A method and device for evaluating the quality of hot melt connection of a polyethylene pipe reducing joint

Abstract

The application discloses a quality evaluation method and device for hot melt connection of a polyethylene pipe reducing joint. The method comprises the following steps: acquiring original data in a hot melt connection process of the polyethylene pipe reducing joint; the original data comprises reducing joint parameters, process parameters, pipe material parameters and quality classification parameters; preprocessing the original data to obtain a preprocessed data set; based on the preprocessed data set, taking the quality classification parameters as labels, a data set is constructed; welding features are extracted from the data set, and key features with high contribution degrees to quality identification are screened out; based on the key features, a feature data set is constructed; the feature data set is used to train a classifier, and the classifier parameters are optimized and iteratively trained to obtain an optimal classification model; and based on the optimal classification model, quality evaluation is performed on a to-be-tested sample. The application can realize construction process control of hot melt welding defects of the reducing polyethylene pipe, reduce the defect rate, and provide technical support for quality and safety of the polyethylene pipe in actual production.

Description

Technical Field

[0001] This application belongs to the technical field of material processing, connection technology and machine learning, and specifically relates to a quality assessment method and device for the hot-melt connection of polyethylene pipe reducing joints. Background Technology

[0002] Polyethylene (PE) pipes are widely used in critical fields such as water supply and gas transmission due to their excellent corrosion resistance, good toughness, and long service life. To ensure the continuity and sealing performance of pipeline systems, hot-melt welding has become the mainstream method for connecting PE pipes.

[0003] The core principle of hot-melt welding is to heat the pipe ends to a molten state and then apply constant pressure to complete the butt joint, thus forming an integrated welded joint. In actual welding processes, factors such as insufficient temperature control precision, uneven pressure application, and deviations in operating procedures can easily lead to various defects in the welded joint, including voids, slag inclusions, incomplete fusion, and incomplete penetration. These defects not only significantly reduce the mechanical strength of the welded joint but may also cause media leakage, pipe rupture, and other safety accidents during long-term pipeline service, directly affecting the operational safety and reliability of the pipeline system. Therefore, a scientific and accurate assessment of the quality of PE pipe welded joints is of significant practical importance.

[0004] Currently, traditional methods for assessing the quality of welded joints in PE pipes mainly include tensile testing, impact testing, and long-term performance testing. Long-term performance testing encompasses hydrostatic testing, NPT testing, PENT testing, and FNCT testing. While these methods can provide preliminary detection of internal weld defects, they are limited by the precision of testing equipment and the specifications of testing materials. Furthermore, because PE is a non-metallic material, its testing procedures typically follow general pipe testing standards, making it difficult to specifically adapt to the quality inspection needs of welded joints. Therefore, how to achieve efficient and accurate assessment of the heat fusion quality of welded joints during on-site construction has become a pressing technical challenge in this field.

[0005] Polyethylene (PE) pipes are widely used in public utilities such as municipal water supply and drainage, and gas transmission due to their outstanding characteristics such as corrosion resistance, excellent flexibility, and long service life. Hot-melt butt welding, as the core technology for connecting PE pipes, directly determines the operational safety and long-term reliability of the entire pipeline system, and is a crucial link in ensuring the quality of pipeline projects.

[0006] Currently, the quality assessment of PE pipe hot-melt joints mainly relies on two methods: post-construction destructive testing and post-weld visual inspection. Destructive testing suffers from drawbacks such as high testing costs, long testing cycles, and limited sample sizes, making it impossible to comprehensively inspect all welded joints on-site. Visual inspection, on the other hand, is affected by factors such as the professional level of the inspectors and differences in subjective judgment, resulting in low accuracy and difficulty in effectively identifying hidden defects such as incomplete fusion, voids, and slag inclusions within the joint. Therefore, there is a lack of a rapid, non-destructive, and reliable technical means for monitoring and assessing the quality of hot-melt joints during on-site construction.

[0007] In existing technological research, some solutions attempt to monitor parameters during the hot-melt welding process of PE pipes. However, most of these studies remain at the level of real-time recording of welding parameters, lacking intelligent analysis of multi-source welding parameters, and thus failing to achieve accurate prediction and classification of welding defects. This is especially true for welding joints of PE pipes of different diameters. Due to the uneven stress state and complex heat field distribution during the welding process, these joints are more prone to various welding defects compared to joints of the same diameter. Traditional experience-based quality control methods are no longer sufficient to meet the high reliability and high precision requirements of these joints.

