Weld joint key failure factor extraction method and system, electronic equipment and storage medium
The correlation and importance of the weld failure factors are calculated by Pearson's correlation coefficient method and the random forest model, and the key failure factors of the pipeline ring weld are identified, which solves the problem of difficulty in accurately identifying the weld failure factors in the existing technology, and improves the problem of improving The accuracy of weld risk control and pipeline safety are provided.
Patent Information
- Application Number
- CN202411176077.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2025-01-07
AI Technical Summary
The prior art is difficult to accurately identify and predict key failure factors of pipeline ring welds, resulting in weld failures may lead to accidents and economic losses.
The Pearson correlation coefficient method and the trained random forest model were used to calculate the correlation and importance between each preset failure factor of the weld and the detection level, and the key failure factors were determined by sorting.
Accurate identification and control of weld risks is achieved, pipeline safety is improved, and the possibility of weld failure is reduced.
Smart Images
Figure CN119272159A_ABST
Abstract
Description
Background Art
[0002] The girth weld on the pipeline is the weak link of the pipeline connection, and its quality is directly related to the safety and stability of the entire pipeline system. In actual projects, accidents caused by abnormal girth welds on the pipeline, such as pipeline leakage, will pose a serious threat to the environment and pipeline safety. In the construction and operation of pipelines, various factors will affect the quality of the girth welds on the pipeline. For example, welding environment, welding equipment and welding process. At the same time, due to some factors such as girth weld cracks and girth weld fatigue, the girth weld on the pipeline will inevitably fail, which will affect the normal operation of the pipeline and cause economic losses. Therefore, it is of great significance to accurately identify the key factors affecting weld failure and avoid the occurrence of girth weld failure on the pipeline. Summary of the invention
[0003] The technical problem to be solved by the present invention is to address the deficiencies of the prior art and specifically provide a method, system, electronic device and storage medium for extracting key failure factors of welds, as follows:
[0004] 1) In the first aspect, the present invention provides a method for extracting key failure factors of welds, and the specific technical scheme is as follows:
[0005] Calculate the correlation between each preset failure factor of the weld and the weld detection level, and sort all the preset failure factors according to the correlation to obtain a first sequence; calculate the importance of each preset failure factor to the weld, and sort all the preset failure factors according to the importance to obtain a second sequence;
[0006] Based on the first sequence and the second sequence, the key failure factors of the weld are determined.
[0007] The beneficial effects of the method for extracting key failure factors of welds provided by the present invention are as follows:
[0008] By calculating the impact of preset failure factors on welds through two different algorithms and comparing them, the key failure factors of welds can be accurately determined, which can effectively guide the prevention and control of weld risks.
[0009] On the basis of the above scheme, a method for extracting key failure factors of welds of the present invention can also be improved as follows.
[0010] Furthermore, the correlation between each preset failure factor of the weld and the weld inspection level is calculated, including:
[0011] The Pearson correlation coefficient method is used to calculate the Pearson correlation coefficient between each preset failure factor of the weld and the weld inspection level, and the Pearson correlation coefficient is used to characterize the degree of correlation.
[0012] Furthermore, the importance of each preset failure factor to the weld is calculated, including:
[0013] The trained random forest model is used to calculate the importance of each preset failure factor to the weld.
[0014] Further, the weld is a girth weld on the pipeline.
[0015] 2) In the second aspect, the present invention also provides a weld key failure factor extraction system, and the specific technical solution is as follows:
[0016] It includes a first calculation module, a second calculation module, a sorting module and a key failure factor determination module;
[0017] The first calculation module is used to calculate the correlation between each preset failure factor of the weld and the weld detection level;
[0018] The second calculation module is used to: calculate the importance of each preset failure factor to the weld;
[0019] The sorting module is used to: sort all the preset failure factors according to the degree of relevance to obtain a first sequence, and sort all the preset failure factors according to the degree of importance to obtain a second sequence;
[0020] The key failure factor determination module is used to determine the key failure factors of the weld according to the first sequence and the second sequence.
[0021] On the basis of the above scheme, the critical failure factor extraction system of a weld of the present invention can also be improved as follows.
