Detection probability verification method of internal detector and related equipment
By constructing a multi-parameter detection probability prediction calculation model and adjusting its parameters, the problem of inaccurate detection probability evaluation of internal detectors is solved, and accurate verification of internal detector performance and improvement of detection effect is achieved.
Patent Information
- Application Number
- CN202310490999.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-04
- Publication Date
- 2024-11-05
AI Technical Summary
The prior art cannot accurately evaluate and verify the detection probability of the detector within it, making it difficult to determine its reliability of detecting defects in actual pipelines.
By obtaining the detection data of the pipeline and mining data, a multi-parameter detection probability prediction calculation model is built, the model parameters are adjusted using logarithmic logic and maximum likelihood estimation algorithm, and finally the performance of the detector is verified based on the adjusted model.
It realizes an accurate evaluation of the performance of the internal detector, ensures that its detection effect meets the detection probability standards provided by the detector, and improves the accuracy and reliability of the detection.
Smart Images

Figure CN118897944A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of in-pipeline detection, and in particular to a detection probability verification method of an in-pipe detector and related equipment. Background Art
[0002] The probability of detection (POD) represents the ability of pipeline internal detectors to detect defects, and is also a key technical indicator for measuring internal detectors. The detection probability of pipeline internal detectors is generally given by the manufacturer when the instrument leaves the factory. The supplier of the internal detector sets the detection probability value of the internal detector based on the detection probability of the minimum defect that the internal detector can detect. The detection probability of the internal detector is generally determined by comparing the detection data of a certain section of the pipe obtained by the internal detector with the excavation verification data of this section of the pipe.
[0003] Since the internal detector is provided by the manufacturer, due to different testing environments and pipeline materials, this value is usually different from the detection probability in actual pipeline operation. Therefore, it is a difficult problem for enterprises to determine whether the internal detector is reliable and whether the actual detection probability of defects meets the theoretical detection probability value provided by the testing company. Summary of the invention
[0004] The present invention provides a detection probability verification method of an internal detector and related equipment, which are used to solve the problem in the prior art that the detection probability of the internal detector cannot be accurately evaluated and verified.
[0005] The present invention provides a detection probability verification method of an internal detector, comprising:
[0006] Acquiring detection data of the pipeline based on the internal detector, and acquiring excavation data of the pipeline;
[0007] Constructing a detection probability prediction calculation model, and obtaining model parameters of the detection probability prediction calculation model based on the detection data and the excavation data;
[0008] According to the model parameters, adjusting the detection probability prediction calculation model;
[0009] The internal detector is verified based on the adjusted detection probability prediction calculation model.
[0010] According to a detection probability verification method of an internal detector provided by the present invention, the acquisition of pipeline detection data obtained based on the internal detector and the excavation data of the pipeline includes:
[0011] Identify the pipeline used to perform the test;
[0012] Conduct defect detection on pipelines based on internal detectors and analyze to obtain detection data;
[0013] Defect excavation is performed on the pipeline according to the detection data, and real defect data of the pipeline is collected to obtain excavation data.
[0014] According to a detection probability verification method of an internal detector provided by the present invention, the construction of a detection probability prediction calculation model and obtaining model parameters of the detection probability prediction calculation model based on the detection data and the excavation data include:
[0015] According to the logarithmic logic of multiple parameters, a multi-parameter detection probability prediction calculation model is constructed, wherein the input quantity of the detection probability prediction calculation model includes at least the depth, length and width of the defect;
[0016] The parameters in the multi-parameter detection probability prediction calculation model are predicted based on the detection data and the excavation data to obtain estimated values of the parameters in the detection probability prediction calculation model.
[0017] According to a detection probability verification method of an internal detector provided by the present invention, the prediction of parameters in the multi-parameter detection probability prediction model is performed based on the detection data and the excavation data to obtain parameter estimation values in the detection probability prediction calculation model, including:
[0018] Comparing the detection data with the excavation data to obtain a detection result corresponding to each defect;
[0019] A likelihood function including each parameter in the detection probability prediction calculation model is constructed, and each parameter in the likelihood function is estimated according to the detection result using a maximum likelihood estimation algorithm to obtain estimated values of the parameters of the detection probability prediction calculation model.
