A distributed monitoring system for nuclear power plants

Abstract

The application provides a nuclear power plant distributed monitoring system, and belongs to the technical field of nuclear power plant equipment monitoring and safety, the system comprises: a field acquisition module, which acquires monitoring data of a nuclear power plant equipment, generates equipment operation state information through a locally deployed artificial intelligence algorithm model, controls the amount of uploaded data according to the change amount of the monitoring data, and generates self-diagnosis state information of the field acquisition module; a radiation-resistant bus, which is used for transmitting data between the field acquisition module and a protocol conversion module; the protocol conversion module, which manages and schedules the field acquisition module, converts a special protocol of the radiation-resistant bus into a general network protocol, and sends the uploaded data of the field acquisition module to an upper computer; and the upper computer, which constructs a nuclear power plant state evaluation model according to the uploaded data of the field acquisition module, and generates a nuclear power plant equipment control instruction. The application realizes accurate evaluation of the state of the nuclear power plant equipment through edge computing, and improves the real-time performance and reliability of monitoring.

Description

Technical Field

[0001] This invention belongs to the field of nuclear power plant equipment monitoring and safety technology, and specifically relates to a distributed monitoring system for nuclear power plants. Background Technology

[0002] During the operation of a nuclear power plant, real-time monitoring of equipment such as main pumps, steam generators, valves, and pipelines, as well as continuous real-time monitoring of environmental conditions such as temperature, pressure, vibration, and radiation dose, are the core of ensuring the safe, stable, and efficient operation of the nuclear power plant.

[0003] However, nuclear reactor building areas are exposed to high doses of radiation. Ordinary electronic equipment and sensors cannot operate stably in radiation areas for long periods of time, and are prone to performance degradation, data drift, or even permanent damage, resulting in monitoring blind spots. Existing monitoring systems mostly adopt the "data acquisition + centralized processing" model, transmitting massive amounts of raw monitoring data to the main control room, which puts enormous pressure on communication bandwidth and central processing units. At the same time, communication delays lead to delayed analysis and decision-making, making it difficult to achieve early fault warnings and adaptive control of equipment. Summary of the Invention

[0004] To address the problems in the prior art, this invention proposes a distributed monitoring system for nuclear power plants. By performing edge processing, fusion analysis, and dynamic uploading control on multi-source monitoring data, it achieves accurate assessment of the operating status of nuclear power plant equipment, improving monitoring real-time performance, data transmission efficiency, and system operational reliability.

[0005] The technical solution of the present invention is as follows: This invention proposes a distributed monitoring system for nuclear power plants, comprising: The on-site data acquisition module collects monitoring data from nuclear power plant equipment. The monitoring data is used to generate equipment operating status information through a locally deployed artificial intelligence algorithm model. The module controls the amount of data uploaded based on changes in the monitoring data and generates self-diagnostic status information for the on-site data acquisition module. An irradiation-resistant bus is used to transmit data between the field acquisition module and the protocol conversion module; The protocol conversion module manages and schedules the field acquisition module, converts the dedicated protocol of the radiation-resistant bus into a general network protocol, and sends the uploaded data from the field acquisition module to the host computer. The host computer constructs a nuclear power plant status assessment model based on the data uploaded by the field acquisition module and generates control commands for the nuclear power plant equipment.

[0006] Furthermore, the on-site data acquisition module includes: Resistance temperature detector acquisition unit, used to acquire the temperature of nuclear power plant equipment; Analog acquisition unit, used to acquire continuously changing analog signals; Digital acquisition unit is used to acquire digital signals of switch status; The video acquisition unit is used to acquire video image information within the nuclear power plant. The edge computing unit locally deploys artificial intelligence algorithm models to generate equipment operating status information and on-site acquisition module self-diagnostic status information. The communication unit is used to send monitoring data, equipment operating status information, and upload self-diagnostic status information from the field acquisition module.

