the pre-trained environmental protection index model includes:

[0017] The pre-trained environmental protection indicator model processes the emission monitoring data of the thermal power plant based on dynamic weighted normalization;

[0018] The specific formula for dynamic weighted normalization is as follows:

[0019]

[0020] Among them, X i The value of i in the emission monitoring data of the thermal power plant; X′ i The normalized eigenvalues; w i The feature weights are determined by the variance of the feature, Var(X). i The larger the variance, the smaller the weight.

[0021] Optionally, the step of storing the predicted emissions data of the thermal power plant at the second time point, and storing the predicted emissions data of the thermal power plant and the Dolby result of the preset emission threshold, and calculating the compliance rate of the predicted emissions data of the thermal power plant further includes:

[0022] The compliance rate report is generated according to a preset time period; wherein the compliance rate report includes at least one of the following: average value, peak value and compliance rate of pollutant emission concentration, number of exceedance events in different time periods and distribution of exceedance types.

[0023] According to a second aspect of this disclosure, a monitoring device for emissions from a thermal power plant is provided, comprising:

[0024] The acquisition unit is used to acquire the first-time emission monitoring data of the thermal power plant and the first-time environmental parameters;

[0025] The prediction unit is used to input the power plant emission monitoring data at the first moment and the real-time environmental parameters at the first moment into the pre-trained environmental protection index model to obtain the power plant emission prediction data at the second moment output by the pre-trained environmental protection index model.

[0026] The alarm unit is used to trigger an alarm and generate rectification suggestions when the predicted emission data of the thermal power plant at the second time exceeds the preset emission threshold.

[0027] Optionally, the device further includes:

[0028] The storage unit is used to, after the alarm unit triggers an alarm and generates a rectification suggestion when the predicted emission data of the thermal power plant at the second time exceeds the preset emission threshold, store the predicted emission data of the thermal power plant at the second time and the Dolby result of the predicted emission data of the thermal power plant and the preset emission threshold, and calculate the compliance rate of the predicted emission data of the thermal power plant.

[0029] Optionally, the preset emission threshold includes a first preset emission threshold, a second preset emission threshold, and a third preset emission threshold; the alarm unit is further configured to:

[0030] When the predicted emissions data of the thermal power plant at the second moment exceeds the first preset emission threshold, a minor exceedance alarm is triggered, and rectification suggestions are generated, including adjusting the operating parameters of the desulfurization equipment and increasing the amount of desulfurizing agent sprayed.

[0031] When the predicted emissions data of the thermal power plant at the second time point exceeds the second preset emission threshold, a moderate exceedance alarm is triggered, and rectification suggestions are generated, including conducting inspections of desulfurization equipment, optimizing the flow distribution in the absorption tower, and adjusting the boiler coal ratio.

[0032] When the predicted emissions data of the thermal power plant at the second moment exceeds the third preset emission threshold, a serious exceedance alarm is triggered, and rectification suggestions are generated, including immediately shutting down the plant to inspect the desulfurization equipment and switching the flue gas treatment process to the backup equipment.

[0033] Among them, the different rectification suggestions have different priorities.

[0034] Optionally, the prediction unit is further configured to:

[0035] The pre-trained environmental protection indicator model processes the emission monitoring data of the thermal power plant based on dynamic weighted normalization;

[0036] The specific formula for dynamic weighted normalization is as follows:

[0037]

[0038] Among them, X i The value of i in the emission monitoring data of the thermal power plant; X′ i The normalized eigenvalues; w i The feature weights are determined by the variance of the feature, Var(X). i The larger the variance, the smaller the weight.

[0039] Optionally, the storage unit is further used for:

[0040] The compliance rate report is generated according to a preset time period; wherein the compliance rate report includes at least one of the following: average value, peak value and compliance rate of pollutant emission concentration, number of exceedance events in different time periods and distribution of exceedance types.

