Thermal power generation intelligent safety information prediction supervision system
The intelligent safety information prediction and monitoring system for thermal power generation has solved the problems of real-time adjustment of equipment monitoring systems and adaptation to power demand, and has realized intelligent control and stable operation of equipment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-29
- Publication Date
- 2026-03-27
AI Technical Summary
The existing thermal power equipment monitoring system lacks the ability to control and adjust equipment in a timely manner, which makes the equipment prone to damage and unable to make real-time adjustments according to changes in electricity demand, resulting in a lag in power generation.
An intelligent safety information prediction and monitoring system for thermal power generation was designed, comprising a data collection layer, a judgment and processing layer, a modeling and simulation layer, and an execution layer. The system collects data through sensors, combines digital twin simulation and database analysis to generate emergency and improvement solutions, and realizes intelligent control of equipment and real-time adjustment of power demand through the execution layer.
It enables real-time status monitoring and early warning of equipment, shortens problem handling time, improves the stability of equipment operation and adaptability to power demand, and reduces equipment damage and maintenance difficulty.
Smart Images
Figure CN121744111A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of power generation management, and in particular to an intelligent safety information prediction and supervision system for thermal power generation. BACKGROUND
[0002] With the development of artificial intelligence and digital technology, more and more enterprises begin to introduce related systems to assist in factory equipment operation and management, further ensuring normal equipment supervision and improving overall operation efficiency. However, the existing related supervision systems applied in the field of thermal power generation can only supervise the abnormal conditions of the equipment, lack the ability to control and adjust the equipment in the first time, and thus the equipment is easily damaged, which brings difficulties to subsequent maintenance and adjustment. At the same time, the existing equipment cannot be adjusted in real time according to the change of power demand, and the personnel need to be controlled according to the peak-valley power demand, which lacks intelligent control and cannot be timely regulated and controlled, and there is a certain power generation lag, so it cannot meet the existing actual use requirements.
[0003] Therefore, an intelligent safety information prediction and supervision system for thermal power generation is proposed. SUMMARY
[0004] Therefore, the technical problem to be solved by the present application is that the existing system can only supervise the abnormal conditions of thermal power equipment, lacks the ability to control and adjust the equipment in the first time, and is easy to cause equipment damage, increasing the difficulty of subsequent maintenance and adjustment.
[0005] The above technical problem is solved by the following technical scheme: the present application proposes an intelligent safety information prediction and supervision system for thermal power generation, which comprises a data collection layer, a judgment processing layer, a modeling simulation layer and an execution layer. The data collection layer comprises a plurality of sensors and a data collection module, the sensors are deployed at key positions of the thermal power equipment to collect equipment operation data, the data collection module receives the change data of the equipment, and the data collection layer packages the data and transmits it to the judgment processing layer. The judgment processing layer compares the received data with the preset normal standard threshold, maintains the equipment operation if the data is normal, extracts abnormal feature data and transmits it to the modeling simulation layer if the data is abnormal. The modeling simulation layer comprises a digital twin simulation module and a database, and performs data simulation based on the abnormal feature data and the database storage information, generates an emergency treatment scheme and an improved treatment scheme, and transmits the emergency treatment scheme to the judgment processing layer for equipment emergency control. The execution layer receives the improved treatment scheme and transmits it to the administrator terminal, and adjusts the equipment based on the scheme after manual review.
[0006] In a preferred embodiment of the intelligent safety information prediction and supervision system for thermal power generation, the data collection layer further comprises a power grid electricity consumption feedback module. The power grid electricity consumption feedback module records power grid electricity consumption trend change data, judges the power grid peak and valley electricity consumption state in combination with historical equipment debugging information, and uploads relevant data to the data collection module. The judgment processing layer adjusts the equipment power based on the peak and valley electricity consumption state to adapt to the power grid electricity demand in combination with the current equipment running state.
