An underwater nuclear industry space monitoring system and method based on digital twin
The construction of an underwater nuclear industry space monitoring system through digital twin technology solves the problem of limited identification accuracy in the underwater environment, realizes efficient safety monitoring of nuclear industrial facilities, and overcomes the defect of high signal noise.
Patent Information
- Application Number
- CN202410111105.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-26
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-01-26
AI Technical Summary
The prior art is difficult to accurately identify and protect nuclear industrial facilities in underwater environments, and is limited by the limitations of visibility, electromagnetic environment and acoustic environment, resulting in limited identification accuracy and identification distance.
The underwater nuclear industrial space monitoring system based on digital twins is used to determine whether the underwater target is an abnormal target by constructing an identification area, calculating protection index, monitoring the signal-to-noise ratio of the sensor, training trajectory prediction model, and generating a digital twin model.
It improves the recognition accuracy and safety of underwater targets, reduces the dependence on single recognition elements, overcomes the defect of high signal noise, and realizes effective monitoring in a noisy environment.
Smart Images

Figure CN118134244B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of underwater target monitoring, and in particular to an underwater nuclear industry space monitoring system and method based on digital twins. Background Art
[0002] With the development of science and technology, people have gradually realized the advantages of nuclear energy in terms of economy, environmental protection, safety, etc. Nuclear energy technology has a significant role and value in solving low-carbon emissions and promoting sustainable development. Under the current development trend, in order to save land on land and solve the problem of thermal pollution, the construction of submarine nuclear industrial facilities has become the focus of attention in related fields.
[0003] Nuclear facilities require strict protection measures due to their inherent dangers and the serious consequences of being damaged. In traditional technical solutions, it is necessary to identify underwater targets and then alarm threatening underwater targets. However, due to the limitations of visibility, electromagnetic environment, and acoustic environment in underwater space, the recognition accuracy and recognition distance of underwater targets are affected. In the existing technology, it is difficult to protect the safety of nuclear industrial facilities under the condition of limited recognition accuracy of underwater targets. Summary of the invention
[0004] The purpose of the present invention is to provide an underwater nuclear industry space monitoring system and method based on digital twins to solve the problems raised in the above background technology.
[0005] In order to solve the above technical problems, the present invention provides the following technical solution: an underwater nuclear industry space monitoring method based on digital twins.
[0006] Step S100: in an area with a distance d from the underwater facility, construct an identification area for identifying underwater targets, obtain a monitoring strategy for the underwater targets, divide the identification area into a number of monitoring areas according to the monitoring strategy, and calculate the protection index of each monitoring area according to the conditions for monitoring the underwater targets;
[0007] Step S200: monitoring the underwater target through several types of sensors, each type of sensor corresponds to a type of identification element, and calculating the identification index of the underwater target according to the signal-to-noise ratio of the monitoring feedback signal corresponding to each identification element;
[0008] Step S300: Collecting recognition records of underwater targets, training an underwater target classification model, collecting historical records of different types of underwater targets traveling in the recognition area, and training a trajectory prediction model for underwater target driving trajectories;
[0009] Step S400: capturing the driving trajectory of the underwater target, obtaining the predicted trajectory of the underwater target, setting the monitoring area through which the predicted trajectory passes as the first type of target area, and establishing a digital twin model of the underwater target in the first type of target area according to the predicted trajectory of the underwater target and the monitoring strategy corresponding to the first target area;
[0010] Step S500: When an underwater target enters the monitoring area, the identification information corresponding to the identification elements of the underwater target is obtained and compared with the digital twin model. When the comparison conditions of the corresponding digital twin model are not met, it is determined to be an abnormal underwater target and the relevant management personnel are notified.
[0011] Furthermore, step S100 includes:
[0012] Step S101: The monitoring strategy for underwater targets includes: setting a number of necessary identification elements in each monitoring area, and each necessary identification element is set with a reference signal-to-noise ratio; the necessary identification element indicates the type of monitoring signal that needs to be captured in the process of underwater target identification within a certain monitoring area, wherein one necessary identification element corresponds to one monitoring signal, and the reference signal-to-noise ratio indicates the signal-to-noise ratio of the monitoring feedback signal of the necessary identification element;
[0013] The identification elements represent the types of underwater target physical properties extracted during the monitoring of underwater targets. These physical properties are used to describe the corresponding underwater targets.
[0014] Step S102: Obtain the monitoring area K farthest from the underwater facility i and K i Adjacent monitoring area K i+1 , K i The class names of all necessary identification elements are imported into the set E i , K i+1 The class names of all necessary identification elements are imported into the set E i+1 , calculate the first protection variation coefficient α1, where α1 = num i+1 -num i , num i+1 Indicates E i+1 The number of required identification element types, num i Indicates E i The number of necessary identification element types is calculated, and the element repetition set E is calculated. r , E r =E i+1 ∩E i , get E r The type of the jth identification element in K i The corresponding reference signal-to-noise ratio SNRj i and K i The corresponding reference signal-to-noise ratio SNR j i+1 , calculate the reference difference d of the type of the j-th identification element r j , where d r j =SNR j i+1 -SNR j i , traverse E r For all the identification elements in , the reference differences are calculated respectively and summed to obtain the second protection variation coefficient α2;
[0015] Different monitoring areas are distinguished according to the types of identification elements or the signal-to-noise ratio of monitoring feedback signals. The types of identification elements in the monitoring area increase as the distance from the underwater facility decreases. As the distance from the underwater facility increases, more necessary identification elements are required or the signal-to-noise ratio of the monitoring feedback signal requiring the necessary identification elements increases.
