Intelligent collecting, preparing and converting system for coal as fired and control method of intelligent collecting, preparing and converting system

Abstract

The invention relates to the technical field of intelligent coal as fired control, and provides an intelligent coal as fired collecting and processing system and a control method thereof.The intelligent coal as fired collecting and processing system comprises a server side, a data collecting terminal, an equipment side and the like, and through a data obtaining unit, an equipment execution monitoring unit, a dynamic simulation deduction unit, an error analysis unit, an execution command optimization unit and the like, the intelligent coal as fired collecting and processing system is obtained; and comprehensive intelligent control on the coal as fired sampling, preparation and chemical process is realized. According to the method, the running state of equipment can be monitored in real time, faults or data acquisition errors can be found and processed in time, continuous and stable running of the system is ensured, and meanwhile, the accuracy and efficiency of task execution are improved through error analysis and command optimization. By applying the system and the method, the intelligent level of coal as fired collection and preparation of a thermal power plant can be remarkably improved, the production process is optimized, and the operation cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control and processing of furnace coal, and in particular to an intelligent mining and processing system for furnace coal and a control method thereof. Background Art

[0002] With the continuous advancement of science and technology, the intelligent collection technology of coal entering the furnace of thermal power plants has been significantly developed. The intelligent collection of coal entering the furnace is mainly controlled by the intelligent fuel integration platform, which comprehensively uses cutting-edge technologies such as electronic tags, intelligent management, mechanical automation, barcode management, and dynamic measurement and control. Through the intelligent integration of these technologies, the intelligent management of the entire process from coal planning, procurement, factory metering, coal collection and processing, storage to video monitoring is realized. This intelligent development not only improves the fuel control efficiency of thermal power plants, but also effectively reduces fuel costs and improves combustion efficiency.

[0003] In actual applications, the intelligent collection technology of coal entering the thermal power plant is mainly operated through the intelligent fuel integration platform. The platform starts with the coal burning plan and uses electronic tags and barcode technology to track and manage the coal throughout the process. When the coal enters the plant, unattended measurement and automatic sampling are realized through advanced laser measurement and wireless radio frequency technology, which improves the efficiency and accuracy of coal entering the plant. In the collection and processing link, the intelligent fuel integration platform uses mechanical automation and dynamic measurement and control technology to realize automated operation, reduce human intervention, and improve the objectivity and accuracy of data. Finally, the entire process is monitored in real time through the video surveillance system to ensure the standardization and safety of the operation.

[0004] Although the intelligent coal collection technology for furnaces has made significant progress, there are still the following technical pain points. First, the coal mining and processing process involves many processes, and the coal mining and processing process is different from the processing industry and the intelligent manufacturing industry in actual use scenarios. The coal slag in the coal-burning site is dusty and the temperature of the coal-burning site is high. In this working environment, the data collection involved in the coal mining and processing process and the completion of the control command execution will be hindered. If the equipment fails or data collection errors occur, and they are not discovered and processed in time, it will affect the continuous operation of the intelligent system. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides an intelligent coal mining and processing system for furnaces and a control method thereof, so as to solve the problem that if equipment failure or data collection error occurs and is not discovered and processed in time, the continuous operation of the intelligent system will be affected.

[0006] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows:

[0007] In a first aspect, the present invention provides an intelligent coal collection and processing system for furnace entry, comprising: a server end, a data acquisition terminal, a device end, a background control end and a user mobile terminal, the server end establishes a communication connection with the data acquisition terminal, the device end, the background control end and the user mobile terminal, the server end processes and analyzes data transmitted by the data acquisition terminal, the background control end and the user mobile terminal, generates a furnace entry coal control command and transmits it to the device end, after the device end receives the furnace entry coal control command, the device end parses the furnace entry coal control command to obtain the parsed furnace entry coal control command, and then transmits the parsed furnace entry coal control command to the device end;

[0008] The equipment end includes belt coal flow sampling device, sample preparation equipment, and coal quality testing equipment;

[0009] Data collection terminals include temperature sensors, pressure sensors, flow sensors, RFID readers, laser scanners, intelligent inspection robots and inspection drones;

[0010] The server side includes:

[0011] A data acquisition unit acquires the equipment operation data of the equipment end and the sensor monitoring data of the data acquisition terminal. The equipment end operation data includes the operation data of the belt coal flow sampling device, the operation data of the sample preparation equipment, and the operation data of the coal quality testing equipment. The sensor monitoring data includes the temperature sensor data, the pressure sensor data, and the flow sensor data;

[0012] The equipment execution monitoring unit receives the execution task command from the background control end, generates the execution task monitoring position point according to the execution task command, establishes the monitoring inspection path according to the execution task detection position point, sends the monitoring inspection path to the intelligent inspection robot and the inspection drone, and the intelligent inspection robot and the inspection drone conduct inspection based on the monitoring inspection path to obtain real-time inspection information;

[0013] The dynamic simulation deduction unit pre-processes the execution task command of the background control terminal and inserts it into the preset digital twin model to obtain the first device execution deduction data, substitutes the real-time inspection information into the preset digital twin model to obtain the second device execution deduction data, performs data comparison and analysis on the first device execution deduction data and the second device execution deduction data to obtain the device command execution deduction error data, selects the device command execution deduction error data with the lowest error value from the device command execution deduction error data, uses the task command corresponding to the device command execution deduction error data with the lowest error value as the real-time task command, sends the real-time task command to the device end, and the device end executes the real-time task command;

[0014] The error analysis unit analyzes the device command execution error data to obtain analyzed device execution error data, matches the analyzed device error data with the device at the device end to obtain classified error data, extracts data features from the classified error data and performs cluster analysis to obtain error analysis results;

[0015] The execution command optimization unit trains the deep algorithm model based on the data in the error analysis results and the data generated by the equipment execution monitoring unit, the dynamic simulation and deduction unit, and the data acquisition unit to obtain a trained error analysis model. The real-time coal entering the furnace execution command error information is generated by the trained error analysis model, and the real-time task command is corrected using the coal entering the furnace execution command error information to obtain a corrected real-time task command. The corrected real-time task command is sent to the equipment end, and the equipment end executes the corrected real-time task command.

