An automatic detection system for online insulation monitoring of marine cables

Abstract

The invention discloses an automatic detection system for online insulation monitoring of ship cables, relates to the technical field of ship cable insulation detection, and comprises a hull model module, a cable model module, a hull force monitoring module, a hull deformation monitoring module, a hull deformation analysis module, a cable deformation analysis module, an environmental monitoring module, a cable hardness prediction module, and a cable safety data analysis module; the automatic detection system for online insulation monitoring of ship cables analyzes the relationship between cable hardness and environmental data changes, thereby predicting the hardness of the cable through the change curve of environmental data, reducing the detection frequency of the cable hardness and reducing the maintenance cost, and updating the cable hardness prediction model through regularly detected cable hardness data to ensure the accuracy of model prediction, comparing the insulation strength predicted based on regression analysis with a set insulation strength standard value, judging whether the cable is abnormal, and reminding the cable to be replaced and maintained when abnormal.

Description

Technical Field

[0001] The invention relates to the technical field of insulation detection of ship cables, and in particular to an automatic detection system for online insulation monitoring of ship cables. Background Art

[0002] During operation, electrical equipment is always under the influence of various external factors, and its performance will continue to change. These external factors mainly include external electric field, environment, high voltage, corrosion and machinery. Under the influence of these adverse factors, power equipment is more prone to unpredictable failures, and serious problems may even lead to power outages. Therefore, it is necessary to ensure the insulation of equipment cables and cables, especially for cables on ships. When ships are sailing on the water, the cables on them are in a high humidity environment for a long time and are more susceptible to corrosion from seawater, river water, etc. Therefore, it is particularly necessary to ensure the insulation performance of the cables on them to ensure the safe operation of electrical equipment on board.

[0003] The prior art with publication number CN117782957A discloses a method and system for testing the aging performance of a shipboard cable, and relates to the field of data processing technology. The method comprises: using a vibration test device to perform a vibration test on the shipboard cable, simulating the actual working conditions of the cable on the ship, recording the vibration frequency, amplitude and duration, and calculating the dynamic factor according to the vibration frequency, amplitude and duration; using a dielectric loss tangent value tester to perform non-destructive testing on the shipboard cable, and obtaining the dielectric loss tangent value of the cable insulation material; substituting the dielectric loss tangent value and the dynamic factor into the thermal life equation, and calculating the aging performance evaluation result of the shipboard cable. The present invention can simulate the thermal aging and mechanical aging process of the cable under actual working conditions, so as to more truly reflect the aging performance of the cable.

[0004] However, when ships sail on rivers and seas, the environment is more severe and they are more susceptible to factors such as weather and waves. Not only will the harsh environment cause the cables to be corroded and their service life to be shortened, but strong winds, waves and other factors may also cause slight deformation of the hull, changing the stress on the cable and increasing the mechanical loss of the cable, thereby reducing the service life of the cable. Summary of the invention

[0005] The object of the present invention is to provide an automatic detection system for online insulation monitoring of shipboard cables to solve the above-mentioned deficiencies in the prior art.

[0006] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: an automatic detection system for online insulation monitoring of ship cables, comprising a hull model module, a cable model module, a hull force monitoring module, a hull deformation monitoring module, a hull deformation analysis module, a cable deformation analysis module, an environmental monitoring module, a cable hardness prediction module, and a cable safety data analysis module;

[0007] The hull model module is used to establish a hull assembly model according to the actual structure and materials of the hull, wherein the hull assembly model truly restores the various structures, parts, materials, etc. of the hull;

[0008] The cable model module is used to establish a cable model and assemble the cable into the hull assembly model according to the actual installation position of the cable;

[0009] The hull force monitoring module is used to monitor the external force on the hull and obtain the hull force data. For example, a strain gauge can be attached to the hull surface to measure the strain of the material to infer the force magnitude;

[0010] The hull deformation monitoring module is used to monitor the deformation of the hull setting position and obtain the hull deformation data. For example, strain gauges, optical fiber sensors, laser rangefinders, etc. can be installed at the setting position to realize deformation monitoring of the setting position, such as bending, elongation, displacement, etc.

