Damage identification method, device and equipment for storage tank bearing platform structure, medium and product

Abstract

The invention relates to a damage identification method and device for a storage tank bearing platform structure, equipment, a medium and a product. The method comprises the steps of obtaining stress, deformation and temperature of distributed optical fibers arranged on the storage tank bearing platform structure; performing damage identification on the stress, the deformation and the temperature by utilizing a target damage identification model, and determining a damage position and a damage grade of the storage tank bearing platform structure; wherein the target damage identification model is obtained by performing damage identification training according to stress samples, deformation samples, temperature samples and corresponding damage position samples under different levels of damage conditions. According to the technical scheme, the damage condition of the storage tank bearing platform structure can be effectively judged.

Description

Technical Field

[0001] The present invention relates to the field of damage identification technology, and in particular to a damage identification method, device, equipment, medium and product for a storage tank support structure. Background Art

[0002] As the demand for liquefied natural gas grows year by year, higher requirements are placed on the storage capacity of liquefied natural gas. Generally, liquefied natural gas is stored in storage tanks. The pedestal structure of the storage tank is located between the upper structure and the foundation of the storage tank, connecting the upper structure and the lower structure, transferring the upper structure load of the storage tank to the foundation, which directly affects the safety of the storage tank structure.

[0003] However, the tanks store a large amount of ultra-low temperature liquefied natural gas (LNG), and are sealed internally after construction. It is impossible to determine the damage to the traditional foundation structure of the tanks. Therefore, it is difficult to determine the health status of the tanks, resulting in risks in the storage of LNG. Summary of the invention

[0004] In view of the above technical problems, the present invention provides a damage identification method, device, equipment, medium and product for a tank pedestal structure, which can effectively determine the damage condition of the tank pedestal structure.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] A damage identification method for a storage tank cap structure, comprising:

[0007] Obtaining stress, deformation and temperature of a distributed optical fiber disposed on a storage tank support structure;

[0008] The target damage identification model is used to perform damage identification on the stress, deformation and temperature to determine the damage location and damage level of the tank base structure; wherein the target damage identification model is obtained by performing damage identification training based on stress samples, deformation samples, temperature samples and corresponding damage location samples under different levels of damage.

[0009] In one embodiment, the stress samples include simulated stress samples and measured stress samples; the deformation samples include simulated deformation samples and measured deformation samples; and the temperature samples include simulated temperature samples and measured temperature samples.

[0010] In one embodiment, the method for obtaining the simulated stress samples, simulated deformation samples, and simulated temperature samples under different levels of damage includes:

[0011] The tank cap structure is simulated according to a preset simulation model to obtain a tank cap simulation model;

[0012] According to different working conditions of the tank cap structure, different levels of damage are generated on different parts of the tank cap simulation model, and numerical simulations are performed on the different levels of damage to obtain simulated stress samples, simulated deformation samples, and simulated temperature samples of the tank cap structure under different levels of damage.

[0013] In one embodiment, the target damage identification model is obtained by performing damage identification training based on stress samples, deformation samples, temperature samples and corresponding damage position samples under different levels of damage, including:

[0014] A multi-fidelity deep neural network is trained for damage identification based on stress samples, deformation samples, temperature samples and corresponding damage position samples of the tank cap structure under different levels of damage to obtain the target damage identification model.

[0015] In one embodiment, damage identification training is performed on a multi-fidelity deep neural network according to stress samples, deformation samples, temperature samples and corresponding damage position samples of the tank cap structure under different levels of damage to obtain the target damage identification model, including:

[0016] According to the simulated stress samples, simulated deformation samples and simulated temperature samples of the tank cap structure under different levels of damage, the first neural network is trained for low-fidelity damage recognition to obtain an initial damage recognition model;

[0017] Input the measured stress samples, measured deformation samples, and measured temperature samples of the tank cap structure into the initial damage identification model for damage identification, and obtain the first predicted damage position and the first predicted damage level;

[0018] The second neural network is trained for high-fidelity damage identification based on the measured stress samples, measured deformation samples, measured temperature samples, the first predicted damage location and the first predicted damage level of the tank foundation structure to obtain the target damage identification model.