[0016] Furthermore, the data acquisition unit of the intelligent coal mining and processing system provided by the present invention includes:

[0017] Acquisition of equipment operation data: The data acquisition unit first establishes a communication connection with the belt coal flow sampling device, sample preparation equipment, and coal quality testing equipment at the equipment end;

[0018] The data acquisition unit receives the operation data sent by the device end, the operation data sent by the device end includes device status information, the device status information includes operation, stop, failure, operation time, quantity of processed coal and quality of processed coal;

[0019] The operating data of the belt coal flow sampling device include the sampling frequency, the amount of coal sampled and the location of the sampling point;

[0020] The operation data of sample preparation equipment and coal quality testing equipment include sample preparation time, temperature, pressure and other parameters during sample preparation, and test results data, which include moisture, ash and volatility of coal;

[0021] Acquisition of monitoring data from sensors at the data acquisition terminal: The data acquisition unit establishes a communication connection with the data acquisition terminal.

[0022] The data acquisition unit receives monitoring data sent by the temperature sensor, the pressure sensor and the reader / writer;

[0023] Temperature sensors provide real-time temperature readings to help monitor the operating environment and coal temperature of the equipment as well as the flow sensor;

[0024] Pressure sensors provide pressure data inside equipment or in pipelines to ensure safe operation.

[0025] Flow sensors provide flow data of fluids (such as coal powder, water, etc.) to help control process flows.

[0026] RFID readers and laser scanners provide identification information of coal and coal-carrying vehicles, as well as logistics data such as coal entering and leaving the warehouse.

[0027] Furthermore, the intelligent coal mining and processing system provided by the present invention includes an equipment execution monitoring unit, which includes:

[0028] The device execution monitoring unit receives and parses the execution task command sent by the background control terminal, and the execution task command sent by the background control terminal includes information about the device, area or specific task to be monitored;

[0029] According to the parsed task command, the equipment execution monitoring unit determines the locations that need to be monitored. The key locations that need to be monitored include equipment components, areas prone to failure, and process flow links that need to be inspected.

[0030] After the locations that need to be monitored are determined, the equipment execution monitoring unit organizes the locations that need to be monitored into a list, which includes the coordinates or identifiers of each location point, so as to subsequently establish an inspection path and perform precise monitoring.

[0031] Furthermore, the intelligent coal mining and processing system provided by the present invention includes a dynamic simulation and deduction unit, which includes:

[0032] The dynamic simulation deduction unit aligns the deduction data executed by the first device with the deduction data executed by the second device in time and space;

[0033] Interpolate or synchronize the deduction data executed by the first device and the deduction data executed by the second device to obtain processed deduction data executed by the first device and processed deduction data executed by the second device;

[0034] The dynamic simulation deduction unit calculates the error between the processed first device execution deduction data and the processed second device execution deduction data, and the difference includes position error, speed error and state error.

[0035] Furthermore, the invention provides an intelligent coal mining and processing system for furnaces, and an error analysis unit, comprising:

[0036] The error analysis unit receives the equipment command execution deduction error data from the dynamic simulation deduction unit, and the equipment command execution deduction error data includes position error, time error, and speed error;

[0037] The error analysis unit pre-processes the standby command execution deduction error data to detect the integrity of the standby command execution deduction error data;

[0038] The device command execution deduction error data is classified according to the device, command type and timestamp. For each type of error data, the specific error value, error direction and context information of the error are further analyzed. The context information of the error includes the device status and ambient temperature, and the error direction includes positive error and negative error.

[0039] Extract features from the parsed error data to reveal the inherent laws and patterns of the error data. The features from the parsed error data include the maximum value, minimum value, average value, standard deviation, and the changing trend of the error over time.

[0040] The error analysis unit outputs analyzed device execution error data.

[0041] Furthermore, the intelligent coal mining and processing system provided by the present invention, the error analysis unit, also includes:

[0042] Each device on the device side has an identification, which includes a device ID, a device name, and a device number;

[0043] The error analysis unit obtains a device list at the device end, including identification information of the device and attributes of the device;

[0044] The error analysis unit matches the device information in the parsed device error data with the device identification in the device list, and the matching result is obtained by comparing the device ID, name or identification;

[0045] When the equipment and the error data are successfully matched, the error analysis unit will classify the error data according to the type or function of the equipment to obtain a classification result. The classification result includes that the error data of the belt coal flow sampling device is classified as a sampling error, and the error data error of the sample preparation equipment is classified as a sample preparation error.

[0046] Furthermore, the intelligent coal mining and processing system provided by the present invention, the error analysis unit, also includes:

[0047] Equipment execution error data includes error size, frequency, duration, and change trend;

[0048] After clustering is completed, the error analysis unit interprets and analyzes each cluster, including identifying the main characteristics of each cluster, the error type, the cause of the error, and the corresponding equipment or operating conditions;

[0049] The error analysis unit integrates the clustering results into an error analysis report, which includes a detailed description of each cluster, error distribution, trend analysis, and suggestions for error improvement.

[0050] Furthermore, the intelligent coal mining and processing system provided by the present invention executes a command optimization unit, including:

[0051] The execution command optimization unit obtains the error analysis result data from the error analysis unit, and also collects the real-time inspection information provided by the equipment execution monitoring unit, the equipment command execution deduction error data of the dynamic simulation deduction unit, and the equipment operation data and sensor monitoring data of the data acquisition unit.

[0052] The data acquired and collected by the execution command optimization unit are integrated into the data set and preprocessed. The execution command optimization unit extracts features from the integrated data. The extracted features include the type of command, execution time, device status, and environmental parameters when the device executes the command;

[0053] The deep algorithm model is trained using the integrated and preprocessed dataset and the extracted features.

