Lining disease data set processing method and device, electronic equipment and storage medium

Abstract

The invention discloses a lining disease data set processing method and device, electronic equipment and a storage medium, and can be applied to the technical field of tunnel detection. According to the invention, after the plurality of standard models are constructed, the construction of the standard model entity structure is guided through the standard models, and after the lining disease model is constructed according to the standard models, the construction of the lining disease model entity structure comprising the plurality of types of disease sub-models is guided through the lining disease model. After radar detection data is obtained by performing radar detection on the lining disease model entity structure in a multi-azimuth and multi-position manner, a lining disease data set is generated according to the radar detection data and lining disease types in the lining disease model entity structure, so that the lining disease data set contains the lining disease types; therefore, high-quality and high-reliability training data is provided for the preset AI model, and the automatic detection accuracy of the preset AI model is improved.

Description

Technical Field

[0001] The present application relates to the technical field of tunnel detection, and in particular to a method and device for processing a lining disease data set, an electronic device and a storage medium. Background Art

[0002] In the related technology, ground penetrating radar is an instrument used to detect the internal structure of reinforced concrete. Especially in tunnel lining detection, ground penetrating radar is used for detection. During the detection process, engineers need to manually judge whether there are internal defects. Once defects are found, such as voids, looseness, water, etc., it is necessary to drill holes and grout backfill the reinforced concrete structure. This operation process has been widely used in engineering inspections such as tunnels and bridges. However, with the development of digitalization and intelligence, traditional manual identification methods can no longer meet new needs. Using artificial intelligence technology to identify radar charts has become a trend, and high-quality and highly reliable data is the basis of AI models. However, it is difficult to obtain highly reliable and high-quality data for lining detection in the prior art, resulting in low detection accuracy of AI models used for lining detection.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a method and device for processing a lining disease data set, an electronic device and a storage medium, which can provide high-quality and highly reliable training data for a lining detection AI model.

[0005] To achieve the above purpose, one aspect of an embodiment of the present application provides a method for processing a lining disease dataset, the method comprising the following steps:

[0006] Constructing a number of standard models, wherein the standard models are used to guide the construction of standard model entity structures;

[0007] A lining disease model is constructed according to the standard model, wherein the lining disease model is provided with several types of disease sub-models, the lining disease model is used to guide the construction of the lining disease model entity structure, and the disease sub-model is used to guide the construction of the disease sub-model entity structure in the lining disease model entity structure;

[0008] Acquire radar detection data of the physical structure of the lining disease model, wherein the radar detection data includes detection data of multi-angle detection orientations and multi-positions;

[0009] generating a lining disease data set according to the radar detection data and the lining disease types in the physical structure of the lining disease model;

[0010] The preset AI model is trained by the lining disease data set, and the preset AI model is used to automatically analyze the disease status of the physical lining.

[0011] In some embodiments, the length, width and height of the standard model physical structure are 2.5 m, 0.7 m and 0.7 m respectively; the construction of the standard model physical structure comprises:

[0012] Constructing on-site timber formwork;

[0013] Tie rods are arranged in the on-site wooden formwork to obtain a standard model entity structure.

[0014] In some embodiments, the step of constructing a lining disease model entity structure includes:

[0015] Obtain entity structures of different types of disease sub-models;

[0016] The disease sub-model entity structure is embedded in the standard model entity structure, and then C30 concrete is cast in the standard model entity structure to obtain the lining disease model entity structure; the slump range of the concrete is 160mm-180mm, the strength of the concrete within 12 hours after casting is greater than 8Mpa, and the impermeability grade of the concrete is P8.

[0017] In some embodiments, the inner bottom plate of the on-site wooden formwork is provided with steel meshes, and the spacing between the steel meshes is 20 cm or 15 cm.

[0018] In some embodiments, after the physical structure of the lining disease model is obtained, the physical structure of the lining disease model is maintained at preset time intervals, and the maintenance time is recorded.

[0019] In some embodiments, generating a lining disease data set according to the radar detection data and the lining disease types in the physical structure of the lining disease model includes:

[0020] Acquire three-dimensional structural description data of the physical structure of the lining disease model;

[0021] Obtaining detection position information corresponding to the radar detection data;

[0022] Acquiring the lining defect type corresponding to the detection position information in the three-dimensional structure description data;

[0023] generating data labels according to the lining disease type;

[0024] Generate a data pair according to the radar detection data and the data label;

[0025] All the data pairs are saved to the lining disease dataset.