[0041] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0042] At least one processor; and

[0043] A memory communicatively connected to the at least one processor; wherein,

[0044] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0045] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0046] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0047] The monitoring method, apparatus, electronic equipment, and storage medium for thermal power plant emissions disclosed in this disclosure mainly include: acquiring thermal power plant emission monitoring data and environmental parameters at a first moment; inputting the thermal power plant emission monitoring data and real-time environmental parameters at the first moment into a pre-trained environmental protection indicator model to obtain the thermal power plant emission prediction data for a second moment output by the pre-trained environmental protection indicator model; triggering an alarm and generating rectification suggestions when the thermal power plant emission prediction data at the second moment exceeds a preset emission threshold. Compared with related technologies, the embodiments of this application effectively predict pollutant emission trends and identify potential exceedance risks in advance by collecting pollutant emission data and environmental parameters from thermal power plants, extracting nonlinear features from the pollutant emission data and environmental parameters, and combining them with time series analysis.

[0048] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0049] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0050] Figure 1 A schematic flowchart illustrating a method for monitoring emissions from a thermal power plant, provided in an embodiment of this disclosure;

[0051] Figure 2 This is a schematic block diagram of a thermal power plant environmental protection intelligent monitoring system provided in an embodiment of the present disclosure;

[0052] Figure 3 A schematic flowchart illustrating a method for monitoring emissions from a thermal power plant, provided in an embodiment of this disclosure;

[0053] Figure 4 A schematic diagram of the structure of a monitoring device for emissions from a thermal power plant provided in an embodiment of this disclosure;

[0054] Figure 5 A schematic diagram of the structure of a monitoring device for emissions from a thermal power plant provided in an embodiment of this disclosure;

[0055] Figure 6 A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation

[0056] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0057] The following description, with reference to the accompanying drawings, outlines a method, apparatus, electronic device, and storage medium for monitoring emissions from thermal power plants according to embodiments of this disclosure.

[0058] Figure 1 This is a schematic flowchart illustrating a method for monitoring emissions from a thermal power plant, provided in an embodiment of this disclosure.

[0059] like Figure 1 As shown, the method includes the following steps:

[0060] Step 101: Obtain the first moment's emission monitoring data of the thermal power plant and the first moment's environmental parameters.

[0061] In some embodiments, the emission monitoring data of thermal power plants is updated in real time with a sampling cycle of one minute, including the concentration data of sulfur dioxide, nitrogen oxides, and particulate matter. In some embodiments, high-precision sensors such as laser particulate matter sensors and electrochemical gas sensors can be used to collect pollutant concentrations in real time. This application does not limit the collection equipment.

[0062] Environmental parameters, including temperature, humidity, wind speed, and wind direction data, can be obtained through industrial Internet of Things (IoT) data interfaces or through relevant testing institutions. This application embodiment does not limit these parameters.

[0063] Please see Figure 2 , Figure 2 This is a schematic block diagram of a thermal power plant environmental protection intelligent monitoring system provided in an embodiment of this application. In some embodiments, during the data acquisition process, the data processing and analysis module needs to filter sensor noise. This embodiment uses the Kalman filter formula for processing, and the specific steps are as follows:

[0064] 1) Prediction Update:

[0065]

[0066] P k|k-1 =A·P k-1|k-1 ·A T +Q

[0067] in, Let A be the predicted state value (e.g., pollutant concentration) at time k; A is the state transition matrix, which describes the dynamic model of the system state. Let B be the estimated state value at time k-1; B is the control input matrix; u k To control inputs (such as the impact of changes in equipment operating status on pollutant concentrations); P k|k-1 is the prediction covariance matrix; Q is the process noise covariance matrix, representing the random disturbances in the state transition.

[0068] 2) Measurement Update:

[0069] K k =P k|k-1 ·H T ·(HP k|k-1 ·H T +R t ) -1

[0070]

[0071] P k|k =(IK k ·H)·P k|k-1

[0072] Among them, K k The Kalman gain is used to balance the weights of predicted and observed data; z k R represents the observed value at time k (sensor-collected value, such as NOx concentration); H is the observation matrix, which maps the state space to the observation space; t The noise covariance matrix is ​​measured to represent the random error in the sensor-acquired data; P represents the updated state value at time k. k|k Let be the updated covariance matrix, representing the uncertainty of the estimated state.

