Sensor layout method for monitoring stress state of jacket

Abstract

The invention discloses a sensor arrangement method for monitoring the stress state of a jacket, and belongs to the technical field of structural health monitoring and the field of ocean engineering, and the method comprises the steps: obtaining the horizontal resultant force of waves to a main leg of the jacket through the ocean current wave mass point acceleration and the water flow acceleration at the main leg of the jacket; and in combination with the wind pressure, determining the UC value of the hot spot area of the rod piece by adopting a deep convolutional neural network model, and further determining the monitoring point position on the jacket to carry out the installation and layout of the sensor. According to the invention, the monitoring accuracy can be greatly improved, and data fluctuation caused by processing reasons is avoided. Meanwhile, monitoring point positions are selected in the direction of one main leg, and the selected monitoring points can be conveniently installed on site; the determined arrangement positions of the sensors are all located on the windward wave side, it is guaranteed that monitoring is carried out at relatively dangerous positions, the monitoring reliability is improved, and the monitoring result is more instructive.

Description

Technical Field

[0001] The present invention relates to the technical field of structural health monitoring and the field of marine engineering, and in particular to a sensor arrangement method for monitoring the stress state of a conductor frame. Background Art

[0002] As an important infrastructure in the field of offshore oil and gas development, the offshore platform jacket has long been subjected to complex marine environmental loads, such as wind, waves, currents, sea ice, etc., which cannot be observed in real time. In addition, the jacket structure is huge and has many rods, so it is impossible to install sensors on each rod for monitoring. Considering the cost and effect, it is necessary to monitor the key points of the jacket. Therefore, through the monitoring of key points, the stress state of the entire jacket can be deduced, providing a scientific basis for later maintenance. In the traditional method, in the process of selecting key points for the deployment of sensors, the impact of the actual environmental conditions of the offshore platform on it is rarely considered. Therefore, the monitored data cannot well reflect the actual stress conditions of the rods. From the perspective of reliability, the guiding significance of the monitoring results is not strong. Summary of the invention

[0003] The invention discloses a sensor arrangement method for monitoring the stress state of a conductor frame, so as to overcome the above technical problems.

[0004] In order to achieve the above object, the technical solution of the present invention is: A sensor deployment method for monitoring the stress state of a conductor frame comprises the following steps: S1: Establish a finite element model of the jacket and obtain the hot spots of the rods in the jacket; S2: Obtain the ocean wave particle acceleration and water flow acceleration at the jacket main leg to obtain the horizontal resultant force of the wave on the jacket main leg; S3: According to the meteorological data of the sea area where the jacket is in service, determine the windward side of the finite element model of the jacket and determine the wind pressure applied to the jacket; S4: According to the finite element model of the jacket, the horizontal resultant force of the waves on the main legs of the jacket, the windward surface of the finite element model of the jacket, and the wind pressure, the UC value of the hot spot area of ​​the rod is determined based on the deep convolutional neural network model; the jacket rod that needs to be monitored is determined, and then multiple monitoring points on the jacket are determined, that is, the sensor layout positions; S5: Install sensors at monitoring points of rods on the conductor frame to complete the deployment of sensors.

[0005] Furthermore, the method for obtaining the hot spot area of ​​the rod in the conductor rack is as follows: According to the finite element model of the conductor frame, based on the fatigue life assessment method, determining the stress concentration factor of the point on the rod; When the stress concentration factor of a point on the rod is greater than a set threshold, the point on the rod belongs to a hot spot area.

[0006] Furthermore, in S2, the ocean wave particle acceleration and water flow acceleration at the main leg of the jacket are obtained as follows: , Where: It represents the ocean wave particle acceleration and water flow acceleration at the main leg of the jacket; is the wave height; is the wave period; for water depth; is the wave number; is the vertical coordinate from sea level to the sea bottom; is the wave circle frequency; for the moment; is the horizontal coordinate of the main leg of the jacket; The horizontal resultant force of the wave on each main leg of the jacket is obtained as follows: , Where: It represents the horizontal resultant force per unit length of the main leg of the jacket by waves; is the density of seawater; is the inertia force coefficient; is the radius of the main leg of the jacket; is the correction factor; is the speed of seawater relative to the main leg; is the correction factor for the jacket weight.