[0016] Step S103: Set the initial value of the protection index C0 and the monitoring area K i The corresponding protection index is C0, calculated with K i Adjacent monitoring area K i+1 Corresponding protection index C i+1 , where C i =α1×m+α2×n, where m and n are two constants, respectively, and m>n. The protection index of each monitoring area is calculated at once according to the order from far to near of the monitoring area to the underwater facilities;
[0017] α1 represents the change in the number of necessary identification elements in the two different monitoring areas where the underwater target passes, and α2 represents the change in the signal-to-noise ratio of the monitoring feedback signal that requires the necessary identification elements. The corresponding coefficients are multiplied to obtain the protection index of the monitoring area. The protection index represents the change in the strictness of monitoring in the two different monitoring areas where the underwater target passes during its travel.
[0018] Further, step S200 includes:
[0019] Step S201: the total number of types of all identification elements monitored for underwater targets in the identification area is set to N, a unit monitoring time is set, and a feedback signal of the identification element of the underwater target is collected once after each unit monitoring time. The number of types of identification elements when collecting feedback signals at a certain time is recorded as n0, and the first identification coefficient β1 corresponding to the collection of feedback signals at a certain time is calculated, β1=n0 / N;
[0020] Step S202: Obtain the corresponding feedback signal signal-to-noise ratio of each identification element of a certain underwater target when the feedback signal is collected once, and arrange the identification elements from high to low according to the signal-to-noise ratio to obtain a sequence L, in which h1, h2, h3, ..., and h k represents the signal-to-noise ratio of the feedback signal corresponding to the first, second, third, ... and kth identification elements in L, and calculates the change rate γ, where Among them, h p represents the signal-to-noise ratio of the feedback signal corresponding to the pth identification element in L, h p+1 Indicates the feedback signal-to-noise ratio corresponding to the p+1th identification element in L, and calculates the second identification coefficient β2, β2=γ-A, where A is a constant and satisfies the condition A≥1;
[0021] Arrange the signal-to-noise ratios of several feedback signals from high to low, calculate the decreasing rules of several signal-to-noise ratios, describe the decrease by the change of the decreasing slope, and take the decreasing slope -A as the boundary. When the decreasing slope is greater than -A, it is considered that the signal-to-noise ratio decreases slowly, and when the decreasing slope is less than -A, it is considered that the signal-to-noise ratio decreases rapidly.
[0022] Step S203: Calculate the recognition index res of the underwater target when the feedback signal is collected once, where res = β1×h1-β2×n0.
[0023] When the signal-to-noise ratio decreases slowly, there are more identification elements that can be referenced. When the signal-to-noise ratio decreases rapidly, there are fewer identification elements that can be referenced. Therefore, when the signal-to-noise ratio decreases slowly, it is more conducive to generating digital twins. Therefore, when the signal-to-noise ratio decreases more slowly, the recognition index is higher.
[0024] β1 indicates the type of underwater target identification elements identified at a certain moment. The larger β1 is, the more conducive it is to generate digital twins, so the larger β1 is, the higher the recognition index is;
[0025] Furthermore, step S400 includes:
[0026] Step S401: Identify underwater targets within a distance d from the underwater facility, set a certain underwater target captured by the sensor heading towards the underwater facility as UV, collect several groups of UV identification elements and monitoring feedback signals corresponding to the identification elements, classify the UV according to the classification model, and obtain the predicted trajectory P of the UV l ;
[0027] Step S402: Locate the UV position and set the UV position in P lThe monitoring area on the path and closest to UV is set as the first target monitoring area. The time t0 of the feedback signal of the last collected identification element before UV enters the first target monitoring area is obtained. The identification elements of UV within the time range of t0 and the signal-to-noise ratio of the monitoring feedback signal corresponding to the identification elements are collected and recorded in the state monitoring set ST0, where the q1th element in ST0 is (f ST0 q1 , snr ST0 q1 ), f ST0 q1 Indicates the q1th identification element in ST0, snr ST0 q1 represents the signal-to-noise ratio of the monitoring feedback signal corresponding to the q1th identification element in ST0;
[0028] Step S403: Obtain the necessary identification elements and the reference signal-to-noise ratio of the necessary identification elements of the first target monitoring area, and record them in the reference set RE, where the q2th element in RE is (f R q2 , snr R q2 ), where f R q2 Indicates the q2th identification element in RE, snr R q2 represents the reference signal-to-noise ratio corresponding to the q2th identification element in RE;
[0029] Step S404: compare the identification elements in the set ST0 and the set RE, obtain the identification elements that exist in ST0 and do not exist in RE, and obtain the signal-to-noise ratio of the monitoring feedback signal corresponding to the identification element from ST0, and record it in the set ST1;
[0030] Step S405: Set the tolerance threshold μ and adjust the q2th element in RE to (f R q2 ,avg q2 ), where avg q2 represents the signal-to-noise ratio range corresponding to the q2th identification element in RE, where avg q2 The value range is (snr R q2 ×(1-ρ1×μ),snr R q2 ×(1+ρ2×μ)), where ρ1 and ρ2 are the coefficients of the tolerance threshold μ, and satisfy the conditions ρ1>0, ρ2>0, ρ1+ρ2=1. All elements in RE are adjusted to obtain the set RE * , construct the description set DEC of the digital twin model, where DEC = RE *∩ST1;
[0031] One of the functions of digital twins is to simulate physical entities. In this solution, underwater targets are identified by monitoring feedback signals corresponding to the identification elements of underwater targets, and digital twins are created in the area where the underwater targets are about to arrive, that is, virtual targets are created within a certain range of monitoring feedback signals.
