Gas engineering construction quality assessment system based on big data

Abstract

The present invention belongs to the field of gas pipeline technology, and specifically is a gas engineering construction quality assessment system based on big data. It first constructs a defect feature tensor, introduces spatiotemporal grid analysis technology to analyze defect disposal time interval data and location defect recurrence frequency data, and converts defect features into quantifiable quality and efficiency scores based on preset quality, efficiency and reliability quantification rules. Secondly, by establishing a spatiotemporal correlation matrix of welding defects, welding process parameters and environmental monitoring parameters, it realizes the deep fusion of multi-source heterogeneous data. On this basis, fuzzy correlation analysis technology and preset process compliance quantification rules are used to convert complex process parameters and environmental conditions into quantifiable process scores. The comprehensive process score and quality and efficiency score are combined to generate a comprehensive assessment value of the target contractor's gas pipeline welding quality, providing a quantifiable intelligent decision support system for the contractor's gas pipeline construction quality control.

Description

Technical Field

[0001] The present invention belongs to the technical field of gas pipelines, and in particular relates to a gas engineering construction quality assessment system based on big data. Background Art

[0002] Against the backdrop of the rapid expansion of urban gas networks, the quality of gas project construction, particularly PE pipeline construction, has become a critical factor in ensuring public safety and system reliability. As the primary contractor, the quality of their work directly impacts the safety and service life of the project. However, traditional construction quality assessment methods suffer from subjectivity and low data utilization, making them inadequate for meeting the high standards of modern engineering construction. Therefore, accurately assessing contractors' gas project quality based on PE pipeline performance is crucial.

[0003] Several existing solutions involve analyzing the construction quality of PE pipelines. For example, Chinese Patent Publication No. CN113379280A describes a method and system for assessing the risk of buried high-molecular-weight polyethylene (PE) gas pipelines. This system collects historical accident and inspection report data and summaries from buried PE gas pipelines to establish a risk database for buried PE gas pipelines, determine the risk classification for buried PE gas pipelines, and identify indicators for assessing the risk of buried PE gas pipeline failures. Based on the characteristics of PE gas pipelines and domestic and international statistical data on the causes of accidents in urban gas PE pipeline systems, the system incorporates the Kent scoring method and the analytic hierarchy process, and introduces extenics to design four primary risk assessment indicators: third-party damage, design factors, misoperation factors, and intrinsic safety quality. A model for assessing the failure risk of PE gas pipelines in urban areas is established, along with calculation methods for scoring and weighting each risk assessment indicator and corresponding software.

[0004] Another Chinese patent, with publication number CN119476958A, is a smart gas pipeline welding monitoring method and IoT system based on government supervision. It is executed on the gas company management platform of the smart gas pipeline welding monitoring IoT system, and includes: obtaining at least one set of welding point information and corresponding pipeline construction information in a preset pipeline area. Based on the pipeline construction information, a first welding risk is determined. Based on the first welding risk and historical welding risks, a first risk value is determined. In response to the first risk value meeting the preset conditions, a welding adjustment instruction is generated. The welding process information uploaded by the welder terminal is obtained. The welding process information is pre-processed to obtain key welding information and stored in the government supervision comprehensive database. The monitoring parameters of the preset pipeline area are determined. The on-site welding quality of the gas pipeline can be more comprehensively monitored according to different environmental factors to improve the safety and efficiency of the welding operation.

[0005] Although the above scheme proposes a quality analysis method for the PE pipeline construction performance dimension, its analysis logic still has limitations when introduced into the contractor's construction quality assessment. Specifically: 1. The existing technology has a single data dimension for PE pipeline construction quality assessment. It mostly relies on weld images or manual sampling records, lacks multi-source data fusion of welding process parameters and environmental monitoring parameters, and cannot build a complete quality assessment factor system.

[0006] 2. Existing technologies are fragmented in their assessment of PE pipeline construction quality. Quality assessment and process assessment are performed separately. Not only does this lack the spatiotemporal correlation analysis between defect characteristics and process parameters, but it also fails to quantify the dynamic impact of environmental variables on welding quality. Process compliance determination relies on static thresholds set in advance, making it impossible to effectively provide feedback on the specific quality level of the contractor's gas construction. Summary of the Invention

[0007] In order to overcome the shortcomings of the background technology, the embodiments of the present invention provide a gas engineering construction quality assessment system based on big data, which can effectively solve the problems involved in the above background technology.

[0008] The purpose of the present invention can be achieved through the following technical solutions: A gas engineering construction quality assessment system based on big data, including: a data acquisition module, a quality and efficiency assessment module, a process assessment module and a comprehensive assessment module.

