Coal-fired power plant intelligent environmental protection island control system based on multi-source data fusion

Abstract

The invention relates to the technical field of coal-fired power plant environmental protection, in particular to a coal-fired power plant intelligent environmental protection island control system based on multi-source data fusion. Comprising a multi-source data acquisition module, a data transmission module, a data preprocessing module, a multi-source data fusion module, an operation state analysis module, an intelligent control decision module, a control instruction execution module and a man-machine interaction module. According to the coal-fired power plant intelligent environmental protection island control system based on multi-source data fusion, equipment operation, environmental monitoring, power grid, fuel and meteorological data are widely acquired through the multi-source data acquisition module, the limitation of a single data source of a traditional system is broken through, a distributed Kalman filtering algorithm is combined with a neural network algorithm for data fusion, and the data fusion efficiency is improved. According to the method, the incidence relation between data can be deeply mined, temperature and pressure parameters of desulfurization equipment and flue gas sulfur dioxide concentration data are subjected to fusion analysis, the reason of desulfurization efficiency reduction can be accurately positioned, and compared with traditional single data source judgment, the fault diagnosis accuracy is improved.

Description

Technical Field

[0001] This invention relates to the field of environmental protection technology for coal-fired power plants, specifically to a smart environmental protection island control system for coal-fired power plants based on multi-source data fusion. Background Technology

[0003] As a core environmental protection facility integrating desulfurization, denitrification, and dust removal functions, the environmental protection island of a coal-fired power plant bears the heavy responsibility of removing pollutants such as sulfur dioxide, nitrogen oxides, and dust from flue gas. Its operational stability and efficiency directly determine whether the power plant can achieve environmental compliance. However, the traditional environmental protection island control systems currently used in most coal-fired power plants are no longer sufficient to meet increasingly stringent environmental and energy efficiency requirements. On the one hand, the desulfurization towers, denitrification reactors, dust collectors, and other equipment within the environmental protection island belong to different suppliers, and their data acquisition systems operate independently, resulting in "information silos" among equipment operation data, environmental monitoring data, and grid load data. According to research, approximately 60% of the environmental protection island data in coal-fired power plants is scattered across more than five independent databases, lacking effective data integration and correlation analysis between systems, making it impossible to form a comprehensive understanding of the environmental protection island's operational status. For example, a dynamic correlation model has not been established between the slurry flow rate and pH value data of the desulfurization equipment and the sulfur dioxide concentration data in the flue gas, making it difficult for operators to quickly pinpoint the root cause of the decline in desulfurization efficiency.

[0004] On the other hand, traditional control systems rely on human experience and fixed control strategies, resulting in rigid control logic. In actual operation, the operating conditions of coal-fired power plants are affected by various factors such as fuel quality fluctuations, grid load changes, and differences in meteorological conditions, and existing control systems cannot promptly perceive and respond to these dynamic changes. Taking a coal-fired power plant in northern China as an example, during the winter heating season, fluctuations in the sulfur content of the coal caused a decrease in the efficiency of the desulfurization system. The traditional control system continued to operate according to preset parameters, resulting in a desulfurizing agent waste rate as high as 20%, and short-term exceedances in emission concentrations. In addition, the monitoring method based on a single data source has weak anti-interference capabilities, and problems such as sensor errors and data transmission delays can easily lead to control decision errors. According to statistics, equipment malfunctions caused by data errors account for 15%-20% in traditional control systems, which not only increases the equipment failure rate but also seriously affects the environmental treatment effect and the economic benefits of the power plant.

[0005] Meanwhile, with the widespread application of technologies such as the Industrial Internet of Things, big data, and artificial intelligence in the power industry, the technical architecture of traditional control systems is gradually showing its limitations. Their distributed data processing model struggles to meet the real-time analysis needs of massive amounts of heterogeneous, multi-source data, and cannot achieve refined management and optimized control of the environmental island's operation. Driven by both "dual-carbon" goals and the construction of new power systems, developing an environmental island control system capable of integrating multi-source data and achieving intelligent and precise control has become an urgent need for coal-fired power plants to improve environmental performance, reduce operating costs, and enhance their core competitiveness. Summary of the Invention

[0006] The purpose of this invention is to provide a smart environmental protection island control system for coal-fired power plants based on multi-source data fusion, so as to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a smart environmental protection island control system for coal-fired power plants based on multi-source data fusion, comprising a multi-source data acquisition module, a data transmission module, a data preprocessing module, a multi-source data fusion module, an operation status analysis module, an intelligent control decision-making module, a control command execution module, and a human-machine interaction module;

[0008] The multi-source data acquisition module is used to collect equipment operation data, environmental monitoring data, power grid data, fuel data, and meteorological data during the operation of the environmental protection island of a coal-fired power plant.

