Method and device for displaying early warning information of cold source disaster-causing matter based on multifunctional monitoring buoy

Abstract

The application relates to the technical field of cold source disaster-causing matter early warning, and discloses a cold source disaster-causing matter early warning information display method and device based on a multifunctional monitoring buoy, which comprises the following steps: acquiring real-time multi-source monitoring data through the multifunctional monitoring buoy; performing distributed storage management on the real-time multi-source monitoring data; sending a recognition model after fusing and sorting the real-time multi-source monitoring data to obtain a risk assessment score; performing fusion analysis and processing on the real-time multi-source monitoring data, correcting the risk assessment score according to the fusion analysis and processing result to obtain a risk real-time score; and performing threshold value judgment according to the risk real-time score, and pushing and displaying early warning information when it is necessary to issue a risk prompt. The multifunctional monitoring buoy is integrated with various monitoring devices, and based on multi-channel wireless high-speed transmission technology and cooperative control technology, comprehensive and cooperative monitoring of disaster elements in a three-dimensional space composed of air, water surface, underwater and coast is realized, and the reliability of early warning is comprehensively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cold source disaster-causing matter early warning, and in particular to a cold source disaster-causing matter early warning information display method and device based on a multifunctional monitoring buoy. BACKGROUND

[0002] The cold source system is the abbreviation of the circulating water system of a power plant, and its English name is Main cooling water system. During the operation of a nuclear power plant, the cold source system continuously obtains cooling water from the external environment, and then provides cooling water to the safety service water of the nuclear island, and also provides cooling water to the condenser and auxiliary cooler of the conventional island. In this process, the heat generated by the reactor is transferred to the cooling water through heat exchange equipment, and then the cooled water is discharged back to the environment to ensure the continuous cooling of the reactor.

[0003] Therefore, the cold source system needs to ensure that the heat generated by the nuclear reactor can be effectively removed, so as to maintain the stable operation of the reactor. However, there are many disaster-causing matters in the sea that may pose a threat to the cold source system, such as phytoplankton (such as brown cyst algae), zooplankton (such as jellyfish, brine shrimp), swimming organisms, large algae, and large benthic animals. These disaster-causing matters may block the water inlet of the circulating water filtration system of the nuclear power plant, resulting in insufficient cooling water, and further causing operation safety incidents such as reactor trip and shutdown.

[0004] Therefore, cold source disaster-causing matter early warning is a crucial part of the safe operation of a nuclear power plant. However, the water inlet of a nuclear power plant is generally located on the sea coast. With the changes in global climate and environment, the marine ecosystem has also undergone tremendous changes, and the types and quantities of disaster-causing matters may also change accordingly. Moreover, cold source disaster-causing matter early warning involves multiple fields, including meteorology, environment, and biology. These cross-field information cannot be effectively utilized at present. SUMMARY

[0005] In order to improve the reliability of the existing cold source disaster-causing matter early warning, the present application provides a cold source disaster-causing matter early warning information display method and device based on a multifunctional monitoring buoy.

[0006] In a first aspect, the present application provides a cold source disaster-causing matter early warning information display method based on a multifunctional monitoring buoy, which adopts the following technical solution:

[0007] A cold source disaster-causing matter early warning information display method based on a multifunctional monitoring buoy, comprising:

[0008] Real-time multi-source monitoring data is acquired by the multifunctional monitoring buoy; the real-time multi-source monitoring data includes GPS position coordinates, weather data, ocean current speed data, CTD data, laser data, remote sensing data, underwater image data, water surface infrared data, unmanned aerial vehicle inspection data, sonar data, and fish finder data;

[0009] The real-time multi-source monitoring data is subjected to distributed storage management;

[0010] After the real-time multi-source monitoring data is subjected to fusion and arrangement, a risk assessment score is acquired by sending an identification model;

[0011] The real-time multi-source monitoring data is subjected to fusion analysis and processing, and the risk assessment score is corrected according to the result of the fusion analysis and processing to obtain a risk real-time score;

[0012] According to the risk real-time score, threshold judgment is performed, and early warning information is pushed and displayed when a risk prompt is needed.