[0008] In summary, there is an urgent need in this field for a technical solution that can achieve real-time monitoring and accurate evaluation of the quality of hot-melt connections during on-site construction, and can provide early warning of potential welding defects, in order to overcome the limitations of existing detection methods and ensure the safe and stable operation of PE pipeline systems. Summary of the Invention

[0009] To address the aforementioned technical problems, this application provides a method and apparatus for quality assessment of the hot-melt connection of polyethylene pipe reducing joints.

[0010] The technical solution provided in this application is as follows.

[0011] Firstly, a method for evaluating the quality of heat-fusion connection of polyethylene pipe reducing joints is provided, including: Obtain raw data during the hot-melt connection process of polyethylene pipe reducing joints; the raw data includes reducing parameters, process parameters, pipe material parameters, and quality classification parameters; wherein, the reducing parameters include reducing ratio, pipe wall thickness difference, and reducing ratio-heating time adaptation coefficient; The original data is preprocessed to obtain a preprocessed dataset; Based on the preprocessed dataset, a dataset is constructed using quality classification parameters as labels; Select key features from the dataset that rank highest in terms of their contribution to quality identification; Construct a feature dataset based on key features; The classifier is trained using the feature dataset, and the classifier parameters are optimized and iteratively trained to obtain the best classification model. The quality of the test samples is assessed based on the optimal classification model.

[0012] In one possible implementation, the process parameters include: peak welding pressure, pressure rise slope, pressure fluctuation variance, deviation between actual and set heating plate temperature, temperature stabilization time, heat absorption time, switching time, cooling time, diameter difference of reducing pipe sections, and pipe wall thickness ratio; the pipe parameters include pipe diameter, wall thickness, and material grade; and the quality classification parameters include qualified, incomplete fusion, over-welded, and cold-welded.

[0013] In one possible implementation, the key features include: peak welding pressure, pressure rise slope, pressure fluctuation variance, deviation between actual and set temperature of heating plate, temperature stabilization time, heat absorption time, switching time, cooling time, diameter difference of different pipe sections, pipe wall thickness ratio, and the ratio of different diameters to heating time adaptation coefficient.

[0014] In one possible implementation, the key feature selection method includes tree-based feature importance ranking and recursive feature elimination.

[0015] In one possible implementation, the classifier includes support vector machines and decision tree models.

[0016] In one possible implementation, the method for optimizing the classifier parameters is grid search or Bayesian optimization.

[0017] Secondly, a quality assessment device for the hot-melt connection of polyethylene pipe reducing joints is provided, comprising: The acquisition module is used to acquire raw data during the hot-melt connection process of polyethylene pipe reducing joints; the raw data includes reducing parameters, process parameters, pipe material parameters, and quality classification parameters; wherein, the reducing parameters include reducing ratio, pipe wall thickness difference, and reducing ratio-heating time adaptation coefficient; The preprocessing module is used to preprocess the raw data to obtain a preprocessed dataset; The first building module is used to construct a dataset based on the preprocessed dataset, using quality classification parameters as labels; The filtering module is used to filter out the key features that rank highest in terms of their contribution to quality recognition from the dataset; The second building module is used to construct a feature dataset based on key features; The model building module is used to train the classifier using the feature dataset, optimize the classifier parameters, and perform iterative training to obtain the best classification model. The output module is used to assess the quality of the test samples based on the best classification model.

[0018] Thirdly, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the quality assessment method for the hot-melt connection of polyethylene pipe reducing joints as described in the first aspect.

[0019] Fourthly, a non-transitory computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the quality assessment method for the hot-melt connection of polyethylene pipe reducing joints as described in the first aspect.

[0020] Fifthly, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the quality assessment method for the hot-melt connection of polyethylene pipe reducing joints as described in the first aspect.

[0021] The beneficial effects of this application are as follows: 1. The technical solution provided in this application constructs a defect sample dataset based on the fusion of multiple parameters in the welding process. By collecting key process parameters such as welding pressure, temperature, and time for joints of different diameters, and combining the appearance quality and internal defect information after welding, a defect sample database with classification labels is constructed, providing a data foundation for subsequent database learning and modeling.