[0022] Furthermore, the first calculation module is used to: use the Pearson correlation coefficient method to calculate the Pearson correlation coefficient between each preset failure factor of the weld and the weld detection level, and use the Pearson correlation coefficient to characterize the degree of correlation.
[0023] Furthermore, the second computing module is used for:
[0024] The trained random forest model is used to calculate the importance of each preset failure factor to the weld.
[0025] Further, the weld is a girth weld on the pipeline.
[0026] 3) In a third aspect, the present invention further provides an electronic device, comprising a processor, the processor being coupled to a memory, the memory storing at least one computer program, the at least one computer program being loaded and executed by the processor, so that the electronic device implements any of the above-mentioned methods for extracting key failure factors of welds.
[0027] 4) In a fourth aspect, the present invention further provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is loaded and executed by a processor so that a computer implements any of the above-mentioned methods for extracting key failure factors of welds.
[0028] It should be noted that the beneficial effects achieved by the technical solutions of the second to fourth aspects of the present invention and the corresponding possible implementation methods can be found in the above-mentioned technical effects of the first aspect and its corresponding possible implementation methods, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:
[0030] Figure 1 A schematic diagram of a flow chart of a method for extracting key failure factors of a weld according to an embodiment of the present invention;
[0031] Figure 2 Schematic diagram of failure factors of girth weld during construction / operation period;
[0032] Figure 3 Schematic diagram of random forest importance ranking of each preset failure factor and weld inspection level;
[0033] Figure 4 A structural schematic diagram of a weld key failure factor extraction system according to an embodiment of the present invention;
[0034] Figure 5 The figure is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0035] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.
[0036] like Figure 1 As shown, a method for extracting key failure factors of welds according to an embodiment of the present invention comprises the following steps:
[0037] S1. Calculate the correlation between each preset failure factor of the weld and the weld detection level, and sort all the preset failure factors according to the correlation to obtain a first sequence; calculate the importance of each preset failure factor to the weld, and sort all the preset failure factors according to the importance to obtain a second sequence;
[0038] Among them, two different artificial intelligence algorithms can be used to calculate the correlation between each preset failure factor of the weld and the weld detection level and the importance of each preset failure factor to the weld. The two different artificial intelligence algorithms can be trained neural networks, trained support vector machines, etc.
[0039] S2. Determine the key failure factors of the weld based on the first sequence and the second sequence.
[0040] For example, there are five preset failure factors, which are recorded as the first preset failure factor, the second preset failure factor, the third preset failure factor, the fourth preset failure factor and the fifth preset failure factor. Then:
[0041] 1) For example, in descending order of relevance, the first sequence is: the first preset failure factor, the second preset failure factor, the third preset failure factor, the fourth preset failure factor and the fifth preset failure factor; in descending order of importance, the second sequence is: the first preset failure factor, the second preset failure factor, the third preset failure factor, the fourth preset failure factor and the fifth preset failure factor. Since the first sequence and the second sequence are the same, the first n preset failure factors in the first sequence can be used as key failure factors, where n is a positive integer and n is less than the total number of preset failure factors.
[0042] 2) For example, in descending order of relevance, the first sequence is: the first preset failure factor, the second preset failure factor, the third preset failure factor, the fourth preset failure factor and the fifth preset failure factor; in descending order of importance, the second sequence is: the second preset failure factor, the first preset failure factor, the third preset failure factor, the fourth preset failure factor and the fifth preset failure factor, then the first two preset failure factors can be regarded as key failure factors.
[0043] 3) For example, in descending order of relevance, the first sequence obtained is: the first preset failure factor, the second preset failure factor, the third preset failure factor, the fourth preset failure factor and the fifth preset failure factor; in descending order of importance, the second sequence obtained is: the fifth preset failure factor, the fourth preset failure factor, the third preset failure factor, the second preset failure factor and the first preset failure factor, indicating that there may be problems with the two different algorithms used. At this time, the algorithm can be upgraded, and subsequent operations such as re-sorting can be performed.