[0007] Furthermore, in S4, the plurality of monitoring points on the conductor frame are located in the same main leg direction of the conductor frame.

[0008] Furthermore, in S4, the method for determining the monitoring point position of the rod on the conductor rack is as follows: The hot spot area of ​​the rod with a UC value greater than the set UC value threshold is determined as the monitoring point of the rod on the conductor rack.

[0009] Furthermore, in S5, the method for arranging sensors at monitoring points of the rods on the conductor frame is as follows: S51: At the location of the monitoring point of the rod on the conductor frame, a number of positioning straight lines parallel to the axis of the rod are evenly drawn in the circumference of the rod; S52: After the projection of the center line of the first protective pipe of the welding sealed cabin on the rod is overlapped with the positioning straight line, the welding sealed cabin is welded; S53: welding and fixing one end of the first wiring protective tube to the first protective tube pipe, and making the projection of the center line of the first wiring protective tube on the rod coincide with the positioning straight line; S54: adjusting the center line of the first wiring protection tube to coincide with the axis line of the designed position of the arc plate plug hole corresponding to the first sensor; S55: One end of the second wiring protection tube is welded and fixed to the second protection tube pipe of the fusion sealing cabin, and the other end is adjusted by fire so that the center line of the second protection tube pipe coincides with the axis of the designed position of the arc plate plug hole corresponding to the second sensor; and a pressure test is performed; S56: After the pressure test is completed, the arc plate is welded and fixed, and the clamping base of the first sensor / the second sensor is welded; S57: After the welding work of the clamping base is completed, the first sensor and the plurality of second sensors are installed and tested at the same time; S58: After the test is completed, the watertight shell is welded and the installation of the monitoring point sensor is completed.

[0010] Furthermore, after S5, the step further includes: S6: After the jacket is installed in the sea area where the jacket is in service, the actual axial force and bending moment of the monitoring point of the rod are obtained through the monitoring data of the sensor, so as to obtain the deviation between the theoretical axial force and bending moment and the actual axial force and bending moment according to the theoretical axial force and bending moment of the monitoring point of the rod, so as to guide the staff of the construction site of the relevant project who will subsequently lay out the jacket to correct the layout of the sensors.

[0011] Beneficial effects: The sensor deployment method for monitoring the stress state of a conductor frame of the present invention obtains the horizontal resultant force of the waves on the main legs of the conductor frame through the ocean wave particle acceleration and water flow acceleration at the main legs of the conductor frame; and according to the finite element model of the conductor frame, the horizontal resultant force of the waves on the main legs of the conductor frame and the windward wind pressure obtained based on the meteorological data of the ocean where the conductor frame is in service, the UC value of the hot spot area of ​​the rod is determined based on the deep convolutional neural network model; to determine the conductor frame rods that need to be monitored, and then determine multiple monitoring points on the conductor frame, and install and deploy sensors at the monitoring points. The present invention monitors key weak points through finite element analysis and calculation, which can reduce the workload of on-site construction and focus on monitoring relatively dangerous points. By monitoring key rods based on the preliminary results of finite element calculations, the accuracy of monitoring can be greatly improved and data fluctuations caused by processing reasons can be avoided. At the same time, the present invention adopts the method of selecting monitoring points in the direction of a main leg. The selected measuring points can be conveniently installed on site under the condition of satisfying the UC value selection. The determined sensor layout positions are all on the windward and wave side, ensuring monitoring in relatively dangerous positions, improving monitoring reliability, and making the monitoring results more instructive. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0013] Figure 1 A flow chart of a sensor deployment method for monitoring the stress state of a catheter rack according to the present invention; Figure 2 Schematic diagram of UC value of a pipe rack rod in an embodiment of the present invention; Figure 3 is a schematic diagram of the arrangement of measuring points of a conductor frame in an embodiment of the present invention; Figure 4 4 schematic diagrams of circumferential arrangement of measuring point sensors in an embodiment of the present invention; Figure 5 It is a schematic diagram of the protection structure of the measuring point sensor in the embodiment of the present invention; Figure 6 A schematic diagram of the welding sequence of the sensor clamping base in an embodiment of the present invention; Figure 7 It is a block diagram of the layout of measuring points and calculation of the conductor frame in an embodiment of the present invention; Figure 8 Schematic diagram of the installation position of the upper assembly sensor in an embodiment of the present invention.