[0032] In an environment with high noise, although the virtual target is relatively fuzzy, this digital twin not only meets the attributes of the underwater target being monitored at the time, but also meets the monitoring requirements of the monitoring area. Therefore, after entering the corresponding monitoring area through the underwater target, the monitoring feedback signal of the underwater target can be compared with the monitoring feedback signal of the digital twin to determine whether the underwater target is an abnormal underwater target;
[0033] Furthermore, the tolerance threshold calculation step in step S405 includes:
[0034] Step S41: obtaining the distance d0 between the UV and the underwater device at time t0, obtaining the time t1 in the T1 time period before t0, the distance between the UV and the underwater device at time t1 is recorded as d1, obtaining the identification index res1 corresponding to the UV at time t1 and the identification index res0 at time t0;
[0035] Step S42: Calculate μ corresponding to UV in the first target monitoring area, μ=(res1-res0) / (d0-d1);
[0036] In the expression of μ, res1-res0 represents the increase in the recognition index after the underwater target moves a distance of d0-d1, and μ means the rate of change of the underwater target recognition index with the travel distance;
[0037] Furthermore, step S500 includes:
[0038] Step S501: after the UV enters the first target monitoring area, the identification elements of the UV and the monitoring feedback signals corresponding to the identification elements are collected and compared with the DEC;
[0039] Step S502: Classify the monitoring feedback signal of UV, the first category is RE * The identification elements included, the second category is the identification elements included in ST1;
[0040] Step S503: Obtain the monitoring feedback signal corresponding to the first type of identification element of UV, and * When the corresponding signal-to-noise ratio is outside the range, it is determined to be an abnormal underwater target;
[0041] Step S504: Obtain the last monitoring area that UV passes through before entering the first target monitoring area, and obtain the protection index C of the monitoring area a and the protection index C of the first target monitoring area b , calculate the change value of protection index ω, ω=(C b -C a ) / C b ;
[0042] Step S505: Get the element corresponding to the q3th identification element in ST1 (f ST1 q3 , snr ST1 q3 ), where f ST1 q3 Indicates the q3th identification element in ST1, snr ST1 q3 represents the signal-to-noise ratio of the monitoring feedback signal corresponding to the q3th identification element in ST1, and calculates snr * q3 =(1+ω)snr ST1 q3 , construct the adjusted element (f ST1 q3 , snr * q3 ), where snr * q3 Indicates SNR ST1 q3 The signal-to-noise ratio adjustment value is used to traverse the elements corresponding to each identification factor in ST1, and the adjusted elements are merged into the set ST1 * ;
[0043] Step S506: Obtain the monitoring feedback signal corresponding to the second type of identification element of UV. When the signal-to-noise ratio of the monitoring feedback signal is less than ST1 * When the signal-to-noise ratio adjustment value of the monitoring feedback signal corresponding to the identification element is reached, it is judged as an abnormal underwater target.
[0044] In order to better implement the above method, an underwater nuclear industry space monitoring system based on digital twin is also proposed. The system includes the following modules: a monitoring area management module, an underwater target management module, a historical data management module, a digital twin model management module and a judgment module. Among them, the monitoring area management module is used to manage the relevant data of the identification area and calculate the protection index of the monitoring area. The underwater target management module is used to monitor the underwater target and calculate the recognition index of the underwater target. The historical data management module is used to collect historical data and generate a trajectory prediction model of the underwater target's driving trajectory through relevant models. The digital twin model management module is used to generate a digital twin model of the underwater target. The judgment module is used to judge whether the underwater target is an abnormal underwater target.