[0026] In some embodiments, the training of a preset AI model using the lining disease dataset includes:

[0027] Preprocessing the data in the masonry disease data set to obtain a target training data set, wherein the preprocessing includes data cleaning and data standardization;

[0028] Constructing the preset AI model based on the encoding-decoding architecture;

[0029] The preset AI model is trained, evaluated and tested using the target training data set.

[0030] To achieve the above-mentioned purpose, another aspect of the embodiment of the present application provides a processing device for a lining disease data set, the device comprising:

[0031] The first module is used to construct a number of standard models, wherein the standard models are used to guide the construction of standard model entity structures;

[0032] The second module is used to construct a lining disease model according to the standard model, wherein the lining disease model is provided with several types of disease sub-models, the lining disease model is used to guide the construction of the lining disease model entity structure, and the disease sub-model is used to guide the construction of the disease sub-model entity structure in the lining disease model entity structure;

[0033] The third module is used to obtain radar detection data of the physical structure of the lining disease model, wherein the radar detection data includes detection data of multi-angle detection orientations and multi-positions;

[0034] A fourth module is used to generate a lining disease data set according to the radar detection data and the lining disease types in the lining disease model entity structure;

[0035] The fifth module is used to train a preset AI model using the lining disease data set, and the preset AI model is used to automatically analyze the disease status of the physical lining.

[0036] To achieve the above object, another aspect of an embodiment of the present application provides an electronic device, including:

[0037] at least one processor;

[0038] at least one memory for storing at least one program;

[0039] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0040] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0041] The embodiments of the present application include at least the following beneficial effects: The present application provides a method and device for processing a lining disease data set, an electronic device and a storage medium. The scheme constructs several standard models, and then uses the standard models to guide the construction of a standard model entity structure. After the lining disease model is constructed according to the standard model, the lining disease model is used to guide the construction of a lining disease model entity structure containing several types of disease sub-models. Then, after radar detection is performed on the lining disease model entity structure in multiple directions and positions to obtain radar detection data, a lining disease data set is generated according to the radar detection data and the lining disease types in the lining disease model entity structure, so that the lining disease data set contains the lining disease types, thereby providing high-quality and highly reliable training data for the preset AI model, thereby improving the automatic detection accuracy of the preset AI model. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flow chart of a method for processing a lining disease data set provided in an embodiment of the present application;

[0043] Figure 2 It is a schematic diagram of the data B-Scan;

[0044] Figure 3 It is a schematic diagram of the data effect of the data label with lined concrete medium;

[0045] Figure 4 is a schematic diagram of the standard model entity structure provided in the embodiment of the present application;

[0046] Figure 5 It is a schematic diagram of the disease sub-model entity structure provided in the embodiment of the present application after being pre-buried in the standard model entity structure;

[0047] Figure 6 It is a schematic diagram of the physical structure of several lining disease models provided in the embodiments of the present application;

[0048] Figure 7 It is a maintenance record schematic diagram provided in an embodiment of the present application;

[0049] Figure 8 It is a structural schematic diagram of a lining disease data set processing device provided in an embodiment of the present application;

[0050] Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application, they are only examples of devices and methods consistent with some aspects of the embodiments of the present application.

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0053] Before describing the embodiments of the present application in detail, some nouns and terms involved in the embodiments of the present application are first described. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations:

[0054] Lining: refers to a permanent support structure built with reinforced concrete and other materials along the perimeter of the tunnel to prevent deformation or collapse of the surrounding rock. Lining technology is usually used in tunnel engineering and water conservancy channels. Lining is simply the inner lining, and the most common lining is block lining, which can be prestressed high-pressure grouting plain concrete lining.

[0055] In related technologies, ground penetrating radar is an instrument used to detect the internal structure of reinforced concrete. Especially in tunnel lining inspection, ground penetrating radar is used for inspection. During the inspection process, engineers need to manually judge whether there are internal defects. Once defects are found, such as voids, looseness, water, etc., it is necessary to drill holes and grout backfill the reinforced concrete structure. This operation process has been widely used in engineering inspections such as tunnels and bridges. However, with the development of digitalization and intelligence, traditional manual identification methods can no longer meet new needs. Using artificial intelligence technology to identify radar charts has become a trend, and high-quality and highly reliable data is the basis of AI models. Among them, the AI ​​intelligent identification model of lining defects is a supervised learning model based on X→Y. The premise for this model to achieve high-accuracy identification is to meet the following two data conditions:

[0056] (1) X: B-Scan data collected by ground penetrating radar. Figure 2 shown.

