A prediction method, system and storage medium for cold source disaster-causing objects

Through a multi-module fusion prediction algorithm of water flow, water temperature, turbulence, visibility and visible light data, an early warning of disasters caused by cold sources is achieved, and the problem that cannot be predicted in advance in the existing technology is solved, and the safety of nuclear power plants is improved.

CN118536655BActive Publication Date: 2024-11-08SHANGHAI APOLLO MACHINERY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410590494.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-13
Publication Date
2024-11-08
Estimated Expiration
2044-05-13

AI Technical Summary

Technical Problem

The existing technology cannot predict the dangers of disasters caused by cold sources in advance, and traditional water filtering systems are difficult to resist threats such as marine organisms, sea drift garbage and sea ice, and cannot effectively warn.

Method used

The water flow detection module, water temperature detection module, flow direction measuring instrument, visibility module and visible light module are used to obtain data, and the warning value is calculated through the preset template, and the cold source disaster prediction warning value is calculated using forward, reverse and fusion prediction algorithms. Achieve advance prediction of hazards caused by cold sources.

Benefits of technology

Through the integration of data from multiple modules, the hazards caused by cold sources can be accurately predicted in advance, improving the safety and operation stability of nuclear power plants.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118536655B_ABST
    Figure CN118536655B_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of nuclear power environment early warning, and discloses a prediction method, system and storage medium for cold source disaster-causing objects. The method comprises acquiring water flow data, and calculating a water flow warning value according to a water flow template; acquiring water temperature data, and calculating a water temperature warning value according to a water temperature template; acquiring turbulence data, and calculating a turbulence warning value according to a turbulence template; acquiring visibility data, and calculating a visibility warning value according to a visibility template; acquiring visible light data, and calculating a visible light warning value according to a visible light template; calculating a forward prediction warning value according to a water flow warning value and a water temperature warning value; calculating a reverse prediction warning value according to a turbulence warning value, a visibility warning value and a visible light warning value; calculating a cold source disaster prediction warning value according to the forward prediction warning value and the reverse prediction warning value; matching and outputting a prediction result from a prediction template according to the cold source disaster prediction warning value; and being able to make an early prediction of the danger of cold source disaster-causing objects.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of nuclear power environment early warning, and in particular to a prediction method, system and storage medium for cold source disaster-causing objects. Background Art

[0002] With the continuous development of nuclear power technology, the number of nuclear power plants is increasing, and the safety is also getting higher and higher. Among them, nuclear power plants are equipped with cold sources, which export the heat generated by the nuclear power plant in the process of power generation. Nuclear power plants are built near the sea, and the cold source is seawater, which can provide seawater with sufficient flow and water quality requirements for the important plant water system and circulating water system of the nuclear power plant.

[0003] As nuclear power plants are put into operation, cold source hazards will appear in the cold source. Cold source hazards refer to marine life, sea floating garbage, sea ice and other substances that enter the cold source system with the flow of seawater during the seawater intake process, which may cause an increase in the pressure difference of the filter device or insufficient water intake of the pump group, endangering production and operation.

[0004] Faced with a series of existing threats, the grille and filter configuration of the traditional water filtration system is difficult to resist. At present, domestic nuclear power plants have begun to develop independent cold source alarm devices, using infrared imaging devices to take pictures of water bodies, and analyze the water body pictures to determine the situation of cold source disaster objects. However, the above technology can only determine the danger of cold source disaster objects when a disaster occurs, and it is impossible to make advance predictions of the danger of cold source disaster objects. Summary of the invention

[0005] In order to make advance predictions of the dangers of cold source disaster-causing objects, the present application provides a prediction method, system and storage medium for cold source disaster-causing objects.