[0007] Furthermore, the amount of data uploaded is controlled based on the changes in monitoring data as follows: The artificial intelligence algorithm model generates threshold values ​​for changes in monitoring data from the resistance temperature detector acquisition unit, analog acquisition unit, digital acquisition unit, and video acquisition unit based on the monitoring data. When the data change of the acquisition unit is less than the corresponding monitoring data change threshold, the statistical characteristic value of the original monitoring data is calculated within a preset time window and uploaded to the protocol conversion module. When the data change of the acquisition unit is greater than or equal to the corresponding monitoring data change threshold, the original monitoring data and self-diagnostic status information are uploaded.

[0008] Furthermore, the system uses a nuclear power plant condition assessment model to periodically update the artificial intelligence algorithm model deployed locally in the field acquisition module.

[0009] Furthermore, the general network protocol is an industrial communication protocol based on TCP / IP network transmission.

[0010] Furthermore, the industrial communication protocols include Modbus TCP, OPC UA, IEC 61850, Profinet, and EtherNet / IP.

[0011] Furthermore, the protocol conversion module packages and verifies the uploaded data from the field acquisition module to generate standardized data frames, and sends the standardized data frames to the host computer. The standardized data frame consists of nuclear power plant equipment number, field acquisition module number, acquisition timestamp, monitoring data, and self-diagnostic status code.

[0012] Furthermore, the protocol conversion module sends standardized data frames to the host computer through a dual-network redundant communication link; The dual-network redundant communication link includes a primary communication link and a backup communication link; During normal operation, standardized data frames are sent to the host computer through the main communication link, while the backup communication link remains in standby mode. When the primary communication link fails, the system automatically switches to the backup communication link to send standardized data frames.

[0013] Furthermore, the field acquisition module is protected by a lead or stainless steel sealed housing.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention deploys an edge computing model locally in the field acquisition module to preprocess, fuse, analyze, and dynamically control the upload of multi-source monitoring data. This enables edge processing and on-demand uploading of monitoring data, reducing the amount of monitoring data uploaded while ensuring the accuracy of equipment status monitoring. This also reduces communication bandwidth usage and the computing load on the host computer, and improves the real-time response capability of the system. By integrating temperature data, analog data, digital status data, and video information, and combining this with self-diagnostic information from the acquisition modules, the system constructs the equipment operating status, enabling collaborative analysis of equipment status assessment and the health status of the acquisition modules. This improves the accuracy of equipment fault identification and the reliability of monitoring data, reduces false alarm rates, and enhances the operational reliability of the nuclear power plant's distributed monitoring system in high-irradiation environments. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the architecture of a distributed monitoring system for a nuclear power plant. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the present invention.

[0017] Example 1: This embodiment provides a distributed monitoring system for nuclear power plants, such as... Figure 1 As shown, it includes: The field acquisition module includes a resistance temperature detector (RTD) acquisition unit, an analog acquisition unit, a digital acquisition unit, a video acquisition unit, an edge computing unit, and a communication unit. The resistance temperature detector acquisition unit is used to acquire the temperature of nuclear power plant equipment, the analog acquisition unit is used to acquire continuously changing analog signals, the digital acquisition unit is used to acquire digital signals of switch status, the video acquisition unit is used to acquire video image information inside the nuclear power plant, and the communication unit uploads the data from the field acquisition module to the protocol conversion module. The edge computing unit locally deploys an artificial intelligence algorithm model to preprocess the data from the field acquisition module, integrate and analyze the data from the field acquisition module, generate equipment operating status information, control the amount of data uploaded according to changes in monitoring data, and diagnose abnormal states of the field acquisition module and generate self-diagnostic status information. An irradiation-resistant bus is used to transmit data between the protocol conversion module and the field acquisition module; The protocol conversion module connects at least 30 field acquisition modules via the radiation-resistant bus, manages and schedules the field acquisition modules, and converts the radiation-resistant bus's proprietary protocol into a general network protocol that can be recognized by the host computer. The host computer constructs a nuclear power plant status assessment model based on data collected from the field acquisition modules and generates control commands for the nuclear power plant equipment.

