Production environment risk pre-judgment system

Abstract

The invention relates to the technical field of production safety, in particular to a production environment risk pre-judgment system which comprises a data acquisition module, a data processing module, a data analysis pre-judgment module, a 3D pre-judgment demonstration module, a data storage module and a control management module. The unmanned aerial vehicle is adopted for data collection, the data collection efficiency is improved, transformation of the internal environment of the thermal power plant is reduced, meanwhile, through the mode that the unmanned aerial vehicle and track sliding are combined, the unmanned aerial vehicle can conveniently conduct off-line data collection in the environment with high electromagnetic interference, and the data collection efficiency is improved. Secondly, analyzing and processing the image data by adopting a convolutional neural network I, analyzing a production plan and an equipment operation condition by adopting an LSTM neural network, pre-judging a development trend of potential hidden dangers of the equipment in a period of time in the future, and constructing unit modeling of a thermal power plant so as to obtain a development trend of the potential hidden dangers of the equipment; and 3D simulation display is carried out on the operation condition of each device and the analyzed development trend, so that the inspection convenience is improved, and production accidents are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of production safety, and particularly to a production environment danger prediction system. Background Art

[0002] A thermal power plant, also known as a thermal power station, is a factory that uses combustibles (such as coal, petroleum, natural gas, etc.) as fuel to produce electric energy. In order to ensure the safe operation of the thermal power plant, it is necessary to conduct inspections on the thermal power plant to reduce the occurrence of equipment failures and dangerous situations in the thermal power plant. Generally, by setting thresholds for sensors, manual inspections, and relying on the experience of staff, the dangers in production are predicted, but the accuracy is relatively low. Moreover, the scope of the thermal power plant is large, and a large number of staff are required for inspections, which is time-consuming and laborious.

[0003] Therefore, currently, most use an intelligent inspection and acquisition system and method for a thermal power plant disclosed in a patent for invention with the publication number CN116091047B and an intelligent inspection system and method for a thermal power plant disclosed in a patent for invention with the publication number CN103839302B, etc., to monitor the operating conditions of various equipment and the surrounding environment in the thermal power plant.

[0004] However, it is found in the use process that most of the existing inspection systems need to build lines or set up signal stations to transform the environment in the thermal power plant, and the transformation of most old thermal power plants is difficult. Moreover, the existing inspection systems are difficult to realize the prediction of production environment dangers based on inspection results, are difficult to respond to dynamic changes in a timely manner, and are difficult to simulate production environment intervention measures in a virtual manner, resulting in poor practicability. Therefore, there is an urgent need for a production environment danger prediction system to improve the above problems. Summary of the Invention

[0005] To solve the above technical problems, the present invention provides a production environment danger prediction system that uses drones to collect data, improves the data collection efficiency, and reduces the transformation of the environment in the thermal power plant. At the same time, by combining drones and track sliding, it is convenient for drones to collect offline data in an environment with strong electromagnetic interference. Secondly, by using a convolutional neural network to analyze and process image data, and then using an LSTM neural network to analyze the production plan and equipment operating conditions, the development trend of potential hidden dangers of equipment in the next period of time is predicted. Furthermore, by using digital twin technology to construct a unit model of the thermal power plant, the operating conditions of each equipment and the analyzed development trend are displayed in 3D simulation, improving the inspection convenience and reducing the occurrence of production accidents.

[0006] A production environment danger prediction system of the present invention includes:

[0007] Data acquisition module: Monitor the operating conditions of various equipment in the thermal power plant, collect and transmit the detection results, and issue an alarm to remind the staff to handle it urgently when a situation exceeding the preset value is found during the detection process;

[0008] Data processing module: Adjust the size of the collected detection results, and perform denoising and grayscale processing;

[0009] Data analysis and prediction module: Analyze the processed data, judge whether there are potential safety hazards in the equipment, and predict the development trend of potential hazards in the equipment in the next period of time based on the analysis results combined with the production plan;

[0010] 3D prediction demonstration module: Display the operating conditions of each equipment, and can also perform 3D simulation display of the analyzed development trend, which is convenient for the staff to formulate maintenance plans or adjust the production plan;

[0011] Data storage module: Store the processed data, analysis results and operation data of the system;

[0012] Control and management module: Centralize the control and management of the data acquisition module, data processing module, data analysis and prediction module, 3D prediction demonstration module and data storage module, verify the identity information of the logged-in personnel, record the operation process of the system at the same time, and transmit the record to the data storage module.

