A pipe aging prediction method, system, device and medium
By collecting and fusing ultraviolet and stress characteristic parameters of pipes, and using machine learning to construct multiple deformation prediction branches and dynamically adjusting the ultraviolet incident angle, the problem of the multi-factor comprehensive influence not being considered in the existing technology is solved, realizing high-precision pipe aging prediction and providing a reliable basis for life assessment.
Patent Information
- Application Number
- CN202511119496.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-11
- Publication Date
- 2026-03-03
- Estimated Expiration
- 2045-08-11
AI Technical Summary
Existing technologies fail to effectively consider the combined effects of multiple factors in pipe aging prediction, resulting in discrepancies between prediction results and actual aging conditions, and thus failing to provide reliable life assessment and preventive maintenance basis.
By collecting ultraviolet and stress characteristic parameters of the pipe installation area, multiple deformation prediction branches are constructed using machine learning, the ultraviolet incident angle is dynamically adjusted, and a confidence-based fusion calculation is performed. Combining the coupled effects of stress and ultraviolet radiation, high-precision aging prediction is achieved.
It significantly improves the accuracy and reliability of pipe aging prediction, provides a more reliable basis for pipeline safety assessment and maintenance strategies, and overcomes the limitation of the disconnect between static environmental parameter assessment and dynamic deformation effects.
Smart Images
Figure CN120950887B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of aging prediction technology, specifically to a method, system, equipment, and medium for predicting the aging of pipes. Background Technology
[0002] In the field of pipeline engineering, accurately predicting the aging degree of pipe materials in the service environment is crucial for ensuring the safe operation of pipeline networks and optimizing maintenance cycles. Pipe aging is a complex process, influenced by a combination of environmental factors. Current technologies for predicting pipe aging typically focus on the analysis of single or independent environmental factors, failing to address the combined aging behavior under the interaction of multiple factors in real-world service environments. This results in discrepancies between predicted and actual aging conditions, hindering reliable data for accurate life assessment and preventative maintenance. Summary of the Invention
[0003] This application provides a method, system, device, and medium for predicting pipe aging, which addresses the technical problem of poor accuracy in predicting pipe aging due to the inability to consider the influence of multiple factors in the prior art.
[0004] In view of the above problems, this application provides a method, system, equipment and medium for predicting pipe aging.
[0005] In a first aspect, this application provides a method for predicting pipe aging, the method comprising:
[0006] The ultraviolet characteristic parameters of the area where the pipe is to be installed, as well as the stress characteristic parameters of the area to be installed, are collected.
[0007] Based on the stress characteristic parameters, pipe deformation is predicted to obtain a pipe deformation parameter sequence and a deformation confidence sequence.
[0008] Based on the pipe deformation parameter sequence, an influence analysis of ultraviolet characteristic parameters is performed to obtain an influential ultraviolet characteristic parameter sequence. Combined with the deformation confidence sequence, the fused ultraviolet characteristic parameters are obtained through fusion processing.
[0009] Based on the deformation confidence sequence, the pipe deformation parameter sequence is fused to obtain fused pipe deformation parameters. Combined with the fused ultraviolet characteristic parameters, pipe aging is predicted to obtain pipe aging parameters.
[0010] Secondly, this application provides a pipe aging prediction system, comprising:
[0011] The parameter acquisition module is used to acquire the ultraviolet characteristic parameters of the area where the pipe is to be installed, as well as the stress characteristic parameters of the area where the pipe is to be installed.
[0012] The deformation prediction module is used to predict pipe deformation based on the stress characteristic parameters, and obtain the pipe deformation parameter sequence and deformation confidence sequence.
[0013] The ultraviolet (UV) feature analysis module is used to perform an influence analysis on UV feature parameters based on the pipe deformation parameter sequence, obtain an influencing UV feature parameter sequence, and combine it with the deformation confidence sequence to obtain fused UV feature parameters.
[0014] The pipe aging prediction module is used to perform fusion processing on the pipe deformation parameter sequence based on the deformation confidence sequence to obtain fused pipe deformation parameters, and combine the fused ultraviolet characteristic parameters to perform pipe aging prediction and obtain pipe aging parameters.
