A method for intelligent monitoring, early warning and risk identification of hydrogen, oil and ammonia areas based on 5G technology

Abstract

The present invention discloses a method for intelligent monitoring, early warning and risk identification of hydrogen, oil and ammonia areas based on 5G technology. It utilizes the perception nodes formed by various sensor terminals in combination with NB-IOT technology to further improve the accuracy of on-site data collection, and conducts three-dimensional intelligent perception and data access to major hazard source data such as engineering vehicle operations, fire conditions, hydrogen, oil and ammonia areas, as well as personnel, resources, and environment information in thermal power plants. It has high fault tolerance and error correction capabilities, improves the safety management and risk early warning capabilities of thermal power plants, and reduces casualties and property losses in power plant accidents.

Description

Technical field:

[0001] The present invention is applied to the monitoring and early warning of major hazardous sources such as hydrogen, oil and ammonia areas in thermal power plants, and specifically relates to an intelligent monitoring and early warning and risk hazard identification method for hydrogen, oil and ammonia areas based on 5G technology. Background technology:

[0002] With the gradual improvement of the current refined management of thermal power plants, the requirements for work content in safety control, monitoring and early warning, and emergency response are also gradually deepening, with a focus on strengthening the dual management of hidden dangers and risks. However, in the monitoring and early warning of hydrogen, oil and ammonia areas of thermal power plants, the phenomenon of information islands is relatively obvious, and the communication methods based on the Internet of Things are constantly developing. With the development of 5G narrowband Internet of Things technology, new application models are brought to the collection of monitoring information. However, domestic research in the field of monitoring and early warning and hidden danger identification based on 5G narrowband Internet of Things technology is still in its infancy, with less research on thermal power plants, and even less research on accident monitoring and early warning and intelligent identification of hidden dangers in thermal power plants.

[0003] Therefore, conducting research and development of intelligent safety management and early warning technologies for major hazardous sources in thermal power plants based on 5G, combined with NB-IOT technology, has important theoretical and practical significance for further intelligent safety management, improving the safety management and risk early warning capabilities of thermal power plants, and reducing casualties and property losses in power plant accidents. Summary of the invention:

[0004] In order to solve the above problems, the present invention proposes a method for intelligent monitoring, early warning and risk identification of hydrogen, oil and ammonia areas based on 5G technology. Combined with NB-IOT technology, it performs three-dimensional intelligent perception and data access on major hazardous source data such as engineering vehicle operations, fire conditions, hydrogen, oil and ammonia areas in thermal power plants, as well as information such as personnel, resources, and the environment. It has high fault tolerance and error correction capabilities, improves the accuracy of on-site data collection, and improves the safety management and risk warning capabilities of thermal power plants.

[0005] In order to solve the above technical problems, the present invention proposes a method for intelligent monitoring, early warning and risk identification of hydrogen, oil and ammonia areas based on 5G technology, specifically:

[0006] Step 1: Use NB-IoT technology to collect basic data of the thermal power plant area;

[0007] Step 2: preprocess the collected data and perform multi-source fusion;

[0008] Step 3: construct a long-term and spatial risk anomaly identification and early warning model for the hydrogen, oil and ammonia areas of thermal power plants;

[0009] Step 4: Using the long-term and spatial risk anomaly identification and early warning model of the hydrogen, oil and ammonia area of ​​the thermal power plant, the real-time monitoring data and abnormal identification information are sent to the server through the 5G network to determine the early warning results;

[0010] Step 5: Evaluate the risk level based on the warning results;

[0011] Step 6: Issue early warnings in the production area through the 5G network based on the risk level assessment results;

[0012] Step 7: Push information via 5G network.

[0013] Furthermore, in step 1, the data types are divided into four categories: thermal power plant site data, including equipment name, equipment location, equipment quantity, and equipment capacity; meteorological environment data, including wind speed, wind direction, temperature and humidity, and air pressure at the thermal power plant site; gas concentration information, including hydrogen and ammonia gas concentrations and oxygen and carbon dioxide gas concentrations; pressure data, including pressure data of oil and gas storage tanks and valves.