[0006] In the first aspect, the present application provides a method for predicting cold source disaster-causing objects, which adopts the following technical solution:

[0007] A method for predicting cold source disaster objects comprises the following steps:

[0008] A water flow detection module for measuring the flow rate of fluid at different positions is used to obtain water flow data, and a water flow warning value is calculated based on the water flow data and a preset water flow template; a water temperature detection module for measuring the temperature of fluid at different positions is used to obtain water temperature data, and a water temperature warning value is calculated based on the water temperature data and a preset water temperature template;

[0009] Based on a flow direction measuring instrument for measuring the distribution degree of flow direction changes at different water depths, turbulence data is obtained, and a turbulence warning value is calculated according to the turbulence data and a preset turbulence template; based on a visibility module for measuring visibility in water at different water depths, visibility data is obtained, and a visibility warning value is calculated according to the visibility data and a preset visibility template; based on a visible light module for measuring visible light absorption wavelength data at different water depths, visible light data is obtained, and a visible light warning value is calculated according to the visible light data and a preset visible light template;

[0010] Calculating a forward prediction warning value using a forward prediction algorithm according to the water flow warning value and the water temperature warning value;

[0011] Calculating a reverse prediction warning value using a reverse prediction algorithm according to the turbulence warning value, the visibility warning value and the visible light warning value;

[0012] Calculate the cold source disaster prediction and warning value using a fusion prediction algorithm according to the forward prediction and warning value and the reverse prediction and warning value;

[0013] According to the cold source disaster prediction and warning value, a prediction result is matched from a preset prediction template and the prediction result is output.

[0014] By adopting the above technical scheme, water flow data and water temperature data can be obtained through the water flow detection module and the water temperature detection module, and the water flow warning value and the water temperature warning value are calculated according to the water flow data and the water temperature data through the corresponding template. The water flow warning value and the water temperature warning value correspond to the flow of seawater and a forward prediction warning value is calculated. Turbulence data, visibility data and visible light data are obtained through the flow direction measuring instrument, the visibility module and the visible light module. The turbulence warning value, the visibility warning value and the visible light warning value are calculated according to the turbulence data, the visibility data and the visible light data through the corresponding template. The turbulence warning value, the visibility warning value and the visible light warning value correspond to the interference data and a reverse prediction warning value is calculated. The forward prediction warning value and the reverse prediction warning value are merged to obtain the cold source disaster prediction warning value, and the prediction result is matched from the prediction template, so that the cold source disaster-causing material danger can be predicted in advance.

[0015] Optionally, the forward prediction algorithm includes:

[0016] The water flow warning value corresponds to a water flow weight, and the water temperature warning value corresponds to a water temperature weight;

[0017] Use the weighted average algorithm to calculate the positive prediction warning value;

[0018] The water flow weight is positively correlated with the value of the water flow data. The higher the value of the water flow data, the greater the water flow weight, and the lower the value of the water flow data, the smaller the water flow weight; or, the water flow weight is positively correlated with the flow calculated by the water flow data. The less the flow, the smaller the water flow weight, and the more the flow, the greater the water flow weight;

[0019] The water temperature weight is set in a positive correlation with the value of the water temperature data. The higher the value of the water temperature data, the larger the water temperature weight, and the lower the value of the water temperature data, the smaller the water temperature weight; or, the water temperature weight is set in a positive correlation with the data uniformity of the water temperature data. The higher the data uniformity, the smaller the water temperature weight, and the lower the data uniformity, the larger the water temperature weight.

[0020] By adopting the above technical solution, a forward prediction algorithm is implemented to calculate accurate and practical forward prediction warning values.

[0021] Optionally, the reverse prediction algorithm includes:

[0022] The turbulence warning value corresponds to a turbulence weight, the visibility warning value corresponds to a visibility weight, and the visible light warning value corresponds to a visible light weight;

[0023] The weighted average algorithm is used to calculate the reverse prediction warning value;

[0024] The turbulence weight is positively correlated with the value of the turbulence data. The larger the value of the turbulence data, the larger the turbulence weight, and the smaller the value of the turbulence data, the smaller the turbulence weight.