[0009] The data acquisition module is connected to the quality and efficiency evaluation module, the quality and efficiency evaluation module is connected to the process evaluation module, and the process evaluation module is connected to the comprehensive evaluation module.

[0010] The data acquisition module obtains the target contractor's gas pipeline historical welding data set through a multi-source data interface. The data set contains welding process parameters, environmental monitoring parameters, and a weld image sequence arranged according to the construction time sequence.

[0011] The quality and efficiency evaluation module extracts defect features from the weld image sequence, generates a feature tensor containing defect type code, spatial coordinates and timestamp, analyzes the defect treatment time interval data and location defect recurrence frequency data in the feature tensor based on spatiotemporal grid analysis, and generates a quality and efficiency score through preset quality and efficiency reliability quantification rules.

[0012] The process evaluation module establishes a spatiotemporal correlation matrix of welding defects, welding process parameters and environmental monitoring parameters, analyzes the defect-process correlation index and environment-process suitability index in the spatiotemporal correlation matrix based on fuzzy correlation analysis, and generates a process score through preset process compliance quantification rules.

[0013] The comprehensive evaluation module is used to perform weighted fusion calculation on the process score and the quality and efficiency score to generate a comprehensive evaluation value of the gas pipeline welding quality of the target contractor and output a visual report.

[0014] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: (1) The present invention realizes three-dimensional data coupling of welding process parameters, environmental monitoring parameters, and visual features through spatiotemporal alignment of multi-source heterogeneous data, and conducts effective and accurate evaluation of the historical welding quality of the target contractor's gas pipeline from the perspectives of process compliance and quality and efficiency reliability, thereby greatly improving the reliability and practicality of the evaluation results.

[0015] (2) The present invention realizes the structured expression of defect information by constructing defect feature tensors. On this basis, the spatiotemporal grid analysis technology is introduced to analyze the defect treatment time interval data and the location defect recurrence frequency data, so as to realize the dynamic tracking and visualization of defect distribution. Furthermore, based on the preset quality, efficiency and reliability quantification rules, the defect characteristics are converted into quantifiable quality and efficiency scores, which highly reflect the contractor's gas pipeline construction quality level.

[0016] (3) The present invention achieves deep fusion of multi-source heterogeneous data by establishing a spatiotemporal correlation matrix of welding defects, welding process parameters and environmental monitoring parameters, breaking through the limitations of traditional single data dimension analysis. On this basis, fuzzy correlation analysis technology and preset process compliance quantification rules are used to convert complex process parameters and environmental conditions into quantifiable process scores, thereby realizing dynamic evaluation of the contractor's gas pipeline construction process. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of module connections provided by the first embodiment of the present invention.

[0019] Figure 2 This is a specific logic diagram of the preset quality-efficiency-reliability quantification rules in the first embodiment of the present invention.

[0020] Figure 3 A schematic structural diagram of a device provided in accordance with the second embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0022] Example 1

[0023] Reference Figure 1 As shown, the first embodiment of the present invention provides a gas engineering construction quality assessment system based on big data, including: a data acquisition module, a quality and efficiency assessment module, a process assessment module and a comprehensive assessment module.

[0024] The data acquisition module is connected to the quality and efficiency evaluation module, the quality and efficiency evaluation module is connected to the process evaluation module, and the process evaluation module is connected to the comprehensive evaluation module.

[0025] The data acquisition module obtains the target contractor's gas pipeline historical welding data set through a multi-source data interface. The data set includes welding process parameters, environmental monitoring parameters, and a weld image sequence arranged according to the construction time sequence.

[0026] It should be noted that the above-mentioned target contractor's gas pipeline historical welding dataset covers the welding data of various gas engineering projects undertaken by the target contractor within a historical preset period according to the construction sequence, and the welding data is recorded in real time by a welding machine or welding gun equipped with a multi-functional sensor and data acquisition device during the operation. For example, welding process parameters (including but not limited to current, voltage, speed, etc.) are collected in real time by the intelligent sensor array carried by the welding machine, and environmental monitoring parameters (including but not limited to temperature and humidity, wind speed, air pressure, etc.) are collected in real time by the micro-meteorological sensor array integrated in the welding machine. The weld image sequence is dynamically acquired by the linear array CCD camera integrated in the welding machine according to the welding rhythm. Since the data acquisition process is carried out synchronously with the welding operation and all data have a unified timestamp and spatial coordinate identifier, the multi-dimensional information in the dataset can achieve precise spatiotemporal alignment operations, providing a high-quality data foundation for subsequent spatiotemporal correlation analysis.

