Quality spot check excavation management method, device and equipment for circumferential weld of pipeline and medium

Abstract

The invention discloses a quality spot check excavation management method, device and equipment for a pipeline circumferential weld and a medium, and relates to the technical field of data processing. According to the method, basic data information of all circumferential welds on a target pipeline is obtained, and a prediction attribute set and an excavation criterion set which are determined in advance and used for circumferential weld quality prediction are obtained; according to the basic data information, determining attribute judgment information of each circumferential weld relative to the prediction attribute set; according to the attribute judgment information and the excavation criterion set, quality risk prediction information of the corresponding circumferential weld is determined; according to the quality risk prediction information, circumferential weld excavation information of the target pipeline is generated, and a target circumferential weld meeting the excavation requirement is determined according to the circumferential weld excavation information. By means of the method, the quality risk of the pipeline circumferential weld is rapidly and accurately evaluated, the target circumferential weld with the high-risk quality risk can be accurately positioned, the judgment accuracy and excavation efficiency of the high-risk circumferential weld are improved, and the excavation cost is reduced.

Description

Quality inspection of pipeline circumferential welds: excavation management methods, equipment, and media. Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, equipment, and medium for quality inspection and excavation management of pipeline circumferential welds. Background Technology

[0002] Long-distance oil and gas pipelines consist of circumferential welds between steel pipes. These circumferential welds are welded on-site, and their quality stability is subject to fluctuations due to multiple factors such as the on-site environment and human operation. Defects such as cracks in the circumferential welds can easily lead to leaks, explosions, and other accidents. Therefore, even after the pipeline is put into operation, it is still necessary to predict the risks of defects and cracks in the circumferential welds, identify high-risk weld joints, and carry out maintenance in advance.

[0003] However, the formation of defects and cracks in circumferential welds is influenced by multiple factors, making accurate prediction difficult using a single detection or evaluation method. This can easily lead to misjudgments or omissions in risk assessment. Furthermore, overlooking high-risk welds may leave safety hazards, or blind excavation may increase maintenance costs and reduce disposal efficiency, failing to meet the actual needs of long-term safe operation of oil and gas pipelines. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and medium for quality inspection and excavation management of pipeline circumferential welds. It addresses the problem that existing methods using a single detection or evaluation approach are insufficient for accurate prediction of circumferential weld quality risks, and are prone to misjudgment and omission of risks. This invention improves the accuracy of identifying high-risk circumferential welds and excavation efficiency, while reducing excavation costs.

[0005] In a first aspect, embodiments of the present invention provide a method for quality inspection and excavation management of pipeline circumferential welds, the method comprising:

[0006] Acquire basic data information of each circumferential weld on the target pipeline, and obtain the pre-determined set of prediction attributes and excavation criteria for predicting the quality of the circumferential welds.

[0007] Based on the basic data information, determine the attribute determination information of each circumferential weld relative to the predicted attribute set;

[0008] Based on the attribute determination information and the excavation criterion set, the quality risk prediction information of the corresponding circumferential weld is determined;

[0009] Based on the quality risk prediction information, the circumferential weld excavation information of the target pipeline is generated, and the target circumferential weld that meets the excavation requirements is determined according to the circumferential weld excavation information.

[0010] Secondly, embodiments of the present invention provide a pipeline circumferential weld quality inspection and excavation management device, the device comprising:

[0011] The acquisition module is used to acquire basic data information of each circumferential weld on the target pipeline, and to acquire the pre-determined prediction attribute set and excavation criterion set used for circumferential weld quality prediction.

[0012] The first information determination module is used to determine the attribute determination information of each of the circumferential welds relative to the predicted attribute set based on the basic data information.

[0013] The second information determination module is used to determine the quality risk prediction information of the corresponding circumferential weld based on the attribute determination information and the excavation criterion set.

[0014] The target circumferential weld determination module is used to generate circumferential weld excavation information for the target pipeline based on the quality risk prediction information, and to determine the target circumferential weld that meets the excavation requirements according to the circumferential weld excavation information.

[0015] Thirdly, embodiments of the present invention provide an electronic device, the electronic device comprising:

[0016] At least one processor;

[0017] and a memory communicatively connected to the at least one processor;

[0018] The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the pipeline circumferential weld quality inspection and excavation management method according to any embodiment of the present invention.

[0019] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute the pipeline circumferential weld quality inspection and excavation management method described in any embodiment of the present invention.

[0020] Fifthly, embodiments of the present invention also provide a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the pipeline circumferential weld quality inspection and excavation management method according to any embodiment of the present invention.

[0021] The technical solution of this invention involves acquiring basic data information of each circumferential weld on a target pipeline, and obtaining a pre-determined set of prediction attributes and excavation criteria for predicting the quality of the circumferential welds. Based on the basic data information, the attribute judgment information of each circumferential weld relative to the prediction attribute set is determined. Based on the attribute judgment information and the excavation criteria set, the quality risk prediction information of the corresponding circumferential weld is determined. Based on the quality risk prediction information, excavation information for the circumferential welds of the target pipeline is generated, and target circumferential welds meeting excavation requirements are determined according to the excavation information. Using this method, based on the basic data information of each circumferential weld on the target pipeline and the pre-determined set of prediction attributes and excavation criteria, a rapid and accurate assessment of the quality risk of pipeline circumferential welds is achieved. This method can accurately locate target circumferential welds with high quality risks, improving the accuracy of identifying high-risk circumferential welds and excavation efficiency, while reducing excavation costs.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] 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.

[0024] Figure 1 is a flowchart of a method for quality inspection and excavation management of pipeline circumferential welds provided in an embodiment of the present invention.

[0025] Figure 2 is a structural schematic diagram of a pipeline circumferential weld quality inspection and excavation management device provided in an embodiment of the present invention.

[0026] Figure 3 shows a schematic diagram of the structure of an electronic device that can be used to implement an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] It is understood that before using the technical methods disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0030] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose, based on the prompt message, whether to provide personal information to the software or hardware such as the electronic device, application, server, or storage medium performing the operations of this disclosed technology.

[0031] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0032] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0033] Specifically, this invention provides a method for quality inspection and excavation management of pipeline circumferential welds. Figure 1 is a flowchart of a method for quality inspection and excavation management of pipeline circumferential welds provided by this invention. This invention is applicable to scenarios where defects and crack risks of circumferential welds are predicted to identify high-risk welds. This method can be executed by a pipeline circumferential weld quality inspection and excavation management device, which can be implemented in the form of software and / or hardware. Optionally, it can be implemented through electronic devices, preferably mobile terminals, desktop computers, laptops, and servers.

[0034] As shown in Figure 1, the pipeline circumferential weld quality inspection and excavation management method provided in this embodiment of the invention may specifically include:

[0035] S101. Obtain basic data information of each circumferential weld on the target pipeline, and obtain the pre-determined prediction attribute set and excavation criterion set for predicting the quality of the circumferential weld.

[0036] In this embodiment, the target pipeline can be considered as a buried, operational long-distance oil and gas pipeline that requires quality inspection and excavation management, consisting of circumferential welds between steel pipes. It is known that a circumferential weld (i.e., the weld joint) is a circular weld formed on-site after two sections of steel pipe are joined together; this is the part of the target pipeline most prone to quality risks. To determine whether there are quality problems with the circumferential welds of the target pipeline, such as welding defects or cracks, excavation of the target pipeline is necessary. However, excavating all circumferential welds is time-consuming, labor-intensive, and costly. Therefore, it is necessary to predict the quality risks of the circumferential welds in order to conduct spot checks and achieve the goal of discovering the greatest hidden dangers with minimal excavation.

[0037] Based on this, in this step, the basic data information of each circumferential weld on the target pipeline is first obtained, along with a pre-determined set of prediction attributes and excavation criteria for predicting the quality of the circumferential welds. The basic data information can be considered as data obtained by integrating relevant materials and inspection data, using a single circumferential weld as the basic data unit. For example, the basic data information may include: as-built data related to the circumferential weld, X-ray films, a list of internally inspected pipe sections, and internal magnetic flux leakage detection signal data, etc.

[0038] Among them, the relevant as-built documentation for circumferential welds can be considered as data forms that record relevant information about the circumferential welds (such as weld number, construction unit, inspection unit, upstream and downstream pipe section lengths and types, etc.). X-ray films can be understood as films obtained through X-ray inspection methods. X-ray inspection is an important technical means to detect whether circumferential welds contain defects exceeding standard requirements during the construction process. The images recorded on the films can be used to determine the extent of defects contained in the circumferential welds.