[0045] Further, the monitoring area management module includes: an area information management unit, a protection change index calculation unit and a protection index calculation unit, wherein the area information management unit is used to manage the necessary identification elements and the reference signal-to-noise ratio of the necessary identification elements for each monitoring area, the protection change index calculation unit is used to calculate the first protection change index and the second protection change index, and the protection index calculation unit is used to calculate the protection index of each monitoring area;
[0046] Furthermore, the underwater target management module includes: an underwater target recognition unit, a recognition coefficient calculation unit and a recognition index calculation unit, wherein the underwater target recognition unit is used to receive a monitoring feedback signal corresponding to the recognition element, the recognition coefficient calculation unit is used to calculate a first recognition coefficient and a second recognition coefficient, and the recognition index calculation unit is used to calculate the recognition index of the underwater target;
[0047] Furthermore, the digital twin model management module includes: a numerical screening unit, a tolerance threshold calculation unit, a first adjustment unit and a second adjustment unit, wherein the numerical screening unit is used to extract corresponding identification element information, the tolerance threshold calculation unit is used to calculate the tolerance threshold, and the first adjustment unit is used to adjust all elements in RE to obtain the set RE * The second adjustment unit is used to traverse each element in ST1 and merge the adjusted elements into the set ST1 * .
[0048] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention collects monitoring feedback signals corresponding to the identification elements of underwater targets, combines the management rules in the management area, generates a digital twin of the underwater target in the corresponding management area, compares it with the underwater target, and determines whether the underwater target is an abnormal underwater target. A variety of identification element data are used to describe the management area and the underwater target respectively. The description method of multiple identification elements improves the resolution of a single identification element compared to replacement, and has the advantage of being easy to implement. Moreover, by the changing characteristics of the number of multiple identification elements, the dependence on a single identification element is reduced to overcome the defects of large signal noise and unstable monitoring signal reception in the underwater environment. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0050] Figure 1 This is a schematic diagram of the structure of a digital twin-based underwater nuclear industry space monitoring system in the present invention;
[0051] Figure 2 It is a flow chart of a method for underwater nuclear industry space monitoring based on digital twins in the patent of this invention. DETAILED DESCRIPTION
[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0053] See also Figure 1 and Figure 2 , the present invention provides a technical solution:
[0054] Step S100: in an area with a distance d from the underwater facility, construct an identification area for identifying underwater targets, obtain a monitoring strategy for the underwater targets, divide the identification area into a number of monitoring areas according to the monitoring strategy, and calculate the protection index of each monitoring area according to the conditions for monitoring the underwater targets;
[0055] Wherein, step S100 includes:
[0056] Step S101: The monitoring strategy for underwater targets includes: setting a number of necessary identification elements in each monitoring area, and each necessary identification element is set with a reference signal-to-noise ratio; the necessary identification element indicates the type of monitoring signal that needs to be captured in the process of underwater target identification within a certain monitoring area, wherein one necessary identification element corresponds to one monitoring signal, and the reference signal-to-noise ratio indicates the signal-to-noise ratio of the monitoring feedback signal of the necessary identification element;
[0057] During the implementation process, common underwater targets include: underwater frogmen, unmanned underwater vehicles (UUVs), underwater robots (ROVs), and unmanned surface vessels (RSVs);
[0058] Common identification elements include: 3D model information of underwater targets, latitude and longitude information of underwater targets, security radar sensor information, optoelectronic equipment sensor information;
[0059] Step S102: Obtain the monitoring area K farthest from the underwater facility i and K i Adjacent monitoring area K i+1 , K i The class names of all necessary identification elements are imported into the set E i , K i+1 The class names of all necessary identification elements are imported into the set E i+1 , calculate the first protection variation coefficient α1, where α1 = num i+1 -num i , num i+1 Indicates E i+1 The number of required identification element types, num i Indicates E i The number of necessary identification element types is calculated, and the element repetition set E is calculated. r , E r =E i+1 ∩E i , get E r The type of the jth identification element in K i The corresponding reference signal-to-noise ratio SNR j i and K i The corresponding reference signal-to-noise ratio SNR j i+1 , calculate the reference difference d of the type of the j-th identification element r j , where d r j =SNR j i+1 -SNR j i , traverse Er For all the identification elements in , the reference differences are calculated respectively and summed to obtain the second protection variation coefficient α2;
[0060] For example, K i The necessary identification elements and the reference signal-to-noise ratios corresponding to the necessary identification elements are (ef1, 5dB), (ef3, 3.7dB) and (ef4, 5dB), K i+1 The necessary identification elements and the reference signal-to-noise ratios corresponding to the necessary identification elements are (ef1, 5dB), (ef2, 3dB), (ef3, 4.5dB) and (ef4, 5.5dB), where the same identification element symbol represents the same identification element;
[0061] It is calculated that α1=1, α2=0.8+0.5=1.3;
[0062] Step S103: Set the initial value of the protection index C0 and the monitoring area K i The corresponding protection index is C0, calculated with K i Adjacent monitoring area K i+1 Corresponding protection index C i+1 , where C i =α1×m+α2×n, m and n are two constants respectively, among which m>n. The protection index of each monitoring area is calculated at once according to the order from far to near of the monitoring area to the underwater facilities.
