Method for real-time monitoring of quality of UV in-situ curing repair of buried pipelines

Abstract

The present invention belongs to the cross-technical field of pipeline repair and machine learning, and particularly relates to a method for real-time monitoring of the quality of ultraviolet light in-situ curing repair of buried pipelines. First, the on-site in-situ curing data of UV-CIPP materials are collected to construct a data set; then a genetic algorithm optimized support vector machine model for predicting the mechanical properties of UV-CIPP materials under the influence of multiple factors is established, referred to as a GA-SVM model, and the GA-SVM model is trained and verified through the data set to obtain an optimal GA-SVM model; secondly, according to the mechanical parameters of the UV-CIPP materials required by the construction design and the optimal GA-SVM model, the optimal curing parameters and curing temperature are predicted; finally, the predicted optimal curing parameters and curing temperature are input into the integrated control system of the buried pipeline ultraviolet light in-situ curing repair trolley to start the pipeline repair construction; during the repair process, the optimal GA-SVM model is used to monitor the quality of ultraviolet light in-situ curing repair of buried pipelines in real time. The present invention realizes real-time monitoring of the quality of ultraviolet light in-situ curing repair of buried pipelines.

Description

Technical Field

[0001] The present invention belongs to the cross-technical field of pipeline repair and machine learning, and in particular relates to a method for real-time monitoring of the quality of ultraviolet light in-situ curing repair of buried pipelines. Background Art

[0002] The municipal drainage network is an important infrastructure of modern cities, shouldering the heavy responsibility of urban sewage and rainwater discharge. However, with the continuous advancement of my country's urbanization process, the total mileage of underground pipe networks has continued to increase, and the service life of old pipes has become shorter and shorter, gradually exposing problems such as rupture, deformation, corrosion, misalignment, ups and downs, disconnection, penetration, deposition, and scaling. If not repaired, it will inevitably cause road collapse, traffic interruption, property loss, and even threaten people's lives in serious cases. Therefore, it is of great significance to strengthen the maintenance and repair of municipal drainage pipes.

[0003] UV curing repair technology is a trenchless repair technology. Compared with other trenchless repair technologies, it has the advantages of fast construction speed, short construction period, continuous lining pipe, high lining strength and smooth surface. Therefore, it has gradually become the mainstream technology for trenchless repair of buried pipelines. However, there is currently no effective method for real-time monitoring of the repair quality during UV in-situ curing repair. It can only be tested by sampling the UV curing material at the pipe mouth after curing, which is time-consuming and labor-intensive, and it is impossible to monitor the curing repair quality deep in the pipeline. In view of this, when performing UV in-situ curing repair of buried pipelines, how to monitor the pipeline repair quality in real time and optimize the construction parameters on this basis is a problem that needs to be solved urgently. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention proposes a method for real-time monitoring of the quality of ultraviolet in-situ curing repair of buried pipelines. The optimal curing parameters and curing temperature corresponding to the mechanical parameters of UV-CIPP materials required by the construction design are predicted through an optimal GA-SVM model, thereby improving the efficiency and quality of the entire pipeline repair; the optimal GA-SVM model can also be used to realize real-time monitoring of the quality of ultraviolet in-situ curing repair of buried pipelines.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] The present invention provides a method for real-time monitoring of the quality of ultraviolet light in-situ curing repair of buried pipelines, comprising the following steps:

[0007] Step 1, collecting in-situ curing data of UV-CIPP materials and constructing a data set;

[0008] Step 2, establishing a genetic algorithm optimized support vector machine model for predicting mechanical properties of UV-CIPP materials under the influence of multiple factors, referred to as a GA-SVM model, training and verifying the GA-SVM model through a data set to obtain the optimal GA-SVM model;

[0009] Step 3, predicting the optimal curing parameters and curing temperature according to the mechanical parameters of UV-CIPP materials required by the construction design and the optimal GA-SVM model;

[0010] Step 4: Input the predicted optimal curing parameters and curing temperature into the integrated control system of the buried pipeline UV in-situ curing repair trolley to start the pipeline repair construction; during the repair process, use the optimal GA-SVM model to monitor the quality of the buried pipeline UV in-situ curing repair in real time.