[0013] Preferably, the data acquisition module includes:

[0014] Equipment monitoring unit: Installed on various equipment in the thermal power plant to monitor the operating conditions of various equipment in the thermal power plant;

[0015] Patrol unit: Collect the detection data of the equipment detection unit and transmit it to the data processing module;

[0016] Alarm unit: When the equipment monitoring unit monitors that the operating value of the equipment exceeds the threshold, it issues an alarm to remind the staff to handle it urgently.

[0017] Preferably, the data preprocessing module includes:

[0018] Size adjustment unit: Adjust the size of the collected image data;

[0019] Denoising unit: Perform denoising processing on the image data;

[0020] Grayscale processing unit: Perform grayscale processing on the image data.

[0021] Preferably, the data analysis and prediction module includes:

[0022] Convolutional neural network one: Analyze the processed image data to determine whether there are potential hidden dangers in the device;

[0023] LSTM neural network: According to the production plan and the analysis results of the convolutional neural network, predict the development trend of potential hidden dangers in the device in the next period of time;

[0024] Database: Store the training data of the convolutional neural network and the recurrent neural network.

[0025] Preferably, the data storage module includes:

[0026] Classification unit: Classify the data according to the data sending source;

[0027] Storage unit: Store the classified data within a limited time;

[0028] Management unit: Set the storage period of the data and delete the data that exceeds the storage period.

[0029] Preferably, the control and management module includes:

[0030] Verification unit: Verify the identity information of the logged-in personnel;

[0031] Central control unit: Conduct centralized control and management of the data acquisition module, data processing module, data analysis and prediction module, 3D prediction demonstration module, and data storage module;

[0032] Recording unit: Record the operation process of the system and transmit the record to the data storage module.

[0033] Preferably, the inspection unit includes a drone, a shooting mechanism, and a conveying mechanism. The shooting mechanism is installed on the drone, and a convolutional neural network two is arranged inside the drone. The conveying mechanism is located in the electromagnetic interference area to assist the drone in moving. The drone carries the shooting mechanism and flies in the air according to a preset route, or the staff operates the drone to fly. At the same time, the shooting mechanism shoots the surrounding environment and the data collected and displayed by the device monitoring unit, and analyzes the captured surrounding images through the convolutional neural network two. When the drone is interfered, it automatically avoids obstacles. In the electromagnetic interference area, the conveying mechanism assists the drone in moving to complete the data acquisition in the magnetic interference area.

[0034] Preferably, the photographing mechanism includes a slide rail, an electric slider I, a high-definition camera, a millimeter-wave radar, and a gas monitor. The slide rail is installed at the bottom of the drone. The electric slider I is slidably installed on the slide rail. The high-definition camera, the millimeter-wave radar, and the gas monitor are all fixedly installed on the electric slider I. By sliding the electric slider I on the slide rail, the positions of the high-definition camera, the millimeter-wave radar, and the gas monitor are adjusted. The surrounding environment is photographed by the high-definition camera, and the data collected and displayed by the equipment monitoring unit is obtained. At the same time, the surrounding radar images are obtained through the millimeter-wave radar, and the surrounding gas is monitored by the gas monitor.

[0035] Preferably, the conveying mechanism includes a silk thread, a magnetic metal block, a track, an electric slider II, a winding shaft, a driving motor, and an electromagnet. An electric winding shaft is arranged inside the drone. The silk thread is wound on the electric winding shaft. The magnetic metal block is installed at one end of the silk thread and is located below the drone. The track is installed in the electromagnetic interference area of the thermal power plant. The electric slider II is slidably installed on the track, and a chamber is arranged inside the electric slider II. An opening is arranged at the top of the electric slider II. The winding shaft is rotatably installed inside the electric slider II. The driving motor is fixedly installed inside the electric slider II, and the output shaft of the driving motor is connected to one end of the winding shaft. The electromagnet is installed on the winding shaft. When the drone flies above the electric slider II, the silk thread is released through the electric winding shaft inside it, so that the magnetic metal block drops into the electric slider II. At the same time, the electromagnet is energized to generate magnetism to attract the magnetic metal block. Then the driving motor is turned on to drive the winding shaft to rotate, and the silk thread is wound on the winding shaft. At the same time, the drone descends and lands on the electric slider II. The electric slider II slides on the track to drive the drone to move in the electromagnetic interference area. After the electric slider II moves out of the electromagnetic interference area, the above steps are repeated in reverse, and the drone flies away.