[0027] The quality and efficiency evaluation module extracts defect features from the weld image sequence, generates a feature tensor containing defect type code, spatial coordinates and timestamp, analyzes the defect treatment time interval data and location defect recurrence frequency data in the feature tensor based on spatiotemporal grid analysis, and generates a quality and efficiency score through preset quality and efficiency reliability quantification rules.

[0028] It should be added that the defect feature extraction of the above-mentioned weld image sequence specifically refers to a preset defect feature library that has integrated various weld defect image features. The cosine similarity is used to calculate the matching degree between the feature vectors extracted from each image to be inspected in the weld image sequence and the various weld defect image features in the preset defect feature library. If the matching degree is greater than or equal to the preset matching degree threshold, it is considered a successful match and the corresponding defect feature extraction processing is performed.

[0029] In a preferred embodiment of the present invention, the defect treatment time interval data is specifically referred to the following parsing process: a three-dimensional space grid is constructed based on the defect type code and space coordinates in the feature tensor.

[0030] The time interval from the welding timestamp to the defect elimination timestamp of the same defect type code in the grid unit is taken as the single defect disposal aging interval. The disposal aging interval of each defect type in each grid unit is collected as the defect disposal aging interval data.

[0031] It should be noted that the camera device integrated in the welding machine usually collects data with millisecond-level granularity, and the timestamp is accurate to the welding moment. Therefore, multiple weld images can be collected during the same process of the weld. The calculation of the defect handling time interval is the defect response time within the same process of the weld, specifically referring to the absolute difference between the welding timestamp and the elimination timestamp of a certain type of defect at the same spatial position of the weld (for example, a porosity is found at the 10th second of root welding, and the porosity disappears after the current is adjusted at the 12th second, with an interval of 2 seconds). If the defect persists until the end of the welding process or is left over across processes, it means that the defect of this type has not been eliminated and the defect handling time interval is automatically set to NULL.

[0032] In a preferred embodiment of the present invention, the location defect recurrence frequency data specifically refers to the following analysis process: recording the time and type of each defect occurrence in the same grid unit within a preset time window, introducing a time attenuation factor and a defect type weight factor for weighting, and obtaining the defect recurrence frequency of the same grid unit.

[0033] It should be added that the recurrence frequency of the defects in the same grid unit can be calculated by referring to the following formula: , Characterize the defect type weight factor, specifically the same grid unit When a defect occurs, its defect type corresponds to a preset weight, which can be set in advance based on factors such as the degree of damage of the defect and the cost of repair. It is used to indicate the degree of influence of different defect types on the recurrence frequency and distinguish their importance. For example, a serious defect (such as a crack) has a higher weight, while a minor defect (such as a surface pore) has a lower weight. Characterize the time attenuation factor, control the impact of the defect occurrence time on the recurrence frequency, the closer the time, the greater the contribution, the farther the time, the smaller the contribution. It is a preset attenuation coefficient used to control the rate of time attenuation and can be set manually at the beginning of system operation. The time span corresponding to the preset time window, For the same grid cell The time interval between the time when the secondary defect occurs and the time of the starting port of the preset time window, is a natural constant, is the number of each defect occurrence in the same grid unit, .

[0034] It should also be added that the weighting logic used in the calculation formula for the defect recurrence frequency of the same grid unit is: Different types of defects are given different weights. Assigning attenuation weights to defects occurring at different times and summing up the double-weighted products is essentially a weighted summation of the impact of each defect, which is explained here to avoid ambiguity.

[0035] As an example, the preset time window is 10 days, the time decay coefficient is 0.1, and the defect occurrence record of a certain grid unit within the preset time window is shown in Table 1 below.

[0036] Table 1 Defect occurrence record data within the preset time window

[0037]

[0038] Therefore, the defect recurrence frequency of this grid unit is calculated to be 2.7585.

[0039] The number of covered grid cells of the same defect type within the preset time window is counted, and its ratio to the total number of three-dimensional space grids is used as the location recurrence frequency of the same defect type.

[0040] The defect recurrence frequency of each grid unit within the preset time window and the location recurrence frequency of each defect type are collected and used together as the location defect recurrence frequency data.

[0041] It should be noted that the welding of a gas pipeline pipe diameter interface (weld) is divided into multiple processes (root welding, hot welding, filling welding, and cap welding). Each process corresponds to a different spatial coordinate range (not an absolute physical point). For example, the root weld covers the weld depth of 0-3mm (axially), the filling weld covers the depth of 3-8mm, and the cap weld covers the surface depth of 0-1mm. Different process defects in the same weld (such as root weld lack of fusion vs. filling weld porosity) belong to different spatial coordinates, not the same location. Therefore, the theoretical basis for the existence of two types of location defect recurrence frequency data can be explained by Table 2 below.