[0022] 2. The technical solution provided in this application uses feature selection to extract 12 key features that contribute highly to the evaluation of welding quality from welding parameters. Based on these features, a support vector machine classification model is further constructed to achieve intelligent classification and defect identification of welded joint quality.

[0023] 3. The technical solution provided in this application can analyze welding parameters in real time during construction, dynamically optimize model parameters, improve classification accuracy, and effectively prevent the generation of welding defects. It integrates process specifications and data-driven methods to improve evaluation reliability. It combines traditional hot-melt welding process specifications with data-driven intelligent evaluation methods to form a "process + data" dual control mechanism, thereby improving the evaluation reliability and engineering applicability of the welding quality of reducing joints. Attached Figure Description

[0024] Figure 1 A flowchart illustrating the quality assessment method for the heat fusion connection of polyethylene pipe reducing joints provided in this application embodiment; Figure 2 A schematic diagram of a quality assessment device for the hot-melt connection of a polyethylene pipe reducer provided in an embodiment of this application; Figure 3 A schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0025] 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 some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0027] In the description of this application, it should also be noted that, unless otherwise expressly specified and limited, the terms "set up," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this technology based on the specific circumstances.

[0028] In the description of this application, spatial relation terms such as "below," "under," "below," "below," "above," "over," etc., are used herein to describe the relationship between one element or feature shown in the figures and other elements or features. It should be understood that, in addition to the orientation shown in the figures, spatial relation terms also include different orientations of the device in use and operation. For example, if the device in the figures is flipped, an element or feature described as "below" or "under" or "below" of other elements or features will be oriented "above" other elements or features. Therefore, the exemplary terms "below" and "under" can include both upper and lower orientations. Furthermore, the device may also include other orientations (e.g., rotated 90 degrees or other orientations), and the spatial descriptive terms used herein are interpreted accordingly.

[0029] In the description of this application, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid unnecessarily obscuring the description of this application. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0030] To address the limitations of existing testing methods for hot-melt welding of PE pipes, this application provides a method for evaluating the quality of hot-melt connections of polyethylene pipe reducers.

[0031] See Figure 1 The present application provides a method for quality assessment of the hot-melt connection of a polyethylene pipe reducing joint, comprising: A quality assessment method for the heat fusion connection of a polyethylene pipe reducer includes: S101. Obtain the raw data during the hot-melt connection process of the polyethylene pipe reducing joint; the raw data includes reducing parameters, process parameters, pipe material parameters and quality classification parameters; wherein, the reducing parameters include reducing ratio, pipe wall thickness difference and reducing ratio-heating time adaptation coefficient.

[0032] It should be noted that among the aforementioned reducing parameters, the reducing ratio is a key parameter for measuring the pressure-bearing capacity of PE pipes. SDR = nominal outer diameter (dn or de) / nominal wall thickness (en); the wall thickness difference refers to the absolute value of the difference between the wall thicknesses of the two reducing pipes; the reducing ratio-heating time adaptation coefficient refers to a coefficient used to adapt and calculate the heating time based on the pipe diameter difference when hot-melting PE pipes of different diameters (reduced diameters), and the heating time (s) = pipe wall thickness (mm) × 10³mm / s.

[0033] The aforementioned diameter reduction parameters were chosen because the diameter reduction ratio and the difference in pipe wall thickness are core parameters for thermofusion joining. The diameter reduction ratio-heating time adaptation coefficient can avoid incomplete fusion defects caused by uneven heat conduction. By using the aforementioned diameter reduction parameters as raw data, this application enables the subsequent feature extraction process to fully consider features related to quality identification, thereby improving the quality, feature richness, and information content of the training data and further enhancing the model's performance.

[0034] In one possible implementation, the process parameters include: peak welding pressure, pressure rise slope, pressure fluctuation variance, deviation between actual heating plate temperature and set value, temperature stabilization time, heat absorption time, switching time, cooling time, diameter difference of different pipe sections, and pipe wall thickness ratio.

[0035] It should be noted that pressure fluctuation variance is a statistical indicator that measures the pressure stability of a hydraulic system during hot-melt welding (mainly the cooling and pressure holding stage). It represents the average of the squares of the deviations between the actual pressure value and the set target pressure value.