[0014] Among them, 1. First protective pipe connection; 2. Second protective pipe connection; 3. First wiring protective pipe; 5. Second wiring protective pipe; 9. Welding sealing cabin. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0016] This embodiment introduces a sensor deployment method for monitoring the stress state of a conductor frame. Figure 1 and Figure 7 As shown, the following steps are included: S1: Establish a finite element model of the jacket and obtain the hot spots of the rods in the jacket; Preferably, the method for obtaining the hot spot area of ​​the rod in the conductor frame is as follows: According to the finite element model of the conductor frame, based on the fatigue life assessment method, determining the stress concentration factor of the point on the rod; When the stress concentration factor of a point on the rod is greater than a set threshold, the point on the rod belongs to a hot spot area; Specifically, the establishment of the finite element model of the jacket in this embodiment is a conventional technology in the art. For example, after the finite element model is established, a fatigue life assessment method is used to determine the fatigue damage accumulation rate of the rod, such as the SN curve method (stress-life curve method): according to the SN curve of the jacket material and the stress history obtained by finite element analysis, the fatigue damage accumulation of each component under different load conditions is calculated. Among them, the SN curve of the jacket material is obtained through conventional material testing, which reflects the fatigue life of the material under different stress amplitudes; the stress history is the process in which the stress at a certain point or a certain area in the model changes with time, load or other parameters during the finite element analysis process. Based on this change process, the fatigue damage accumulation rate, that is, the stress concentration factor, can be obtained; In this embodiment, when the stress concentration factor is greater than 3, it is determined that a certain point on the rod belongs to the hot spot area. Specifically, the finite element model identifies the points on the rod where fatigue damage accumulates faster, that is, the stress concentration factor is greater than 3, through fatigue damage accumulation calculation, and finally determines the hot spot area on the rod. These hot spots are where fatigue damage is most likely to occur and develop under long-term environmental loads and working loads. For example, at certain locations of underwater components that are frequently impacted by waves, fatigue damage may accumulate rapidly due to repeated stress cycles.

[0017] S2: Obtain the ocean wave particle acceleration and water flow acceleration at the main legs of the jacket to obtain the horizontal resultant force of the wave on each main leg of the jacket; Preferably, in S2, the ocean wave particle acceleration and water flow acceleration at the main leg of the jacket are obtained as follows: , Where: It represents the ocean wave particle acceleration and water flow acceleration at the main leg of the jacket; is the wave height; is the wave period; for water depth; is the wave number; is the vertical coordinate from sea level to the sea bottom; is the wave circle frequency; for the moment; is the horizontal coordinate of the main leg of the jacket; The horizontal resultant force of the wave on each main leg of the jacket is obtained as follows: , Where: It represents the horizontal resultant force per unit length of the main leg of the jacket by waves; is the density of seawater; is the inertia force coefficient; is the radius of the main leg of the jacket; is the correction factor; is the speed of seawater relative to the main leg; is the correction factor for the jacket weight.

