An alarm device for multi-scenario energy safety monitoring and its use method

Abstract

The present invention discloses an alarm device for multi-scenario energy safety monitoring and a method of using the same, including an installation box, a collection component installed on the top of the installation box, the collection component including an infrared camera, an infrared thermal imaging, a temperature and humidity sensor, and a gas sensor, the collection component is used to collect oil depot operation data, and a control mainboard is installed on the back of the inner cavity of the installation box. The present invention achieves the effect of real-time monitoring and early warning of the environment around the oil depot by setting a collection component, a control mainboard, an early warning component, and a transmission module. The field data is collected in real time by an infrared camera, an infrared thermal imaging, a temperature and humidity sensor, and a gas sensor. The collection component sends the collected data to the control mainboard, so that abnormal situations can be judged in time. Early warning information can be issued in time through the early warning component and the transmission module, so that the staff can be notified in time to take corresponding measures to reduce the loss of accidents.

Description

Technical Field

[0001] The present invention relates to the technical field of alarm devices for energy security monitoring, and specifically to an alarm device for multi-scenario energy security monitoring and a method of using the same. Background Art

[0002] Energy refers to resources that can provide energy, including various forms of energy sources, such as coal, oil, natural gas, electricity, etc. Energy is prone to store safety hazards during storage. In order to reduce the occurrence of safety accidents, real-time safety monitoring of the surrounding environment and equipment of energy storage is usually carried out. Especially in the oil and gas storage environment, due to its flammable and explosive characteristics, any small safety hazard may bring huge risks. In order to ensure the safety of oil storage, monitoring devices will be deployed in oil depots to detect hidden dangers in advance and take timely measures to reduce losses;

[0003] According to the Chinese patent application number: 202222931575.8, a remote safety monitoring and alarm device for oil depot storage and transportation is disclosed, including a controller host, a display is installed on the outer surface of the controller host, a 4G module and a main control board are installed inside the controller host, a 4G antenna is provided at the outer top of the controller host, and a power cord, a 485 interface, a detector 1 and a detector 2 and an alarm are sequentially arranged at the outer bottom of the controller host. The outer surface of the power cord is wrapped with a shielding layer, and the PVC sleeve 1 is filled with glass fiber, thereby increasing its insulation performance, heat resistance, corrosion resistance and mechanical strength, improving the safety performance and service life of the power supply, and the fire-resistant layer is a double-layer mica tape wrapped layer, so the fire resistance of the entire wire is greatly increased, in order to enhance the tensile strength of the power cord;

[0004] The existing technology effectively solves the problem that when the power cord of the monitoring alarm device is pulled, it will cause the power cord to break, causing the entire equipment to stop working, thereby affecting the efficiency of the monitoring alarm. It has the advantage of being able to increase the pulling force of the wire, thereby improving the efficiency of the monitoring alarm. However, the monitoring of this type of energy safety monitoring alarm device is relatively single and can only monitor environmental gases, which is not conducive to being deployed at any location in the oil depot, thereby reducing the use effect of the monitoring device. Summary of the invention

[0005] The purpose of the present invention is to provide an alarm device for multi-scenario energy security monitoring and a method of using the same, which has the advantages of multi-scenario monitoring and early warning of energy security, and solves the problem that the energy security monitoring alarm device has a relatively single monitoring function and can only monitor environmental gases, which is not conducive to being deployed at any location in an oil depot, thereby reducing the use effect of the monitoring device.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an alarm device for multi-scenario energy safety monitoring, comprising an installation box, a collection component is installed on the top of the installation box, the collection component includes an infrared camera, an infrared thermal imaging, a temperature and humidity sensor and a gas sensor, the collection component is used to collect oil depot operation data, a control mainboard is installed on the back of the inner cavity of the installation box, the control mainboard is used to analyze and process the operation data, an early warning component is installed on the surface of the installation box, the early warning component includes an audible and visual alarm and a display, the early warning component is used for early warning prompts, a transmission module is installed on one side of the inner cavity of the installation box, the transmission module is used for remote transmission, the output end of the collection component is connected to the input end of the control mainboard, the output end of the control mainboard is distributed and connected to the input end of the early warning component and the transmission module, and the output end of the transmission module is connected to the input end of the remote terminal.