[0019] In one embodiment, the distributed optical fiber is disposed between the upper and lower steel meshes of the tank foundation structure, and the distributed optical fiber covers the upper and lower steel meshes of the tank foundation structure.

[0020] The present invention also provides a damage identification device for a storage tank support structure, comprising:

[0021] An acquisition module, used to acquire the stress, deformation and temperature of the distributed optical fiber arranged on the tank support structure;

[0022] An identification module, configured to use a target damage identification model to identify damage to the stress, deformation, and temperature, and determine the damage location and damage level of the storage tank foundation structure; wherein, the target damage identification model is obtained by performing damage identification training based on stress samples, deformation samples, temperature samples, and corresponding damage location samples under different levels of damage. The present invention also provides an electronic device, including:

[0023] A memory and a processor;

[0024] The memory is connected to the processor and is used to store programs;

[0025] The processor, by running the program in the memory, implements the above-mentioned damage identification method for the storage tank foundation structure.

[0026] The present invention also provides a storage medium, on which a computer program is stored. When the computer program is run by a processor, the above-mentioned damage identification method for the storage tank foundation structure is implemented.

[0027] The present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the above-mentioned damage identification method for the storage tank foundation structure is implemented.

[0028] Due to the above technical solutions adopted by the present invention, it has the following advantages:

[0029] Obtain the stress, deformation, and temperature of the distributed optical fiber arranged on the storage tank foundation structure; use the target damage identification model to identify damage to the stress, deformation, and temperature, and determine the damage location and damage level of the storage tank foundation structure; wherein, the target damage identification model is obtained by performing damage identification training based on stress samples, deformation samples, temperature samples, and corresponding damage location samples under different levels of damage. Thus, it can be seen that the damage location and damage level of the storage tank foundation structure can be determined based on stress, deformation, and temperature, so as to effectively identify the damage of the foundation structure, realize the intelligence of damage identification of the storage tank foundation structure, and ensure the safety of liquefied natural gas storage. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic flow chart of a method for identifying damage to a storage tank foundation structure according to an embodiment of the present invention;

[0031] Figure 2 It is a specific schematic flow chart of a training method for a target damage identification model according to an embodiment of the present invention;

[0032] Figure 3 It is a schematic structural diagram of a device for identifying damage to a storage tank foundation structure according to an embodiment of the present invention;

[0033] Figure 4 It is a schematic structural diagram of an electronic device in one embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention is described clearly and completely below. 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 persons in the art without creative work are within the scope of protection of the present invention.

[0035] Unless otherwise defined, the technical or scientific terms used in the present invention shall have the usual meanings understood by persons with ordinary skills in the field to which the present invention belongs. The words "first", "second", "third", "fourth" and similar terms used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Words such as "include" or "comprise" and the like mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connect" or "connected" and the like are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect.

[0036] As the demand for liquefied natural gas increases year by year, higher requirements are also placed on the storage capacity of liquefied natural gas. Generally, liquefied natural gas is stored in storage tanks, so the overall stability of the storage tanks is crucial. The traditional pile structure of the storage tank is buried underground, and the storage tank is usually located at the seaside far away from the crowded areas. It is in a salt spray environment for a long time, and the pedestal structure is more susceptible to corrosion and damage. At present, it is impossible to detect whether the pedestal structure of the tank is damaged, so it is difficult to determine the health status of the tank, resulting in risks in the storage of liquefied natural gas. In response to the above technical problems, the present invention provides a damage identification method, device, equipment, medium and product for the pedestal structure of the tank, which can effectively judge the damage of the pedestal structure of the tank. The technical scheme of the present invention is described in detail below with reference to specific examples.

[0037] Reference Figure 1 As shown, a damage identification method for a storage tank cap structure according to the present invention comprises:

[0038] S110, obtaining the stress, deformation and temperature of the distributed optical fiber arranged on the tank support structure;

[0039] S120. Use a target damage identification model to perform damage identification on the stress, deformation and temperature to determine the damage location and damage level of the tank base structure; wherein the target damage identification model is obtained by performing damage identification training based on stress samples, deformation samples, temperature samples and corresponding damage location samples under different levels of damage.