[0039] After the target pipeline is constructed, the pipeline operator will periodically conduct magnetic flux leakage (MF) internal testing to promptly detect changes in the pipeline's condition. This results in a list of inspected pipe sections and MF internal testing signal data. The list of inspected pipe sections records relevant information such as the length and type of upstream and downstream pipe sections of the circumferential weld. This information can be compared with the information recorded in the circumferential weld as-built documentation to determine if any weld joints are not recorded in the documentation. The MF internal testing signal data is a magnetic signal spectrum obtained through MF internal testing, similar to an X-ray film, and can also be used to qualitatively determine the presence of defects in the circumferential weld.

[0040] The predicted attribute set can be understood as a pre-determined standard attribute framework for all circumferential welds, used to predict the quality of circumferential welds. The predicted attribute set can include attribute items and corresponding attribute judgment rules. Attribute items can be considered factors that influence the quality risk of circumferential welds. The attribute judgment rules corresponding to attribute items can include the value range of the attribute item and the value judgment rules. Optionally, the predicted attribute set can be determined based on expert knowledge and information gain algorithms. For example, the predicted attribute set can include whether the weld is questionable on radiograph (yes / no), whether it is suspected of being a black weld (yes / no), the severity of the anomaly (no anomaly / slight / relatively serious / serious), whether it is a dead weld (yes / no), the type of downstream pipe section for internal inspection (straight pipe / elbow / cold-bent pipe), and whether the radiographic inspection is qualified (yes / no / unknown), etc. The predicted attribute set may also include attribute items such as the construction unit and welding date, as well as their corresponding value ranges and attribute judgment rules.

[0041] The excavation criterion set can be considered a collection used to assess the quality risk of circumferential welds to support excavation management, and it consists of multiple criterion description items. Each criterion description item includes attribute determination descriptions and quality risk prediction indicators. Attribute determination descriptions can be considered as conditions consisting of a series of attribute constraints, i.e., the attribute determination description includes attribute items and attribute constraints on the relative values ​​of the attribute items. Quality risk prediction information can be understood as predictive information used to assess the level of quality risk of circumferential welds. For example, the excavation criterion set may include the following criterion description items: the attribute determination description of the criterion description item is [Radiographic inspection_qualified = no, internal inspection downstream pipe section type = non-straight pipe, whether to repair the opening = yes, whether to change wall thickness = yes], and the corresponding quality risk prediction indicators may include a crack proportion prediction value of 100% and a prediction fluctuation range of 100% ± 0%.

[0042] S102. Based on the basic data information, determine the attribute judgment information of each ring weld relative to the predicted attribute set.

[0043] In this embodiment, for each circumferential weld of the target pipeline, the specific values ​​of the corresponding attributes are extracted one by one from the basic data information of the circumferential weld based on the attribute items in the predicted attribute set. The specific values ​​of the corresponding attributes are then judged according to the attribute judgment rules corresponding to each attribute item, thereby obtaining attribute judgment information. For example, the attribute judgment information corresponding to the attribute items "Radiation Inspection Qualified" and "Construction Unit" in the predicted attribute set for the circumferential weld can be: "Radiation Inspection Qualified" = Yes; "Construction Unit" = Unit 1.

[0044] S103. Based on the attribute judgment information and the excavation criterion set, determine the quality risk prediction information of the corresponding circumferential weld.

[0045] In this embodiment, the attribute determination information of each circumferential weld on the target pipeline is precisely matched with the excavation criterion set. If the attribute determination information of the circumferential weld meets the attribute determination description of a certain criterion description item, then the quality risk prediction index corresponding to the attribute determination description is determined as the quality risk prediction information of the circumferential weld.

[0046] S104. Based on the quality risk prediction information, generate the circumferential weld excavation information for the target pipeline, and determine the target circumferential weld that meets the excavation requirements according to the circumferential weld excavation information.

[0047] In this context, circumferential weld excavation information can be understood as information used to indicate the excavation sequence and location of each circumferential weld on the target pipeline. The target circumferential weld can be considered as a circumferential weld that requires excavation, i.e., a circumferential weld to be excavated.

[0048] In this embodiment, the basic excavation sequence of each circumferential weld can be determined based on the quality risk prediction information of each circumferential weld. Furthermore, the final excavation sequence can be further determined based on the hierarchical information customized by the interactive object. Based on the excavation sequence, the circumferential weld number, location, and quality risk prediction information, circumferential weld excavation information is generated to facilitate on-site construction. Next, based on the circumferential weld excavation information and actual excavation requirements, such as the required excavation quantity, the target circumferential weld is further identified.

[0049] The pipeline circumferential weld quality inspection and excavation management method provided in this invention obtains basic data information of each circumferential weld on the target pipeline, and acquires a pre-determined prediction attribute set and excavation criterion set for circumferential weld quality prediction; based on the basic data information, it determines the attribute judgment information of each circumferential weld relative to the prediction attribute set; based on each attribute judgment information and the excavation criterion set, it determines the corresponding circumferential weld quality risk prediction information; based on each quality risk prediction information, it generates circumferential weld excavation information for the target pipeline, and determines the target circumferential welds that meet the excavation requirements according to the circumferential weld excavation information. Using this method, based on the basic data information of each circumferential weld on the target pipeline and the pre-determined prediction attribute set and excavation criterion set, it achieves rapid and accurate assessment of the quality risk of pipeline circumferential welds, accurately locates target circumferential welds with high quality risks, improves the accuracy of high-risk circumferential weld judgment and excavation efficiency, and reduces excavation costs.

[0050] As a first optional embodiment of the present invention, based on the above embodiments, the step of determining the attribute determination information of each circumferential weld relative to the predicted attribute set according to the basic data information can be specified as the following steps:

[0051] a1) For each circumferential weld on the target pipeline, determine the specific value of the attribute relative to each attribute item contained in the predicted attribute set based on the basic data information.

[0052] In this embodiment, field information or derived features corresponding to each attribute item can be extracted from basic data information of the circumferential weld, such as as-built data, X-ray films, internal inspection pipe section list, and internal leakage magnetic field detection signal data, as specific attribute values.

[0053] b1) Based on the attribute determination rules corresponding to each attribute item in the predicted attribute set, determine the specific value of the corresponding attribute to obtain the attribute determination result.

[0054] For example, an attribute determination rule can be considered as a determination rule that includes a mapping relationship, which can be a mapping relationship between the specific value of an attribute and the value of the attribute item within the value range.

[0055] In this embodiment, the specific value corresponding to the attribute item can be determined according to the attribute judgment rule, and this value is determined as the attribute judgment result. For example, the attribute item is the severity of the abnormality, and the value range is no abnormality / slight / moderately severe / severe. The attribute judgment result determined based on the specific value of the attribute and the attribute judgment rule can be moderately severe.

[0056] c1) Summarize each attribute item and the corresponding attribute determination results to form the attribute determination information of the circumferential weld.

[0057] In this embodiment, each attribute item has a corresponding and unique attribute determination result. The attribute items and their corresponding attribute determination results are summarized to form the attribute determination information of the circumferential weld.

[0058] The above-described technical solution in this embodiment determines the specific value of each attribute item based on basic data information for each circumferential weld on the target pipeline, and determines the attribute judgment result corresponding to the specific attribute value based on preset attribute judgment rules, thereby obtaining attribute judgment information. This realizes the transformation from basic data information to a usable judgment description for quality risk assessment, improves the efficiency and accuracy of obtaining the quality risk profile of the circumferential weld, and provides support for efficient and accurate final quality risk prediction in combination with excavation criteria.

[0059] As a second optional embodiment of the present invention, based on the above embodiments, the excavation criterion set includes multiple criterion description items, each criterion description item includes a quality risk prediction index and an attribute judgment description relative to the attribute items in the prediction attribute set;

[0060] Accordingly, the determination of the quality risk prediction information of the corresponding circumferential weld based on the attribute determination information and the excavation criterion set can be optimized as follows:

[0061] a2) For each circumferential weld on the target pipeline, match the attribute determination information with the attribute determination description of any criterion description item in the excavation criterion set.

[0062] In this embodiment, for each circumferential weld on the target pipeline, the attribute determination description of each criterion description item in the excavation criterion set is traversed based on its attribute determination information. For example, each attribute item and its corresponding attribute determination result in the attribute determination information can be compared with the attribute determination description of any criterion description item in the excavation criterion set to determine whether the attribute determination result meets the comparison conditions. Attribute determination results that meet the comparison conditions generally have a higher probability of exhibiting quality risks such as unqualified / cracked welds than attribute determination results that do not meet the comparison conditions.