[0054] During the training process, the deep algorithm model tries to minimize the difference between the predicted error and the actual error, and adjusts its internal parameters through the back-propagation algorithm;

[0055] During the training process, the execution command optimization unit uses the validation dataset to evaluate the performance of the model;

[0056] By adjusting the model's hyperparameters, including learning rate, batch size, and number of hidden layers, the model's performance is optimized;

[0057] After the training is completed, it will be deployed to the production environment for real-time coal-in-furnace execution command error information generation.

[0058] Furthermore, the intelligent coal mining and processing system provided by the present invention also includes:

[0059] The execution command optimization unit collects real-time data from the data acquisition unit, the equipment execution monitoring unit and the dynamic simulation deduction unit. The collected real-time data includes equipment operation status, sensor readings, execution task commands and equipment command execution deduction error data;

[0060] The collected real-time data is used as input, and the trained error analysis model is used to process the input data. Based on the learned patterns and relationships, the error that will be generated by the current execution command is predicted to obtain the prediction result, which is the real-time error information of the execution command of the coal entering the furnace.

[0061] According to the predicted error type and size, the execution command optimization unit adjusts the parameters of the original command to reduce or eliminate the predicted error.

[0062] In a second aspect, the present invention provides a method for controlling the intelligent collection and processing of incoming coal, which is applied to the intelligent collection and processing system of incoming coal, comprising:

[0063] S101, the server side obtains the equipment operation data of the equipment side and the sensor monitoring data of the data acquisition terminal, the equipment side operation data includes the operation data of the belt coal flow sampling device, the sample preparation equipment operation data, and the coal quality testing equipment operation data, and the sensor monitoring data includes the temperature sensor data, the pressure sensor data, and the flow sensor data;

[0064] S102, the server receives the task execution command from the background control end, generates the task execution monitoring position point according to the task execution command, establishes the monitoring inspection path according to the task execution detection position point, sends the monitoring inspection path to the intelligent inspection robot and the inspection drone, and the intelligent inspection robot and the inspection drone perform inspection based on the monitoring inspection path to obtain real-time inspection information;

[0065] S103, the server side pre-processes the execution task command of the background control terminal and inserts it into the preset digital twin model to obtain the first device execution deduction data, substitutes the real-time inspection information into the preset digital twin model to obtain the second device execution deduction data, compares and analyzes the first device execution deduction data with the second device execution deduction data to obtain device command execution deduction error data, selects the device command execution deduction error data with the lowest error value from the device command execution deduction error data, uses the task command corresponding to the device command execution deduction error data with the lowest error value as the real-time task command, sends the real-time task command to the device side, and the device side executes the real-time task command;

[0066] S104, the server side parses the device command execution error data to obtain parsed device execution error data, matches the parsed device error data with the device on the device side to obtain classified error data, extracts data features from the classified error data and performs cluster analysis to obtain error analysis results;

[0067] S105, the server side trains the deep algorithm model based on the data in the error analysis results and the data generated by the equipment execution monitoring unit, the dynamic simulation and deduction unit, and the data acquisition unit to obtain a trained error analysis model, generates real-time error information of the coal entering the furnace execution command through the trained error analysis model, uses the error information of the coal entering the furnace execution command to correct the real-time task command, obtains the corrected real-time task command, and sends the corrected real-time task command to the equipment side.

[0068] Beneficial effects of the present invention;

[0069] Improve the continuity and stability of system operation: Through real-time inspections by intelligent inspection robots and inspection drones, as well as comprehensive analysis of equipment operating status and sensor monitoring data, the present invention can promptly detect and handle equipment failures or data collection errors, avoid these problems affecting the continuous operation of the intelligent system, and ensure the efficiency and stability of the system.

[0070] Improve data accuracy and reliability: The system integrates a variety of sensors and monitoring equipment to monitor the coal mining and processing process from all directions and angles, which improves the accuracy and reliability of data collection and provides a solid data foundation for subsequent coal quality analysis and control.

[0071] Optimize task execution efficiency: The dynamic simulation and deduction unit pre-processes and simulates the task commands, selects the task commands with the lowest error value, reduces command execution errors, and improves task execution efficiency and accuracy.

[0072] Realize intelligent management and decision support: The error analysis unit provides detailed data support and decision-making basis, which helps to realize intelligent management and scientific decision-making.

[0073] Enhance the system's adaptability and learning ability: The execution command optimization unit trains the deep algorithm model based on the error analysis results and real-time data, corrects the real-time task commands, enhances the system's adaptability and learning ability, optimizes the control strategy, and improves the overall operation efficiency.

[0074] In summary, the present invention comprehensively and intelligently manages and controls the coal mining and processing process entering the furnace, providing powerful technical support for the fuel control of thermal power plants. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0076] Figure 1 A schematic diagram of a process method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0077] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The technical solutions provided by the embodiments of the present invention are described in detail below in conjunction with the drawings.

[0078] In order to better understand the purpose of the present invention, the present invention is described in further detail below.

[0079] In a first aspect, the present invention provides an intelligent coal collection and processing system for furnace entry, comprising: a server end, a data acquisition terminal, a device end, a background control end and a user mobile terminal, the server end establishes a communication connection with the data acquisition terminal, the device end, the background control end and the user mobile terminal, the server end processes and analyzes data transmitted by the data acquisition terminal, the background control end and the user mobile terminal, generates a furnace entry coal control command and transmits it to the device end, after the device end receives the furnace entry coal control command, the device end parses the furnace entry coal control command to obtain the parsed furnace entry coal control command, and then transmits the parsed furnace entry coal control command to the device end;

[0080] The equipment end includes belt coal flow sampling device, sample preparation equipment, and coal quality testing equipment;

[0081] Data collection terminals include temperature sensors, pressure sensors, flow sensors, RFID readers, laser scanners, intelligent inspection robots and inspection drones;

[0082] The server side includes:

[0083] A data acquisition unit acquires the equipment operation data of the equipment end and the sensor monitoring data of the data acquisition terminal. The equipment end operation data includes the operation data of the belt coal flow sampling device, the operation data of the sample preparation equipment, and the operation data of the coal quality testing equipment. The sensor monitoring data includes the temperature sensor data, the pressure sensor data, and the flow sensor data;

[0084] The equipment execution monitoring unit receives the execution task command from the background control end, generates the execution task monitoring position point according to the execution task command, establishes the monitoring inspection path according to the execution task detection position point, sends the monitoring inspection path to the intelligent inspection robot and the inspection drone, and the intelligent inspection robot and the inspection drone conduct inspection based on the monitoring inspection path to obtain real-time inspection information;

[0085] Receiving execution task commands: The equipment execution monitoring unit will first receive execution task commands from the background control end. The commands are usually issued by the background control personnel based on production requirements or system plans to guide the equipment to perform specific monitoring tasks.