[0015] Thirdly, this application provides a pipe aging prediction device, comprising:
[0016] Memory, used to store the first computer program;
[0017] A processor is used to read and execute a first computer program, thereby realizing the pipe aging prediction method of the first aspect.
[0018] Fourthly, this application provides a non-transitory computer-readable storage medium storing a second computer program, which, when executed by a processor, implements the pipe aging prediction method as described in the first aspect.
[0019] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0020] This application proposes a method, system, equipment, and medium for predicting pipe aging. By dynamically coupling stress-induced deformation and ultraviolet aging effects, and intelligently fusing the confidence levels of multiple prediction branches, it significantly improves the accuracy and reliability of predicting the degree of aging of pipes during long-term service, providing an accurate reference for predicting and maintaining pipe aging failures. Compared with traditional methods, the technical solution provided in this application significantly overcomes the limitation of the disconnect between static environmental parameter assessment and the dynamic influence of deformation.
[0021] This application achieves the technical effect of realizing high-precision and high-robustness prediction of pipe aging, providing a more reliable basis for pipeline safety assessment, scientific formulation of maintenance strategies and extension of pipe service life. Attached Figure Description
[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0023] Figure 1 This is a flowchart illustrating a pipe aging prediction method provided in an embodiment of this application.
[0024] Figure 2 This is a schematic diagram of the structure of a pipe aging prediction system provided in an embodiment of this application.
[0025] Figure 3 This is a schematic diagram of the structure of a pipe aging prediction device provided in an embodiment of this application.
[0026] Figure 4 This is a schematic diagram of the structure of the storage medium provided in the embodiments of this application.
[0027] The components represented by each number in the attached diagram are explained below:
[0028] The system includes a parameter acquisition module 100, a deformation prediction module 200, an ultraviolet feature analysis module 300, a pipe aging prediction module 400, a pipe aging prediction device 500, a memory 510, a processor 520, a first computer program 511, a computer-readable storage medium 600, and a second computer program 611. Detailed Implementation
[0029] This application provides a method, system, device, and medium for predicting pipe aging, which addresses the technical problem of poor accuracy in predicting pipe aging due to the inability to consider multiple factors in the prior art.
[0030] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.
[0031] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.
[0032] Example 1, as Figure 1 As shown, this application provides a method for predicting pipe aging, wherein the method includes:
[0033] S10: Collect the ultraviolet characteristic parameters of the area where the pipe is to be installed, as well as the stress characteristic parameters of the area where the pipe is to be installed.
[0034] In predicting pipe aging, existing methods often suffer from weak predictive foundations due to incomplete or untargeted initial parameter collection.
[0035] Step S10 in the method provided in this application embodiment includes:
[0036] Ultraviolet (UV) irradiation parameters of the area where the pipes are to be installed are collected, and the maximum UV radiation and the corresponding UV angle are extracted to obtain UV characteristic parameters.
[0037] Collect the planned support parameters for pipe installation within the area to be installed to obtain stress characteristic parameters.
[0038] In this embodiment of the application, an ultraviolet radiometer is used to collect the ultraviolet radiation in the area to be installed, the maximum ultraviolet radiation is selected, and the azimuth angle of the sun at the time of the maximum ultraviolet radiation is recorded as the ultraviolet angle.
[0039] The planned support parameters for pipe installation within the installation area are used to obtain stress characteristic parameters. These stress characteristic parameters include the planned support parameters for installation, such as fixing the pipe with supports every 50cm.
[0040] By accurately collecting ultraviolet and stress characteristic parameters of the pipe installation area, the two core environmental driving factors affecting pipe aging—ultraviolet exposure conditions and stress conditions—were fully captured, laying a solid and reliable data foundation for subsequent aging prediction.
[0041] S20: Based on the stress characteristic parameters, predict the deformation of the pipe to obtain the pipe deformation parameter sequence and deformation confidence sequence.
[0042] When assessing the impact of stress, pipe aging prediction methods are usually limited to static analysis of initial stress or deformation estimation of a single scenario, failing to fully simulate the various deformation states and possibilities that may occur in pipes under long-term complex service environments.