[0063] For example, when the attribute judgment description corresponding to an attribute item has a unique value, the comparison condition can be that the attribute judgment result of the attribute item is consistent with the attribute judgment description of the attribute item, such as both being "whether to rework" = "yes". When the attribute judgment description corresponding to an attribute item has a non-unique value, the comparison condition can be that the attribute judgment result of the attribute item is consistent with any value in the attribute judgment description of the attribute item, such as the attribute judgment description of the attribute item being "ray inspection - whether qualified" = "no" / "unknown". Either "no" or "unknown" in the attribute judgment result of the attribute item can be considered to satisfy the comparison condition.

[0064] b2) If the attribute determination information matches the attribute determination description, then the quality risk prediction index contained in the criterion description item is determined as the quality risk prediction information of the circumferential weld.

[0065] In this embodiment, if the attribute judgment results of each attribute item corresponding to the attribute judgment description in the attribute judgment information are consistent with the attribute judgment description, that is, the attribute judgment results of all compared attribute items satisfy the attribute judgment description, it is considered that the attribute judgment information matches the attribute judgment description. Then, the quality risk prediction index contained in the criterion description item corresponding to the attribute judgment description is directly reused, and the quality risk prediction index is determined as the quality risk prediction information of the circumferential weld.

[0066] The above-described technical solution in this embodiment improves the efficiency and accuracy of determining the quality risk prediction information of the circumferential weld by matching the attribute determination information of each circumferential weld on the target pipeline with the attribute determination description, and determining the quality risk prediction index contained in the criterion description item as the quality risk prediction information of the circumferential weld when they match, thereby providing data support for quickly identifying high-risk circumferential welds.

[0067] As a third optional embodiment of the present invention, based on the above embodiments, the step of generating the circumferential weld excavation information of the target pipeline according to the quality risk prediction information can be specified as follows:

[0068] a3) Obtain the risk ratio prediction value in each of the quality risk prediction information, and obtain the excavation classification threshold associated with the excavation demand. The risk ratio prediction value includes the non-conforming ratio prediction value and / or the crack ratio prediction value.

[0069] The predicted risk ratio can be understood as the predicted proportion of quality risk. It should be noted that the quality risk prediction index includes a pre-determined average predicted risk ratio. After the quality risk prediction index is determined as the quality risk prediction information for the circumferential weld, the average predicted risk ratio can be used as the predicted risk ratio for the corresponding circumferential weld. For example, a predicted non-conforming rate of 80% in the predicted risk ratio indicates that the circumferential weld has an 80% probability of being non-conforming; a predicted crack rate of 30% in the predicted risk ratio indicates that the circumferential weld has a 30% probability of having cracks.

[0070] In this embodiment, excavation requirements may include maximizing the detection of non-conforming circumferential welds and maximizing the detection of cracked circumferential welds. The excavation grading threshold can be understood as a threshold used to determine different grades within the excavation grading system. For example, when the goal is to maximize the detection of non-conforming circumferential welds, the excavation grading threshold set for Grade 1 (the highest risk grade) can be 52%, meaning that circumferential welds with a predicted non-conforming percentage higher than 52% are in Grade 1. Optionally, the excavation grading threshold associated with the excavation requirements can be set by the interactive object or determined based on historical data or experience.

[0071] b3) Arrange each of the circumferential welds in descending order of the predicted risk ratio to obtain the circumferential weld excavation sequence.

[0072] Among them, the circumferential weld excavation sequence can be considered as a sequence used to characterize the excavation order of the circumferential weld.

[0073] For example, all circumferential welds of the target pipeline can be sorted from highest to lowest according to the predicted proportion of non-conformity or crack proportion, resulting in a circumferential weld excavation sequence guided by the predicted risk proportion. Circumferential welds with the same predicted risk proportion can be excavated in the same order within the circumferential weld excavation sequence.

[0074] c3) Determine the excavation level for each circumferential weld based on the excavation classification threshold and risk ratio threshold to form excavation classification information.

[0075] For example, when setting excavation classification thresholds for Level 1, if the goal is to maximize the detection of non-conforming circumferential welds, circumferential welds with a predicted non-conforming ratio higher than 52% are classified as Level 1. If the goal is to maximize the detection of cracked circumferential welds, circumferential welds with a predicted crack ratio higher than 12% are classified as Level 1. For the remaining circumferential welds, they can be classified from high to low according to the risk ratio thresholds set by the risk ratio prediction value and the relative risk ratio prediction value, and every two circumferential welds belonging to different excavation sequences constitute Level 1. Regarding specific pipeline data, the interactive object can adjust the recommended number of circumferential welds to be excavated (i.e., excavation quantity requirements), the excavation classification threshold, the risk ratio threshold, and how many criteria or circumferential welds constitute Level 1 after Level 1.

[0076] d3) The circumferential weld excavation sequence and the excavation classification information are determined as the circumferential weld excavation information of the target pipeline.

[0077] In this embodiment, the excavation sequence and excavation classification information of the circumferential weld can be determined as the circumferential weld excavation information of the target pipeline to clarify the excavation priority of each circumferential weld. At the same time, basic information such as the number and location of the circumferential weld can be marked to facilitate on-site construction.

[0078] As a fourth optional embodiment of the present invention, based on the above embodiments, the step of determining the target circumferential weld that meets the excavation requirements according to the circumferential weld excavation information can be specified as the following steps:

[0079] a4) Obtain the excavation quantity requirement and excavation cost consumption set under the excavation requirements;

[0080] b4) Select the circumferential weld that meets the excavation quantity requirements and excavation cost consumption from the circumferential weld excavation information, and determine it as the target circumferential weld.

[0081] For example, if the excavation quantity requirement is 1000, the first 1000 unexcavated circumferential welds can be selected as target circumferential welds from the circumferential weld excavation information, provided that the excavation cost is met.

[0082] In one experiment, for the same pipeline, the risk ratio values ​​corresponding to the 1000 target circumferential welds most deserving excavation, determined by this method, were compared with the risk ratio values ​​corresponding to the 2599 verification circumferential welds determined by existing methods in the verification data. Specifically, the proportion of excavation non-compliance (or excavation crack ratio) was estimated using the portion of these 1000 target circumferential welds already excavated in the verification data. That is, let 'a' be the number of welds already excavated in the verification data among the 1000 target circumferential welds, and 'b' be the number of non-compliance circumferential welds (or cracked circumferential welds) already excavated in the target circumferential welds. Then, the proportion of newly excavated non-compliance (or newly excavated crack ratio) can be calculated. The specific method can be... Assuming the calculated value represents the excavation failure rate (or excavation crack rate) of 1000 target circumferential welds, by comparing this value with the excavation failure rate (or excavation crack rate) of 2599 verification circumferential welds, we can roughly determine the change in the excavation failure rate (or excavation crack rate) using this method compared to the original algorithm using verification circumferential welds, given the same excavation cost for 1000 circumferential welds.

[0083] In the verification data obtained from an experiment, a total of 211,765 unqualified circumferential welds were recommended for excavation, and the unqualified excavation rate of 2,599 verification circumferential welds was 25.74%. Of the 1,000 target circumferential welds identified by this method, 238 have already been excavated in the verification data, i.e., a=238. Based on the number of unqualified circumferential welds included in these 238 target circumferential welds, the preliminary verification of the unqualified excavation rate of the 1,000 target circumferential welds is determined to be 36.13% (36.13% determined by the specific calculation method described above), which is an absolute percentage increase of 10.39% (a relative increase of 40%) compared to the unqualified excavation rate of 25.74% for verification circumferential welds. This also means that within the scope of circumferential weld excavation information, for every 100 unqualified circumferential welds excavated, this method requires excavating approximately 277 circumferential welds, while the original algorithm required excavating approximately 389 circumferential welds. This demonstrates that, to achieve the same benefits, this method requires lower excavation costs.

[0084] For excavated cracked circumferential welds, verification data from another experiment recommended a total of 211,765 cracked circumferential welds for excavation, with 2,599 verification circumferential welds showing an excavation crack ratio of 2.92%. Of the 1,000 target circumferential welds identified by this method, 386 have already been excavated in the verification data (a=386). Based on the number of cracked circumferential welds contained in these 386 target circumferential welds, the preliminary verification of the excavation crack ratio for the 1,000 target circumferential welds is 6.48%, an absolute percentage increase of 3.56% and a relative increase of 122% compared to the 2.92% excavation crack ratio for the verification circumferential welds. Specifically, prioritizing the excavation of cracked welds within the excavation cost of 1,000 circumferential welds can increase the number of obtained cracked circumferential welds by approximately 36. Within the scope of circumferential weld excavation information, for every 10 cracked circumferential welds excavated, this technical solution can reduce the number of excavated circumferential welds by approximately 188.

[0085] In summary, with the same excavation cost, this technical solution can locate more circumferential welds with defects or cracks compared to the control method, thereby improving the effectiveness of excavation management and repair efficiency of pipeline circumferential welds.

