Intelligent monitoring system and method for carbon emission of coal chemical industry

Abstract

The invention relates to the technical field of carbon emission monitoring, in particular to a coal chemical industry carbon emission intelligent monitoring system and method, and the method comprises the following steps: S1, data collection: collecting carbon emission data in a coal chemical industry production process; s2, data preprocessing: preprocessing the collected carbon emission data; s3, carbon emission trend prediction and process adjustment: dynamically predicting the carbon emission trend, and automatically adjusting production process parameters; and S4, carbon emission monitoring and alarming: performing real-time monitoring on the carbon emission condition of each link in the production process, comparing real-time carbon emission data with a standard value, and giving an alarm and taking emergency measures in time if a comparison result is found to exceed a set threshold value. According to the invention, carbon emission changes in the production process can be coped with in real time, and the accuracy and response speed of carbon emission control are improved, so that coal chemical enterprises are helped to realize dual optimization of environmental protection and production benefits.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission monitoring, and particularly to an intelligent monitoring system and method for coal chemical carbon emissions. Background Art

[0002] The coal chemical industry is an important field for national energy and chemical production. However, a large amount of harmful gases such as carbon dioxide, nitrogen oxides, and sulfur dioxide are emitted during the coal chemical production process, causing serious environmental pollution. Therefore, how to effectively control carbon emissions, reduce energy consumption, and optimize production efficiency has become an important issue faced by the coal chemical industry. To address this challenge, coal chemical enterprises have gradually introduced intelligent monitoring and automation control technologies. By real-time monitoring and analyzing carbon emission data during the production process, precise control and optimization adjustment of carbon emissions are achieved.

[0003] Currently, although many coal chemical enterprises have adopted some carbon emission monitoring systems, most of the existing technologies still have the following deficiencies: First, the accuracy of data collection and analysis is relatively low, lacking dynamic prediction of carbon emission trends, resulting in the failure to timely identify the trend of excessive emissions. Second, the process adjustment lacks real-time and adaptive capabilities, usually relying on manual judgment and control, and it is difficult to effectively respond to the instantaneous fluctuations of carbon emissions during the production process. Third, most of the existing carbon emission monitoring systems cannot combine external environmental factors, such as meteorological data and energy consumption, for comprehensive emission prediction and optimization adjustment. Therefore, traditional carbon emission monitoring methods are difficult to meet the requirements of precise, efficient, and flexible control during the coal chemical production process.

[0004] The purpose of the present invention is to provide an intelligent monitoring system and method for coal chemical carbon emissions, which can timely identify abnormal carbon emissions and trigger alarms, ensuring the environmental protection and safety of the production process, thereby helping coal chemical enterprises achieve double optimization of environmental protection and production benefits. Summary of the Invention

[0005] The present invention provides an intelligent monitoring system and method for coal chemical carbon emissions.

[0006] An intelligent monitoring method for coal chemical carbon emissions includes the following steps:

[0007] S1, data collection: Real-time collect carbon emission data during the coal chemical production process, including gas concentration, temperature, pressure, flow rate, meteorological information, and energy consumption data;

[0008] S2, data preprocessing: Preprocess the collected carbon emission data, including denoising, smoothing, standardization, and missing value filling;

[0009] S3, Carbon Emission Trend Prediction and Process Adjustment: Based on the preprocessed carbon emission data, use the Adaptive Neural Network (ANN) model to dynamically predict the carbon emission trend. According to the prediction results, automatically adjust the production process parameters (reaction efficiency, fuel ratio, reaction pressure);

[0010] S4, Carbon Emission Monitoring and Alarm: Based on the adjusted production process parameters, monitor the carbon emission situation in each link of the production process in real time, and compare the real-time carbon emission data with the standard value. If it is found that the comparison result exceeds the set threshold, send an alarm in time and take emergency measures.

[0011] Optionally, the data collection in S1 includes:

[0012] S11, Gas Concentration Collection: Use gas sensors to monitor the gas concentration data in the coal chemical production process in real time, including carbon dioxide, nitrogen oxides, and sulfur dioxide;

[0013] S12, Temperature, Pressure and Flow Collection: Use industrial-grade sensors to collect the temperature, pressure and flow data in the coal chemical production process in real time;

[0014] S13, Meteorological Information Collection: Use meteorological sensors to collect the meteorological information of the external environment, including wind speed, wind direction, air temperature, and humidity;

[0015] S14, Energy Consumption Data Collection: Use energy metering devices to monitor the energy consumption situation in the coal chemical production process in real time, including the energy consumption data of coal, natural gas, and electricity.