[0020] According to a detection probability verification method of an internal detector provided by the present invention, the detection data is compared with the excavation data to obtain the detection state corresponding to each defect, including:
[0021] Matching the detection data with the excavation data to obtain the detection status of the defects contained in the excavation data, wherein the detection status includes detected and undetected;
[0022] The defects are marked according to the detection status, and a detection result of each defect is determined, wherein the detection result includes defect information of the defect and the detection status, and the defect information includes at least the depth, length and width of the defect.
[0023] According to a detection probability verification method of an internal detector provided by the present invention, the internal detector is verified according to the adjusted detection probability prediction calculation model, including:
[0024] Obtaining the factory detection probability of the internal detector;
[0025] Simplifying the detection probability prediction calculation model to obtain a detection probability prediction model with the independent variable being the defect size relationship, wherein the size relationship is a power relationship between the depth, length, width of the defect and the corresponding parameter estimation value;
[0026] According to the factory detection probability and the simplified detection probability prediction calculation model, a calculated value of the size relationship of the defects that can be detected in the pipeline is calculated;
[0027] Comparing the calculated value of the detectable defect size relationship with a target calculated value of the defect size of the target defect to be verified, calculated based on the size relationship, to verify the internal detector;
[0028] If the target calculated value is greater than or equal to the calculated value, then it is determined that the verification is passed;
[0029] If the target calculated value is less than the calculated value, it is determined that the verification fails.
[0030] According to a detection probability verification method of an internal detector provided by the present invention, after calculating the calculated value of the size relationship of the detectable defects in the pipeline according to the factory detection probability and the simplified detection probability prediction calculation model, it also includes:
[0031] Determining a parameter in the defect size of the target defect as a fixed parameter, and obtaining a two-dimensional curve of the defect size based on the calculated value and the fixed parameter;
[0032] According to the defect size and the fixed parameters, the size coordinates of the target defect are obtained;
[0033] The internal detector is verified based on the comparison between the size coordinates and the two-dimensional curve.
[0034] The present invention also provides a detection probability verification device for an internal detector, comprising:
[0035] A data acquisition module, used to acquire detection data of the pipeline based on the internal detector, and to acquire excavation data of the pipeline;
[0036] A parameter determination module constructs a detection probability prediction calculation model and obtains model parameters of the detection probability prediction calculation model based on the detection data and the excavation data;
[0037] A model adjustment module, used to adjust the detection probability prediction calculation model according to the model parameters;
[0038] A verification processing module is used to verify the internal detector according to the adjusted detection probability prediction calculation model.
[0039] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a detection probability verification method of an internal detector as described in any one of the above-mentioned methods is implemented.
[0040] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a detection probability verification method for an internal detector as described in any one of the above.
[0041] The detection probability verification method and related equipment of the internal detector provided by the present invention, when verifying the internal detector, first obtain the detection data obtained by the internal detector in the pipeline, and at the same time obtain the excavation data corresponding to the pipeline, wherein the excavation data is the actual defect data of the pipeline, and then build a multi-parameter detection probability calculation model based on logarithmic logic, and then determine the model parameters of the detection probability calculation model according to the obtained detection data and excavation data to adjust the detection probability calculation model, and finally complete the verification of the internal detector according to the adjusted detection probability calculation model. It is realized that the detection probability calculation model for accuracy verification of the internal detector is built based on the actual data of the internal detector and the excavation data of the pipeline, so as to accurately evaluate the performance of the internal detector. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0043] Figure 1 It is a flow chart of the detection probability verification method of the internal detector provided by the present invention;
[0044] Figure 2 It is a flow chart of the steps of obtaining model parameters provided by the present invention;
[0045] Figure 3 It is a schematic diagram of the curve relationship between the detection probability and the defect size provided by the present invention;
[0046] Figure 4 It is a schematic diagram of the curve relationship corresponding to the verification conditions provided in this application;
[0047] Figure 5 It is a structural schematic diagram of the detection probability verification device of the internal detector provided by the present invention;
[0048] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION
[0049] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.