[0036] Preferably, a rotary joint is arranged at the other end of the winding shaft; it is connected to the power supply through the rotary joint to supply power to the electromagnet.

[0037] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0038] 1. The method of using a drone for data collection is adopted to improve the data collection efficiency and reduce the transformation of the environment inside the thermal power plant. At the same time, through the combination of the drone and the track sliding, it is convenient for the drone to perform offline data collection in an environment with strong electromagnetic interference.

[0039] 2. The convolutional neural network is used to analyze and process the image data, and then the LSTM neural network is used to analyze the production plan and the equipment operation status to predict the development trend of potential hidden dangers of the equipment in a period of time in the future.

[0040] 3. Build a unit model of a thermal power plant through digital twin technology, and conduct 3D simulation displays on the operating conditions and analyzed development trends of each device to improve the convenience of inspection and reduce the occurrence of production accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 is a schematic structural diagram of the production environment hazard prediction system of the present invention;

[0042] Figure 2 is a schematic structural diagram of the data acquisition module of the present invention;

[0043] Figure 3 is a schematic structural diagram of the data processing module of the present invention;

[0044] Figure 4 is a schematic structural diagram of the data analysis and prediction module of the present invention;

[0045] Figure 5 is a schematic structural diagram of the data storage module of the present invention;

[0046] Figure 6 is a schematic structural diagram of the control and management module of the present invention;

[0047] Figure 7 is a first axonometric structural diagram of the inspection unit of the present invention;

[0048] Figure 8 is a second axonometric structural diagram of the inspection unit of the present invention;

[0049] Figure 9 is the present invention Figure 8 in the enlarged structural diagram of part A;

[0050] Figure 10 is a front sectional structural diagram of the conveying mechanism of the present invention.

[0051] Reference numerals in the drawings: 1, unmanned aerial vehicle; 2, slide rail; 3, electric slider 1; 4, high-definition camera; 5, millimeter-wave radar; 6, gas monitor; 7, silk thread; 8, magnetic metal block; 9, track; 10, electric slider 2; 11, winding shaft; 12, drive motor; 13, electromagnet; 14, rotary joint. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. The present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided to make the disclosure of the present invention more thorough and comprehensive.

[0053] Embodiment 1: As Figures 1 to 10As shown in the figure, a production environment hazard prediction system includes:

[0054] Data acquisition module: Monitor the operating conditions of various devices in the thermal power plant, collect and transmit the detection results, and when a situation exceeding the preset value is found during the detection process, issue an alarm to remind the staff to handle it urgently;

[0055] Data processing module: Adjust the size of the collected detection results, and perform denoising and grayscale processing;

[0056] Data analysis and prediction module: Analyze the processed data, judge whether there are potential safety hazards in the devices, and combine the analysis results with the production plan to predict the development trend of potential hazards in the devices within a certain period of time in the future;

[0057] 3D prediction demonstration module: Display the operating conditions of various devices, and can also perform 3D simulation display of the analyzed development trend, which is convenient for the staff to formulate maintenance plans or adjust the production plan;

[0058] Data storage module: Store the processed data, analysis results and operation data of the system;

[0059] Control and management module: Conduct centralized control and management of the data acquisition module, data processing module, data analysis and prediction module, 3D prediction demonstration module and data storage module, verify the identity information of the logged-in personnel, record the operation process of the system at the same time, and transmit the record to the data storage module;

[0060] The data acquisition module includes:

[0061] Device monitoring unit: Installed on various devices in the thermal power plant to monitor the operating conditions of various devices in the thermal power plant;

[0062] Patrol unit: Collect the detection data of the device detection unit and transmit it to the data processing module;

[0063] Alarm unit: When the device monitoring unit monitors that the operating value of the device exceeds the threshold, issue an alarm to remind the staff to handle it urgently;

[0064] The data preprocessing module includes:

[0065] Size adjustment unit: Adjust the size of the collected image data;

[0066] Denoising unit: Perform denoising processing on the image data;