[0025] The visibility weight is set in an anti-correlation with the value of the visibility data. The larger the value of the visibility data is, the smaller the visibility weight is, and the smaller the value of the visibility data is, the larger the visibility weight is.

[0026] The visible light weight is positively correlated with the absorption wavelength of the visible light data. The longer the absorption wavelength is, the smaller the visible light weight is, and the shorter the absorption wavelength is, the larger the visible light weight is.

[0027] By adopting the above technical solution, a reverse prediction algorithm is implemented to calculate accurate and practical reverse prediction warning values.

[0028] Optionally, the fusion prediction algorithm includes:

[0029] According to the forward prediction warning value, a corresponding forward weight is matched from a preset forward weight set;

[0030] According to the reverse prediction warning value, a corresponding reverse weight is matched from a preset reverse weight set;

[0031] Calculate the ratio of the forward weight to the reverse weight, and adjust the weight difference between the forward weight and the reverse weight according to the ratio; the larger the ratio, the larger the weight difference, and the smaller the ratio, the smaller the weight difference;

[0032] The weighted average algorithm is used to calculate the cold source disaster prediction and warning values.

[0033] By adopting the above technical solution, a fusion prediction algorithm is implemented to calculate accurate and practical cold source disaster prediction and warning values.

[0034] Optionally, the method further comprises the following steps:

[0035] The unmanned submersible carries the flow direction measuring instrument and the visibility module to perform measurement;

[0036] The diving speed of the unmanned submersible diving detection is adjusted in an anti-correlated manner according to the weight difference. The larger the weight difference, the slower the diving speed; the smaller the weight difference, the faster the diving speed.

[0037] By adopting the above technical solution, the diving speed of the unmanned submersible is adjusted according to the weight difference, which is beneficial to improving the accuracy of the data measured by the flow direction meter and the visibility module.

[0038] Optionally, the method further comprises the following steps:

[0039] adjusting the detection period of the flow direction measuring instrument and the visibility module according to the anti-correlation of the diving speed;

[0040] The slower the diving speed, the longer the detection period, and the faster the diving speed, the shorter the detection period.

[0041] By adopting the above technical solution, the detection cycle is adjusted according to the diving speed of the unmanned submersible, which is beneficial to improving the accuracy of the data measured by the flow direction meter, visibility module and visible light module.

[0042] Optionally, the method further comprises the following steps:

[0043] The unmanned submersible carries the water temperature module and the visible light module for measurement;

[0044] The diving acceleration of the unmanned submersible diving detection is adjusted according to the positive correlation of the weight difference. The larger the weight difference, the greater the diving acceleration, and the smaller the weight difference, the smaller the diving acceleration.

[0045] By adopting the above technical solution, the diving speed of the unmanned submersible is adjusted according to the weight difference, which is beneficial to improving the accuracy of the data measured by the flow direction meter and the visibility module.

[0046] Optionally, the method further comprises the following steps:

[0047] Positively adjusting the single detection duration of the water temperature module and the visible light module according to the diving acceleration;

[0048] The smaller the diving acceleration is, the shorter the single detection time is, and the larger the diving acceleration is, the longer the single detection time is.

[0049] By adopting the above technical solution, the duration of a single detection is adjusted according to the diving speed of the unmanned submersible, which is beneficial to improving the accuracy of the data measured by the water temperature module and the visible light module.

[0050] In the second aspect, the present application provides a prediction system for cold source disaster-causing objects, which adopts the following technical solutions:

[0051] A method, system and storage medium for predicting cold source disaster objects, comprising a processor, wherein the program of the method for predicting cold source disaster objects described in any one of the above items is run in the processor.

[0052] In a third aspect, the present application provides a storage medium, which adopts the following technical solution:

[0053] A storage medium stores a program of the method for predicting cold source disaster-causing objects as described in any one of the above.