[0043] Step S20 in the method provided in this application embodiment includes:
[0044] The stress characteristic parameters are input into the pipe deformation predictor to predict multiple pipe deformation amplitudes, which are used as a sequence of pipe deformation parameters. The pipe deformation predictor includes multiple pipe deformation prediction branches.
[0045] The construction steps of the pipe deformation predictor include:
[0046] Based on historical data of pipe installation, use and maintenance, a set of sample stress characteristic parameters is collected, and the deformation amplitude of the pipe after a preset time length under different sample stress characteristic parameters is collected, and the deformation amplitude set of sample pipe is obtained by labeling.
[0047] Machine learning is used to construct multiple branches for predicting pipe deformation.
[0048] The set of sample stress characteristic parameters and the set of sample pipe deformation amplitudes are randomly divided to obtain multiple sets of pipe deformation prediction training data. Supervised training is performed on multiple pipe deformation prediction branches respectively, and a pipe deformation predictor is obtained after convergence.
[0049] The accuracy of the multiple pipe deformation prediction branches is tested and used as the deformation confidence score to obtain a deformation confidence score sequence.
[0050] In this embodiment, based on historical data of pipe installation, use, and maintenance, a set of sample stress characteristic parameters is collected, and the deformation amplitude of the pipe after a preset time length under different sample stress characteristic parameters is collected, and the sample pipe deformation amplitude set is obtained by labeling. For example, the preset time is set to 30 days, and the deformation amplitude of the pipe is characterized by the amount of pipe deformation, such as bending and collapse caused by pipe aging, with a bending and collapse height of 3cm and a bending and collapse section length of 100cm.
[0051] Machine learning is employed to construct multiple branches for predicting pipe deformation. An exemplary three-layer structure is used: the input layer receives stress feature parameters, the hidden layer has 32 nodes activated using the ReLU function, and the output layer outputs the predicted pipe deformation amplitude.
[0052] Multiple random partitions with replacement are performed on the sample stress characteristic parameter set and the sample pipe deformation amplitude set to obtain multiple sets of pipe deformation prediction training data. Using these multiple sets of training data, supervised training is performed on multiple pipe deformation prediction branches. After all pipe deformation prediction branches converge, for example, by inputting stress characteristic parameters, the arithmetic mean of the results of all pipe prediction branches is calculated as the output of the pipe deformation predictor. If the accuracy is above 85%, the training is considered complete, and the pipe deformation predictor is obtained.
[0053] The accuracy of multiple pipe deformation prediction branches is tested. For example, 20 stress feature parameters from non-training data are input into each pipe deformation prediction branch to obtain 20 predicted pipe deformation amplitudes. These are compared with the actual measured pipe deformation amplitudes. The ratio of the number of predicted pipe deformation amplitudes that match the actual pipe deformation amplitudes to the total number of predicted pipe deformation amplitudes is used as the deformation confidence level. For example, if 18 of the 20 predicted pipe deformation amplitudes are accurate, the deformation confidence level is 18 ÷ 20 = 0.9. The confidence levels of all pipe deformation prediction branches are integrated to obtain a deformation confidence level sequence.
[0054] By utilizing collected stress characteristic parameters and employing a pipe deformation predictor with multiple prediction branches, this method not only predicts a series of potential future deformation amplitudes of the pipe but also simultaneously outputs quantitative indicators reflecting the reliability of each branch's prediction results. This achieves the prediction of the potential deformation state of the pipe under stress and introduces a fine-grained quantification of the confidence level of each prediction scenario. The obtained deformation parameter sequence and confidence score sequence address the problem of traditional methods lacking reliability assessment.
[0055] S30: Based on the pipe deformation parameter sequence, perform an influence analysis on the ultraviolet characteristic parameters to obtain an influence ultraviolet characteristic parameter sequence. Combine this sequence with the deformation confidence sequence and perform fusion processing to obtain fused ultraviolet characteristic parameters.
[0056] Traditional UV aging assessments of pipes have a major drawback: their analysis is based on static UV parameters at the initial installation state, neglecting the crucial fact that the pipe's surface geometry dynamically changes due to stress deformation during service. This change significantly alters the actual effective angle of incidence of sunlight relative to different parts of the pipe, thus greatly affecting the true UV radiation dose and distribution received.