[0042] Table 2 Connotation of recurrence frequency of location defects

[0043]

[0044] Reference Figure 2 As shown, in a preferred embodiment of the present invention, the preset quality, efficiency and reliability quantification rules include the following contents: obtaining the corresponding score values ​​of each grid unit, each defect type and each disposal time interval through a preset score mapping table, and obtaining the timeliness score through layered averaging and normalization processing.

[0045] It should be noted that the above-mentioned stratified averaging processing includes the first, second and third-level averaging processing. Specifically, the first level performs the arithmetic average of the corresponding scores of multiple disposal time intervals for the same defect to eliminate the randomness of single disposal. The second level performs the arithmetic average of the average scores of all defect types under the same grid unit. The third level performs the global average of the final scores of all grid units.

[0046] The average defect recurrence frequency of grid units and the average location recurrence frequency of defect types within the preset time window are respectively substituted into the preset penalty function, and the grid recurrence degradation value and type diffusion degradation value are quantified. The higher of the two-dimensional degradation values ​​is taken, and the higher deduction is performed on the initial stability full score to obtain the stability score.

[0047] It should be added that the above preset penalty function can refer to the following calculation formula: , is the average defect recurrence frequency of the grid cells or the average location recurrence frequency of the defect type within the preset time window, The preset grid unit defect recurrence allowable benchmark frequency or defect type location recurrence allowable benchmark frequency, which is set based on historical data or industry standards. The preset penalty coefficients for grid unit defect recurrence and defect type location recurrence are used to control the growth rate of degradation value, which needs to be determined through sensitivity experimental analysis. is a preset control factor used to control the numerical range of the output result of the preset penalty function. In this embodiment Take the value 0.5, The value is 2. The value is 1.

[0048] This formula selects an exponential function, which aims to nonlinearly amplify the risk of exceeding the benchmark value, which is consistent with the characteristic of "accumulation of small problems leading to qualitative changes" in actual engineering.

[0049] As an example, the average defect recurrence frequency of grid units within the preset time window is 2.5, the average location recurrence frequency of the defect type is 0.12, the grid unit defect recurrence permission benchmark frequency is 2, and the defect type location recurrence permission benchmark frequency is 0.1. After calculation, the grid recurrence degradation value is 0.133, and the type diffusion degradation value is 0.491.

[0050] It should also be added that the above-mentioned high-value deduction process specifically refers to the initial stability full score (100 points) multiplied by the absolute difference between the higher of the two-dimensional degradation values ​​and 1. Based on the above example, the higher of the two-dimensional degradation values ​​is 0.491, and the high-value deduction process is: , resulting in a stability score of 50.9 points.

[0051] The sum of the timeliness score and the stability score is taken as the quality and effectiveness score.

[0052] In a preferred embodiment of the present invention, the preset scoring mapping table includes a nonlinear mapping relationship between the time interval for handling each defect type and the scoring value.

[0053] The embodiment of the present invention realizes the structured expression of defect information by constructing a defect feature tensor. On this basis, the spatiotemporal grid analysis technology is introduced to analyze the defect treatment time interval data and the location defect recurrence frequency data, so as to realize the dynamic tracking and visualization of the defect distribution. Furthermore, based on the preset quality, efficiency and reliability quantification rules, the defect characteristics are converted into quantifiable quality and efficiency scores, which highly reflects the contractor's gas pipeline construction quality level.

[0054] The process evaluation module establishes a spatiotemporal correlation matrix of welding defects, welding process parameters, and environmental monitoring parameters, analyzes the defect-process correlation index and environment-process suitability index in the spatiotemporal correlation matrix based on fuzzy correlation analysis, and generates a process score through preset process compliance quantitative rules.

[0055] In a preferred embodiment of the present invention, the spatiotemporal correlation matrix establishes a mapping relationship between each welding defect and the corresponding process environment condition by spatiotemporally aligning the welding process parameters with the environmental monitoring parameters.

[0056] In a preferred embodiment of the present invention, the defect-process correlation index specifically refers to the following analytical process: the synchronous welding process parameters corresponding to the time intervals of occurrence of each welding defect are retrieved, a trapezoidal membership function is used to construct a fuzzy level classification standard for the process parameters, and the welding process parameters are mapped to predefined fuzzy levels through fuzzy processing to generate a process parameter membership matrix corresponding to the moment of each welding defect.