[0013] By adopting the above technical solution, a Beidou high-precision positioning device, a water surface camera, an underwater camera, a high-frequency sonar, a fish finder, a split-beam sonar, a CTD, a weather instrument, a laser radar, a current meter, a water surface infrared night vision instrument, and other monitoring devices are integrated on the multifunctional monitoring buoy, multi-channel wireless high-speed transmission technology and collaborative control technology are used, comprehensive and collaborative monitoring of disaster elements in a three-dimensional space composed of the air, the water surface, the underwater, and the coast is realized, two-step risk calculation is adopted, the judgment result of the identification model is corrected through the fusion analysis result of the multi-source data, reliable positioning of the risk position can be realized, real-time risk position pushing and display are performed in the control hall through the visualization technology, and the reliability of the cold source disaster warning is comprehensively improved.

[0014] Optionally, the process of acquiring the risk assessment score by sending the identification model after the real-time multi-source monitoring data is subjected to fusion and arrangement includes:

[0015] For each kind of real-time multi-source monitoring data, a corresponding change curve is generated;

[0016] The specific numerical value of the real-time multi-source monitoring data is quantified through the color depth of the change curve;

[0017] All the real-time multi-source monitoring data are collected in the same blank picture to obtain a corresponding sampling picture;

[0018] The sampling picture is framed according to a preset window framing rule, and at least c different sampling frame pictures are selected;

[0019] The sampling frame picture is packaged and sent to the identification model, and the average value of the output result is taken as the risk assessment score U.

[0020] By adopting the technical solution, the real-time multi-source monitoring data can be simultaneously reflected in the same picture, the changes of all categories of multi-source monitoring data in the same time period are intercepted in the picture multiple times, and the trained recognition model is used for recognition, each sampling frame picture corresponds to an output result, the output result is a risk probability value, and the average value of the output result is used as the risk assessment score U, so that the possibility of misjudgment can be reduced.

[0021] Optionally, the preset window frame selection rule comprises:

[0022] The number m of categories of the real-time multi-source monitoring data whose variance is greater than the corresponding specified variance threshold in a specified time period is obtained;

[0023] The formula is The current frame selection time interval ΔT is confirmed;

[0024] Wherein, ΔT0 is an initial frame selection time interval, β is a preset constant term and 0.2≤β≤0.6, m th is a preset category boundary quantity, and n is a total number of categories.

[0025] By adopting the technical solution, the number m of categories represents the fluctuation of the multi-source monitoring data as a whole, and the greater the value of m, the more intense the fluctuation of the whole. At this time, the frame selection time interval ΔT can be increased to increase the amount of information contained in the sample, which occupies more computing power, but helps to discover risks in time in the case of intense overall fluctuations. When the fluctuation degree is small, the frame selection time interval ΔT can be reduced to reduce the waste of computing power, that is, power, while ensuring the early warning effect, the energy saving effect can also be considered.

[0026] Optionally, the process of selecting at least c different sampling frame pictures comprises:

[0027] If ΔT<ΔT0, then c=c1, otherwise c=c2;

[0028] Wherein, c1

[0029] By adopting the technical solution, when the fluctuation degree is small, the number of sampling frame pictures can be reduced to reduce the waste of computing power, that is, power, while ensuring the early warning effect, the energy saving effect can also be considered.

[0030] In addition, more importantly, in the training stage, a large number of different sampling samples can be generated for picture data of real-time multi-source monitoring data in a specified time period by adjusting the selected time interval ΔT and the number of sampling frame diagrams, so that the recognition accuracy of the recognition model can be greatly improved in the case of multi-dimensional data changes; in the embodiment of the application, the recognition model is trained based on a convolutional neural network (CNN), and the CNN is a kind of feedforward neural network (Feedforward Neural Networks) containing convolution calculation and having a deep structure, and is one of representative algorithms of deep learning (deeplearning).

[0031] The basic structure of the CNN is composed of an input layer, a convolution layer, a pooling layer (also called a sampling layer), a full connection layer and an output layer. The convolution layer and the pooling layer are generally taken several times, and the convolution layer and the pooling layer are alternately arranged, that is, one convolution layer is connected with one pooling layer, and one convolution layer is connected after the pooling layer, and so on. In the convolutional neural network, different convolution kernels are needed to convolve the input image (each convolution kernel is convolved from the beginning to the end to extract features and form a feature map, and multiple convolution kernels extract multiple feature maps to form a convolution depth) to extract different features of the image (multi-kernel convolution); at the same time, multiple convolution layers are needed to convolve to extract deep features (deep convolution).