[0018] S3: According to the meteorological data of the sea area where the jacket is in service, determine the windward side of the finite element model of the jacket and determine the wind pressure applied to the jacket; Specifically, obtain the meteorological data of the sea area where the conductor frame is in service, and determine the main wind direction in the sea area. Establish a spatial rectangular coordinate system to determine the orientation of each surface, and identify the windward side of the finite element model of the conductor frame under the action of the wind direction in the SACS software. Then, combine the ocean current wave particle acceleration and the water flow acceleration at the main legs of the conductor frame to obtain the horizontal resultant force of the waves on each main leg of the conductor frame, apply it to the finite element model of the conductor frame, and establish a fluid-solid coupling model analysis model to simulate the stress condition of the conductor frame under the combined action of complex ocean currents and wind, so as to further determine the windward side and its wind pressure distribution. This can ensure that the final monitoring point is located on the relatively more stressed side of the main leg; S4: According to the finite element model of the jacket, the horizontal resultant force of the waves on the main legs of the jacket, the windward surface of the finite element model of the jacket, and the wind pressure, the UC value of the hot spot area of ​​the rod is determined based on the deep convolutional neural network model; the jacket rod that needs to be monitored is determined, and then multiple monitoring points on the jacket are determined, that is, the sensor layout positions; Preferably, the multiple monitoring points on the conductor frame are located in the same main leg direction of the conductor frame; Specifically, in this embodiment, the horizontal resultant force and wind pressure of the wave on each main leg of the conductor frame are applied to the finite element model of the conductor frame, and the UC value of the hot spot area of ​​the rod is determined based on the deep convolutional neural network model; the monitoring point position of the rod on the conductor frame is determined, and then the sensor layout position on the main leg of the conductor frame is determined; Specifically, the hot spot area on the rod is used as the key calculation area of ​​the UC value. In the hot spot area on the rod, combined with the specific geometric shape parameters, stress state and other factors of the rod, the specific detailed structure UC value is further determined, such as Figure 2 As shown. In this embodiment, a UC value prediction algorithm based on deep learning is adopted, wherein the deep convolutional neural network model adopted inputs the rod structure data, including geometric shape parameters, material properties, load conditions, etc., through the input layer, and the output layer outputs the UC value of the rod. By training the deep convolutional neural network model, the mapping relationship between the rod structure data and the UC value is learned: Specifically, a large amount of conductor frame structure data and corresponding UC values ​​are collected, including data on structural stress, strain, fatigue damage, etc. under different working conditions. These data are used to train the deep convolutional neural network model, and the parameters and weights of the model are adjusted so that the model can accurately predict the UC value. During the training process, methods such as cross-validation are used to improve the generalization ability of the model. By continuously optimizing the neural network model, the prediction accuracy and reliability of the model are improved. For example, the structure, parameters, training methods, etc. of the model are adjusted so that the model can better adapt to complex structures and load conditions. At the same time, the model is verified and improved in combination with actual engineering applications to ensure the practicality and effectiveness of the model; Specifically, after the deep convolutional neural network model is trained, the new conductor frame structural parameters are input into the trained neural network model to predict the UC value of the new conductor frame rod. The deep convolutional neural network model can automatically calculate the UC value of the rod based on the input rod structure data, that is, it can know the UC value of the hot spot area of ​​the rod. By analyzing and evaluating the prediction results, the location and number of UC value monitoring points are determined; Preferably, the method for determining the monitoring point position of the rod on the conductor rack is as follows: Determine the hot spot area of ​​the rod with a UC value greater than a set UC value threshold as the monitoring point of the rod on the conductor rack; Specifically, the UC value of a rod represents the ratio of its bearing capacity to the use requirements, that is, the ratio of the ultimate bearing capacity of the rod to the actual bearing capacity. The smaller the UC value, the higher the safety factor of the rod and the greater the bearing capacity. Conversely, it means that the safety factor is lower and the bearing capacity is smaller. The UC value is one of the important indicators for the design and selection of rods. It is usually required that the UC value should not be greater than 1.0 to ensure the safety and reliability of the rod during use. Specifically, according to the calculation result of the UC value of the hot spot area of ​​the rod, the rod with a larger UC value in the hot spot area is selected as the catheter rack rod that needs to be monitored. Then, according to the structural characteristics of the catheter rack, specific monitoring points (cross braces, diagonal braces and main legs) are selected, that is, positions that are easy to install and have no interference are selected as measurement points; in this embodiment, the monitoring points of the catheter rack rods that need to be monitored are selected according to one of the main leg directions, such as Figure 3 Specifically, for horizontally installed conductor racks, the main leg where the sensors are laid should be located on the side of the launch slideway to reduce overhead work during installation, which is beneficial for inversion calculation and layout and installation; among them, the equipment, cross braces, diagonal braces, etc. adjacent to a main leg are all in the direction of the main leg; Specifically, in this embodiment, when determining the location of the monitoring point on the selected rod with a larger UC value, ensure that the location of the monitoring point of the cross brace and the main leg is greater than 1 meter away from the location of the main leg K point; the monitoring points are symmetrically arranged at the cross intersection of the diagonal brace, and the distance between the monitoring point and the intersection is greater than 1 meter; Sensors are laid out at the selected monitoring points. The sensors are laid out symmetrically along the circumference of the rod. The number of sensors can be 2, 4, 6, 8, etc. The distance between the sensor installation position and the circumferential and longitudinal welds is not less than 200 mm. Figure 4 The schematic diagram shows the arrangement of four sensors symmetrically along the circumference of the rod; S5: Installing sensors at monitoring points of rods on the conductor frame to complete the deployment of sensors; Preferably, the method for arranging sensors at monitoring points of rods on the conductor frame is as follows: S51: At the location of the monitoring point of