Safety early warning management system and device for oil depot

Abstract

The invention discloses a safety early warning system based on an oil depot, and the system employs a video monitoring module to collect the information in the oil depot, obtains the on-site real-time data, and the collected data comprises the operation information of an oil depot worker. The meteorological monitoring module is used for monitoring meteorological factors such as air temperature and humidity, wind speed and atmospheric pressure of an oil depot site; the lightning early warning module is used for collecting outdoor information and judging lightning activity conditions, so that potential safety hazards are reduced; the oil tank monitoring module is used for detecting oil tank foundation and deformation; the static electricity accurate measurement module is used for monitoring field static electricity conditions; the system further comprises a safety analysis module and an alarm module, the safety analysis module carries out safety analysis on monitored information and then uploads information which may generate risks to the alarm system, and the alarm system sends out sound and light signals to carry out early warning. The effect of safety management is achieved by collecting information around the oil depot.

Description

Technical Field

[0001] The present invention relates to the technical field of oil depot risk management, and particularly relates to a safety warning management system and device for an oil depot. Background Art

[0002] An oil depot is a facility and place for storing crude oil, refined oil, liquefied petroleum gas, natural gas and other petroleum products. It is a link coordinating crude oil production, crude oil processing, refined oil supply and transportation, and is a base for petroleum storage and supply. An oil depot generally can be divided into: an oil storage area, a loading and unloading area, an auxiliary facility area, etc. The oil storage area is the core area of the oil depot, which contains multiple oil storage tanks for storing a large amount of oil products.

[0003] Since an oil depot is a place for storing a large amount of petroleum products, these products have characteristics such as flammability, explosiveness, and volatility. Once an accident occurs, it may lead to serious consequences such as fires and explosions, posing a huge threat to personnel safety, environmental safety, and property safety. Therefore, conducting risk management on the oil depot, identifying potential safety hazards, and formulating corresponding preventive measures are necessary contents in the process of oil depot work.

[0004] However, the existing technology cannot predict the risks existing in the oil depot in advance during oil depot risk management, lacks foresight, and cannot foresee possible risks in advance and take corresponding measures for prevention, resulting in the inability to respond in a timely manner when risks occur. Summary of the Invention

[0005] Embodiments of the present invention provide a safety warning management system and device for an oil depot to solve the problem in the existing technology that possible risks cannot be foreseen in advance and corresponding measures cannot be taken for prevention, resulting in the inability to respond in a timely manner when risks occur.

[0006] To have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary part is not a general review, nor is it to identify key / important constituent elements or delineate the protection scope of these embodiments. Its sole purpose is to present some concepts in a simple form as a preface to the subsequent detailed description.

[0007] According to a first aspect of an embodiment of the present invention, a safety warning system based on an oil depot is provided, characterized in that the safety warning system includes:

[0008] A video monitoring module, which collects information in the oil depot to obtain on-site real-time data, and the collected data includes oil depot personnel operation information;

[0009] A meteorological monitoring module: The meteorological monitoring module is used to monitor meteorological factors such as air temperature and humidity, wind speed, and atmospheric pressure at the oil depot site;

[0010] Lightning warning module: The lightning warning module is used to collect outdoor information and then judge the lightning activity situation to reduce potential safety hazards;

[0011] Oil tank detection module, the oil tank monitoring module is used to detect the foundation and deformation of the oil tank;

[0012] Static electricity detection module, the static electricity precise detection module is used to monitor the static electricity situation on site;

[0013] It also includes a safety analysis module and an alarm module. The safety analysis module performs safety analysis on the information monitored by the video monitoring module, meteorological monitoring module, lightning warning module, oil tank detection module and the static electricity detection module, and then uploads the information that may generate risks to the alarm system, and the alarm system issues a sound and light signal for early warning.