[0009] The data transmission module is used to transmit the data collected by the multi-source data acquisition module to the data processing center;

[0010] The data preprocessing module is used to perform preprocessing operations such as cleaning, filtering, and normalization on the transmitted raw data.

[0011] The multi-source data fusion module is used to apply data fusion algorithms to fuse pre-processed data, establish a data fusion model, and obtain comprehensive data that reflects the actual operating status of the environmental protection island.

[0012] The operational status analysis module is used to perform real-time analysis and evaluation of the operational status of the environmental protection island based on the fused data and using big data analysis and machine learning algorithms.

[0013] The intelligent control decision module is used to generate intelligent control commands based on the evaluation results of the operation status analysis module, combined with preset control objectives and optimization strategies, using an expert system and model predictive control algorithms.

[0014] The control command execution module is used to transmit the control commands generated by the intelligent control decision module to each actuator of the environmental protection island, so as to realize the automated control of the environmental protection island equipment and provide feedback on the execution status of the control commands.

[0015] The human-machine interface module provides a visual operating interface for operators to view operating data, operating status analysis results, and control command execution status, as well as manually input control commands and receive alarm information.

[0016] Preferably, the equipment operation data includes the temperature, pressure, flow rate, rotation speed, and motor current parameters of the desulfurization equipment, denitrification equipment, and dust removal equipment; the environmental monitoring data includes the sulfur dioxide concentration, nitrogen oxide concentration, dust concentration, flue gas temperature, flue gas humidity, and flue gas flow rate data at the flue gas emission outlet.

[0017] Preferably, the multi-source data fusion module uses a distributed Kalman filter algorithm combined with a neural network algorithm to perform feature extraction and correlation analysis on data from different sources.

[0018] Preferably, the operation status analysis module includes an equipment health status assessment unit, an environmental protection treatment effect assessment unit, and an energy consumption analysis unit; the equipment health status assessment unit judges potential equipment failures and predicts the remaining service life based on the changing trends of equipment operation data and historical data; the environmental protection treatment effect assessment unit evaluates the efficiency and effect of environmental protection treatment by analyzing the relationship between environmental monitoring data and equipment operation parameters; the energy consumption analysis unit analyzes energy consumption by combining equipment operation data, fuel data, and power grid data.

[0019] Preferably, the data preprocessing module performs data cleaning by setting a threshold range, performs filtering by using the Kalman filter algorithm, and performs normalization by converting the data to a uniform numerical range.

[0020] Preferably, the model predictive control algorithm of the intelligent control decision module solves for the optimal control sequence by constructing a system prediction model and a performance index function through rolling optimization.

[0021] Preferably, the human-machine interaction module has an audible and visual alarm function, which displays the alarm cause and handling suggestions when the environmental protection island malfunctions or fails to meet standards.

[0022] Preferably, the data transmission module uses one of industrial Ethernet, 5G or Wi-Fi for data transmission to ensure the real-time performance, stability and accuracy of data transmission.

[0023] Preferably, the machine learning algorithm used in the operation status analysis module includes a long short-term memory network, which learns the normal operation data patterns of the equipment to identify potential faults such as bearing wear and pipe blockage in advance, thereby realizing real-time monitoring and prediction of the health status of the equipment.

[0024] Preferably, the expert system in the intelligent control decision module stores various operating conditions, problems and corresponding solutions during the operation of the environmental protection island. When the operation status analysis module reports problems such as substandard environmental treatment effect or excessive energy consumption, the expert system searches for similar cases in the knowledge base through pattern matching and provides preliminary control decision suggestions.