[0086] Generate execution task monitoring location points: After receiving the task command, the equipment execution monitoring unit will analyze and determine the key location points that need to be monitored based on the specific content of the command. These location points are key parts of the equipment, nodes prone to failure, or areas that require special attention.

[0087] Establish monitoring inspection path: Once the monitoring location is determined, the equipment execution monitoring unit will further plan an efficient inspection path. This path will ensure that the intelligent inspection equipment can traverse all key location points for effective data collection and status inspection.

[0088] Sending monitoring and inspection routes: The planned monitoring and inspection routes will be sent to intelligent inspection robots and inspection drones. These intelligent devices will conduct autonomous inspections along the preset routes.

[0089] Conduct inspections and obtain real-time inspection information: Intelligent inspection robots and inspection drones work along designated inspection routes, collect real-time data from each monitoring location, such as temperature, pressure, flow and other key parameters, and transmit this information back to the equipment execution monitoring unit in real time.

[0090] The equipment execution monitoring unit ensures that the system can detect equipment failures or data collection errors in a timely manner, so as to respond and adjust quickly to maintain the continuous and stable operation of the system. At the same time, the data collected by the intelligent inspection equipment also provides an information basis for subsequent data analysis, fault prediction and preventive maintenance. In the entire system, the equipment execution monitoring unit plays a key role in connecting the upper and lower levels. It is not only the execution of the background control commands, but also the premise of subsequent data processing and optimization.

[0091] The dynamic simulation deduction unit pre-processes the execution task command of the background control terminal and inserts it into the preset digital twin model to obtain the first device execution deduction data, substitutes the real-time inspection information into the preset digital twin model to obtain the second device execution deduction data, performs data comparison and analysis on the first device execution deduction data and the second device execution deduction data to obtain the device command execution deduction error data, selects the device command execution deduction error data with the lowest error value from the device command execution deduction error data, uses the task command corresponding to the device command execution deduction error data with the lowest error value as the real-time task command, sends the real-time task command to the device end, and the device end executes the real-time task command;

[0092] Substituting into the digital twin model: The dynamic simulation deduction unit will first receive the execution task commands from the background control terminal and pre-process these commands. The pre-processed task commands will be substituted into the preset digital twin model to obtain the first device execution deduction data, which reflects the expected results of the device execution command under ideal conditions.

[0093] At the same time, the digital twin model will also receive real-time inspection information, and this information will also be substituted into the digital twin model to obtain the second device execution deduction data. These data reflect the status of the device in actual operation.

[0094] Data comparison and analysis: Next, the dynamic simulation and deduction unit will compare and analyze the deduction data executed by the first device and the deduction data executed by the second device. The purpose of this step is to find out the differences and errors in the command execution process.

[0095] Through comparison, the unit is able to generate device command execution error data that reveals the gap between actual execution and ideal execution.

[0096] Filter the data with the lowest error value: In the device command execution deduction error data, the dynamic simulation deduction unit will filter out the data with the lowest error value. This means finding the command execution solution that is closest to the actual execution and has the smallest error.

[0097] After filtering out the device command execution deduction error data with the lowest error value, the corresponding task command will be regarded as the optimal command.

[0098] Send real-time task command: Finally, the optimized and filtered real-time task command will be sent to the device. After receiving the command, the device will execute it immediately, thus ensuring that the device operates in an efficient and accurate manner.

[0099] The error analysis unit analyzes the device command execution error data to obtain analyzed device execution error data, matches the analyzed device error data with the device at the device end to obtain classified error data, extracts data features from the classified error data and performs cluster analysis to obtain error analysis results;

[0100] Data analysis: The error analysis unit first receives the equipment command execution error data, which comes from the previous dynamic simulation or other monitoring links;

[0101] Next, the error analysis unit analyzes the error data and converts it into a format that can be further analyzed and processed. The analysis process includes steps such as data cleaning and format conversion to ensure the accuracy and consistency of the data.

[0102] Data matching and classification: The parsed device execution error data is matched with the actual device on the device side. This step is to determine which error data is associated with a specific device.

[0103] Through matching, the error data is further classified based on multiple factors such as device type, command type, execution time period, etc., which helps to analyze the root causes and patterns of errors more accurately in the future.

[0104] Data feature extraction: After the classification is completed, the error analysis unit will extract features for each type of error data. This includes identifying key indicators, trends, periodic changes, etc. in the data. These features will help understand the nature and cause of the error.

[0105] Feature extraction involves statistical methods, time series analysis and other techniques to extract the most valuable information for error analysis.

[0106] Cluster analysis: Next, the error analysis unit performs cluster analysis on the extracted features. Clustering is an unsupervised learning method that can group similar data points together, thereby revealing hidden patterns in the data.

[0107] In the context of error analysis, cluster analysis can help identify groups of data with similar error characteristics, including those pointing to specific equipment failure modes, improper operation, or environmental factors.

[0108] Generate error analysis results: Based on the above steps, the error analysis unit will eventually generate a detailed error analysis result. This result includes information such as the type, frequency, severity, and cause of the error.

[0109] This analysis is critical for equipment maintenance, failure prevention, and system optimization because it provides deep insights into equipment operating status and early warnings of potential problems.

[0110] The execution command optimization unit trains the deep algorithm model based on the data in the error analysis results and the data generated by the equipment execution monitoring unit, the dynamic simulation and deduction unit, and the data acquisition unit to obtain a trained error analysis model. The real-time coal entering the furnace execution command error information is generated by the trained error analysis model, and the real-time task command is corrected using the coal entering the furnace execution command error information to obtain a corrected real-time task command. The corrected real-time task command is sent to the equipment end, and the equipment end executes the corrected real-time task command.