[0016] Optionally, the data preprocessing in S2 includes:

[0017] S21, Denoising Processing: Use the moving average method to denoise the collected carbon emission data;

[0018] S22, Smoothing Processing: Use the Exponentially Weighted Moving Average (EWMA) method to smooth the carbon emission data;

[0019] S23, Standardization Processing: Standardize the collected carbon emission data;

[0020] S24, Missing Value Filling: Use the linear interpolation method to fill in the missing values of the collected carbon emission data.

[0021] Optionally, the carbon emission trend prediction and process adjustment in S3 includes:

[0022] S31, Dynamic Prediction of Carbon Emission Trend: Based on the preprocessed carbon emission data, use the Adaptive Neural Network (ANN) model to dynamically predict the carbon emission trend for a future period of time (12 hours);

[0023] S32, Process parameter adjustment strategy generation: According to the prediction results of the carbon emission trend, use an optimization algorithm to automatically generate an adjustment strategy and determine the optimal combination of production process parameters;

[0024] S33, Automatic process parameter adjustment and execution: Apply the generated process parameter adjustment strategy to the production process and execute the adjustment of process parameters through an automated control unit.

[0025] Optionally, the dynamic prediction of the carbon emission trend in S31 includes:

[0026] S311, Data input: Based on the preprocessed carbon emission data as input features, construct a data input layer;

[0027] S312, Carbon emission trend prediction: Use an Adaptive Neural Network (ANN) model for dynamic prediction of the carbon emission trend. The Adaptive Neural Network (ANN) model consists of multiple layers of neurons, and the output result is obtained through layer-by-layer weighted and biased calculations;

[0028] S313, Model parameter optimization: Use an optimization algorithm to adjust the parameters (weights and biases) of the Adaptive Neural Network (ANN) model. By using the Mean Squared Error (MSE) as the loss function, calculate the error between the predicted value and the true value of the Adaptive Neural Network (ANN) model.

[0029] Optionally, the process parameter adjustment strategy generation in S32 includes:

[0030] S321, Construct an optimization objective function: According to the prediction results of the carbon emission trend, construct an optimization objective function with the goal of minimizing carbon emissions, and consider production efficiency and the feasibility of process parameters;

[0031] S322, Apply an optimization algorithm to generate an adjustment strategy: Use the Particle Swarm Optimization (PSO) optimization algorithm to solve the optimization objective function and automatically generate the optimal combination of process parameters;

[0032] S323, Generate the optimal combination of process parameters: Through iterative calculations of the optimization algorithm, obtain the optimal combination of production process parameters p opt .

[0033] Optionally, the automatic process parameter adjustment and execution in S33 includes:

[0034] S331, Calculate the adjustment amount: According to the current combination of process parameters p t and the optimal combination of process parameters p opt , calculate the adjustment amount Δp of each process parameter i ;

[0035] S332. Execute the adjustment command: Through the automatic control unit, apply the calculated adjustment amount Δp i to the corresponding control equipment in the production process, and automatically adjust each process parameter through the PID control algorithm.

[0036] Optionally, the carbon emission monitoring and alarm in S4 include:

[0037] S41. Real-time carbon emission data collection and monitoring: According to the adjusted process parameters, collect carbon emission data in real time through sensors installed in each production link;

[0038] S42. Comparison of carbon emission data with the standard value: Compare the real-time collected carbon emission data with the set standard value, and calculate the difference e t ;

[0039] S43. Alarm judgment and trigger of emergency measures: Compare according to the calculated deviation and the set threshold Δy thresh When |e t |≥Δy thresh then trigger an alarm and take emergency measures.

[0040] Optionally, the emergency measures in S43 include:

[0041] Automatically adjust process parameters: Adjust the process parameters (reaction efficiency, fuel ratio, reaction pressure) in the production process to reduce carbon emissions;

[0042] Suspend production or partial production suspension: After the alarm is triggered, automatically cut off the operation of the equipment, suspend the production line or adjust the production load;

[0043] Increase the operation of emission purification equipment: Start or strengthen emission purification devices, including desulfurization, denitrification or carbon capture devices;

[0044] Notify the operator for manual intervention: When the automatic adjustment is ineffective or there is a failure, notify the manual operator for intervention;

[0045] Optimize the energy use strategy: Adjust the energy ratio through the energy management unit;

[0046] Increase the emission monitoring frequency: Automatically adjust the data collection frequency.