[0032] The receptive field refers to the size of the region on the input image that each pixel point on the feature map output by each layer of the convolutional neural network is mapped back to. The larger the receptive field of the neuron, the larger the range of the original image it can contact, which means that it can learn more global and higher semantic level feature information; on the contrary, the smaller the range, the more local and detailed the features it contains, so the CNN is suitable for providing relatively accurate judgments in the process of multi-dimensional data changes in the application, but has a higher requirement for the number of samples.

[0033] Optionally, the process of fusing and analyzing the real-time multi-source monitoring data comprises:

[0034] calculating and obtaining a single risk value Zi corresponding to the ith data in the real-time multi-source monitoring data;

[0035]

[0036] wherein x i is the ith data value, is the average value of the ith data in the previous specified time period, and Δt is the interval of the specified time period.

[0037] According to the single risk value, an overall risk value PZ is calculated;

[0038]

[0039] wherein, δi is a specified dynamic weighting coefficient, and After each of the specified time periods, the dynamic weighting coefficients are reconfigured according to the fault items of the last specified time period.

[0040] By using the above technical solution, the dynamic weighting coefficients can be arranged in descending order according to the categories of the fault items of the last specified time period, and in the current specified time period, the first largest dynamic weighting coefficient is matched with the category of the corresponding fault item to improve the corresponding weight and realize key monitoring.

[0041] Optionally, the process of obtaining a risk real-time score by correcting the risk assessment score according to the result of the fusion analysis processing comprises:

[0042]

[0043] wherein, G is the risk real-time score, PccZ is the risk real-time score of the last specified time period, and PceZ is the risk real-time score of the last but one specified time period.

[0044] By using the above technical solution, the risk real-time score can be adjusted according to the fluctuation of the risk real-time score corresponding to the last three specified time periods, and the internal logic is that when the fluctuation degree is large, the tolerance to risk is reduced, which can prevent problems from occurring.

[0045] Optionally, the process of performing threshold value judgment according to the risk real-time score and pushing and displaying warning information when a risk prompt is needed comprises:

[0046] The current risk real-time score G is compared with a preset risk threshold Gthr, if G < Gthr, it is determined that there is no risk, and if G ≥ Gthr, according to the position information of the multifunctional monitoring buoy, a bubble warning is pushed on a visual map.

[0047] In the second aspect, the application provides a cold source disaster-causing material warning information display method and device based on a multifunctional monitoring buoy, which adopts the following technical solution:

[0048] A cold source disaster-causing material warning information display device based on a multifunctional monitoring buoy comprises a processor, and the processor runs a program of the cold source disaster-causing material warning information display method based on a multifunctional monitoring buoy.

[0049] In summary, the application has at least one of the following beneficial technical effects:

[0050] 1. This invention integrates Beidou high-precision positioning equipment, surface cameras, underwater cameras, high-frequency sonar, fish finders, split-beam sonar, CTD, weather instruments, lidar, current meters, and surface infrared night vision devices onto a multi-functional monitoring buoy. Based on multi-channel wireless high-speed transmission technology and collaborative control technology, it achieves comprehensive and collaborative monitoring of disaster elements in a three-dimensional space consisting of air, surface, underwater, and coastline. It adopts a two-step risk calculation, and corrects the judgment results of the identification model by fusing and analyzing the results of multi-source data, which can achieve reliable location of risk. Then, through visualization technology, the risk location is pushed and displayed in real time in the control hall, which comprehensively improves the reliability of early warning of cold source disasters.

[0051] 2. In this invention, real-time multi-source monitoring data are simultaneously displayed in the same image. The image is repeatedly cropped to capture the changes in all categories of multi-source detection data within the same time period. The changes are then identified by a trained recognition model. Each sampling frame corresponds to an output result, which is the probability value of the existence of risk. The average value of the output results is used as the risk assessment score U to reduce the possibility of misjudgment.

[0052] 3. In this invention, the number of types m represents the overall fluctuation of the multi-source detection data. The larger the value of m, the more severe the overall fluctuation. In this case, the amount of information contained in the sample can be increased by increasing the frame selection time interval ΔT. Although more computing power is required, it helps to detect risks in a timely manner when the overall fluctuation is severe. When the fluctuation is small, the frame selection time interval ΔT can be reduced to reduce the waste of computing power, i.e., electricity. While ensuring early warning, energy saving can also be taken into account. Attached Figure Description

[0053] Figure 1 This is a flowchart illustrating the principle of the cold source disaster warning information display method in this invention. Detailed Implementation

[0054] The embodiments of this application are described in detail below, and examples of the embodiments are shown in the accompanying drawings.