[0057] Step S30 in the method provided in this application embodiment includes:
[0058] The ultraviolet angle within the ultraviolet characteristic parameters is obtained, and combined with the pipe installation direction, a basic incident angle is generated.
[0059] Based on the pipe deformation parameter sequence, the pipe installation direction is adjusted and compensated to obtain the pipe deformation angle sequence.
[0060] A sequence of deformation incident angles is generated based on the pipe deformation angle and the base incident angle.
[0061] Based on the deformation confidence sequence, the deformation incident angle sequence is weighted and fused to obtain the fused incident angle. Combined with the ultraviolet radiation amount within the ultraviolet characteristic parameters, the fused ultraviolet characteristic parameters are obtained.
[0062] In this embodiment, the ultraviolet angle within the ultraviolet characteristic parameters is obtained and combined with the pipe installation direction to generate the basic incident angle. For example, on a horizontal plane, the angle between the azimuth of sunlight and the pipe is calculated as the basic incident angle.
[0063] Based on the pipe deformation parameter sequence, the pipe installation direction is adjusted and compensated to obtain the pipe deformation angle sequence. For example, based on the pipe deformation parameter sequence, the bending collapse height is 3cm and the bending collapse section length is 100cm. Using trigonometric functions to calculate the pipe angle after deformation, the pipe deformation angle = arcsin(3÷100) = 1.72°.
[0064] The pipe deformation angle and the base incident angle are added together to generate a sequence of deformation incident angles. Deformation incident angle = pipe deformation angle + base incident angle. For example, if the pipe deformation angle is 1.72° and the base incident angle is 70°, then the deformation incident angle = 1.72 + 70 = 71.72°.
[0065] Based on the deformed confidence sequence, a weighted fusion calculation is performed on the deformed incident angle sequence to obtain the fused incident angle. The fused incident angle = ∑[deformed incident angle × (confidence level / total confidence level sum)]. For example, when the deformed incident angle is 71.72°, the confidence level is 0.9; when the deformed incident angle is 70°, the confidence level is 0.8; and the total confidence level sum = 0.9 + 0.8 = 1.7. Therefore, the fused incident angle = 71.72 × (0.9 ÷ 1.7) + 70 × (0.8 ÷ 1.7) = 70.09°.
[0066] By combining the ultraviolet radiation amount within the ultraviolet characteristic parameters, the fused ultraviolet characteristic parameters are obtained. The fused ultraviolet characteristic parameters include the fused incident angle and the ultraviolet radiation amount.
[0067] This application dynamically assesses the actual impact of pipe deformation on ultraviolet (UV) exposure conditions. It utilizes a predicted sequence of pipe deformation parameters to dynamically adjust the pipe's geometric orientation, calculating a more realistic effective UV incident angle, thus accurately reflecting how deformation alters the actual effect of UV radiation. Weighted fusion calculations of UV parameters under different deformation scenarios are performed using confidence levels. This fusion mechanism, based on prediction reliability, ensures that high-confidence prediction scenarios contribute more significantly to the final result, effectively suppressing interference from low-confidence scenarios, and ultimately generating fused UV characteristic parameters that more robustly and accurately represent future comprehensive UV exposure conditions.
[0068] S40: Based on the deformation confidence sequence, the pipe deformation parameter sequence is fused to obtain fused pipe deformation parameters. Combined with the fused ultraviolet characteristic parameters, pipe aging prediction is performed to obtain pipe aging parameters.
[0069] Existing models often treat UV and stress / deformation factors independently or simply superimpose them, failing to establish the coupling influence mechanism between the two in the dynamic process. This makes it impossible to accurately simulate the complex aging process under their interaction, resulting in a gap between the final prediction results and the actual aging behavior.
[0070] Step S40 in the method provided in this application embodiment includes:
[0071] Based on the deformation confidence sequence, the deformation parameter sequence of the pipe is weighted and fused to obtain the fused pipe deformation amplitude.
[0072] The deformation range of the fused pipe is used as the deformation parameter of the fused pipe.