[0007] In a preferred embodiment of the intelligent safety information prediction and supervision system for thermal power generation, the normal standard threshold of the judgment processing layer is initially set by manual setting, and is dynamically adjusted based on the equipment normal running data obtained by the modeling simulation layer. The judgment processing layer performs real-time threshold comparison on the equipment running data transmitted by the data collection layer, and sends warning information to the administrator terminal when the data exceeds the safety threshold.
[0008] In a preferred embodiment of the intelligent safety information prediction and supervision system for thermal power generation, the judgment processing layer further comprises a data feature processing module. The data feature processing module processes the equipment running data through preset data filtering, data cleaning and data noise reduction algorithms, and retains the core feature data in the data.
[0009] In a preferred embodiment of the intelligent safety information prediction and supervision system for thermal power generation, the modeling simulation layer further comprises a data fusion perception unit. The data fusion perception unit comprises a prediction subunit and an update subunit, which perform real-time prediction and dynamic adjustment on the state changes that may occur to the equipment based on abnormal feature data through preset prediction algorithms and update algorithms.
[0010] In a preferred embodiment of the intelligent safety information prediction and supervision system for thermal power generation, the modeling simulation layer further comprises a modeling simulation unit. The modeling simulation unit simulates the material, temperature and displacement related data of the equipment under different scenarios through partial differential equations, and learns and processes in combination with abnormal feature information.
[0011] In a preferred embodiment of the intelligent safety information prediction and supervision system for thermal power generation, the execution layer verifies the simulation results output by the modeling simulation layer, and confirms the feasibility of the emergency treatment scheme and the improved treatment scheme. The execution layer uploads the verified improved treatment scheme to the administrator terminal, and after manual confirmation and execution, it summarizes the scheme and stores it in the database, and after audit, it debugs the equipment based on the scheme.
[0012] In a preferred embodiment of the intelligent safety information prediction and supervision system for thermal power generation, the administrator terminal can obtain and display the equipment operation data collected by the sensors in the data collection layer in real time, and support manual access to the historical operation data, real-time operation data and corresponding processing schemes of the equipment, thereby realizing manual supervision of the equipment operation state.
[0013] In a preferred embodiment of the intelligent safety information prediction and supervision system for thermal power generation, the abnormal equipment processing schemes are pre-recorded in the database of the modeling simulation layer. The digital twin simulation module calls the abnormal processing schemes in the database to perform simulation experiments and model training, thereby optimizing the generation efficiency and accuracy of the emergency processing schemes and improved processing schemes.
[0014] In a preferred embodiment of the intelligent safety information prediction and supervision system for thermal power generation, after the sensors are installed, the data collection layer records the installation position information of each sensor. The data collection layer is connected with the information transmission interface of the thermal power generation equipment through an adaptive data interaction mode, thereby realizing data interaction with multiple types of power generation equipment.
[0015] The present application has the following advantages: by setting the data collection layer, the data information of the thermal power generation facility and the power grid power demand can be fully obtained, real-time data state supervision and control are facilitated, by setting the judgment processing layer, the working state of the power generation device can be assisted to be judged, the normal and stable operation of the equipment is ensured, abnormal states can be analyzed and judged for early warning, the overall feedback efficiency is improved, by setting the modeling simulation layer, the equipment operation state in a period of time can be predicted and early warning can be performed in advance, and when an abnormal state is received, different solutions can also be simulated, an emergency scheme is obtained and directly executed, thereby greatly shortening the problem processing time, by setting the execution layer, the equipment control can be debugged by manual operation, the stable operation of the power generation facility is fully ensured, and the corresponding solutions for the modeling simulation layer are provided, thereby facilitating simulation calling. BRIEF DESCRIPTION OF DRAWINGS
[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below only relate to some embodiments of the present application, but not limit the present application.
[0017] Figure 1 The overall structure schematic diagram of the intelligent safety information prediction and supervision system for thermal power generation is shown. DETAILED DESCRIPTION
[0018] For a better understanding of the present application, the present application will be described in further detail below in connection with the specific embodiments and the accompanying drawings.