[0011] According to the method for real-time monitoring of the quality of buried pipeline UV in-situ curing repair of the present invention, preferably, step 1 comprises the following steps:

[0012] Step 11, collecting the curing temperature and curing parameters of the UV-CIPP material during in-situ curing;

[0013] Step 12, collecting various mechanical parameters of the UV-CIPP material after in-situ curing is completed;

[0014] Step 13, process the data, use the list method to make the data in step 11 correspond to each other in step 12, establish the "curing parameters-curing temperature-various mechanical parameters" database for on-site curing of UV-CIPP materials, and divide the data set proportionally.

[0015] According to the method for real-time monitoring of the quality of UV in-situ curing repair of buried pipelines of the present invention, preferably, the curing temperature is the peak temperature of the curing reaction; the curing parameters include curing time, curing distance, material thickness and UV lamp power; the mechanical parameters include tensile strength and bending strength; and dividing the data set in proportion refers to randomly dividing the data set into a training set and a test set in a ratio of 8:2.

[0016] According to the method for real-time monitoring of the quality of buried pipeline UV in-situ curing repair of the present invention, preferably, step 2 comprises the following steps:

[0017] Step 21, import the data set, determine the population size, termination iteration number, crossover probability and mutation probability of the GA algorithm;

[0018] Step 22, encoding the SVM model parameters to generate an initial population;

[0019] Step 23, import the training set into the SVM model for training, and calculate the fitness of each individual;

[0020] Step 24, determine whether the optimal individual fitness meets the convergence condition, if yes, execute step 26, otherwise execute step 25;

[0021] Step 25, perform genetic operations on the population, obtain a new population through selection, crossover, and mutation, and then execute step 23;

[0022] Step 26, import the test set into the SVM model for performance testing, and output various evaluation indicators;

[0023] Step 27, determine whether each evaluation index meets the requirements, if yes, execute step 28, otherwise execute step 25;

[0024] Step 28, assigning the optimal SVM model parameters as the initial parameters of the SVM model to obtain the optimal GA-SVM model.

[0025] According to the method for real-time monitoring of the quality of UV in-situ curing repair of buried pipelines of the present invention, preferably, the kernel function selected by the SVM model is a polynomial kernel function, and the parameters involved include a penalty parameter c and a kernel function parameter g, and the initial penalty parameter c and the kernel function parameter g are both set to 0.

[0026] According to the method for real-time monitoring of the quality of UV in-situ curing repair of buried pipelines of the present invention, preferably, the individual fitness in step 23 refers to the difference between the output value of the SVM model and the expected value of the experiment.

[0027] According to the method for real-time monitoring of the quality of UV in-situ curing repair of buried pipelines of the present invention, preferably, the process of performing genetic operations on the population in step 25 is actually performing genetic operations on the penalty parameter c and the kernel function parameter g of the SVM model to optimize the penalty parameter c and the kernel function parameter g.

[0028] According to the method for real-time monitoring of the quality of UV in-situ curing repair of buried pipelines of the present invention, preferably, step 3 comprises the following steps:

[0029] Step 31, randomly generating a number of input parameters in the input parameter solution space and encoding the input parameters to generate an initial population, wherein the input parameters are the curing temperature and the curing parameters;

[0030] Step 32, inputting the input parameters in step 31 into the optimal GA-SVM model for training, and calculating the fitness of each individual;

[0031] Step 33, judging whether the optimal individual fitness meets the convergence condition, if so, determining the optimal curing parameters and curing temperature corresponding to the mechanical parameters of the UV-CIPP material required by the construction design; otherwise, executing step 34;

[0032] Step 34, perform genetic operations on the population, obtain a new population through selection, crossover, and mutation, and execute step 32.