[0025] Compared with the prior art, the beneficial effects of the present invention are:

[0026] 1. This intelligent environmental protection island control system for coal-fired power plants, based on multi-source data fusion, extensively collects five categories of data—equipment operation, environmental monitoring, power grid, fuel, and meteorology—through a multi-source data acquisition module. Breaking through the limitations of traditional systems with a single data source, it utilizes a distributed Kalman filter algorithm combined with a neural network algorithm for data fusion. This enables in-depth analysis of the correlations between data, allowing for the fusion and analysis of temperature and pressure parameters of desulfurization equipment with flue gas sulfur dioxide concentration data. This accurately pinpoints the causes of desulfurization efficiency decline, significantly improving fault diagnosis accuracy compared to traditional single-source data analysis.

[0027] 2. This intelligent environmental protection island control system for coal-fired power plants, based on multi-source data fusion, dynamically optimizes control strategies by combining expert systems and model predictive control algorithms with operational status analysis results. In practical applications, when the sulfur content of coal fluctuates, the system can automatically adjust the absorbent dosage and circulation pump frequency of the desulfurization equipment. Compared with traditional fixed parameter control, desulfurization and denitrification efficiency are improved, while absorbent consumption is reduced. Through precise adjustment and start-up / shutdown optimization of equipment operating parameters, the system can reduce the overall energy consumption of the environmental protection island, effectively balancing the needs of environmental compliance and economic operation, and helping power plants achieve green and low-carbon transformation.

[0028] 3. This intelligent environmental protection island control system for coal-fired power plants, based on multi-source data fusion, employs machine learning algorithms such as long short-term memory networks to monitor and predict the health status of equipment in real time. By learning the normal operating data patterns of the equipment, it can identify potential faults such as bearing wear and pipeline blockage in advance. The fault warning time is earlier than that of traditional periodic inspections, reducing the probability of sudden equipment failures. The multi-source data fusion and preprocessing mechanism effectively filters data noise and outliers, improving data reliability, avoiding control errors caused by data errors, ensuring the stable operation of environmental protection island equipment, reducing unplanned downtime, and improving the continuity of power plant production. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a system architecture diagram of the present invention. Detailed Implementation

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] Please see Figure 1 This invention provides a technical solution: a smart environmental protection island control system for coal-fired power plants based on multi-source data fusion, comprising the following modules:

[0033] Multi-source data acquisition module: Used to collect various data during the operation of the environmental protection island of a coal-fired power plant, specifically including:

[0034] Equipment operation data: By installing sensors on key equipment such as desulfurization equipment, denitrification equipment, and dust removal equipment in the environmental protection island, operating parameters such as temperature, pressure, flow rate, speed, and motor current are collected to reflect the operating status of the equipment in real time.

[0035] Environmental monitoring data: Environmental monitoring equipment is installed at locations such as flue gas emission outlets on the environmental protection island to collect data such as sulfur dioxide concentration, nitrogen oxide concentration, dust concentration, flue gas temperature, flue gas humidity, and flue gas flow rate in the flue gas, which are used to evaluate the effectiveness of environmental protection treatment and whether emissions meet standards.

[0036] Power Grid Data: Connects to the power plant's power grid system to obtain data such as voltage, frequency, and load, and understands the impact of the power grid's operating status on the operation of equipment on the environmental protection island.

[0037] Fuel data: Collect data on the composition of coal, such as volatile matter, fixed carbon, sulfur content, ash content, etc., as well as data on fuel consumption. These data will affect the combustion process and the amount of pollutants generated.

[0038] Meteorological data: By connecting to the data interface of the meteorological department, meteorological data such as ambient temperature, humidity, wind speed, and wind direction are obtained. Meteorological conditions will have a certain impact on flue gas diffusion and the operation of environmental protection equipment.

[0039] Data transmission module: Transmits the data collected by the multi-source data acquisition module to the data processing center via wired network (such as industrial Ethernet) or wireless network (such as 5G, Wi-Fi) to ensure the real-time performance, stability and accuracy of data transmission.

[0040] Data preprocessing module: Performs preprocessing operations such as cleaning, filtering, and normalization on the transmitted raw data. Specifically, it includes:

[0041] Data cleaning: removing noise, outliers, and duplicate data from the data. By setting reasonable data threshold ranges, it identifies and removes data that is obviously inconsistent with the actual situation.