[0007] Preferably, the control main board is provided with a data analysis module and a data storage module, and the data storage module adopts cloud storage to store historical operation data.

[0008] Preferably, the data analysis module has an AI algorithm to analyze the running data, and the running steps of the data analysis module include data preprocessing, feature extraction and model training, and the AI ​​algorithm uses an isolation forest algorithm to monitor outliers.

[0009] Preferably, the operating principle of the AI ​​algorithm is:

[0010] First, assume that the data set has N data, build an iTree tree, uniformly sample from the N data, and take out ψ samples as the training samples of this tree;

[0011] Then randomly select a feature in the sample, and randomly select a value within the range of all values ​​of this feature, perform binary partitioning on the sample, and divide the sample with values ​​less than the value to the left of the node, and divide the sample with values ​​greater than or equal to the value to the right of the node, so as to obtain a splitting condition and left and right data sets, and then repeat the above process on the left and right data sets respectively, and directly reach the termination condition. There are two termination conditions: one is that the data itself cannot be divided any more, and the other is that the height of the tree reaches log2(ψ);

[0012] Then, the data is predicted through the established iTree tree, and the test data is moved down along the corresponding conditional branch on the iTree tree until it reaches the leaf node, and the path length h(x) passed in the process is recorded, that is, the number of edges passed from the root node, through the middle node, and finally to the leaf node;

[0013] Finally, h(x) is substituted in to calculate the anomaly score of each piece of data to be tested. The calculation formula is:

[0014]

[0015] The average path length of the tree is c(n):

[0016]

[0017] Where H(i) is the harmonic number, which can be estimated as ln(i)+0.5772156649, and c(n) is the average path length for a given sample number n, which is used to standardize the path length h(x) of sample x.

[0018] Preferably, the data preprocessing includes data cleaning, data standardization and data filling, and the feature extraction includes time series features, environmental features and equipment features.

[0019] Preferably, an electric pan-tilt head is fixedly connected to the top of the installation box, the infrared camera and infrared thermal imaging are respectively installed on both sides of the top of the electric pan-tilt head, and the temperature and humidity sensor and gas sensor are respectively fixed on both sides of the top of the installation box.

[0020] Preferably, the display is embedded in the surface of the installation box, the sound and light alarm is fixed on the top of the installation box, and the transmission module adopts a wireless communication module.

[0021] Preferably, the method of use comprises the following steps:

[0022] a) First, a safety monitoring model is built through AI algorithms. The model is used to achieve real-time monitoring and early warning of on-site operation data. The on-site operation data is collected through the acquisition component. The analysis module pre-processes the operation data through data cleaning, data standardization and data filling. Then, features related to safety monitoring are extracted through time series features, environmental features and equipment features.

[0023] b) Then, an isolation forest model is constructed based on the isolation forest algorithm, and the parameters of the isolation forest model are set. The isolation forest model is trained using the preprocessed data. The model constructs multiple isolated trees. Each tree divides the data by randomly selecting features and split points. For each data point, the path length in each isolated tree is calculated using a formula. The anomaly score of each data point is calculated. The closer the score is, the more likely it is an anomaly point. The anomaly detection threshold is set according to actual needs. The trained isolation forest model is deployed in a security monitoring environment to monitor data flow in real time.

