A method for monitoring the sliding rail arrangement of a nuclear power plant PX pump house equipment
By optimizing the layout of the monitoring slide rails in the PX pump room of a nuclear power plant using deep learning algorithms, the problem of unreasonable layout of monitoring equipment was solved, the accuracy of instrument readings and the monitoring range were maximized, and the engineering cost was reduced.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CNNC FUJIAN FUQING NUCLEAR POWER
- Filing Date
- 2022-04-06
- Publication Date
- 2026-06-09
AI Technical Summary
The layout of monitoring equipment in the PX pump room of nuclear power plants in the existing technology is unreasonable, which leads to limited monitoring range, inability to obtain comprehensive data, and increased engineering costs.
Deep learning algorithms are used to optimize the slide rail layout scheme. Through simulation verification and nonlinear fuzzy model, the monitoring probes are rationally arranged to ensure that the instrument reading error is small and the monitoring range is maximized, thereby reducing the number of monitoring devices.
This ensures accurate readings from the monitoring probe directly in front of the instrument, maximizes the monitoring range, and reduces engineering costs.
Smart Images

Figure CN116929439B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of pump room equipment monitoring technology, specifically a method for arranging sliding rails for monitoring equipment in a nuclear power plant PX pump room. Background Technology
[0002] PX pump houses are short for nuclear power plant auxiliary pump houses. They are a crucial sub-item related to nuclear safety within the supporting facilities of a nuclear power plant, and therefore have high design and construction standards. In actual construction, due to limitations such as geographical location, construction period, and schedule, the construction of PX pump houses and their intake systems often needs to be carried out in winter. Construction of pump houses and related structures in cold weather where the average daily outdoor temperature is below 5°C for five consecutive days requires compliance with numerous regulations and certain construction safeguards to meet the increased structural strength requirements during winter construction.
[0003] Numerous pieces of equipment exist within the PX pump room of a nuclear power plant, many of which are equipped with instruments. The readings on these instruments provide a clear indication of the equipment's safety. Traditionally, this involved manual periodic checks of the instrument readings to determine if the equipment was functioning properly. However, this method has been gradually phased out, replaced by real-time monitoring equipment. Yet, the layout of these monitoring devices in current technology significantly impacts the overall project cost. Furthermore, an inappropriate layout can limit the monitoring range of the instruments, resulting in incomplete data collection. Summary of the Invention
[0004] The technical problem to be solved by the present invention is to provide a method for arranging the monitoring slide rails of PX pump room equipment in nuclear power plants. This solves the problem that in the prior art, the rationality of the layout of monitoring equipment seriously affects the cost of the entire project. At the same time, an unreasonable layout of monitoring equipment will limit the monitoring range of the instruments, resulting in the inability to obtain comprehensive monitoring data.
[0005] This invention provides a method for arranging monitoring slide rails in a PX pump room of a nuclear power plant, the method comprising the following steps:
[0006] S1. First, measure the internal space dimensions of the nuclear power plant's PX pump room and determine the location of the equipment within the pump room. Then, construct a model of the nuclear power plant's PX pump room on the drawing software and load the equipment within the pump room into the model at a 1:1 scale.
[0007] S2. Simulate different slide rail layout schemes in drawing software, and select the optimal layout scheme for simulation verification;
[0008] S3. Based on the results of the above verification, determine the final slide rail arrangement and define the slide rails into the model according to the slide rail arrangement.
[0009] S4. Construct a monitoring probe model on the slide rail of the overall model, simulate the movement trajectory of the monitoring probe model on the slide rail, and analyze the maximum monitoring range of the monitoring probe.
[0010] S5. Machining the slide rails according to a 1:1 scale, installing the slide rails in the pump room according to the arrangement, and then installing the monitoring probes on the slide rails. After installation, test the data.