[0014] Further, the safety analysis module includes: a characteristic index screening module, which is used to select test samples from the oil depot data, divide the training set and the test set according to a preset ratio, and screen risk characteristic indexes based on the test samples;

[0015] Risk judgment model construction module, which is used to establish a partial least squares discriminant analysis method to fit the training set, and calculate the model classification threshold using the receiver operating characteristic curve to construct a risk judgment model;

[0016] Abnormal data value calculation module, which is used to input the oil depot production data into the risk judgment model in turn to output the abnormal data value during the operation of the oil depot.

[0017] Among them, the selection of test samples from the oil depot data, dividing the training set and the test set according to a preset ratio, and screening risk characteristic indexes based on the test samples includes:

[0018] Pre-classify the oil depot production data according to the data type to obtain category data, select test samples for risk judgment from the category data, and divide the test samples into a training set, a validation set and a test set according to a preset ratio;

[0019] Use the training set and the validation set to screen the risk factor characteristic indexes respectively, and establish two groups of initial least squares discriminant analysis models to decompose the test samples;

[0020] Judge the variable projection importance of each index in the two groups of initial least squares discriminant analysis models, and screen the indexes with the importance result greater than the threshold based on the judgment result;

[0021] Sort the indexes with the importance greater than the threshold in reverse order, and perform index merging operation, and use the merging result as the risk characteristic index.

[0022] Among them, the establishment of the partial least squares discriminant analysis method to fit the training set and the construction of the risk judgment model by calculating the model classification threshold using the receiver operating characteristic curve include:

[0023] Use the partial least squares discriminant analysis method to fit the training set for initial model construction, obtain model parameters, and predict the validation set based on the obtained initial model to get the initial receiver operating characteristic curve;

[0024] Use the initial model to predict the test set to get the predicted risk prediction score, and select the prediction score threshold within the preset interval range as the classification threshold based on the score result;

[0025] Judge the risk prediction sensitivity and specificity of the classification threshold respectively, draw the receiver operating characteristic curve based on the judgment result, and compare the receiver operating characteristic curve with the initial receiver operating characteristic curve for coincidence;

[0026] Select the classification threshold with sensitivity and specificity equal to the standard value as the threshold result based on the comparison result, and combine the threshold result with the initial model to obtain the risk judgment model.

[0027] Furthermore, the expression of the risk judgment model is:

[0028]

[0029] In the formula, R represents the risk judgment result, represents the risk characteristic index, β represents the weight of each risk characteristic index in risk prediction, σ represents the optimal classification threshold determined by receiver operating characteristic curve analysis, and sinn represents the sign function.

[0030] This application also includes a safety warning management device, including: a video acquisition device: the video acquisition device includes a front-end acquisition device and a video analysis server. The front-end acquisition device forms video images of on-site information and transmits them to the video analysis server. The video analysis server analyzes the acquired information and transmits it to the safety analysis module to further achieve the effect of whether to give a warning.

[0031] A meteorological monitoring device: the meteorological detection device includes a meteorological workstation, and the meteorological workstation is connected to at least three meteorological monitoring devices; a lightning warning device and an electrostatic detection device. Furthermore, the meteorological detection device includes a meteorological workstation, and the meteorological workstation is connected to at least three meteorological monitoring devices.

[0032] Preferably, the meteorological acquisition device includes at least a wind direction sensor, a temperature and humidity sensor, and a pressure sensor

[0033] Preferably, the lightning warning device includes at least an atmospheric electric field meter.

[0034] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0035] A safety warning system based on an oil depot, including a video monitoring module, which collects information in the oil depot to obtain on-site real-time data, and the collected data includes the operation information of the oil depot personnel; a meteorological monitoring module: the meteorological monitoring module is used to monitor meteorological factors such as air temperature and humidity, wind speed, and atmospheric pressure at the oil depot site; a lightning warning module: the lightning warning module is used to collect outdoor information and then judge the lightning activity situation to reduce potential safety hazards; an oil tank detection module, the oil tank monitoring module is used to detect the foundation and deformation of the oil tank; an electrostatic detection module, the electrostatic detection module is used to monitor the on-site electrostatic situation; it also includes a safety analysis module and an alarm module. The safety analysis module performs safety analysis on the information monitored by the video monitoring module, meteorological monitoring module, lightning warning module, oil tank detection module, and the electrostatic detection module, and then uploads the information that may generate risks to the alarm system, and the alarm system issues an audible and visual signal for warning. The safety management effect is achieved by collecting information around the oil depot.