[0014] Furthermore, in step 1, since the thermal power plant area is usually relatively large, in order to collect meteorological and environmental data more accurately, it is divided into N non-overlapping areas according to the layout of the thermal power plant area, where N>1; multiple collection devices are set in each area, and the collection devices in the area are networked and connected using NB-IoT technology to form N collection networks. Different collection networks are also interconnected using NB-IoT technology, where each collection network corresponds to a region and is responsible for collecting meteorological and environmental data in the region; different weights k are set for meteorological and environmental collection devices in different regions according to the size of the region. n , calculate the meteorological environment parameter M in the thermal power plant area, where the meteorological environment parameter M indicates whether the meteorological environment in the thermal power plant area meets the standard for safe production;

[0015] M=∑(k n ·M n ), where n∈N;

[0016] M n =α·S+(1-R)+β·(100-T)+1 / (Pa-1000);

[0017] M n are the meteorological environmental parameters in the nth region, where S represents wind speed, R represents humidity in the region, T represents temperature in the region, Pa represents air pressure in the region, and α and β are adjustment coefficients, which are adjusted differently according to the production season.

[0018] Furthermore, in step 2, the data preprocessing method includes first calibrating the thermal power plant site data, the thermal power plant site data, the meteorological environment data, the gas concentration information and the pressure data, and then converting the data format to convert all the data into a usable mode.

[0019] Furthermore, in step 3, based on the accident case collection and the experience accumulated by professional engineers and maintenance personnel in their daily work practice, the theory and experience are combined to analyze and derive a long-term and spatial risk anomaly identification and early warning model for the hydrogen, oil and ammonia areas of thermal power plants; through the analysis of the long-term and spatial risk anomaly identification and early warning model for the hydrogen, oil and ammonia areas of typical thermal power plants, the accident case analysis conclusions and the hidden danger judgments of professional engineers and maintenance personnel are quantified into numerical values ​​and calculation formulas, the early warning criteria are clarified, and a complete early warning mechanism is established.

[0020] Furthermore, in step 4, the automatically collected real-time data is stored through the long-term and spatiotemporal risk anomaly identification and early warning technology for the hydrogen, oil and ammonia areas of thermal power plants in step 3, and combined with the expert knowledge base and the common hidden danger database, the hidden danger early warning criteria established and maintained in the long-term and spatiotemporal risk anomaly identification and early warning model for the hydrogen, oil and ammonia areas of thermal power plants are calculated and analyzed to determine whether the early warning criteria are established, and the information of real-time monitoring, fire source identification and equipment abnormality identification is sent to the server through the 5G network to determine the early warning result.

[0021] Furthermore, in step 5, a risk index is determined according to the warning result. The risk index RPN is determined based on the possibility of risk occurrence P1, the severity of the result P2 and the identifiability of the risk P3, specifically: RPN = P1 × P2 × P3; the risk level is determined according to the risk index.

[0022] Furthermore, in step 6, based on the fast and low latency characteristics of the 5G network, data mining algorithms, artificial intelligence technology, and video image recognition and analysis systems are used to obtain hidden danger risk identification and warning information. According to the warning information, real-time monitoring and viewing of observation points where hidden dangers may occur in the hydrogen, oil, and ammonia areas are carried out. By checking the equipment that has issued the warning, it is determined whether it is caused by an abnormality in its upstream equipment and whether it will affect the operation of its downstream equipment. Combined with the artificial intelligence-based production area smoke and temperature warning technology, risks and hidden dangers in the production area can be avoided in advance and the loss of personnel and equipment can be reduced. Safety management is implemented in key protection danger areas such as hydrogen, oil, and ammonia, regular monitoring and inspection of the entire safety area is achieved, and key prevention safety areas are constructed.

