System and method for monitoring the condition of boiler water-cooled walls in power plants and for early fault warning.

Abstract

The power plant boiler water-cooled wall condition monitoring and early fault warning system includes a field data collection system, a host system, and a network communication system. The field data collection system includes various measuring devices and data acquisition devices placed on the boiler water-cooled wall. The data acquisition devices are connected to the host system via the network communication system. The host system includes a computer simulation system and an early fault warning system. The computer simulation system acquires a digital twin model including the temperature field distribution and stress field distribution of the entire boiler water-cooled wall. The early fault warning system performs safety assessments and predictive warnings based on field measurement point data and computational simulation data, providing online assessments and intelligent early fault warnings for the safety of the boiler water-cooled wall, thereby significantly improving the accuracy of early warnings.

Description

TECHNICAL FIELD

[0001] The present invention belongs to the field of condition monitoring and safety assessment of power plant equipment in operation, and relates to a system and method for condition monitoring and early fault warning of boiler water walls in power plants.

BACKGROUND ART

[0002] In recent years, with the need for the construction of new-type power systems, the role of thermal power generating units in power supply has also changed. In accordance with national policies, thermal power generating units are recommended to undergo flexible retrofitting and participate in deep peak shaving. However, frequent start-up and shutdown of units, long-term low-load operation, and rapid load increase and decrease caused by deep peak shaving have a significant impact on the safe operation of critical equipment of the units, especially boiler water walls. As a result, accidents such as tube rupture, cracking and deformation of boiler water walls have occurred frequently in recent years, posing a serious threat to the safety of operating personnel. At present, countermeasures for boiler water wall accidents mainly focus on strengthening patrol inspections by on-site personnel, enhancing metal monitoring, repair and maintenance during outages, but due to the lack of online monitoring of the health status of boiler water walls, it is impossible to discover existing safety risks in advance, and perform assessment and real-time intelligent early warning. In view of this, it is extremely necessary to develop a system for condition monitoring and early fault warning of boiler water walls in power plants, which measures the basic operating state data of boiler water walls and is implemented based on data-physics fusion.

SUMMARY OF THE INVENTION

PROBLEMS TO BE SOLVED BY THE INVENTION

[0003] The objective of the present invention is to overcome the above drawbacks of the prior art, and to provide a system and method for condition monitoring and early fault warning of boiler water walls in power plants driven by data-physics fusion. By using this system and method, the condition of boiler water walls in power plants where deep peak shaving is implemented can be monitored in real time, and online safety assessment and intelligent early fault warning can be performed on their safety. [Means for solving the problem]

[0004] The power plant boiler water cooling wall condition monitoring and early fault warning system, including the field collection system, the higher-level system, and the network communication system, The field data collection system includes various measuring and data acquisition devices positioned on the boiler water-cooled wall. Various measuring devices include several temperature measuring devices (21, 22~2n), several strain measuring devices (31, 32~3n), several displacement measuring devices (41, 42~4n), and several vibration measuring devices (51, 52~5n). The data acquisition device is connected to a higher-level system via a network communication system. The higher-end system is characterized by including a computer simulation system and an early fault warning system.

[0005] The computer simulation system (9) is used to obtain a digital twin model including the temperature and stress field distributions of the entire boiler water-cooled wall by constructing a physical model of the boiler water-cooled wall based on the original input data, performing simulation calculations of the temperature and stress fields to obtain the initial temperature and stress field distributions, and fusing them with collected data such as temperature, displacement, vibration, and stress using a transfer learning model. The fault early warning system is used to issue warnings for exceeding limit values ​​based on on-site measurement point data and real-time calculation simulation data. Furthermore, it can also perform safety assessments and issue predictive warnings based on on-site measurement point data and real-time calculation simulation data.