[0050] Combine the following Figure 1-Figure 4 The detection probability verification method of the internal detector of the present invention is described. The internal detector will be provided with corresponding detection information when leaving the factory, such as the detection probability of corrosion defects of the pipeline, including corrosion defects of different sizes, where the different sizes include depth, length and width. Since the detection probability of the internal detector is provided by the manufacturer, in order to ensure the accuracy of its detection, it needs to be verified after the internal detection to ensure that the actual detection effect of the internal detector meets the detection probability standard provided by the detection provider.
[0051] Figure 1 FIG. 1 is a flow chart of the detection probability verification method of the internal detector provided by the present invention. Figure 1 As shown, the method includes:
[0052] Step 101, obtaining pipeline detection data based on an internal detector, and obtaining pipeline excavation data.
[0053] Among them, the probability of detection (POD) represents the probability of the internal detector in the pipeline detecting a defect, and is also a key technical indicator for measuring the internal detector. The pipeline excavation verification data can be used to evaluate the detection effect of the internal detector in the actual working environment. Before conducting the internal inspection, the inspection company will provide parameters such as the detection probability of the internal detector according to the requirements of the pipeline operating unit. Therefore, further excavation verification is required to determine the actual ability of the internal detector to detect defects based on the actual inspection data of the internal detector and the actual corrosion conditions of the pipeline, thereby ensuring that the internal detector accurately completes the defect detection during use.
[0054] Specifically, before verification, first obtain the pipeline inspection data and pipeline excavation data based on the internal detector, wherein the inspection data is the data obtained by inspection based on the internal detector, and the excavation data is the real data of defects obtained by excavating and verifying the pipeline based on the inspection data, such as the specific location of the defect in the pipeline and the specific size of the defect.
[0055] Exemplarily, when obtaining the inspection data and excavation data of the pipeline, the pipeline to be inspected is first determined, and the inspection data and excavation data are obtained through actual inspection and acquisition of real data, which specifically includes: determining the pipeline to be inspected; performing defect detection on the pipeline based on an internal detector, and analyzing it to obtain inspection data; and verifying the excavation of the pipeline based on the inspection data, and collecting excavation data.
[0056] When the internal detector moves in the pipeline for detection, it detects defects of different sizes in the pipeline, and the defects that can be detected will be recorded, while the defects that are too small to be detected will not be recorded. That is, the obtained detection data are the defects that can be detected, and the position and size information of the detected defects in the pipeline can also be obtained, wherein the size information at least includes the depth, length and width of the defect.
[0057] The excavation data of the pipeline contains relevant information about the actual defects obtained by excavating and verifying some of the detected defects on the pipeline. The excavation data includes two situations: defects detected by the detector after excavation verification and defects discovered through excavation that were missed by the detector. The excavation data also includes defect size information and location information.
[0058] Step 102: construct a detection probability prediction calculation model, and obtain model parameters of the detection probability prediction calculation model based on the detection data and excavation data.
[0059] First, a corresponding detection probability prediction calculation model is constructed, and then the relevant model parameters of the detection probability prediction calculation model are determined. Specifically, after the detection probability prediction calculation model is constructed, the model parameters of the detection probability prediction calculation model are optimized and determined according to the detection data and excavation data. For example, the specific values of the model parameters of the detection probability prediction calculation model can be calculated according to the set relevant calculation method.
[0060] Furthermore, when constructing the detection probability calculation model, the optimal detection probability calculation model can be constructed according to the characteristics between the data, and then the specific values of each model parameter in the model can be determined. Specifically, when constructing the detection probability calculation model and processing to obtain the model parameters, reference can be made to Figure 2 , Figure 2It is a flowchart of the steps of obtaining model parameters provided by the present invention, wherein the steps include steps 201 to 202.