[0047] A coal chemical carbon emission intelligent monitoring system for implementing the above-mentioned coal chemical carbon emission intelligent monitoring method, including the following modules:

[0048] Data collection module: Real-time collect carbon emission data in the coal chemical production process, including gas concentration, temperature, pressure, flow rate, meteorological information and energy consumption data;

[0049] Data preprocessing module: Denoise, smooth, standardize and fill in missing values for the collected carbon emission data;

[0050] Carbon emission trend prediction and process adjustment module: Based on the preprocessed carbon emission data, use an adaptive neural network model to dynamically predict the carbon emission trend, and automatically adjust the production process parameters according to the prediction results, including reaction efficiency, fuel ratio, and reaction pressure;

[0051] Carbon emission monitoring and alarm module: Real-time monitor the carbon emission situation of each link in the production process, compare the real-time carbon emission data with the standard value, and when it is found that the carbon emission exceeds the set threshold, issue an alarm and execute emergency measures.

[0052] Advantages of the present invention:

[0053] In the present invention, through real-time data collection, precise preprocessing, carbon emission trend prediction and process adjustment based on an adaptive neural network, and a comprehensive carbon emission monitoring and alarm mechanism, it is possible to dynamically optimize the production process, reduce carbon emissions, and ensure the stability of the production process. By comparing the real-time carbon emission data with the standard value, abnormal situations of excessive carbon emissions can be detected in a timely manner and the alarm mechanism can be triggered. At the same time, the production process is adjusted through an automated control system, avoiding errors and delays in manual operations, being able to respond to carbon emission changes in the production process in real time, improving the accuracy and response speed of carbon emission control, and thus helping coal chemical enterprises to achieve double optimization of environmental protection and production benefits.

[0054] In the present invention, through preprocessing and data collection, the quality and stability of carbon emission data can be effectively improved, ensuring the consistency and reliability of the data in analysis. Data processing means such as denoising, smoothing, standardization and filling in missing values not only eliminate sensor noise and short-term fluctuations, but also unify the dimensions of different data types, providing high-quality data input for carbon emission trend prediction. At the same time, setting thresholds based on historical data and dynamic adjustment can achieve precise monitoring of carbon emissions, and ensure that the system can flexibly respond and adjust the alarm threshold in different production environments, further optimizing carbon emission management.

[0055] In the present invention, through the process parameter adjustment strategy, an optimal combination of production process parameters can be automatically generated based on the carbon emission trend prediction, and adjusted in real time through an optimization algorithm to minimize carbon emissions to the greatest extent. The application of the particle swarm optimization algorithm makes the adjustment of process parameters more scientific and precise, avoiding the limitations of manual operations. By executing these adjustment measures through an automated control unit, it is possible to ensure the high efficiency and stability of the production process while reducing carbon emissions. In addition, the introduction of emergency measures ensures that effective response plans can be quickly taken in case of abnormal carbon emissions, further guaranteeing the environmental protection and safety of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only those of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0057] Figure 1 It is a schematic flowchart of the monitoring method according to an embodiment of the present invention;

[0058] Figure 2 It is a schematic diagram of the system function modules according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] The present invention will be described in detail below in conjunction with the drawings and specific embodiments. At the same time, it should be noted here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments. For some well-known technologies, those skilled in the art can also adopt other alternative methods for implementation; moreover, the drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0060] It should be pointed out that in the specification, when referring to "an embodiment", "embodiments", "exemplary embodiments", "some embodiments", etc., it indicates that the described embodiments may include specific features, structures or characteristics, but not necessarily every embodiment includes such specific features, structures or characteristics. In addition, when combining an embodiment to describe a specific feature, structure or characteristic, implementing such a feature, structure or characteristic in combination with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the relevant art.

[0061] Generally, the terms can be understood at least in part from their use in the context. For example, at least in part depending on the context, the term "one or more" used herein can be used to describe any feature, structure or characteristic in a singular sense, or can be used to describe a combination of features, structures or characteristics in a plural sense. In addition, the term "based on" can be understood as not necessarily intended to convey a set of exclusive factors, but instead, at least in part depending on the context, allowing the existence of other factors that may not be explicitly described.