[0011] The hull deformation analysis module is used to perform force analysis based on the hull assembly model to obtain a hull force analysis model, which is used to analyze the hull deformation data at various locations of the hull assembly model corresponding to various hull force data under various loads of the hull assembly model;

[0012] The hull deformation analysis module is also used to calibrate the hull force model based on the hull force data and the hull deformation data.

[0013] The cable deformation analysis module is used to extract the deformation data of the hull position corresponding to the cable from the hull deformation data analyzed by the hull deformation analysis module to obtain the cable deformation data;

[0014] The environmental monitoring module is used to obtain environmental data on the hull, and the environmental data includes temperature and humidity. The environmental monitoring module can use a temperature sensor and a humidity sensor to monitor the temperature and humidity respectively.

[0015] The cable hardness prediction module is used to detect the hardness of the cable to obtain cable hardness data, and is also used to obtain environmental data, draw an environmental data change curve, and train a deep learning model based on the environmental data change curve and the cable hardness data to obtain a cable hardness prediction model, which is used to output the corresponding cable hardness data prediction value based on the input environmental data change curve; during the training process, the environmental data change curve and the cable hardness data are used as samples, and the environmental data change curve is used as input and the cable hardness data is used as output.

[0016] The cable safety data analysis module is also used to test the safety elongation and insulation strength of the cable when testing the hardness data of each cable. The safety elongation is the maximum elongation of the cable when the cable surface is guaranteed to be undamaged. Based on the cable hardness data, the safety elongation and the insulation strength, regression analysis is performed to obtain a safety elongation regression model and an insulation strength regression model, which are used to calculate the corresponding safety elongation prediction value and insulation strength prediction value based on the cable hardness data.

[0017] The cable safety data analysis module is also used to determine whether the cable deformation data is greater than the predicted value of the safe elongation at the corresponding time, and if so, an early warning is issued; at the same time, it is used to determine whether the predicted value of the insulation strength is less than the set insulation strength standard value, and if so, an early warning is issued.

[0018] Furthermore, the cable hardness prediction module is also used to obtain the detected cable hardness data and train and update the cable hardness prediction model, including the following steps:

[0019] A1. Perform hardness test on the cable according to the set period, and save the obtained cable hardness data into the test sample set. During the test, the cables on board are divided into multiple sections, and part of the cable in each section is taken as the test sample for hardness test;

[0020] A2. Determine whether the number of cable hardness data in the test sample set is greater than or equal to the set sample number;

[0021] A3. If yes, the cable hardness prediction model is trained and updated using the test sample set, so that the cable hardness prediction model is regularly calibrated using the tested cable hardness data to ensure the prediction accuracy of the cable prediction model.

[0022] Furthermore, the cable safety data analysis module obtains a safety elongation regression model, comprising the following steps:

[0023] B1. Obtain cables with different hardness data;

[0024] B2. Performing a tensile test on the cables of each hardness data, gradually increasing the stretching length during the tensile test, and performing ultrasonic flaw detection on the cables to determine whether there is mechanical damage on the cable surface;

[0025] B3. If not, return to B2. If yes, obtain the elongation of the cable at this time to obtain the safe elongation of the cable corresponding to the hardness data. When performing the tensile test, multiple tensile tests can be performed on the cable of each hardness data to obtain multiple safe elongations under the corresponding hardness data, and finally the average value of the multiple safe elongations is taken as the safe elongation corresponding to the hardness data of the cable;

[0026] B4. Based on the hardness data of the cable and the safe elongation corresponding to the hardness data, a regression analysis is performed to obtain a safe elongation regression model, which is used to output the corresponding predicted value of the safe elongation based on the input hardness data.