[0036] 1. First, the present invention constructs a control platform through industrial Internet technology to be able to obtain in real time the oil depot production data collected by monitoring devices within the operation range, ensuring real-time monitoring of the operation status of the oil depot, providing a timely and accurate information basis for later risk management and decision-making. At the same time, combining the oil depot production data with the partial least squares method technology to construct a risk judgment model can accurately identify abnormal data values during the operation of the oil depot, and use the risk standard threshold to judge the exceeding value of the abnormal data value, realizing the quantitative assessment of risks, helping to predict future risk changes, and providing forward-looking guidance for risk management.

[0037] 2. The present invention combines the oil depot production data with the partial least squares method technology to construct a risk judgment model, which can accurately identify abnormal data values during the operation of the oil depot, provides strong support for the safety management of the oil depot, realizes real-time processing of the oil depot production data, discovers and responds to abnormal situations in a timely manner, and ensures the safe operation of the oil depot, providing strong support for the safety management of the oil depot.

[0038] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present invention, and are used together with the specification to explain the principles of the present invention.

[0040] Figure 1It is a schematic block diagram of a safety warning system based on an oil depot shown according to an exemplary embodiment; Figure 2 It is a schematic structural diagram of a computer device shown according to an exemplary embodiment. Detailed implementation manners

[0041] The following description and drawings fully illustrate the specific implementation manners herein, enabling those skilled in the art to practice them. Parts and features of some embodiments may be included in or replaced by parts and features of other embodiments. The scope of the embodiments herein includes the entire scope of the claims and all available equivalents of the claims. In this document, terms such as "first", "second", etc. are only used to distinguish one element from another element, and do not require or imply any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a structure, device or equipment including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such structure, device or equipment. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the structure, device or equipment including the said element. The various embodiments herein are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts among the various embodiments can be referred to each other.

[0042] In this document, terms such as "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be construed as a limitation of the present invention. In the description of this document, unless otherwise specified and defined, the terms "installed", "connected", "coupled" should be understood in a broad sense. For example, it can be a mechanical connection or an electrical connection, or it can be the communication inside two elements. It can be directly connected or indirectly connected through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to specific circumstances.

[0043] In this document, unless otherwise stated, the term "plurality" means two or more.

[0044] In this document, the character " / " indicates that the objects before and after are in an "or" relationship. For example, A / B means: A or B.

[0045] In this text, the term "and / or" describes the relationship between objects and represents three possible relationships. For example, A and / or B means: A or B, or A and B.

[0046] It should be understood that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this text, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the figure may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0047] Each module in the device of this application or the safety warning system and device based on the oil depot can be implemented in whole or in part by software, hardware, or a combination thereof. The above-mentioned modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0048] Without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0049] A safety warning system based on an oil depot, characterized in that the safety warning system includes:

[0050] Video monitoring module 1, which collects information in the oil depot to obtain on-site real-time data. The collected data includes the operation information of oil depot personnel. Among them, for an oil depot equipped with a video intelligent analysis system, 1 video analysis server is configured on-site to realize video intelligent recognition of key areas such as major hazard sources and the central control room. It should be able to automatically recognize and alarm the absence / sleeping of personnel in the central control room, early smoke and fire in the oil depot, etc., so as to improve the safety management efficiency of the enterprise. Video analysis server (GPU server)

[0051] For an oil depot that meets the requirements of the "Construction Guide for the Intelligent Management and Control Platform for Work Safety Risks of Oil and Gas Storage Enterprises" document, a video analysis server (GPU service) is installed in the oil depot to access the oil depot monitoring video cameras, deploy the trained AI recognition algorithm, and upload the warning information obtained from the recognition and analysis to the headquarters emergency system through the production private network. Front-end monitoring equipment

[0052] The system utilizes the front-end cameras of the video surveillance system already built in the oil depot to collect video images of key areas in the oil depot and connect them to the video analysis server to provide image sources for video analysis.