[0044] Optionally, in S1, calculating the correlation between each preset failure factor of the weld and the weld detection level includes:
[0045] S11. Using the Pearson correlation coefficient method, calculate the Pearson correlation coefficient between each preset failure factor of the weld and the weld inspection level, and use the Pearson correlation coefficient to characterize the degree of correlation.
[0046] Among them, the value range of the Pearson correlation coefficient is [-1,1]. If the Pearson correlation coefficient between any preset failure factor and the weld detection level is negative, it means that the preset failure factor and the weld detection level are negatively correlated; when the Pearson correlation coefficient is -1, it indicates a complete negative correlation; if the Pearson correlation coefficient between any preset failure factor and the weld detection level is positive, it means that the preset failure factor and the weld detection level are positively correlated; when the Pearson correlation coefficient is 1, it indicates a complete positive correlation; if the Pearson correlation coefficient between any preset failure factor and the weld detection level is 0, it means that there is no linear correlation between the preset failure factor and the weld detection level; the larger the Pearson correlation coefficient, the greater the degree of correlation and the greater the degree of influence on the weld.
[0047] Optionally, in S1, calculating the importance of each preset failure factor to the weld includes:
[0048] The trained random forest model is used to calculate the importance of each preset failure factor to the weld.
[0049] Optionally, in the above technical solution, the weld is a girth weld on the pipeline.
[0050] Optionally, in the above technical solution, after the key failure factors of the weld are determined, the key failure factors are analyzed to reduce the impact of the key failure factors on the weld.
[0051] Optionally, in the above technical solution, there are 10 preset failure factors: film missing, geological disasters, penetration, cutting, elbow, joint, short section, pipe section length, connection and repair opening.
[0052] With the development of data analysis algorithms, data analysis algorithms have shown powerful performance in the fields of characteristic factor identification and failure prediction. There are many factors for the failure of girth welds, which involves the evaluation and analysis of massive pipeline data. Therefore, based on the data analysis algorithm, the present invention proposes a characteristic factor identification framework, which can quickly and effectively identify the characteristic factors that have a significant impact on the quality of the weld, i.e., the key failure factors. The effectiveness of this method is verified based on historical data.
[0053] Since there are many factors causing girth weld failure, it involves the evaluation and analysis of massive pipeline data. The present invention uses the III / IV girth weld detected by radiography as the abnormal weld, and uses two sets of artificial intelligence algorithms to analyze and compare the main features of the abnormal weld, thus ensuring the reliability of the evaluation results.
[0054] The present invention proposes a method for extracting key failure factors of welds. The algorithm jointly uses two sets of algorithms (Pearson correlation coefficient method and trained random forest model) and conducts comparative verification, which solves the problem that key characteristic indicators of abnormal welds are difficult to mine, realizes the online identification of key indicators (key failure factors) of abnormal pipeline welds, and can effectively guide the prevention and control of weld risks.
[0055] The present invention first uses the trained random forest model to calculate the importance of each preset failure factor to the weld. However, considering that the importance calculated by the trained random forest model can only evaluate the importance of each preset failure factor to the weld, it is not possible to clarify the specific impact of each preset failure factor on the weld. Therefore, based on the random forest evaluation result, the Pearson correlation coefficient method is further used to calculate the correlation coefficient of each preset failure factor relative to the weld, that is, the Pearson correlation coefficient, to clarify the specific impact of each preset failure factor on the weld, and to verify each other with the random forest evaluation result.
[0056] In another embodiment, the steps include:
[0057] S101. The Pearson correlation coefficient method calculates the correlation coefficient between the independent variable (preset failure factor) and the target variable (weld inspection level), namely the Pearson correlation coefficient.
[0058] S102. Calculate the Pearson correlation coefficient r between each preset failure factor and the weld detection level through S101. r represents the correlation between the preset failure factor and the abnormal weld, and its value range is between -1 and 1. -1 represents a complete negative correlation, 1 represents a complete positive correlation, and 0 represents no linear correlation. The larger the r value, the greater the correlation between each factor and the weld detection level, and the greater the impact on the abnormal weld.