[0027] Furthermore, the cable safety data analysis module obtains an insulation strength regression model, comprising the following steps:

[0028] C1. Obtain cables with different hardness data;

[0029] C2. Conduct insulation strength tests on cables with different hardness data respectively to obtain insulation strength data corresponding to the cables with different hardness data;

[0030] C3. Perform regression analysis based on the hardness data of the cable and the insulation strength data corresponding to the hardness data to obtain an insulation strength regression model, which is used to output an insulation strength prediction value based on the input hardness data.

[0031] Furthermore, the cable safety data analysis module is also used to determine whether the cable deformation data is greater than the predicted value of the safety elongation at the corresponding time, and if so, an early warning is issued, including the following steps:

[0032] Acquire monitoring data of a hull force monitoring module to obtain historical hull force data of the hull;

[0033] Analyzing the historical hull force data based on the box plot, filtering out abnormal historical hull force data, and obtaining a normal hull force data interval of the hull;

[0034] Analyze the normal force data interval of the hull based on the hull force analysis model to obtain the normal deformation data interval of the hull, and extract the deformation data of the hull position corresponding to the cable to obtain the normal deformation data interval of the cable;

[0035] Input the current environmental data change curve into the cable hardness prediction model to obtain the current cable hardness data prediction value, and input the current cable hardness data prediction value into the safety elongation regression model to obtain the current safety elongation prediction value;

[0036] It is determined whether the current predicted safe elongation value is greater than the normal deformation data interval of the cable. If not, a first type of warning is issued.

[0037] Furthermore, the cable safety data analysis module is also used to determine whether the cable deformation data is greater than the predicted value of the safe elongation at the corresponding time, and if so, an early warning is issued, and the following steps are also included:

[0038] Obtain real-time hull force data;

[0039] Analyzing the real-time hull force data based on the hull force analysis model to obtain the real-time hull deformation data, and extracting the deformation data of the hull position corresponding to the cable to obtain the real-time cable deformation data;

[0040] It is determined whether the real-time deformation data of the cable is greater than the current safe elongation. If so, a second type of warning is issued.

[0041] Further, the step of judging whether the predicted insulation strength value is less than the set insulation strength standard value and issuing an early warning if so comprises the following steps:

[0042] Set the insulation strength standard value, where the insulation strength standard value can be set according to industry standards. For example, the insulation strength standard of ship cables usually requires that the insulation be guaranteed when the test voltage applied within 1 minute is 2500 volts;

[0043] Input the current environmental data change curve into the cable hardness prediction model to obtain the current cable hardness data prediction value, and input the current cable hardness data prediction value into the insulation strength regression model to obtain the current insulation strength prediction value;

[0044] It is determined whether the current insulation strength prediction value is greater than or equal to the insulation strength standard value. If not, a second type of warning is issued.

[0045] 1. Compared with the prior art, the present invention provides an automatic detection system for online insulation monitoring of ship cables. By setting a hull model module, a cable model module, a hull force monitoring module, a hull deformation monitoring module, a hull deformation analysis module, and a cable deformation analysis module, a three-dimensional assembly model of the hull is established, which accurately reflects the structure and material of the hull, facilitates force analysis, and can simulate and analyze the deformation conditions of various parts of the hull according to the external force received by the monitored hull, thereby obtaining the cable deformation conditions reflected by the deformation conditions at the hull cable, and can correct the results of the model analysis through the deformation conditions monitored by the hull deformation monitoring module set in some areas, thereby improving the accuracy of the hull deformation analysis and the cable deformation analysis.

[0046] 2. Compared with the prior art, the present invention provides an automatic detection system for online insulation monitoring of marine cables. By setting an environmental monitoring module and a cable hardness prediction module, the cable hardness prediction model can be obtained by analyzing the relationship between the cable hardness and the changes in environmental data such as temperature and humidity, so as to predict the hardness of the cable through the change curve of the environmental data, and the cable hardness model can be updated by regularly performing hardness tests on the cable and using the cable hardness data obtained through the test. Thus, the hardness of the cable can be predicted through the change curve of the environmental data, the hardness of the cable can be known in real time, the detection frequency of the cable hardness can be reduced, so as to reduce the damage to the cable during the hardness test and reduce the maintenance cost, and the cable hardness prediction model can be updated through the regularly tested cable hardness data to ensure the accuracy of the model prediction.