[0053] Meteorological monitoring module 2: The meteorological monitoring module 2 is used to monitor meteorological factors such as air temperature and humidity, wind speed, and atmospheric pressure at the oil depot site; among them: Meteorological monitoring terminal equipment is configured at the oil depot to collect meteorological data of the oil depot. The system is connected to the safety production monitoring platform through the production private network. By positioning the oil depot, local meteorological information is obtained and pushed to the oil depot application client. The meteorological detection device includes a meteorological workstation, and the meteorological workstation is connected to at least three meteorological monitoring devices. Among them, the meteorological acquisition device includes at least a wind direction sensor, a temperature and humidity sensor, and a pressure sensor. The wind direction sensor is installed in Dingnan

[0054] We set the due north as the "0-degree angle", then the due south is the "180-degree angle". Looking down at the sensor, the larger the angle of the wind direction head rotating in the "clockwise" direction, the maximum angle is 359° (when fixing the sensor, the deviation between the Dingnan line and the geographical south should be minimized as much as possible). Before fixing the meteorological station bracket, the wind direction sensor needs to be set to the south

[0055] The specific operation method is as follows:

[0056] (1) Taking the axis of the wind direction sensor as the starting point, connect a ray with the Dingnan line on the sensor label;

[0057] (2) Adjust the sensor cup so that the ray points to the due south. At this time, the Dingnan line on the sensor should be facing the due south. During the south-setting process, do not care about the direction of the wind direction leaves, just make sure that the Dingnan line is facing the geographical due south; as shown in the following figure:

[0058] Setting of the wind direction correction angle of the acquisition instrument

[0059] (1) Before fixing the meteorological station bracket, try to install the wind direction sensor and turn the metal head of the wind direction sensor to point to the geographical due north (using a compass, red is south, white is north), and read the wind direction value on "Page 2" of the acquisition instrument: A (Note: The setting range of A is 1-180°. If A > 180°, the entire device needs to be rotated to make A ≤ 180°).

[0060] (2) Enter the setting interface of the acquisition instrument -> Other settings -> Wind direction correction -> Wind direction correction angle, and enter the value of the wind direction correction angle V here: V = 360 - A, press the "Confirm" key on the acquisition instrument, and then press the "Cancel" key to return to the main interface after the Dingnan line of the due south Dingnan line ray meteorological workstation. (Explanation: This operation of wind direction correction only corrects the value transmitted by the acquisition instrument to the upper computer and will not change the wind direction value on the display interface of the acquisition instrument).

[0061] Connect the instrument to the computer software. According to the communication method of the purchased equipment, refer to the instruction manuals such as "YG-Weather Automatic Weather Station Standalone Software" or "YG-Cloud Internet of Things Cloud Platform Client" to connect the instrument to the computer, and record, analyze, store, and export the data.

[0062] Lightning warning module 3: The lightning warning module is used to collect outdoor information and then judge the lightning activity situation to reduce potential safety hazards.

[0063] Oil tank detection module 4, which is used to detect the foundation and deformation of the oil tank.

[0064] Static electricity detection module 5, which is used to monitor the static electricity situation on site.

[0065] It also includes a safety analysis module 6 and an alarm module 7. The safety analysis module 6 conducts safety analysis on the information monitored by the video monitoring module 1, meteorological monitoring module 2, lightning warning module 3, oil tank detection module 4, and static electricity detection module 5, and then uploads the information that may pose risks to the alarm module 7, and the alarm system issues an audible and visual signal for early warning.

[0066] In this alternative embodiment, the safety analysis module 6 includes:

[0067] Feature index screening module, which is used to select test samples from the oil depot production data, divide the training set and the test set according to a preset ratio, and screen risk feature indexes based on the test samples.