[0062] As Figure 1 shown, a smart monitoring method for coal chemical carbon emissions includes the following steps:

[0063] S1, data collection: Real-time collect carbon emission data during the coal chemical production process, including gas concentration, temperature, pressure, flow rate, meteorological information and energy consumption data;

[0064] S2, Data preprocessing: Preprocess the collected carbon emission data, including denoising, smoothing, standardization, and missing value filling;

[0065] S3, Carbon emission trend prediction and process adjustment: Based on the preprocessed carbon emission data, use an Adaptive Neural Network (ANN) model to dynamically predict the carbon emission trend. According to the prediction results, automatically adjust the production process parameters (reaction efficiency, fuel ratio, reaction pressure) to reduce carbon emissions and ensure the stability of the production process;

[0066] S4, Carbon emission monitoring and alarm: Based on the adjusted production process parameters, monitor the carbon emissions in each link of the production process in real time, and compare the real-time carbon emission data with the standard value. If it is found that the comparison result exceeds the set threshold, issue an alarm in time and take emergency measures;

[0067] Through the above content, real-time data collection, precise preprocessing, carbon emission trend prediction and process adjustment based on the Adaptive Neural Network, and a comprehensive carbon emission monitoring and alarm mechanism can dynamically optimize the production process, reduce carbon emissions, ensure the stability of the production process, respond to carbon emission changes in the production process in real time, effectively improve the accuracy and response speed of carbon emission control, and thus help coal chemical enterprises achieve double optimization of environmental protection and production efficiency.

[0068] The data collection in S1 includes:

[0069] S11, Gas concentration collection: Use gas sensors to monitor the gas concentration data in the coal chemical production process in real time, including carbon dioxide, nitrogen oxides, and sulfur dioxide;

[0070] S12, Temperature, pressure, and flow collection: Use industrial-grade sensors to collect the temperature, pressure, and flow data in the coal chemical production process in real time;

[0071] S13, Meteorological information collection: Use meteorological sensors to collect the meteorological information of the external environment, including wind speed, wind direction, temperature, and humidity;

[0072] S14, Energy consumption data collection: Use energy metering devices to monitor the energy consumption in the coal chemical production process in real time, including the energy consumption data of coal, natural gas, and electricity;

[0073] Through the above content, the operating status of the production process can be grasped in real time, and the impact of external environmental factors on carbon emissions can be effectively evaluated. Through the cooperation of high-precision sensors and energy metering devices, various types of data can be accurately obtained, providing reliable data support for subsequent carbon emission analysis, prediction, and process optimization, helping to achieve precise carbon emission control and resource conservation, and improving the safety, stability, and environmental friendliness of the production process.

[0074] The data preprocessing in S2 includes:

[0075] S21, denoising processing: Denoise the collected carbon emission data by the moving average method, expressed as:

[0076]

[0077] where x t-i is the collected data at the i-th moment before time point t, y t is the denoised carbon emission data, and n is the size of the sliding window;

[0078] S22, smoothing processing: Smooth the carbon emission data by the exponentially weighted moving average (EWMA) method, expressed as:

[0079]

[0080] where S t is the smoothed data, α is the smoothing factor, α ∈ (0, 1), x t is the currently collected carbon emission data, and S t-1 is the smoothed value at the previous moment;

[0081] S23, standardization processing: Standardize the collected carbon emission data so that the data has a unified dimension and eliminate the scale differences between different data sources, expressed as:

[0082]

[0083] where z t is the standardized data, x t is the original data, μ is the mean of the data, and σ is the standard deviation of the data;

[0084] S24, missing value filling: Fill the missing values in the collected carbon emission data by the linear interpolation method, expressed as:

[0085]

[0086] where x t is the missing value, and x t-1 and x t+1 are the valid data at the previous and next moments respectively;

[0087] Through the above, the quality and stability of carbon emission data are effectively improved. Denoising and smoothing can eliminate sensor noise and short-term fluctuations, retain the long-term trend of the data, ensure the consistency and reliability of the data in analysis. Standardization unifies the dimensions of different data types, eliminates scale differences, enabling various data to be compared and predicted under the same standard. Missing value imputation avoids analysis biases caused by missing data, guarantees data integrity, and can provide high-quality input data for subsequent carbon emission trend prediction and process adjustment, improving prediction accuracy, enhancing the system's response ability and decision-making efficiency.

[0088] The carbon emission trend prediction and process adjustment in S3 include:

[0089] S31, Dynamic prediction of carbon emission trend: Based on the preprocessed carbon emission data, an Adaptive Neural Network (ANN) model is used to dynamically predict the carbon emission trend for a future period (12 hours).

[0090] S32, Generation of process parameter adjustment strategy: According to the prediction results of the carbon emission trend, an optimization algorithm is used to automatically generate an adjustment strategy to determine the optimal combination of production process parameters.

[0091] S33, Automatic adjustment and execution of process parameters: Apply the generated process parameter adjustment strategy to the production process, and execute the adjustment of process parameters through an automated control unit.

[0092] Through the above, the changing trend of carbon emissions can be identified in advance, providing a timely basis for adjustment in the production process. Combining the process parameter adjustment strategy generated by the optimization algorithm, the optimal combination of production process parameters can be automatically determined to effectively reduce carbon emissions and ensure the stability of the production process. At the same time, the automated control system ensures the efficient execution of process parameter adjustment, reduces errors and delays caused by human intervention, improves the accuracy and response speed of carbon emission management, and promotes the development of coal chemical production towards low-carbon, environmental protection, and sustainable directions.