[0024] c) During operation, the surrounding environment data is collected in real time through infrared cameras, infrared thermal imaging, temperature and humidity sensors, and gas sensors. The collection component sends the collected data to the control main board, and the control main board uses AI algorithms for real-time monitoring, so that abnormal situations can be judged in time. When the control main board determines the abnormal data, an alarm is issued through the sound and light alarm, and the display can display various operating data in real time. When the sound and light alarm issues an alarm, the control main board sends an alarm message to the remote terminal through the transmission module. Through the cooperation of the collection component, the control main board, the early warning component and the transmission module, multi-scenario monitoring of the oil depot environment can be realized, so that it can be deployed at any location in the oil depot.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] The present invention achieves the effect of real-time monitoring and early warning of the environment around the oil depot by setting up a collection component, a control main board, an early warning component and a transmission module. The field data is collected in real time through an infrared camera, infrared thermal imaging, a temperature and humidity sensor and a gas sensor. The collection component sends the collected data to the control main board, and the control main board uses an AI algorithm to perform real-time monitoring, so that abnormal situations can be judged in time. Early warning information can be issued in time through the early warning component and the transmission module, so that the staff can be notified in time to take corresponding measures to reduce the loss of the accident. The field data is collected in real time through an infrared camera, infrared thermal imaging, a temperature and humidity sensor and a gas sensor. The collection component sends the collected data to the control main board, and the control main board uses an AI algorithm to perform real-time monitoring, so that abnormal situations can be judged in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic diagram of the main structure of the present invention;

[0028] Figure 2 It is a schematic cross-sectional structural diagram of the installation box of the present invention;

[0029] Figure 3 It is a schematic diagram of the system flow of the present invention;

[0030] Figure 4 Schematic diagram of the data analysis process of the present invention.

[0031] In the figure: 1. Installation box; 2. Collection component; 201. Infrared camera; 202. Infrared thermal imaging; 203. Temperature and humidity sensor; 204. Gas sensor; 3. Control main board; 4. Early warning component; 401. Sound and light alarm; 402. Display; 5. Transmission module; 6. Electric pan / tilt head. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] The installation box 1, collection component 2, infrared camera 201, infrared thermal imaging 202, temperature and humidity sensor 203, gas sensor 204, control main board 3, early warning component 4, sound and light alarm 401, display 402, transmission module 5 and electric pan / tilt head 6 of the present invention are all universal standard parts or parts known to those skilled in the art, and their structures and principles can be known to those skilled in the art through technical manuals or through conventional experimental methods.

[0034] Example 1

[0035] like Figure 1-4 As shown, it is the first embodiment of the present invention, which provides an alarm device for multi-scenario energy security monitoring and a method of using the same, including an installation box 1, a collection component 2 is installed on the top of the installation box 1, the collection component 2 includes an infrared camera 201, an infrared thermal imaging 202, a temperature and humidity sensor 203 and a gas sensor 204, the collection component 2 is used to collect oil depot operation data, a control mainboard 3 is installed on the back of the inner cavity of the installation box 1, the control mainboard 3 is used to analyze and process the operation data, an early warning component 4 is installed on the surface of the installation box 1, the early warning component 4 includes an audible and visual alarm 401 and a display 402, the early warning component 4 is used for early warning prompts, a transmission module 5 is installed on one side of the inner cavity of the installation box 1, the transmission module 5 is used for remote transmission, the output end of the collection component 2 is connected to the input end of the control mainboard 3, the output end of the control mainboard 3 is distributed and connected to the input end of the early warning component 4 and the transmission module 5, and the output end of the transmission module 5 is connected to the input end of the remote terminal.

[0036] like Figure 1-4As shown, a safety monitoring model is constructed, and real-time monitoring and early warning of on-site operation data are achieved through the model. On-site data is collected in real time through infrared cameras 201, infrared thermal imaging 202, temperature and humidity sensors 203, and gas sensors 204. The collection component 2 sends the collected data to the control mainboard 3, and the control mainboard 3 uses the AI ​​algorithm to perform real-time monitoring, so that abnormal situations can be judged in time. When the control mainboard 3 judges abnormal data, an alarm is issued through the sound and light alarm 401, and the display 402 can display various operation data in real time. When the sound and light alarm 401 issues an alarm, the control mainboard 3 sends an alarm message to the remote terminal through the transmission module 5. Through the cooperation of the collection component 2, the control mainboard 3, the early warning component 4 and the transmission module 5, multi-scenario monitoring of the oil depot environment can be realized, so that it can be deployed at any location in the oil depot.