[0006] The method for monitoring the condition of the boiler water cooling wall at a power plant and for early fault detection is as follows: Step 1 involves inputting the original design parameters of the boiler water-cooled wall (1) into a computer simulation system (9) in order to construct a finite element stress calculation model for the boiler water-cooled wall (1) in Step 3. The temperature-sensitive region, deformation-sensitive region, and vibration-sensitive region of the boiler water-cooled wall were analyzed and determined. Step 2 involves placing several temperature measuring devices (21, 22~2n) in the boiler water-cooled wall (1) including the temperature-sensitive region, placing several displacement measuring devices (41, 42~4n) in the boiler water-cooled wall (1) including the deformation-sensitive region, and placing several vibration measuring devices (51, 52~5n) in the boiler water-cooled wall (1) including the vibration-sensitive region, according to the established rules. Step 3 involves obtaining a digital twin model that includes the temperature field distribution and stress field distribution of the entire boiler water-cooled wall, based on finite element calculations and transfer learning models. The system is characterized by including step 4, which provides a limit value exceedance warning and a predictive warning based on on-site measurement point data and calculation simulation data. [Effects of the Invention]

[0007] The beneficial effects of the present invention are as follows: Compared to conventional technologies, the present invention designs a data-physics-integrated system and method for monitoring the condition of a boiler water-cooled wall in a power plant and providing early fault warnings. Based on finite element calculations and transfer learning models, it acquires a digital twin model including the temperature field distribution and stress field distribution of the entire boiler water-cooled wall. Furthermore, based on field measurement point data and digital twin model simulation data, it performs limit value exceedance warnings and safety evaluations and predictions. It also performs online safety evaluations and intelligent early fault warnings for the safety of the boiler water-cooled wall, thereby significantly improving the accuracy of early warnings. [Brief explanation of the drawing]

[0008] [Figure 1] This is a schematic diagram of the structure of the present invention. [Figure 2] This is a schematic diagram of the water-cooled wall in the AA direction. [Figure 3] This is a step diagram of the method of the present invention. [Figure 4] This is a flowchart of the process for the present invention. [Modes for carrying out the invention]

[0009] The technical solutions in embodiments of the present invention will be described clearly and completely below with reference to the drawings of embodiments of the present invention, but obviously the embodiments described are only a part of the embodiments of the present invention, not all embodiments. All other embodiments obtained based on embodiments of the present invention without the creative effort of a person skilled in the art are within the scope of protection of this application.

[0010] As shown in Figure 1, the power plant boiler water-cooled wall condition monitoring and early fault warning system includes a field data collection system, a higher-level system, and a network communication system.

[0011] The field data collection system includes various measuring and data acquisition devices positioned on the boiler water-cooled wall.

[0012] The boiler water-cooled wall (1) to be monitored is composed of water-cooled wall tubes (11) and fins (12). Various measuring devices include several temperature measuring devices (21, 22~2n), several strain measuring devices (31, 32~3n), several displacement measuring devices (41, 42~4n), and several vibration measuring devices (51, 52~5n). Several data acquisition devices (61, 62-6n) may be connected to various measuring devices via data lines.

[0013] To facilitate signal detection across the entire structural surface of the water-cooled wall, several data acquisition devices (61, 62-6n) can be distributed, and each data acquisition device may be connected via a data line to one or more of the following: temperature measuring devices, strain measuring devices, displacement measuring devices, and vibration measuring devices. Specifically, the entire structural surface of the water-cooled wall is first divided into multiple array monitoring areas, and one data acquisition device is provided corresponding to each monitoring area. Depending on the arrangement of the measurement points, one or more of the following may be connected to temperature measuring devices, strain measuring devices, displacement measuring devices, and vibration measuring devices, and the connected measuring devices can collect temperature data, strain data, displacement data, and vibration data in the corresponding monitoring area in real time. The data acquired by each data acquisition device is transmitted to a network communication system via a network, where either a wired or wireless network communication system may be used. A switch is provided in the network communication system.

[0014] When using a wired network, some data acquisition devices can be connected to a field bus and exchange data with switches connected to the field bus. When using a wireless network, some data acquisition devices can be connected to a ZigBee or WIFI network and communicate with switches via the wireless network.

[0015] The switch is then connected to a higher-level system.

[0016] It also includes a power supply system capable of supplying power to the field data collection system, the higher-level system, and the network communication system.