[0073] An ultraviolet aging predictor is obtained, wherein the ultraviolet aging predictor is trained using a sample ultraviolet characteristic parameter set, a sample pipe deformation parameter set, and a sample pipe aging parameter set after a preset time length, and each sample pipe aging parameter includes the aging progress.
[0074] The fused ultraviolet characteristic parameters and fused pipe deformation parameters are input into the ultraviolet aging predictor, and the pipe aging parameters are obtained from the prediction output.
[0075] In this embodiment of the application, the deformation parameter sequence of the pipe is weighted and fused according to the deformation confidence sequence to obtain the fused pipe deformation amplitude. The deformation range of the integrated pipe is calculated as follows: ∑[pipe deformation parameter × (confidence level / total confidence level sum)]. For example, if a pipe deformation parameter is a bending collapse height of 3cm and a bending collapse section length of 100cm, the confidence level corresponding to this deformation parameter is 0.9. If a pipe deformation parameter is a bending collapse height of 4cm and a bending collapse section length of 100cm, the confidence level corresponding to this deformation parameter is 0.85. The total confidence level sum is 0.9 + 0.85 = 1.75. Therefore, the bending collapse height in the integrated pipe deformation range is 3 × (0.9 ÷ 1.75) + 4 × (0.85 ÷ 1.75) = 3.48, and the bending collapse height in the integrated pipe deformation range is 100 × (0.9 ÷ 1.75) + 100 × (0.85 ÷ 1.75) = 100. The integrated pipe deformation range has a bending collapse height of 3.48cm and a bending collapse section length of 100cm.
[0076] The deformation amplitude of the fused pipe is used as the deformation parameter of the fused pipe.
[0077] Machine learning is used to construct an ultraviolet aging predictor, which adopts an exemplary three-layer structure: the input layer receives ultraviolet feature parameters and pipe deformation parameters, the hidden layer has 64 nodes and is activated using the ReLU function, and the output layer outputs the pipe aging parameters.
[0078] Ultraviolet (UV) characteristic parameters are integrated into a sample UV characteristic parameter set, and pipe deformation parameters are integrated into a sample pipe deformation parameter set. Pipe aging parameters are collected after a preset time period and used as a sample pipe aging parameter set. For example, if the preset time period is set to 30 days, the pipe aging parameter represents the aging progress, with a value range of 0 to 100, where 0 indicates no aging and 100 indicates complete aging and unusable.
[0079] The ultraviolet predictor is trained in a supervised manner until convergence using a set of sample ultraviolet characteristic parameters, a set of sample pipe deformation parameters, and a set of sample pipe aging parameters after a preset time length. For example, if the accuracy of the output aging progress is above 90% when inputting ultraviolet characteristic parameters and pipe deformation parameters, the ultraviolet predictor training is complete.
[0080] The fused ultraviolet characteristic parameters and fused pipe deformation parameters are input into the ultraviolet aging predictor, and the predicted output obtains the pipe aging parameters as the aging prediction result.
[0081] By using a weighted fusion calculation of the pipe deformation parameter sequence using a deformation confidence sequence, a fused pipe deformation parameter is obtained that comprehensively reflects the probability and reliability of various prediction scenarios, providing a robust and representative deformation state input for aging prediction. This fused deformation parameter, along with fused ultraviolet characteristic parameters, is then input into a comprehensive aging prediction model. Through this collaborative prediction mechanism based on confidence-fused key parameter input and coupled aging effects, the final output pipe aging parameters significantly improve the accuracy and reliability of the prediction results in real service environments, providing a more credible basis for life assessment and maintenance decisions.
[0082] Example 2, as Figure 2 As shown, based on the same inventive concept as the pipe aging prediction method provided in Embodiment 1, this embodiment of the invention also provides a pipe aging prediction system, including:
[0083] The parameter acquisition module 100 is used to acquire the ultraviolet characteristic parameters of the area where the pipe is to be installed, as well as the stress characteristic parameters of the area where the pipe is to be installed.
[0084] The deformation prediction module 200 is used to predict the deformation of the pipe based on the stress characteristic parameters, and to obtain the pipe deformation parameter sequence and deformation confidence sequence.