[0055] In the description of this specification, the references to "certain embodiments," "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples" refer to specific features, structures, materials, or characteristics described in connection with the described embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0056] The embodiment of the application discloses a cold source disaster-causing matter early warning information display method based on a multifunctional monitoring buoy, as shown in the figure, comprising: Figure 1

[0057] Real-time multi-source monitoring data is acquired by the multifunctional monitoring buoy; the real-time multi-source monitoring data comprises GPS position coordinates, meteorological data, ocean current speed data, CTD data, laser data, remote sensing data, underwater image data, water surface infrared data, unmanned aerial vehicle inspection data, sonar data and fish finder data;

[0058] The real-time multi-source monitoring data is subjected to distributed storage management;

[0059] After the real-time multi-source monitoring data is subjected to fusion and arrangement, a risk assessment score is acquired by sending an identification model;

[0060] The real-time multi-source monitoring data is subjected to fusion analysis and processing, and the risk assessment score is corrected according to the result of the fusion analysis and processing to obtain a real-time risk score;

[0061] According to the real-time risk score, threshold value judgment is performed, and early warning information is pushed and displayed when a risk prompt is needed.

[0062] In the embodiment of the application, by integrating Beidou high-precision positioning equipment, water surface cameras, underwater cameras, high-frequency sonars, fish finders, split-beam sonars, CTDs, weather meters, laser radars, current meters, water surface infrared night vision instruments and other monitoring equipment on the multifunctional monitoring buoy, based on multi-channel wireless high-speed transmission technology and cooperative control technology, comprehensive and cooperative monitoring of disaster elements in a three-dimensional space composed of the air, the water surface, the underwater and the coast is realized, two-step risk calculation is adopted, the judgment result of the identification model is corrected through the fusion analysis result of the multi-source data, reliable positioning of the risk position can be realized, and real-time risk position pushing and display in the control hall are realized through the visualization technology, and the reliability of cold source disaster-causing matter early warning is comprehensively improved.

[0063] Optionally, the process of acquiring the risk assessment score by sending the identification model after the real-time multi-source monitoring data is subjected to fusion and arrangement comprises:

[0064] For each kind of real-time multi-source monitoring data, a corresponding change curve is generated;

[0065] ​For meteorological data, the wind speed component data in the direction of the line connecting the location of the multifunctional monitoring buoy and the water intake of the cold source system can be obtained, the ocean current speed data can be the seawater flow speed component data in the direction of the line connecting the location of the multifunctional monitoring buoy and the water intake of the cold source system, the CTD data can be the seawater surface layer conductivity, the laser data, underwater image data, water surface infrared data, sonar data and fish probe data can be the monitoring and analysis results of biological factors at the location of the multifunctional monitoring buoy, and the remote sensing data and unmanned aerial vehicle inspection data can provide visual conditions near the multifunctional monitoring buoy site.

[0066] The specific values of the real-time multi-source monitoring data are quantified by the color depth of the change curve;

[0067] All the real-time multi-source monitoring data are collected in the same blank picture to obtain a corresponding sampling picture;

[0068] The sampling picture is framed according to a preset window framing rule, and at least c different sampling frame pictures are selected;

[0069] The sampling frame pictures are packaged and sent to a recognition model, and the average value of the output results is taken as the risk assessment score U.

[0070] By using the above technical solution, the real-time multi-source monitoring data can be simultaneously reflected in the same picture, and the change of all categories of multi-source detection data in the same time period is intercepted multiple times in the picture, which is recognized by the trained recognition model. Every sampling frame picture corresponds to an output result, the output result is a probability value of existing risk, and the average value of the output result is taken as the risk assessment score U, which can reduce the possibility of misjudgment.

[0071] Optionally, the preset window framing rule includes:

[0072] The number m of categories of the real-time multi-source monitoring data whose variance is greater than the corresponding specified variance threshold in a specified time period is obtained;

[0073] The formula The current framing time interval ΔT is confirmed;

[0074] Where ΔT0 is the initial framing time interval, β is a preset constant term and 0.2≤β≤0.6, m th is a preset category boundary quantity, and n is the total number of categories.