[0054] In summary, the present application includes at least one of the following beneficial technical effects: water flow data and water temperature data can be obtained through the water flow detection module and the water temperature detection module, and the water flow warning value and the water temperature warning value are obtained by calculating the corresponding templates according to the water flow data and the water temperature data, the water flow warning value and the water temperature warning value correspond to the flow of seawater and a forward prediction warning value is calculated, turbulence data, visibility data and visible light data are obtained through the flow direction measuring instrument, the visibility module and the visible light module, and the turbulence warning value, the visibility warning value and the visible light warning value are obtained by calculating the corresponding templates according to the turbulence data, the visibility data and the visible light data, the turbulence warning value, the visibility warning value and the visible light warning value correspond to the interference data and a reverse prediction warning value is calculated, the forward prediction warning value and the reverse prediction warning value are merged to obtain the cold source disaster prediction warning value, the prediction result is matched from the prediction template, and the cold source disaster-causing material danger can be predicted in advance. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a schematic diagram of the hardware layout of a method for predicting cold source disaster objects in an embodiment of the present application.

[0056] Figure 2 It is a schematic diagram of the overall method flow of a method for predicting cold source disaster-causing objects in an embodiment of the present application.

[0057] Figure 3 It is a method flow chart of the forward prediction algorithm in the embodiment of the present application.

[0058] Figure 4 It is a method flow chart of the reverse prediction algorithm in the embodiment of the present application.

[0059] Figure 5 It is a schematic diagram of the method flow of the fusion prediction algorithm in the embodiment of the present application.

[0060] Figure numerals: 1. Water flow detection module; 2. Water temperature detection module; 3. Flow direction measuring instrument; 4. Visibility module; 5. Visible light module. DETAILED DESCRIPTION

[0061] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the attached Figure 1-5 Shown in.

[0062] In the description of this specification, the description with reference to the terms "certain embodiments", "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0063] The present application embodiment discloses a method for predicting cold source disaster objects, referring to Figure 1 and Figure 2 , including the following steps:

[0064] The water flow detection module 1 based on measuring the flow rate of the fluid at different positions obtains the water flow data, and the water flow warning value is calculated according to the water flow data and the preset water flow template. The water temperature detection module 2 based on measuring the temperature of the fluid at different positions obtains the water temperature data, and the water temperature warning value is calculated according to the water temperature data and the preset water temperature template. Among them, the preset water flow template can be calculated by template matching or convolutional neural network, and then calculated by table lookup. Similarly, the preset water temperature template can also be calculated by template matching or convolutional neural network, and then calculated by table lookup.

[0065] For example, in the sea or waters around the nuclear power plant, multiple water flow detection modules are evenly placed. The water flow detection module can use the Model-803 ROV underwater robot flow rate sensor. 4-6 water flow detection modules are evenly distributed in a fan-shaped area with the nuclear power plant as the center, and multiple water flow data can be obtained. Then, the data of multiple water flows are converted into a matrix, i.e., water flow data, and the water flow warning value is matched from the water flow template through the matrix. The water flow template contains a matrix composed of multiple water flow data and a water flow warning value corresponding to the matrix one by one. In this embodiment, the water flow data and the water flow warning value can correspond directly. In some other embodiments, the water flow data can correspond to the water flow warning value through the calculated value. For example, in the sea or waters around the nuclear power plant, multiple water temperature detection modules are evenly placed. The water temperature detection modules can use the ISD4000 series-temperature depth measurement Impact underwater depth and temperature sensor. 3-6 water temperature detection modules are evenly distributed in a fan-shaped area with the nuclear power plant as the center, and multiple water depth and water temperature data can be obtained. Then, the multiple water temperature data are converted into a matrix, that is, water temperature data, and the water temperature warning value is matched from the water temperature template through the water temperature data. The water temperature template contains a matrix composed of multiple water temperature data and a water temperature warning value corresponding to the matrix one by one. In this embodiment, the water temperature data and the water temperature warning value can correspond directly. In some other embodiments, the water temperature data can correspond to the water temperature warning value through the calculated value.