[0085] The ultraviolet feature analysis module 300 is used to perform an influence analysis on ultraviolet feature parameters based on the pipe deformation parameter sequence, obtain an influence ultraviolet feature parameter sequence, and combine it with the deformation confidence sequence to obtain fused ultraviolet feature parameters.
[0086] The pipe aging prediction module 400 is used to perform fusion processing on the pipe deformation parameter sequence according to the deformation confidence sequence to obtain fused pipe deformation parameters, and combine the fused ultraviolet characteristic parameters to perform pipe aging prediction and obtain pipe aging parameters.
[0087] In one embodiment, the parameter acquisition module 100 is further configured to:
[0088] Ultraviolet (UV) irradiation parameters of the area where the pipes are to be installed are collected, and the maximum UV radiation and the corresponding UV angle are extracted to obtain UV characteristic parameters.
[0089] Collect the planned support parameters for pipe installation within the area to be installed to obtain stress characteristic parameters.
[0090] In one embodiment, the deformation prediction module 200 is further configured to:
[0091] The stress characteristic parameters are input into the pipe deformation predictor to predict multiple pipe deformation amplitudes, which are used as a sequence of pipe deformation parameters. The pipe deformation predictor includes multiple pipe deformation prediction branches.
[0092] The construction steps of the pipe deformation predictor include:
[0093] Based on historical data of pipe installation, use and maintenance, a set of sample stress characteristic parameters is collected, and the deformation amplitude of the pipe after a preset time length under different sample stress characteristic parameters is collected, and the deformation amplitude set of sample pipe is obtained by labeling.
[0094] Machine learning is used to construct multiple branches for predicting pipe deformation.
[0095] The set of sample stress characteristic parameters and the set of sample pipe deformation amplitudes are randomly divided to obtain multiple sets of pipe deformation prediction training data. Supervised training is performed on multiple pipe deformation prediction branches respectively, and a pipe deformation predictor is obtained after convergence.
[0096] The accuracy of the multiple pipe deformation prediction branches is tested and used as the deformation confidence score to obtain a deformation confidence score sequence.
[0097] In one embodiment, the ultraviolet feature analysis module 300 is further used for:
[0098] The ultraviolet angle within the ultraviolet characteristic parameters is obtained, and combined with the pipe installation direction, a basic incident angle is generated.
[0099] Based on the pipe deformation parameter sequence, the pipe installation direction is adjusted and compensated to obtain the pipe deformation angle sequence.
[0100] A sequence of deformation incident angles is generated based on the pipe deformation angle and the base incident angle.
[0101] Based on the deformation confidence sequence, the deformation incident angle sequence is weighted and fused to obtain the fused incident angle. Combined with the ultraviolet radiation amount within the ultraviolet characteristic parameters, the fused ultraviolet characteristic parameters are obtained.
[0102] In one embodiment, the pipe aging prediction module 400 is further configured to:
[0103] Based on the deformation confidence sequence, the deformation parameter sequence of the pipe is weighted and fused to obtain the fused pipe deformation amplitude.
[0104] The deformation range of the fused pipe is used as the deformation parameter of the fused pipe.
[0105] An ultraviolet aging predictor is obtained, wherein the ultraviolet aging predictor is trained using a sample ultraviolet characteristic parameter set, a sample pipe deformation parameter set, and a sample pipe aging parameter set after a preset time length, and each sample pipe aging parameter includes the aging progress.
[0106] The fused ultraviolet characteristic parameters and fused pipe deformation parameters are input into the ultraviolet aging predictor, and the pipe aging parameters are obtained from the prediction output.
[0107] Example 3, as Figure 3 As shown, this embodiment of the invention also provides a pipe aging prediction device 500, comprising:
[0108] Memory 510 is used to store the first computer program 511;
[0109] The processor 520 is used to read and execute the first computer program 511, thereby implementing the pipe aging prediction method of Embodiment 1.
[0110] Example 4, as Figure 4 As shown, this embodiment of the invention also provides a non-transitory computer-readable storage medium 600, which stores a second computer program 611. When the second computer program 611 is executed by a processor, it implements the pipe aging prediction method as described in Embodiment 1.