[0047] 3. Compared with the prior art, the present invention provides an automatic detection system for online insulation monitoring of ship cables, which tests the safe elongation and insulation strength of the cable at various hardnesses by setting a body model module, a cable model module, a hull force monitoring module, a hull deformation analysis module, a cable deformation analysis module, and a cable safety data analysis module. The relationship between the cable hardness and the safe elongation and insulation strength is analyzed through regression analysis, and the normal deformation data interval of the cable is obtained by obtaining the external force range that the hull bears during navigation. The safe elongation predicted based on the regression analysis is compared with the normal deformation data interval of the cable, and the insulation strength predicted based on the regression analysis is compared with the set insulation strength standard value, to determine whether the cable is abnormal and to remind the cable to be replaced and maintained when abnormal, thereby further improving the safety of the cable. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0049] Figure 1 A system structure block diagram provided for an embodiment of the present invention;

[0050] Figure 2 A diagram of the steps for training and updating the cable hardness prediction model provided by an embodiment of the present invention;

[0051] Figure 3 A step diagram of a regression model for obtaining safe elongation by a cable safety data analysis module provided by an embodiment of the present invention;

[0052] Figure 4 A step diagram of obtaining an insulation strength regression model by a cable safety data analysis module provided by an embodiment of the present invention;

[0053] Figure 5 A diagram of the steps for determining the safe elongation of a cable safety data analysis module provided by an embodiment of the present invention;

[0054] Figure 6 A diagram of another safe elongation determination step of the cable safety data analysis module provided by an embodiment of the present invention;

[0055] Figure 7 A diagram of the insulation strength determination steps of a cable safety data analysis module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0057] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0058] Example embodiments will be described more fully below with reference to the accompanying drawings, but the example embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. On the contrary, the purpose of providing these embodiments is to make the present disclosure thorough and complete and to enable those skilled in the art to fully understand the scope of the present disclosure.

[0059] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0060] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0061] The terms used herein are only used to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a", "an" and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof is not excluded.

[0062] The embodiments described herein may be described with reference to plan views and / or cross-sectional views by means of idealized schematic diagrams of the present disclosure. Therefore, the example illustrations may be modified according to manufacturing techniques and / or tolerances. Therefore, the embodiments are not limited to the embodiments shown in the accompanying drawings, but include modifications of the configurations formed based on the manufacturing process. Therefore, the regions illustrated in the accompanying drawings have schematic properties, and the shapes of the regions shown in the figures illustrate the specific shapes of the regions of the elements, but are not intended to be limiting.

[0063] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless explicitly defined as such herein.

[0064] See also Figure 1 , an automatic detection system for online insulation monitoring of marine cables, including a hull model module, a cable model module, a hull force monitoring module, a hull deformation monitoring module, a hull deformation analysis module, a cable deformation analysis module, an environmental monitoring module, a cable hardness prediction module, and a cable safety data analysis module;

[0065] The hull model module is used to establish a hull assembly model based on the actual hull structure and materials, wherein the hull assembly model truly restores the various structures, parts, materials, etc. of the hull;

[0066] The cable model module is used to establish the cable model and assemble it into the hull assembly model according to the actual installation position of the cable;

[0067] The hull force monitoring module is used to monitor the external force on the hull and obtain the hull force data. For example, the strain gauge can be attached to the hull surface to measure the strain of the material to infer the force magnitude; the pressure sensor can be installed in key locations, such as the hull shell or contact points, to detect the pressure of external water flow or collision; the accelerometer can be fixed on the hull to measure the acceleration change to infer the magnitude and direction of the impact force;

[0068] The hull deformation monitoring module is used to monitor the deformation amount of the hull setting position and obtain the hull deformation data. For example, strain gauges, optical fiber sensors, laser rangefinders, etc. can be installed at the setting position to realize deformation monitoring of the setting position, such as bending, elongation, displacement, etc.; the hull deformation monitoring module can be installed in some positions to monitor the deformation amount, which is used to verify and correct the deformation data analyzed by the hull deformation analysis module.