[0019] The terms used in the present application are those general terms currently widely used in the art in consideration of the functions of the present application, but the terms can vary according to the intention of those of ordinary skill in the art, precedents, or new technology in the art. Also, specific terms can be selected by the applicant, and in this case, the detailed meaning thereof will be described in the detailed description of the present application. Therefore, the terms used in the specification should be understood not simply as the names of the terms but based on the meaning of the terms and the overall description of the present application.
[0020] Referring to Figure 1 The present embodiment provides a thermal power generation intelligent safety information prediction monitoring system, which comprises a data collection layer, a judgment processing layer, a modeling simulation layer, and an execution layer. The data collection layer comprises a plurality of sensors and a data collection module. The sensors are deployed at key positions of the thermal power generation equipment to collect equipment operation data. The sensors can be erected at the corresponding key positions to identify the power, heat, pressure, main shaft vibration, and actual power generation data during the operation of the device, respectively.
[0021] The data collection module receives the change data of the equipment. After the data collection layer sorts and packages the data, the data is transmitted to the judgment processing layer. The judgment processing layer compares the received data with the preset normal standard threshold value. If the data is normal, the equipment is maintained in operation. If the data is abnormal, the abnormal feature data is extracted and transmitted to the modeling simulation layer. The modeling simulation layer comprises a digital twin simulation module and a database. Based on the abnormal feature data and the database storage information, data simulation is performed to generate an emergency treatment scheme and an improved treatment scheme. The emergency treatment scheme is delivered to the judgment processing layer to realize emergency control of the equipment. The execution layer receives the improved treatment scheme and transmits it to the administrator terminal. After manual review and adjustment based on the scheme, the equipment is debugged.
[0022] The administrator terminal can obtain and display the equipment operation data collected by the sensors in the data collection layer in real time, and support manual review of the historical operation data, real-time operation data, and corresponding treatment scheme of the equipment, to realize manual supervision of the equipment operation state.
[0023] The data collection layer further comprises a power grid power consumption feedback module. The power grid power consumption feedback module records the power grid power consumption trend change data. The power grid power consumption feedback records the power consumption trend change data within a time period, judges the power grid peak and valley power consumption state in combination with historical equipment debugging information, and uploads the related data to the data collection module. The judgment processing layer adjusts the power of the equipment based on the peak-valley power consumption state to adapt to the power grid power demand in combination with the current running state of the equipment.
[0024] The judgment processing layer gradually increases or reduces the power of the equipment based on the current state of the power generation equipment to meet the power demand at peak and valley times. The power demand at peak and valley times significantly increases and decreases. The judgment processing layer adjusts the power generation and increases the operating power of the power generation facility according to the time node, regional location, and other measures to meet the corresponding power demand.
[0025] When the power consumption is in the valley or some facilities need to be maintained, the corresponding control program is started to free up the corresponding equipment while meeting the normal power demand.
[0026] The normal standard threshold of the judgment processing layer is initially set by manual setting and dynamically adjusted based on a large amount of normal operating range data obtained by the modeling simulation layer. The judgment processing layer performs real-time threshold comparison on the equipment operating data transmitted by the data collection layer and sends warning information to the administrator terminal when the data exceeds the safety threshold.
[0027] The judgment processing layer also includes a data feature processing module. The data feature processing module processes the equipment operating data through preset data filtering, data cleaning, and data noise reduction algorithms to retain the core feature data in the data.
[0028] The algorithm used for data filtering is the moving average method, and its formula is: wherein, is the time point is the output value after filtering, is the time point is the original input value at the time point N is the size of the moving window. The algorithm used for cleaning and noise reduction processing is Isolation Forest, and its formula is: wherein is the anomaly score of the data point is the average path length of the data point in all isolation trees, is the standardized path length reference value.
[0029] The modeling simulation layer also includes a data fusion perception unit. The data fusion perception unit includes a prediction subunit and an update subunit, which perform real-time prediction and dynamic adjustment of the state changes that can occur to the equipment based on abnormal feature data through preset prediction algorithms and update algorithms.