[0017] When deploying the system, Several temperature measuring devices (21, 22~2n), several strain measuring devices (31, 32~3n), several displacement measuring devices (41, 42~4n), and several vibration measuring devices (51, 52~5n) are all connected to the water-cooled wall tube (11) or fin (12) being monitored by a direct fixing method or a positioning device. Several temperature measuring devices (21, 22 to 2n) are arranged in the temperature-sensitive region of the water-cooled wall tubes (11) or fins (12) of the boiler water-cooled wall tubes (1), Several strain measuring devices (31, 32 to 3n) are arranged in the stress-failure-sensitive region of the water-cooled wall tubes (11) or fins (12) of the boiler water-cooled wall tubes (1), Several displacement measuring devices (41, 42 to 4n) are arranged in the deformation-sensitive region of the water-cooled wall tubes (11) or fins (12) of the boiler water-cooled wall tubes (1), Several vibration measuring devices (51, 52 to 5n) are arranged in the vibration-sensitive region of the water-cooled wall tubes (11) or fins (12) of the boiler water-cooled wall tubes (1), The temperature measuring devices (21, 22 to 2n), strain measuring devices (31, 32 to 3n), displacement measuring devices (41, 42 to 4n), and vibration measuring devices (51, 52 to 5n) are all arranged on the monitored water-cooled wall tubes (11) or fins (12) according to set rules, the other ends thereof are connected to several distributed data acquisition devices (61, 62 to 6n) via data lines according to set rules, and then connected to the host system via a switch system (7), The host system includes a control operating system, a computer simulation system, and an early fault warning system.

[0018] The control operating system (8) is used to provide functions such as human-computer interaction, data acquisition, data storage, statistical analysis, and system setting.

[0019] The computer simulation system (9) is used to construct a physical model of the boiler water-cooled wall based on original input data, perform simulation calculation of the temperature field and stress field to obtain initial temperature field distribution and stress field distribution, and use a transfer learning model to fuse them with collected data such as temperature, displacement, vibration and stress, so as to obtain a digital twin model including the temperature field distribution and stress field distribution of the entire boiler water-cooled wall, The fault early warning system (10) is used to provide warnings for exceeding limit values ​​based on field measurement point data and real-time calculation simulation data. Furthermore, it can also perform safety assessments and provide predictive warnings based on field measurement point data and real-time calculation simulation data.

[0020] As shown in Figures 1 and 2, in a method for monitoring the condition of a boiler water-cooled wall of a power plant and for early fault warning, the corresponding boiler water-cooled wall digital twin model is calculated first, and the method is as follows: Step 1 involves inputting the original design parameters of the boiler water-cooled wall (1) into a computer simulation system (9) in order to construct a finite element stress calculation model for the boiler water-cooled wall (1) in Step 3. The temperature-sensitive region, deformation-sensitive region, and vibration-sensitive region of the boiler water-cooled wall were analyzed and determined. Step 2 involves placing several temperature measuring devices (21, 22~2n) in the boiler water-cooled wall (1) including the temperature-sensitive region, placing several displacement measuring devices (41, 42~4n) in the boiler water-cooled wall (1) including the deformation-sensitive region, and placing several vibration measuring devices (51, 52~5n) in the boiler water-cooled wall (1) including the vibration-sensitive region, according to the established rules. Step 3 involves obtaining a digital twin model that includes the temperature field distribution and stress field distribution of the entire boiler water-cooled wall, Step 3-1 involves constructing a finite element stress calculation model for the boiler water-cooled wall (1), Step 3-2 involves performing temperature field calculations under the coupled action of multiple fields (combustion field, structural field, and fluid field) based on a finite element stress calculation model of the boiler water-cooled wall (1), obtaining simulated temperature field distribution data, fusing it with real-time temperature measurement data collected by a transfer learning model, and obtaining the real-time temperature field distribution of the boiler water-cooled wall (1) based on digital twin technology. Step 3-3 involves applying the real-time temperature field distribution data of the boiler water-cooled wall (1) obtained in step 3-2 above to the finite element stress calculation model of the boiler water-cooled wall (1), performing a stress field calculation under thermal-structural interaction, and obtaining simulated stress field distribution data. Step 3-4 involves determining the stress fracture susceptibility region based on the collected displacement and vibration measurement data of the deformation-sensitive region and vibration-sensitive region, in combination with the simulation stress field distribution data from step 3-3 above, and then collecting real-time strain data by appropriately positioning several strain measuring devices (31, 32, 3n). Step 3 includes step 3-5, which involves fusing the simulation stress field distribution data from step 3-2 with the collected real-time stress measurement data using a transfer learning model, obtaining the real-time stress field distribution of the entire boiler water-cooled wall (1) based on digital twin technology, and obtaining a digital twin model that includes the real-time temperature field distribution and real-time stress field distribution of the entire boiler water-cooled wall. Step 4 involves performing limit value exceedance warnings and predictive warnings based on on-site measurement point data and calculation simulation data, If the temperature, vibration, and displacement values ​​at each measurement point of the boiler water-cooled wall (1), which are collected in real time, are greater than the set thresholds a, b, and c respectively, the power plant's boiler water-cooled wall condition monitoring and fault early warning system (10) generates a corresponding alarm signal in step 4-1. If the temperature value at any point in the actual temperature field calculated by the computer simulation system (9) exceeds a set temperature threshold d, the power plant boiler water-cooled wall condition monitoring and fault early warning system (10) generates a corresponding alarm signal in step 4-2. The computer simulation system (9) combines calculated real-time stress field distribution data, real-time displacement data collected by displacement measuring devices (41, 42-4n), and real-time vibration data collected by vibration measuring devices (51, 52-5n) to predict and evaluate the safety of the boiler water-cooled wall (1). If it determines that there is a safety risk, the power plant's boiler water-cooled wall condition monitoring and fault early warning system (10) includes step 4-3, which includes generating a corresponding alarm signal.