the rod on the conductor frame, a number of positioning straight lines parallel to the axis of the rod are evenly drawn in the circumference of the rod; S52: after the projection of the center line of the first protective pipe 1 at the protruding position of the front end of the welding sealing cabin 9 on the rod is coincided with the positioning straight line, the center line position of the welding sealing cabin 9 is determined, and the welding sealing cabin 9 is welded; S53: welding and fixing one end of the first wiring protective tube 3 to the first protective tube pipe 1, and making the projection of the center line of the first wiring protective tube 3 on the rod coincide with the positioning straight line; S54: adjusting the center line of the first wiring protection tube 3 to coincide with the axis line of the designed position of the arc plate plug hole corresponding to the first sensor; Specifically, a welding sealed cabin 9 and a plurality of sensors are provided at the location of the monitoring point, wherein a protective pipe pipe connected to the protective pipe of the sensor connecting line is provided on the side wall surface of the welding sealed cabin 9; wherein the protective pipe pipe whose axis projection on the rod coincides with the positioning straight line is taken as the first protective pipe pipe, the sensor corresponding to the first protective pipe pipe is the first sensor, the other plurality of sensors provided at the monitoring point are the second sensors, and the other protective pipe pipes on the welding sealed cabin 9 are the second protective pipe pipes; wherein the monitoring point of this embodiment is provided with 4 sensors, including 1 first sensor and 3 second sensors, and correspondingly, the welding sealed cabin is provided with 1 first protective pipe pipe 1 and 3 second protective pipe pipes 2, such as Figure 5 As shown, the projection of the center line of the first protective pipe 1 on the rod coincides with the positioning straight line; When positioning the welding sealed cabin 9, the center line of the first wiring protective tube 3 of the welding sealed cabin 9 must coincide with the projection of the center line of the protective tube on the rod, that is, coincide with the positioning straight line. At the same time, the corresponding sensor, the center line of the clamping base, and the projection of the center line of the metal shell of the sensor on the rod must coincide with the positioning straight line and be in the same straight line as the projection of the center line of the first protective tube 1 of the welding sealed cabin 9. Specifically, when positioning and welding the first wiring protective tube 3, one end of the first wiring protective tube 3 is connected to the first protective tube 1 extending from the welding sealing cabin 9, so that the projection of the center line of the first wiring protective tube 3 on the rod coincides with the positioning straight line, and the axis of the wiring protective tube coincides with the axis of the designed position of the arc plate plug hole (assisted by the arc plate for positioning); the arc plate is used for auxiliary positioning to determine the distance from the center of the protective tube to the conductor frame (optionally 69mm±5mm). If the distance from the center of the protective tube to the conductor frame is not within the required range, a flame adjustment is required. Specifically, when the protective tube is installed on site, the prefabricated shape may deviate from the actual on-site shape. At this time, the angle of the protective tube must be fine-tuned on-site by flame heating the protective tube. In the shipbuilding industry, this is called flame adjustment, which is a conventional technology in this field. S55: One end of the second wiring protection tube 5 is welded and fixed to the second protection tube pipe 2 of the fusion sealing cabin 9, and the other end is adjusted by fire so that the center line of the second protection tube pipe 2 coincides with the axis of the designed position of the arc plate plug hole corresponding to the second sensor; and a pressure test is performed to determine that the fusion sealing cabin 9 after welding meets the use requirements. The second wiring protection tube is a curved tube; Specifically, since the welding sealed cabin 9 and the elbow are both working at a depth of 200 meters underwater, pressure testing must be performed after welding and installation are completed to confirm that there are no problems with welding and ensure the overall sealing. The pressure testing method for the sealed welding cabin and the elbow as a whole in this embodiment is as follows: the minimum pressure testing pressure is not less than 1.2 times the hydrostatic pressure of the corresponding water depth, the test pressure is 2.6MPa, and the pressure holding time is not less than 2 hours; S56: After the pressure test is completed, the arc plate is welded and fixed, and two clamping bases of each sensor of the first sensor / the second sensor are welded; Specifically, the arc plate is welded to the pipe frame. The arc plate is vertically positioned and welded on the rod structure, and the arc plate welding requires double-sided welding; S57: After the welding of the clamping base is completed, the first sensor and the second sensor are installed and tested simultaneously according to the welded clamping base. Specifically, four sensors are installed simultaneously at the same measuring point; S58: After the test is completed, the watertight shell is welded according to the sensors that have been tested normally, and the installation of the monitoring point sensors is completed; Specifically, a curved plate is provided on one side of the watertight housing of this embodiment that is connected to the wiring protective tube, and a curved plate plug hole is provided on the curved plate, and the wiring protective tube passes through the curved plate plug hole to enter the watertight housing. Among them, the argon arc welding technology is used to fully weld the watertight housing, and the ratio of the sensor temperature rise ℃ to the welding speed cm / min is controlled to be no greater than 7.5; Specifically, the sensor of this embodiment is fixed by two clamping bases, each clamping base fixes one side of the sensor. The clamping base is a prior art in the art and will not be described in detail here; Specifically, when welding the clamping base of this embodiment, the diagonal welding process must be met and the welding must be performed in the order of 1234. Figure 6 As shown, during the welding process, please note that the same clamping base must be completely cooled before welding the next corresponding number position; Preferably, after S5, the step further includes: S6: After the jacket is installed in the jacket service sea area, the actually measured axial force and bending moment of the monitoring point of the rod are obtained through the monitoring data of the sensor, so as to obtain the deviation between the theoretical axial force and bending moment and the actually measured axial force and bending moment according to the theoretical axial force and bending moment of the monitoring point of the rod, so as to guide the staff of the construction site of the related project who will subsequently lay out the jacket to correct the layout of the sensor; Specifically, the measured axial force and bending moment of each monitoring point are calculated according to the sensor layout of the point. The calculation process is as follows: Based on the monitoring information of the sensor, the calculation formula for the axial force and bending moment of the section where the monitoring position is located is established.