[0057] The preset association rule library is scanned by a preset association rule algorithm (which can be exemplified by the Apriori association rule algorithm), and a set of strong association rules that matches the membership matrix of the process parameters at the time corresponding to the welding defect is extracted. The confidence weight of each strong association rule is recorded, and a linear weighted calculation method is used to obtain the correlation between each welding defect and the welding process parameters at the corresponding time. The correlation index between the welding defect and the welding process parameters is output through mean calculation.

[0058] It should be added that the above-mentioned preset association rule library is a set of rules pre-established through historical data mining or expert experience, which is used to describe the association between welding process parameters and defect types, as well as the adaptation relationship between welding variables and environmental variables. Each rule in the rule library contains the following core information: a) Defect association rule: Low current Low voltage defect , this example explains that the low current level combined with the low voltage level causes the defect occur.

[0059] b) Environmental adaptation rules: high wind speed The welding speed is high. This example explains that if the wind speed in the welding environment is at a high level, the welding speed must also be at a high level. That is, the strongly correlated environmental variable corresponding to the welding speed is the wind speed. Simultaneously, the preset association rule library stores pre-defined benchmark values ​​for each environmental variable and the numerical intervals divided into low, medium, and high levels.

[0060] c) Support: the frequency of the rule appearing in historical data (e.g., the number of rule occurrences / total number of samples).

[0061] d) Confidence: The probability that the consequent will also occur when the antecedent of the rule occurs (e.g., the number of times the antecedent and consequent occur together / the number of times the antecedent occurs).

[0062] Special Note: Each environmental adaptation rule in the preset association rule library uses a single, strongly correlated environmental variable to point to its influencing welding variable. Although welding variables may be affected by multiple environmental variables, during the initial development of the preset association rule library, a manual comparison was performed to analyze the impact of each environmental variable on the same welding variable, and the environmental variable with the greatest impact was selected as the single, strongly correlated environmental variable. Therefore, the single, strongly correlated environmental variable in the preset association rule library does not mean that the welding variable is affected by only one environmental variable. Instead, it is used to simplify the rule library structure and highlight the primary influencing factors. This clarification is provided to avoid ambiguity.

[0063] It should also be added that the above-mentioned strong association rule set extracted to match the process parameter membership matrix at the time corresponding to the welding defect must meet the following conditions: (1) The antecedent of the rule must be completely contained in the process parameter membership matrix at the time corresponding to the welding defect. Among them, the numerical value of the membership matrix element represents the fuzzy level of the process parameter. The fuzzy level of each process parameter in the antecedent of the rule must be completely consistent with the numerical meaning of the corresponding element of the membership matrix. Only when this condition is met can it be considered as a matching association rule. Rules that meet this condition are only considered as matching association rules.

[0064] (2) A matching association rule must satisfy both the support greater than or equal to the preset critical support and the confidence greater than or equal to the preset critical confidence to be considered a strong association rule. The preset critical support and the preset critical confidence are determined by the initial establishment of the preset association rule library, based on the support and confidence data of all rules in the library, through mean analysis or quartile analysis.

[0065] The following are welding defects The specific calculation example of the correlation degree of the welding process parameters at the corresponding moment: The fuzzy result of the welding process parameters at this moment is shown in Table 3 below (i.e. the tabular form of the membership matrix)

[0066] Table 3 Fuzzy results of welding process parameters

[0067]

[0068] The matching association rules in the preset rule library related to the welding process parameters at this moment are shown in Table 4 below.

[0069] Table 4 Corresponding matching association rules of welding process parameter fuzzy results

[0070]

[0071] Record the confidence of each strong association rule in Table 4 (i.e. 0.8, 0.85), Calculated welding defects The correlation degree with the welding process parameters at the corresponding moment.

[0072] In a preferred embodiment of the present invention, the environment-process suitability index specifically refers to the following analytical process: randomly extract a welding variable from the welding process parameters at a certain spatial coordinate at a certain time, mark the welding variable as a target welding variable, retrieve strongly associated environmental variables that match the target welding variable through a preset association rule library, and compare and retrieve the monitoring values ​​of the strongly associated environmental variables at the same spatial coordinate and the same time.

[0073] The standard value of the target welding variable is defined according to the material characteristics of the spatial coordinate gas pipeline, and the standard value of the target welding variable is corrected by the monitoring value of the strongly correlated environmental variable to generate a process adaptation range of the target welding variable.