[0111] Specifically, the data acquisition unit of the intelligent coal mining and processing system provided by the present invention includes:

[0112] Acquisition of equipment operation data: The data acquisition unit first establishes a communication connection with the belt coal flow sampling device, sample preparation equipment, and coal quality testing equipment at the equipment end;

[0113] The data acquisition unit receives the operation data sent by the device end, the operation data sent by the device end includes device status information, the device status information includes operation, stop, failure, operation time, quantity of processed coal and quality of processed coal;

[0114] The operating data of the belt coal flow sampling device include the sampling frequency, the amount of coal sampled and the location of the sampling point;

[0115] The operation data of sample preparation equipment and coal quality testing equipment include sample preparation time, temperature, pressure and other parameters during sample preparation, and test results data, which include moisture, ash and volatility of coal;

[0116] Acquisition of monitoring data from the data acquisition terminal sensor: The data acquisition unit establishes a communication connection with the data acquisition terminal.

[0117] The data acquisition unit receives monitoring data sent by the temperature sensor, the pressure sensor and the reader / writer;

[0118] Temperature sensors provide real-time temperature readings to help monitor the operating environment and coal temperature of the equipment as well as the flow sensor;

[0119] Pressure sensors provide pressure data inside equipment or in pipelines to ensure safe operation.

[0120] Flow sensors provide flow data of fluids (such as coal powder, water, etc.) to help control process flows.

[0121] RFID readers and laser scanners provide identification information of coal and coal-carrying vehicles, as well as logistics data such as coal entering and leaving the warehouse.

[0122] Specifically, the intelligent coal mining and processing system provided by the present invention includes an equipment execution monitoring unit, which includes:

[0123] The device execution monitoring unit receives and parses the execution task command sent by the background control terminal, and the execution task command sent by the background control terminal includes information about the device, area or specific task to be monitored;

[0124] According to the parsed task command, the equipment execution monitoring unit determines the locations that need to be monitored. The key locations that need to be monitored include equipment components, areas prone to failure, and process flow links that need to be inspected.

[0125] After the locations that need to be monitored are determined, the equipment execution monitoring unit organizes the locations that need to be monitored into a list, which includes the coordinates or identifiers of each location point, so as to subsequently establish an inspection path and perform precise monitoring.

[0126] Specifically, the intelligent coal mining and processing system provided by the present invention, the dynamic simulation and deduction unit, includes:

[0127] The dynamic simulation deduction unit aligns the deduction data executed by the first device with the deduction data executed by the second device in time and space;

[0128] Interpolate or synchronize the deduction data executed by the first device and the deduction data executed by the second device to obtain processed deduction data executed by the first device and processed deduction data executed by the second device;

[0129] The dynamic simulation deduction unit calculates the error between the processed first device execution deduction data and the processed second device execution deduction data, and the difference includes position error, speed error and state error.

[0130] Specifically, the intelligent coal mining and processing system for furnace input provided by the present invention, the error analysis unit, includes:

[0131] The error analysis unit receives the equipment command execution deduction error data from the dynamic simulation deduction unit, and the equipment command execution deduction error data includes position error, time error, and speed error;

[0132] The error analysis unit pre-processes the standby command execution deduction error data to detect the integrity of the standby command execution deduction error data;

[0133] The device command execution deduction error data is classified according to the device, command type and timestamp. For each type of error data, the specific error value, error direction and context information of the error are further analyzed. The context information of the error includes the device status and ambient temperature. The error direction includes positive error and negative error.

[0134] Extract features from the parsed error data to reveal the inherent laws and patterns of the error data. The features from the parsed error data include the maximum value, minimum value, average value, standard deviation, and the changing trend of the error over time.

[0135] The error analysis unit outputs analyzed device execution error data.

[0136] Specifically, the intelligent coal mining and processing system provided by the present invention, the error analysis unit, also includes:

[0137] Each device on the device side has an identification, which includes a device ID, a device name, and a device number;

[0138] The error analysis unit obtains a device list at the device end, including identification information of the device and attributes of the device;

[0139] The error analysis unit matches the device information in the parsed device error data with the device identification in the device list, and the matching result is obtained by comparing the device ID, name or identification;

[0140] When the equipment and the error data are successfully matched, the error analysis unit will classify the error data according to the type or function of the equipment to obtain a classification result. The classification result includes that the error data of the belt coal flow sampling device is classified as a sampling error, and the error data of the sample preparation equipment is classified as a sample preparation error.

[0141] Specifically, the intelligent coal mining and processing system provided by the present invention, the error analysis unit, also includes:

[0142] Equipment execution error data includes error size, frequency, duration, and change trend;

[0143] After clustering is completed, the error analysis unit interprets and analyzes each cluster, including identifying the main characteristics of each cluster, the error type, the cause of the error, and the corresponding equipment or operating conditions;

[0144] The error analysis unit integrates the clustering results into an error analysis report, which includes a detailed description of each cluster, error distribution, trend analysis, and suggestions for error improvement.

[0145] Specifically, the intelligent coal mining and processing system provided by the present invention executes a command optimization unit, including:

[0146] The execution command optimization unit obtains the error analysis result data from the error analysis unit, and also collects the real-time inspection information provided by the equipment execution monitoring unit, the equipment command execution deduction error data of the dynamic simulation deduction unit, and the equipment operation data and sensor monitoring data of the data acquisition unit.

[0147] The data acquired and collected by the execution command optimization unit are integrated into the data set and preprocessed. The execution command optimization unit extracts features from the integrated data. The extracted features include the type of command, execution time, device status, and environmental parameters when the device executes the command;

[0148] The deep algorithm model is trained using the integrated and preprocessed dataset and the extracted features.