[0069] The hull deformation analysis module is used to perform force analysis based on the hull assembly model to obtain the hull force analysis model, which is used to analyze the hull deformation data at each location of the hull assembly model corresponding to each hull force data under each load;

[0070] The hull deformation analysis module is also used to correct the hull force model based on the hull force data and the hull deformation data; further, the force analysis can be performed by the finite element method, for example, by the following steps:

[0071] a. Define the analysis objectives and scope: Identify the structural parts and operating conditions that need to be evaluated (e.g., hull, deck, cargo hold, etc.). Clarify the objectives, such as evaluating the strength and stability of the hull under different loads and sea conditions.

[0072] b. Collect ship data: Obtain ship design drawings, including hull structure, material specifications, dimensions, etc. Collect actual operation data, such as sailing speed, load distribution, sea condition information, etc.

[0073] c. Select and configure analysis tools: Finite element analysis (FEA) software: such as ANSYS and ABAQUS, used to simulate the stress and deformation of the hull under different loads. Computational fluid dynamics (CFD) software: such as OpenFOAM, used to simulate the impact of the marine environment on the hull.

[0074] d. Model building: Geometric modeling: Building a three-dimensional geometric model of the hull according to the design drawings. Meshing: Dividing the hull model into a finite number of units for the convenience of finite element analysis.

[0075] e. Define material properties and boundary conditions: Input the mechanical properties data of the hull material, such as elastic modulus, Poisson's ratio, yield strength, etc. Set boundary conditions and loads, including hydrostatic pressure, wave load, cargo load, etc.

[0076] f. Conduct structural analysis: Static analysis: evaluate the stress distribution and deformation under static loads. Dynamic analysis: consider the impact of dynamic loads such as waves and wind on the hull structure. Fatigue analysis: evaluate the fatigue damage that may occur to the hull under repeated loads.

[0077] g. Result verification: Compare and verify the simulation results with the actual test data, and conduct structural tests in the laboratory or on the actual ship to verify the accuracy of the analysis results.

[0078] The cable deformation analysis module is used to extract the deformation data of the hull position corresponding to the cable from the hull deformation data analyzed by the hull deformation analysis module to obtain the cable deformation data;

[0079] The environmental monitoring module is used to obtain environmental data on the hull, and the environmental data include temperature and humidity. The environmental monitoring module can use temperature sensors and humidity sensors to monitor the temperature and humidity respectively. Preferably, the environmental monitoring modules can be evenly arranged along the direction of the cable, and the temperature and humidity of each area are the average temperature and humidity obtained by the environmental monitoring module of the area, thereby improving the accuracy of the environmental data of the monitored area.

[0080] The cable hardness prediction module is used to detect the hardness of the cable to obtain the cable hardness data, and is also used to obtain environmental data, draw the environmental data change curve, and train the deep learning model based on the environmental data change curve and the cable hardness data to obtain the cable hardness prediction model, which is used to output the corresponding cable hardness data prediction value based on the input environmental data change curve; the present invention does not limit the specific deep learning model, and can select a suitable model for training according to the actual situation during the training process to ensure the accuracy of the trained model. For example, a feedforward neural network model, a long short-term memory network model, a convolutional neural network model, etc. can be used; in the training process, the environmental data change curve is used as the training model. The environmental data change curve and cable hardness data are taken as samples, the environmental data change curve is taken as input, and the cable hardness data is taken as output. The samples are divided into a training set and a validation set at a ratio of 6:4. The deep learning model of the training set is used for training to obtain the parameters of the model. After substituting the deep learning model into the parameters, the accuracy of the deep learning model output is verified by the validation set. If the accuracy meets the set requirements, the model parameters are determined to obtain the cable hardness prediction model. If the accuracy does not meet the set requirements, the model parameters are adjusted, or the model, activation function, loss function, etc. are reselected and retrained until the accuracy of the trained model output meets the set requirements.