[0011] Preferably, the specific content of step 2 is as follows:
[0012] 1) Simulation verification uses a trained deep learning model. A deep learning algorithm is established based on the slide rail trajectory. The obtained feature value coordinates are imported into the deep learning algorithm formula. After importing, the original two-dimensional slide rail image can be generated.
[0013] 2) At the same time, a deep learning model is established based on the deep learning algorithm. The two-dimensional sliding rail image is imported into the deep learning model, and all feature value coordinates are calculated according to the deep learning algorithm. The deep learning model is trained to fuse all feature value coordinates and generate the final three-dimensional sliding rail image.
[0014] Preferably, the specific content of step 4 is as follows:
[0015] The manually drawn sliding track trajectory is imported into the 3D sliding track image. The model compares its own drawn trajectory with the manually drawn trajectory, and then analyzes the difference between the two through a training learning algorithm, and establishes a relevant drawing algorithm based on the training learning algorithm.
[0016] Preferably, the specific content of step 5 is as follows:
[0017] 1) Collect monitoring probe movement data, record relevant parameters of the monitoring probe at corresponding times, and statistically analyze the characteristic values related to time;
[0018] 2) Divide the statistical feature values into segments and set corresponding feature intervals with time parameters as nodes;
[0019] 3) Convert precise quantities into fuzzy single-point sets on the standard universe of discourse, and convert precise quantities into basic elements on the standard universe of discourse through correspondence relations;
[0020] 4) Establish a nonlinear fuzzification model and train a nonlinear fuzzification algorithm;
[0021] 5) Based on the nonlinear fuzzification algorithm, the fuzzy values are inferred and the precise values are determined, and then the final precise quantity output is obtained.
[0022] Compared with existing technologies, the method for arranging monitoring slide rails in nuclear power plant PX pump room equipment of the present invention has the following advantages:
[0023] This invention, through the establishment of models and algorithms, enables the rational layout of slide rails, allowing the monitoring probe to take readings directly in front of the instrument, ensuring that the instrument reading error is minimized within a reasonable range. At the same time, the arrangement of the slide rails maximizes the monitoring range, thereby reducing the number of monitoring devices and saving engineering costs. Attached Figure Description
[0024] Figure 1 This is a schematic diagram of the slide rail structure of the present invention;
[0025] Figure 2 This is a schematic diagram of the process of the present invention. Detailed Implementation
[0026] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0027] Example:
[0028] like Figure 1-2 As shown in the figure, this embodiment of the invention provides a method for arranging monitoring slide rails in a PX pump room of a nuclear power plant. The method includes the following steps:
[0029] S1. First, measure the internal space dimensions of the nuclear power plant's PX pump room and determine the location of the equipment within the pump room. Then, construct a model of the nuclear power plant's PX pump room on the drawing software and load the equipment within the pump room into the model at a 1:1 scale.
[0030] S2. Simulate different slide rail layout schemes in drawing software, and select the optimal layout scheme for simulation verification;
[0031] The details are as follows:
[0032] 1) Simulation verification uses a trained deep learning model. A deep learning algorithm is established based on the slide rail trajectory. The obtained feature value coordinates are imported into the deep learning algorithm formula. After importing, the original two-dimensional slide rail image can be generated.
[0033] 2) At the same time, a deep learning model is built based on the deep learning algorithm. The two-dimensional sliding rail image is imported into the deep learning model. All feature value coordinates are calculated according to the deep learning algorithm. The deep learning model is trained to fuse all feature value coordinates and generate the final three-dimensional sliding rail image.
[0034] S3. Based on the results of the above verification, determine the final slide rail arrangement and define the slide rails into the model according to the slide rail arrangement.
[0035] S4. Construct a monitoring probe model on the slide rail of the overall model, simulate the movement trajectory of the monitoring probe model on the slide rail, and analyze the maximum monitoring range of the monitoring probe.
[0036] The details are as follows:
[0037] The manually drawn sliding track trajectory is imported into the 3D sliding track image. The model compares its own drawn trajectory with the manually drawn trajectory, and then analyzes the difference between the two through a training and learning algorithm, and establishes a relevant drawing algorithm based on the training and learning algorithm.