[0033] According to the method for real-time monitoring of the quality of UV in-situ curing repair of buried pipelines of the present invention, preferably, the individual fitness in step 32 refers to the difference between the output value of the optimal GA-SVM model and the mechanical parameter value of the UV-CIPP material required by the construction design; the process of performing genetic operations on the population in step 34 is actually performing genetic operations on the input parameters to optimize the curing parameters and the curing temperature.

[0034] According to the method for real-time monitoring of the quality of buried pipeline UV in-situ curing repair of the present invention, preferably, step 4 comprises the following steps:

[0035] Step 41, inputting the optimal curing parameters and curing temperature into the integrated control system of the buried pipeline UV in-situ curing repair trolley;

[0036] Step 42, the trolley integrated control system monitors the curing parameters and curing temperature in real time to determine whether they reach the optimal curing parameters and curing temperature. If they reach them, the pipeline repair construction begins; if not, step 43 is executed;

[0037] Step 43, adjusting the curing parameters and curing temperature by adjusting the ultraviolet lamp power and the lamp chain pulling speed until the curing parameters and curing temperature reach the optimal curing parameters and curing temperature;

[0038] Step 44, during the repair process, the optimal GA-SVM model obtains the mechanical parameters of the corresponding UV-CIPP material based on the input real-time curing parameters and curing temperature of the construction site.

[0039] Compared with the prior art, the present invention has the following advantages:

[0040] 1. The present invention combines the GA algorithm with the SVM model to construct a GA-SVM model, and uses the strong global optimization ability of the GA algorithm to optimize the parameters of the SVM model, which greatly improves the robustness and generalization ability of the SVM model and makes the prediction results more accurate.

[0041] 2. The optimal GA-SVM model established in the present invention can obtain the mechanical parameters of the UV-CIPP material during the UV in-situ curing repair process of buried pipelines based on the curing parameters and curing temperature obtained at the construction site, and can realize real-time monitoring of the quality of UV in-situ curing repair of buried pipelines without damaging the pipelines.

[0042] 3. The present invention can iteratively optimize the curing parameters and curing temperature according to the mechanical property requirements of the UV-CIPP material in the construction design requirements to obtain the optimal curing parameters and curing temperature; the trolley integrated control system monitors the curing parameters and curing temperature in real time, and when the optimal curing parameters and curing temperature are reached, the pipeline repair construction is started; the present invention intelligently optimizes the on-site construction parameters while ensuring the construction quality, which is beneficial to improving the work efficiency and repair quality of the entire repair process. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 It is a flow chart of a method for real-time monitoring of the quality of UV in-situ curing repair of buried pipelines according to an embodiment of the present invention;

[0045] Figure 2 is a schematic diagram of a process for establishing an optimal GA-SVM model according to an embodiment of the present invention;

[0046] Figure 3 is a schematic diagram of a process for obtaining optimal curing parameters and curing temperature according to an embodiment of the present invention;

[0047] Figure 4 It is a flow chart of the trolley integrated control system and the optimal GA-SVM model real-time monitoring according to an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] like Figure 1As shown, the method for real-time monitoring of the quality of UV in-situ curing repair of buried pipelines in this embodiment includes the following steps:

[0050] Step S1, collecting on-site in-situ curing data of UV-CIPP materials and constructing a data set; specifically including steps S11 to S13.

[0051] Step S11, collecting the curing temperature and curing parameters of the UV-CIPP material during in-situ curing. The curing temperature and curing parameters are collected on-site during the UV light in-situ curing of the pipeline repair, and the curing parameters include curing time, curing distance, material thickness and UV lamp power; the curing temperature is the peak temperature of the curing reaction.

[0052] Step S12, collecting various mechanical parameters of the UV-CIPP material after in-situ curing is completed; specifically, the mechanical parameters include tensile strength and flexural strength.