[0067] Grayscale processing unit: Perform grayscale processing on the image data;

[0068] The data analysis and prediction module includes:

[0069] Convolutional neural network 1: Analyze the processed image data to determine whether there are potential hidden dangers in the device;

[0070] LSTM neural network: Based on the production plan and the analysis results of the convolutional neural network, predict the development trend of potential hidden dangers in the device in the next period of time;

[0071] Database: Store the training data of the convolutional neural network and the recurrent neural network;

[0072] The data storage module includes:

[0073] Classification unit: Classify the data according to the data source;

[0074] Storage unit: Store the classified data within a limited time;

[0075] Management unit: Set the storage period of the data and delete the data that exceeds the storage period;

[0076] The control and management module includes:

[0077] Verification unit: Verify the identity information of the logged-in personnel;

[0078] Central control unit: Centralize the control and management of the data acquisition module, data processing module, data analysis and prediction module, 3D prediction demonstration module and data storage module;

[0079] Recording unit: Record the operation process of the system and transmit the record to the data storage module;

[0080] The inspection unit includes UAV 1, a shooting mechanism and a conveying mechanism. The shooting mechanism is installed on UAV 1, and a convolutional neural network 2 is arranged inside UAV 1. The conveying mechanism is located in the electromagnetic interference area to assist UAV 1 in moving;

[0081] The shooting mechanism includes a slide rail 2, an electric slider 1 3, a high-definition camera 4, a millimeter-wave radar 5 and a gas monitor 6. The slide rail 2 is installed at the bottom of UAV 1, the electric slider 1 3 is slidably installed on the slide rail 2, and the high-definition camera 4, the millimeter-wave radar 5 and the gas monitor 6 are all fixedly installed on the electric slider 1 3;

[0082] The operation status of each device in the thermal power plant is monitored by the device monitoring unit. Then, the unmanned aerial vehicle 1 carries the shooting mechanism and flies in the air according to the preset route, or the staff operates the unmanned aerial vehicle 1 to fly. At the same time, the electric slider 1 slides on the slide rail 2 to adjust the positions of the high-definition camera 4, the millimeter-wave radar 5, and the gas monitor 6. The surrounding environment is photographed by the high-definition camera 4 and the data collected and displayed by the device monitoring unit. At the same time, the surrounding radar images are obtained by the millimeter-wave radar 5, the surrounding gas is monitored by the gas monitor 6, and the surrounding images taken are analyzed by the convolutional neural network 2. When the unmanned aerial vehicle 1 is interfered, it can automatically avoid obstacles. In the electromagnetic interference area, the conveying mechanism is used to assist the unmanned aerial vehicle 1 to move to complete the data collection in the magnetic interference area. Then, the collected data is transmitted to the data processing module. The data processing module adjusts the size of the collected detection results, performs denoising and grayscale processing, and then analyzes the processed image data by the convolutional neural network 1 to judge whether there are potential hidden dangers in the device. According to the production plan and the analysis results of the convolutional neural network, the LSTM neural network predicts the development trend of potential hidden dangers in the device in the next period of time. Then, the 3D prediction demonstration module displays the operation status of each device, and can also perform 3D simulation display on the analyzed development trend, which is convenient for the staff to formulate maintenance plans or adjust the production plan, thereby improving the practicability of the production environment danger prediction system.

[0083] Embodiment 2: As Figures 1 to 10 shown, a production environment danger prediction system further includes, on the basis of Embodiment 1:

[0084] The conveying mechanism includes a silk thread 7, a magnetic metal block 8, a track 9, an electric slider 2 10, a winding shaft 11, a driving motor 12, and an electromagnet 13. An electric winding shaft is arranged inside the unmanned aerial vehicle 1. The silk thread 7 is wound on the electric winding shaft. The magnetic metal block 8 is installed at one end of the silk thread 7, and the magnetic metal block 8 is located below the unmanned aerial vehicle 1. The track 9 is installed in the electromagnetic interference area in the thermal power plant. The electric slider 2 10 is slidably installed on the track 9, and a chamber is arranged inside the electric slider 2 10. An opening is arranged at the top of the electric slider 2 10. The winding shaft 11 is rotatably installed inside the electric slider 2 10. The driving motor 12 is fixedly installed inside the electric slider 2 10, and the output shaft of the driving motor 12 is connected to one end of the winding shaft 11. The electromagnet 13 is installed on the winding shaft 11;