[0086] Optionally, based on the above embodiments, the following optimizations can be made: updating the quality risk prediction information of the unexcavated circumferential welds according to the excavation results of the excavated circumferential welds on the target pipeline, and generating circumferential weld excavation information relative to the unexcavated circumferential welds based on the updated quality risk prediction information.

[0087] As a fifth optional embodiment of the present invention, based on the above embodiments, it further includes:

[0088] a5) Based on the historical data of each circumferential weld on the pilot pipeline, determine one or more attribute items, obtain the attribute determination rules for each attribute item, and form the predicted attribute set.

[0089] It should be noted that in order to efficiently and accurately predict the quality risks of the target pipeline, it is necessary to predetermine a standardized set of prediction attributes that can be used for predicting the quality risks of circumferential welds.

[0090] In this embodiment, a set of predictive attributes can be determined based on a selected pilot pipeline. The pilot pipeline shares the same characteristics as the target pipeline, namely, it is also a long-distance oil and gas pipeline composed of circumferential welds between steel pipes, and it faces the same quality risk issues. The pilot pipeline has multiple excavated circumferential welds. Historical data may include as-built documentation, X-ray films, lists of internally inspected pipe sections, and magnetic flux leakage internal detection signal data related to each excavated circumferential weld on the pilot pipeline.

[0091] As one implementation method, the process of determining one or more attribute items based on historical data information of each circumferential weld on the pilot pipeline, obtaining attribute determination rules for each attribute item, and forming the predicted attribute set can be further optimized into the following steps:

[0092] a51) Based on expert knowledge, determine one or more baseline attribute items, and based on the historical data information combined with the information gain algorithm, determine the target attribute item.

[0093] The baseline attribute can be understood as the attribute that can be used to construct the criterion description based on expert knowledge information; the target attribute can be considered as the attribute that can be used to construct the criterion description based on the analysis of other attribute items besides the baseline attribute using the information gain algorithm, in order to supplement the baseline attribute.

[0094] Optionally, determining the target attribute item based on the historical data information combined with the information gain algorithm includes:

[0095] Obtain one or more pre-defined candidate attribute items, and obtain a first attribute value range constructed relative to the baseline attribute item and a second attribute value range constructed relative to the candidate attribute item;

[0096] Based on the historical data, the range of values ​​for the first attribute, and the range of values ​​for the second attribute, determine the first gain value of the baseline attribute item and the second gain value of the candidate attribute item;

[0097] The candidate attribute item corresponding to the second gain value that matches the first gain value is determined as the target attribute item.

[0098] Candidate attribute items can be understood as attribute items other than the baseline attribute items that may affect the prediction of circumferential weld quality risks, and can be determined based on historical experience or historical data. For example, candidate attribute items may include the construction unit, welding date, etc.

[0099] In this embodiment, the baseline attribute item and the corresponding first attribute value range can first be determined based on expert knowledge. For example, the baseline attribute item and the corresponding first attribute value range may include: 1. Whether the weld joint is questionable on the film (Yes / No); 2. Whether it is suspected of being a black weld (Yes / No); 3. Severity of abnormality (No abnormality / Slight / Severe / Severe); 4. Whether it is a dead joint (Yes / No); 5. Whether it is a connecting joint (Yes / No); 6. Whether it is a repair joint (Yes / No); 7. Whether it is a joint with varying wall thickness (Yes / No); 8. Whether it is a bend or elbow (Yes / No); 9. Whether it is a gold joint (Yes / No); 10. Type of downstream pipe section for internal inspection (straight pipe / elbow / cold-bent pipe); 11. Whether the radiographic inspection is qualified (Yes / No / Unknown).

[0100] Next, the candidate attribute items are analyzed using the information gain algorithm. Specifically, this can be done by first determining the corresponding gain values ​​for the baseline attribute item and the candidate attribute items. For example, the specific method for determining the gain value of an attribute item can be expressed as follows:

[0101] ;

[0102] ;

[0103] in, This indicates all excavated circumferential welds on the pilot pipeline. The first one that satisfies the attribute item A ring weld with a value of [number]; Indicates the number of possible values ​​for an attribute item; To indicate that the circumferential weld seam has been excavated The proportion of unqualified circumferential welds in the system.

[0104] Then, the second gain value can be compared with the first gain value to determine the target attribute item. For example, if the second gain value is greater than the first gain value, or if the difference between the first and second gain values ​​is less than a preset threshold when the second gain value is less than the first gain value, then the second gain value is determined to match the first gain value. In this case, the candidate attribute item corresponding to the second gain value can be determined as the target attribute item. For example, if among the first gain values ​​of each benchmark attribute item, the first gain value for "whether the film has a questionable weld joint" is the highest, at 0.010, and the second gain value for the construction unit among the candidate attribute items is 0.030, then the construction unit can be determined as the target attribute item.

[0105] The above-described technical solution in this embodiment combines expert knowledge information to determine the core benchmark attribute items, and determines the target gain value that is close to the gain value from the candidate attribute items based on the gain value of the benchmark attribute items. This supplements the benchmark attribute items and improves the richness, effectiveness and reliability of the attribute items in the prediction attribute set.

[0106] a52) The baseline attribute item and the target attribute item are determined as attribute items, and the first attribute value range relative to the baseline attribute item and the second attribute value range relative to the target attribute item are determined as attribute value ranges.

[0107] a53) Based on the attribute value range and the historical data information, determine the risk ratio value of the corresponding attribute item, and obtain the attribute judgment rule configured according to each risk ratio value relative to the attribute item.

[0108] In this embodiment, the risk ratio value may include the circumferential weld defect rate value. For example, for each attribute item, the circumferential weld defect rate filtered from all possible values ​​of the attribute item can be determined based on historical data. Then, the attribute judgment rule configured relative to the attribute item can be determined based on the attribute value range, the filtered circumferential weld defect rate, and the average defect rate of excavated circumferential welds on the current pilot pipeline.

[0109] Optionally, the attribute determination rules can define the values ​​marked as "satisfied" for attribute items. For example, if the proportion of unqualified circumferential welds selected from historical data for a certain attribute item is higher than the average proportion of unqualified circumferential welds already excavated on the current pilot pipeline, that value is marked as "satisfied," and can be annotated with an underline, i.e., an underlined value indicates "satisfied," and a non-underlined value is marked as "unsatisfied." Values ​​marked as "satisfied" generally have a higher probability of unqualified / cracked circumferential welds than values ​​marked as "unsatisfied." For example, the attribute item "whether it is a rework port" has a value range including yes and no. A value of "yes" corresponds to a circumferential weld unqualified proportion of 30%, and a value of "no" corresponds to a circumferential weld unqualified proportion of 5%. The average proportion of unqualified circumferential welds already excavated on the current pilot pipeline is 12%. Therefore, a value of "yes" can be marked as "satisfied," and a value of "no" can be marked as "unsatisfied."

[0110] a54) Summarize the attribute items and the corresponding attribute determination rules to form the predicted attribute set.

[0111] b5) Based on the predicted attribute set and the historical data information, determine multiple criterion description items to form the excavation criterion set.

[0112] As one implementation method, the step of determining multiple criterion description items based on the predicted attribute set and the historical data information to form the excavation criterion set can be further specified as the following steps:

[0113] b51) Based on the historical data information, determine the circumferential weld dataset, and form at least one first data subset by grouping the circumferential weld dataset.

[0114] In this embodiment, based on historical data including pilot pipeline information, the location of the circumferential weld on the pilot pipeline, and related attribute information, information is organized around the circumferential weld to form a circumferential weld dataset. Next, the circumferential weld dataset can be grouped by sampling to obtain a first subset of data after grouping. For example, random sampling with replacement can be used for grouping. First, the circumferential weld dataset is divided into... The total number of weld joints is (units). Therefore, the probability of each weld being sampled is... Random sampling based on this probability This process can generate a dataset of the same size as the circumferential weld dataset in one go, and the process can be repeated. It can be formed in one time. This is the first subset of data. It's important to note that we still retain the circumferential weld dataset in this subset. Therefore, the actual data generated by sampling is only a fraction of the total data. share.

[0115] By using statistical random sampling with replacement to group the circumferential weld dataset, the predictive generalization performance of subsequent criterion descriptions can be improved. Furthermore, since the risk proportion value can be used as the analysis object, its... The mean and standard deviation of the first data subset are used to determine the predicted fluctuation range of the criterion description term, thereby providing a measure of the reliability of the prediction results and providing a confidence reference for subsequent excavation decisions.

[0116] b52) Determine the initial excavation criterion set based on the first data subset and the predicted attribute set.