[0053] Step S13, processing the data, using the list method to make the data in step S11 correspond one to one with the data in step S12, establishing a database of "curing parameters-curing temperature-various mechanical parameters" for on-site in-situ curing of UV-CIPP materials, and dividing the data set in proportion; in this example, dividing the data set in proportion means randomly dividing the data set into a training set and a test set in a ratio of 8:2.

[0054] Step S2, establishing a genetic algorithm optimized support vector machine model for predicting mechanical properties of UV-CIPP materials under the influence of multiple factors, referred to as a GA-SVM model, training and verifying the GA-SVM model through a data set to obtain an optimal GA-SVM model; specifically including steps S21 to S28, such as Figure 2 shown.

[0055] Step S21, importing a data set, determining the population size, termination iteration times, crossover probability, and mutation probability of the GA algorithm.

[0056] In this example, the population size is set to 20, the number of termination iterations is set to 100, the crossover probability is set to 0.9, and the mutation probability is set to 0.005.

[0057] Step S22, encoding the SVM model parameters to generate an initial population.

[0058] Specifically, the kernel function selected by the SVM model is a polynomial kernel function, and the parameters involved include a penalty parameter c and a kernel function parameter g, and the initial penalty parameter c and the kernel function parameter g are both set to 0; the encoding method adopts a binary method, that is, the individual is encoded as a binary string.

[0059] Step S23, importing the training set into the SVM model for training, and calculating the fitness of each individual; the individual fitness here refers to the difference between the output value of the SVM model and the expected value of the experiment.

[0060] Step S24, determine whether the optimal individual fitness meets the convergence condition, if yes, execute step S26, otherwise execute step S25. Specifically, the convergence condition is that the optimal individual fitness value and the group fitness value no longer decrease, tend to be stable, or the number of algorithm iterations reaches a preset termination number of iterations.

[0061] Step S25, perform genetic operations on the population, obtain a new population through selection, crossover, and mutation, and then execute step 23; specifically, the selection operation adopts the roulette selection method; in addition, this step is actually to perform genetic operations on the penalty parameter c and the kernel function parameter g of the SVM model, and optimize the penalty parameter c and the kernel function parameter g.

[0062] Step S26, import the test set into the SVM model for performance testing, and output various evaluation indicators; specifically, the evaluation indicators include mean square error MSE and goodness of fit R 2 .

[0063] Step S27, determine whether each evaluation index meets the requirements, if yes, execute step S28, otherwise execute step S25.

[0064] Step S28, assign the optimal SVM model parameters as the initial parameters of the SVM model to obtain the optimal GA-SVM model. Specifically, the optimal GA-SVM model is determined based on the mean square error MSE being as small as possible and the goodness of fit R being as small as possible. 2 As big as possible.

[0065] Step S3, predicting the best curing parameters and curing temperature according to the mechanical parameters of UV-CIPP materials required by the construction design and the optimal GA-SVM model. Specifically including steps S31 to S34, such as Figure 3 shown.

[0066] Step S31 , randomly generating a number of input parameters in the input parameter solution space and encoding the input parameters to generate an initial population, wherein the input parameters are the curing temperature and the curing parameters.

[0067] Specifically, each construction parameter of the UV in-situ curing repair technology has a certain setting range, and the setting range can be used as an input parameter solution space, and the randomly generated input parameters are used as the set construction parameters.

[0068] Step S32, inputting the input parameters in step S31 into the optimal GA-SVM model for training, and calculating the fitness of each individual; the individual fitness here refers to the difference between the output value of the optimal GA-SVM model and the mechanical parameter value of the UV-CIPP material required by the construction design, which needs to be distinguished from the individual fitness in step S23.