[0057] (2) Y: Data with data labels of lining concrete medium, such as labels of steel bars, voids, etc. The data effect is as follows Figure 3 shown.

[0058] However, in actual engineering applications, data label Y is extremely difficult to obtain. For example, to mark the location of the void, either the concrete needs to be chiseled open or a professional identification engineer needs to be hired for judgment, which can also lead to inaccurate data labels, slow data flow, and high costs. It can be seen that the AI ​​model trained based on existing data has low detection accuracy in the field of lining disease detection.

[0059] In view of this, an embodiment of the present application provides a method and device for processing a lining disease data set, an electronic device and a storage medium. After constructing several standard models, this embodiment uses the standard model to guide the construction of a standard model entity structure, and after constructing a lining disease model according to the standard model, the lining disease model is used to guide the construction of a lining disease model entity structure containing several types of disease sub-models, and then radar detection is performed on the lining disease model entity structure in multiple directions and positions to obtain radar detection data, and then a lining disease data set is generated according to the radar detection data and the lining disease types in the lining disease model entity structure, so that the lining disease data set contains the lining disease type, thereby providing high-quality and highly reliable training data for the preset AI model, thereby improving the automatic detection accuracy of the preset AI model.

[0060] The processing method of the lining disease data set provided in the embodiment of the present application relates to the field of tunnel detection technology. The processing method of the lining disease data set provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server, and can also be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or it can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements the processing method of the lining disease data set, etc., but is not limited to the above forms.

[0061] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0062] Figure 1 is an optional flow chart of a method for processing a lining disease data set provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S110 to S150:

[0063] Step S110, constructing several standard models, wherein the standard models are used to guide the construction of standard model entity structures;

[0064] Step S120: construct a lining disease model according to the standard model, wherein the lining disease model is provided with several types of disease sub-models, the lining disease model is used to guide the construction of the lining disease model entity structure, and the disease sub-model is used to guide the construction of the disease sub-model entity structure in the lining disease model entity structure;

[0065] Step S130, obtaining radar detection data of the physical structure of the lining disease model, wherein the radar detection data includes detection data of multi-angle detection orientations and multi-positions;

[0066] Step S140, generating a lining disease data set according to the radar detection data and the lining disease types in the lining disease model entity structure;

[0067] Step S150: training a preset AI model using a lining disease data set, wherein the preset AI model is used to automatically analyze the disease status of the physical lining.

[0068] In the embodiment of the present application, by generating simulation data for experiments, it is verified that the minimum length that the model can adapt to is 2m, and then according to the length of the radar itself (plus the measuring wheel, close to 50cm), the length of the standard model entity structure is determined to be 2.5m (length). The width of the radar is 25cm, and the concrete width on the left and right sides of the radar needs to reserve 15cm of concrete to prevent the loss of electromagnetic wave information. The width of the standard model entity structure is determined to be 0.7m (width). The concrete test block simulates the block design of the tunnel secondary lining. The thickness of the tunnel secondary lining is generally 70cm, and the width of the standard model entity structure is determined to be 0.7m (height). In this embodiment, after the on-site wooden formwork is constructed by on-site wooden boards, tie rods are set in the on-site wooden formwork to strengthen it, thereby obtaining a standard model entity structure. Specifically, the inner bottom plate of the on-site wooden formwork is provided with a Φ8 steel mesh, the protective layer is 50mm, the length is 9cm, the spacing between the steel mesh is 20cm or 15cm, and there are 12 in total, as follows Figure 4 As shown in the figure, two Φ16 "J"-shaped round steel bars are set on the top surface as hanging bars, with the size of 10+5+90+15+90+5+10=225cm, 20cm away from the edges on both sides, 10cm exposed, 80cm below the concrete surface, hooking the bottom plate mesh steel bars, and the iron wire suspension reinforcement can be used for the reinforcement of the pre-pressed block. A groove of 20cm (width)*25cm (length)*12cm deep is reserved at the hanging ring, and the hanging ring cannot be exposed from the concrete surface.