[0042] Filtering: Digital filtering algorithms, such as Kalman filtering, are used to smooth data with large fluctuations, thereby improving the reliability of the data.

[0043] Normalization: Converting data of different types and dimensions into a unified numerical range to facilitate subsequent data fusion and analysis.

[0044] Multi-source data fusion module: This module uses data fusion algorithms to fuse preprocessed data. Specifically, it employs a distributed Kalman filter algorithm combined with a neural network algorithm to extract features and perform correlation analysis on data from different sources, establishing a data fusion model. This model fuses multi-source data into more comprehensive, accurate, and reliable integrated data to reflect the true operational status of the environmental protection island.

[0045] For data from different sources, such as equipment operation data and environmental monitoring data, neural network algorithms are used for feature extraction. This includes temperature data (T), pressure data (P), and sulfur dioxide concentration data in the flue gas from the desulfurization equipment. For example, let's construct a multilayer perceptron neural network, with the weight matrix from the input layer to the hidden layer denoted as W. ij The bias is b j If the activation function of the hidden layer is σ(x), then the output of the hidden layer is h. j The calculation formula is: Where x i For input data (such as T, P and ...) By using multi-layer neural network calculations, key features of the data are extracted to prepare for subsequent fusion.

[0046] Distributed Kalman Filter Fusion: The extracted feature data are fused using a distributed Kalman filter algorithm. Let the system state equation be: x k =F k x k-1 +G k w k-1 The observation equation is: z k =H k x k +v k , where x k Let F be the system state vector at time k, which includes the fused state of equipment operating parameters and environmental monitoring parameters; k G is the state transition matrix; k The process noise driving matrix; w k-1 The process noise follows a Gaussian distribution N(0, Q). k-1 );zk H is the observation vector at time k; k v is the observation matrix; k The observed noise follows a Gaussian distribution N(0, R). k ).

[0047] Data fusion is achieved through two steps: prediction and updating.

[0048] State prediction:

[0049] Covariance prediction:

[0050] Kalman gain:

[0051] Status Update:

[0052] Covariance update: P k|k =(IK k H k )P k|k-1 .

[0053] By continuously iterating the above process, dynamic fusion of multi-source data is achieved, resulting in comprehensive data reflecting the operational status of the environmental protection island.

[0054] Operational Status Analysis Module: Based on the fused data, this module uses big data analytics and machine learning algorithms to perform real-time analysis and evaluation of the environmental island's operational status. Specifically, it includes:

[0055] Equipment health status assessment: Based on the changing trends and historical data of equipment operation, determine whether there are potential faults in the equipment and predict the remaining service life of the equipment.

[0056] A time-series-based machine learning model, such as a Long Short-Term Memory (LSTM) network, is used to analyze the changing trends of equipment operation data. Let the time series of equipment operation data be (x1, x2, ..., x...). n The input gate, forget gate, output gate, and cell state update formulas for the LSTM network are as follows:

[0057] Input gate: i t =σ(W ix x t +W ih h t-1 +b i );

[0058] Forgotten Gate: f t =σ(W fx x t +W fh h t-1 +bf );

[0059] Cell status update:

[0060] Output gate: o t =σ(W ox x+W oh h t-1 +b o );

[0061] Hidden state:

[0062] Among them, W ij Let b be the weight matrix. i Let σ(x) be the bias vector, and σ(x) be the sigmoid activation function. This involves element-wise multiplication. By training an LSTM network, the system learns the data characteristics and change patterns during normal device operation. When real-time data deviates from the normal pattern to a certain threshold, it determines that the device has potential faults. This is combined with historical data and prediction algorithms, such as the grey prediction model. Where x (0) (k) is the original data sequence. The sequence is generated by accumulation, where a and b are parameters to be estimated, to predict the remaining service life of the equipment.

[0063] Environmental treatment effect evaluation: By analyzing the relationship between environmental monitoring data and equipment operating parameters, the efficiency and effect of environmental treatment processes such as desulfurization, denitrification, and dust removal are evaluated to determine whether they meet environmental emission standards.