[0149] During the training process, the deep algorithm model tries to minimize the difference between the predicted error and the actual error, and adjusts its internal parameters through the back-propagation algorithm;

[0150] During the training process, the execution command optimization unit uses the validation dataset to evaluate the performance of the model;

[0151] By adjusting the model's hyperparameters, including learning rate, batch size, and number of hidden layers, the model's performance is optimized;

[0152] After the training is completed, it will be deployed to the production environment for real-time coal-in-furnace execution command error information generation.

[0153] Specifically, the intelligent coal mining and processing system provided by the present invention also includes:

[0154] The execution command optimization unit collects real-time data from the data acquisition unit, the equipment execution monitoring unit and the dynamic simulation deduction unit. The collected real-time data includes equipment operation status, sensor readings, execution task commands and equipment command execution deduction error data;

[0155] The collected real-time data is used as input, and the trained error analysis model is used to process the input data. Based on the learned patterns and relationships, the error that will be generated by the current execution command is predicted to obtain the prediction result, which is the real-time error information of the execution command of the coal entering the furnace.

[0156] According to the predicted error type and size, the execution command optimization unit adjusts the parameters of the original command to reduce or eliminate the predicted error.

[0157] Second, see Figure 1 The present invention provides a method for controlling the intelligent collection and processing of coal entering a furnace, which is applied to the intelligent collection and processing system of coal entering a furnace, and comprises:

[0158] S101, the server side obtains the equipment operation data of the equipment side and the sensor monitoring data of the data acquisition terminal, the equipment side operation data includes the operation data of the belt coal flow sampling device, the sample preparation equipment operation data, and the coal quality testing equipment operation data, and the sensor monitoring data includes the temperature sensor data, the pressure sensor data, and the flow sensor data;

[0159] S102, the server receives the task execution command from the background control end, generates the task execution monitoring position point according to the task execution command, establishes the monitoring inspection path according to the task execution detection position point, sends the monitoring inspection path to the intelligent inspection robot and the inspection drone, and the intelligent inspection robot and the inspection drone perform inspection based on the monitoring inspection path to obtain real-time inspection information;

[0160] S103, the server side pre-processes the execution task command of the background control terminal and inserts it into the preset digital twin model to obtain the first device execution deduction data, substitutes the real-time inspection information into the preset digital twin model to obtain the second device execution deduction data, compares and analyzes the first device execution deduction data with the second device execution deduction data to obtain device command execution deduction error data, selects the device command execution deduction error data with the lowest error value from the device command execution deduction error data, uses the task command corresponding to the device command execution deduction error data with the lowest error value as the real-time task command, sends the real-time task command to the device side, and the device side executes the real-time task command;

[0161] S104, the server side parses the device command execution error data to obtain parsed device execution error data, matches the parsed device error data with the device on the device side to obtain classified error data, extracts data features from the classified error data and performs cluster analysis to obtain error analysis results;

[0162] S105, the server side trains the deep algorithm model based on the data in the error analysis results and the data generated by the equipment execution monitoring unit, the dynamic simulation and deduction unit, and the data acquisition unit to obtain a trained error analysis model, generates real-time error information of the coal entering the furnace execution command through the trained error analysis model, uses the error information of the coal entering the furnace execution command to correct the real-time task command, obtains the corrected real-time task command, and sends the corrected real-time task command to the equipment side.

[0163] The present invention solves the problem that if a device fails or a data collection error occurs and is not discovered and processed in time, the continuous operation of the intelligent system will be affected through the following technical solutions:

[0164] Real-time data collection and monitoring: The present invention collects the operation data and sensor monitoring data of the equipment end (belt coal flow sampling device, sample preparation equipment, coal quality testing equipment) in real time through the data collection terminal (including temperature sensor, pressure sensor, flow sensor, RFID reader / writer, laser scanner, intelligent inspection robot and inspection drone). These real-time data help to timely discover equipment abnormalities or data collection errors.

[0165] Equipment execution monitoring unit: The equipment execution monitoring unit receives the execution task command from the background control end, generates and executes the monitoring inspection path, conducts inspections through intelligent inspection robots and inspection drones, and obtains real-time inspection information. This automated inspection significantly improves the timely detection rate of equipment failures.

[0166] Dynamic simulation and deduction unit: By substituting background control commands and real-time inspection information into the digital twin model for deduction, comparing the errors between the deduced data and the actual situation, and selecting the task commands with the lowest errors as real-time task commands for execution, it helps to discover and correct potential problems in advance.

[0167] Error analysis unit: parses, classifies, extracts features and performs cluster analysis on the equipment command execution error data to generate an error analysis report. The error analysis report provides data support for equipment maintenance and optimization, and helps identify equipment or operating links where errors frequently occur.

[0168] Execution command optimization unit: Based on the error analysis results, the deep algorithm model is used to generate real-time error information of the coal execution command entering the furnace, and the real-time task command is corrected, ensuring that even if data collection errors or equipment failures occur, the system can be adjusted in time to maintain continuous and stable operation.

[0169] Comprehensive communication connection: The server establishes communication connection with data acquisition terminal, equipment terminal, background control terminal and user mobile terminal, ensuring real-time transmission of information and rapid response of commands.

[0170] Through the above technical scheme, the present invention realizes comprehensive monitoring and dynamic optimization of the coal mining and processing process, effectively solves the impact of equipment failure and data collection errors on the continuous operation of the intelligent system, and improves the stability and reliability of the system.

[0171] The specific use of the technical solution of the present invention in the scenario of intelligent coal mining and processing in a thermal power plant is as follows:

[0172] System composition and communication: The system consists of a server, data acquisition terminal, device, background control terminal and user mobile terminal. The server establishes communication connections with the data acquisition terminal, device, background control terminal and user mobile terminal to realize data transmission and processing.

[0173] Data collection and processing: The data collection terminal includes temperature sensors, pressure sensors, flow sensors, RFID readers, laser scanners, intelligent inspection robots and inspection drones, which are used to obtain various data in the coal mining and processing process in real time. The data acquisition unit on the server side receives these data and performs preliminary processing and analysis.