[0023] Furthermore, in step 7, information push is specifically carried out by using the Internet of Things technology to conduct an impact analysis based on the fire location information and the leakage point information, and push it to the managers on the PC or mobile APP side through the 5G network to issue early warning prompts, prompting the managers to take emergency measures in time, dynamically analyze the demand for emergency materials, realize the rapid dispatch and emergency disposal of emergency resources, and ensure the production safety of the thermal power plant.

[0024] The advantages of the present invention are:

[0025] The present invention utilizes the sensing nodes formed by various sensor terminals and 5G technologies such as NB-IoT, through regional collection, grid management, and collaborative processing of all areas, to improve the accuracy of on-site data collection. It uses a similar calculation algorithm for adjacent areas to obtain the collected data of the fault area in a timely manner, improves the fault tolerance of the system, and performs three-dimensional intelligent perception and data access on major hazardous source data such as fire conditions, hydrogen, oil and ammonia areas, and personnel, resources, and environment information in thermal power plants. It has high fault tolerance and error correction capabilities, standardizes and visualizes the collected data, realizes multi-platform and multi-business docking, scientific data early warning, comprehensive command and rescue disposal, and cross-departmental multi-network linkage, strengthens the construction of information interaction and coordination mechanisms, and improves the production safety, risk early warning, and emergency response capabilities of thermal power plants. Description of the drawings:

[0026] Figure 1 It is an intelligent monitoring, early warning and risk identification method for hydrogen, oil and ammonia areas based on 5G technology. Specific implementation method:

[0027] The present invention will be further described below in conjunction with the accompanying drawings and specific implementation methods.

[0028] Figure 1 The intelligent monitoring, early warning and risk identification method of hydrogen, oil and ammonia areas based on 5G technology is demonstrated.

[0029] Step 1: Use NB-IoT technology to collect basic data such as the hydrogen, oil and ammonia areas of the power plant.

[0030] The data types are divided into four categories: thermal power plant site data, including equipment name, equipment location, equipment quantity, and equipment capacity; meteorological environment data, including wind speed, wind direction, temperature, humidity, and air pressure at the thermal power plant site; gas concentration information, including hydrogen and ammonia gas concentrations, and oxygen and carbon dioxide gas concentrations; pressure data, including oil and gas storage tanks and valve pressure data. Due to the different sources and storage forms of these data, the data collection methods are also different.

[0031] Since the plant area of ​​a thermal power plant is usually large, in order to collect meteorological and environmental data more accurately, it is divided into N non-overlapping areas according to the layout of the thermal power plant area, where N>1; multiple collection devices are set up in each area, and the collection devices in the area are networked and connected using NB-IoT technology to form N collection networks. Different collection networks are also interconnected using NB-IoT technology, where each collection network corresponds to a region and is responsible for collecting meteorological and environmental data in the region; different weights k are set for meteorological and environmental collection devices in different regions according to the size of the region. n , calculate the meteorological environment parameter M in the thermal power plant area, where the meteorological environment parameter M indicates whether the meteorological environment in the thermal power plant area meets the standard for safe production;

[0032] M=∑(k n ·M n ), where n∈N;

[0033] M n =α·S+(1-R)+β·(100-T)+1 / (Pa-1000),

[0034] M n are the meteorological environmental parameters in the nth region, where S represents wind speed, R represents humidity in the region, T represents temperature in the region, Pa represents air pressure in the region, and α and β are adjustment coefficients, which are adjusted differently according to the production season.

[0035] Furthermore, if the meteorological environment collection equipment in a certain area fails, in order to ensure that the data collection process in the entire factory is not affected, the meteorological environment parameter W of the faulty area is estimated based on the results collected by the collection equipment in the adjacent area by using the similarity calculation algorithm of the adjacent area.