[0064] Establish a mathematical model for the environmental protection treatment process, focusing on desulfurization efficiency. For example, the calculation formula is as follows: in The concentration of sulfur dioxide in the flue gas at the inlet of the desulfurization equipment. The outlet concentration. Combined with equipment operating parameters (such as absorbent dosage m, liquid-to-gas ratio L / G, etc.), a multiple linear regression model was used. Where β i (where ε is the regression coefficient and ε is the error term) to analyze the relationship between equipment operating parameters and environmental protection treatment effects, evaluate the efficiency and effectiveness of environmental protection treatment processes such as desulfurization, denitrification, and dust removal, and determine whether environmental emission standards are met.

[0065] Energy consumption analysis: By combining equipment operation data, fuel data, and power grid data, analyze the energy consumption of the environmental protection island and identify the high-energy-consuming links and their causes.

[0066] Based on equipment operating data (such as motor power P) motor Running time t and fuel data (such as coal consumption m) coalcalorific value of coal Q coal Using data from the power grid (such as electricity consumption E), calculate the energy consumption index for the environmental island. Total energy consumption E total The calculation formula is: By analyzing the energy consumption ratio of different equipment and different processes, the energy consumption data is clustered to identify the processes and reasons for high energy consumption.

[0067] Intelligent control decision module: Based on the evaluation results of the operation status analysis module, combined with the preset control objectives and optimization strategies, it uses expert systems and model predictive control algorithms to generate intelligent control commands.

[0068] Specifically, it includes:

[0069] An expert system knowledge base is constructed to store various operating conditions, problems, and corresponding solutions during the operation of the environmental protection island. When the operation status analysis module reports problems such as substandard environmental treatment effects or excessive energy consumption, the expert system uses pattern matching to search for similar cases in the knowledge base and provides preliminary control decision suggestions. For example, when the desulfurization efficiency is lower than the target value, the expert system, based on historical experience, suggests increasing the amount of absorbent or adjusting the operating temperature of the desulfurization tower.

[0070] Model predictive control (MPC) algorithm is used to optimize the initial decision. Let the predictive model of the system be: x k+i|k =f(x) k+i-1|k ,u k+i-1|k ), where x k+i|k For the system state at time k+i predicted based on data at time k, u k+i-1|k This is the control input at time k+i-1.

[0071] Define the performance index function:

[0072] Among them, y k+i|k To predict the output, y sp,k+i Here, Q is the setpoint, R is the output error weight matrix, and N is the control increment weight matrix. p For predicting the time domain, N u To control the time domain.

[0073] By employing rolling optimization, the minimum value of the performance index function is obtained at each sampling time, thus yielding the optimal control sequence. and the first control quantity u k|k As the current control command output, it enables the adjustment of the operating parameters of the environmental protection island equipment and the control of equipment start-up and shutdown, so as to optimize the equipment operating efficiency and environmental protection effect, while reducing energy consumption.

[0074] Control command execution module: Transmits the control commands generated by the intelligent control decision module to various actuators in the environmental protection island, such as regulating valves, frequency converters, and motor controllers, to achieve automated control of the equipment in the environmental protection island. Simultaneously, it provides real-time feedback on the execution status of the control commands to ensure control effectiveness.

[0075] Human-Machine Interface Module: This module provides a visual operating interface, allowing operators to easily view real-time operational data, operational status analysis results, and control command execution status of the environmental protection island. Operators can also manually input control commands through this interface to intervene and adjust the system. Furthermore, this module has an alarm function; when the environmental protection island malfunctions or fails to meet standards, it promptly issues audible and visual alarms, displays the alarm cause, and provides suggested solutions.