[0075] By adopting the technical scheme, the number m of categories represents the fluctuation of the overall multi-source detection data, and the greater the m value, the more intense the overall fluctuation, at which time the information amount contained by the sample can be improved by increasing the time interval ΔT of the frame selection, which occupies more computing power, but helps to discover risks in time in the case of intense overall fluctuation, and the time interval ΔT of the frame selection can be reduced to reduce the waste of computing power, that is, power, in the case of small fluctuation degree, which can ensure the early warning while taking into account the energy-saving effect.

[0076] Optionally, the process of selecting at least c different sampling frame diagrams comprises:

[0077] If ΔT < ΔT0, c = c1, otherwise c = c2;

[0078] Wherein, c1 < c2, and c1 and c2 are both specified constants.

[0079] By adopting the technical scheme, the number of sampling frame diagrams can be reduced to reduce the waste of computing power, that is, power, in the case of small fluctuation degree, which can ensure the early warning while taking into account the energy-saving effect.

[0080] Optionally, the process of fusing and analyzing the real-time multi-source monitoring data comprises:

[0081] Calculating and obtaining a single risk value Zi corresponding to the i-th data in the real-time multi-source monitoring data;

[0082]

[0083] Wherein, x i is the i-th data value, is the average value of the i-th data in the last specified time period, and Δt is the interval of the specified time period;

[0084] Calculating an overall risk value PZ according to the single risk value;

[0085]

[0086] Wherein, δi is a specified dynamic weighting coefficient, and δi is reconfigured according to the fault items in the last specified time period every specified time period.

[0087] By adopting the technical scheme, the dynamic weighting coefficients can be arranged in descending order according to the categories of the fault items in the last specified time period, and in the current specified time period, the first largest dynamic weighting coefficient is matched with the category of the corresponding fault item to improve the corresponding weight, thereby achieving key monitoring.

[0088] For example, after a specified time period of the non-faulty project, the dynamic weighting coefficient can be evenly distributed to each project. If the fault project in the last specified time period is caused by fish and shrimp blockage, the weight of the project related to fish and shrimp quantity and species monitoring, such as the monitoring and analysis results of biological factors at the location of the multifunctional monitoring buoy by laser data, underwater image data, water surface infrared data, sonar data and fish probe data, can be increased by 5% in the current specified time period. The specific increase can be determined according to experience.

[0089] Optionally, the process of correcting the risk assessment score according to the result of the fusion analysis processing to obtain a risk real-time score includes:

[0090]

[0091] Wherein, G is the risk real-time score, PccZ is the risk real-time score of the last specified time period, and PceZ is the risk real-time score of the last but one specified time period.

[0092] By using the above technical solution, the fluctuation of the risk real-time score corresponding to the last three specified time periods can be adjusted. The internal logic is that when the fluctuation degree is large, the tolerance to risk is reduced, which can prevent problems from occurring.

[0093] Optionally, the process of judging the threshold value according to the risk real-time score and pushing and displaying warning information when it is necessary to issue a risk prompt includes:

[0094] The current risk real-time score G is compared with a preset risk threshold Gthr. If G < Gthr, it is judged that there is no risk. If G ≥ Gthr, a bubble warning is pushed on the visual map according to the position information of the multifunctional monitoring buoy.

[0095] The various processes and processes described above, such as a method, can be executed by a CPU. For example, in some embodiments, a method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as a memory. In some embodiments, part or all of the computer program can be loaded and / or installed on a computing device via a ROM and / or a communication unit. When the computer program is loaded into the RAM and executed by the CPU, the above-described method or action based on multi-sensor fusion intelligent cold source disaster-causing object monitoring can be executed.

[0096] The present disclosure relates to methods, computing devices, computer-readable storage media, and / or computer program products. The computer program product can include computer-readable program instructions for performing various aspects of the present disclosure.

[0097] Computer readable storage media can be tangible storage devices that can retain and store instructions for use by an instruction execution device. Computer readable storage media can be, for example, but is not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer readable storage media include the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

[0098] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0099] Computer readable program instructions for carrying out operations of the present disclosure can be assembly instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate array (FPGA), or programmable logic array (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0100] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can include a non-transitory computer readable storage medium that can direct a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including a manufacture of one or more aspects of a multi-sensor fusion based intelligent cold source hazard monitoring method or actions.

[0101] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement a multi-sensor fusion based intelligent cold source hazard monitoring method or actions.

[0102] Embodiments of the present disclosure have been described above, the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes are obvious to those skilled in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles, practical applications, or technical improvements in the art, or to enable other ordinary skilled persons in the art to understand the embodiments disclosed herein.