[0040] In step S110, illustratively, the distributed optical fiber adopts distributed optical fiber sensing technology, which measures the physical scattering signals of light such as Raman scattering, Brillouin scattering and Rayleigh scattering in the optical fiber to achieve the measurement of temperature, stress and deformation. The external part of the distributed optical fiber is wrapped with armor or composited with carbon fiber to ensure the safety of the optical fiber during the construction and operation stages and will not be easily torn off. The distributed optical fiber can form multiple loops or an overall loop.

[0041] Preferably, the distributed optical fiber is arranged between the upper and lower steel mesh sheets of the tank pedestal structure, and the distributed optical fiber covers the upper and lower steel mesh sheets of the tank pedestal structure. In this way, the changes of the pedestal structure can be effectively sensed. Specifically, the distributed optical fiber tank pedestal structure is installed and laid inside the structure during the construction phase, and the specific form is that it is fixed on the steel cage and cast inside the concrete at the same time. In this embodiment, the distributed optical fiber is a plurality of distributed optical fibers, which are laid along the main bars of the steel cage during the construction process. The distributed optical fiber is orthogonally arranged in the central area of ​​the upper and lower steel mesh sheets of the pedestal, and is arranged circumferentially and radially on the outer circle and the side, so as to evenly cover the upper and lower steel mesh sheets of the entire pedestal.

[0042] It should be noted that when arranging distributed optical fibers, the sensing optical cables should be pre-tensioned to keep the cables straight and tied to the main reinforcement with cable ties at intervals of 1-2m. The sensing optical cables should be in straight contact with the reinforcement without bending or bulging. The cables should be tied more tightly when crossing the main stirrups. At the same time, loose tubes should be used to protect the bending parts of the distributed optical fibers to prevent excessive bending. The bending radius of the optical fiber should not be less than 5cm. During the steel bar welding process, welding slag should be prevented from splashing onto the sensing optical cables. If welding is required around the optical cables, the optical cables should be covered with wet towels to avoid damage from high temperatures.

[0043] The optical cable joint can adopt the heat-shrinkable tube sealing optical cable joint technology, specifically as follows: Use a utility knife and diagonal pliers to remove the sheath and strengthening member at the optical cable joint; Use a wire stripper to remove the coating layer and cladding of the optical fiber, exposing a certain length of the optical fiber core; Use a cutting knife to cut the optical fiber core to make the optical fiber interface flat; Put a heat-shrinkable tube on one end of the optical fiber joint, fuse the two optical fiber joints with a fusion splicer, and complete the splicing after heat-shrinking protection with the heat-shrinkable tube; For environments with destructive conditions, a fusion splicing protection tube should be used for enhanced protection during the splicing process. In step S120, exemplarily, based on a large number of simulation experiments, that is, multiple different damage positions existing in the pile cap structure are determined in advance. Different levels are set according to different damage positions, so as to obtain the mapping relationship between the stress sample, deformation sample, temperature sample, and the corresponding damage position sample and damage level. The neural network model is trained for damage identification according to the above mapping relationship until the convergence criterion is met, and the damage identification model is output. It can be seen that through the above damage identification model, the damage position and damage level can be identified according to stress, deformation, and temperature.

[0044] In the technical solution of the present application, the stress, deformation, and temperature of the distributed optical fiber arranged on the storage tank pile cap structure are obtained; The target damage identification model is used to perform damage identification on the stress, the deformation, and the temperature, and determine the damage position and damage level of the storage tank pile cap structure; Wherein, the target damage identification model is obtained by training for damage identification according to the stress sample, deformation sample, temperature sample, and the corresponding damage position sample under different levels of damage. Thus, it can be seen that according to stress, deformation, and temperature, the damage position and damage level of the storage tank pile cap structure can be determined, so as to effectively identify the damage of the pile cap structure, realize the intelligent damage identification of the storage tank pile cap structure, and ensure the safety of the storage of liquefied natural gas. At the same time, using the model for damage prediction does not require introducing too many devices, reduces the damage identification cost of the storage tank pile cap structure, and makes the identification result safer and more reliable.