[0037] Example 2

[0038] Reference Figure 3 and 4 , which is the second embodiment of the present invention, and this embodiment is based on the previous embodiment.

[0039] In this embodiment, the control mainboard 3 is provided with a data analysis module and a data storage module. The data storage module adopts cloud storage to store historical operation data.

[0040] The data analysis module has AI algorithm to analyze the running data. The operation steps of the data analysis module include data preprocessing, feature extraction and model training, and the AI ​​algorithm uses isolation forest algorithm to monitor outliers.

[0041] The operating principle of the AI ​​algorithm is:

[0042] First, assume that the data set has N data, build an iTree tree, uniformly sample from the N data, and take out ψ samples as the training samples of this tree;

[0043] Then randomly select a feature in the sample, and randomly select a value within the range of all values ​​of this feature, perform binary partitioning on the sample, and divide the sample with values ​​less than the value to the left of the node, and divide the sample with values ​​greater than or equal to the value to the right of the node, so as to obtain a splitting condition and left and right data sets, and then repeat the above process on the left and right data sets respectively, and directly reach the termination condition. There are two termination conditions: one is that the data itself cannot be divided any more, and the other is that the height of the tree reaches log2(ψ);

[0044] Then, the data is predicted through the established iTree tree, and the test data is moved down along the corresponding conditional branch on the iTree tree until it reaches the leaf node, and the path length h(x) passed in the process is recorded, that is, the number of edges passed from the root node, through the middle node, and finally to the leaf node;

[0045] Finally, h(x) is substituted in to calculate the anomaly score of each piece of data to be tested. The calculation formula is:

[0046]

[0047] The average path length of the tree is c(n):

[0048]

[0049] Where H(i) is the harmonic number, which can be estimated as ln(i)+0.5772156649, and c(n) is the average path length for a given sample number n, which is used to standardize the path length h(x) of sample x.

[0050] like Figure 3 and 4 As shown, it can be seen from the calculation that when Ehx→cn, s→0.5, that is, when the average path length of sample x is close to the average path length of the tree, it cannot be distinguished whether it is an abnormality. When Ehx→0, s→1, that is, when the anomaly score of x is close to 1, it is judged to be abnormal. When Ehx→n-1, s→0, it is judged to be normal. Data cleaning is used to remove duplicate data, data standardization is used to convert data of different scales into a unified standard, and data filling is used to supplement missing data. Feature data related to safety monitoring is selected through feature extraction, and then the preprocessed data is analyzed and monitored through the model.

[0051] Example 3

[0052] Reference Figure 1 and 2 , which is the third embodiment of the present invention, and this embodiment is based on the previous two embodiments.

[0053] In this embodiment, the top of the installation box 1 is fixedly connected to an electric pan-tilt head 6, the infrared camera 201 and the infrared thermal imaging 202 are respectively installed on both sides of the top of the electric pan-tilt head 6, and the temperature and humidity sensor 203 and the gas sensor 204 are respectively fixed on both sides of the top of the installation box 1.

[0054] The display 402 is embedded on the surface of the installation box 1, the sound and light alarm 401 is fixed on the top of the installation box 1, and the transmission module 5 adopts a wireless communication module.

[0055] like Figure 1 and 2As shown, the monitoring directions of the infrared camera 201 and the infrared thermal imaging 202 can be adjusted by the electric pan / tilt head 6, so that the infrared camera 201 and the infrared thermal imaging 202 can perform real-time monitoring of positions at different angles. The infrared camera 201 is used to photograph the surrounding environment, and the infrared thermal imaging 202 can perform infrared detection on the on-site pipeline equipment, so as to judge the operation status of the equipment. The gas sensor 204 can detect the gas in the surrounding environment, so as to find out whether there is a leak. The display 402 can display the data collected by the collection component 2 in real time, which is convenient for inspection personnel to view.