[0093] The dynamic prediction of carbon emission trend in S31 includes:

[0094] S311, Data input: Based on the preprocessed carbon emission data as input features, construct a data input layer, denoted as:

[0095] X t-W+1:t =[x t-W+1 ,x t-W+2 ,...,x t ;

[0096] where X t-W+1:t is the input feature at time step t, containing carbon emission data for the past W time steps, x t-W+1 ,xt-W+2 ,...,x t represents the data from time t - W + 1 to t;

[0097] S312, Carbon emission trend prediction: Use an Adaptive Neural Network (ANN) model for dynamic prediction of carbon emission trends. The Adaptive Neural Network (ANN) model consists of multiple layers of neurons and obtains the output result through layer-by-layer weighted and bias calculations. Specifically, it includes:

[0098] Calculation from the input layer to the hidden layer:

[0099] where h t is the output of the hidden layer, x i is the input feature, w i is the weight connecting the input and the hidden layer, b is the bias term, f is the ReLU activation function, and n is the number of input features;

[0100] Calculation from the hidden layer to the output layer:

[0101] where y t is the final output of the model, i.e., the predicted carbon emission value, h i is the output of the hidden layer, w i ′ is the weight from the hidden layer to the output layer, b′ is the bias term, g is the linear activation function of the output layer, and m is the number of neurons in the hidden layer;

[0102] S313, Model parameter optimization: Use an optimization algorithm to adjust the parameters (weights and biases) of the Adaptive Neural Network (ANN) model. By using the Mean Squared Error (MSE) as the loss function, calculate the error between the predicted value and the true value of the Adaptive Neural Network (ANN) model. The loss function is expressed as:

[0103]

[0104] where y t is the actual carbon emission value, is the predicted carbon emission value, T is the total number of samples, L is the loss function, and update the weights and biases of the network by minimizing the loss function;

[0105] Through the above content, the prediction accuracy and robustness are comprehensively improved. By dynamically predicting the carbon emission trend in the next 12 hours, it can timely identify emission changes, provide a decision-making basis, thereby optimizing the production process and carbon emission control, can handle complex production conditions, ensure a high prediction accuracy in a dynamically changing environment, and contribute to achieving the low-carbon emission goal of the coal chemical industry.

[0106] The generation of the process parameter adjustment strategy in S32 includes:

[0107] S321. Construct an optimization objective function: Based on the prediction results of the carbon emission trend, construct an optimization objective function with the goal of minimizing carbon emissions, and consider the feasibility of production efficiency and process parameters. The optimization objective function is expressed as:

[0108]

[0109] where, is the predicted carbon emission value, p i is the i-th process parameter (reaction efficiency, fuel ratio, reaction pressure), p set is the set ideal process parameter, λ is the adjustment coefficient, and l is the number of process parameters;

[0110] S322. Apply an optimization algorithm to generate an adjustment strategy: Use the particle swarm optimization (PSO) algorithm to solve the optimization objective function and automatically generate the optimal combination of process parameters. Let the initial value of the process parameter be p 0 =[p 1 , p 2 ,..., p m . The optimization algorithm adjusts the process parameters step by step through iterative calculations to find the optimal solution that minimizes the objective function J, expressed as:

[0111] v i (t + 1)=w·v i (t)+c 1 ·rand 1 ·(p i,best -p i )+c 2 ·rand 2 ·(g best -p i );

[0112] p i (t + 1)=p i (t)+v i (t + 1);

[0113] where, v i (t) is the velocity of particle i, p i (t) is the position of particle i (i.e., the process parameter), p i,best is the historical optimal position of particle i, g best is the global optimal position, w is the inertia weight, c 1 and c 2 are the learning factors, rand 1 and rand 2 are random numbers;

[0114] S323. Generate the optimal process parameter combination: Through iterative calculations using an optimization algorithm, obtain the optimal production process parameter combination p opt , which can minimize carbon emissions to the greatest extent while ensuring the stability and efficiency of the production process;

[0115] Based on the above, the optimal production process parameter combination can be automatically generated, ensuring the best balance between carbon emission control and production efficiency. By using the Particle Swarm Optimization (PSO) algorithm, the process parameters can be adjusted in real time in a complex production environment, such as reaction efficiency, fuel ratio, and reaction pressure, effectively reducing carbon emissions and improving the stability and energy utilization efficiency of the production process, avoiding human operation errors, and being able to respond in real time to changes in carbon emissions and process conditions during production, thus promoting the coal chemical industry to achieve more environmentally friendly and efficient production goals.