[0059] S103. Use the pandas module to import data and call the corr function to calculate the correlation coefficients between each pair of data columns.
[0060] S104. Establish a random forest model to evaluate the importance of each preset failure factor to the weld.
[0061] S105. Use the pandas module to import data and build a random forest model based on the sklearn library.
[0062] S106. Select the target variable, and select the data from the first column in the imported data to the last column in the imported data as the independent variable.
[0063] S107. Create a random forest model.
[0064] S108. Print the random forest feature importance.
[0065] S109. Compare and verify the evaluation results of the Pearson correlation coefficient and the random forest importance ranking, and output the correlation ranking and importance ranking of the key factors of abnormal welds.
[0066] S101 includes the following steps:
[0067] Suppose there are two variables X and Y, containing n data points, namely X1, X2, ..., X n , and Y1,Y2,...,Y n .
[0068] S1011, Utilization Calculate the mean of variable X use Calculate the mean of variable Y
[0069] S1012, Utilization and Calculate the difference between each data point and the mean.
[0070] S1013, using ∑dX i .dY i Compute the sum of the products of the differences.
[0071] S1014, using ∑(dX i ) 2 andΣ(dY i ) 2 Calculate the sum of the squares of the differences.
[0072] S1015, Use Calculate the Pearson correlation coefficient.
[0073] S104 includes the following steps:
[0074] S1041. For each decision tree in the random forest, the corresponding OOB (out-of-bag) data is used to calculate the out-of-bag data error, denoted as errOOB1.
[0075] S1042. Randomly change a feature of all samples of the out-of-bag data OOB, and calculate the out-of-bag data error again, recorded as errOOB2.
[0076] S1043. Assuming there are N trees in the random forest, the importance of feature X is:
[0077]
[0078] In another embodiment, comprising:
[0079] Step 1: Data from the construction and operation period of a pipeline were collected, with a total of 2920 valid data for model training. The abnormal welds (III / IV defects) detected by excavation were used as the correlation analysis criteria, and random forest importance ranking and Pearson correlation coefficient analysis were performed. Figure 2 The Pearson correlation coefficient method is used to calculate the correlation coefficient between each preset failure factor and the weld inspection level, and the results are shown in Table 1.
[0080] Table 1:
[0081] Preset failure factors Pearson correlation coefficient Positive correlation / negative correlation Negatives missing 0.0042 Positive correlation Geological disasters 0.0105 Positive correlation Crossing 0.0117 Positive correlation Cutting 0.0248 Positive correlation Elbow 0.0254 Negative correlation Chrysostom 0.0311 Positive correlation Short section 0.0321 Positive correlation Pipe length 0.0366 Negative correlation Connection port 0.0436 Positive correlation Repair port 0.0703 Positive correlation
[0082] According to Table 1, the Pearson correlation coefficient analysis identified 10 characteristic factors that significantly affect the weld inspection level, namely the preset failure factors, among which the "repair opening" has the greatest impact. The correlation coefficient is 0.07, and the positive correlation indicates that the presence of a "repair opening" will increase the probability of abnormal weld inspection level.
[0083] The analysis code of the Pearson correlation coefficient method is as follows:
[0084] 1. import numpy as np;
[0085] 2. import pandas as pd;
[0086] 3.df1 = pd.read_csv(r'processed1.csv')#Import data;
[0087] 4.df1;
[0088] 5.import matplotlib.pyplot as plt;
[0089] 6. import seaborn as sns;
[0090] 7. import matplotlib as mpl;
[0091] 8.plt.rcParams['font.sans-serif']=['simhei'];
[0092] 9.plt.rcParams['axes.unicode_minus']=False;
[0093] 10.corr = df1.corr();
[0094] 11.corr#Calculate the correlation coefficient;
[0095] 12.f,ax=plt.subplots(figsize=(10,8));
[0096] 13.ax=sns.heatmap(corr,cmap='RdBu',ax=ax,vmin=-1,vmax=1,annot=True,fmt='0.1g')#Visualization of correlation coefficient.
[0097] Step 2: Calculate the importance of each preset failure factor and weld inspection level based on random forest importance ranking.