[0073] To enhance the Kalman filter's adaptability to sensor noise variations, this embodiment introduces a dynamic adjustment of the measurement noise covariance matrix R. t The strategy is:

[0074]

[0075] Where R0 is the initial measurement noise covariance matrix; β is the dynamic adjustment coefficient, representing the effect of noise changes on R0. t The degree of influence; Δt is the error between the sensor's collected value and the reference value at time k; Δ max This represents the maximum permissible range of error.

[0076] In this embodiment, the sensor is automatically calibrated every 24 hours, and the error Δt between the collected value and the reference value is recorded; R is dynamically updated based on the error.t Real-time adjustment of filtering to assess the reliability of collected data; when R t When the set threshold is exceeded, a sensor maintenance prompt is triggered.

[0077] This application embodiment dynamically adjusts R. t It can respond in real time to the effects of sensor aging or increased environmental noise, improve the filter's adaptability to the acquired data, and combine Kalman filter prediction updates with measurement updates to smooth the acquired data and reduce the interference of abnormal fluctuations on subsequent analysis.

[0078] Step 102: Input the power plant emission monitoring data at the first moment and the real-time environmental parameters at the first moment into the pre-trained environmental protection index model to obtain the power plant emission prediction data at the second moment output by the pre-trained environmental protection index model.

[0079] In some embodiments, a suitable pre-trained environmental indicator model can be pre-trained based on historical data, which can process emission data and environmental parameters from thermal power plants and predict future emissions.

[0080] Based on the model's requirements, extract features from the data. This includes selecting variables highly correlated with emissions or constructing new features to improve the model's predictive ability. Input the preprocessed data into the pre-trained model, ensuring the data format matches the model's input layer requirements. Run the model to obtain predicted emissions data from the power plant at the second time point. The predicted data includes the expected emission concentrations of various pollutants.

[0081] Step 103: When the predicted emission data of the thermal power plant at the second time exceeds the preset emission threshold, an alarm is triggered and a rectification suggestion is generated.

[0082] In some embodiments, reasonable emission thresholds may be set in accordance with environmental regulations and standards to ensure that the impact of emission levels on the environment and public health is within acceptable limits.

[0083] If any indicator in the predicted data exceeds a preset threshold, an alarm is triggered. The alarm can be issued in various ways, such as email, SMS, system notification, or audible and visual alarms. This application embodiment does not limit the specific methods used.

[0084] The alarm content should include the alarm level (e.g., warning, serious warning), the specific pollutants exceeding the standard and the amount exceeding the standard, the potential impact of exceeding the standard on the environment and health, and generate suggested emergency response measures. Specifically, these measures can be configured in advance according to actual conditions, such as adjusting the combustion process, optimizing fuel ratio, inspecting and maintaining emission control systems such as desulfurization, denitrification and dust removal equipment, optimizing production scheduling, and reducing production activities during peak emission periods. However, this application does not limit the specific measures in this embodiment.

[0085] The monitoring method for emissions from thermal power plants disclosed in this paper mainly includes the following technical solutions: acquiring monitoring data of thermal power plant emissions and environmental parameters at a first moment; inputting the monitoring data of thermal power plant emissions and real-time environmental parameters at the first moment into a pre-trained environmental protection indicator model to obtain the predicted data of thermal power plant emissions at a second moment output by the pre-trained environmental protection indicator model; triggering an alarm and generating rectification suggestions when the predicted data of thermal power plant emissions at the second moment exceeds a preset emission threshold. Compared with related technologies, the embodiments of this application effectively predict pollutant emission trends and identify potential risks of exceeding standards in advance by collecting pollutant emission data and environmental parameters from thermal power plants, extracting nonlinear features from the pollutant emission data and environmental parameters, and combining them with time series analysis.