[0116] The process parameter automatic adjustment and execution in S33 include:

[0117] S331. Calculate the adjustment amount: According to the current process parameter combination p t and the optimal process parameter combination p opt , calculate the adjustment amount Δp i for each process parameter, expressed as:

[0118]

[0119] where Δp i represents the adjustment amount of the i-th process parameter, p i is the current process parameter, and is the optimal process parameter;

[0120] S332. Execute the adjustment command: Through the automatic control unit, apply the calculated adjustment amount Δp i to the corresponding control equipment in the production process, and automatically adjust each process parameter through the PID control algorithm, expressed as:

[0121]

[0122] where u(t) is the control signal (i.e., the adjustment amount), e(t) is the deviation, i.e., the difference between the current process parameter and the target process parameter, K p 、K i 、K d are the proportional, integral, and differential gain constants respectively, and t is the time;

[0123] Through the above, the accuracy and response speed of carbon emission control are improved. By calculating the adjustment amount and smoothly implementing the adjustment using the PID control algorithm, it is ensured that various process parameters in the production process can quickly and accurately reach the optimal state, minimizing carbon emissions while maintaining production efficiency. At the same time, the introduction of a real-time feedback mechanism ensures that the process parameters can be dynamically adjusted according to the actual carbon emission situation, avoiding errors and delays in manual operations. This not only optimizes the stability and environmental friendliness of the production process but also effectively improves resource utilization rate, providing strong support for the low-carbon and sustainable development of the coal chemical industry.

[0124] The carbon emission monitoring and alarm in S4 include:

[0125] S41, Real-time carbon emission data collection and monitoring: According to the adjusted process parameters, carbon emission data is collected in real time through sensors installed in each production link.

[0126] S42, Comparison of carbon emission data with the standard value: The real-time collected carbon emission data is compared with the set standard value, and the difference e is calculated t , expressed as:

[0127]

[0128] where e t is the deviation between the carbon emission data and the standard value, is the carbon emission value monitored in real time, y std is the set standard carbon emission value;

[0129] S43, Alarm judgment and triggering of emergency measures: The calculated deviation is compared with the set threshold Δy thresh . When |e t | ≥ Δy thresh , an alarm is triggered and emergency measures are taken;

[0130] The threshold Δy thresh is set based on historical data, specifically including:

[0131] Collect historical carbon emission data: Collect historical carbon emission data over a period of time, including the carbon emission situation of each production link. The data includes carbon emission values under different process conditions;

[0132] Calculate the mean and standard deviation of the carbon emission data: Based on the historical carbon emission data, calculate the mean μ y and the standard deviation σ y , expressed as:

[0133]

[0134] where μ yis the mean value of carbon emission data, and σ y is the standard deviation of carbon emission data, s is the number of samples of historical data, and y i is the carbon emission data at the i-th time point;

[0135] Set the carbon emission deviation threshold: According to the mean value and standard deviation of historical data, set the carbon emission deviation threshold Δy thresh , which is expressed as:

[0136] Δy thresh = β·σ y ;

[0137] where β is an empirical coefficient, set to 2 or 3;

[0138] Through the above content, it is possible to monitor the carbon emissions of each link in the production process in real time, and when the carbon emissions exceed the predetermined range, an alarm is issued in a timely manner and emergency measures are taken. It can automatically adapt to and adjust the threshold according to the fluctuations of the actual production process, ensuring that the alarm system always maintains a high-efficiency response in various production environments. By closely combining with production process parameters, it can not only identify carbon emission anomalies in a timely manner, but also automatically adjust process parameters, avoiding errors and delays in manual operations, and ensuring the stability and environmental protection of the production process.

[0139] The emergency measures in S43 include:

[0140] Automatically adjust process parameters: Adjust the process parameters (reaction efficiency, fuel ratio, reaction pressure) in the production process to reduce carbon emissions;

[0141] Suspend production or partial production suspension: After the alarm is triggered, automatically cut off the operation of the equipment, suspend the production line or adjust the production load to reduce emissions;

[0142] Increase the operation of emission purification equipment: Start or strengthen emission purification devices, including desulfurization, denitrification or carbon capture devices, to reduce the emission of harmful gases;

[0143] Notify the operator for manual intervention: When the automatic adjustment is ineffective or fails, notify the manual operator for intervention;

[0144] Optimize the energy use strategy: Adjust the energy ratio through the energy management unit to reduce the consumption of high-carbon energy and use more environmentally friendly energy for production;