[0036] Temperature stabilization time refers to the time required after the heating plate reaches the set temperature until its temperature field is uniformly distributed and the temperature difference at various points on the surface enters the allowable tolerance range (i.e., the temperature is in a dynamic equilibrium state).

[0037] The heat absorption time (also known as the heating time) refers to the duration during which the end face of the pipe (or fitting) is heated to melt under the action of welding pressure (or slight heat absorption pressure) while in close contact with the heating plate.

[0038] Switching time refers to the longest time interval from when the heating plate leaves the molten pipe end face to when the two ends of the pipe are rejoined under welding pressure.

[0039] Cooling time refers to the time required for a welded joint to cool to a safe temperature under natural or forced conditions under continuous welding pressure (i.e., butt welding pressure).

[0040] In one possible implementation, the pipe parameters include the pipe diameter, wall thickness, and material grade.

[0041] In one possible implementation, the quality classification parameters include qualified, incomplete fusion, over-welded, and cold-welded.

[0042] For example, after welding is completed, the joint is visually inspected (flange shape, size, uniformity, presence of defects) and necessary non-destructive testing (such as ultrasonic testing) is performed, and each joint is marked with quality (such as "qualified", "not fused", "over-welded", "cold welded", etc.).

[0043] It should be noted that "over-welding" refers to excessive heat input during welding. For example, excessively long heating time, excessively high temperature, or improper cooling can lead to overheating of the material. "Cold welding" refers to insufficient heat input during welding, such as insufficient heating time / temperature, excessively long switching time, or excessively low ambient temperature.

[0044] Specifically, the coding method for quality classification parameters is as follows: qualified 1, not fused 0, over-welded 2, cold welded 3.

[0045] It should be noted that the quality classification is obtained after the welded products are sent for inspection.

[0046] S102. Preprocess the original data to obtain a preprocessed dataset.

[0047] In one possible implementation, the preprocessing includes: data cleaning, normalization, and alignment.

[0048] Furthermore, the data cleaning includes removing invalid data.

[0049] S103. Based on the preprocessed dataset, construct a dataset using quality classification parameters as labels.

[0050] S104. Select the key features that rank highest in terms of contribution to quality recognition from the dataset.

[0051] In one possible implementation, the key features include: peak welding pressure, pressure rise slope, pressure fluctuation variance, deviation between actual and set temperature of heating plate, temperature stabilization time, heat absorption time, switching time, cooling time, diameter difference of different pipe sections, pipe wall thickness ratio, and the ratio of different diameters to heating time adaptation coefficient.

[0052] In one possible implementation, the key feature selection method includes tree-based feature importance ranking and recursive feature elimination.

[0053] S105. Construct a feature dataset based on key features.

[0054] In one possible implementation, the feature dataset includes key features and corresponding quality classification labels.

[0055] S106. Train the classifier using the feature dataset, optimize the classifier parameters and perform iterative training to obtain the best classification model.

[0056] In one possible implementation, the classifier includes support vector machines (SVMs) and decision trees.

[0057] Preferably, the classifier is a support vector machine (SVM).

[0058] In one possible implementation, the classifier parameters are optimized using grid search or Bayesian optimization, which optimizes the classifier's model parameters (e.g., kernel function, penalty coefficient C, kernel parameter γ).

[0059] In one possible implementation, the iterative training method includes: Newly acquired feature data (including key features and their corresponding labels) are incorporated into the feature database, and the data is retrained periodically to achieve iterative evolution of the classification model and improve prediction accuracy.

[0060] S107. Based on the optimal classification model, assess the quality of the test samples.

[0061] In one possible implementation, S107, the method for quality assessment of the sample to be tested includes: The key features of the sample to be tested are obtained, input into the optimal classification model, and the quality assessment results are output.

[0062] For example, the output is "Pass": The system prompts to continue welding and records the data.

[0063] Output "Defect Type (e.g., cold welding risk)": The system immediately issues an audible and visual alarm and can provide possible causes (e.g., "insufficient heating time") based on model interpretability analysis, guiding the operator to highlight or immediately address the joint.

[0064] The content of this application will be further described below with reference to specific embodiments.

[0065] First, the construction process of hot-melt connection of polyethylene pipe reducing joints is introduced. The steps are as follows: a. Before and after hot-melt connection, wipe the dirt off the heated surface of the connection tool with a clean cotton cloth.