[0086] In some embodiments, after triggering an alarm and generating rectification suggestions when the predicted emissions data of the thermal power plant at the second time point exceeds a preset emission threshold, the method further includes:

[0087] The emission prediction data of the thermal power plant at the second time point is stored, and the Dolby result of the emission prediction data of the thermal power plant and the preset emission threshold is stored, and the compliance rate of the emission prediction data of the thermal power plant is calculated.

[0088] Please see Figure 3 , Figure 2 A flowchart illustrating a method for monitoring emissions from a thermal power plant, provided as an embodiment of this disclosure, includes:

[0089] Step 201: When the predicted emission data of the thermal power plant at the second time exceeds the first preset emission threshold, a minor exceedance alarm is triggered, and rectification suggestions are generated, including adjusting the operating parameters of the desulfurization equipment and increasing the amount of desulfurizing agent sprayed.

[0090] Please continue reading. Figure 2 The intelligent decision-making and alarm module will generate intelligent decisions based on alarm triggering conditions and send alarm information based on intelligent decisions to the mobile devices of relevant personnel. The content includes the type of exceedance, rectification suggestions and execution priority. If the exceedance continues, the alarm level will be upgraded every 30 minutes.

[0091] The following example illustrates the issue of excessive sulfur dioxide (SO2):

[0092] Surveillance background

[0093] Triggering conditions for exceeding the limit:

[0094] According to national emission standards, the concentration of SO2 emitted by thermal power plants must not exceed 200 mg / m³. 3 If the emission concentration within a certain period of time Exceeding this threshold is considered exceeding the limit.

[0095] Monitoring data:

[0096] Real-time collection of sulfur dioxide concentration Exceeding the limit:

[0097]

[0098] in, It is the preset threshold for sulfur dioxide.

[0099] Slight exceedance: 0 < ΔC ≤ 50 mg / m³ 3 This indicates that the equipment is operating normally, but may be due to minor equipment malfunctions or abnormal coal composition.

[0100] The formula for rectification suggestions is:

[0101] Suggestion = f(△C,S) 脱硫设备 ,F 燃煤 )

[0102] Where ΔC is the extent of SO2 exceeding the limit; S 脱硫设备 This refers to the current operating status of the desulfurization unit (e.g., desulfurization efficiency); F 燃煤 This refers to the compositional analysis results (such as sulfur content) of the coal currently in use.

[0103] Example of specific suggestions:

[0104] Slightly exceeded the standard (ΔC = 30 mg / m²) 3 ):

[0105] Check whether the equipment is operating normally, paying particular attention to factors such as the spray tower and absorbent concentration;

[0106] It is recommended to adjust the amount of desulfurizing agent sprayed appropriately to improve absorption efficiency.

[0107] Step 202: When the predicted emission data of the thermal power plant at the second time exceeds the second preset emission threshold, a moderate exceedance alarm is triggered, and rectification suggestions are generated, including conducting inspections of desulfurization equipment, optimizing the flow distribution in the absorption tower, and adjusting the boiler coal ratio.

[0108] Following the above-mentioned application embodiments, moderate exceedance: 50 < ΔC ≤ 100 mg / m³ 3 This may be caused by a decrease in the efficiency of the desulfurization unit or an increase in the sulfur content of the coal, and requires close attention.

[0109] Moderate exceedance (ΔC = 60 mg / m²) 3 The rectification suggestions are as follows:

[0110] Increase the frequency of inspections of flue gas desulfurization equipment;

[0111] Improve the uniformity of flow distribution in the absorption tower to ensure sufficient contact between flue gas and desulfurization liquid;

[0112] Optimize coal blending and use low-sulfur coal for combustion.

[0113] Step 203: When the predicted emission data of the thermal power plant at the second time exceeds the third preset emission threshold, a serious exceedance alarm is triggered, and rectification suggestions are generated, including immediately shutting down the plant to check the desulfurization equipment and switching the flue gas treatment process to the standby equipment.