[0066] Reference Figure 1 and Figure 3 , the forward prediction algorithm is used to calculate the forward prediction warning value according to the water flow warning value and the water temperature warning value. The forward prediction algorithm includes: the water flow warning value corresponds to the water flow weight, the water temperature warning value corresponds to the water temperature weight; the weighted average algorithm is used to calculate the forward prediction warning value. In this way, the forward prediction algorithm is implemented to calculate an accurate and practical forward prediction warning value. For example, the water flow warning value is 10.0, the water flow weight is 0.7, the water temperature warning value is 5.0, and the water temperature weight is 0.3; the forward prediction warning value = 10.0 × 0.7 + 5.0 × 0.3 = 8.5. The above data reflects the change trend of the actual parameters and does not have the actual units of the actual parameters.

[0067] The water flow weight is positively correlated with the value of the water flow data. The higher the value of the water flow data, the greater the water flow weight, and the lower the value of the water flow data, the smaller the water flow weight; or, the water flow weight is positively correlated with the flow calculated by the water flow data. The less the flow calculated by the water flow data, the greater the water flow weight, and the more the flow calculated by the water flow data, the smaller the water flow weight. Based on the water flow data, the approximate flow of the sea or water area can be simply calculated.

[0068] The water temperature weight is positively correlated with the value of the water temperature data. The higher the value of the water temperature data, the greater the water temperature weight, and the lower the value of the water temperature data, the smaller the water temperature weight; or, the water temperature weight is positively correlated with the data uniformity of the water temperature data. The less the data uniformity of the water temperature data, the greater the water temperature weight, and the more the data uniformity of the water temperature data, the smaller the water temperature weight. The data uniformity of the water temperature data can be obtained by calculating the discreteness of multiple data in the water temperature data, and the discreteness algorithm can adopt the existing discrete value calculation method.

[0069] The turbulence data is obtained by using a flow direction measuring instrument 3 that measures the distribution degree of flow direction changes at different water depths, and the turbulence warning value is calculated based on the turbulence data and the preset turbulence template. The flow direction measuring instrument can use a measuring rod with a long flexible strip or a long flexible belt, and a strain gauge is provided on the flexible strip or the flexible belt. The stress of the strain gauge is used to determine whether the flow direction of the water is a stable flow direction or turbulence. A camera can also be set on the measuring rod to shoot the action mode of the flexible strip or the flexible belt, and the flow direction corresponding to the action mode is identified by the template matching method or the AI ​​algorithm, whether it is a stable flow direction or turbulence. The visibility module 4 that measures the visibility in the water at different water depths is used to obtain visibility data, and the visibility warning value is calculated based on the visibility data and the preset visibility template. The visible light module 5 that measures the visible light absorption wavelength data at different water depths is used to obtain visible light data, and the visible light warning value is calculated based on the visible light data and the preset visible light template. Both the visibility module 4 and the visible light module 5 can use image detection modules. For example, the distance that blurs the image in the sea reflects visibility, and the imaging effect of light of different wavelengths in the sea or the blurred distance reflects the wavelength of visible light absorption. The absorbed visible light has poor imaging effect on the seabed. The process of calculating the turbulence warning value, visibility warning value and visible light warning value is similar to the principle and data format of calculating the water flow warning value and water temperature warning value, which will not be repeated here.

[0070] Reference Figure 1 and Figure 4 , the reverse prediction warning value is calculated using the reverse prediction algorithm according to the turbulence warning value, visibility warning value and visible light warning value. The reverse prediction algorithm includes: the turbulence warning value corresponds to the turbulence weight, the visibility warning value corresponds to the visibility weight, and the visible light warning value corresponds to the visible light weight; the reverse prediction warning value is calculated using the weighted average algorithm. In this way, the reverse prediction algorithm is implemented to calculate an accurate and practical reverse prediction warning value. For example, the turbulence warning value is 5.0, the turbulence weight is 0.4; the visibility warning value is 4.0, the visibility weight is 0.4; the visible light warning value is 1.0, the visible light weight is 0.2, and the reverse prediction warning value = 5.0 × 0.4 + 4.0 × 0.4 + 1.0 × 0.2 = 3.8. The above data reflects the changing trend of the actual parameters and does not have the actual units of the actual parameters.