[0074] It should be noted that when defining the standard values ​​of welding variables based on the material properties of the gas pipeline, the standard range of welding variables specified in the gas pipeline material manual is primarily referenced, and the median of this range is selected as the standard value. At the same time, the fluctuation range of the welding variable standard range specified in the material manual is recorded and used as the basis for the fluctuation range of the subsequent process adaptation range. Specifically, the process adaptation range of the target welding variable is a dynamic value range generated by using the modified adaptation value of the target welding variable as the median of the interval and the fluctuation range specified in the material manual as the interval width.

[0075] It should also be added that the specific process of correcting the target welding variable standard value by using the monitoring value of the strongly correlated environmental variable includes: extracting the predefined reference value of the strongly correlated environmental variable and its correction direction relative to the target welding variable from the preset association rule library (depending on the environmental adaptation rules of the target welding variable and the strongly correlated environmental variable, such as high wind speed). The correction direction of welding speed in high and medium welding speed is upward.

[0076] The deviation ratio between the monitored value of the strongly correlated environmental variable and its baseline value is calculated, and the calculation logic is specifically the ratio of the absolute difference between the two and the baseline value.

[0077] The deviation ratio is multiplied by the confidence of the environmental adaptation rule of the strongly correlated environmental variable for the target welding variable to obtain a correction factor, and the sign of the correction factor is determined by the correction direction (upward adjustment is positive, downward adjustment is negative).

[0078] The correction coefficient is defined as the cumulative value of 1 and the correction factor, and the product of the correction coefficient and the standard value of the target welding variable is used as the adapted value of the target welding variable after correction.

[0079] As an example, assume that the target welding variable is welding current, whose standard value is 180A, and the strongly associated environmental variable matching the target welding variable is temperature, whose predefined reference value is 25°C. The monitoring value at the same spatial coordinate and the same time is 30°C. The environmental adaptation rule for the strongly associated environmental variable to the target welding variable is retrieved from the preset association rule library. The welding current is high and the confidence level is 0.8, so it can be determined that the correction direction is positive. Then, by calculation, we can know that: deviation ratio = , correction factor = 0.2×0.8=0.16, correction coefficient = 1+0.16=1.16, target adaptation value = 180×1.16=208.8A, so the corrected welding current adaptation value is 208.8A.

[0080] The actual value of the target welding variable is compared with its process adaptation interval, and the fitness of the target welding variable and its strongly associated environmental variable is output. Similarly, the fitness of each welding variable and its strongly associated environmental variable in the welding process parameters at each spatial coordinate and at each moment is collected, and the environment-process fitness index is obtained through layered averaging.

[0081] In a preferred embodiment of the present invention, the adaptability of the target welding variable and its strongly associated environmental variables is specifically described in the following output process: if the actual value of the target welding variable is within its process adaptation range, the adaptability of the output target welding variable and its strongly associated environmental variables is 1.

[0082] If the actual value of the target welding variable is outside its process adaptation interval, the deviation amplitude of the actual value of the target welding variable and its process adaptation interval is quantified, and the negative form of the deviation amplitude is introduced into the natural exponential function to solve the fitness of the target welding variable and its strongly associated environmental variables.

[0083] It should be added that the specific quantification process of the deviation amplitude of the actual value of the above-mentioned target welding variable and its process adaptation interval is as follows: if the actual value of the target welding variable is greater than the upper limit value of its process adaptation interval, then the excess value of the actual value of the target welding variable relative to the upper limit value of its process adaptation interval is obtained, and a ratio analysis (normalization processing) is performed with the upper limit value of its process adaptation interval to obtain the deviation amplitude.

[0084] If the actual value of the target welding variable is less than the lower limit of its process adaptation interval, the absolute difference between the actual value of the target welding variable and the lower limit of its process adaptation interval is obtained, and a ratio analysis is performed with the lower limit of its process adaptation interval to obtain the deviation amplitude.

[0085] In a preferred embodiment of the present invention, the preset process compliance quantification rules include the following: according to the preset defect-process correlation index interval, the preset environment-process adaptability index interval and the preset process score value corresponding to each process level ladder, the defect-process correlation index and the environment-process adaptability index analyzed in the time-space correlation matrix are respectively determined to correspond to the process level ladder, and the preset process score values ​​of the process level ladder corresponding to the interval of the dual indicators are weighted according to the preset weight ratio to obtain the process score.