[0174] Equipment execution monitoring and inspection: The backend control end sends the execution task command to the server end. The equipment execution monitoring unit on the server end generates a monitoring inspection path according to the task command and sends it to the intelligent inspection robot and inspection drone, which conduct inspections and obtain real-time inspection information.

[0175] Dynamic simulation and deduction: The server side will execute task commands and real-time inspection information into the preset digital twin model for dynamic simulation and deduction.

[0176] By comparing and analyzing the deduction data executed by the first device and the deduction data executed by the second device, the task command with the lowest error value is screened out as the real-time task command and sent to the device end for execution.

[0177] Error analysis and reporting: The error analysis unit analyzes and classifies the device command execution error data, extracts features and performs cluster analysis. It generates an error analysis report that describes the error distribution, trend analysis and improvement suggestions in detail.

[0178] Execution command optimization: Based on the error analysis results and other relevant data, the deep algorithm model is trained to generate real-time coal execution command error information. The real-time task command is corrected using the error information and the corrected command is sent to the device for execution.

[0179] Real-time control and optimization: The entire system acquires data in real time and dynamically adjusts control commands to ensure the accuracy and efficiency of the coal mining and processing process. Through continuous data analysis and model optimization, the intelligence level and operation efficiency of the system are continuously improved.

[0180] In summary, the technical solution of the present invention realizes comprehensive intelligent monitoring and optimization of the coal mining and processing process of thermal power plants by integrating multiple intelligent devices and algorithm models, which significantly improves production efficiency and data accuracy.

[0181] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations, and the above-described embodiments of the present invention do not constitute a limitation on the scope of protection of the present invention.

Claims

1. An intelligent coal mining and processing system for furnace, characterized in that: include: The server side, the data acquisition terminal, the device side, the background control side and the user mobile terminal establish a communication connection with the data acquisition terminal, the device side, the background control side and the user mobile terminal. The server side processes and analyzes the data transmitted by the data acquisition terminal, the background control side and the user mobile terminal, generates a furnace coal control command and transmits it to the device side. After receiving the furnace coal control command, the device side parses the furnace coal control command to obtain the parsed furnace coal control command, and then transmits the parsed furnace coal control command to the device side. The equipment end includes belt coal flow sampling device, sample preparation equipment, and coal quality testing equipment; Data collection terminals include temperature sensors, pressure sensors, flow sensors, RFID readers, laser scanners, intelligent inspection robots and inspection drones; The server side includes: A data acquisition unit acquires the equipment operation data of the equipment end and the sensor monitoring data of the data acquisition terminal. The equipment end operation data includes the operation data of the belt coal flow sampling device, the operation data of the sample preparation equipment, and the operation data of the coal quality testing equipment. The sensor monitoring data includes the temperature sensor data, the pressure sensor data, and the flow sensor data; The equipment execution monitoring unit receives the execution task command from the background control end, generates the execution task monitoring position point according to the execution task command, establishes the monitoring inspection path according to the execution task detection position point, sends the monitoring inspection path to the intelligent inspection robot and the inspection drone, and the intelligent inspection robot and the inspection drone conduct inspection based on the monitoring inspection path to obtain real-time inspection information; The dynamic simulation deduction unit pre-processes the execution task command of the background control terminal and inserts it into the preset digital twin model to obtain the first device execution deduction data, substitutes the real-time inspection information into the preset digital twin model to obtain the second device execution deduction data, performs data comparison and analysis on the first device execution deduction data and the second device execution deduction data to obtain the device command execution deduction error data, selects the device command execution deduction error data with the lowest error value from the device command execution deduction error data, uses the task command corresponding to the device command execution deduction error data with the lowest error value as the real-time task command, sends the real-time task command to the device end, and the device end executes the real-time task command; The error analysis unit analyzes the device command execution error data to obtain analyzed device execution error data, matches the analyzed device error data with the device at the device end to obtain classified error data, extracts data features from the classified error data and performs cluster analysis to obtain error analysis results; The execution command optimization unit trains the deep algorithm model based on the data in the error analysis results and the data generated by the equipment execution monitoring unit, the dynamic simulation and deduction unit, and the data acquisition unit to obtain a trained error analysis model. The real-time coal entering the furnace execution command error information is generated by the trained error analysis model, and the real-time task command is corrected using the coal entering the furnace execution command error information to obtain a corrected real-time task command. The corrected real-time task command is sent to the equipment end, and the equipment end executes the corrected real-time task command.

2. The intelligent coal mining and processing system according to claim 1 is characterized in that: The data acquisition unit comprises: Acquisition of equipment operation data: The data acquisition unit first establishes a communication connection with the belt coal flow sampling device, sample preparation equipment, and coal quality testing equipment at the equipment end; The data acquisition unit receives the operation data sent by the device end; The operating data of the belt coal flow sampling device include the sampling frequency, the amount of coal sampled and the location of the sampling point; The operation data of sample preparation equipment and coal quality testing equipment include sample preparation time, temperature, pressure and other parameters during sample preparation, and test results data, which include moisture, ash and volatility of coal; Acquisition of monitoring data from sensors at the data acquisition terminal: The data acquisition unit establishes a communication connection with the data acquisition terminal. The data acquisition unit receives the monitoring data sent by the temperature sensor, the pressure sensor and the reader / writer.

3. The intelligent coal mining and processing system according to claim 1 is characterized in that: The equipment execution monitoring unit includes: The device execution monitoring unit receives and parses the execution task command sent by the background control terminal, and the execution task command sent by the background control terminal includes information about the device, area or specific task to be monitored; According to the parsed task command, the equipment execution monitoring unit determines the locations that need to be monitored. The key locations that need to be monitored include equipment components, areas prone to failure, and process flow links that need to be inspected. After the location points to be monitored are determined, the device execution monitoring unit organizes the location points to be monitored into a list, where the list includes the coordinates or identifier of each location point.

4. The intelligent coal mining and processing system according to claim 1, characterized in that: Dynamic simulation and deduction unit, including: The dynamic simulation deduction unit aligns the deduction data executed by the first device with the deduction data executed by the second device in time and space; Interpolate or synchronize the deduction data executed by the first device and the deduction data executed by the second device to obtain processed deduction data executed by the first device and processed deduction data executed by the second device; The dynamic simulation deduction unit calculates the error between the processed first device execution deduction data and the processed second device execution deduction data, and the difference includes position error, speed error and state error.