[0068] Risk judgment model construction module, which is used to establish a partial least squares discriminant analysis method to fit the training set, and calculate the model classification threshold using the receiver operating characteristic curve to construct a risk judgment model.

[0069] Abnormal data value calculation module, which is used to input the oil depot production data into the risk judgment model in sequence to output the abnormal data values during the operation of the oil depot.

[0070] In this alternative embodiment, selecting test samples from the oil depot production data and dividing the training set and the test set according to a preset ratio, and screening risk characteristic indicators based on the test samples include: classifying the oil depot production data according to data types in advance to obtain category data, and selecting test samples for risk judgment from the category data, dividing the test samples into a training set, a validation set, and a test set according to a preset ratio; respectively using the training set and the validation set to screen risk factor characteristic indicators, establishing two groups of initial least squares discriminant analysis models to decompose the test samples; judging the variable projection importance of each indicator in the two groups of initial least squares discriminant analysis models, and screening indicators with importance results greater than the threshold based on the judgment results; arranging the screened indicators with importance greater than the threshold in reverse order, and performing an indicator merging operation, and taking the merging result as the risk characteristic indicator.

[0071] In this alternative embodiment, respectively using the training set and the validation set to screen risk factor characteristic indicators, and establishing two groups of initial least squares discriminant analysis models to decompose the test samples includes: using the training set for feature selection to identify variables most relevant to the risk, which can be completed by statistical methods such as correlation analysis, principal component analysis (PCA), or other feature selection techniques; repeating the above process, this time using the validation set to screen features; using the features screened out from the training set to establish the first group of partial least squares discriminant analysis models, and similarly using the features screened out from the validation set to establish the second group of partial least squares discriminant analysis models; using the cross-validation technique for the two groups of models to evaluate their prediction accuracy and stability; applying the two trained PLS-DA models to the test samples to analyze their performance and risk prediction ability.

[0072] In this alternative embodiment, judging the variable projection importance of each indicator in the two groups of initial least squares discriminant analysis models, and screening indicators with importance results greater than the threshold based on the judgment results includes: calculating the projection importance (VIP) of each variable in the partial least squares discriminant analysis model; calculating and analyzing the VIP values of the two groups of models respectively, and comparing the VIP values of the same variables in the two groups of models to evaluate which variables show high importance in both models; setting a VIP threshold according to experience or statistical methods, usually this threshold is set to 1.0 or higher, indicating that the variable has a significant influence in the model; screening out variables with VIP values greater than the set threshold from each model, integrating the results screened out by the two groups of models, and determining the final variable set for constructing or optimizing the least squares discriminant analysis model.

[0073] Specifically, the calculation formula for the projection importance (VIP) is:

[0074]

[0075] where VIP jrepresents the projection importance of the j-th variable, w jk represents the weight of the j-th variable on the k-th component, represents the explanatory power of the k-th component for the model, q represents the total number of variables, and A represents the number of components.

[0076] In this alternative embodiment, establishing a partial least squares discriminant analysis method to fit the training set and calculating the model classification threshold using the receiver operating characteristic curve to construct a risk judgment model includes: using the partial least squares discriminant analysis method to fit the training set for initial model construction, obtaining model parameters, and predicting the validation set based on the obtained initial model to obtain an initial receiver operating characteristic curve; predicting the test set using the initial model to obtain predicted risk prediction scores, selecting a prediction score threshold within a preset interval range as the classification threshold based on the score results; respectively judging the risk prediction sensitivity and specificity of the classification threshold, drawing a receiver operating characteristic curve based on the judgment results, and comparing the receiver operating characteristic curve with the initial receiver operating characteristic curve; selecting a classification threshold with sensitivity and specificity equal to the standard value as the threshold result based on the comparison results, and combining the threshold result with the initial model to obtain a risk judgment model.