[0061] Step 201, constructing a multi-parameter detection probability calculation model according to multi-parameter logarithmic logic, wherein the input quantity of the detection probability prediction calculation model at least includes the depth, length and width of the defect;
[0062] Step 202: predict the parameters in the multi-parameter detection probability prediction calculation model based on the detection data and the excavation data to obtain the estimated values of the parameters in the detection probability calculation model.
[0063] Specifically, when constructing the detection probability calculation model, the corresponding detection probability calculation model is constructed according to the logarithmic logic of multiple parameters, and then the parameters are calculated according to the detection data and the excavation data to obtain the model parameters of the detection probability calculation model.
[0064] For example, when constructing the detection probability calculation model, through statistics and analysis of defect data, it can be found that the distribution of the length, width and depth of the defect conforms to the log-normal distribution, and the effects of the length, width and depth of the defect on the detection probability are independent of each other. Therefore, when constructing the detection probability calculation model, the detection probability calculation model is associated with the depth, length and depth of the corrosion defect, that is, the depth, length and width of the corrosion defect are used as the input of the detection probability calculation model, and the detection probability is used as the output of the model.
[0065] The detection probability calculation model constructed using multi-parameter logarithmic logic is:
[0066]
[0067] Among them, d is the depth of the corrosion defect, l is the length of the corrosion defect, w is the width of the corrosion defect, and a0, a1, a2, and a3 are model parameters that need to be calculated in the detection probability calculation model. The advantage of this detection probability calculation model is that the curve of the detection probability can be determined, and the estimated value is always less than 1. The detection probability obtained by this type of data model is a conservative estimate.
[0068] When the model parameters of the detection probability calculation model are calculated based on the test data and the excavation data, it includes: comparing the test data with the excavation data to obtain the test results corresponding to each defect in the sample defects; constructing a likelihood function including each parameter in the detection probability prediction calculation model, and using the maximum likelihood estimation algorithm to estimate each parameter in the likelihood function according to the test results to obtain the estimated values of the parameters of the detection probability prediction calculation model.
[0069] In order to calculate the model parameters of the detection probability calculation model based on the detection data and excavation data, the obtained detection data and excavation data can be integrated to obtain sample defect data for parameter calculation. For example, the sample defect data can be marked by comparing the detection data and excavation data in a human-assisted manner.
[0070] Specifically, the detection data is compared with the excavation data to obtain the detection results corresponding to the sample defects. Then, when calculating and predicting the model parameters, a likelihood function of each parameter in the detection probability prediction calculation model is constructed, and the maximum likelihood estimation algorithm is used to calculate the detection results corresponding to the sample defects to obtain the estimated values of the model parameters of the constructed detection probability calculation model.
[0071] Exemplarily, when associating the detection data with the excavation data, the defects can be arranged in order, and the size and other information of the sample defects can be recorded, and whether they are detected can be marked. Therefore, when the detection results of the sample defects are obtained by association, it includes: matching the detection data with the excavation data to obtain the detection status of the defects contained in the excavation data, where the detection status includes detected and undetected; marking the defects according to the detection status, and determining the detection results of each sample defect, where the detection results include the defect information and the detection status of the defect, and the defect information includes at least the depth, length and width of the defect.
[0072] Furthermore, the maximum likelihood estimation mathematical method is used to obtain the estimated values of the four unknown parameters in the detection probability calculation model. Assume that the data sample includes n pipeline defects, and the depth, length and width of the defects are represented by d1, d2, …, d n and l1,l2,…,l n and w1,w2,...,w n Since defects have two detection states: detected and undetected, for a defect i that can be detected, the detection probability is POD i , and for defects that cannot be detected, the probability of detection is 1-POD i .Right now:
[0073]
[0074] Among them, h i Indicates whether the i-th defect can be detected by the internal detector. i =1 indicates that it is detected. i =0 means not detected.