[0076] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0077] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A smart environmental protection island control system for coal-fired power plants based on multi-source data fusion, comprising a multi-source data acquisition module, a data transmission module, a data preprocessing module, a multi-source data fusion module, an operation status analysis module, an intelligent control decision-making module, a control command execution module, and a human-machine interaction module, characterized in that: The multi-source data acquisition module is used to collect equipment operation data, environmental monitoring data, power grid data, fuel data, and meteorological data during the operation of the environmental protection island of a coal-fired power plant. The data transmission module is used to transmit the data collected by the multi-source data acquisition module to the data processing center; The data preprocessing module is used to perform preprocessing operations such as cleaning, filtering, and normalization on the transmitted raw data. The multi-source data fusion module is used to apply data fusion algorithms to fuse pre-processed data, establish a data fusion model, and obtain comprehensive data that reflects the actual operating status of the environmental protection island. The operational status analysis module is used to perform real-time analysis and evaluation of the operational status of the environmental protection island based on the fused data and using big data analysis and machine learning algorithms. The intelligent control decision module is used to generate intelligent control commands based on the evaluation results of the operation status analysis module, combined with preset control objectives and optimization strategies, using an expert system and model predictive control algorithms. The control command execution module is used to transmit the control commands generated by the intelligent control decision module to each actuator of the environmental protection island, so as to realize the automated control of the environmental protection island equipment and provide feedback on the execution status of the control commands. The human-machine interface module provides a visual operating interface for operators to view operating data, operating status analysis results, and control command execution status, as well as manually input control commands and receive alarm information.

2. The intelligent environmental protection island control system for coal-fired power plants based on multi-source data fusion as described in claim 1, characterized in that: The equipment operation data includes the temperature, pressure, flow rate, speed, and motor current parameters of the desulfurization equipment, denitrification equipment, and dust removal equipment; the environmental monitoring data includes the sulfur dioxide concentration, nitrogen oxide concentration, dust concentration, flue gas temperature, flue gas humidity, and flue gas flow rate data at the flue gas emission outlet.

3. The intelligent environmental protection island control system for coal-fired power plants based on multi-source data fusion as described in claim 1, characterized in that: The multi-source data fusion module uses a distributed Kalman filter algorithm combined with a neural network algorithm to perform feature extraction and correlation analysis on data from different sources.

4. The intelligent environmental protection island control system for coal-fired power plants based on multi-source data fusion as described in claim 1, characterized in that: The operational status analysis module includes an equipment health status assessment unit, an environmental protection treatment effect assessment unit, and an energy consumption analysis unit. The equipment health status assessment unit judges potential equipment failures and predicts the remaining service life based on the changing trends of equipment operation data and historical data. The environmental protection treatment effect assessment unit evaluates the efficiency and effectiveness of environmental protection treatment by analyzing the relationship between environmental monitoring data and equipment operation parameters. The energy consumption analysis unit analyzes energy consumption by combining equipment operation data, fuel data, and power grid data.

5. The intelligent environmental protection island control system for coal-fired power plants based on multi-source data fusion as described in claim 1, characterized in that: The data preprocessing module cleans the data by setting a threshold range, performs filtering by using the Kalman filter algorithm, and normalizes the data by converting it to a uniform numerical range.

6. The intelligent environmental protection island control system for coal-fired power plants based on multi-source data fusion as described in claim 1, characterized in that: The model predictive control algorithm of the intelligent control decision module solves for the optimal control sequence by constructing a system prediction model and performance index function and performing rolling optimization.

7. The intelligent environmental protection island control system for coal-fired power plants based on multi-source data fusion as described in claim 1, characterized in that: The human-computer interaction module has an audible and visual alarm function. When the environmental protection island malfunctions or fails to meet standards, it displays the alarm cause and handling suggestions.

8. The intelligent environmental protection island control system for coal-fired power plants based on multi-source data fusion according to claim 1, characterized in that: The data transmission module uses one of industrial Ethernet, 5G, or Wi-Fi for data transmission to ensure the real-time performance, stability, and accuracy of data transmission.

9. The intelligent environmental protection island control system for coal-fired power plants based on multi-source data fusion as described in claim 1, characterized in that: The operational status analysis module employs machine learning algorithms including Long Short-Term Memory (LSTM) networks. By learning the normal operating data patterns of the equipment, it can identify potential faults such as bearing wear and pipe blockage in advance, thereby enabling real-time monitoring and prediction of the equipment's health status.

10. The intelligent environmental protection island control system for coal-fired power plants based on multi-source data fusion according to claim 1, characterized in that: The expert system in the intelligent control decision module stores various operating conditions, problems, and corresponding solutions during the operation of the environmental protection island. When the operation status analysis module reports problems such as substandard environmental treatment effect or excessive energy consumption, the expert system uses pattern matching to search for similar cases in the knowledge base and provides preliminary control decision suggestions.

Images