[0077] In this alternative embodiment, the expression of the risk judgment model is:

[0078]

[0079] In the formula, R represents the risk judgment result, represents the risk characteristic index, β represents the weight of each risk characteristic index in risk prediction, σ represents the optimal classification threshold determined by receiver operating characteristic curve analysis, and sinn represents the sign function.

[0080] A safety warning management device includes: a video acquisition device: the video acquisition device includes a front-end acquisition device and a video analysis server, the front-end acquisition device forms video images of on-site information and transmits them to the video analysis server, and the video analysis server analyzes the acquired information and transmits it to a safety analysis module to achieve the effect of whether to give a warning. A meteorological monitoring device: the meteorological detection device includes a meteorological workstation, and the meteorological workstation is connected to at least three meteorological monitoring devices; a lightning warning device and an electrostatic detection device.

[0081] The meteorological detection device includes a meteorological workstation, and the meteorological workstation is connected to at least three meteorological monitoring devices.

[0082] Among them, the meteorological acquisition device includes at least a wind direction sensor, a temperature and humidity sensor, and a pressure sensor

[0083] The lightning warning device at least includes an atmospheric electric field meter. The power supply and signal cables of the atmospheric electric field meter are DJYVP22-2x2x1.5mm2 cables, which are laid underground with a depth greater than 0.8m. According to the specifications, protective measures such as laying bricks for underground cables and passing steel pipes for cables above ground are adopted. An angle steel grounding electrode is installed 3 meters away from the atmospheric electric field meter. The grounding electrode is 3 50*50*5 hot-dip galvanized angle steels, and the grounding busbar is 40*4 hot-dip galvanized flat steel. The grounding resistance is less than 10Ω. The mounting bracket is connected to the grounding body, and the cross-sectional area of ​​the grounding wire is not less than 16mm2.

[0084] In this optional embodiment, the use of industrial Internet of Things technology and management needs to build an underlying architecture, and generating a management platform in combination with terminal hardware configuration information includes: determining the management platform management main interface based on management needs, defining the port application layer in the management main interface, and applying industrial Internet of Things technology to build a headquarters data center in the management main interface to determine the underlying architecture; integrating the underlying architecture with the oil depot terminal hardware equipment to obtain the edge perception layer, and generating a management platform through the edge perception layer, the underlying architecture and the port application layer; performing security reinforcement and function analysis and statistics on the management platform by calling the interface, and after determining the security of the management platform based on the analysis results, deploying the management platform on an encrypted authentication storage disk.

[0085] In this optional embodiment, the underlying architecture includes a service layer, a data layer and a resource layer; the oil depot terminal hardware equipment includes an oil depot data acquisition monitor, an oil depot security device, an oil depot fire fighting device and an environmental monitor.

[0086] It needs to be explained that the edge perception layer, as the data support platform of the management platform, mainly includes process automatic control instruments, combustible gas monitoring equipment, video surveillance equipment, personnel access management equipment, vehicle identification equipment, environmental monitoring equipment, etc. The perception layer equipment is installed at the oil depot site, and the equipment communicates with the oil depot automatic control system (SCADA system), security system and other production systems to collect data.

[0087] The oil depot has built an automatic control system, security system, fire protection system, and environmental monitoring system, which are deployed in the oil depot production duty center. The oil depot uses this system to carry out production operations. The system integrates the equipment status, operation data, oil inventory data, security monitoring data, etc. of the perception layer. The systems and equipment of this layer connect the production data to the aviation fuel company's safety production monitoring platform and liquid level measurement system through the production dedicated network.

[0088] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0089] The present invention is not limited to the structures that have been described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A safety early warning system based on an oil depot, characterized in that: The safety early warning system includes: A video monitoring module collects information in the oil depot and obtains real-time data on site. The collected data includes operation information of oil depot personnel; Meteorological monitoring module: The meteorological monitoring module is used to monitor meteorological factors such as air temperature and humidity, wind speed and atmospheric pressure at the oil depot site; Lightning warning module: The lightning warning module is used to collect outdoor information and then judge the lightning activity to reduce safety hazards; The oil tank monitoring module is used to detect the oil tank foundation and deformation; An electrostatic detection module, wherein the electrostatic precision measurement module is used to monitor the electrostatic conditions on site; It also includes a safety analysis module and an alarm module. The safety analysis module performs safety analysis on the information monitored by the video monitoring module, the weather monitoring module, the lightning warning module, the oil tank detection module and the electrostatic detection module, and then uploads the information that may cause risks to the alarm system. The alarm system sends out sound and light signals for warning.