[0071] Among them, the turbulence weight is positively correlated with the value of the turbulence data. The larger the value of the turbulence data, the larger the turbulence weight, and the smaller the value of the turbulence data, the smaller the turbulence weight. The visibility weight is negatively correlated with the value of the visibility data. The larger the value of the visibility data, the smaller the visibility weight, and the smaller the value of the visibility data, the larger the visibility weight. The visible light weight is positively correlated with the absorption wavelength of the visible light data. The longer the absorption wavelength, the smaller the visible light weight, and the shorter the absorption wavelength, the larger the visible light weight.

[0072] Reference Figure 5 , the cold source disaster prediction and warning value is calculated using a fusion prediction algorithm based on the forward prediction and warning value and the reverse prediction and warning value. The fusion prediction algorithm includes: matching the corresponding forward weight from the preset forward weight set according to the forward prediction and warning value; matching the corresponding reverse weight from the preset reverse weight set according to the reverse prediction and warning value; calculating the ratio of the forward weight to the reverse weight, and adjusting the difference between the forward weight and the reverse weight according to the ratio; the larger the ratio, the larger the weight difference, and the smaller the ratio, the smaller the weight difference; using a weighted average algorithm to calculate the cold source disaster prediction and warning value. For example, there are multiple values ​​in the forward weight set, each value corresponds to a forward prediction and warning value, and there are multiple values ​​in the reverse weight set, each value corresponds to a reverse prediction and warning value. The forward prediction warning value is 8.5, and the corresponding forward weight is 1.1; the reverse prediction warning value is 3.8, and the corresponding reverse weight is 0.4; the cold source disaster prediction warning value is 8.5×1.1-3.8×0.4, and the result is 9.35-1.52=7.83. The ratio is 2.75, and the weight difference is 0.7. The difference can be enlarged or reduced according to the ratio. The fusion prediction algorithm is implemented to calculate accurate and practical cold source disaster prediction warning values.

[0073] According to the cold source disaster prediction and warning value, the prediction result is matched from the preset prediction template, and the prediction result is output. The prediction template can be a matrix corresponding to two groups of internal elements, one group of matrices is a plurality of cold source disaster prediction and warning values, and one group of matrices is a plurality of prediction results. The corresponding prediction result can be output according to the cold source disaster prediction and warning value. The content of the prediction result can be the percentage of the occurrence of the danger, or the remaining time of the danger, or the type of the danger, etc.

[0074] The water flow detection module 1, the water temperature detection module 2, the flow direction measuring instrument 3, the visibility module 4, and the visible light module 5 are all fixed near the nuclear power plant, and can also be carried by an unmanned submersible and moved underwater. The unmanned submersible can be a submersible that dives into deep water or a submersible that dives into shallow water.

[0075] In some other embodiments, it also includes: the unmanned submersible is equipped with a flow direction measuring instrument 3 and a visibility module 4 for measurement. The diving speed of the unmanned submersible diving detection is adjusted according to the anti-correlation of the weight difference. The larger the weight difference, the slower the diving speed, and the smaller the weight difference, the faster the diving speed. Adjusting the diving speed of the unmanned submersible according to the second difference is conducive to improving the accuracy of the data measured by the flow direction measuring instrument 3 and the visibility module 4. For example, when the weight difference is 0.7, the diving speed of the unmanned submersible is 5 meters per second; when the weight difference is 0.8, the diving speed of the unmanned submersible is 4 meters per second.