[0030] The prediction related algorithm is: wherein, is the state estimation vector based on the data at is the predicted value of the current state of the system, is the state transition matrix at describes how the state of the system evolves from to is the optimal state estimation vector at is the control input matrix at is the control input vector at is the state estimation covariance matrix based on the data at indicates the uncertainty of the state prediction value, is the state transition matrix at is the optimal state estimation covariance matrix at is the transpose matrix of is the process noise covariance matrix at
[0031] The update related algorithm is: wherein, is the Kalman gain at indicates the contribution weight of the observation value to the state estimation, is the state prediction covariance matrix based on the data at is used to describe the uncertainty of the predicted state, is the observation matrix at is the observation matrix at is the transpose matrix of is the observation noise covariance matrix at
[0032] is the optimal equipment state estimation vector at the time of observation correction, is the equipment state prediction vector at the time of observation correction, is the actual observation value at the time of observation correction, is the observation residual, which is used to reflect the deviation between the prediction and the actual value.
[0033] is the corrected state estimation covariance matrix at the time of observation correction, which is used to describe the uncertainty of the optimal equipment state estimation, represents the unit matrix. As an improvement, the modeling simulation simulates the data content including materials, temperature, displacement under different conditions through strong form PDE, and learns and processes the characteristic information, and the related algorithm includes:
[0034] wherein, is the transport coefficient, which represents the material attribute, is the field variable to be solved, is the source term or load, is the solution region; is the test function, and the boundary term is the physical condition used to describe the boundary of the region; is the system stiffness matrix, is the load vector; The modeling simulation unit of the modeling simulation layer further includes a modeling simulation unit; The modeling simulation unit simulates the material, temperature and displacement related data of the equipment under different scenarios through partial differential equation, and learns and processes the abnormal characteristic information.
[0035] The execution layer verifies the simulation results output by the modeling simulation layer, and confirms the feasibility of the emergency treatment scheme and the improved treatment scheme; The execution layer uploads the improved treatment scheme after verification to the administrator terminal, confirms the execution after manual confirmation, and stores the scheme into the database after execution, confirms the execution, and stores the scheme into the database after execution, and at the same time, the scheme is audited, and the equipment is debugged based on the scheme after the audit is passed.
[0036] The equipment abnormal treatment scheme is pre-recorded in the database of the modeling simulation layer; The digital twin simulation module calls the abnormal handling scheme in the database for simulation experiment and model training, thereby optimizing the generation efficiency and accuracy of the emergency handling scheme and the improved handling scheme.
[0037] After the sensors are installed, the data collection layer records the installation position information of each sensor; The data collection layer is connected with the information transmission interface of the thermal power generation equipment through an adaptive data interaction mode, so as to realize data interaction with various power generation equipment.
[0038] In use, the data sensor needs to record the corresponding installation position information after installation, and the information transmission interface of the power generation equipment can also be connected with the data collection layer through a line for connection and interaction, so as to facilitate data connection of various equipment. After the corresponding data information is obtained by the judgment processing layer, data comparison is performed. If the content is within the normal threshold range, the operation is maintained. If abnormal data is generated, the data is feature extracted and uploaded to the modeling simulation layer. At this time, the digital twin simulation receives the corresponding abnormal data, synchronously retrieves the historical data in the database for rapid judgment and scheme summary, and then performs corresponding verification summary. At this time, the judgment processing layer will preferentially receive the corresponding emergency handling scheme, quickly adjust the operation state of the corresponding equipment to emergency takeover, avoid further disaster or expansion, and at the same time, the improved scheme is uploaded to the execution layer. The execution layer will combine artificial judgment to confirm and summarize, and after being audited, the corresponding equipment debugging operation will be executed to stabilize the equipment operation.
[0039] Finally, it should be pointed out that the above detailed description of the method and device is only an embodiment, and those skilled in the art can modify the embodiment in different ways without departing from the scope of the present application.