[0018] Preferably, controlling the amount of uploaded data based on changes in monitoring data specifically includes: The artificial intelligence algorithm model evaluates the status of the acquisition unit based on the data from the on-site acquisition module and generates threshold values ​​for the change in monitoring data of each acquisition unit. When the data change of the acquisition unit is less than the corresponding monitoring data change threshold, the statistical feature value of the original acquisition data is calculated within a 10-second time window and uploaded to the protocol conversion module. When the data change of the acquisition unit is greater than or equal to the corresponding monitoring data change threshold, the original acquisition data and self-diagnostic status information are uploaded. The statistical characteristics include the mean, maximum, minimum, and standard deviation.

[0019] Preferably, the construction of the nuclear power plant status assessment model is implemented using a Bayesian network model or a random forest model.

[0020] Preferably, the field acquisition module is protected by a lead or stainless steel sealed housing.

[0021] Preferably, the resistance temperature detector acquisition unit adopts a four-wire resistance temperature detector, and each resistance temperature detector acquisition unit acquires at least 8 four-wire resistance temperature detectors, with isolation between the 8 channels.

[0022] Preferably, the analog acquisition unit acquires at least 8 channels of 4~20mA analog signals, and the 8 channels are isolated from each other.

[0023] Preferably, the digital acquisition unit acquires at least 16 channels of 24V digital signals, and the 16 channels are isolated from each other.

[0024] Preferably, the artificial intelligence algorithm model deployed locally on the edge computing unit is updated periodically using the nuclear power plant status assessment model.

[0025] Example 2: This embodiment provides an operation flow for a distributed monitoring system for a nuclear power plant, the flow of which includes the following steps: According to the monitoring requirements of nuclear power plants, each unit in the on-site acquisition module synchronously completes the on-site acquisition of the corresponding monitoring signals at a preset acquisition rate. The edge computing units of each field acquisition module preprocess the acquired raw monitoring signals, including filtering, noise reduction, and scaling transformation, converting the raw monitoring signals into digital signals and controlling the amount of data uploaded according to changes in the monitoring data. The temperature data uploaded by the resistance temperature detector acquisition unit, the analog signal data uploaded by the analog acquisition unit, the digital signal data uploaded by the digital acquisition unit, and the video information are correlated. Temperature features, operating parameter features, equipment status features, and video image features are extracted respectively. The data are then fused and analyzed using a locally deployed artificial intelligence algorithm model to generate equipment operating status information and self-diagnostic status information. The radiation-resistant bus transmits digital signals and self-diagnostic status information to the protocol conversion module, and manages the field acquisition module through polling scheduling to ensure the orderly transmission of data and avoid data conflicts. After receiving digital signals and self-diagnostic status information from all field acquisition modules, the protocol conversion module converts the dedicated protocol of the radiation-resistant bus into a general network protocol that can be recognized by the host computer. At the same time, it packages and verifies the data to generate standardized data frames. The host computer receives all digital signals and self-diagnostic status information, performs fusion analysis, constructs a nuclear power plant status assessment model, generates nuclear power plant equipment control commands, and realizes unified storage and correlation analysis of multi-source acquired data.

[0026] Preferably, the general network protocol is an industrial communication protocol based on TCP / IP network transmission.

[0027] Preferably, the industrial communication protocols include Modbus TCP, OPC UA, IEC 61850, Profinet, and EtherNet / IP.

[0028] Preferably, the standardized data frame consists of a device number, a field acquisition module number, an acquisition timestamp, acquired data, and a self-diagnostic status code.

[0029] Preferably, the protocol conversion module sends standardized data frames to the host computer through a dual-network redundant communication link, wherein the dual-network redundant communication link includes a main communication link and a backup communication link; During normal operation, data is sent to the host computer through the main communication link, while the backup communication link remains in standby mode. When a communication timeout, link interruption, or data verification anomaly is detected on the main communication link, the protocol conversion module automatically switches to the backup communication link to continue data transmission, ensuring the continuous uploading of monitoring data.