[0098] like Figure 3 As shown in the figure, 10 characteristic factors with significant impact on weld inspection level were identified using random forest importance ranking, among which the most influential one was "repair opening". The importance was 0.7, which was consistent with the Pearson correlation coefficient analysis result, verifying the effectiveness of the identification method.
[0099] Combining Pearson correlation coefficient analysis with random forest importance ranking, the key factors affecting abnormal welds are: "segment length", "film loss", "elbow mouth", "geological disaster", "connection mouth", "repair mouth", "through mouth", "cut mouth", "gold mouth" and "short joint".
[0100] Random forest importance ranking code:
[0101] 1.from sklearn.ensemble import RandomForestClassifier;
[0102] 2. import pandas as pd;
[0103] 3. import numpy as np;
[0104] 4.data = pd.read_csv(r"wv.csv")#The data format is csv utf-8;
[0105] 5.print(data)#output data;
[0106] 6.y=data.iloc[:,-1]#Select the last column of the given data set uploaded as the target variable;
[0107] 7.X = data.iloc[:,1:-1];
[0108] 8.rf = RandomForestClassifier (n_estimators = 100, random_state = 0) # Create a random forest classifier;
[0109] 9.rf.fit(X,y);
[0110] 10.importance_scores=rf.feature_importances;
[0111] 11.feature_importance_dict={};
[0112] 12.for feature,importance in zip(X.columns,importance_scores);
[0113] 13.feature_importance_dict[feature]=importance;
[0114] 14. sorted_feature_importance = sorted(feature_importance_dict.items(), key = lambdax:x[1], reverse = True) # Sort the importance scores and simply sort the selected features from the highest to the lowest importance scores;
[0115] 15.for feature,importance in sorted_feature_importance;
[0116] 16.print(f"{feature}:{importance:.4f}")#Print the importance ranking of features.
[0117] The method for extracting key failure factors of welds of the present invention is specifically an algorithm for extracting key failure factors of girth welds based on Pearson correlation coefficient analysis and random forest importance, and has the following beneficial effects:
[0118] The present invention identifies the key influencing factors of abnormal welds based on the Pearson correlation coefficient and random forest importance ranking. The algorithm can realize the evaluation of massive multi-dimensional data of pipeline girth welds, has high recognition efficiency, is easy to operate, and does not require professionals to interpret the results.
[0119] In the above embodiments, although the steps are numbered S1, S2, etc., these are only specific embodiments given by the present invention. Those skilled in the art may adjust the execution order of S1, S2, etc. according to actual conditions, which is also within the protection scope of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.
[0120] like Figure 4 As shown, a weld key failure factor extraction system 200 according to an embodiment of the present invention includes a first calculation module 201, a second calculation module 202, a sorting module 203 and a key failure factor determination module 204;
[0121] The first calculation module 201 is used to calculate the correlation between each preset failure factor of the weld and the weld detection level;
[0122] The second calculation module 202 is used to calculate the importance of each preset failure factor to the weld;
[0123] The sorting module 203 is used to sort all the preset failure factors according to the degree of relevance to obtain a first sequence, and sort all the preset failure factors according to the degree of importance to obtain a second sequence;
[0124] The critical failure factor determination module 204 is used to determine the critical failure factors of the weld according to the first sequence and the second sequence.
[0125] Optionally, in the above technical solution, the first calculation module 201 is used to: use the Pearson correlation coefficient method to calculate the Pearson correlation coefficient between each preset failure factor of the weld and the weld detection level, and use the Pearson correlation coefficient to characterize the degree of correlation.
[0126] Optionally, in the above technical solution, the second calculation module 202 is used for:
[0127] The trained random forest model is used to calculate the importance of each preset failure factor to the weld.
[0128] Optionally, in the above technical solution, the weld is a girth weld on the pipeline.
[0129] It should be noted that the beneficial effects of a weld key failure factor extraction system 200 provided in the above embodiment are the same as the beneficial effects of the above weld key failure factor extraction method, which will not be repeated here. In addition, when the system provided in the above embodiment realizes its functions, it only takes the division of the above functional modules as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to actual conditions to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.