[0076] In some other embodiments, the detection cycle of the flow direction measuring instrument 3, the visibility module 4 and the visible light module 5 is adjusted according to the diving speed. The slower the diving speed, the longer the detection cycle, and the faster the diving speed, the shorter the detection cycle. Adjusting the detection cycle according to the diving speed of the unmanned submersible is conducive to improving the accuracy of the data measured by the flow direction measuring instrument 3, the visibility module 4 and the visible light module 5. For example, when the diving speed of the unmanned submersible is 5 meters per second, the detection cycle is 2 seconds; when the diving speed of the unmanned submersible is 4 meters per second, the detection cycle is 3 seconds.

[0077] In some other embodiments, the method further includes: the unmanned submersible is equipped with the water temperature module and the visible light module for measurement. The diving acceleration of the unmanned submersible diving detection is adjusted according to the positive correlation of the weight difference. The larger the weight difference, the greater the diving acceleration, and the smaller the weight difference, the smaller the diving acceleration. The diving speed of the unmanned submersible is adjusted according to the weight difference, which is conducive to improving the accuracy of the data measured by the flow direction measuring instrument and the visibility module.

[0078] In some other embodiments, the method further includes: positively adjusting the single detection time of the water temperature module and the visible light module according to the diving acceleration. The smaller the diving acceleration, the shorter the single detection time, and the greater the diving acceleration, the longer the single detection time. Adjusting the single detection time according to the diving speed of the unmanned submersible is conducive to improving the accuracy of the data measured by the water temperature module and the visible light module.

[0079] Water flow data and water temperature data can be obtained through the water flow detection module 1 and the water temperature detection module 2. Water flow warning values ​​and water temperature warning values ​​are calculated based on the water flow data and water temperature data through the corresponding templates. The water flow warning values ​​and water temperature warning values ​​correspond to the flow conditions of seawater and a forward prediction warning value is calculated. Turbulence data, visibility data and visible light data are obtained through the flow direction measuring instrument 3, the visibility module 4 and the visible light module 5. Turbulence warning values, visibility warning values ​​and visible light warning values ​​are calculated based on the turbulence data, visibility data and visible light data through the corresponding templates. Turbulence warning values, visibility warning values ​​and visible light warning values ​​correspond to interference data and a reverse prediction warning value is calculated. The forward prediction warning value and the reverse prediction warning value are merged to obtain a cold source disaster prediction warning value. The prediction result is matched from the prediction template, and the cold source disaster-causing material danger can be predicted in advance.

[0080] The embodiment of the present application further discloses a prediction system for cold source disaster-causing objects, comprising a processor, wherein the program of any one of the above-mentioned cold source disaster-causing object prediction methods is running on the processor.

[0081] The embodiment of the present application further discloses a storage medium storing a program of the method for predicting cold source disaster-causing objects as described in any one of the above.