[0019] Axial force calculation formula: ,unit , Bending moment calculation formula: ,unit , ,unit , in: represents Young's modulus, ,unit ; represents the cross-sectional area of ​​the pipe, ,unit ; represents the moment of inertia of the tube section, ,unit ; The monitored strain at each measuring point is as follows in clockwise direction: ,unit ; Indicates pipe diameter, Indicates wall thickness, Indicates the sensor cover influence coefficient.

[0020] A specific implementation of the present invention is as follows: This example verifies the axial force of the jacket of an offshore oil platform project in the South China Sea. The process is as follows: 1) Obtain the weighing weight and center of gravity of the topside module of the offshore oil platform provided by the construction unit; 2) According to the offshore oil platform drawings, the monitoring points are determined through finite element software analysis and calculation, and the sensors are installed. Figure 8 The schematic diagram of the sensor installation position of the upper assembly of the jacket is shown; 3) According to the input data such as the weight and center of gravity of each part, the axial force analysis theory of each leg is calculated in the finite element software. The calculation results are shown in Table 1: Table 1 Theoretical calculation results of axial force analysis of jacket legs ; 4) Offshore oil platforms obtain a large amount of raw data through sensor monitoring. The raw data is screened and processed. The main steps of data processing are as follows: a. Preprocess the data sequence X to be analyzed. If its sample mean is not zero, subtract the sample mean from each data point to ensure that the data sequence X is a zero-mean data vector; b. Use Fourier transform to calculate the amplitude spectrum A(f) and phase spectrum φ(f) of the sequence X, where f is the frequency in Hz. The amplitude spectrum shows the intensity of different frequency components in the data, while the phase spectrum provides the phase information of these frequency components relative to the starting point of the time series; c. Determine the frequency range [ fl, fu ] to be filtered out (where fl and fu are the lower and upper bounds of the selected frequency range, respectively), and set the amplitude A(fi ) corresponding to each frequency value fi in the frequency range to zero. The purpose of data filtering is achieved by cutting out unnecessary frequency components in the amplitude spectrum; d. Perform inverse Fourier transform based on the new amplitude spectrum and the original phase spectrum processed by the above steps, and take the real part of the transformation result as the new data sequence X'. After the above steps, the new amplitude spectrum has removed unnecessary frequency components, so the sequence X' is the data sequence after filtering; e. Calculate the axial force according to the above axial force calculation formula based on the screened measured data to obtain the real axial force under the actual state; 5) Comparison between theoretical calculation and actual monitoring, As shown in Table 2: Table 2 Comparison of theoretical calculation and actual monitoring data ; By comparing the theoretical values ​​and measured values ​​in Table 2, the deviation is less than 5%, which verifies the accuracy of the algorithm in this embodiment.