[0030] The above descriptions are merely embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structures made using the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A distributed monitoring system for a nuclear power plant, characterized in that, include: The on-site data acquisition module collects monitoring data from nuclear power plant equipment. The monitoring data is used to generate equipment operating status information through a locally deployed artificial intelligence algorithm model. The module controls the amount of data uploaded based on changes in the monitoring data and generates self-diagnostic status information for the on-site data acquisition module. An irradiation-resistant bus is used to transmit data between the field acquisition module and the protocol conversion module; The protocol conversion module manages and schedules the field acquisition module, converts the dedicated protocol of the radiation-resistant bus into a general network protocol, and sends the uploaded data from the field acquisition module to the host computer. The host computer constructs a nuclear power plant status assessment model based on the data uploaded by the field acquisition module and generates control commands for the nuclear power plant equipment.

2. The distributed monitoring system for a nuclear power plant according to claim 1, characterized in that, The on-site data acquisition module includes: Resistance temperature detector acquisition unit, used to acquire the temperature of nuclear power plant equipment; Analog acquisition unit, used to acquire continuously changing analog signals; Digital acquisition unit is used to acquire digital signals of switch status; The video acquisition unit is used to acquire video image information within the nuclear power plant. The edge computing unit locally deploys artificial intelligence algorithm models to generate equipment operating status information and on-site acquisition module self-diagnostic status information. The communication unit is used to send monitoring data, equipment operating status information, and upload self-diagnostic status information from the field acquisition module.

3. A distributed monitoring system for a nuclear power plant according to claim 2, characterized in that, The amount of data uploaded is controlled based on the changes in monitored data, specifically as follows: The artificial intelligence algorithm model generates threshold values ​​for changes in monitoring data from the resistance temperature detector acquisition unit, analog acquisition unit, digital acquisition unit, and video acquisition unit based on the monitoring data. When the data change of the acquisition unit is less than the corresponding monitoring data change threshold, the statistical characteristic value of the original monitoring data is calculated within a preset time window and uploaded to the protocol conversion module. When the data change of the acquisition unit is greater than or equal to the corresponding monitoring data change threshold, the original monitoring data and self-diagnostic status information are uploaded.

4. A distributed monitoring system for a nuclear power plant according to claim 1, characterized in that, The system uses a nuclear power plant condition assessment model to periodically update the locally deployed artificial intelligence algorithm model of the field acquisition module.

5. A distributed monitoring system for a nuclear power plant according to claim 1, characterized in that, The general network protocol is an industrial communication protocol based on TCP / IP network transmission.

6. A distributed monitoring system for a nuclear power plant according to claim 5, characterized in that, The industrial communication protocols include Modbus TCP, OPC UA, IEC 61850, Profinet, and EtherNet / IP.

7. A distributed monitoring system for a nuclear power plant according to claim 1, characterized in that, The protocol conversion module packages and verifies the uploaded data from the field acquisition module, generates standardized data frames, and sends the standardized data frames to the host computer. The standardized data frame consists of nuclear power plant equipment number, field acquisition module number, acquisition timestamp, monitoring data, and self-diagnostic status code.

8. A distributed monitoring system for a nuclear power plant according to claim 7, characterized in that, The protocol conversion module sends standardized data frames to the host computer through dual network redundant communication links; The dual-network redundant communication link includes a primary communication link and a backup communication link; During normal operation, standardized data frames are sent to the host computer through the main communication link, while the backup communication link remains in standby mode. When the primary communication link fails, the system automatically switches to the backup communication link to send standardized data frames.

9. A distributed monitoring system for a nuclear power plant according to claim 1, characterized in that, The field acquisition module is protected by a lead or stainless steel sealed housing.

Images