[0117] Optionally, determining the initial excavation criterion set based on the first data subset and the predicted attribute set includes:

[0118] For each first data subset, a pre-constructed initial criterion set is obtained. After determining that each attribute item in the predicted attribute set is added to the initial criterion set, the first target rate of risk-type circumferential welds is screened out through the initial criterion set.

[0119] Obtain a first filtering condition relative to the first target rate, determine a first type of attribute item from the attribute items according to the first filtering condition, and form a criterion description item based on the attribute judgment rule of the first type of attribute item and add it to the initial criterion set;

[0120] Return to the previous step and re-execute the operation of determining that each attribute item in the predicted attribute set is added to the initial criterion set, and then use the initial criterion set to filter out the first target rate of risk-type circumferential welds until the loop termination condition is met, and obtain the initial criterion set after the loop ends;

[0121] From the initial criterion sets corresponding to each of the first data subsets, determine the initial excavation criterion sets that satisfy the selected conditions.

[0122] The initial excavation criterion set can be understood as a preliminary set of criteria used to detect high-risk circumferential welds, consisting of one or more attribute constraints. The initial criterion set can be considered a pre-constructed set of initialization criteria, which is usually empty.

[0123] In this embodiment, as one implementation method, the attribute items in the prediction attribute set can be traversed sequentially, and attribute items can be selected one by one to be added to the initial criterion set. If adding an attribute item can further and significantly increase the first target rate (such as the non-conforming ratio or crack ratio) of the risk-type circumferential welds selected by the initial criterion set compared to other attribute items, then the attribute item is determined to be a first-type attribute item, and a criterion description item is formed based on the attribute judgment rules of the first-type attribute item, such as forming a criterion description item based on the value marked as "satisfied" in the first-type attribute item, and then the criterion description item is added to the initial criterion set. Next, it is determined whether the current loop termination condition is met. If not, the search continues for other attribute items in the prediction attribute set that can be added to the initial criterion set until the loop termination condition is met. For example, the loop termination condition can be that adding any attribute item cannot further increase the first target rate of the selected risk-type circumferential welds.

[0124] Since attribute items are searched on multiple first data subsets, an initial criterion set with the same number of subsets as the first data subsets can be obtained. To determine which initial criterion set has the highest stable mean, the first target rate of risk circumferential welds selected from each first data subset by the initial criterion set obtained after satisfying the loop termination condition can be determined, and the initial criterion set with the highest mean of the first target rate is taken as the preliminary excavation criterion set.

[0125] b53) The circumferential weld dataset is segmented according to the initial excavation criterion set to obtain a first number of second data subsets, wherein the data of each second data subset do not overlap.

[0126] Optionally, the step of segmenting the circumferential weld dataset according to the initial excavation criterion set to obtain a first number of second data subsets includes:

[0127] Obtain the first type of attribute item associated with each criterion description item included in the initial excavation criterion set;

[0128] Obtain the segmentation and filtering conditions set according to the attribute determination rules of the first type of attribute item;

[0129] Based on the segmentation and screening conditions and the combinatorial formula, the circumferential weld dataset is segmented into a first number of non-overlapping second data subsets, wherein the first number is the same as the number of combinations corresponding to the combinatorial formula.

[0130] In this embodiment, to generate more criterion description items that can help improve the target rate and apply to more circumferential welds, the segmentation can be performed in this step based on the number of attribute items. As one implementation method, the first type of attribute items associated with each criterion description item can be determined from the initial excavation criterion set, and the number of first type attribute items can be counted. For example, the number of first type attribute items is... The segmentation and filtering criteria can be selected from the first type of attribute items. One first-class attribute item, The value range is 0 to ,Require There is one and only this in the first type of attribute item. The values ​​of the first type of attribute item are denoted as "satisfied". This allows the circumferential weld dataset to be segmented into... (First quantity) non-overlapping second subsets of data.

[0131] b54) Based on each of the second data subsets and each of the first data subsets, the excavation criterion set is formed.

[0132] Optionally, forming the excavation criterion set based on each of the second data subsets and each of the first data subsets includes:

[0133] (b541) For each second data subset, perform full criterion mining on the second data subset according to the first search strategy and the second search strategy respectively to obtain a full criterion library.

[0134] Optionally, the step of performing full criterion mining on the second data subset according to the first search strategy and the second search strategy respectively to obtain a full criterion library includes:

[0135] For each second data subset, the same search logic as that used to determine the initial excavation criterion set is executed according to the first search strategy to obtain the first excavation criterion set for the second data subset, and the first attribute item in the first excavation criterion set is used to form the criterion set to be expanded according to the second search strategy.

[0136] After determining that each attribute item in the predicted attribute set is added to the criteria set to be expanded, the second target rate of non-risk circumferential welds is selected through the criteria set to be expanded.

[0137] Obtain a second filtering condition relative to the second target rate, determine a second type of attribute item from the attribute items according to the second filtering condition, and form a criterion description item based on the attribute judgment rule of the second type of attribute item and add it to the criterion set to be expanded;

[0138] After returning to the previous operation, the operation of adding each attribute item in the predicted attribute set to the criteria set to be expanded is performed again. Then, the operation of filtering out the second target rate of non-risk circumferential welds through the criteria set to be expanded is performed until the loop termination condition is met. The criteria set to be expanded after the loop ends is determined as the second excavation dataset.

[0139] A complete set of criteria is formed based on each of the first excavation criterion sets and each of the second excavation datasets.

[0140] The first search strategy uses the same search logic as the one used to determine the initial excavation criterion set. It filters out combinations of attribute constraints to form high-risk criterion descriptions (corresponding to high non-conformity rates or high crack rates), maximizing the increase of the second target rate corresponding to the second data subset. This results in a first excavation criterion set capable of locating high-risk circumferential welds. All attribute values ​​in the first excavation criterion set must be satisfied. The second search strategy, on the other hand, filters out combinations of attribute constraints to form low-risk criterion descriptions (corresponding to low non-conformity rates or low crack rates), maximizing the decrease of the second target rate corresponding to the second data subset. This results in a second excavation dataset capable of locating low-risk circumferential welds. All attribute values ​​in the second excavation criterion set must be unsatisfied.

[0141] In this embodiment, a first search strategy and a second search strategy are executed on each second data subset to obtain a criterion description for locating a relatively dangerous circumferential weld and a criterion description for locating a relatively safe circumferential weld on each second data subset.

[0142] As an implementation method, the second search strategy can be specifically described as follows: A criterion set to be expanded is constructed using the first attribute item in the first excavation criterion set. This criterion set can be understood as an initialized criterion set, where all attribute items are required to be non-compliant. Attribute items are selected one by one from the predicted attribute set and added to the criterion set to be expanded. The second target rate (non-conforming ratio or crack ratio) for non-risk circumferential welds selected through the criterion set to be expanded is determined. If adding this attribute item can further reduce the non-risk circumferential welds selected through the criterion set to be expanded to the maximum extent compared to adding other attribute items, then... If there is a second target rate, then the attribute item is determined to meet the second screening condition, and the attribute item is identified as the second type of attribute item. Based on the attribute judgment rule of the second type of attribute item, a criterion description item is formed and added to the criterion set to be expanded. It is then determined whether the loop termination condition is met. If not, the search continues to search for other attribute items in the prediction attribute set that can be added to the criterion set to be expanded until the loop termination condition is met. If adding any attribute item cannot further reduce the second target rate of the screened non-risk circumferential welds, the search stops, and the criterion set to be expanded after the loop ends is identified as the second excavation dataset.

[0143] In one experiment, for a second subset of data satisfying the criteria of [whether the weld is questionable on film = Yes, downstream pipe section type detected internally = non-straight pipe, whether the X-ray inspection is qualified = Yes, whether it is a repair joint = No, whether it is a joint = No, whether it is a variable wall thickness joint = No], the process of executing the first search strategy and the second search strategy can be as follows: Executing the first search strategy increases the target proportion of risk-type circumferential welds found by continuously adding attribute constraints. During the first traversal, it is determined that the criterion description item "whether it is a dead joint = Yes" is added to the initial criterion set. In this case, the first target rate increases from the initial 45.66% to 64.83%, and the predicted fluctuation range increases from the initial... Become The total number of risk-class circumferential welds decreased from the initial 450 to 6; during the second traversal, it was determined that the criterion description "whether it is an elbow or pipe bend = yes" would be added to the initial criterion set. Under this condition, the first target rate increased from 64.83% to 100%, and the predicted fluctuation range increased from... Become The total number of risk-class circumferential welds is reduced from 6 to 2. If the cycle termination condition is met at this time, the criterion description items in the first excavation criterion set include "whether it is a dead joint = yes" and "whether it is a bend or pipe = yes".