[0038] S5. Machining the slide rails according to a 1:1 scale, installing the slide rails in the pump room according to the arrangement, and then installing the monitoring probes on the slide rails. After installation, test the data.
[0039] The details are as follows:
[0040] 1) Collect monitoring probe movement data, record relevant parameters of the monitoring probe at corresponding times, and statistically analyze the characteristic values related to time;
[0041] 2) Divide the statistical feature values into segments and set corresponding feature intervals with time parameters as nodes;
[0042] 3) Convert precise quantities into fuzzy single-point sets on the standard universe of discourse, and convert precise quantities into basic elements on the standard universe of discourse through correspondence relations;
[0043] 4) Establish a nonlinear fuzzification model and train a nonlinear fuzzification algorithm;
[0044] 5) Based on the nonlinear fuzzification algorithm, the fuzzy values are inferred and the precise values are determined, and then the final precise quantity output is obtained.
[0045] Reference for the specific shape of slide rail 1 Figure 1 As shown, a main mounting beam 2 is installed on the slide rail 1. The main mounting beam 2 is used to connect with the inner wall of the pump room. The specific length of the main mounting beam 2 is determined according to the span of the installation position. A traveling device 3 is slidably connected to the slide rail 1. The traveling device 3 can move freely on the slide rail 1. An electric telescopic rod 4 is fixedly connected to the bottom of the traveling device 3. A rotating device 5 is fixedly connected to the output end of the electric telescopic rod 4. A monitoring probe 6 is fixedly connected to the output end of the rotating device 5. The electric telescopic rod 4 is used to lift and lower the monitoring probe 6, and the rotating device 5 is used to rotate the monitoring probe 6.
[0046] This invention, through the establishment of models and algorithms, enables the rational layout of slide rails, allowing the monitoring probe to take readings directly in front of the instrument, ensuring that the instrument reading error is minimized within a reasonable range. At the same time, the arrangement of the slide rails maximizes the monitoring range, thereby reducing the number of monitoring devices and saving engineering costs.
[0047] The above description of the embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. It should be noted that those skilled in the art can make several improvements and modifications to the present invention without departing from the principles of the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.
[0048] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for arranging monitoring slide rails in a PX pump room of a nuclear power plant, characterized in that: The method includes the following steps: Step S1: First, measure the space dimensions inside the PX pump room of the nuclear power plant, and at the same time determine the location area of the equipment inside the pump room. Construct a model of the PX pump room of the nuclear power plant on the drawing software, and load the equipment inside the pump room into the model at a 1:1 scale. Step S2: Simulate different slide rail layout schemes in drawing software, and select the optimal layout scheme for simulation verification; Step S3: Determine the final slide rail layout scheme based on the above verification results, and define the slide rails into the model according to the slide rail layout scheme; Step S4: Construct a monitoring probe model on the slide rail of the overall model, simulate the motion trajectory of the monitoring probe model on the slide rail, and analyze the maximum monitoring range of the monitoring probe. Step S5: Machin the slide rails according to a 1:1 scale, install the slide rails in the pump room according to the layout plan, and then install the monitoring probes on the slide rails. After installation, test the data. The specific contents are as follows: 1) Collect monitoring probe movement data, record relevant parameters of the monitoring probe at corresponding times, and statistically analyze the characteristic values related to time; 2) Divide the statistical feature values into segments and set corresponding feature intervals with time parameters as nodes; 3) Convert precise quantities into fuzzy single-point sets on the standard universe of discourse, and convert precise quantities into basic elements on the standard universe of discourse through correspondence relations; 4) Establish a nonlinear fuzzification model and train a nonlinear fuzzification algorithm; 5) Based on the nonlinear fuzzification algorithm, the fuzzy values are inferred and the precise values are determined, and then the final precise quantity output is obtained.