[0021] This embodiment is applied to the jacket structure health monitoring system in marine engineering to monitor the stress and strain conditions of the jacket part, and has the following beneficial effects: 1) Since the conductor frame is a very large and complex rod structure, it is impossible to add sensors to each rod for monitoring. However, this embodiment uses finite element analysis and calculation to monitor key weak points, which can reduce the workload of on-site construction and focus on monitoring relatively dangerous points. By monitoring key rods based on the preliminary results of finite element calculation, the accuracy of monitoring can be greatly improved, avoiding data fluctuations caused by processing reasons; 2) Since the number of sensors installed at each measuring point in this embodiment is an even number, they can be calibrated with each other, and the sensor layout adopts a circumferentially symmetrical arrangement. The more points are arranged, the more accurate the measured data is, and the axial force and bending moment of the rod can be accurately calculated, thereby improving the measurement accuracy; 3) Because the jacket structure is basically a symmetrical structure, the present embodiment adopts the selection of monitoring points in one main leg direction, and the selected measuring points can be conveniently installed on site under the condition that the UC value selection is met; 4) The sensors of this embodiment are arranged at the "windward and wave-facing" side, ensuring monitoring at the most dangerous position, improving monitoring reliability, and making the monitoring results more instructive.

[0022] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A sensor deployment method for monitoring the stress state of a conductor frame, characterized in that: The steps include: S1: Establish a finite element model of the jacket and obtain the hot spots of the rods in the jacket; S2: Obtain the ocean wave particle acceleration and water flow acceleration at the jacket main leg to obtain the horizontal resultant force of the wave on the jacket main leg; S3: According to the meteorological data of the sea area where the jacket is in service, determine the windward side of the finite element model of the jacket and determine the wind pressure applied to the jacket; S4: determining the UC value of the hot spot area of ​​the rod based on the deep convolutional neural network model according to the finite element model of the jacket, the horizontal resultant force of the waves on the main leg of the jacket, the windward surface of the finite element model of the jacket, and the wind pressure; To determine the pipe rack rods that need to be monitored, and then determine multiple monitoring points on the pipe rack, that is, sensor layout locations; S5: Install sensors at monitoring points of rods on the conductor frame to complete the deployment of sensors.