[0066] b. The heating time and temperature for hot-melt connection shall comply with the regulations of the hot-melt connection tool manufacturer and the pipe and fitting manufacturer.

[0067] c. During the pressure holding and cooling time of the hot melt connection, the connector must not be moved or any external force must not be applied to the connector.

[0068] d. Before pipe connection, fix the pipe on the frame, remove the milling cutter, close the clamp, and mill the end face of the pipe. When continuous cutting is achieved, remove the clamp and check the gap between the two ends of the pipe (it must not exceed 3mm). The electrofusion connection surface should be clean and the initial surface skin should be scraped off.

[0069] e. For hot-melt butt joints, both pipe sections should extend a certain free length beyond the clamp. Align the connectors to ensure they are on the same axis, and the misalignment should not exceed 10% of the wall thickness.

[0070] f. When the heating plate temperature is suitable (220±10℃), it is best to wait 10 minutes after the indicator light comes on to ensure that the entire heating plate is heated evenly.

[0071] g. Place the heating plate at a suitable temperature on the frame, close the clamp, and set the system pressure. After the absorption time is reached, quickly open the clamp and remove the heating plate. Avoid collisions with the molten end face.

[0072] h. Quickly close the clamp and, within the specified time, uniformly adjust the pressure to the working pressure while pressing the cooling time button. After the cooling time is reached, press the cooling time button again to reduce the pressure to zero, open the clamp, and remove the welded pipe.

[0073] i. Before unloading the hose, the pressure must be reduced to zero. If the welding machine is moved, the hydraulic hose should be disconnected and the joints should be protected from dust.

[0074] j. A qualified weld should have two flanges. On the outer circumference of the pipe where the weld bead is rolled, the shape and size of the two flanges should be uniform and consistent, without pores, bubbles and cracks. The root of the gap between the two flanges should not be lower than the surface of the pipe being welded.

[0075] k. When connecting pipes, welding can be carried out in the trench if site conditions permit, and the pipe openings should be temporarily sealed. In windy conditions, protective measures should be taken or the construction process adjusted.

[0076] Next, we introduce quality assessment methods based on the aforementioned approaches, including: Step S1: Real-time acquisition of multiple parameters: During the welding process, the system simultaneously monitors and records 12 key parameters, including the welding pressure curve, the actual temperature of the heating plate, the heat absorption and cooling time, the diameter ratio, and the difference in pipe wall thickness.

[0077] Step S2, Real-time Analysis by the Intelligent Model: Data is fed into a pre-trained Support Vector Machine (SVM) classification model in real time, and the model outputs the evaluation result within 3 seconds. For example, in a welding process, the system prompts "Cold welding risk: Insufficient heating time, it is recommended to extend the heat absorption time by 8 seconds".

[0078] Step S3, Process Optimization and Iterative Learning: The operator immediately adjusted the process parameters based on the prompts and re-executed the welding process. The subsequent system evaluation result was "qualified," and all parameters of the joint were automatically recorded to the feature database for model iterative learning.

[0079] The optimal model is cross-validated and tested using an independent test set.

[0080] In practical applications, the measured results of this method are as follows: a total of 87 reducing joints were welded, the system provided early warnings and assisted in correcting 11 potential defective welds, and the final non-destructive testing pass rate of all joints reached 100%, which is about 15% higher than previous projects, and significantly reduces the cost of later maintenance and rework.

[0081] The following describes the quality assessment device for the thermal fusion connection of polyethylene pipe reducing joints provided in this application. The quality assessment device for the thermal fusion connection of polyethylene pipe reducing joints described below can be referred to in correspondence with the quality assessment method for the thermal fusion connection of polyethylene pipe reducing joints described above.

[0082] Figure 2 This is a schematic diagram of the structure of the quality assessment device for the heat fusion connection of polyethylene pipe reducing joints provided in the embodiments of this application, as shown below. Figure 2 As shown, it includes: an acquisition module 21, a preprocessing module 22, a first construction module 23, a filtering module 24, a second construction module 25, a model construction module 26, and an output module 27, wherein: The acquisition module 21 is used to acquire raw data during the hot-melt connection process of polyethylene pipe reducing joints; the raw data includes reducing parameters, process parameters, pipe material parameters and quality classification parameters; wherein, the reducing parameters include reducing ratio, pipe wall thickness difference and reducing ratio-heating time adaptation coefficient; Preprocessing module 22 is used to preprocess the raw data to obtain a preprocessed dataset; The first building module 23 is used to build a dataset based on the preprocessed dataset, using quality classification parameters as labels; The filtering module 24 is used to filter out the key features that rank highest in terms of contribution to quality recognition from the dataset; The second building module 25 is used to build a feature dataset based on key features; The model building module 26 is used to train the classifier using the feature dataset, optimize the classifier parameters and perform iterative training to obtain the best classification model. Output module 27 is used to assess the quality of the test samples based on the best classification model.