[0036] W=(∑(W neighbors ·p neighbors )) / i

[0037] p neighbors is the similarity of adjacent regions, p neighbors The value of is any real number between 0 and 1, which is determined by the size of the adjacent area and the number of production equipment between the adjacent areas. If the size of the fault area and the number of production equipment between the adjacent areas are closer, the neighbors The closer it is to 1, the closer it is to 0; neighbors is the meteorological environment parameter of the area adjacent to the fault area, which can take any value, and i represents the number of areas adjacent to the fault area. When a fault occurs in a certain area, the meteorological environment data of the entire plant area can be obtained based on the meteorological environment parameters of the adjacent areas to ensure normal production operations and improve the fault tolerance of the system.

[0038] Furthermore, gas collection sensors are used to collect relevant parameters of toxic and flammable gases such as hydrogen and ammonia in the thermal power plant area. According to the relevant parameters of the gases in different areas, the relevant parameters of the gases in the entire plant area are calculated. When the relevant parameters of the toxic and flammable gases in a certain area or in the entire plant area exceed the threshold value for safe production, it can be determined that a toxic and flammable gas leak has occurred.

[0039] Step 2: Select, preprocess and integrate the collected data.

[0040] Furthermore, data selection is the first step in multi-source data fusion, and the correctness of data selection must be ensured. Processing is done by selecting high-quality data objects in the hydrogen, oil and ammonia area of ​​the thermal power plant.

[0041] Furthermore, after the data is reasonably selected, it must be preprocessed first to prevent the unprocessed data from affecting the fusion effect during multi-source fusion, so that the fused data cannot meet the early warning monitoring requirements of the hydrogen, oil and ammonia area of ​​the thermal power plant. The data preprocessing method mainly includes first calibrating the thermal power plant site data, thermal power plant site data, meteorological environment data, gas concentration information and pressure data, and then converting the data format to convert all the data into a usable mode.

[0042] Furthermore, data fusion is performed. During the data fusion operation, image processing methods can be used to fuse the pre-processed data. Data fusion technologies such as decision-level fusion can be used to fuse multi-source data after processing.

[0043] Step 3: Construct a long-term and spatial risk anomaly identification and early warning model for the hydrogen, oil and ammonia areas of thermal power plants.

[0044] Furthermore, based on the experts' professional knowledge, accident case analysis and the experience accumulated by professional engineers and maintenance personnel in their daily work practices, the theory and experience are combined to analyze and summarize a set of long-term and spatial risk anomaly identification and early warning models for hydrogen, oil and ammonia areas of typical thermal power plants, including safety hazard signs, analysis, solutions, etc. Through the analysis and formula quantification of the long-term and spatial risk anomaly identification and early warning model for hydrogen, oil and ammonia areas of typical thermal power plants, the experts' knowledge, accident case analysis conclusions and the hidden danger judgments of professional engineers and maintenance personnel are quantified into a series of clear early warning criteria such as data and calculation formulas, and a complete early warning mechanism is established.

[0045] Step 4: Utilize the long-term and spatial risk anomaly identification and early warning model for the hydrogen, oil and ammonia areas of thermal power plants to send real-time monitoring data and anomaly identification information to the server through the 5G network to determine the early warning results.

[0046] Furthermore, through the long-term and spatial risk anomaly identification and early warning technology for the hydrogen, oil and ammonia areas of thermal power plants in step 3, the automatically collected real-time data is stored, combined with the expert knowledge base and the common hidden danger database, and then calculated and analyzed according to the hidden danger warning criteria established and maintained in the long-term and spatial risk anomaly identification and early warning model for the hydrogen, oil and ammonia areas of thermal power plants to determine whether the warning criteria are established, and the real-time monitoring data, fire source identification and equipment abnormality identification information are sent to the server through the 5G network to determine the warning results.

[0047] Step 5: Assess the risk level based on the early warning results.