[0081] refer to Figure 2 The cable hardness prediction module is also used to obtain the cable hardness data obtained by detection and train and update the cable hardness prediction model, including the following steps:

[0082] A1. Perform hardness test on the cable according to the set period, and save the obtained cable hardness data into the test sample set. During the test, the cables on board are divided into multiple sections, and part of the cable in each section is taken as the test sample for hardness test;

[0083] A2. Determine whether the number of cable hardness data in the test sample set is greater than or equal to the set sample number;

[0084] A3. If yes, the cable hardness prediction model is trained and updated using the test sample set, so that the cable hardness prediction model is regularly calibrated using the tested cable hardness data to ensure the prediction accuracy of the cable prediction model.

[0085] The cable safety data analysis module is also used to test the safety elongation and insulation strength of the cable when testing the hardness data of each cable. The safety elongation is the maximum elongation of the cable when the cable surface is guaranteed to be undamaged. Based on the cable hardness data, the safety elongation and the insulation strength, regression analysis is performed to obtain the safety elongation regression model and the insulation strength regression model, which are used to calculate the corresponding safety elongation prediction value and insulation strength prediction value based on the cable hardness data.

[0086] Among them, reference Figure 3 , the cable safety data analysis module obtains the safety elongation regression model, including the following steps:

[0087] B1. Obtain cables with different hardness data;

[0088] B2. Conduct tensile tests on cables of different hardness data respectively, gradually increase the stretching length during the tensile test, and conduct ultrasonic flaw detection on the cables at the same time to determine whether there is mechanical damage on the cable surface;

[0089] B3. If not, return to B2. If yes, obtain the elongation of the cable at this time to obtain the safe elongation of the cable corresponding to the hardness data. When performing the tensile test, multiple tensile tests can be performed on the cable of each hardness data to obtain multiple safe elongations under the corresponding hardness data. Finally, the average value of the multiple safe elongations is taken as the safe elongation corresponding to the hardness data of the cable.

[0090] B4. Based on the hardness data of the cable and the safe elongation corresponding to the hardness data, a regression analysis is performed to obtain a safe elongation regression model, which is used to output the corresponding predicted value of the safe elongation based on the input hardness data.

[0091] refer to Figure 4 , the cable safety data analysis module obtains the insulation strength regression model, including the following steps:

[0092] C1. Obtain cables with different hardness data;

[0093] C2. Conduct insulation strength tests on cables with different hardness data respectively to obtain insulation strength data corresponding to the cables with different hardness data;

[0094] C3. Perform regression analysis based on the hardness data of the cable and the insulation strength data corresponding to the hardness data to obtain an insulation strength regression model, which is used to output an insulation strength prediction value based on the input hardness data.

[0095] refer to Figure 5-Figure 6 The cable safety data analysis module is also used to determine whether the cable deformation data is greater than the predicted value of the safety elongation at the corresponding time. If so, an early warning is issued, including the following steps:

[0096] D1a, obtaining monitoring data of the hull force monitoring module, and obtaining historical hull force data of the hull;

[0097] D2a, analyzing the historical hull stress data based on the box plot, filtering out abnormal historical hull stress data, and obtaining the normal hull stress data range of the hull;

[0098] D3a. Analyze the normal force data interval of the hull based on the hull force analysis model to obtain the normal deformation data interval of the hull, and extract the deformation data of the hull position corresponding to the cable to obtain the normal deformation data interval of the cable;