[0083] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include a processor 310, a communications interface 320, a memory 330, and a communications bus 340. The processor 310, communications interface 320, and memory 330 communicate with each other via the communications bus 340. The processor 310 can call logic instructions from the memory 330 to execute a quality assessment method for the hot-melt connection of polyethylene pipe reducing joints.

[0084] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0085] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the quality assessment method for the hot-melt connection of polyethylene pipe reducing joints provided by the above methods.

[0086] In another aspect, this application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the quality assessment method for the thermal fusion connection of polyethylene pipe reducing joints provided by the methods described above.

[0087] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0088] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for evaluating the quality of heat fusion connection of a polyethylene pipe reducing joint, characterized by, include: Obtain raw data during the hot-melt connection process of polyethylene pipe reducing joints; the raw data includes reducing parameters, process parameters, pipe material parameters, and quality classification parameters; wherein, the reducing parameters include reducing ratio, pipe wall thickness difference, and reducing ratio-heating time adaptation coefficient; The original data is preprocessed to obtain a preprocessed dataset; Based on the preprocessed dataset, a dataset is constructed using quality classification parameters as labels; Select key features from the dataset that rank highest in terms of their contribution to quality identification; Construct a feature dataset based on key features; The classifier is trained using the feature dataset, and the classifier parameters are optimized and iteratively trained to obtain the best classification model. The quality of the test samples is assessed based on the optimal classification model.

2. The method of claim 1, wherein, The process parameters include: peak welding pressure, pressure rise slope, pressure fluctuation variance, deviation between actual heating plate temperature and set value, temperature stabilization time, heat absorption time, switching time, cooling time, diameter difference of different pipe sections, and pipe wall thickness ratio; the pipe parameters include pipe diameter, wall thickness, and material grade; the quality classification parameters include qualified, incomplete fusion, over-welded, and cold-welded.

3. The method of claim 1, wherein, The key features include: peak welding pressure, pressure rise slope, pressure fluctuation variance, deviation between actual heating plate temperature and set value, temperature stabilization time, heat absorption time, switching time, cooling time, diameter difference of different pipe sections, pipe wall thickness ratio, and the matching coefficient of different diameter ratio-heating time.

4. The method of claim 1, wherein, The key feature selection methods include feature importance ranking based on a tree model and recursive feature elimination.

5. The method of claim 1, wherein, The classifiers include support vector machines and decision tree models.

6. The method of claim 1, wherein, The method for optimizing classifier parameters is either grid search or Bayesian optimization.

7. A quality assessment device for the heat fusion connection of polyethylene pipe reducing joints, characterized in that, include: The acquisition module is used to acquire raw data during the hot-melt connection process of polyethylene pipe reducing joints; the raw data includes reducing parameters, process parameters, pipe material parameters, and quality classification parameters; wherein, the reducing parameters include reducing ratio, pipe wall thickness difference, and reducing ratio-heating time adaptation coefficient; The preprocessing module is used to preprocess the raw data to obtain a preprocessed dataset; The first building module is used to construct a dataset based on the preprocessed dataset, using quality classification parameters as labels; The filtering module is used to filter out the key features that rank highest in terms of their contribution to quality recognition from the dataset; The second building module is used to construct a feature dataset based on key features; The model building module is used to train the classifier using the feature dataset, optimize the classifier parameters, and perform iterative training to obtain the best classification model. The output module is used to assess the quality of the test samples based on the best classification model.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the quality assessment method for the hot-melt connection of polyethylene pipe reducing joints as described in any one of claims 1 to 6. 9.A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed by the processor, it implements the quality assessment method for the hot-melt connection of polyethylene pipe reducing joints as described in any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the quality assessment method for the hot-melt connection of polyethylene pipe reducing joints as described in any one of claims 1 to 6.

Images