[0111] In summary, the embodiments of this application have at least the following technical effects:
[0112] This application proposes a method, system, device, and medium for predicting pipe aging. By dynamically coupling stress-induced deformation and ultraviolet aging effects and intelligently fusing the confidence levels of multiple prediction branches, it significantly improves the accuracy and reliability of predicting the degree of aging of pipes during long-term service. Compared with traditional methods, the technical solution provided in this application significantly overcomes the limitation of the disconnect between static environmental parameter assessment and the dynamic influence of deformation. This application collects ultraviolet characteristic parameters and stress characteristic parameters of the area to be installed, and uses a pipe deformation predictor with multiple branches trained on historical data. It not only predicts the possible deformation amplitude sequence of the pipe in the future, but also simultaneously outputs the deformation confidence sequence reflecting the reliability of each branch prediction, enabling subsequent analysis to finely quantify the probability of different deformation scenarios. This application dynamically analyzes the actual impact of pipe deformation on future ultraviolet exposure conditions, that is, it uses the predicted deformation parameter sequence to dynamically compensate for the pipe installation direction, solving the key problem of inaccurate ultraviolet dose assessment caused by neglecting deformation in traditional methods. Furthermore, by utilizing the deformation confidence sequence, a confidence-based weighted fusion calculation is performed on the dynamically generated deformation incident angle sequence and the pipe deformation parameter sequence itself. This ensures that the prediction branches with high reliability contribute more to the final result, effectively suppressing the noise and uncertainty that may be introduced by the low-confidence prediction branches. Ultimately, this enables the aging prediction model to more realistically and reliably simulate the comprehensive aging behavior of pipes under complex environments.
[0113] This application achieves the technical effect of realizing high-precision and high-robustness prediction of pipe aging, providing a more reliable basis for pipeline safety assessment, scientific formulation of maintenance strategies and extension of pipe service life.
[0114] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.
[0115] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.
[0116] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.
Claims
1. A pipe aging prediction method characterized by comprising: The method comprises: Collecting the ultraviolet characteristic parameters of the pipe material to-be-installed area and the stress characteristic parameters of the to-be-installed area; According to the stress characteristic parameters, pipe material deformation prediction is performed to obtain a pipe material deformation parameter sequence and a deformation confidence sequence; According to the pipe material deformation parameter sequence, influence analysis of the ultraviolet characteristic parameters is performed to obtain an influence ultraviolet characteristic parameter sequence, and the deformation confidence sequence is combined to obtain a fused ultraviolet characteristic parameter through fusion processing; According to the deformation confidence sequence, the pipe material deformation parameter sequence is fused to obtain a fused pipe material deformation parameter, and the fused pipe material deformation parameter is combined with the fused ultraviolet characteristic parameter to perform pipe material aging prediction and obtain a pipe material aging parameter.
2. The pipe aging prediction method according to claim 1, characterized by, Collecting the ultraviolet characteristic parameters of the pipe material to-be-installed area and the stress characteristic parameters of the to-be-installed area comprises: Collecting the ultraviolet irradiation parameters of the pipe material to-be-installed area, extracting the maximum value of the ultraviolet radiation amount and the corresponding ultraviolet angle to obtain the ultraviolet characteristic parameters; Collecting the planning support parameters for pipe material installation in the to-be-installed area to obtain the stress characteristic parameters.
3. The pipe aging prediction method according to claim 1, characterized by, According to the stress characteristic parameters, pipe material deformation prediction is performed to obtain a pipe material deformation parameter sequence and a deformation confidence sequence, which comprises: The stress characteristic parameters are input into a pipe material deformation predictor to predict a plurality of pipe material deformation amplitudes as the pipe material deformation parameter sequence, wherein the pipe material deformation predictor comprises a plurality of pipe material deformation prediction branches; The accuracy of the plurality of pipe material deformation prediction branches is tested and obtained as the deformation confidence to obtain a deformation confidence sequence.