[0099] D4a, input the current environmental data change curve into the cable hardness prediction model to obtain the current cable hardness data prediction value, and input the current cable hardness data prediction value into the safety elongation regression model to obtain the current safety elongation prediction value;

[0100] D5a, judging whether the current predicted value of safe elongation is greater than the normal deformation data range of the cable, if not, issuing a first-class warning;

[0101] D1b, obtain real-time hull force data;

[0102] D2b. Analyze the real-time hull force data based on the hull force analysis model to obtain the real-time hull deformation data, and extract the deformation data of the hull position corresponding to the cable to obtain the real-time cable deformation data;

[0103] D3b. Determine whether the real-time deformation data of the cable is greater than the current safe elongation. If so, issue a second type of warning.

[0104] refer to Figure 7 At the same time, the cable safety data analysis module is also used to determine whether the predicted insulation strength value is less than the set insulation strength standard value. If so, an early warning is issued, including the following steps:

[0105] E1. Set the insulation strength standard value, where the insulation strength standard value can be set according to industry standards. For example, the insulation strength standard of ship cables usually requires that the insulation be guaranteed when the test voltage applied within 1 minute is 2500 volts;

[0106] E2. Input the current environmental data change curve into the cable hardness prediction model to obtain the current cable hardness data prediction value, and input the current cable hardness data prediction value into the insulation strength regression model to obtain the current insulation strength prediction value;

[0107] E3. Determine whether the current insulation strength prediction value is greater than or equal to the insulation strength standard value. If not, issue a second type of warning.

[0108] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. An automatic detection system for online insulation monitoring of marine cables, characterized in that: It includes hull model module, cable model module, hull force monitoring module, hull deformation monitoring module, hull deformation analysis module, cable deformation analysis module, environmental monitoring module, cable hardness prediction module, and cable safety data analysis module; The hull model module is used to establish a hull assembly model according to the actual hull structure and materials; The cable model module is used to establish a cable model and assemble the cable into the hull assembly model according to the actual installation position of the cable; The hull force monitoring module is used to monitor the external force on the hull and obtain the hull force data; The hull deformation monitoring module is used to monitor the deformation amount of the hull setting position and obtain the hull deformation data; The hull deformation analysis module is used to perform force analysis based on the hull assembly model to obtain a hull force analysis model, which is used to analyze the hull deformation data at various locations of the hull assembly model corresponding to various hull force data under various loads of the hull assembly model; The hull deformation analysis module is also used to calibrate the hull force model based on the hull force data and the hull deformation data; The cable deformation analysis module is used to extract the deformation data of the hull position corresponding to the cable from the hull deformation data analyzed by the hull deformation analysis module to obtain the cable deformation data; The environmental monitoring module is used to obtain environmental data on the hull, and the environmental data includes temperature and humidity; The cable hardness prediction module is used to detect the hardness of the cable to obtain cable hardness data, and is also used to obtain environmental data, draw an environmental data change curve, and train a deep learning model based on the environmental data change curve and the cable hardness data to obtain a cable hardness prediction model, which is used to output a corresponding cable hardness data prediction value based on the input environmental data change curve; The cable safety data analysis module is also used to test the safety elongation and insulation strength of the cable when testing the hardness data of each cable. The safety elongation is the maximum elongation of the cable when the cable surface is guaranteed to be undamaged. Based on the cable hardness data, the safety elongation and the insulation strength, regression analysis is performed to obtain a safety elongation regression model and an insulation strength regression model, which are used to calculate the corresponding safety elongation prediction value and insulation strength prediction value based on the cable hardness data. The cable safety data analysis module is also used to determine whether the cable deformation data is greater than the predicted value of the safe elongation at the corresponding time, and if so, an early warning is issued; at the same time, it is used to determine whether the predicted value of the insulation strength is less than the set insulation strength standard value, and if so, an early warning is issued.