[0114] Following the above-mentioned application examples, the following serious exceedance occurred: ΔC > 100 mg / m³ 3 This indicates that the desulfurization unit has failed or that low-quality, high-sulfur coal has been used for a long time, requiring emergency handling.

[0115] Severely exceeding the standard (ΔC=120mg / m²) 3 The rectification suggestions are as follows:

[0116] An emergency shutdown was initiated to inspect the desulfurization system, with a focus on checking for nozzle blockages inside the desulfurization tower.

[0117] Adjust the boiler combustion load to reduce SO2 production;

[0118] In the short term, a rapid switching scheme for flue gas bypass can be implemented to switch emission control to backup equipment.

[0119] Among them, the different rectification suggestions have different priorities.

[0120] Execution priority is evaluated based on the following three factors:

[0121] Exceeding the limit: The greater the exceedance, the higher the priority;

[0122] Potential environmental penalties: The longer the exceedance lasts, the more severe the penalties will be.

[0123] Equipment condition and operational safety: Equipment failure may lead to greater environmental pollution or safety hazards.

[0124] Specific priority calculation formula:

[0125] P = α·△C + β·T s +γ·R s

[0126] Where P is the execution priority, and the higher the value, the higher the response level; Ts is the duration of exceeding the limit; Rs is the equipment safety risk level (range 0-1, 1 represents the highest risk); α, β, γ are weighting coefficients, which are adjusted according to actual needs.

[0127] Priority example:

[0128] Slightly exceeded the standard: P=30

[0129] Execution priority: Low. The rectification is recommended to be completed within the specified timeframe; the equipment is operating normally and does not require shutdown.

[0130] Moderate exceedance: P=70

[0131] Execution priority: Medium. It is recommended to immediately initiate adjustment measures for the desulfurization equipment and optimize its operating parameters.

[0132] Severely exceeding the standard: P=120

[0133] Priority: High. The plant must be shut down immediately for rectification to reduce pollutant emissions, and the matter must be reported to the environmental protection authorities.

[0134] Alarm output example:

[0135] Alarm information is sent to relevant personnel through the system, and a rectification report is generated. For example:

[0136] Alarm message (slight exceedance):

[0137] Time: 10:30 AM, November 18, 2024

[0138] Alarm type: Sulfur dioxide exceeds standard (slight exceedance)

[0139] Exceeding concentration: 260 mg / m³ 3

[0140] Suggestions for rectification:

[0141] Check the operating status of the desulfurization equipment, paying particular attention to the operation of the spray tower nozzles.

[0142] Appropriately increase the amount of desulfurizing agent sprayed to improve absorption efficiency.

[0143] Execution priority: Low (30)

[0144] Alarm message (seriously exceeded):

[0145] Time: 12:45 PM, November 18, 2024

[0146] Alarm type: Sulfur dioxide exceeds standard (severely exceeded standard)

[0147] Exceeding concentration: 320 mg / m³ 3

[0148] Suggestions for rectification:

[0149] An emergency shutdown was initiated to inspect the desulfurization equipment, with a focus on checking for blockages in the spray tower.

[0150] Adjust the boiler combustion load to reduce SO2 production.

[0151] Short-term implementation of flue gas bypass switching to standby equipment to ensure emissions meet standards.

[0152] Execution priority: High (120)

[0153] In some embodiments, the step of inputting the power plant emission monitoring data at the first moment and the real-time environmental parameters at the first moment into a pre-trained environmental protection index model to obtain the power plant emission prediction data for the second moment output by the pre-trained environmental protection index model includes:

[0154] The pre-trained environmental protection indicator model processes the emission monitoring data of the thermal power plant based on dynamic weighted normalization;

[0155] The specific formula for dynamic weighted normalization is as follows:

[0156]

[0157] Among them, X i The value of i in the emission monitoring data of the thermal power plant; X′ i The normalized eigenvalues; w i The feature weights are determined by the variance of the feature, Var(X). i The larger the variance, the smaller the weight.