[0021] Finally, it should be noted that the above description is merely an interpretation of the present invention and is not intended to limit it. Despite the detailed description of the present invention, those skilled in the art can still modify the above technical solutions or replace some of the technical features therein with equivalent ones. Any modifications, equivalent replacements, or improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention. [Explanation of Symbols]

[0022] 1. Boiler water-cooled wall 21,22~2n Temperature measuring device 31, 32~3n Strain Measurement Device 41,42~4n Displacement measuring device 51, 52~5n vibration measuring device 61, 62~6n Data Acquisition Device 7 Switch System 8 Control Operating System 9. Computer Simulation System 10. Early fault warning system 11 Water-cooled wall tubes 12 fins 13 Power System 14 Power line

Claims

1. A power plant boiler water cooling wall condition monitoring and fault early warning system including a field collection system, a higher-level system, and a network communication system, The aforementioned field data collection system includes various measuring devices and data acquisition devices arranged on the boiler water-cooled wall. The various measuring devices include several temperature measuring devices (21, 22-2n), several strain measuring devices (31, 32-3n), several displacement measuring devices (41, 42-4n), and several vibration measuring devices (51, 52-5n). The data acquisition device is connected to the host system via the network communication system. The aforementioned higher-level system includes a computer simulation system and an early fault warning system. The computer simulation system (9) is used to construct a physical model of the boiler water-cooled wall based on the original input data, perform simulation calculations of the temperature field and stress field to obtain the initial temperature field distribution and stress field distribution, and then use a transfer learning model to fuse them with the collected data such as temperature, displacement, vibration, and stress, thereby obtaining a digital twin model that includes the temperature field distribution and stress field distribution of the entire boiler water-cooled wall. The aforementioned early fault warning system is used to provide warnings for exceeding limit values ​​based on on-site measurement point data and real-time calculation simulation data, and is also capable of performing safety evaluations and providing predictive warnings based on the aforementioned on-site measurement point data and real-time calculation simulation data, characterized in that it is a system for monitoring the condition of a boiler water-cooled wall of a power plant and providing early fault warnings.

2. The boiler water-cooled wall condition monitoring and fault early warning system for a power plant according to claim 1, characterized in that several of the data acquisition devices (61, 62-6n) and the various measuring devices are connected via data lines, several of the data acquisition devices (61, 62-6n) are arranged in a distributed manner, and each of the data acquisition devices is connected via the data lines to one or more of the temperature measuring device, the strain measuring device, the displacement measuring device, and the vibration measuring device.

3. The boiler water-cooled wall condition monitoring and fault early warning system for a power plant according to claim 2, characterized in that the entire structural surface of the water-cooled wall is divided into multiple array monitoring areas, and one data acquisition device is provided corresponding to each of the array monitoring areas.

4. The network communication system communicates using a wired network or a wireless network, and when using a wired network, some of the data acquisition devices are connected to a field bus and can exchange data with a switch connected to the field bus, and when using a wireless network, some of the data acquisition devices are connected to a ZigBee or Wi-Fi network and can communicate with the switch via the wireless network, characterized in that the boiler water cooling wall condition monitoring and fault early warning system for a power plant according to claim 2.

5. The boiler water-cooled wall condition monitoring and fault early warning system for a power plant according to claim 1, characterized in that several of the temperature measuring devices (21, 22-2n), several of the strain measuring devices (31, 32-3n), several of the displacement measuring devices (41, 42-4n), and several of the vibration measuring devices (51, 52-5n) are all connected to the water-cooled wall tubes (11) or fins (12) to be monitored by a direct fixing method or a positioning device.