[0144] The second search strategy reduces the second target rate of non-risk circumferential welds by continuously adding attribute constraints. The first attribute item in the first excavation criterion set, "whether it's a dead joint = yes," forms the criterion set to be expanded. Under this condition, the second target rate decreases from the initial 45.66% to 45.44%, and the predicted fluctuation range increases from the initial... Become The total number of non-risk circumferential welds decreased from the initial 450 to 444. Next, a search was conducted along a different search path than the first search strategy, determining that the criterion description "downstream pipe section type detected internally = non-straight pipe" should be added to the criterion set to be expanded. In this case, the second target rate decreased from 45.44% to 29.23%, and the predicted fluctuation range increased from... Become The total number of non-risk circumferential welds is reduced from 444 to 35. If the cycle termination condition is met at this time, the criterion description items in the second excavation criterion set include "whether it is a dead joint = yes" and "internal detection of downstream pipe section type = non-straight pipe".

[0145] The above-described technical solution in this embodiment performs bidirectional search through a first search strategy and a second search strategy, and forms a complete set of criteria by integrating a first excavation criterion set and a second excavation dataset. This enables the accurate location of both high-risk and relatively safe circumferential weld seams, thereby improving the accuracy and efficiency of predicting the quality risk of circumferential weld seams.

[0146] (b542) For each criterion description item in the full criterion library, determine the quality risk prediction index corresponding to the criterion description item based on each of the first data subsets.

[0147] Optionally, determining the quality risk prediction index corresponding to each of the first data subsets includes:

[0148] Determine the risk ratio value corresponding to the criterion description item in each of the first data subsets, and determine the predicted mean and standard deviation of the risk ratio corresponding to the criterion description item based on each of the risk ratio values;

[0149] Based on the predicted mean and standard deviation of the risk ratio, and combined with the predicted volatility formula, the predicted volatility range of the criterion description item is determined.

[0150] The predicted mean, standard deviation, and predicted fluctuation range of the risk ratio are determined as the quality risk prediction indicators of the criterion description item.

[0151] In this embodiment, for each criterion description item, the risk ratio value (such as non-conforming ratio, crack ratio) of the criterion description item in each first data subset can be determined. Then, the mean and standard deviation of the risk ratio value are determined as the predicted mean and standard deviation of the risk ratio corresponding to the criterion description item. The predicted mean of the risk ratio may include the predicted mean of the non-conforming ratio and / or the predicted mean of the crack ratio.

[0152] As one implementation method, the way to determine the risk proportion prediction mean and standard deviation corresponding to the criterion description item can be: the first subset of data has Each item is determined to be a criterion description item. The risk proportion value of the selected circumferential weld in the first data subset. For example... The risk proportions of a single criterion description item in the four datasets are 44.5%, 56.7%, 26.7%, and 38.5%, respectively. The mean risk proportion prediction is:

[0153] ;

[0154] The standard deviation is:

[0155] .

[0156] Based on this, the predicted fluctuation range of the criterion description term can be 41.6% ± 10.82%. The basis for taking one standard deviation is the sigma principle, that is, if the data satisfies a normal distribution, then the data distribution is within a certain range. The probability within the range is 65.26%. Optionally, the use of the 2sigma or even 3sigma principle can be adjusted based on actual verification results to determine the predicted fluctuation range of the criterion description term. The 2sigma principle states that if the data follows a normal distribution, then the data distribution is within the range of 65.26%. The probability of it being within a certain range is 95.44%. The 3 Sigma principle states that if the data follows a normal distribution, then the data is distributed within a certain range. The probability within is 99.74%.

[0157] (b543) Update the quality risk prediction index to the criterion description item, and integrate each of the criterion description items to form the excavation criterion set.

[0158] In this embodiment, the quality risk prediction index is updated to the criterion description item and bound to the attribute judgment description in the criterion description item to form the final criterion description item. The criterion description items are then integrated to form an excavation criterion set that can be used to predict the quality risk of the target pipeline.

[0159] The above-described technical solution in this embodiment determines the predicted mean, standard deviation, and predicted fluctuation range of the risk ratio corresponding to the criterion description item, and updates the criterion description item with the predicted mean, standard deviation, and predicted fluctuation range as the quality risk prediction index. This realizes the implementation from attribute definition to quantitative risk judgment, forming an excavation criterion set that includes both attribute judgment description and quality risk prediction index, with the criterion description item as the unit. This provides support for efficient and accurate quality risk prediction or assessment of target pipelines in the application stage, thereby improving the ability to conduct quality spot checks and excavation management of pipeline circumferential welds.

[0160] Figure 2 is a schematic diagram of a pipeline circumferential weld quality inspection excavation management device provided in an embodiment of the present invention. As shown in Figure 2, the device includes: an acquisition module 21, a first information determination module 22, a second information determination module 23, and a target circumferential weld determination module 24.

[0161] Among them, the acquisition module 21 is used to acquire the basic data information of each circumferential weld on the target pipeline, and to acquire the pre-determined prediction attribute set and excavation criterion set for predicting the quality of the circumferential weld.

[0162] The first information determination module 22 is used to determine the attribute determination information of each of the circumferential welds relative to the predicted attribute set based on the basic data information.

[0163] The second information determination module 23 is used to determine the quality risk prediction information of the corresponding circumferential weld based on the attribute determination information and the excavation criterion set.

[0164] The target circumferential weld determination module 24 is used to generate circumferential weld excavation information for the target pipeline based on the quality risk prediction information, and to determine the target circumferential weld that meets the excavation requirements according to the circumferential weld excavation information.

[0165] The pipeline circumferential weld quality inspection and excavation management device provided in this invention acquires basic data information of each circumferential weld on the target pipeline, and obtains a pre-determined prediction attribute set and excavation criterion set for circumferential weld quality prediction; based on the basic data information, it determines the attribute judgment information of each circumferential weld relative to the prediction attribute set; based on each attribute judgment information and the excavation criterion set, it determines the corresponding circumferential weld quality risk prediction information; based on each quality risk prediction information, it generates circumferential weld excavation information for the target pipeline, and determines the target circumferential welds that meet the excavation requirements according to the circumferential weld excavation information. Using this device, based on the basic data information of each circumferential weld on the target pipeline and the pre-determined prediction attribute set and excavation criterion set, it achieves rapid and accurate assessment of the quality risk of pipeline circumferential welds, accurately locates target circumferential welds with high quality risks, improves the accuracy of high-risk circumferential weld judgment and excavation efficiency, and reduces excavation costs.

[0166] Furthermore, the first information determination module 22 can specifically be used for:

[0167] For each circumferential weld on the target pipeline, the specific value of the attribute is determined relative to each attribute item contained in the predicted attribute set based on the basic data information.

[0168] According to the attribute determination rules corresponding to each attribute item in the predicted attribute set, the specific value of the corresponding attribute is determined to obtain the attribute determination result.

[0169] The attribute items and corresponding attribute determination results are summarized to form the attribute determination information of the circumferential weld.

[0170] Furthermore, the excavation criterion set includes multiple criterion description items, each of which contains a quality risk prediction index and an attribute judgment description relative to the attribute items in the prediction attribute set.

[0171] The second information determination module 23 can be specifically used for:

[0172] For each circumferential weld on the target pipeline, the attribute determination information is matched with the attribute determination description of any criterion description item in the excavation criterion set;

[0173] If the attribute determination information matches the attribute determination description, then the quality risk prediction index contained in the criterion description item is determined as the quality risk prediction information of the circumferential weld.

[0174] Furthermore, the target circumferential weld determination module 24 can specifically be used for:

[0175] Obtain the risk ratio prediction value from each of the quality risk prediction information, and obtain the excavation grading threshold associated with the excavation demand. The risk ratio prediction value includes the non-conforming ratio prediction value and / or the crack ratio prediction value.

[0176] Arrange the circumferential welds in descending order of the predicted risk ratio to obtain the circumferential weld excavation sequence;

[0177] The excavation level is determined for each circumferential weld based on the excavation classification threshold and risk ratio threshold, thus forming excavation classification information;

[0178] The circumferential weld excavation sequence and the excavation classification information are determined as the circumferential weld excavation information of the target pipeline.

[0179] Furthermore, the target circumferential weld determination module 24 can also be used specifically for:

[0180] Obtain the required excavation quantity and excavation cost under the stated excavation requirements;

[0181] Select the circumferential welds that meet the excavation quantity requirements and excavation cost from the circumferential weld excavation information, and determine them as the target circumferential welds.

[0182] Furthermore, the device also includes:

[0183] The predictive attribute set determination module is used to determine one or more attribute items based on historical data information of each circumferential weld on the pilot pipeline, and to obtain the attribute determination rules for each attribute item to form the predictive attribute set.