[0069] It is understood that the use of Φ8 steel mesh in the internal base plate means that a steel mesh with a diameter of 8 mm (Φ indicates diameter) is used as the basic support inside the base plate. This design ensures the stability and strength of the base plate. 20cm (most areas) and 15cm (specific areas): The distribution of steel bars follows a specific spacing standard. This difference is for strength and to adapt to specific load requirements. The size of the hanger bar is 225cm, which means that the hanger bar, as a key component connecting the upper and lower structures, has a total length of 225 cm. This is described by adding a specific size along the length line (for example, 10cm+5cm+90cm+15cm+90cm+5cm+10cm), which indicates its length in the structure. The reserved 20cm*25cm*12cm deep groove is a space reserved specifically for the lifting ring, which ensures a safe and concealed installation of the lifting ring in the entire structure, avoiding the hazards and damage that may be caused by the exposed lifting ring.

[0070] In an embodiment of the present application, after obtaining the standard model entity structure, different types of disease sub-model entity structures are obtained, and then the disease sub-model entity structure is pre-embedded in the standard model entity structure, and then C30 concrete is cast in the standard model entity structure to obtain the lining disease model entity structure. Among them, the slump range of concrete is 160mm-180mm, the strength of concrete within 12 hours after casting is greater than 8Mpa, and the impermeability grade of concrete is P8. It can be understood that C30 cast-in-place concrete refers to the strength grade of concrete. C (concrete) stands for concrete, and the number after it represents the compressive strength of concrete (in MPa). C30 concrete means that its compressive strength is at least 30MPa. Specifically to the error range of 0.3Mpa, the standard range of compressive strength of C30 is 23.5MPa to 38.5MPa. Cast-in-place concrete means that the concrete is cast on site, rather than prefabricated or premixed.

[0071] The design slump range of 160mm-180mm is the fluidity that concrete needs to maintain during construction. Slump is a fluidity indicator that measures the degree of deformation of the top concrete pile when it falls freely from a certain height above the concrete. 160+20mm means the allowable slump range, with a minimum of 160mm and a maximum of 180mm. This parameter has a direct impact on the pouring and fluidity of concrete.

[0072] The strength should reach 8MPa or above within 12 hours after pouring, which refers to the early strength requirement of concrete after construction is completed. Early strength refers to the minimum compressive strength that can be achieved shortly after concrete pouring (here within 12 hours). Reaching 8MPa ensures that the supporting force from the formwork can be well carried by the continuously growing concrete body under wet and warm conditions, avoiding concrete quality problems caused by insufficient structural strength.

[0073] The impermeability grade refers to the grade of concrete's ability to resist water penetration. The number after P refers to the concrete's ability to resist water penetration, and the unit is MPa*hour. A design impermeability grade of P8 means that the concrete can remain impermeable for at least 2 hours under a pressure of 8MPa. This is a very critical indicator of drainage and water resistance.

[0074] In the embodiment of the present application, the physical structure of the disease sub-model can be made of a mold made of an acrylic plate of known size, or a container of other materials filled with air or water. The thickness of the acrylic plate is 8 mm, and the size and shape of the box made of the acrylic plate are varied, ranging from 30 cm to 1 m. After obtaining the physical structure of the disease sub-model, Figure 5As shown, the entity structure of the diseased sub-model is embedded in the entity structure of the standard model, and then cast with concrete. During the casting process, precise positioning is performed through special structures and casting processes, and the entity structure of the diseased sub-model is fixed with black ropes to prevent it from floating when pouring concrete. After pouring, non-destructive testing methods can also be used for auxiliary verification, such as taking photos of each test block and recording pouring videos.

[0075] In the present application example, after obtaining Figure 6 After the physical structures of several lining disease models are constructed, the physical structures of the lining disease models are maintained at preset time intervals, and the maintenance time is numbered and recorded. The recording effect is as follows: Figure 7 shown.