2. A sensor deployment method for monitoring the stress state of a conductor frame according to claim 1, characterized in that: The method to obtain the hot spot area of ​​the rod in the pipe rack is as follows: According to the finite element model of the conductor frame, based on the fatigue life assessment method, determining the stress concentration factor of the point on the rod; When the stress concentration factor of a point on the rod is greater than a set threshold, the point on the rod belongs to a hot spot area.

3. A sensor deployment method for monitoring the stress state of a conductor frame according to claim 1, characterized in that: In S2, the ocean wave particle acceleration and water flow acceleration at the main leg of the jacket are obtained as follows: ， Where: It represents the ocean wave particle acceleration and water flow acceleration at the main leg of the jacket; is the wave height; is the wave period; for water depth; is the wave number; is the vertical coordinate from sea level to the sea bottom; is the wave circle frequency; for the moment; is the horizontal coordinate of the main leg of the jacket; The horizontal resultant force of the wave on each main leg of the jacket is obtained as follows: ， Where: It represents the horizontal resultant force per unit length of the main leg of the jacket by waves; is the density of seawater; is the inertia force coefficient; is the radius of the main leg of the jacket; is the correction factor; is the speed of seawater relative to the main leg; is the correction factor for the jacket weight.

4. A sensor deployment method for monitoring the stress state of a conductor frame according to claim 1, characterized in that: In the above S4, the multiple monitoring points on the conductor frame are located in the same main leg direction of the conductor frame.

5. The sensor deployment method for monitoring the stress state of a conductor frame according to claim 1, characterized in that: In S4, the method for determining the monitoring point position of the rod on the conductor frame is as follows: The hot spot area of ​​the rod with a UC value greater than the set UC value threshold is determined as the monitoring point of the rod on the conductor rack.

6. A sensor deployment method for monitoring the stress state of a conductor frame according to claim 1, characterized in that: In S5, the method used for arranging sensors at monitoring points of rods on the conductor frame is as follows: S51: At the location of the monitoring point of the rod on the conductor frame, a number of positioning straight lines parallel to the axis of the rod are evenly drawn in the circumference of the rod; S52: After the projection of the center line of the first protective pipe (1) of the welding sealed cabin (9) on the rod is made to coincide with the positioning straight line, the welding sealed cabin (9) is welded; S53: welding one end of the first wiring protective tube (3) to the first protective tube connecting pipe (1) and making the projection of the center line of the first wiring protective tube (3) on the rod coincide with the positioning straight line; S54: adjusting the center line of the first wiring protection tube (3) by a fire adjustment method so that the center line of the first wiring protection tube (3) coincides with the axis line of the designed position of the arc plate plug hole corresponding to the first sensor; S55: One end of the second wiring protective tube (5) is welded and fixed to the second protective tube pipe (2) of the fusion sealing cabin (9), and the other end is adjusted by means of fire so that the center line of the second protective tube pipe (2) coincides with the axis of the designed position of the arc plate plug hole corresponding to the second sensor; and a pressure test is performed; S56: After the pressure test is completed, the arc plate is welded and fixed, and the clamping base of the first sensor / the second sensor is welded; S57: After the welding work of the clamping base is completed, the first sensor and the second sensor are installed and tested at the same time; S58: After the test is completed, the watertight shell is welded and the installation of the monitoring point sensor is completed.

7. A sensor deployment method for monitoring the stress state of a conductor frame according to claim 1, characterized in that: The S5 also includes: S6: After the jacket is installed in the sea area where the jacket is in service, the actual axial force and bending moment of the monitoring point of the rod are obtained through the monitoring data of the sensor, so as to obtain the deviation between the theoretical axial force and bending moment and the actual axial force and bending moment according to the theoretical axial force and bending moment of the monitoring point of the rod, so as to guide the staff of the construction site of the relevant project who will subsequently lay out the jacket to correct the layout of the sensors.

Images