[0056] A method for using an alarm device for multi-scenario energy safety monitoring, the method comprising the following steps:

[0057] a) First, a safety monitoring model is constructed through the AI ​​algorithm. The model is used to implement real-time monitoring and early warning of on-site operation data. The on-site operation data is collected through the acquisition component 2. The analysis module pre-processes the operation data through data cleaning, data standardization and data filling. Then, features related to safety monitoring are extracted through time series features, environmental features and equipment features.

[0058] b) Then, an isolation forest model is constructed based on the isolation forest algorithm, and the parameters of the isolation forest model are set. The isolation forest model is trained using the preprocessed data. The model constructs multiple isolated trees. Each tree divides the data by randomly selecting features and split points. For each data point, the path length in each isolated tree is calculated using a formula. The anomaly score of each data point is calculated. The closer the score is to 1, the more likely it is an anomaly point. The threshold for anomaly detection is set according to actual needs. The trained isolation forest model is deployed in a security monitoring environment to monitor data flow in real time.

[0059] c) During operation, the surrounding environment data is collected in real time through the infrared camera 201, infrared thermal imaging 202, temperature and humidity sensor 203 and gas sensor 204. The collection component 2 sends the collected data to the control main board 3. The control main board 3 uses the AI ​​algorithm to perform real-time monitoring, so that abnormal situations can be judged in time. When the control main board 3 determines the abnormal data, an alarm is issued through the sound and light alarm 401, and the display 402 can display various operating data in real time. When the sound and light alarm 401 issues an alarm, the control main board 3 sends an alarm message to the remote terminal through the transmission module 5. Through the cooperation of the collection component 2, the control main board 3, the early warning component 4 and the transmission module 5, multi-scenario monitoring of the oil depot environment can be realized, so that it can be deployed at any location in the oil depot.

[0060] The standard parts used in this application document can all be purchased from the market and can be customized according to the description in the specification and drawings. The specific connection methods of each part adopt conventional means such as mature bolts, rivets, welding, etc. in the prior art. The machinery, parts and equipment all adopt conventional models in the prior art. The control method is automatic control through a controller. The control circuit of the controller can be implemented through simple programming by technicians in this field, which is common knowledge in the field. This application is mainly used to protect mechanical devices, so this application no longer explains the control method and circuit connection in detail.

[0061] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0062] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An alarm device for multi-scenario energy safety monitoring, comprising an installation box (1), characterized in that: A collection component (2) is installed on the top of the installation box (1), the collection component (2) comprising an infrared camera (201), an infrared thermal imaging device (202), a temperature and humidity sensor (203) and a gas sensor (204), the collection component (2) being used to collect oil depot operation data, a control mainboard (3) is installed on the back of the inner cavity of the installation box (1), the control mainboard (3) being used to analyze and process the operation data, an early warning component (4) is installed on the surface of the installation box (1), the early warning component (4) comprising an audible and visual alarm (401) and a display (402), the early warning component (4) being used to provide early warning prompts, a transmission module (5) is installed on one side of the inner cavity of the installation box (1), the transmission module (5) being used for remote transmission, the output end of the collection component (2) being connected to the input end of the control mainboard (3), the output end of the control mainboard (3) being connected to the input end of the early warning component (4) and the transmission module (5), the output end of the transmission module (5) being connected to the input end of the remote terminal.

2. The multi-scenario energy security monitoring alarm device according to claim 1, characterized in that: The control mainboard (3) is provided with a data analysis module and a data storage module, and the data storage module adopts cloud storage for storing historical operation data.

3. The multi-scenario energy security monitoring alarm device according to claim 2 is characterized in that: The data analysis module has an AI algorithm to analyze the running data. The running steps of the data analysis module include data preprocessing, feature extraction and model training, and the AI ​​algorithm uses an isolation forest algorithm to monitor outliers.