[0063] Step S200: monitoring the underwater target through several types of sensors, each type of sensor corresponds to a type of identification element, and calculating the identification index of the underwater target according to the signal-to-noise ratio of the monitoring feedback signal corresponding to each identification element;
[0064] Wherein, step S200 includes:
[0065] Step S201: the total number of types of all identification elements monitored for underwater targets in the identification area is set to N, a unit monitoring time is set, and a feedback signal of the identification element of the underwater target is collected once after each unit monitoring time. The number of types of identification elements when collecting feedback signals at a certain time is recorded as n0, and the first identification coefficient β1 corresponding to the collection of feedback signals at a certain time is calculated, β1=n0 / N;
[0066] When N = 10, n0 = 3, β1 = 0.3;
[0067] Step S202: Obtain the corresponding feedback signal signal-to-noise ratio of each identification element of a certain underwater target when the feedback signal is collected once, and arrange the identification elements from high to low according to the signal-to-noise ratio to obtain a sequence L, in which h1, h2, h3, ..., and h krepresents the signal-to-noise ratio of the feedback signal corresponding to the first, second, third, ... and kth identification elements in L, and calculates the change rate γ, where Among them, h p represents the signal-to-noise ratio of the feedback signal corresponding to the pth identification element in L, h p+1 Indicates the feedback signal-to-noise ratio corresponding to the p+1th identification element in L, and calculates the second identification coefficient β2, β2=γ-A, where A is a constant and satisfies the condition A≥1;
[0068] For example, the arrangement of the signal-to-noise ratio of UV is: 4.2dB, 3.8dB and 2.9dB, and γ = 0.65 is calculated. When A = 1, β2 = -0.35 is obtained;
[0069] Step S203: Calculate the identification index res of the underwater target when the feedback signal is collected once, where res = β1×h1-β2×n0;
[0070] Calculate the res of UV, res = 0.3 × 4.2 + 0.35 × 3 = 2.31;
[0071] Step S300: Collecting recognition records of underwater targets, training an underwater target classification model, collecting historical records of different types of underwater targets traveling in the recognition area, and training a trajectory prediction model for underwater target driving trajectories;
[0072] Step S400: capturing the driving trajectory of the underwater target, obtaining the predicted trajectory of the underwater target, setting the monitoring area through which the predicted trajectory passes as the first type of target area, and establishing a digital twin model of the underwater target in the first type of target area according to the predicted trajectory of the underwater target and the monitoring strategy corresponding to the first target area;
[0073] Wherein, step S400 includes:
[0074] Step S401: Identify underwater targets within a distance d from the underwater facility, set a certain underwater target captured by the sensor heading towards the underwater facility as UV, collect several groups of UV identification elements and monitoring feedback signals corresponding to the identification elements, classify the UV according to the classification model, and obtain the predicted trajectory P of the UV l ;
[0075] Step S402: Locate the UV position and set the UV position in P lThe monitoring area on the path and closest to UV is set as the first target monitoring area. The time t0 of the feedback signal of the last collected identification element before UV enters the first target monitoring area is obtained. The identification elements of UV within the time range of t0 and the signal-to-noise ratio of the monitoring feedback signal corresponding to the identification elements are collected and recorded in the state monitoring set ST0, where the q1th element in ST0 is (f ST0 q1 , snr ST0 q1 ), f ST0 q1 Indicates the q1th identification element in ST0, snr ST0 q1 represents the signal-to-noise ratio of the monitoring feedback signal corresponding to the q1th identification element in ST0;
[0076] Step S403: Obtain the necessary identification elements and the reference signal-to-noise ratio of the necessary identification elements of the first target monitoring area, and record them in the reference set RE, where the q2th element in RE is (f R q2 , snr R q2 ), where f R q2 Indicates the q2th identification element in RE, snr R q2 represents the reference signal-to-noise ratio corresponding to the q2th identification element in RE;
[0077] Step S404: compare the identification elements in the set ST0 and the set RE, obtain the identification elements that exist in ST0 and do not exist in RE, and obtain the signal-to-noise ratio of the monitoring feedback signal corresponding to the identification element from ST0, and record it in the set ST1;
[0078] Step S405: Set the tolerance threshold μ and adjust the q2th element in RE to (f R q2 ,avg q2 ), where avg q2 represents the signal-to-noise ratio range corresponding to the q2th identification element in RE, where avg q2 The value range is (snr R q2 ×(1-ρ1×μ),snr R q2 ×(1+ρ2×μ)), where ρ1 and ρ2 are the coefficients of the tolerance threshold μ, and satisfy the conditions ρ1>0, ρ2>0, ρ1+ρ2=1. All elements in RE are adjusted to obtain the set RE * , construct the description set DEC of the digital twin model, where DEC = RE *∩ST1;
[0079] Wherein, step S405 includes:
[0080] Step S41: obtaining the distance d0 between the UV and the underwater device at time t0, obtaining the time t1 in the T1 time period before t0, the distance between the UV and the underwater device at time t1 is recorded as d1, obtaining the identification index res1 corresponding to the UV at time t1 and the identification index res0 at time t0;
[0081] Step S42: Calculate μ corresponding to UV in the first target monitoring area, μ=(res1-res0) / (d0-d1);
[0082] When res0 = 2.31, res1 = 3.05, d0 = 100m, d1 = 97m, μ = 0.247 is calculated;
[0083] Step S500: When an underwater target enters the monitoring area, the identification information corresponding to the identification element of the underwater target is obtained and compared with the digital twin model. If the comparison condition of the corresponding digital twin model is not met, it is determined to be an abnormal underwater target and the relevant management personnel are notified;
[0084] Wherein, step S500 includes:
[0085] Step S501: after the UV enters the first target monitoring area, the identification elements of the UV and the monitoring feedback signals corresponding to the identification elements are collected and compared with the DEC;
[0086] Step S502: Classify the monitoring feedback signal of UV, the first category is RE * The identification elements included, the second category is the identification elements included in ST1;
[0087] Step S503: Obtain the monitoring feedback signal corresponding to the first type of identification element of UV, and * When the corresponding signal-to-noise ratio is outside the range, it is determined to be an abnormal underwater target;
[0088] Step S504: Obtain the last monitoring area that UV passes through before entering the first target monitoring area, and obtain the protection index C of the monitoring area a and the protection index C of the first target monitoring area b , calculate the change value of protection index ω, ω=(C b -C a ) / C b ;
[0089] For example, C b , =2.5, C a =1.8, we get ω=0.28;
[0090] Step S505: Get the element corresponding to the q3th identification element in ST1 (f ST1 q3 , snr ST1 q3 ), where f ST1 q3 Indicates the q3th identification element in ST1, snr ST1 q3 represents the signal-to-noise ratio of the monitoring feedback signal corresponding to the q3th identification element in ST1, and calculates snr * q3 =(1+ω)snr ST1 q3 , construct the adjusted element (f ST1 q3 , snr * q3 ), where snr * q3 Indicates SNR ST1 q3 The signal-to-noise ratio adjustment value is used to traverse the elements corresponding to each identification factor in ST1, and the adjusted elements are merged into the set ST1 * ;
[0091] Step S506: Obtain the monitoring feedback signal corresponding to the second type of identification element of UV. When the signal-to-noise ratio of the monitoring feedback signal is less than ST1 * When the signal-to-noise ratio adjustment value of the monitoring feedback signal corresponding to the identification element is reached, it is judged as an abnormal underwater target.
[0092] The system includes:
[0093] Monitoring area management module, underwater target management module, historical data management module, digital twin model management module and judgment module;
[0094] The monitoring area management module is used to manage the relevant data of the identification area and calculate the protection index of the monitoring area. The monitoring area management module includes: an area information management unit, a protection change index calculation unit and a protection index calculation unit. The area information management unit is used to manage the necessary identification elements and the reference signal-to-noise ratio of the necessary identification elements for each monitoring area. The protection change index calculation unit is used to calculate the first protection change index and the second protection change index. The protection index calculation unit is used to calculate the protection index of each monitoring area.
[0095] The underwater target management module is used to monitor the underwater target and calculate the recognition index of the underwater target. The underwater target management module includes: an underwater target recognition unit, a recognition coefficient calculation unit and a recognition index calculation unit. The underwater target recognition unit is used to receive the monitoring feedback signal corresponding to the recognition element, the recognition coefficient calculation unit is used to calculate the first recognition coefficient and the second recognition coefficient, and the recognition index calculation unit is used to calculate the recognition index of the underwater target.
[0096] Among them, the historical data management module is used to collect historical data and generate a trajectory prediction model of the underwater target's driving trajectory through relevant models;
[0097] The digital twin model management module is used to generate a digital twin model of an underwater target. The digital twin model management module includes: a numerical screening unit, a tolerance threshold calculation unit, a first adjustment unit and a second adjustment unit. The numerical screening unit is used to extract corresponding identification element information, the tolerance threshold calculation unit is used to calculate the tolerance threshold, and the first adjustment unit is used to adjust all elements in RE to obtain a set RE. * The second adjustment unit is used to traverse each element in ST1 and merge the adjusted elements into the set ST1 * ;
[0098] Among them, the judgment module is used to judge whether the underwater target is an abnormal underwater target.