6. The above-level system includes a control operating system, the control operating system (8) is used to provide human-computer interaction, data acquisition, data storage, statistical analysis, and system configuration functions, characterized in that it is a boiler water-cooled wall condition monitoring and fault early warning system for a power plant according to claim 1.

7. A method for monitoring the condition of a boiler water-cooled wall in a power plant and for early fault warning, Step 1 involves inputting the original design parameters of the boiler water-cooled wall (1) into a computer simulation system (9) in order to construct a finite element stress calculation model for the boiler water-cooled wall (1) in Step 3. The temperature-sensitive region, deformation-sensitive region, and vibration-sensitive region of the boiler water-cooled wall are analyzed and determined. Step 2 involves placing several temperature measuring devices (21, 22-2n) in the portion of the boiler water-cooled wall (1) including the temperature-sensitive region, placing several displacement measuring devices (41, 42-4n) in the portion of the boiler water-cooled wall (1) including the deformation-sensitive region, and placing several vibration measuring devices (51, 52-5n) in the boiler water-cooled wall (1) including the vibration-sensitive region, according to the established rules. Step 3 involves obtaining a digital twin model that includes the temperature field distribution and stress field distribution of the entire boiler water-cooled wall based on finite element calculations and a transfer learning model. A method for monitoring the condition of a boiler water-cooled wall of a power plant and providing early fault warnings, characterized by including step 4, which provides a limit value exceedance warning and a predictive warning based on on-site measurement point data and calculation simulation data.

8. Step 3 above is, Step 3-1 involves constructing a finite element stress calculation model for the boiler water-cooled wall (1), The method for monitoring the condition of a boiler water-cooled wall of a power plant and providing early fault warnings, characterized by comprising step 3-2, which involves performing a temperature field calculation under the coupled action of multiple fields, a combustion field, a structural field, and a fluid field, based on a finite element stress calculation model of the boiler water-cooled wall (1), acquiring simulated temperature field distribution data, fusing it with real-time temperature measurement data collected by a transfer learning model, and acquiring the real-time temperature field distribution of the boiler water-cooled wall (1) based on digital twin technology.

9. Step 3 above is, Step 3-3 involves applying the real-time temperature field distribution data of the boiler water-cooled wall (1) obtained in step 3-2 to the finite element stress calculation model of the boiler water-cooled wall (1), performing a stress field calculation under thermal-structural interaction, and obtaining simulated stress field distribution data. Step 3-4 involves determining the stress fracture susceptibility region by combining the collected displacement measurement data and vibration measurement data of the deformation-sensitive region and the vibration-sensitive region with the simulation stress field distribution data from step 3-3, and then arranging several strain measuring devices (31, 32, 3n) in a timely manner to collect real-time strain data. The method for monitoring the condition of a boiler water-cooled wall of a power plant and providing early fault warnings, further comprising step 3-5, which involves fusing the simulated stress field distribution data from step 3-2 with real-time stress measurement data collected by a transfer learning model, obtaining a real-time stress field distribution of the entire boiler water-cooled wall (1) based on digital twin technology, and obtaining a digital twin model that includes the real-time temperature field distribution and real-time stress field distribution of the entire boiler water-cooled wall.

10. Step 4 is, If the temperature, vibration, and displacement values ​​at each measurement point of the boiler water-cooled wall (1), which are collected in real time, are greater than the set thresholds a, b, and c respectively, the power plant's boiler water-cooled wall condition monitoring and fault early warning system (10) performs step 4-1, which generates a corresponding alarm signal. If the temperature value of any point in the actual temperature field calculated by the computer simulation system (9) exceeds a set temperature threshold d, the boiler water-cooled wall condition monitoring and fault early warning system (10) of the power plant performs step 4-2, which generates a corresponding alarm signal. The method for monitoring the condition of a boiler water-cooled wall of a power plant and early fault warning, according to claim 7, is characterized in that the computer simulation system (9) combines calculated actual real-time stress field distribution data, real-time displacement data collected by the displacement measuring devices (41, 42-4n), and real-time vibration data collected by the vibration measuring devices (51, 52-5n) to predict and evaluate the safety of the boiler water-cooled wall (1), and if it is determined that there is a safety risk, the power plant's boiler water-cooled wall condition monitoring and early fault warning system (10) generates a corresponding alarm signal.

Images