[0045] In one embodiment, the stress sample includes a simulated stress sample and a measured stress sample; The deformation sample includes a simulated deformation sample and a measured deformation sample; The temperature sample includes a simulated temperature sample and a measured temperature sample.

[0046] Specifically, the measured data (i.e., the measured stress sample, measured deformation sample, and measured temperature sample) are the data obtained by monitoring the storage tank pile cap structure in reality, which belong to high-fidelity data. However, generally, the number of high-fidelity data is small. Therefore, low-fidelity data (i.e., the simulated stress sample, simulated deformation sample, and simulated temperature sample) are used for joint training with the high-fidelity data to improve the accuracy of the trained damage identification model.

[0047] Preferably, the method for obtaining the simulated stress samples, simulated deformation samples, and simulated temperature samples under different levels of damage includes:

[0048] The tank cap structure is simulated according to a preset simulation model to obtain a tank cap simulation model;

[0049] According to different working conditions of the tank cap structure, different levels of damage are generated on different parts of the tank cap simulation model, and numerical simulations are performed on the different levels of damage to obtain simulated stress samples, simulated deformation samples, and simulated temperature samples of the tank cap structure under different levels of damage.

[0050] In this embodiment, simulation software is used to modify the parameters of the preset simulation model to obtain a tank cap simulation model that is the same as the tank cap structure. The preset simulation model can be a common model in the simulation software, which is not limited here. The simulation software includes commercial general finite element analysis software or professional finite element analysis software, and the finite element simulation real-time calculation results have a three-dimensional display space resolution of meters, and the calculation results of key structural components have a three-dimensional display space resolution of centimeters.

[0051] First, determine the working conditions of the tank cap simulation model, including construction conditions, operation conditions, water pressure test conditions, different liquid level heights, etc. Then, generate different levels of damage on the tank cap simulation model in turn, and then perform numerical simulation on the damaged tank cap simulation model to output the simulated stress samples, simulated deformation samples, and simulated temperature samples under the damage level. And record the simulated stress samples, simulated deformation samples, and simulated temperature samples to obtain a sample set. In this way, the simulated stress samples, simulated deformation samples, and simulated temperature samples of the tank cap structure are obtained more accurately.

[0052] In one embodiment, the target damage identification model is obtained by performing damage identification training based on stress samples, deformation samples, temperature samples and corresponding damage position samples under different levels of damage, and includes:

[0053] A multi-fidelity deep neural network is trained for damage identification based on stress samples, deformation samples, temperature samples and corresponding damage position samples of the tank cap structure under different levels of damage to obtain the target damage identification model.

[0054] Specifically, data of different fidelity are collected, usually including a large amount of low-fidelity data and a small amount of high-fidelity data. Low-fidelity data is usually easier to obtain and has a lower cost, while high-fidelity data is more accurate but has a high cost. Therefore, low-fidelity data (i.e., simulated stress samples, simulated deformation samples, simulated temperature samples) are used together with high-fidelity data for joint training to improve the prediction accuracy and generalization ability of the model.

[0055] Furthermore, if Figure 2 As shown, the multi-fidelity deep neural network is trained for damage identification based on stress samples, deformation samples, temperature samples and corresponding damage position samples of the tank cap structure under different levels of damage to obtain the target damage identification model, including:

[0056] S210, performing low-fidelity damage recognition training on the first neural network according to simulated stress samples, simulated deformation samples, and simulated temperature samples of the tank cap structure under different levels of damage to obtain an initial damage recognition model;

[0057] S220, inputting the measured stress samples, measured deformation samples, and measured temperature samples of the tank cap structure into the initial damage identification model for damage identification, and obtaining a first predicted damage position and a first predicted damage level;

[0058] S230, performing high-fidelity damage identification training on the second neural network according to the measured stress samples, measured deformation samples, measured temperature samples, the first predicted damage location and the first predicted damage level of the tank foundation structure to obtain the target damage identification model.