[0085] The other end of the winding shaft 11 is provided with a rotary joint 14;

[0086] The operating conditions of each device in the thermal power plant are monitored by the device monitoring unit. Then, the unmanned aerial vehicle 1 carries the imaging mechanism and flies in the air according to a preset route, or the staff operates the unmanned aerial vehicle 1 to fly. At the same time, the electric slider 1 slides on the slide rail 2 to adjust the positions of the high-definition camera 4, the millimeter-wave radar 5, and the gas monitor 6. The surrounding environment is photographed by the high-definition camera 4, and the data collected and displayed by the device monitoring unit is also photographed. At the same time, the surrounding radar images are obtained through the millimeter-wave radar 5, the surrounding gas is monitored by the gas monitor 6, and the surrounding images taken are analyzed through the convolutional neural network 2. When the unmanned aerial vehicle 1 is interfered with, it automatically avoids obstacles. When flying to the electromagnetic interference area, the unmanned aerial vehicle 1 flies above the electric slider 2. The silk thread 7 is loosened through the electric winding shaft inside it, so that the magnetic metal block 8 drops into the electric slider 2. At the same time, the electromagnet 13 is energized to generate magnetism to attract the magnetic metal block 8. Then, the drive motor 12 is turned on to drive the winding shaft 11 to rotate, and the silk thread 7 is wound on the winding shaft 11. At the same time, the unmanned aerial vehicle 1 descends and lands on the electric slider 2. The electric slider 2 slides on the track 9 to drive the unmanned aerial vehicle 1 to move within the electromagnetic interference area. After the electric slider 2 moves out of the electromagnetic interference area, the above steps are repeated in reverse, and the unmanned aerial vehicle 1 flies away to complete the data collection in the magnetic interference area. Then, the collected data is transmitted to the data processing module. The data processing module adjusts the size of the collected detection results, performs denoising and grayscale processing, and then analyzes the processed image data through the convolutional neural network 1 to judge whether there are potential hidden dangers in the device. According to the production plan and the analysis results of the convolutional neural network, the LSTM neural network predicts the development trend of potential hidden dangers in the device in the next period of time. Then, the 3D prediction demonstration module displays the operating conditions of each device, and can also perform 3D simulation display of the analyzed development trend, which is convenient for the staff to formulate maintenance plans or adjust the production plan, thereby improving the practicability of the production environment danger prediction system.

[0087] The main functions realized by the present invention are as follows:

[0088] 1. The data is collected by using the unmanned aerial vehicle method, which improves the data collection efficiency and reduces the transformation of the environment in the thermal power plant. At the same time, through the combination of the unmanned aerial vehicle and the track sliding, it is convenient for the unmanned aerial vehicle to collect offline data in an environment with strong electromagnetic interference;

[0089] 2. The convolutional neural network 1 is used to analyze and process the image data, and the LSTM neural network is used to analyze the production plan and the operating conditions of the device to predict the development trend of potential hidden dangers in the device in the next period of time;

[0090] 3. By using digital twin technology to construct a unit model of a thermal power plant, 3D simulation display is carried out on the operating conditions of each device and the analyzed development trend, improving the convenience of inspection and reducing the occurrence of production accidents.

[0091] For a production environment hazard prediction system of the present invention, its installation method, connection method or setting method are all common mechanical methods, and any implementation that can achieve its beneficial effects can be carried out; the drone 1, electric slider 1, high-definition camera 4, millimeter-wave radar 5, gas monitor 6, electric slider 2, drive motor 12, electromagnet 13 and rotary joint 14 of a production environment hazard prediction system of the present invention are purchased on the market, and technicians in this industry only need to install and operate according to the attached user manual, without the need for technicians in this field to make creative efforts.