[0082] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for predicting cold source disasters, characterized in that: The steps include: A water flow detection module for measuring the flow rate of fluid at different positions is used to obtain water flow data, and a water flow warning value is calculated based on the water flow data and a preset water flow template; a water temperature detection module for measuring the temperature of fluid at different positions is used to obtain water temperature data, and a water temperature warning value is calculated based on the water temperature data and a preset water temperature template; Based on a flow direction measuring instrument for measuring the distribution degree of flow direction changes at different water depths, turbulence data is obtained, and a turbulence warning value is calculated according to the turbulence data and a preset turbulence template; based on a visibility module for measuring visibility in water at different water depths, visibility data is obtained, and a visibility warning value is calculated according to the visibility data and a preset visibility template; based on a visible light module for measuring visible light absorption wavelength data at different water depths, visible light data is obtained, and a visible light warning value is calculated according to the visible light data and a preset visible light template; Calculating a forward prediction warning value using a forward prediction algorithm according to the water flow warning value and the water temperature warning value; Calculating a reverse prediction warning value using a reverse prediction algorithm according to the turbulence warning value, the visibility warning value and the visible light warning value; Calculate the cold source disaster prediction and warning value using a fusion prediction algorithm according to the forward prediction and warning value and the reverse prediction and warning value; Matching a prediction result from a preset prediction template according to the cold source disaster prediction and warning value, and outputting the prediction result; The forward prediction algorithm includes: The water flow warning value corresponds to a water flow weight, and the water temperature warning value corresponds to a water temperature weight; Use the weighted average algorithm to calculate the positive prediction warning value; The water flow weight is positively correlated with the value of the water flow data. The higher the value of the water flow data, the greater the water flow weight, and the lower the value of the water flow data, the smaller the water flow weight; or, the water flow weight is positively correlated with the flow calculated by the water flow data. The less the flow, the smaller the water flow weight, and the more the flow, the greater the water flow weight; The water temperature weight is set in a positive correlation with the value of the water temperature data. The higher the value of the water temperature data, the greater the water temperature weight, and the lower the value of the water temperature data, the smaller the water temperature weight; or, the water temperature weight is set in a positive correlation with the data uniformity of the water temperature data. The higher the data uniformity, the smaller the water temperature weight, and the lower the data uniformity, the greater the water temperature weight; The reverse prediction algorithm includes: The turbulence warning value corresponds to a turbulence weight, the visibility warning value corresponds to a visibility weight, and the visible light warning value corresponds to a visible light weight; The weighted average algorithm is used to calculate the reverse prediction warning value; The turbulence weight is positively correlated with the value of the turbulence data. The larger the value of the turbulence data, the larger the turbulence weight, and the smaller the value of the turbulence data, the smaller the turbulence weight. The visibility weight is set in an anti-correlation with the value of the visibility data. The larger the value of the visibility data is, the smaller the visibility weight is, and the smaller the value of the visibility data is, the larger the visibility weight is. The visible light weight is positively correlated with the absorption wavelength of the visible light data; the longer the absorption wavelength, the smaller the visible light weight, and the shorter the absorption wavelength, the larger the visible light weight; The fusion prediction algorithm includes: According to the forward prediction warning value, a corresponding forward weight is matched from a preset forward weight set; According to the reverse prediction warning value, a corresponding reverse weight is matched from a preset reverse weight set; Calculate the ratio of the forward weight to the reverse weight, and adjust the weight difference between the forward weight and the reverse weight according to the ratio; the larger the ratio, the larger the weight difference, and the smaller the ratio, the smaller the weight difference; The weighted average algorithm is used to calculate the cold source disaster prediction and warning values.

2. The method for predicting cold source disaster objects according to claim 1, characterized in that: The method further comprises the steps of: The unmanned submersible carries the flow direction measuring instrument and the visibility module to perform measurement; The diving speed of the unmanned submersible diving detection is adjusted in an anti-correlated manner according to the weight difference. The larger the weight difference, the slower the diving speed; the smaller the weight difference, the faster the diving speed.

3. The method for predicting cold source disaster-causing objects according to claim 2, characterized in that: The method further comprises the steps of: adjusting the detection period of the flow direction measuring instrument and the visibility module according to the anti-correlation of the diving speed; The slower the diving speed, the longer the detection period, and the faster the diving speed, the shorter the detection period.

4. The method for predicting cold source disaster objects according to claim 1, characterized in that: The method further comprises the steps of: The unmanned submersible is equipped with a water temperature module and the visible light module for measurement; The diving acceleration of the unmanned submersible diving detection is adjusted according to the positive correlation of the weight difference. The larger the weight difference, the greater the diving acceleration, and the smaller the weight difference, the smaller the diving acceleration.

5. The method for predicting cold source disaster-causing objects according to claim 4, characterized in that: The method further comprises the steps of: Positively adjusting the single detection duration of the water temperature module and the visible light module according to the diving acceleration; The smaller the diving acceleration is, the shorter the single detection time is, and the larger the diving acceleration is, the longer the single detection time is.

6. A prediction system for cold source disasters, characterized in that: The method comprises a processor in which a program of a method for predicting cold source disaster-causing objects as claimed in any one of claims 1 to 5 is run.

7. A storage medium, characterized in that: A program storing the method for predicting cold source disaster objects as claimed in any one of claims 1 to 5.