[0076] In an embodiment of the present application, after obtaining the physical structure of the lining disease model (concrete test block), a geological radar is used to measure the concrete test block. Each concrete test block stores a set of accurate three-dimensional structural description data, and also stores several sets of radar detection data measured from different angles and different positions. Among them, the three-dimensional structural description data is used to describe the location and type of lining disease defects in each concrete test block. The radar detection data format represents the lining disease in a specific form of geometric body, and records it in the three-dimensional structural description data of the corresponding test block. In addition to recording the location of the disease, the three-dimensional structural description data also needs to record the non-destructive detection data of the test block, including the original data of the sensor, and the visualization data after signal processing. The model, power and other parameters of the detection equipment should also be recorded as detailed as possible. Therefore, after obtaining the radar detection data, this embodiment can obtain the lining disease type corresponding to the detection position information in the 3D structure description data by obtaining the 3D structure description data of the entity structure of the lining disease model and the detection position information corresponding to the radar detection data, and then generate a data label according to the lining disease type, generate a data pair (a data pair of radar image X and label image Y) according to the radar detection data and the data label, and save all the data pairs to the lining disease data set. Specifically, the lining disease data set of this embodiment contains at least 1200 pairs of data pairs.

[0077] In the embodiment of the present application, after obtaining the lining disease data set, the preset AI model is trained by using the lining disease data set. It is understandable that the training process of the preset AI model includes but is not limited to the following steps:

[0078] Step 1: Data preprocessing:

[0079] Data cleaning: Noise filtering and outlier removal are performed on the 1,200 pairs of collected data (radar chart X and label chart Y) to ensure data quality.

[0080] Data standardization: Normalize the data to a uniform scale to eliminate the impact of different dimensions and facilitate model processing.

[0081] Step 2: Divide the preprocessed data set:

[0082] The dataset is divided into training set (70%), validation set (15%) and test set (15%).

[0083] Training set: The main dataset used for model training.

[0084] Validation set: used to adjust model parameters to avoid overfitting.

[0085] Test set: used to evaluate the final performance of the model.

[0086] Step 3: Model selection:

[0087] Model framework: Based on the encoder-decoder architecture, a preset AI model is built to process serialized geological radar data.

[0088] Backbone design: Convolutional neural network (CNN) combined with attention mechanism (Attention) is used as the basic feature extraction and processing module of the model.

[0089] Data encoding: Encoder is used to extract the features of radar images and convolution and pooling operations are used to reduce the spatial dimension of the data while retaining important disease features.

[0090] Attention mechanism: The introduction of the attention module enables the model to focus on the areas in the data that are most relevant to the disease and improve recognition accuracy.

[0091] Sequence decoding: The Decoder part is designed to reconstruct or translate the encoded features for disease location and inversion reconstruction.

[0092] Step 4: Model training:

[0093] Parameter setting: Determine hyperparameters such as learning rate, batch size, and number of iterations.

[0094] Loss function: weighted sum of L2-norm and multi-scale structural similarity (MSSIM), as follows:

[0095] Loss = α 1 L 2 (x,y)-α 2 MSSIM(x,y);

[0096] Optimization Algorithm: Select Adam as the optimization algorithm.

[0097] Step 5: Model Evaluation

[0098] Use the validation set to evaluate the model and monitor overfitting. Adjust the model parameters or structure based on the evaluation results to improve performance.

[0099] Step 6: Model testing

[0100] The final performance of the model is evaluated on the test set to ensure the generalization ability of the model.

[0101] When the preset AI model test passes, the lining defects are automatically identified through the current preset AI model.

[0102] In summary, the method provided in the embodiment of the present application can provide high-quality, highly reliable training data that is close to actual lining diseases for the preset AI model, thereby improving the detection accuracy of the preset AI model during the application process.

[0103] Reference Figure 8 , an embodiment of the present application provides a processing device for a lining disease data set, the device comprising:

[0104] The first module 810 is used to construct a plurality of standard models, wherein the standard models are used to guide the construction of the standard model entity structure;

[0105] The second module 820 is used to construct a lining disease model according to the standard model, wherein the lining disease model is provided with several types of disease sub-models, the lining disease model is used to guide the construction of the lining disease model entity structure, and the disease sub-model is used to guide the construction of the disease sub-model entity structure in the lining disease model entity structure;

[0106] The third module 830 is used to obtain radar detection data of the physical structure of the lining disease model, wherein the radar detection data includes detection data of multi-angle detection orientations and multi-positions;

[0107] The fourth module 840 is used to generate a lining disease data set according to the radar detection data and the lining disease type in the lining disease model entity structure;

[0108] The fifth module 850 is used to train a preset AI model using a lining disease data set, wherein the preset AI model is used to automatically analyze the disease status of the physical lining.