4. The multi-scenario energy security monitoring alarm device according to claim 3 is characterized in that: The operating principle of the AI ​​algorithm is: First, assume that the data set has N data, build an iTree tree, uniformly sample from the N data, and take out ψ samples as the training samples of this tree; Then randomly select a feature in the sample, and randomly select a value within the range of all values ​​of this feature, perform binary partitioning on the sample, and divide the sample with values ​​less than the value to the left of the node, and divide the sample with values ​​greater than or equal to the value to the right of the node, so as to obtain a splitting condition and left and right data sets, and then repeat the above process on the left and right data sets respectively, and directly reach the termination condition. There are two termination conditions: one is that the data itself cannot be divided any more, and the other is that the height of the tree reaches log2(ψ); Then, the data is predicted through the established iTree tree, and the test data is moved down along the corresponding conditional branch on the iTree tree until it reaches the leaf node, and the path length h(x) passed in the process is recorded, that is, the number of edges passed from the root node, through the middle node, and finally to the leaf node; Finally, h(x) is substituted in to calculate the anomaly score of each piece of data to be tested. The calculation formula is: The average path length of the tree is c(n): Where H(i) is the harmonic number, which can be estimated as ln(i)+0.5772156649, and c(n) is the average path length for a given sample number n, which is used to standardize the path length h(x) of sample x.

5. The multi-scenario energy security monitoring alarm device according to claim 3 is characterized in that: The data preprocessing includes data cleaning, data standardization and data filling, and the feature extraction includes time series features, environmental features and equipment features.

6. The multi-scenario energy security monitoring alarm device according to claim 1 is characterized in that: The top of the installation box (1) is fixedly connected to an electric pan-tilt head (6); the infrared camera (201) and the infrared thermal imaging device (202) are respectively installed on two sides of the top of the electric pan-tilt head (6); and the temperature and humidity sensor (203) and the gas sensor (204) are respectively fixed on two sides of the top of the installation box (1).

7. The multi-scenario energy security monitoring alarm device according to claim 1 is characterized in that: The display (402) is embedded in the surface of the installation box (1), the sound and light alarm (401) is fixed on the top of the installation box (1), and the transmission module (5) adopts a wireless communication module.

8. A method for using a multi-scenario energy security monitoring alarm device according to any one of claims 1 to 7, characterized in that: The method of use includes the following steps: a) First, a safety monitoring model is constructed through an AI algorithm. The model is used to implement real-time monitoring and early warning of on-site operation data. The on-site operation data is collected through the acquisition component (2). The analysis module pre-processes the operation data through data cleaning, data standardization, and data filling. Then, features related to safety monitoring are extracted through time series features, environmental features, and equipment features. b) Then, an isolation forest model is constructed based on the isolation forest algorithm, and the parameters of the isolation forest model are set. The isolation forest model is trained using the preprocessed data. The model constructs multiple isolated trees. Each tree divides the data by randomly selecting features and split points. For each data point, the path length in each isolated tree is calculated using a formula. The anomaly score of each data point is calculated. The closer the score is to 1, the more likely it is an anomaly point. The threshold for anomaly detection is set according to actual needs. The trained isolation forest model is deployed in a security monitoring environment to monitor data flow in real time. c) During operation, the surrounding environment data is collected in real time through the infrared camera (201), infrared thermal imaging (202), temperature and humidity sensor (203) and gas sensor (204). The collection component (2) sends the collected data to the control main board (3). The control main board (3) uses the AI ​​algorithm to perform real-time monitoring, so as to timely judge abnormal situations. When the control main board (3) judges abnormal data, it issues an alarm through the sound and light alarm (401). The display (402) can display various operation data in real time. When the sound and light alarm (401) issues an alarm, the control main board (3) sends an alarm message to the remote terminal through the transmission module (5). Through the cooperation of the collection component (2), the control main board (3), the early warning component (4) and the transmission module (5), multi-scenario monitoring of the oil depot environment can be realized, so that it can be deployed at any location in the oil depot for use.

Images