4. The pipe aging prediction method according to claim 3, characterized by, The construction steps of the pipe material deformation predictor comprise: According to the historical data of pipe material installation, use and maintenance, a sample stress characteristic parameter set is collected, and the amplitudes of pipe material deformation after a preset time length under different sample stress characteristic parameters are collected to obtain a sample pipe material deformation amplitude set; Machine learning is used to construct a plurality of pipe material deformation prediction branches; The sample stress characteristic parameter set and the sample pipe material deformation amplitude set are randomly divided to obtain a plurality of pipe material deformation prediction training data, and the plurality of pipe material deformation prediction branches are respectively supervised and trained, and the pipe material deformation predictor is obtained after convergence.
5. The pipe aging prediction method according to Claim 1, characterized by, According to the pipe material deformation parameter sequence, influence analysis of the ultraviolet characteristic parameters is performed to obtain an influence ultraviolet characteristic parameter sequence, and the deformation confidence sequence is combined to obtain a fused ultraviolet characteristic parameter through fusion processing, which comprises: The ultraviolet angle in the ultraviolet characteristic parameters is obtained, and the pipe material installation direction is combined to generate a basic incidence angle; According to the pipe material deformation parameter sequence, the pipe material installation direction is adjusted and compensated to obtain a pipe material deformation angle sequence; According to the pipe material deformation angle and the basic incidence angle, a deformation incidence angle sequence is generated; According to the deformation confidence sequence, the deformation incidence angle sequence is weighted and fused to calculate a fused incidence angle, and the ultraviolet radiation amount in the ultraviolet characteristic parameters is combined to obtain a fused ultraviolet characteristic parameter.
6. The pipe aging prediction method according to Claim 1, characterized by, According to the deformation confidence sequence, the pipe material deformation parameter sequence is fused to obtain a fused pipe material deformation parameter, which comprises: According to the deformation confidence sequence, the pipe deformation parameter sequence is weighted and fused to obtain a fused pipe deformation amplitude; The fused pipe deformation amplitude is taken as a fused pipe deformation parameter.
7. The pipe aging prediction method according to Claim 1, characterized by, In combination with the fused ultraviolet characteristic parameter, pipe aging prediction is performed to obtain a pipe aging parameter, including: An ultraviolet aging predictor is acquired, wherein the ultraviolet aging predictor is trained by using a sample ultraviolet characteristic parameter set, a sample pipe deformation parameter set, and a sample pipe aging parameter set of the pipe after a preset time length, and each sample pipe aging parameter includes an aging progress; The fused ultraviolet characteristic parameter and the fused pipe deformation parameter are input into the ultraviolet aging predictor to obtain a pipe aging parameter through prediction output.
8. A pipe aging prediction system characterized by comprising: A system for implementing the pipe aging prediction method of any one of claims 1 to 7, the system comprising: A parameter acquisition module configured to acquire an ultraviolet characteristic parameter of a pipe installation area and a stress characteristic parameter of the installation area; A deformation prediction module configured to perform pipe deformation prediction according to the stress characteristic parameter to obtain a pipe deformation parameter sequence and a deformation confidence sequence; An ultraviolet characteristic analysis module configured to perform influence analysis of the ultraviolet characteristic parameter according to the pipe deformation parameter sequence to obtain an influence ultraviolet characteristic parameter sequence, and to obtain a fused ultraviolet characteristic parameter through fusion processing in combination with the deformation confidence sequence; A pipe aging prediction module configured to perform fusion processing on the pipe deformation parameter sequence to obtain a fused pipe deformation parameter according to the deformation confidence sequence, and to perform pipe aging prediction in combination with the fused ultraviolet characteristic parameter to obtain a pipe aging parameter.
9. A pipe aging prediction device characterized by comprising: including: A memory configured to store a first computer program; A processor configured to read and execute the first computer program to implement the pipe aging prediction method of claims 1 to 7.
10. A non-transitory computer-readable storage medium, comprising: The storage medium stores a second computer program, and the second computer program is executed by the processor to implement the pipe aging prediction method of any one of claims 1 to 7.
Citation Information
Patent Citations
Oil and gas pipeline axial strain intelligent monitoring device and method
CN114034277A
Method and system for predicting aging life of waterproof coating
CN119647084A