[0069] Step S33, judging whether the optimal individual fitness meets the convergence condition, if so, determining the optimal curing parameters and curing temperature corresponding to the mechanical parameters of the UV-CIPP material required by the construction design; otherwise, executing step S34; specifically, the convergence condition is that the optimal individual fitness value and the group fitness value no longer decrease, tend to be stable, or the number of algorithm iterations reaches a preset termination iteration number.

[0070] Step S34, perform genetic operations on the population, obtain a new population through selection, crossover, and mutation, and execute step S32; specifically, the selection operation adopts the roulette wheel selection method; in addition, this step is actually a genetic operation on the input parameters to optimize the curing parameters and the curing temperature, which needs to be distinguished from the genetic operation in step S25.

[0071] Step S4, input the predicted optimal curing parameters and curing temperature into the integrated control system of the buried pipeline UV in-situ curing repair trolley, and start the pipeline repair construction; during the repair process, the optimal GA-SVM model is used to monitor the quality of the buried pipeline UV in-situ curing repair in real time. Specifically, it includes steps S41 to S44, such as Figure 4 shown.

[0072] Step S41, inputting the optimal curing parameters and curing temperature into the integrated control system of the buried pipeline UV in-situ curing repair trolley.

[0073] Step S42, the trolley integrated control system monitors the curing parameters and curing temperature in real time to determine whether they have reached the optimal curing parameters and curing temperature. If so, the pipeline repair construction is started; if not, step S43 is executed.

[0074] Step S43, adjusting the curing parameters and curing temperature by adjusting the ultraviolet lamp power and the lamp chain pulling speed until the curing parameters and curing temperature reach the optimal curing parameters and curing temperature.

[0075] Step S44, during the repair process, the optimal GA-SVM model obtains the corresponding mechanical parameters of the UV-CIPP material based on the input real-time curing parameters and curing temperature of the construction site.

[0076] The present invention proposes a multi-level optimized machine learning model, which can be used to realize real-time monitoring of the repair quality of buried pipelines during UV in-situ curing repair. The model can also be used to optimize the construction parameters in reverse, and the corresponding optimal construction parameters can be obtained according to the mechanical parameters of the UV-CIPP material required by the construction design, thereby greatly accelerating the construction progress, making full use of the mechanical properties of the UV-CIPP material, and extending the service life of the repaired pipeline.

[0077] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The solutions in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and interpreted scripting language JavaScript, etc.

[0078] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0079] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0080] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0081] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0082] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for real-time monitoring of the quality of UV in-situ curing repair of buried pipelines, characterized in that: The following steps are involved: Step 1, collecting in-situ curing data of UV-CIPP materials and constructing a data set; Step 2, establishing a genetic algorithm optimized support vector machine model for predicting mechanical properties of UV-CIPP materials under the influence of multiple factors, referred to as a GA-SVM model, training and verifying the GA-SVM model through a data set to obtain the optimal GA-SVM model; Step 3, predicting the optimal curing parameters and curing temperature according to the mechanical parameters of the UV-CIPP material required by the construction design and the optimal GA-SVM model, wherein the curing temperature is the peak temperature of the curing reaction; The curing parameters include curing time, curing distance, material thickness and UV lamp power; this step specifically includes: Step 31, randomly generating a number of input parameters in the input parameter solution space and encoding the input parameters to generate an initial population, wherein the input parameters are the curing temperature and the curing parameters; Step 32, inputting the input parameters in step 31 into the optimal GA-SVM model for training, and calculating the fitness of each individual; the individual fitness refers to the difference between the output value of the optimal GA-SVM model and the mechanical parameter value of the UV-CIPP material required by the construction design; Step 33, judging whether the optimal individual fitness meets the convergence condition, if so, determining the optimal curing parameters and curing temperature corresponding to the mechanical parameters of the UV-CIPP material required by the construction design; otherwise, executing step 34; Step 34, perform genetic operations on the population, obtain a new population through selection, crossover, and mutation, and execute step 32; the process of performing genetic operations on the population is actually performing genetic operations on the input parameters to optimize the curing parameters and curing temperature; Step 4: Input the predicted optimal curing parameters and curing temperature into the integrated control system of the buried pipeline UV in-situ curing repair trolley to start the pipeline repair construction; during the repair process, use the optimal GA-SVM model to monitor the quality of the buried pipeline UV in-situ curing repair in real time.