[0048] Further, the risk index is determined based on the early warning results. The determination of the risk index RPN is based on the possibility of risk occurrence P1, the severity of the result P2 and the identifiability of the risk P3. P1, P2 and P3 are determined by the early warning results. The risk index RPN = possibility of occurrence × severity of the result × identifiability of the risk. The risk level is determined based on the risk index. Risk level: A score of less than 20 points is low risk, 20-30 points is medium risk, and greater than 30 points is high risk. Low risk with RPN of less than 20 points is a reasonably acceptable risk.

[0049] Step 6: Issue early warnings in production areas through the 5G network based on risk level assessment results.

[0050] Furthermore, based on the fast and low-latency characteristics of the 5G network, data mining algorithms, artificial intelligence technology, and video image recognition and analysis systems are used to obtain hidden danger risk identification and warning information. According to the warning information, real-time monitoring and viewing of observation points where hidden dangers may occur in the hydrogen, oil, and ammonia areas are carried out. By checking the equipment that has issued the warning, it is determined whether it is caused by an abnormality in its upstream equipment and whether it will affect the operation of its downstream equipment. Combined with the artificial intelligence-based production area smoke and temperature warning technology, risks and hidden dangers in the production area can be avoided in advance and the loss of personnel and equipment can be reduced. Safety management is implemented in key protection danger areas such as hydrogen, oil, and ammonia, regular monitoring and inspection of the entire safety area is achieved, and key prevention safety areas are constructed.

[0051] Step 7: Push information via 5G network.

[0052] Furthermore, IoT technology is used to conduct impact analysis based on fire location information and leakage point information, and push it to managers on the PC or mobile APP side through the 5G network to issue early warning prompts, prompting managers to take emergency measures in a timely manner, dynamically analyze emergency material needs, and achieve rapid dispatch and emergency response of emergency resources to ensure the production safety of thermal power plants.

[0053] In summary, although the basic structure, principle and method of the present invention are specifically described through the above examples, it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, several simple deductions or substitutions can be made without departing from the concept of the present invention.

Claims

1. A method for intelligent monitoring, early warning and risk identification of hydrogen, oil and ammonia areas based on 5G technology. It is characterized in that The steps include: Step 1: Use NB-IoT technology to collect basic data of the thermal power plant area using data collection and monitoring equipment. The data types are divided into four categories: thermal power plant site data, meteorological environment data, gas concentration information, and pressure data; Step 2, preprocessing and multi-source fusion of the collected data; the data preprocessing method includes first calibrating the thermal power plant site data, meteorological environment data, gas concentration information and pressure data, and then converting the data format to convert all the data into a usable mode; Step 3: construct a long-term and spatial risk anomaly identification and early warning model for the hydrogen, oil and ammonia areas of thermal power plants; Step 4: Using the long-term and spatial risk anomaly identification and early warning model of the hydrogen, oil and ammonia area of ​​the thermal power plant, the real-time monitoring data and abnormal identification information are sent to the server through the 5G network to determine the early warning results; Step 5: Evaluate the risk level based on the warning results; Step 6: Issue early warnings in the production area through the 5G network based on the risk level assessment results; Step 7: Push information via 5G network; In step 1, according to the layout of the thermal power plant, it is divided into N non-overlapping areas, where N>1; multiple collection devices are set in each area, and the collection devices in the area are networked and connected using NB-IoT technology to form N collection networks. Different collection networks are also interconnected using NB-IoT technology, where each collection network corresponds to a region and is responsible for collecting meteorological and environmental data in the region; different weights k are set for meteorological and environmental collection devices in different regions according to the size of the region. n , calculate the meteorological environment parameter M in the thermal power plant area, where the meteorological environment parameter M indicates whether the meteorological environment in the thermal power plant area meets the standard for safe production; M=∑(k n ·M n ), where n∈N; M n =α·S+(1-R)+β·(100-T)+1 / (Pa-1000); M n is the meteorological environment parameter of the nth region, where S represents wind speed, R represents humidity in the region, T represents temperature in the region, Pa represents air pressure in the region, and α and β are adjustment coefficients, which are adaptively adjusted according to different production seasons.