[0086] It should be noted that the default weighting ratio for the process-level tier corresponding to the intervals of the aforementioned two indicators is set based on the following logic: the Defect-Process Correlation Index is greater than the Environment-Process Suitability Index. This is based on the fact that the Defect-Process Correlation Index directly reflects the contractor's process execution capabilities (e.g., welding time control and groove preparation), which is a 100% controllable factor. Accident statistics from the Ministry of Housing and Urban-Rural Development show that 68% of PE pipe defects (e.g., excessive misalignment and insufficient welding temperature) can be attributed to substandard process operations, and that the process stability of the same contractor varies by as much as 52% under different environments (e.g., a company's welding pass rate fluctuates by less than 5% in dry and humid environments, reflecting the process's ability to resist interference). Environment-Process Suitability, which reflects the process's passive adaptability to the environment (e.g., whether cooling time is adjusted when humidity exceeds 80%), is a partially controllable factor. Therefore, the default weighting ratio for the default process-level tier corresponding to the intervals of the Defect-Process Correlation Index is set relatively high.

[0087] For example, the preset weight ratios of the preset process assignment scores corresponding to the process level ladder in the interval where the above-mentioned dual indicators are located can be set to 0.72 for the defect-process correlation index and 0.28 for the environment-process adaptability index.

[0088] The embodiment of the present invention achieves deep fusion of multi-source heterogeneous data by establishing a spatiotemporal correlation matrix of welding defects, welding process parameters and environmental monitoring parameters, breaking through the limitations of traditional single data dimension analysis. On this basis, fuzzy correlation analysis technology and preset process compliance quantification rules are adopted to convert complex process parameters and environmental conditions into quantifiable process scores, thereby realizing dynamic evaluation of the contractor's gas pipeline construction process.

[0089] The comprehensive evaluation module is used to perform weighted fusion calculation on the process score and the quality and efficiency score to generate a comprehensive evaluation value of the gas pipeline welding quality of the target contractor and output a visual report.

[0090] The embodiment of the present invention achieves three-dimensional data coupling of welding process parameters, environmental monitoring parameters, and visual features through spatiotemporal alignment of multi-source heterogeneous data. This allows for an effective and accurate assessment of the historical welding quality of the target contractor's gas pipeline from the perspectives of process compliance and quality and efficiency reliability, thereby greatly improving the reliability and practicality of the assessment results.

[0091] Example 2

[0092] Reference Figure 3As shown, a second embodiment of the present invention provides an apparatus comprising: a processor, a memory, and a communication bus. The memory stores a computer-readable program executable by the processor. The communication bus enables communication between the processor and the memory. When the processor executes the computer-readable program, it implements the big data-based gas engineering construction quality assessment system.

[0093] Specifically, the above-mentioned memory and processor can be general-purpose memory and processor, which are not specifically limited here. When the processor runs the computer-readable program stored in the memory, it can execute the above-mentioned system-related steps.

[0094] The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above system can be completed by hardware integrated logic circuits in the processor or software instructions. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, or discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of this application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The system-related method steps disclosed in the embodiments of this application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above system in combination with its hardware.

[0095] The above content is merely an example and explanation of the structure of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. The gas engineering construction quality assessment system based on big data is characterized by: The system includes: A data acquisition module, which acquires the target contractor's gas pipeline historical welding data set through a multi-source data interface. The data set contains welding process parameters, environmental monitoring parameters, and weld image sequences arranged according to the construction time sequence. The quality and efficiency evaluation module extracts defect features from the weld image sequence, generates a feature tensor containing defect type code, spatial coordinates, and timestamp, analyzes the defect treatment time interval data and location defect recurrence frequency data in the feature tensor based on spatiotemporal grid analysis, and generates a quality and efficiency score based on preset quality and efficiency reliability quantification rules; The process evaluation module establishes a spatiotemporal correlation matrix of welding defects, welding process parameters, and environmental monitoring parameters. It analyzes the defect-process correlation index and environment-process suitability index in the spatiotemporal correlation matrix based on fuzzy correlation analysis, and generates a process score based on preset process compliance quantitative rules. The defect-process correlation index is specifically described in the following analytical process: the synchronous welding process parameters corresponding to the time intervals of each welding defect occurrence are retrieved, a trapezoidal membership function is used to construct a fuzzy level classification standard for the process parameters, and the welding process parameters are mapped to predefined fuzzy levels through fuzzification processing to generate a process parameter membership matrix corresponding to each welding defect at the corresponding moment; The preset association rule library is scanned using a preset association rule algorithm to extract a set of strong association rules that matches the process parameter membership matrix at the time corresponding to the welding defect. The confidence weight of each strong association rule is recorded, and a linear weighted calculation method is used to obtain the correlation between each welding defect and the welding process parameter at the corresponding time. The correlation index between the welding defect and the welding process parameter is output through mean calculation; The environment-process suitability index is specifically described in the following analytical process: randomly extract a welding variable from the welding process parameters at a certain spatial coordinate at a certain time, mark the welding variable as a target welding variable, retrieve strongly associated environmental variables that match the target welding variable through a preset association rule library, and compare and retrieve the monitoring values ​​of the strongly associated environmental variables at the same spatial coordinate and the same time; Defining a standard value of a target welding variable according to the material characteristics of the gas pipeline in the spatial coordinates, and correcting the standard value of the target welding variable by using the monitored value of the strongly correlated environmental variable to generate a process adaptation range of the target welding variable; The actual value of the target welding variable is compared with its process adaptation interval, and the adaptability of the target welding variable and its strongly associated environmental variable is output. Similarly, the adaptability of each welding variable and its strongly associated environmental variable in the welding process parameters at each spatial coordinate and at each moment is collected, and the environment-process adaptability index is obtained through layered averaging. The comprehensive evaluation module is used to perform weighted fusion calculation on the process score and the quality and efficiency score to generate a comprehensive evaluation value of the gas pipeline welding quality of the target contractor and output a visual report.