[0092] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art in the technical field, without departing from the technical principle of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. A production environment danger prediction system, characterized in that, Including: Data acquisition module: Monitor the operating conditions of various devices in the thermal power plant, collect and transmit the detection results, and issue an alarm to remind the staff to handle it urgently when a situation exceeding the preset value is found during the detection process; Data processing module: Adjust the size of the collected detection results, and perform denoising and grayscale processing; Data analysis and pre-judgment module: Analyze the processed data, judge whether there are potential safety hazards in the equipment, and predict the development trend of potential hazards in the equipment in the next period of time based on the analysis results combined with the production plan; 3D pre-judgment demonstration module: Display the operating conditions of various devices, and can also perform 3D simulation display of the analyzed development trend, which is convenient for the staff to formulate maintenance plans or adjust the production plan; Data storage module: Store the processed data, analysis results and operation data of the system; Control and management module: Centralized control and management of the data acquisition module, data processing module, data analysis and pre-judgment module, 3D pre-judgment demonstration module and data storage module, verify the identity information of the logged-in personnel, record the operation process of the system at the same time, and transmit the record to the data storage module.

2. The production environment danger pre-judgment system according to claim 1, characterized in that, The data acquisition module includes: Equipment monitoring unit: Installed on various devices in the thermal power plant to monitor the operating conditions of various devices in the thermal power plant; Patrol unit: Collect the detection data of the equipment detection unit and transmit it to the data processing module; Alarm unit: When the equipment monitoring unit monitors that the operating value of the equipment exceeds the threshold, it issues an alarm to remind the staff to handle it urgently.

3. The production environment danger prediction system according to claim 1, characterized in that, The data preprocessing module includes: Size adjustment unit: Adjust the size of the collected image data; Denoising unit: Perform denoising processing on the image data; Grayscale processing unit: Perform grayscale processing on the image data.

4. A production environment hazard prediction system as claimed in claim 1, wherein, The data analysis and pre-judgment module includes: Convolutional neural network 1: Analyze the processed image data to judge whether there are potential hazards in the equipment; LSTM neural network: Predict the development trend of potential hazards in the equipment in the next period of time based on the production plan and the analysis results of the convolutional neural network; Database: Store the training data of the convolutional neural network and the recurrent neural network.

5. A production environment hazard prediction system according to claim 1, characterized in that, The data storage module includes: Classification unit: Classify the data according to the data sending source; Storage unit: Store the classified data within a limited time; Management unit: Set the storage period of the data and delete the data that exceeds the storage period.

6. The production environment danger pre-judgment system according to claim 1, characterized in that, The control and management module includes: Verification unit: Verify the identity information of the logged-in personnel; Central control unit: Centralized control and management of the data acquisition module, data processing module, data analysis and pre-judgment module, 3D pre-judgment demonstration module and data storage module; Recording unit: Record the operation process of the system and transmit the record to the data storage module.

7. The production environment danger prediction system according to claim 2, wherein The patrol unit includes a drone (1), a shooting mechanism and a conveying mechanism. The shooting mechanism is installed on the drone (1), and a convolutional neural network 2 is arranged inside the drone (1). The conveying mechanism is located in the electromagnetic interference area to assist the drone (1) to move.

8. The production environment danger pre-judgment system according to claim 7, wherein The photographing mechanism includes a slide rail (2), an electric slider one (3), a high-definition camera (4), a millimeter-wave radar (5), and a gas monitor (6). The slide rail (2) is installed at the bottom of the unmanned aerial vehicle (1). The electric slider one (3) is slidably installed on the slide rail (2). The high-definition camera (4), the millimeter-wave radar (5), and the gas monitor (6) are all fixedly installed on the electric slider one (3).

9. The production environment hazard prediction system according to claim 7, characterized in that The conveying mechanism includes a silk thread (7), a magnetic metal block (8), a track (9), an electric slider two (10), a winding shaft (11), a driving motor (12), and an electromagnet (13). An electric winding shaft is arranged inside the unmanned aerial vehicle (1). The silk thread (7) is wound on the electric winding shaft. The magnetic metal block (8) is installed at one end of the silk thread (7), and the magnetic metal block (8) is located below the unmanned aerial vehicle (1). The track (9) is installed in the electromagnetic interference area inside the thermal power plant. The electric slider two (10) is slidably installed on the track (9), and a chamber is arranged inside the electric slider two (10). An opening is arranged at the top of the electric slider two (10). The winding shaft (11) is rotatably installed inside the electric slider two (10). The driving motor (12) is fixedly installed inside the electric slider two (10), and the output shaft of the driving motor (12) is connected to one end of the winding shaft (11). The electromagnet (13) is installed on the winding shaft (11).

10. A production environment danger prediction system according to claim 9, characterized in that, The other end of the winding shaft (11) is provided with a rotary joint (14).

Images