5. The intelligent coal mining and processing system according to claim 1, characterized in that: Error analysis unit, including: The error analysis unit receives the equipment command execution deduction error data from the dynamic simulation deduction unit, and the equipment command execution deduction error data includes position error, time error, and speed error; The error analysis unit pre-processes the standby command execution deduction error data to detect the integrity of the standby command execution deduction error data; The device command execution deduction error data is classified according to the device, command type and timestamp. For each type of error data, the specific error value, error direction and context information of the error are further analyzed. The context information of the error includes the device status and ambient temperature, and the error direction includes positive error and negative error. Extract features from the parsed error data to reveal the inherent laws and patterns of the error data. The features from the parsed error data include the maximum value, minimum value, average value, standard deviation, and the changing trend of the error over time. The error analysis unit outputs analyzed device execution error data.

6. The intelligent coal mining and processing system according to claim 5, characterized in that: The error analysis unit further comprises: Each device on the device side has an identification, which includes a device ID, a device name, and a device number; The error analysis unit obtains a device list at the device end, including identification information of the device and attributes of the device; The error analysis unit matches the device information in the parsed device error data with the device identification in the device list, and the matching result is obtained by comparing the device ID, name or identification; When the equipment and the error data are successfully matched, the error analysis unit will classify the error data according to the type or function of the equipment to obtain a classification result. The classification result includes that the error data of the belt coal flow sampling device is classified as a sampling error, and the error data of the sample preparation equipment is classified as a sample preparation error.

7. The intelligent coal mining and processing system according to claim 6, characterized in that: The error analysis unit further comprises: Equipment execution error data includes error size, frequency, duration, and change trend; After clustering is completed, the error analysis unit interprets and analyzes each cluster, including identifying the main characteristics of each cluster, the error type, the error cause, and the corresponding equipment or operating conditions; The error analysis unit integrates the clustering results into an error analysis report, which includes a detailed description of each cluster, error distribution, trend analysis, and suggestions for error improvement.

8. The intelligent coal mining and processing system according to claim 1, characterized in that: Execute command optimization unit, including: The execution command optimization unit obtains the error analysis result data from the error analysis unit, and also collects the real-time inspection information provided by the equipment execution monitoring unit, the equipment command execution deduction error data of the dynamic simulation deduction unit, and the equipment operation data and sensor monitoring data of the data acquisition unit; The data acquired and collected by the execution command optimization unit are integrated into the data set and preprocessed. The execution command optimization unit extracts features from the integrated data. The extracted features include the type of command, execution time, device status, and environmental parameters when the device executes the command; Use the integrated and preprocessed dataset and extracted features to train the deep algorithm model; During the training process, the deep algorithm model tries to minimize the difference between the predicted error and the actual error, and adjusts its internal parameters through the back-propagation algorithm; During the training process, the execution command optimization unit uses the validation dataset to evaluate the performance of the model; By adjusting the model's hyperparameters, including learning rate, batch size, and number of hidden layers, the model's performance is optimized; After the training is completed, it will be deployed to the production environment for real-time coal-in-furnace execution command error information generation.

9. The intelligent coal mining and processing system according to claim 8, characterized in that: Also includes: The execution command optimization unit collects real-time data from the data acquisition unit, the equipment execution monitoring unit and the dynamic simulation deduction unit. The collected real-time data includes equipment operation status, sensor readings, execution task commands and equipment command execution deduction error data; The collected real-time data is used as input, and the trained error analysis model is used to process the input data. Based on the learned patterns and relationships, the error that will be generated by the current execution command is predicted to obtain the prediction result, which is the real-time error information of the execution command of the coal entering the furnace. According to the predicted error type and size, the execution command optimization unit adjusts the parameters of the original command to reduce or eliminate the predicted error.

10. A method for controlling the intelligent collection and processing of incoming coal, applied to the intelligent collection and processing system of incoming coal as claimed in any one of claims 1 to 9, characterized in that: include: S101, the server side obtains the equipment operation data of the equipment side and the sensor monitoring data of the data acquisition terminal, the equipment side operation data includes the operation data of the belt coal flow sampling device, the sample preparation equipment operation data, and the coal quality testing equipment operation data, and the sensor monitoring data includes the temperature sensor data, the pressure sensor data, and the flow sensor data; S102, the server receives the task execution command from the background control end, generates the task execution monitoring position point according to the task execution command, establishes the monitoring inspection path according to the task execution detection position point, sends the monitoring inspection path to the intelligent inspection robot and the inspection drone, and the intelligent inspection robot and the inspection drone perform inspection based on the monitoring inspection path to obtain real-time inspection information; S103, the server side pre-processes the execution task command of the background control terminal and inserts it into the preset digital twin model to obtain the first device execution deduction data, substitutes the real-time inspection information into the preset digital twin model to obtain the second device execution deduction data, compares and analyzes the first device execution deduction data with the second device execution deduction data to obtain device command execution deduction error data, selects the device command execution deduction error data with the lowest error value from the device command execution deduction error data, uses the task command corresponding to the device command execution deduction error data with the lowest error value as the real-time task command, sends the real-time task command to the device side, and the device side executes the real-time task command; S104, the server side parses the device command execution error data to obtain parsed device execution error data, matches the parsed device error data with the device on the device side to obtain classified error data, extracts data features from the classified error data and performs cluster analysis to obtain error analysis results; S105, the server side trains the deep algorithm model based on the data in the error analysis results and the data generated by the equipment execution monitoring unit, the dynamic simulation and deduction unit, and the data acquisition unit to obtain a trained error analysis model, generates real-time error information of the coal entering the furnace execution command through the trained error analysis model, uses the error information of the coal entering the furnace execution command to correct the real-time task command, obtains the corrected real-time task command, and sends the corrected real-time task command to the equipment side.

Images