[0103] Based on the same inventive concept, the embodiments of the present application provide an intelligent terminal, comprising a memory and a processor, the memory stores a computer program capable of being loaded and executed by the processor.

[0104] In a second aspect, the application provides a cold source disaster-causing object early warning information display method and device based on a multifunctional monitoring buoy, which adopts the following technical scheme:

[0105] A cold source disaster-causing object early warning information display device based on a multifunctional monitoring buoy, comprising a processor, wherein the processor runs a program of the cold source disaster-causing object early warning information display method based on the multifunctional monitoring buoy.

[0106] Although the embodiments of the present application have been shown and described above, it can be understood that the above-described embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-described embodiments within the scope of the present application.

Claims

1. A cold source disaster-causing object early warning information display method based on a multifunctional monitoring buoy, characterized in that, The method comprises the following steps: acquiring real-time multi-source monitoring data through the multifunctional monitoring buoy; the real-time multi-source monitoring data comprises GPS position coordinates, weather data, ocean current velocity data, CTD data, laser data, remote sensing data, underwater image data, water surface infrared data, unmanned aerial vehicle inspection data, sonar data and fish probe data; performing distributed storage management on the real-time multi-source monitoring data; sending the real-time multi-source monitoring data to an identification model after fusion and arrangement to acquire a risk assessment score U; performing fusion analysis and processing on the real-time multi-source monitoring data, and correcting the risk assessment score according to the result of the fusion analysis and processing to obtain a risk real-time score; performing threshold judgment according to the risk real-time score, and pushing and displaying early warning information when a risk prompt is needed; the process of performing fusion analysis and processing on the real-time multi-source monitoring data comprises: calculating a single risk value corresponding to the i-th data in the real-time multi-source monitoring data ; ； wherein, is the i-th data value, is the average of the i-th data over the previous specified time period, is the interval of the specified time period; calculating an overall risk value from the single risk values ; ； wherein, is a specified dynamic weighting coefficient, and , is reconfigured according to the fault items of the last specified time period, and n is the total amount of categories. the process of correcting the risk assessment score according to the result of the fusion analysis and processing to obtain a risk real-time score comprises: ； wherein, a risk real-time score for the risk, a risk real-time score for the risk for a previous specified time period, a risk real-time score for the risk for a previous previous specified time period.

2. The cold-source disaster-causing object early warning information display method based on a multifunctional monitoring buoy according to claim 1, characterized by, the process of sending the real-time multi-source monitoring data to an identification model after fusion and arrangement to acquire a risk assessment score comprises: generating a corresponding change curve for each kind of real-time multi-source monitoring data; quantifying the specific value of the real-time multi-source monitoring data through the color depth of the change curve; collecting all the real-time multi-source monitoring data in the same blank picture to obtain a corresponding sampling picture; selecting at least c different sampling frame pictures according to a preset window framing rule; packing the sampling frame pictures and sending them to an identification model, and taking the average value of the output result as the risk assessment score U.

3. The cold-source disaster-causing object early warning information display method based on a multifunctional monitoring buoy according to claim 2, characterized by, the preset window framing rule comprises: acquiring the number m of kinds of real-time multi-source monitoring data whose variance in a specified time period is greater than the corresponding specified variance threshold value; By the equation Confirming the current marquee time interval ; wherein, is an initial frame selection time interval, is a preset constant term and , is a preset category boundary amount, and n is a total amount of categories.

4. The cold-source disaster-causing object early warning information display method based on a multifunctional monitoring buoy according to claim 3, characterized by, the process of selecting at least c different sampling frame pictures comprises: If , then , else ; wherein , and are specified constants.

5. The cold-source disaster-causing object early warning information display method based on a multifunctional monitoring buoy according to claim 1, characterized by the process of performing threshold judgment according to the risk real-time score, and pushing and displaying early warning information when a risk prompt is needed comprises: Real-time scoring of current risk with a preset risk threshold If , it is determined that there is no risk, and if , a bubble push warning is performed on a visualized map according to position information corresponding to the multifunctional monitoring buoy.

6. A cold source disaster-causing object early warning information display device based on a multifunctional monitoring buoy, characterized by a processor having a program of the cold source disaster-causing material early warning information display method based on a multifunctional monitoring buoy according to any one of claims 1-5 running in the processor.

Images