[0130] like Figure 5 As shown, an electronic device 300 of an embodiment of the present invention includes a processor 320, the processor 320 is coupled to a memory 310, and the memory 310 stores at least one computer program 330, and the at least one computer program 330 is loaded and executed by the processor 320, so that the electronic device 300 implements any of the above-mentioned weld key failure factor extraction methods, specifically:
[0131] The electronic device 300 may have relatively large differences due to different configurations or performances, and may include one or more processors 320 (Central Processing Units, CPU) and one or more memories 310, wherein at least one computer program 330 is stored in the one or more memories 310, and the at least one computer program 330 is loaded and executed by the one or more processors 320, so that the electronic device 300 implements any of the weld key failure factor extraction methods provided in the above embodiments. Of course, the electronic device 300 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output. The electronic device 300 may also include other components for realizing the functions of the device, which will not be repeated here. The electronic device may specifically be a computer, etc.
[0132] A computer-readable storage medium according to an embodiment of the present invention stores at least one computer program, and the at least one computer program is loaded and executed by a processor so that a computer implements any of the above-mentioned methods for extracting key failure factors of welds.
[0133] Optionally, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.
[0134] In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes any of the above-mentioned methods for extracting critical failure factors of welds.
[0135] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects and represent the definition of a specific order or sequence. The order of use of similar objects can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than the order shown or described.
[0136] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.
[0137] Any combination of one or more computer-readable media can be used. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.
[0138] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.
Claims
1. A method for extracting key failure factors of welds, characterized in that: include: Calculate the correlation between each preset failure factor of the weld and the weld detection level, and sort all the preset failure factors according to the correlation to obtain a first sequence; calculate the importance of each preset failure factor to the weld, and sort all the preset failure factors according to the importance to obtain a second sequence; According to the first sequence and the second sequence, a key failure factor of the weld is determined.
2. A method for extracting key failure factors of welds according to claim 1, characterized in that: Calculate the correlation between each preset failure factor of the weld and the weld inspection level, including: The Pearson correlation coefficient method is used to calculate the Pearson correlation coefficient between each preset failure factor of the weld and the weld detection level, and the Pearson correlation coefficient is used to characterize the correlation degree.
3. A method for extracting key failure factors of welds according to claim 1, characterized in that: Calculate the importance of each pre-set failure factor to the weld, including: The trained random forest model is used to calculate the importance of each preset failure factor to the weld.
4. A method for extracting key failure factors of welds according to any one of claims 1 to 3, characterized in that: The weld is a girth weld on the pipeline.
5. A weld key failure factor extraction system, characterized in that: It includes a first calculation module, a second calculation module, a sorting module and a key failure factor determination module; The first calculation module is used to calculate the correlation between each preset failure factor of the weld and the weld detection level; The second calculation module is used to: calculate the importance of each preset failure factor to the weld; The sorting module is used to sort all the preset failure factors according to the degree of relevance to obtain a first sequence, and sort all the preset failure factors according to the degree of importance to obtain a second sequence; The critical failure factor determination module is used to determine the critical failure factor of the weld according to the first sequence and the second sequence.
6. A weld key failure factor extraction system according to claim 5, characterized in that: The first calculation module is used to: use the Pearson correlation coefficient method to calculate the Pearson correlation coefficient between each preset failure factor of the weld and the weld detection level, and use the Pearson correlation coefficient to characterize the degree of correlation.
7. A weld key failure factor extraction system according to claim 5, characterized in that: The second calculation module is used for: The trained random forest model is used to calculate the importance of each preset failure factor to the weld.
8. A weld key failure factor extraction system according to any one of claims 5 to 7, characterized in that: The weld is a girth weld on the pipeline.
9. An electronic device, characterized in that: The electronic device includes a processor, the processor is coupled to a memory, at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor so that the electronic device implements a method for extracting key failure factors of welds as described in any one of claims 1 to 4.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one computer program, and the at least one computer program is loaded and executed by a processor so that the computer implements a method for extracting key failure factors of welds as claimed in any one of claims 1 to 4.