[0184] The excavation criterion set determination module is used to determine multiple criterion description items based on the predicted attribute set and the historical data information to form the excavation criterion set.

[0185] Furthermore, the prediction attribute set determination module may specifically include:

[0186] The first determining unit is used to determine one or more benchmark attribute items based on expert knowledge information, and to determine the target attribute item based on the historical data information combined with the information gain algorithm.

[0187] The second determining unit is used to determine the benchmark attribute item and the target attribute item as attribute items, and to determine the first attribute value range relative to the benchmark attribute item and the second attribute value range relative to the target attribute item as attribute value ranges.

[0188] The third determining unit is used to determine the risk ratio value of the corresponding attribute item based on the attribute value range and the historical data information, and to obtain the attribute judgment rule configured according to each risk ratio value relative to the attribute item.

[0189] The predictive attribute set determination unit is used to summarize the attribute items and the corresponding attribute determination rules to form the predictive attribute set.

[0190] Furthermore, the first determining unit can specifically be used for:

[0191] Obtain one or more pre-defined candidate attribute items, and obtain a first attribute value range constructed relative to the baseline attribute item and a second attribute value range constructed relative to the candidate attribute item;

[0192] Based on the historical data, the range of values ​​for the first attribute, and the range of values ​​for the second attribute, determine the first gain value of the baseline attribute item and the second gain value of the candidate attribute item;

[0193] The candidate attribute item corresponding to the second gain value that matches the first gain value is determined as the target attribute item.

[0194] Furthermore, the excavation criterion set determination module may specifically include:

[0195] A grouping processing unit is used to determine the circumferential weld seam dataset based on the historical data information, and to form at least one first data subset by grouping the circumferential weld seam dataset;

[0196] The initial excavation criterion set determination unit is used to determine the initial excavation criterion set based on the first data subset and the predicted attribute set;

[0197] The segmentation unit is used to segment the circumferential weld dataset according to the initial excavation criterion set to obtain a first number of second data subsets, wherein the data of each second data subset does not overlap.

[0198] The excavation criterion set determination unit is used to form the excavation criterion set based on each of the second data subsets and each of the first data subsets.

[0199] Furthermore, the initial excavation criterion set determination unit can specifically be used for:

[0200] For each first data subset, a pre-constructed initial criterion set is obtained. After determining that each attribute item in the predicted attribute set is added to the initial criterion set, the first target rate of risk-type circumferential welds is screened out through the initial criterion set.

[0201] Obtain a first filtering condition relative to the first target rate, determine a first type of attribute item from the attribute items according to the first filtering condition, and form a criterion description item based on the attribute judgment rule of the first type of attribute item and add it to the initial criterion set;

[0202] Return to the previous step and re-execute the operation of determining that each attribute item in the predicted attribute set is added to the initial criterion set, and then use the initial criterion set to filter out the first target rate of risk-type circumferential welds until the loop termination condition is met, and obtain the initial criterion set after the loop ends;

[0203] From the initial criterion sets corresponding to each of the first data subsets, determine the initial excavation criterion sets that satisfy the selected conditions.

[0204] Furthermore, the segmentation unit can specifically be used for:

[0205] Obtain the first type of attribute item associated with each criterion description item included in the initial excavation criterion set;

[0206] Obtain the segmentation and filtering conditions set according to the attribute determination rules of the first type of attribute item;

[0207] Based on the segmentation and screening conditions and the combinatorial formula, the circumferential weld dataset is segmented into a first number of non-overlapping second data subsets, wherein the first number is the same as the number of combinations corresponding to the combinatorial formula.

[0208] Furthermore, the excavation criterion set determination unit may specifically include:

[0209] The full criterion database determination subunit is used to perform full criterion mining on each second data subset according to the first search strategy and the second search strategy respectively to obtain the full criterion database.

[0210] The indicator determination subunit is used to determine the quality risk prediction indicator corresponding to each criterion description item in the full criterion library based on each of the first data subsets.

[0211] An integration subunit is used to update the quality risk prediction index to the criterion description item and integrate each of the criterion description items to form the excavation criterion set.

[0212] Furthermore, the full criterion library determination subunit can specifically be used for:

[0213] For each second data subset, the same search logic as that used to determine the initial excavation criterion set is executed according to the first search strategy to obtain the first excavation criterion set for the second data subset, and the first attribute item in the first excavation criterion set is used to form the criterion set to be expanded according to the second search strategy.

[0214] After determining that each attribute item in the predicted attribute set is added to the criteria set to be expanded, the second target rate of non-risk circumferential welds is selected through the criteria set to be expanded.

[0215] Obtain a second filtering condition relative to the second target rate, determine a second type of attribute item from the attribute items according to the second filtering condition, and form a criterion description item based on the attribute judgment rule of the second type of attribute item and add it to the criterion set to be expanded;

[0216] After returning to the previous operation, the operation of adding each attribute item in the predicted attribute set to the criteria set to be expanded is performed again. Then, the operation of filtering out the second target rate of non-risk circumferential welds through the criteria set to be expanded is performed until the loop termination condition is met. The criteria set to be expanded after the loop ends is determined as the second excavation dataset.

[0217] A complete set of criteria is formed based on each of the first excavation criterion sets and each of the second excavation datasets.

[0218] Furthermore, the indicator determination subunit can be specifically used for:

[0219] Determine the risk ratio value corresponding to the criterion description item in each of the first data subsets, and determine the predicted mean and standard deviation of the risk ratio corresponding to the criterion description item based on each of the risk ratio values;

[0220] Based on the predicted mean and standard deviation of the risk ratio, and combined with the predicted volatility formula, the predicted volatility range of the criterion description item is determined.

[0221] The predicted mean, standard deviation, and predicted fluctuation range of the risk ratio are determined as the quality risk prediction indicators of the criterion description item.

[0222] The pipeline circumferential weld quality inspection and excavation management device provided in this embodiment of the invention can execute the pipeline circumferential weld quality inspection and excavation management method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0223] Figure 3 illustrates a schematic diagram of an electronic device 30 that can be used to implement embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0224] As shown in Figure 3, the electronic device 30 includes at least one processor 31 and a memory, such as a read-only memory (ROM) 32 and a random access memory (RAM) 33, communicatively connected to the at least one processor 31. The memory stores computer programs executable by the at least one processor. The processor 31 can perform various appropriate actions and processes based on the computer program stored in the ROM 32 or loaded from storage unit 38 into the RAM 33. The RAM 33 can also store various programs and data required for the operation of the electronic device 30. The processor 31, ROM 32, and RAM 33 are interconnected via a bus 34. An input / output (I / O) interface 35 is also connected to the bus 34.

[0225] Multiple components in electronic device 30 are connected to I / O interface 35, including: input unit 36, such as keyboard, mouse, etc.; output unit 37, such as various types of monitors, speakers, etc.; storage unit 38, such as disk, optical disk, etc.; and communication unit 39, such as network card, modem, wireless transceiver, etc. Communication unit 39 allows electronic device 30 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0226] Processor 31 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 31 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 31 performs the various methods and processes described above, such as the quality inspection excavation management method for pipe circumferential welds.

[0227] In some embodiments, the method for quality inspection and excavation management of pipe circumferential welds can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 38. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 30 via ROM 32 and / or communication unit 39. When the computer program is loaded into RAM 33 and executed by processor 31, one or more steps of the method for quality inspection and excavation management of pipe circumferential welds described above can be performed. Alternatively, in other embodiments, processor 31 can be configured to perform the method for quality inspection and excavation management of pipe circumferential welds by any other suitable means (e.g., by means of firmware).

[0228] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0229] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0230] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0231] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0232] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0233] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0234] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0235] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for quality inspection and excavation management of pipeline circumferential welds, characterized in that, include: The process involves acquiring basic data information for each circumferential weld on the target pipeline, as well as a pre-determined set of prediction attributes and excavation criteria for predicting the quality of the circumferential welds. Based on the basic data information, the process determines the attribute judgment information of each circumferential weld relative to the prediction attribute set. Based on the attribute judgment information and the excavation criteria set, the process determines the quality risk prediction information of the corresponding circumferential weld. Based on the quality risk prediction information, the process generates circumferential weld excavation information for the target pipeline, and determines the target circumferential welds that meet the excavation requirements according to the circumferential weld excavation information.

2. The method according to claim 1, characterized in that, The step of determining the attribute determination information of each circumferential weld relative to the predicted attribute set based on the basic data information includes: for each circumferential weld on the target pipeline, determining the specific value of the attribute relative to each attribute item included in the predicted attribute set based on the basic data information; determining the specific value of the corresponding attribute according to the attribute determination rules corresponding to each attribute item in the predicted attribute set to obtain the attribute determination result; and summarizing each attribute item and the corresponding attribute determination result to constitute the attribute determination information of the circumferential weld.