[0145] Increase the emission monitoring frequency: Automatically adjust the data collection frequency, speed up data feedback, and facilitate quick response and adjustment;

[0146] Through the above, effective measures can be taken promptly when carbon emissions exceed the standard to ensure the stability and environmental friendliness of the production process. Automatically adjusting process parameters, pausing production or partially suspending production helps reduce carbon emissions in a timely manner, while increasing the operation of emission purification equipment reduces environmental pollution by strengthening pollutant removal. By optimizing the energy use strategy and reducing the consumption of high-carbon energy, not only is carbon emissions reduced, but also the energy use efficiency is improved. Increasing the emission monitoring frequency can ensure real-time understanding of the carbon emission situation, enabling rapid response and adjustment. In addition, by notifying the operator for manual intervention, the flexibility and response ability of the system are further improved, avoiding the risk when automatic adjustment fails to effectively solve the problem.

[0147] As Figure 2 shown, a coal chemical carbon emission intelligent monitoring system for implementing the above-mentioned coal chemical carbon emission intelligent monitoring method includes the following modules:

[0148] Data acquisition module: Real-time acquisition of carbon emission data during the coal chemical production process, including gas concentration, temperature, pressure, flow rate, meteorological information, and energy consumption data;

[0149] Data preprocessing module: Denoising, smoothing, standardizing, and filling missing values for the collected carbon emission data;

[0150] Carbon emission trend prediction and process adjustment module: Based on the preprocessed carbon emission data, using an adaptive neural network model to dynamically predict the carbon emission trend, and automatically adjusting the production process parameters according to the prediction results, including reaction efficiency, fuel ratio, and reaction pressure;

[0151] Carbon emission monitoring and alarm module: Real-time monitoring of the carbon emission situation in each link of the production process, comparing the real-time carbon emission data with the standard value, and when it is found that the carbon emission exceeds the set threshold, issuing an alarm and implementing emergency measures.

[0152] The present invention covers any alternatives, modifications, equivalent methods, and solutions made within the essence and scope of the present invention. To enable the public to have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, and those skilled in the art can fully understand the present invention without these detailed descriptions. In addition, well-known methods, processes, procedures, components, and circuits are not described in detail to avoid unnecessary confusion to the essence of the present invention.

[0153] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, several improvements and refinements can be made without departing from the principle of the present invention, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for intelligent monitoring of carbon emissions from coal chemical industry, characterized in that: The following steps are involved: S1, data collection: real-time collection of carbon emission data in the coal chemical production process, including gas concentration, temperature, pressure, flow, meteorological information and energy consumption data; S2, data preprocessing: preprocessing the collected carbon emission data, including denoising, smoothing, standardization and missing value filling; S3, Carbon emission trend prediction and process adjustment: Based on the pre-processed carbon emission data, the adaptive neural network model is used to dynamically predict the carbon emission trend, and the production process parameters are automatically adjusted according to the prediction results; S4, Carbon emission monitoring and alarm: Based on the adjusted production process parameters, the carbon emissions of each link in the production process are monitored in real time, and the real-time carbon emission data are compared with the standard value. If the comparison result exceeds the set threshold, an alarm is issued in time and emergency measures are taken.

2. The method for intelligent monitoring of carbon emissions from coal chemical industry according to claim 1, characterized in that: The data collection in S1 includes: S11, gas concentration collection: Use gas sensors to monitor gas concentration data in the coal chemical production process in real time, including carbon dioxide, nitrogen oxides, and sulfur dioxide; S12, temperature, pressure and flow collection: real-time collection of temperature, pressure and flow data in the coal chemical production process through industrial-grade sensors; S13, meteorological information collection: using meteorological sensors to collect meteorological information of the external environment, including wind speed, wind direction, temperature, and humidity; S14, energy consumption data collection: Real-time monitoring of energy consumption in the coal chemical production process through energy metering devices, including energy consumption data of coal, natural gas and electricity.

3. The method for intelligent monitoring of carbon emissions from coal chemical industry according to claim 1, characterized in that: The data preprocessing in S2 includes: S21, denoising: denoising the collected carbon emission data by using a moving average method; S22, smoothing: the carbon emission data is smoothed using the exponentially weighted moving average method; S23, standardization processing: standardizing the collected carbon emission data; S24, missing value filling: Linear interpolation is used to fill missing values ​​in the collected carbon emission data.