2. The gas engineering construction quality assessment system based on big data according to claim 1 is characterized by: The defect treatment time interval data is specifically referred to the following parsing process: constructing a three-dimensional space grid based on the defect type code and spatial coordinates in the feature tensor; The time interval from the welding timestamp to the defect elimination timestamp of the same defect type code in the grid unit is taken as the single defect disposal aging interval. The disposal aging interval of each defect type in each grid unit is collected as the defect disposal aging interval data.

3. The gas engineering construction quality assessment system based on big data according to claim 2 is characterized by: The location defect recurrence frequency data is specifically referred to the following analysis process: recording the time and type of each defect occurrence in the same grid unit within a preset time window, introducing a time attenuation factor and a defect type weight factor for weighting, and obtaining the defect recurrence frequency in the same grid unit; Count the number of covered grid cells of the same defect type within the preset time window, and use the ratio of the covered grid cells to the total number of three-dimensional space grid cells as the location recurrence frequency of the same defect type; The defect recurrence frequency of each grid unit within the preset time window and the location recurrence frequency of each defect type are collected and used together as the location defect recurrence frequency data.

4. The gas engineering construction quality assessment system based on big data according to claim 3 is characterized by: The preset quality, efficiency and reliability quantification rules include the following: obtaining the corresponding score values ​​of each grid unit, each defect type and each treatment time interval through a preset score mapping table, and obtaining the timeliness score through layered averaging and normalization processing; The average defect recurrence frequency of the grid cells and the average location recurrence frequency of the defect type within the preset time window are respectively substituted into the preset penalty function to quantify the grid recurrence degradation value and the type diffusion degradation value. The higher of the two-dimensional degradation values ​​is taken and the higher value is deducted from the initial stability full score to obtain the stability score. The sum of the timeliness score and the stability score is taken as the quality and effectiveness score.

5. The gas engineering construction quality assessment system based on big data according to claim 4 is characterized by: The preset scoring mapping table includes a nonlinear mapping relationship between the processing time interval of each defect type and the scoring value.

6. The gas engineering construction quality assessment system based on big data according to claim 1 is characterized by: The spatiotemporal correlation matrix establishes a mapping relationship between each welding defect and the corresponding process environment condition by aligning the spatiotemporal of the welding process parameters and the environmental monitoring parameters.

7. The gas engineering construction quality assessment system based on big data according to claim 1 is characterized by: The adaptability of the target welding variable and its strongly associated environmental variables is specifically described in the following output process: if the actual value of the target welding variable is within its process adaptation interval, the adaptability of the target welding variable and its strongly associated environmental variables is output as 1; If the actual value of the target welding variable is outside its process adaptation interval, the deviation amplitude of the actual value of the target welding variable and its process adaptation interval is quantified, and the negative form of the deviation amplitude is introduced into the natural exponential function to solve the fitness of the target welding variable and its strongly associated environmental variables.

8. The gas engineering construction quality assessment system based on big data according to claim 1 is characterized by: The preset process compliance quantification rules include the following: according to the preset defect-process correlation index interval, the preset environment-process adaptability index interval and the preset process score value corresponding to each process level ladder, the defect-process correlation index and the environment-process adaptability index analyzed in the spatiotemporal correlation matrix are respectively determined to correspond to the process level ladder, and the preset process score values ​​of the process level ladder corresponding to the interval of the dual indicators are weighted according to the preset weight ratio to obtain the process score.

Images