[0158] In this embodiment, the environmental indicator prediction model is built based on the TensorFlow framework and is a multilayer perceptron (MLP) network. The environmental indicator prediction model includes an input layer, multiple hidden layers, and an output layer. The input layer is used to input pollutant and environmental parameter data; the hidden layers are used to extract nonlinear features using the ReLU activation function; and the output layer is used to predict environmental indicator data. The loss function of the environmental indicator prediction model uses a weighted mean square error calculation formula.

[0159] The model input features include:

[0160] Real-time pollutant concentration

[0161]

[0162] Environmental parameters

[0163] P = {T,H,V} w D w}

[0164] Model output formula:

[0165] I p =σ(W2·ReLU(W1·X+b1)+b2)

[0166] Among them, I pThe predicted environmental indicator is (e.g., Air Quality Index (AQI) or pollution emission intensity); X is the input feature vector, X = [C, P]; W1 and W2 are the weight matrices of the model; b1 and b2 are the bias terms of the model; σ(x) is the activation function used to normalize the output value to a reasonable range (e.g., Sigmoid or Softmax).

[0167] To address the variability in the environmental impact of different pollutants, this embodiment introduces dynamic weighted normalization:

[0168]

[0169] Among them, X i The value of the original feature i; X′ i The normalized eigenvalues; w i The feature weights are determined by the variance of the feature, Var(X). i The larger the variance, the smaller the weight. This embodiment improves the model's ability to model complex relationships between different pollutants and environmental parameters through dynamic feature normalization, thereby enhancing prediction accuracy.

[0170] In some embodiments, storing the predicted emissions data of the thermal power plant at the second time point, and the Dolby result of the predicted emissions data of the thermal power plant and the preset emission threshold, and calculating the compliance rate of the predicted emissions data of the thermal power plant further includes:

[0171] The compliance rate report is generated according to a preset time period; wherein the compliance rate report includes at least one of the following: average value, peak value and compliance rate of pollutant emission concentration, number of exceedance events in different time periods and distribution of exceedance types.

[0172] Formula for calculating the basic compliance rate:

[0173]

[0174] Where R represents the compliance rate; the total number of compliance periods is the number of time periods during which environmental indicators do not exceed the standards; and the total number of monitoring periods is the total number of time periods monitored by the system.

[0175] Time-weighted achievement rate formula:

[0176]

[0177] Among them, R w Time-weighted achievement rate; w j Time-weighted (e.g., higher weight for highly polluted seasons); d j This represents the compliance indicator for time period j (1 for compliance, 0 for exceeding the standard). This time-weighted compliance rate formula effectively reflects the impact of high-pollution periods on the overall compliance rate, providing a more accurate environmental management assessment.

[0178] Corresponding to the aforementioned method for monitoring emissions from thermal power plants, this invention also proposes a monitoring device for emissions from thermal power plants. Since the device embodiments of this invention correspond to the method embodiments described above, details not disclosed in the device embodiments can be referred to in the method embodiments, and will not be repeated here.

[0179] Figure 4 This is a schematic diagram of the structure of a monitoring device for emissions from a thermal power plant, provided in an embodiment of this disclosure. Figure 4 As shown, it includes:

[0180] Acquisition unit 31 is used to acquire the first-time emission monitoring data of the thermal power plant and the first-time environmental parameters;

[0181] The prediction unit 32 is used to input the power plant emission monitoring data at the first moment and the real-time environmental parameters at the first moment into the pre-trained environmental protection index model to obtain the power plant emission prediction data at the second moment output by the pre-trained environmental protection index model.

[0182] The alarm unit 33 is used to trigger an alarm and generate rectification suggestions when the predicted emission data of the thermal power plant at the second time exceeds the preset emission threshold.