[0075] According to the detection status results of the comparison between the detection data and the excavation data, it can be known whether the defect is detected by the detector in the pipeline, that is, each defect corresponds to h1, h2, …, h n Therefore, when calculating the model parameters in the detection probability calculation model, the likelihood function of the parameters of the detection probability calculation model can be obtained through computational simplification, and then the calculation is performed based on the obtained likelihood function, where the obtained likelihood function is as follows:
[0076]
[0077] Where n is the number of sample defects.
[0078] Furthermore, when calculating and determining parameters, according to the principle of maximum likelihood estimation, the logarithms of the model parameters a0, a1, a2, a3 in formula (3) are taken respectively, and the equations after taking the logarithm are set equal to 0, and the maximum likelihood estimates of the parameters a0, a1, a2, a3 can be obtained. That is, when formula (3) reaches its maximum value, is the value of a0, a1, a2, a3.
[0079] Taking the inspection of a pipeline by an internal detector as an example, after the inspection data is associated with the excavation data, a pipeline sample defect table for calculating the parameters in the detection probability calculation model of the internal detector can be obtained. Table 1 is a sample defect table obtained by comparing a pipeline inspection and excavation verification by an internal detector.
[0080] Table 1 Sample defect table of a certain internal inspection detection probability prediction model
[0081]
[0082]
[0083]
[0084]
[0085] It can be seen from Table 1 above that the number of defects contained in the excavation data obtained by detecting the pipeline using the internal detector is 300, while the number of defects contained in the detection data is 284. When correlating, the defects detected in the excavation data are marked as "1", and the defects not detected are marked as "0".
[0086] Based on the data in Table 1, the model parameters are calculated according to formula (3): a0 = 1.3201, a1 = 1.0891, a2 = 0.6325, a3 = 0.2731.
[0087] Step 103: Optimize and adjust the detection probability calculation model according to the model parameters.
[0088] Specifically, when the detection probability calculation model is optimized and adjusted according to the obtained model parameters, the detection probability calculation model is simplified by substituting the obtained model parameters into the detection probability calculation model.
[0089] For example, after obtaining the model parameters based on Table 1, the parameters are substituted into formula (1). The detection probability calculation model obtained at this time is as follows:
[0090]
[0091] Simplifying the calculation model, we can get the detection probability calculation model of the internal detector as follows:
[0092]
[0093] Among them, the unit of d, l, and w is mm.
[0094] Step 104, verifying the internal detector according to the adjusted detection probability calculation model.
[0095] Specifically, after the adjusted detection probability calculation model is obtained, the internal detector will be verified according to the adjusted detection probability calculation model to determine whether the detection probability of the internal detector provided by the internal detection provider meets the standard.
[0096] Exemplarily, the verification of the internal detector includes: obtaining the factory detection probability of the internal detector; simplifying the detection probability prediction calculation model to obtain a detection probability prediction model with the defect size relationship as the independent variable, wherein the size relationship is the power relationship between the depth, length, width of the defect and the corresponding parameter estimation value; calculating the calculated value of the size relationship of the detectable defects in the pipeline according to the factory detection probability and the simplified detection probability prediction calculation model; comparing the calculated value of the size relationship of the detectable defects with the target calculated value calculated based on the size relationship of the defect size of the target defect to be verified, and verifying the internal detector; if the target calculated value is greater than or equal to the calculated value, it is determined that the verification has passed; if the target calculated value is less than the calculated value, it is determined that the verification has failed.
[0097] For the internal detector, the corresponding detection probability and the minimum detection defect are set at the factory. During verification, the actual detection probability of the internal detector is obtained, and then the calculated value of the size relationship of the detected defect in the pipeline can be calculated based on the factory detection probability and the detection probability calculation model. The size relationship is the power relationship between the depth, length, width of the defect and the estimated value of the corresponding parameter, as shown in formula (5): 1.0891 l 0.6325 w0.2731 ,Finally, the internal detector is verified based on the calculated value of the obtained size relationship and the corresponding target size relationship calculated value of the target defect.