[0099] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0100] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A method for underwater nuclear industry space monitoring based on digital twins, characterized in that: The method comprises the following steps: Step S100: in an area with a distance d from the underwater facility, construct an identification area for identifying underwater targets, obtain a monitoring strategy for the underwater targets, divide the identification area into a number of monitoring areas according to the monitoring strategy, and calculate the protection index of each monitoring area according to the conditions for monitoring the underwater targets; Step S100 includes: Step S101: The monitoring strategy for underwater targets includes: setting a number of necessary identification elements in each monitoring area, and each necessary identification element is set with a reference signal-to-noise ratio; the necessary identification element indicates the type of monitoring signal that needs to be captured in the process of underwater target identification within a certain monitoring area, wherein one necessary identification element corresponds to one monitoring signal, and the reference signal-to-noise ratio indicates the signal-to-noise ratio of the monitoring feedback signal of the necessary identification element; Step S102: Obtain the monitoring area K farthest from the underwater facility i and K i Adjacent monitoring area K i+1 , K i The class names of all necessary identification elements are imported into the set E i , K i+1 The class names of all necessary identification elements are imported into the set E i+1 , calculate the first protection variation coefficient α1, where α1 = num i+1 -num i , num i+1 Indicates E i+1 The number of required identification element types, num i Indicates E i The number of necessary identification element types is calculated, and the element repetition set E is calculated. r , E r =E i+1 ∩E i , get E r The type of the jth identification element in K i The corresponding reference signal-to-noise ratio SNR j i and K i The corresponding reference signal-to-noise ratio SNR j i+1 , calculate the reference difference d of the type of the j-th identification element r j , where d r j =SNR j i+1 -SNR j i , traverse E r For all the identification elements in , the reference differences are calculated respectively and summed to obtain the second protection variation coefficient α2; Step S103: Set the initial value of the protection index C0 and the monitoring area K i The corresponding protection index is C0, calculated with K i Adjacent monitoring area K i+1 Corresponding protection index C i+1 , where C i =α1×m+α2×n, where m and n are two constants, respectively, and m>n. The protection index of each monitoring area is calculated at once according to the order from far to near of the monitoring area to the underwater facilities; Step S200: monitoring the underwater target through several types of sensors, each type of sensor corresponds to a type of identification element, and calculating the identification index of the underwater target according to the signal-to-noise ratio of the monitoring feedback signal corresponding to each identification element; Step S200 includes: Step S201: the total number of types of all identification elements monitored for underwater targets in the identification area is set to N, a unit monitoring time is set, and a feedback signal of the identification element of the underwater target is collected once after each unit monitoring time. The number of types of identification elements when collecting feedback signals at a certain time is recorded as n0, and the first identification coefficient β1 corresponding to the collection of feedback signals at a certain time is calculated, β1=n0 / N; Step S202: Obtain the corresponding feedback signal signal-to-noise ratio of each identification element of a certain underwater target when the feedback signal is collected once, and arrange the identification elements from high to low according to the signal-to-noise ratio to obtain a sequence L, in which h1, h2, h3, ..., and h k represents the signal-to-noise ratio of the feedback signal corresponding to the first, second, third, ... and kth identification elements in L, and calculates the change rate γ, where Among them, h p represents the signal-to-noise ratio of the feedback signal corresponding to the pth identification element in L, h p+1 Indicates the feedback signal-to-noise ratio corresponding to the p+1th identification element in L, and calculates the second identification coefficient β2, β2=γ-A, where A is a constant and satisfies the condition A≥1; Step S203: Calculate the identification index res of the underwater target when the feedback signal is collected once, where res = β1×h1-β2×n0; Step S300: Collecting recognition records of underwater targets, training an underwater target classification model, collecting historical records of different types of underwater targets traveling in the recognition area, and training a trajectory prediction model for underwater target driving trajectories; Step S400: capturing the driving trajectory of the underwater target, obtaining the predicted trajectory of the underwater target, setting the monitoring area through which the predicted trajectory passes as the first type of target area, and establishing a digital twin model of the underwater target in the first type of target area according to the predicted trajectory of the underwater target and the monitoring strategy corresponding to the first target area; Step S400 includes: Step S401: Identify underwater targets within a distance d from the underwater facility, set a certain underwater target captured by the sensor heading towards the underwater facility as UV, collect several groups of UV identification elements and monitoring feedback signals corresponding to the identification elements, classify the UV according to the classification model, and obtain the predicted trajectory P of the UV l ; Step S402: Locate the UV position and set the UV position in P l The monitoring area on the path and closest to UV is set as the first target monitoring area. The time t0 of the feedback signal of the last collected identification element before UV enters the first target monitoring area is obtained. The identification elements of UV within the time range of t0 and the signal-to-noise ratio of the monitoring feedback signal corresponding to the identification elements are collected and recorded in the state monitoring set ST0, where the q1th element in ST0 is (f ST0 q1 , snr ST0 q1 ), f ST0 q1 Indicates the q1th identification element in ST0, snr ST0 q1 represents the signal-to-noise ratio of the monitoring feedback signal corresponding to the q1th identification element in ST0; Step S403: Obtain the necessary identification elements and the reference signal-to-noise ratio of the necessary identification elements of the first target monitoring area, and record them in the reference set RE, where the q2th element in RE is (f R q2 , snr R q2 ), where f R q2 Indicates the q2th identification element in RE, snr R q2 