2. According to the 5G technology-based intelligent monitoring, early warning and risk identification method for hydrogen, oil and ammonia areas in claim 1, Features: In step 2, data fusion also includes: using image processing means to fuse the pre-processed multiple data during the data fusion operation, and using decision-level fusion data fusion technology to perform multi-source data fusion on the processed data.

3. The method for intelligent monitoring, early warning and risk identification of hydrogen, oil and ammonia areas based on 5G technology as claimed in claim 1, Features: In step 3, based on the accident case collection and the experience accumulated by professional engineers and maintenance personnel in their daily work practice, the theory and experience are combined to analyze and derive a long-term and spatial risk anomaly identification and early warning model for the hydrogen, oil and ammonia areas of thermal power plants; through the analysis of the long-term and spatial risk anomaly identification and early warning model for the hydrogen, oil and ammonia areas of typical thermal power plants, the accident case analysis conclusions and the hidden danger judgments of professional engineers and maintenance personnel are quantified into numerical values ​​and calculation formulas, the early warning criteria are clarified, and a complete early warning mechanism is established.

4. The method for intelligent monitoring, early warning and risk identification of hydrogen, oil and ammonia areas based on 5G technology as claimed in claim 1, Features: In step 4, the automatically collected real-time data is stored through the long-term and spatial risk anomaly identification and early warning technology for the hydrogen, oil and ammonia areas of thermal power plants in step 3, and combined with the expert knowledge base and the common hidden danger database, the hidden danger early warning criteria established and maintained in the long-term and spatial risk anomaly identification and early warning model for the hydrogen, oil and ammonia areas of thermal power plants are calculated and analyzed to determine whether the early warning criteria are established, and the real-time monitoring data, fire source identification information and equipment abnormality identification information are sent to the server through the 5G network to determine the early warning results.

5. The method for intelligent monitoring, early warning and risk identification of hydrogen, oil and ammonia areas based on 5G technology as claimed in claim 1, Features: In step 5, the risk index is determined according to the warning results. The risk index RPN is determined based on the possibility of risk occurrence P1, the severity of the result P2 and the identifiability of the risk P3, specifically: RPN = P1 × P2 × P3; The risk level is determined based on the risk index.

6. The method for intelligent monitoring, early warning and risk identification of hydrogen, oil and ammonia areas based on 5G technology as claimed in claim 1, Features: In step 6, based on the fast and low latency characteristics of the 5G network, data mining algorithms, artificial intelligence technology, and video image recognition and analysis systems are used to obtain hidden danger risk identification and warning information. According to the warning information, real-time monitoring and viewing of observation points where hidden dangers may occur in the hydrogen, oil, and ammonia areas are carried out. By checking the equipment that has issued the warning, it is determined whether it is caused by an abnormality in its upstream equipment and whether it will affect the operation of its downstream equipment. Combined with the artificial intelligence-based production area smoke and temperature warning technology, risks in the production area can be avoided in advance and the loss of personnel and equipment can be reduced. Safety management is implemented in the key protection danger areas of hydrogen, oil, and ammonia, regular monitoring and inspection of the entire safety area is achieved, and key prevention safety areas are constructed.

7. The method for intelligent monitoring, early warning and risk identification of hydrogen, oil and ammonia areas based on 5G technology as claimed in claim 1, Features: In step 7, information push is specifically carried out by using IoT technology to conduct impact analysis based on fire location information and leakage point information, and push it to managers on the PC or mobile APP side through the 5G network to issue early warning prompts, prompting managers to take emergency measures in a timely manner, dynamically analyze emergency material needs, realize rapid dispatch and emergency disposal of emergency resources, and ensure the production safety of thermal power plants.

Images