[0098] According to the factory detection probability and the detection probability calculation model, the calculated value of the size relationship of the detected defects in the pipeline is calculated, specifically including assigning the factory detection probability value to the POD in the detection probability calculation model formula, and then calculating the calculated value of the detectable defect size relationship corresponding to the factory detection probability, that is, the relationship between the depth, length and width of the detectable defect.
[0099] Taking the detection probability curve obtained based on Table 1 as an example, if the factory detection probability is 90%, then the calculated value of the defect size relationship that the detector can detect is 2.404. 1.0891 l 0.6325 w 0.2731 When >2.404, the detection probability is greater than 90%.
[0100] Similarly, based on the detection probability calculation model obtained in Table 1, when d 1.0891 l 0.6325 w 0.2731 As a whole, we can get d 1.0891 l 0.6325 w 0.2731 The relationship between the detection probability POD and the specific relationship curve can be shown as Figure 3 Of course, the curves obtained will be different if the detection probability is set differently.
[0101] When based on curve comparison, it also includes: determining a parameter in the defect size of the target defect as a fixed parameter, and obtaining a two-dimensional curve of the defect size based on the calculated value and the fixed parameter; obtaining the size coordinates of the target defect according to the defect size and the fixed parameter; and verifying the internal detector by comparing the size coordinates with the two-dimensional curve.
[0102] Specifically, at this time, it can be determined whether the defect size corresponding to the obtained factory detection probability is on the curve obtained based on the verification conditions. If it is on or above the curve, it is determined that the verification has passed. Otherwise, if it is below the curve, it is determined that the verification has failed.
[0103] Exemplarily, the size of the defect includes length, depth and width. After obtaining the detection probability calculation model shown in formula (5), the calculated value of the size relationship can be calculated according to the set detection probability value, and then by fixing a certain size, the change relationship between the remaining two sizes can be obtained. Optimally, when the width is fixed, the change relationship between the length and depth can be obtained while satisfying the detection probability.
[0104] Taking the detection probability calculation model obtained based on Table 1 as an example, when the factory detection probability is 90%, when the fixed parameter is the width of the defect, the curve corresponding to the verification condition is as follows: Figure 4 As shown, the fixed defect widths are 100mm, 50mm and 10mm respectively. During the verification, only the defects of various sizes on or above the curve can be detected by the internal detector with a probability of reaching or exceeding 90%, while the defects of various sizes below the curve have a probability of being detected by the internal detector of less than 90%.
[0105] In the detection probability verification method of the internal detector in the above embodiment, when verifying the internal detector, the detection data obtained by the internal detector in the pipeline is first obtained, and the excavation data corresponding to the pipeline is obtained at the same time, wherein the excavation data is the actual defect data of the pipeline, and then a multi-parameter detection probability calculation model is constructed based on logarithmic logic, and then the model parameters of the detection probability calculation model are determined according to the obtained detection data and excavation data, so as to optimize and adjust the detection probability calculation model, and finally the verification of the internal detector is completed according to the adjusted detection probability calculation model. It is realized that a detection probability calculation model for accuracy verification of the internal detector is constructed based on the actual data of the internal detector and the excavation data of the pipeline, so as to accurately evaluate the performance of the internal detector.
[0106] The detection probability verification device of the internal detector provided by the present invention is described below. The detection probability verification device of the internal detector described below and the detection probability verification method of the internal detector described above can be referenced to each other.
[0107] Figure 5 Schematic diagram of the structure of the detection probability verification device of the internal detector provided by the present invention, such as Figure 5 As shown, the detection probability verification device 500 of the internal detector includes:
[0108] The data acquisition module 501 is used to acquire the detection data of the pipeline based on the internal detector and to acquire the excavation data of the pipeline;
[0109] The parameter determination module 502 constructs a detection probability calculation model and obtains model parameters of the detection probability calculation model based on the detection data and the excavation data;
[0110] A model adjustment module 503, used to adjust the detection probability calculation model according to the model parameters;
[0111] The verification processing module 504 is used to verify the internal detector according to the adjusted detection probability calculation model.