represents the reference signal-to-noise ratio corresponding to the q2th identification element in RE; Step S404: compare the identification elements in the set ST0 and the set RE, obtain the identification elements that exist in ST0 and do not exist in RE, and obtain the signal-to-noise ratio of the monitoring feedback signal corresponding to the identification element from ST0, and record it in the set ST1; Step S405: Set the tolerance threshold μ and adjust the q2th element in RE to (f R q2 ,avg q2 ), where avg q2 represents the signal-to-noise ratio range corresponding to the q2th identification element in RE, where avg q2 The value range is (snr R q2 ×(1-ρ1×μ), snr R q2 ×(1+ρ2×μ)), where ρ1 and ρ2 are the coefficients of the tolerance threshold μ, and satisfy the conditions ρ1>0, ρ2>0, ρ1+ρ2=1. All elements in RE are adjusted to obtain the set RE * , construct the description set DEC of the digital twin model, where DEC = RE * ∩ST1; Step S500: When an underwater target enters the monitoring area, the identification information corresponding to the identification element of the underwater target is obtained and compared with the digital twin model. If the comparison condition of the corresponding digital twin model is not met, it is determined to be an abnormal underwater target and the relevant management personnel are notified; Step S500 includes: Step S501: after the UV enters the first target monitoring area, the identification elements of the UV and the monitoring feedback signals corresponding to the identification elements are collected and compared with the DEC; Step S502: Classify the monitoring feedback signal of UV, the first category is RE * The identification elements included, the second category is the identification elements included in ST1; Step S503: Obtain the monitoring feedback signal corresponding to the first type of identification element of UV, and * When the corresponding signal-to-noise ratio is outside the range, it is determined to be an abnormal underwater target; Step S504: Obtain the last monitoring area that UV passes through before entering the first target monitoring area, and obtain the protection index C of the monitoring area a and the protection index C of the first target monitoring area b , calculate the change value of protection index ω, ω=(C b -C a ) / C b ; Step S505: Get the element corresponding to the q3th identification element in ST1 (f ST1 q3 , snr ST1 q3 ), where f ST1 q3 Indicates the q3th identification element in ST1, snr ST1 q3 represents the signal-to-noise ratio of the monitoring feedback signal corresponding to the q3th identification element in ST1, and calculates snr * q3 =(1+ω)snr ST1 q3 , construct the adjusted element (f ST1 q3 , snr * q3 ), where snr * q3 Indicates SNR ST1 q3 The signal-to-noise ratio adjustment value is used to traverse the elements corresponding to each identification factor in ST1, and the adjusted elements are merged into the set ST1 * ; Step S506: Obtain the monitoring feedback signal corresponding to the second type of identification element of UV. When the signal-to-noise ratio of the monitoring feedback signal is less than ST1 * When the signal-to-noise ratio adjustment value of the monitoring feedback signal corresponding to the identification element is reached, it is judged as an abnormal underwater target.
2. According to claim 1, a method for underwater nuclear industry space monitoring based on digital twins is characterized in that: The tolerance threshold calculation step in step S405 includes: Step S41: obtaining the distance d0 between the UV and the underwater device at time t0, obtaining the time t1 in the T1 time period before t0, the distance between the UV and the underwater device at time t1 is recorded as d1, obtaining the identification index res1 corresponding to the UV at time t1 and the identification index res0 at time t0; Step S42: Calculate μ corresponding to UV in the first target monitoring area, μ=(res1-res0) / (d0-d1).
3. An underwater nuclear industry space monitoring system for the underwater nuclear industry space monitoring method based on digital twins according to any one of claims 1 to 2, characterized in that: The system includes the following modules: a monitoring area management module, an underwater target management module, a historical data management module, a digital twin model management module and a judgment module, wherein the monitoring area management module is used to manage the relevant data of the identification area and calculate the protection index of the monitoring area; the underwater target management module is used to monitor the underwater target and calculate the identification index of the underwater target; the historical data management module is used to collect historical data and generate a trajectory prediction model of the underwater target's driving trajectory through relevant models; the digital twin model management module is used to generate a digital twin model of the underwater target; and the judgment module is used to judge whether the underwater target is an abnormal underwater target.
4. The underwater nuclear industry space monitoring system according to claim 3 is characterized by: The monitoring area management module includes: an area information management unit, a protection change index calculation unit and a protection index calculation unit, wherein the area information management unit is used to manage the necessary identification elements and the reference signal-to-noise ratio of the necessary identification elements for each monitoring area, the protection change index calculation unit is used to calculate the first protection change index and the second protection change index, and the protection index calculation unit is used to calculate the protection index of each monitoring area.
5. The underwater nuclear industry space monitoring system according to claim 4 is characterized in that: The underwater target management module includes: an underwater target recognition unit, a recognition coefficient calculation unit and a recognition index calculation unit, wherein the underwater target recognition unit is used to receive a monitoring feedback signal corresponding to the recognition element, the recognition coefficient calculation unit is used to calculate a first recognition coefficient and a second recognition coefficient, and the recognition index calculation unit is used to calculate the recognition index of the underwater target.
6. The underwater nuclear industry space monitoring system according to claim 5, characterized in that: The digital twin model management module includes: a numerical screening unit, a tolerance threshold calculation unit, a first adjustment unit and a second adjustment unit, wherein the numerical screening unit is used to extract the corresponding identification element information, the tolerance threshold calculation unit is used to calculate the tolerance threshold, and the first adjustment unit is used to adjust all elements in RE to obtain the set RE * The second adjustment unit is used to traverse each element in ST1 and merge the adjusted elements into the set ST1 * .