[0059] Specifically, the simulated stress samples, simulated deformation samples, simulated temperature samples and the corresponding damage positions and damage levels are used to form a learning pattern pair of the training network. The artificial neural network algorithm is used to normalize and dimensionlessly process the simulated stress samples, simulated deformation samples, simulated temperature samples and the corresponding damage positions and damage levels in the selected initial learning pattern pair, and the final structure is used to form the final training pattern pair. Then, the artificial neural network algorithm is used to select a suitable network topology, initialize the network, establish the convergence criterion, and finally provide the final training pattern to the network, and train the network until the convergence criterion is met, and output the initial damage recognition model.

[0060] Then, high-fidelity network training is carried out in combination with measured stress samples, measured deformation samples, and measured temperature samples. That is, the input is the measured stress samples, measured deformation samples, measured temperature samples and the output of the low-fidelity network (i.e., the initial damage identification model), and the output is the damage location and damage level. Using multi-fidelity data for model training can improve the accuracy of damage identification of the pedestal structure.

[0061] Furthermore, when the target damage identification model predicts the damage location and damage level, and when the damage location or damage level meets the structural failure condition, an early warning message is sent to the staff. The structural failure condition may be that the damage location is a high-risk location and the damage level is a high-risk level. It is understandable that the high-risk location and the high-risk level are both set according to the actual situation and are not limited here.

[0062] The present invention also provides a damage identification device for a storage tank support structure, referring to Figure 3 As shown, including:

[0063] An acquisition module 310 is used to acquire the stress, deformation and temperature of the distributed optical fiber arranged on the tank support structure;

[0064] The identification module 320 is used to identify the stress, the deformation and the temperature using the target damage identification model to determine the damage location and damage level of the tank cap structure; wherein the target damage identification model is obtained by performing damage identification training based on stress samples, deformation samples, temperature samples and corresponding damage location samples under different levels of damage. wherein the structural dynamic feature samples include simulated structural dynamic feature samples and measured structural dynamic feature samples; and the response samples include simulated response samples and measured response samples.

[0065] In one embodiment, the stress samples include simulated stress samples and measured stress samples; the deformation samples include simulated deformation samples and measured deformation samples; and the temperature samples include simulated temperature samples and measured temperature samples.

[0066] In one embodiment, the method for obtaining the simulated stress samples, simulated deformation samples, and simulated temperature samples under different levels of damage includes:

[0067] The tank cap structure is simulated according to a preset simulation model to obtain a tank cap simulation model;

[0068] According to different working conditions of the tank cap structure, different levels of damage are generated on different parts of the tank cap simulation model, and numerical simulations are performed on the different levels of damage to obtain simulated stress samples, simulated deformation samples, and simulated temperature samples of the tank cap structure under different levels of damage.

[0069] In one embodiment, the target damage identification model is obtained by performing damage identification training based on stress samples, deformation samples, temperature samples and corresponding damage position samples under different levels of damage, including:

[0070] A multi-fidelity deep neural network is trained for damage identification based on stress samples, deformation samples, temperature samples and corresponding damage position samples of the tank cap structure under different levels of damage to obtain the target damage identification model.

[0071] In one embodiment, damage identification training is performed on a multi-fidelity deep neural network according to stress samples, deformation samples, temperature samples and corresponding damage position samples of the tank cap structure under different levels of damage to obtain the target damage identification model, including:

[0072] According to the simulated stress samples, simulated deformation samples and simulated temperature samples of the tank cap structure under different levels of damage, the first neural network is trained for low-fidelity damage recognition to obtain an initial damage recognition model;

[0073] Input the measured stress samples, measured deformation samples, and measured temperature samples of the tank cap structure into the initial damage identification model for damage identification, and obtain the first predicted damage position and the first predicted damage level;

[0074] The second neural network is trained for high-fidelity damage identification based on the measured stress samples, measured deformation samples, measured temperature samples, the first predicted damage location and the first predicted damage level of the tank foundation structure to obtain the target damage identification model.

[0075] In one embodiment, the distributed optical fiber is disposed between the upper and lower steel meshes of the tank foundation structure, and the distributed optical fiber covers the upper and lower steel meshes of the tank foundation structure.