2. The safety warning management system according to claim 1, characterized in that: The safety analysis module includes: The feature index screening module is used to select test samples from the oil depot data, divide the training set and the test set according to a preset ratio, and screen the risk feature index based on the test samples; The risk judgment model building module is used to establish a partial least squares discriminant analysis method to fit the training set, and use the sensitivity curve to calculate the model classification threshold to build a risk judgment model; The abnormal data value obtaining module is used to input the oil depot production data into the risk judgment model in sequence and output the abnormal data values ​​during the oil depot operation.

3. The oil depot safety early warning system according to claim 2 is characterized in that: The selecting of test samples from the oil depot data to divide the training set and the test set according to a preset ratio, and screening of risk characteristic indicators based on the test samples include: Classify the oil depot production data in advance according to the data type to obtain category data, select test samples for risk judgment from the category data, and divide the test samples into training set, verification set and test set according to the preset ratio; The risk factor characteristic indicators were screened using the training set and the validation set, and two groups of initial least squares discriminant analysis models were established to decompose the test samples; Determine the variable projection importance of each indicator in the two initial least squares discriminant analysis models, and screen indicators whose importance results are greater than the threshold based on the judgment results; The screened indicators whose importance is greater than the threshold are arranged in reverse order, and the indicator merging operation is performed, and the merging result is used as the risk characteristic indicator.

4. The safety warning management system according to claim 2, characterized in that: The method of establishing a partial least squares discriminant analysis method to fit the training set and using the sensitivity curve to calculate the model classification threshold to construct a risk judgment model includes: The partial least squares discriminant analysis method is used to fit the training set to construct the initial model, obtain the model parameters, and predict the validation set based on the obtained initial model to obtain the initial sensitivity curve; The initial model is used to predict the test set to obtain a predicted risk prediction score, and based on the score result, a prediction score threshold within a preset range is selected as a classification threshold; The risk prediction sensitivity and specificity of the classification threshold are determined respectively, and the sensitivity curve is drawn based on the determination results, and the sensitivity curve is overlapped and compared with the initial sensitivity curve; Based on the comparison results, the classification threshold with sensitivity and specificity equal to the standard value is selected as the threshold result, and the threshold result is combined with the initial model to obtain the risk judgment model.

5. The safety warning management system according to claim 4, characterized in that: The expression of the risk judgment model is: In the formula, R represents the risk judgment result, represents the risk characteristic index, β represents the weight of each risk characteristic index in risk prediction, σ represents the optimal classification threshold determined by sensitivity curve analysis, and sinn represents the sign function.

6. A safety warning management device, It is characterized in that Including: Video acquisition device: The video acquisition device includes a front-end acquisition device and a video analysis server. The front-end acquisition device converts the on-site information into a video image and transmits it to the video analysis server. The video analysis server analyzes the acquired information and transmits it to the security analysis module to thereby play a role in early warning. Meteorological monitoring device: The meteorological detection device includes a meteorological workstation, and the meteorological workstation is connected to at least three meteorological monitoring devices; Lightning warning device and static electricity detection device.

7. The safety warning management device according to claim 6, characterized in that: The meteorological detection device comprises a meteorological workstation, and the meteorological workstation is connected to at least three meteorological monitoring devices.

8. The safety warning management device according to claim 6, characterized in that: The meteorological collection device at least includes a wind direction sensor, a temperature and humidity sensor and a pressure sensor.

9. The safety warning management device according to claim 6, characterized in that: The lightning warning device at least includes an atmospheric electric field meter.

Images