[0109] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0110] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned lining disease data set processing method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.

[0111] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0112] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0113] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0114] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the processing method of the lining disease data set in the embodiment of this application;

[0115] Input / output interface 903, used to implement information input and output;

[0116] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0117] A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0118] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0119] The embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method for processing the lining disease data set described above is implemented.

[0120] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0121] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0122] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0123] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0124] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0125] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0126] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0127] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0128] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, 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 through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0129] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0130] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0131] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0132] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for processing lining disease data set, characterized in that: The method comprises the following steps: Constructing a number of standard models, wherein the standard models are used to guide the construction of standard model entity structures; A lining disease model is constructed according to the standard model, wherein the lining disease model is provided with several types of disease sub-models, the lining disease model is used to guide the construction of the lining disease model entity structure, and the disease sub-model is used to guide the construction of the disease sub-model entity structure in the lining disease model entity structure; Acquire radar detection data of the physical structure of the lining disease model, wherein the radar detection data includes detection data of multi-angle detection orientations and multi-positions; generating a lining disease data set according to the radar detection data and the lining disease types in the physical structure of the lining disease model; The preset AI model is trained by the lining disease data set, and the preset AI model is used to automatically analyze the disease status of the physical lining.

2. The method according to claim 1, characterized in that The length, width and height of the standard model entity structure are 2.5m, 0.7m and 0.7m respectively; The construction of the standard model entity structure includes: Constructing on-site timber formwork; Tie rods are arranged in the on-site wooden formwork to obtain a standard model entity structure.

3. The method according to claim 1, characterized in that The method of constructing a lining disease model entity structure includes: Obtain entity structures of different types of disease sub-models; The disease sub-model entity structure is embedded in the standard model entity structure, and then C30 concrete is cast in the standard model entity structure to obtain the lining disease model entity structure; the slump range of the concrete is 160mm-180mm, the strength of the concrete within 12 hours after casting is greater than 8Mpa, and the impermeability grade of the concrete is P8.

4. The method according to claim 3, characterized in that The inner bottom plate of the on-site wooden formwork is provided with steel meshes, and the spacing between the steel meshes is 20 cm or 15 cm.

5. The method according to claim 3, characterized in that: After obtaining the physical structure of the lining disease model, the physical structure of the lining disease model is maintained at preset time intervals, and the maintenance time is recorded.

6. The method according to claim 1, characterized in that The generating of the lining disease data set according to the radar detection data and the lining disease types in the physical structure of the lining disease model comprises: Acquire three-dimensional structural description data of the physical structure of the lining disease model; Obtaining detection position information corresponding to the radar detection data; Acquiring the lining defect type corresponding to the detection position information in the three-dimensional structure description data; generating data labels according to the lining disease type; Generate a data pair according to the radar detection data and the data label; All the data pairs are saved to the lining disease dataset.

7. The method according to claim 1, characterized in that The method of training a preset AI model through the lining disease data set includes: Preprocessing the data in the masonry disease data set to obtain a target training data set, wherein the preprocessing includes data cleaning and data standardization; Constructing the preset AI model based on the encoding-decoding architecture; The preset AI model is trained, evaluated and tested using the target training data set.

8. A processing device for lining disease data set, characterized in that: The device comprises: The first module is used to construct a number of standard models, wherein the standard models are used to guide the construction of standard model entity structures; The second module is used to construct a lining disease model according to the standard model, wherein the lining disease model is provided with several types of disease sub-models, the lining disease model is used to guide the construction of the lining disease model entity structure, and the disease sub-model is used to guide the construction of the disease sub-model entity structure in the lining disease model entity structure; The third module is used to obtain radar detection data of the physical structure of the lining disease model, wherein the radar detection data includes detection data of multi-angle detection orientations and multi-positions; A fourth module is used to generate a lining disease data set according to the radar detection data and the lining disease types in the lining disease model entity structure; The fifth module is used to train a preset AI model using the lining disease data set, and the preset AI model is used to automatically analyze the disease status of the physical lining.

9. An electronic device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images