[0076] The damage identification device for the tank pedestal structure provided in this embodiment belongs to the same application concept as the damage identification method for the tank pedestal structure provided in the above-mentioned embodiments of this application, and can execute the damage identification method for the tank pedestal structure provided in any of the above-mentioned embodiments of this application, and has the corresponding functional modules and beneficial effects of executing the damage identification method for the tank pedestal structure. For technical details not fully described in this embodiment, please refer to the specific processing content of the damage identification method for the tank pedestal structure provided in the above-mentioned embodiments of this application, which will not be repeated here.

[0077] The functions implemented by the above acquisition module 310 and identification module 320 can be implemented by the same or different processors, respectively, and the embodiment of the present application is not limited thereto.

[0078] It should be understood that the modules in the above devices can be implemented in the form of a processor calling software. For example, the device includes a processor, the processor is connected to a memory, and instructions are stored in the memory. The processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of each unit of the device, wherein the processor can be a general-purpose processor, such as a CPU or a microprocessor, etc., and the memory can be a memory in the device or a memory outside the device. Alternatively, the unit in the device can be implemented in the form of a hardware circuit, and the functions of some or all units can be realized by designing the hardware circuit. The hardware circuit can be understood as one or more processors; for example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are realized by designing the logical relationship of the components in the circuit; for another example, in another implementation, the hardware circuit can be implemented by PLD, taking FPGA as an example, which can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by a configuration file, so as to realize the functions of some or all of the above units. All units of the above devices can be implemented in the form of a processor calling software, or in the form of a hardware circuit, or in part by a processor calling software, and the remaining part is implemented in the form of a hardware circuit.

[0079] It should be noted that in the embodiments of the present application, the processor is a circuit with the ability to process signals. In one implementation, the processor may be a circuit with the ability to read and run instructions, such as a CPU, a microprocessor, a GPU, or a DSP; in another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the configuration of the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, DPU, etc.

[0080] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0081] In addition, all or part of the units in the above device can be integrated together, or can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a SOC. The SOC may include at least one processor for implementing any of the above methods or implementing the functions of each unit of the device. The type of the at least one processor may be different, for example, including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0082] Reference Figure 4 As shown, the present invention also provides an electronic device, the device comprising:

[0083] Memory 400 and processor 410;

[0084] The memory 400 is connected to the processor 410 and is used to store programs;

[0085] The processor 410 is used to implement the damage identification method of the tank support structure disclosed in any of the above embodiments by running the program stored in the memory 400.

[0086] Specifically, the electronic device may further include: a bus, a communication interface 420 , an input device 430 and an output device 440 .

[0087] The processor 410, the memory 400, the communication interface 420, the input device 430 and the output device 440 are connected to each other via a bus.

[0088] A bus may include a pathway that transfers information between components of a computer system.

[0089] Processor 410 may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the scheme of the present invention. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0090] The processor 410 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0091] The memory 400 stores a program for executing the technical solution of the present invention, and may also store an operating system and other key services. Specifically, the program may include a program code, and the program code includes a computer operation instruction. More specifically, the memory 400 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk storage, a flash, and the like.

[0092] The input device 430 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor.

[0093] Output device 440 may include a device that allows information to be output to a user, such as a display screen, a printer, a speaker, etc.

[0094] The communication interface 420 may include any transceiver or the like to communicate with other devices or communication networks, such as Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0095] The processor 410 executes the program stored in the memory 400 and calls other devices, which can be used to implement each step of the damage identification method of any tank pedestal structure provided in the above embodiments of the present application.

[0096] The present invention also provides a computer program product and a storage medium

[0097] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the damage identification method for the tank platform structure according to various embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

[0098] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0099] In addition, an embodiment of the present application may also be a storage medium on which a computer program is stored, and the computer program is executed by a processor to execute the steps of the damage identification method of the tank base structure according to various embodiments of the present application described in the above "Exemplary Method" section of this specification. The specific working content of the above-mentioned electronic device, as well as the specific working content of the above-mentioned computer program product and the computer program on the storage medium when being executed by the processor, can all be referred to the contents of the above-mentioned method embodiment, and will not be repeated here.

[0100] For the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0101] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0102] The steps in the methods of each embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0103] The modules and sub-modules in the devices and terminals of the various embodiments of the present application can be combined, divided and deleted according to actual needs.