[0183] The monitoring device for emissions from thermal power plants disclosed in this application mainly includes the following technical solutions: acquiring monitoring data of thermal power plant emissions and environmental parameters at a first moment; inputting the monitoring data of thermal power plant emissions and real-time environmental parameters at the first moment into a pre-trained environmental protection indicator model to obtain the predicted data of thermal power plant emissions at a second moment output by the pre-trained environmental protection indicator model; triggering an alarm and generating rectification suggestions when the predicted data of thermal power plant emissions at the second moment exceeds a preset emission threshold. Compared with related technologies, the embodiments of this application effectively predict pollutant emission trends and identify potential risks of exceeding standards in advance by collecting pollutant emission data and environmental parameters from thermal power plants, extracting nonlinear features from the pollutant emission data and environmental parameters, and combining them with time series analysis.

[0184] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 5 As shown, the device further includes:

[0185] The storage unit 34 is used to store the thermal power plant emission prediction data at the second time and the Dolby result of the thermal power plant emission prediction data and the preset emission threshold after the alarm unit 33 triggers an alarm and generates a rectification suggestion when the thermal power plant emission prediction data at the second time exceeds the preset emission threshold, and to calculate the compliance rate of the thermal power plant emission prediction data.

[0186] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 5 As shown, the preset emission thresholds include a first preset emission threshold, a second preset emission threshold, and a third preset emission threshold; the alarm unit 33 is further used for:

[0187] When the predicted emissions data of the thermal power plant at the second moment exceeds the first preset emission threshold, a minor exceedance alarm is triggered, and rectification suggestions are generated, including adjusting the operating parameters of the desulfurization equipment and increasing the amount of desulfurizing agent sprayed.

[0188] When the predicted emissions data of the thermal power plant at the second time point exceeds the second preset emission threshold, a moderate exceedance alarm is triggered, and rectification suggestions are generated, including conducting inspections of desulfurization equipment, optimizing the flow distribution in the absorption tower, and adjusting the boiler coal ratio.

[0189] When the predicted emissions data of the thermal power plant at the second moment exceeds the third preset emission threshold, a serious exceedance alarm is triggered, and rectification suggestions are generated, including immediately shutting down the plant to inspect the desulfurization equipment and switching the flue gas treatment process to the backup equipment.

[0190] Among them, the different rectification suggestions have different priorities.

[0191] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 5 As shown, the prediction unit 32 is further configured to:

[0192] The pre-trained environmental protection indicator model processes the emission monitoring data of the thermal power plant based on dynamic weighted normalization;

[0193] The specific formula for dynamic weighted normalization is as follows:

[0194]

[0195] Among them, X i The value of i in the emission monitoring data of the thermal power plant; X′ i The normalized eigenvalues; w i The feature weights are determined by the variance of the feature, Var(X). i The larger the variance, the smaller the weight.

[0196] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 5 As shown, the storage unit 34 is further used for:

[0197] The compliance rate report is generated according to a preset time period; wherein the compliance rate report includes at least one of the following: average value, peak value and compliance rate of pollutant emission concentration, number of exceedance events in different time periods and distribution of exceedance types.

[0198] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of the embodiments of this disclosure, and the principle is the same. Therefore, the embodiments of this disclosure are not limited thereto.

[0199] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0200] Figure 6 A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0201] like Figure 6 As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 402 or a computer program loaded from storage unit 408 into RAM (Random Access Memory) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. I / O (Input / Output) interface 405 is also connected to bus 404.

[0202] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0203] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as methods for monitoring emissions from thermal power plants. For example, in some embodiments, the method for monitoring emissions from thermal power plants may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the aforementioned monitoring method for emissions from thermal power plants by any other suitable means (e.g., by means of firmware).

[0204] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0205] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0206] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0207] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0208] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0209] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0210] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0211] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0212] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for monitoring emissions from a thermal power plant, characterized in that, include: Acquire the first-time emission monitoring data of the thermal power plant and the first-time environmental parameters; The emission monitoring data of the thermal power plant at the first moment and the real-time environmental parameters at the first moment are input into the pre-trained environmental protection index model to obtain the emission prediction data of the thermal power plant at the second moment output by the pre-trained environmental protection index model. When the predicted emissions data of the thermal power plant at the second time point exceeds the preset emission threshold, an alarm is triggered and rectification suggestions are generated.