2. The method for real-time monitoring of the quality of buried pipeline UV in-situ curing repair according to claim 1 is characterized in that: Step 1 contains the following steps: Step 11, collecting the curing temperature and curing parameters of the UV-CIPP material during in-situ curing; Step 12, collecting various mechanical parameters of the UV-CIPP material after in-situ curing is completed; Step 13, process the data, use the list method to make the data in step 11 correspond to each other in step 12, establish the "curing parameters-curing temperature-various mechanical parameters" database of UV-CIPP material on-site in-situ curing, and divide the data set in proportion.

3. The method for real-time monitoring of the quality of buried pipeline UV in-situ curing repair according to claim 2 is characterized in that: The mechanical parameters include tensile strength and flexural strength; and dividing the data set in proportion means randomly dividing the data set into a training set and a test set in a ratio of 8:

2.

4. The method for real-time monitoring of the quality of UV in-situ curing repair of buried pipelines according to claim 3 is characterized in that: Step 2 contains the following steps: Step 21, import the data set, determine the population size, termination iteration number, crossover probability and mutation probability of the GA algorithm; Step 22, encoding the SVM model parameters to generate an initial population; Step 23, import the training set into the SVM model for training, and calculate the fitness of each individual; Step 24, determine whether the optimal individual fitness meets the convergence condition, if yes, execute step 26, otherwise execute step 25; Step 25, perform genetic operations on the population, obtain a new population through selection, crossover, and mutation, and then execute step 23; Step 26, import the test set into the SVM model for performance testing, and output various evaluation indicators; Step 27, determine whether each evaluation index meets the requirements, if yes, execute step 28, otherwise execute step 25; Step 28, assigning the optimal SVM model parameters as the initial parameters of the SVM model to obtain the optimal GA-SVM model.

5. The method for real-time monitoring of the quality of buried pipeline UV in-situ curing repair according to claim 4 is characterized in that: The kernel function selected by the SVM model is a polynomial kernel function, and the parameters involved include a penalty parameter c and a kernel function parameter g, and the initial penalty parameter c and the kernel function parameter g are both set to 0.

6. The method for real-time monitoring of the quality of buried pipeline UV in-situ curing repair according to claim 4 is characterized in that: The individual fitness in step 23 refers to the difference between the output value of the SVM model and the expected value of the experiment.

7. The method for real-time monitoring of the quality of buried pipeline UV in-situ curing repair according to claim 5 is characterized in that: The process of performing genetic operation on the population in step 25 is actually to perform genetic operation on the penalty parameter c and the kernel function parameter g of the SVM model, and to optimize the penalty parameter c and the kernel function parameter g.

8. The method for real-time monitoring of the quality of buried pipeline UV in-situ curing repair according to claim 1 is characterized in that: Step 4 includes the following steps: Step 41, inputting the optimal curing parameters and curing temperature into the integrated control system of the buried pipeline UV in-situ curing repair trolley; Step 42, the trolley integrated control system monitors the curing parameters and curing temperature in real time to determine whether they reach the optimal curing parameters and curing temperature. If they reach them, the pipeline repair construction begins; if not, step 43 is executed; Step 43, adjusting the curing parameters and curing temperature by adjusting the ultraviolet lamp power and the lamp chain pulling speed until the curing parameters and curing temperature reach the optimal curing parameters and curing temperature; Step 44, during the repair process, the optimal GA-SVM model obtains the mechanical parameters of the corresponding UV-CIPP material based on the input real-time curing parameters and curing temperature of the construction site.

Images