Claims
1. An intelligent safety information prediction and monitoring system for thermal power generation, characterized in that: It includes a data collection layer, a decision processing layer, a modeling and simulation layer, and an execution layer; The data collection layer includes multiple sets of sensors and data collection modules. The sensors are deployed at key locations of the thermal power generation equipment to collect equipment operation data. The data collection modules receive the equipment change data. The data collection layer organizes and packages the data and then transmits it to the judgment and processing layer. The judgment and processing layer compares the received data with a preset normal standard threshold. If the data is normal, the device continues to operate. If the data is abnormal, the abnormal feature data is extracted and transmitted to the modeling and simulation layer. The modeling and simulation layer includes a digital twin simulation module and a database. It performs data simulation based on abnormal feature data and database storage information to generate emergency handling plans and improved handling plans. The emergency handling plans are sent to the judgment and processing layer to realize emergency control of the equipment. The execution layer receives the improved processing scheme and transmits it to the administrator terminal. After manual review and adjustment, the device is debugged based on the scheme.
2. The intelligent safety information prediction and monitoring system for thermal power generation according to claim 1, characterized in that: The data collection layer also includes a power grid power consumption feedback module; The power grid power consumption feedback module records power grid power consumption trend change data, combines historical equipment debugging information to determine the peak and valley power consumption status of the power grid, and uploads the relevant data to the data collection module; The judgment and processing layer combines the current operating status of the equipment and adjusts the equipment power based on peak and valley electricity consumption to adapt to the power grid demand.
3. The intelligent safety information prediction and monitoring system for thermal power generation according to claim 2, characterized in that: The normal standard threshold of the judgment and processing layer is initially set manually and dynamically adjusted based on the normal operation data of the equipment obtained by the modeling and simulation layer. The judgment and processing layer performs real-time threshold comparison on the device operation data transmitted by the data collection layer, and sends a warning message to the administrator terminal when the data exceeds the safety threshold.
4. The intelligent safety information prediction and monitoring system for thermal power generation according to claim 3, characterized in that: The judgment processing layer also includes a data feature processing module; The data feature processing module processes the equipment operation data through preset data filtering, data cleaning, and data noise reduction algorithms, retaining the core feature data in the data.
5. The intelligent safety information prediction and monitoring system for thermal power generation according to claim 4, characterized in that: The modeling and simulation layer also includes a data fusion and perception unit; The data fusion sensing unit includes a prediction subunit and an update subunit. Through preset prediction and update algorithms, it performs real-time prediction and dynamic adjustment of possible state changes of the device based on abnormal feature data.
6. The intelligent safety information prediction and monitoring system for thermal power generation according to claim 5, characterized in that: The modeling and simulation layer also includes a modeling and simulation unit; The modeling and simulation unit simulates the material, temperature, and displacement-related data of the equipment under different scenarios using partial differential equations, and learns and processes the data in conjunction with abnormal feature information.
7. The intelligent safety information prediction and monitoring system for thermal power generation according to claim 6, characterized in that: The execution layer verifies the simulation results output by the modeling and simulation layer to confirm the feasibility of the emergency response plan and the improved response plan. The execution layer uploads the verified improved processing solution to the administrator terminal. After manual confirmation and execution, the solution is summarized and stored in the database. After approval, the equipment is debugged based on the solution.
8. The intelligent safety information prediction and monitoring system for thermal power generation according to claim 7, characterized in that: The administrator terminal can acquire and display the device operation data collected by the sensors in the data collection layer in real time, and supports manual access to the device's historical operation data, real-time operation data and corresponding processing solutions, so as to realize manual supervision of the device's operation status.
9. The intelligent safety information prediction and monitoring system for thermal power generation according to claim 8, characterized in that: The database of the modeling and simulation layer contains pre-entered equipment anomaly handling schemes; The digital twin simulation module calls the anomaly handling schemes in the database to conduct simulation experiments and model training, thereby optimizing the generation efficiency and accuracy of emergency handling schemes and improved handling schemes.
10. The intelligent safety information prediction and monitoring system for thermal power generation according to claim 9, characterized in that: After the sensors are installed, the data collection layer records the installation location information of each sensor; The data collection layer connects to the information transmission interface of thermal power generation equipment through an adapted data interaction method, enabling data interaction with various types of power generation equipment.