2. The automatic detection system for online insulation monitoring of marine cables according to claim 1 is characterized in that: The cable hardness prediction module is also used to obtain the cable hardness data obtained by detection, and train and update the cable hardness prediction model, including the following steps: A1. Perform hardness test on the cable according to the set period, and save the obtained cable hardness data into the test sample set; A2. Determine whether the number of cable hardness data in the test sample set is greater than or equal to the set sample number; A3. If yes, use the test sample set to train and update the cable hardness prediction model.

3. The automatic detection system for online insulation monitoring of marine cables according to claim 1 is characterized in that: The cable safety data analysis module obtains a safety elongation regression model, including the following steps: B1. Obtain cables with different hardness data; B2. Performing a tensile test on the cables of each hardness data, gradually increasing the stretching length during the tensile test, and performing ultrasonic flaw detection on the cables to determine whether there is mechanical damage on the cable surface; B3. If no, return to B2. If yes, obtain the elongation of the cable at this time to obtain the safe elongation of the cable corresponding to the hardness data; B4. Based on the hardness data of the cable and the safe elongation corresponding to the hardness data, a regression analysis is performed to obtain a safe elongation regression model, which is used to output the corresponding predicted value of the safe elongation based on the input hardness data.

4. The automatic detection system for online insulation monitoring of marine cables according to claim 1 is characterized in that: The cable safety data analysis module obtains an insulation strength regression model, including the following steps: C1. Obtain cables with different hardness data; C2. Conduct insulation strength tests on cables with different hardness data respectively to obtain insulation strength data corresponding to the cables with different hardness data; C3. Perform regression analysis based on the hardness data of the cable and the insulation strength data corresponding to the hardness data to obtain an insulation strength regression model, which is used to output an insulation strength prediction value based on the input hardness data.

5. The automatic detection system for online insulation monitoring of marine cables according to claim 1 is characterized in that: The cable safety data analysis module is also used to determine whether the cable deformation data is greater than the predicted value of the safe elongation at the corresponding time, and if so, issue an early warning, including the following steps: Acquire monitoring data of a hull force monitoring module to obtain historical hull force data of the hull; Analyzing the historical hull force data based on the box plot, filtering out abnormal historical hull force data, and obtaining a normal hull force data interval of the hull; Analyze the normal force data interval of the hull based on the hull force analysis model to obtain the normal deformation data interval of the hull, and extract the deformation data of the hull position corresponding to the cable to obtain the normal deformation data interval of the cable; Input the current environmental data change curve into the cable hardness prediction model to obtain the current cable hardness data prediction value, and input the current cable hardness data prediction value into the safety elongation regression model to obtain the current safety elongation prediction value; It is determined whether the current predicted safe elongation value is greater than the normal deformation data interval of the cable. If not, a first type of warning is issued.

6. The automatic detection system for online insulation monitoring of marine cables according to claim 5 is characterized in that: The cable safety data analysis module is also used to determine whether the cable deformation data is greater than the predicted value of the safe elongation at the corresponding time, and if so, an early warning is issued, and further includes the following steps: Obtain real-time hull force data; Analyzing the real-time hull force data based on the hull force analysis model to obtain the real-time hull deformation data, and extracting the deformation data of the hull position corresponding to the cable to obtain the real-time cable deformation data; It is determined whether the real-time deformation data of the cable is greater than the current safe elongation. If so, a second type of warning is issued.

7. The automatic detection system for online insulation monitoring of marine cables according to claim 6 is characterized in that: The step of judging whether the predicted insulation strength value is less than the set insulation strength standard value and issuing an early warning if so comprises the following steps: Set the insulation strength standard value; Input the current environmental data change curve into the cable hardness prediction model to obtain the current cable hardness data prediction value, and input the current cable hardness data prediction value into the insulation strength regression model to obtain the current insulation strength prediction value; It is determined whether the current insulation strength prediction value is greater than or equal to the insulation strength standard value. If not, a second type of warning is issued.

Images