[0104] In the several embodiments provided in the present application, it should be understood that the disclosed terminals, devices and methods can be implemented in other ways. For example, the terminal embodiments described above are only schematic, for example, the division of modules or submodules is only a logical function division, and there may be other division methods in actual implementation, for example, multiple submodules or modules can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0105] The modules or submodules described as separate components may or may not be physically separated, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place, or they may be distributed on multiple network modules or submodules. Some or all of the modules or submodules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0106] In addition, each functional module or submodule in each embodiment of the present application may be integrated into one processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into one module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or in the form of software functional modules or submodules.

[0107] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0108] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly by hardware, software units executed by a processor, or a combination of the two. The software units may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0109] 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 make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A damage identification method for a tank cap structure, characterized in that: include: Obtaining stress, deformation and temperature of a distributed optical fiber disposed on a storage tank support structure; The target damage identification model is used to perform damage identification on the stress, deformation and temperature to determine the damage location and damage level of the tank base structure; wherein the target damage identification model is obtained by performing damage identification training based on stress samples, deformation samples, temperature samples and corresponding damage location samples under different levels of damage.

2. The method according to claim 1, characterized in that in, The stress samples include simulated stress samples and measured stress samples; the deformation samples include simulated deformation samples and measured deformation samples; the temperature samples include simulated temperature samples and measured temperature samples.

3. The method according to claim 2, characterized in that The method for obtaining the simulated stress samples, simulated deformation samples, and simulated temperature samples under the conditions of different levels of damage includes: The tank cap structure is simulated according to a preset simulation model to obtain a tank cap simulation model; According to different working conditions of the tank cap structure, different levels of damage are generated on different parts of the tank cap simulation model, and numerical simulations are performed on the different levels of damage to obtain simulated stress samples, simulated deformation samples, and simulated temperature samples of the tank cap structure under different levels of damage.

4. The method according to claim 3, characterized in that The target damage identification model is obtained by performing damage identification training based on stress samples, deformation samples, temperature samples and corresponding damage position samples under different levels of damage, and includes: A multi-fidelity deep neural network is trained for damage identification based on stress samples, deformation samples, temperature samples and corresponding damage position samples of the tank cap structure under different levels of damage to obtain the target damage identification model.

5. The method according to claim 4, characterized in that The multi-fidelity deep neural network is trained for damage identification based on stress samples, deformation samples, temperature samples and corresponding damage position samples of the tank cap structure under different levels of damage to obtain the target damage identification model, including: According to the simulated stress samples, simulated deformation samples and simulated temperature samples of the tank cap structure under different levels of damage, the first neural network is trained for low-fidelity damage recognition to obtain an initial damage recognition model; Input the measured stress samples, measured deformation samples, and measured temperature samples of the tank cap structure into the initial damage identification model for damage identification, and obtain the first predicted damage position and the first predicted damage level; The second neural network is trained for high-fidelity damage identification based on the measured stress samples, measured deformation samples, measured temperature samples, the first predicted damage location and the first predicted damage level of the tank foundation structure to obtain the target damage identification model.

6. The method according to any one of claims 1 to 5, characterized in that The distributed optical fiber is arranged between the upper and lower steel mesh sheets of the tank support structure, and the distributed optical fiber covers the upper and lower steel mesh sheets of the tank support structure.

7. A damage identification device for a tank support structure, characterized in that: include: An acquisition module, used to acquire the stress, deformation and temperature of the distributed optical fiber arranged on the tank support structure; An identification module is used to use a target damage identification model to perform damage identification on the stress, deformation and temperature, and determine the damage location and damage level of the tank base structure; wherein the target damage identification model is obtained by performing damage identification training based on stress samples, deformation samples, temperature samples and corresponding damage location samples under different levels of damage.

8. An electronic device, characterized in that: include: Memory and processor; The memory is connected to the processor and is used to store programs; The processor implements the damage identification method for the tank pedestal structure as claimed in any one of claims 1 to 6 by running the program in the memory.

9. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the damage identification method for the tank foundation structure according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the damage identification method for a tank cap structure according to any one of claims 1 to 6 is implemented.

Images