4. The method for intelligent monitoring of carbon emissions from coal chemical industry according to claim 1, characterized in that: The carbon emission trend prediction and process adjustment in S3 include: S31, dynamic prediction of carbon emission trends: Based on the pre-processed carbon emission data, an adaptive neural network model is used to dynamically predict the carbon emission trends in the future; S32, process parameter adjustment strategy generation: based on the prediction results of carbon emission trends, an optimization algorithm is used to automatically generate an adjustment strategy to determine the optimal combination of production process parameters; S33, automatic adjustment and execution of process parameters: applying the generated process parameter adjustment strategy to the production process, and executing the adjustment of the process parameters through the automated control unit.

5. The method for intelligent monitoring of carbon emissions from coal chemical industry according to claim 4, characterized in that: The dynamic prediction of carbon emission trends in S31 includes: S311, data input: construct the data input layer based on the preprocessed carbon emission data as input features; S312, Carbon emission trend prediction: Use an adaptive neural network model to dynamically predict carbon emission trends. The adaptive neural network model consists of multiple layers of neurons, and the output results are obtained by layer-by-layer weighted and biased calculations; S313, model parameter optimization: using an optimization algorithm to adjust the parameters of the adaptive neural network model, and calculating the error between the predicted value and the true value of the adaptive neural network model by using the mean square error as the loss function.

6. A method for intelligent monitoring of carbon emissions from coal chemical industry according to claim 5, characterized in that: The process parameter adjustment strategy generation in S32 includes: S321, constructing an optimization objective function: constructing an optimization objective function based on the prediction results of the carbon emission trend, the goal is to minimize carbon emissions and consider the feasibility of production efficiency and process parameters; S322, applying the optimization algorithm to generate the adjustment strategy: using the particle swarm optimization algorithm to solve the optimization objective function and automatically generate the optimal process parameter combination; S323, generate the optimal process parameter combination: after iterative calculation by the optimization algorithm, the optimal production process parameter combination p is obtained. opt .

7. A method for intelligent monitoring of carbon emissions from coal chemical industry according to claim 6, characterized in that: The automatic adjustment and execution of the process parameters in S33 include: S331, calculate the adjustment amount: according to the current process parameter combination p t and the optimal process parameter combination p opt , calculate the adjustment amount Δp of each process parameter i ; S332, execute the adjustment command: use the automation control unit to calculate the adjustment amount Δp i Applied to the corresponding control equipment in the production process, various process parameters are automatically adjusted through the PID control algorithm.

8. The method for intelligent monitoring of carbon emissions from coal chemical industry according to claim 7, characterized in that: The carbon emission monitoring and alarm in S4 includes: S41, real-time carbon emission data collection and monitoring: based on the adjusted process parameters, carbon emission data is collected in real time through sensors installed in various production links; S42, Comparison of carbon emission data with standard values: Compare the real-time collected carbon emission data with the set standard values ​​and calculate the difference e t ; S43, alarm judgment and emergency measures triggering: according to the calculated deviation and the set threshold Δy thresh For comparison, when |e t |≥Δy thresh When an emergency occurs, an alarm is triggered and emergency measures are taken.

9. The method for intelligent monitoring of carbon emissions from coal chemical industry according to claim 8, characterized in that: The emergency measures in S43 include: Automatic adjustment of process parameters: Adjust process parameters during production to reduce carbon emissions; Suspend or partially stop production: After the alarm is triggered, automatically cut off the operation of the equipment, suspend the production line or adjust the production load; Increase the operation of emission purification equipment: start or strengthen emission purification equipment, including desulfurization, denitrification or carbon capture equipment; Notify the operator to intervene manually: when the automatic adjustment is invalid or fails, notify the operator to intervene; Optimize energy usage strategy: adjust energy ratio through energy management unit; Increase emission monitoring frequency: Automatically adjust data collection frequency.

10. A coal chemical carbon emission intelligent monitoring system, used to implement a coal chemical carbon emission intelligent monitoring method as claimed in any one of claims 1 to 9, characterized in that: Includes the following modules: Data acquisition module: real-time collection of carbon emission data in the coal chemical production process, including gas concentration, temperature, pressure, flow, meteorological information and energy consumption data; Data preprocessing module: denoising, smoothing, standardization and missing value filling of collected carbon emission data; Carbon emission trend prediction and process adjustment module: Based on the pre-processed carbon emission data, the adaptive neural network model is used to dynamically predict the carbon emission trend, and the production process parameters, including reaction efficiency, fuel ratio, and reaction pressure, are automatically adjusted according to the prediction results; Carbon emission monitoring and alarm module: real-time monitoring of carbon emissions in each link of the production process, comparing the real-time carbon emission data with the standard value, and issuing an alarm and implementing emergency measures when it is found that carbon emissions exceed the set threshold.

Images