2. The method according to claim 1, characterized in that, When the predicted emissions data of the thermal power plant at the second time point exceeds the preset emission threshold, after triggering an alarm and generating rectification suggestions, the method further includes: The emission prediction data of the thermal power plant at the second time point is stored, and the Dolby result of the emission prediction data of the thermal power plant and the preset emission threshold is stored, and the compliance rate of the emission prediction data of the thermal power plant is calculated.

3. The method according to claim 1, characterized in that, The preset emission thresholds include a first preset emission threshold, a second preset emission threshold, and a third preset emission threshold; the step of triggering an alarm and generating rectification suggestions when the predicted emission data of the thermal power plant at the second time exceeds the preset emission thresholds also includes: When the predicted emissions data of the thermal power plant at the second moment exceeds the first preset emission threshold, a minor exceedance alarm is triggered, and rectification suggestions are generated, including adjusting the operating parameters of the desulfurization equipment and increasing the amount of desulfurizing agent sprayed. When the predicted emissions data of the thermal power plant at the second time point exceeds the second preset emission threshold, a moderate exceedance alarm is triggered, and rectification suggestions are generated, including conducting inspections of desulfurization equipment, optimizing the flow distribution in the absorption tower, and adjusting the boiler coal ratio. When the predicted emissions data of the thermal power plant at the second moment exceeds the third preset emission threshold, a serious exceedance alarm is triggered, and rectification suggestions are generated, including immediately shutting down the plant to inspect the desulfurization equipment and switching the flue gas treatment process to the backup equipment. Among them, the different rectification suggestions have different priorities.

4. The method according to claim 1, characterized in that, The step of inputting the power plant emission monitoring data at the first moment and the real-time environmental parameters at the first moment into the pre-trained environmental protection index model to obtain the power plant emission prediction data for the second moment output by the pre-trained environmental protection index model includes: The pre-trained environmental protection indicator model processes the emission monitoring data of the thermal power plant based on dynamic weighted normalization; The specific formula for dynamic weighted normalization is as follows: Among them, X i The value of i in the emission monitoring data of the thermal power plant; X′ i The normalized eigenvalues; w i The feature weights are determined by the variance of the feature, Var(X). i The larger the variance, the smaller the weight.

5. The method according to any one of claims 1-4, characterized in that, The process of storing the predicted emissions data of thermal power plants at the second time point, and the Dolby result of comparing the predicted emissions data with the preset emission threshold, and calculating the compliance rate of the predicted emissions data of thermal power plants, further includes: The compliance rate report is generated according to a preset time period; wherein the compliance rate report includes at least one of the following: average value, peak value and compliance rate of pollutant emission concentration, number of exceedance events in different time periods and distribution of exceedance types.

6. A monitoring device for emissions from a thermal power plant, characterized in that, include: The acquisition unit is used to acquire the first-time emission monitoring data of the thermal power plant and the first-time environmental parameters; The prediction unit is used to input the power plant emission monitoring data at the first moment and the real-time environmental parameters at the first moment into the pre-trained environmental protection index model to obtain the power plant emission prediction data at the second moment output by the pre-trained environmental protection index model. The alarm unit is used to trigger an alarm and generate rectification suggestions when the predicted emission data of the thermal power plant at the second time exceeds the preset emission threshold.

7. The apparatus according to claim 6, characterized in that, The device further includes: The storage unit is used to, after the alarm unit triggers an alarm and generates a rectification suggestion when the predicted emission data of the thermal power plant at the second time exceeds the preset emission threshold, store the predicted emission data of the thermal power plant at the second time and the Dolby result of the predicted emission data of the thermal power plant and the preset emission threshold, and calculate the compliance rate of the predicted emission data of the thermal power plant.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-5.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-5.

Images