3. The method according to claim 1, characterized in that, The excavation criterion set includes multiple criterion description items, each of which contains a quality risk prediction index and an attribute judgment description relative to the attribute items in the prediction attribute set. Determining the quality risk prediction information of the corresponding circumferential weld based on each attribute judgment information and the excavation criterion set includes: for each circumferential weld on the target pipeline, matching the attribute judgment information with the attribute judgment description of any criterion description item in the excavation criterion set; if the attribute judgment information matches the attribute judgment description, then the quality risk prediction index contained in the criterion description item is determined as the quality risk prediction information of the circumferential weld.

4. The method according to claim 1, characterized in that, The step of generating circumferential weld excavation information for the target pipeline based on the quality risk prediction information includes: obtaining the risk ratio prediction value from each of the quality risk prediction information and obtaining the excavation grading threshold associated with the excavation requirements, wherein the risk ratio prediction value includes the non-conforming ratio prediction value and / or the crack ratio prediction value; arranging each circumferential weld in descending order of the risk ratio prediction value to obtain a circumferential weld excavation sequence; determining the excavation level for each circumferential weld based on the excavation grading threshold and the risk ratio threshold to form excavation grading information; and determining the circumferential weld excavation sequence and the excavation grading information as the circumferential weld excavation information for the target pipeline.

5. The method according to claim 1, characterized in that, The step of determining the target circumferential weld that meets the excavation requirements according to the circumferential weld excavation information includes: obtaining the excavation quantity requirement and excavation cost consumption set under the excavation requirements; selecting the circumferential weld that meets the excavation quantity requirement and excavation cost consumption from the circumferential weld excavation information, and determining it as the target circumferential weld.

6. The method according to any one of claims 1-5, characterized in that, Also includes: Based on historical data of each circumferential weld on the pilot pipeline, one or more attribute items are determined, and attribute judgment rules for each attribute item are obtained to form the predicted attribute set; based on the predicted attribute set and the historical data, multiple criterion description items are determined to form the excavation criterion set.

7. The method according to claim 6, characterized in that, The process of determining one or more attribute items and obtaining attribute determination rules for each attribute item based on historical data of each circumferential weld on the pilot pipeline to form the predicted attribute set includes: determining one or more benchmark attribute items based on expert knowledge information, and determining target attribute items based on the historical data information combined with an information gain algorithm; defining the benchmark attribute items and the target attribute items as attribute items, and defining the first attribute value range relative to the benchmark attribute items and the second attribute value range relative to the target attribute items as attribute value ranges; determining the risk ratio value of the corresponding attribute item based on the attribute value range and the historical data information, and obtaining attribute determination rules configured relative to each attribute item based on the risk ratio value; and summarizing the attribute items and the corresponding attribute determination rules to form the predicted attribute set.

8. The method according to claim 7, characterized in that, The step of determining the target attribute item based on the historical data information and the information gain algorithm includes: obtaining one or more pre-set candidate attribute items, and obtaining a first attribute value range constructed relative to the benchmark attribute item and a second attribute value range constructed relative to the candidate attribute items; determining a first gain value of the benchmark attribute item and a second gain value of the candidate attribute item based on the historical data information, the first attribute value range, and the second attribute value range; and determining the candidate attribute item corresponding to the second gain value that matches the first gain value as the target attribute item.

9. The method according to claim 6, characterized in that, The step of determining multiple criterion descriptions based on the predicted attribute set and the historical data information to form the excavation criterion set includes: determining a circumferential weld dataset based on the historical data information, and forming at least one first data subset by grouping the circumferential weld dataset; determining an initial excavation criterion set based on the first data subset and the predicted attribute set; segmenting the circumferential weld dataset according to the initial excavation criterion set to obtain a first number of second data subsets, wherein the data in each second data subset does not overlap; and forming the excavation criterion set based on each second data subset and each first data subset.

10. The method according to claim 9, characterized in that, The step of determining the initial excavation criterion set based on the first data subset and the predicted attribute set includes: for each first data subset, obtaining a pre-constructed initial criterion set; after determining that each attribute item in the predicted attribute set is added to the initial criterion set, filtering out a first target rate for risk-type circumferential welds through the initial criterion set; obtaining a first screening condition relative to the first target rate; determining a first type of attribute item from the attribute items according to the first screening condition; and forming a criterion description item based on the attribute judgment rule of the first type of attribute item and adding it to the initial criterion set; returning to re-execute the operation of determining that each attribute item in the predicted attribute set is added to the initial criterion set and filtering out the first target rate for risk-type circumferential welds through the initial criterion set, until the loop termination condition is met, and obtaining the initial criterion set after the loop termination; and determining the initial excavation criterion set that meets the selected condition from the initial criterion sets corresponding to each first data subset.

11. The method according to claim 9, characterized in that, The step of segmenting the circumferential weld dataset according to the initial excavation criterion set to obtain a first number of second data subsets includes: obtaining a first type of attribute item associated with each criterion description item included in the initial excavation criterion set; obtaining segmentation filtering conditions set according to the attribute determination rules of the first type of attribute item; and segmenting the circumferential weld dataset into a first number of non-overlapping second data subsets according to the segmentation filtering conditions and the combinatorial formula, wherein the first number is the same as the number of combinations corresponding to the combinatorial formula.

12. The method according to claim 9, characterized in that, The step of forming the excavation criterion set based on each of the second data subsets and each of the first data subsets includes: for each second data subset, performing full criterion mining on the second data subset according to a first search strategy and a second search strategy respectively to obtain a full criterion library; for each criterion description item in the full criterion library, determining the quality risk prediction index corresponding to the criterion description item according to each of the first data subsets; updating the quality risk prediction index to the criterion description item, and integrating each of the criterion description items to form the excavation criterion set.

13. The method according to claim 12, characterized in that, The step of performing full criterion mining on the second data subset according to the first search strategy and the second search strategy to obtain a full criterion library includes: for each second data subset, executing the same search logic as the initial excavation criterion set determination according to the first search strategy to obtain a first excavation criterion set for the second data subset, and constructing a criterion set to be expanded using the first attribute item in the first excavation criterion set according to the second search strategy; after determining that each attribute item in the predicted attribute set is added to the criterion set to be expanded, filtering out the second target rate of non-risk circumferential welds through the criterion set to be expanded; obtaining the relative second The second screening condition for the target rate is set. Based on the second screening condition, a second type of attribute item is determined from the attribute items. A criterion description item is formed based on the attribute judgment rule of the second type of attribute item and added to the criterion set to be expanded. The operation of determining that each attribute item in the predicted attribute set is added to the criterion set to be expanded is re-executed. The operation of filtering out the second target rate of non-risk circumferential welds through the criterion set to be expanded is carried out until the loop termination condition is met. The criterion set to be expanded after the loop termination is determined as the second excavation dataset. A full criterion set is formed based on each of the first excavation criterion sets and each of the second excavation datasets.

14. The method according to claim 12, characterized in that, The step of determining the quality risk prediction index corresponding to the criterion description item based on each of the first data subsets includes: determining the risk ratio value corresponding to the criterion description item in each of the first data subsets, and determining the predicted mean and standard deviation of the risk ratio corresponding to the criterion description item based on each of the risk ratio values; determining the predicted fluctuation range of the criterion description item based on the predicted mean and standard deviation of the risk ratio, combined with the prediction fluctuation formula; and determining the predicted mean, standard deviation, and prediction fluctuation range of the risk ratio as the quality risk prediction index of the criterion description item.

15. A device for quality inspection and excavation management of pipeline circumferential welds, characterized in that, include: The acquisition module is used to acquire basic data information of each circumferential weld on the target pipeline, and to acquire a pre-determined set of prediction attributes and a set of excavation criteria for predicting the quality of the circumferential weld; the first information determination module is used to determine the attribute determination information of each circumferential weld relative to the set of prediction attributes based on the basic data information. The second information determination module is used to determine the quality risk prediction information of the corresponding circumferential weld based on the attribute determination information and the excavation criterion set. The target circumferential weld determination module is used to generate circumferential weld excavation information for the target pipeline based on the quality risk prediction information, and to determine the target circumferential weld that meets the excavation requirements according to the circumferential weld excavation information.

16. An electronic device, characterized in that, The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the pipeline circumferential weld quality inspection excavation management method according to any one of claims 1-14.

17. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the pipeline circumferential weld quality inspection and excavation management method as described in any one of claims 1-14.

18. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the pipeline circumferential weld quality inspection and excavation management method as described in any one of claims 1-14.

Images