[0112] Based on the above embodiment, the data acquisition module 501 is further used for:
[0113] Identify the pipeline used to perform the test;
[0114] Conduct defect detection on pipelines based on internal detectors and analyze to obtain detection data;
[0115] Defect excavation is performed on the pipeline based on the detection data, and the actual defect data of the pipeline is collected to obtain excavation data.
[0116] Based on the above embodiment, the parameter determination module 502 is further specifically used for:
[0117] According to the multi-parameter logarithmic logic, a multi-parameter detection probability prediction calculation model is constructed, wherein the input quantity of the detection probability prediction calculation model at least includes the depth, length and width of the defect;
[0118] The parameters in the multi-parameter detection probability prediction calculation model are predicted based on the detection data and the excavation data to obtain the estimated values of the parameters in the detection probability prediction calculation model.
[0119] Based on the above embodiment, the parameter determination module 502 is further specifically used for:
[0120] Compare the inspection data with the excavation data to obtain the inspection results corresponding to each defect;
[0121] A likelihood function including each parameter in the detection probability prediction calculation model is constructed, and each parameter in the likelihood function is estimated according to the detection results using a maximum likelihood estimation algorithm to obtain estimated values of the parameters of the detection probability prediction calculation model.
[0122] Based on the above embodiment, the parameter determination module 502 is further specifically used for:
[0123] Matching the inspection data with the excavation data to obtain the detection status of the defects contained in the excavation data, wherein the detection status includes detected and undetected;
[0124] The defects are marked according to the detection status, and the detection result of each defect is determined, wherein the detection result includes defect information and the detection status of the defect, and the defect information includes at least the depth, length and width of the defect.
[0125] Based on the above embodiment, the verification processing module 504 is further used for:
[0126] Obtain the factory detection probability of the internal detector;
[0127] The detection probability prediction calculation model is simplified to obtain a detection probability prediction model with the defect size relationship as the independent variable, where the size relationship is the power relationship between the depth, length, width of the defect and the corresponding parameter estimation value;
[0128] According to the factory detection probability and the simplified detection probability prediction calculation model, the calculated value of the size relationship of the defects that can be detected in the pipeline is calculated;
[0129] Compare the calculated value of the detectable defect size relationship with the target calculated value of the defect size of the target defect to be verified based on the size relationship to verify the internal detector;
[0130] If the target calculated value is greater than or equal to the calculated value, the verification is determined to be passed;
[0131] If the target calculated value is less than the calculated value, it is determined that the verification fails.
[0132] Based on the above embodiment, the verification processing module 504 is further used for:
[0133] A parameter is determined as a fixed parameter in the defect size of the target defect, and a two-dimensional curve of the defect size is obtained based on the calculated value and the fixed parameter;
[0134] According to the defect size and fixed parameters, the size coordinates of the target defect are obtained;
[0135] The internal detector is verified by comparing the size coordinates with the two-dimensional curve.
[0136] In the detection probability verification device of the internal detector in the above embodiment, when the internal detector is verified, the detection data obtained by the internal detector in the pipeline is first obtained, and the excavation data corresponding to the pipeline is obtained at the same time, wherein the excavation data is the actual defect data of the pipeline, and then a multi-parameter detection probability calculation model is constructed based on logarithmic logic, and then the model parameters of the detection probability calculation model are determined according to the obtained detection data and excavation data, so as to optimize and adjust the detection probability calculation model, and finally the verification of the internal detector is completed according to the adjusted detection probability calculation model. It is realized that the detection probability calculation model for accuracy verification of the internal detector is constructed based on the actual data of the internal detector and the excavation data of the pipeline, so as to accurately evaluate the performance of the internal detector.
[0137] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the detection probability verification method of the internal detector, the method comprising: obtaining the detection data of the pipeline obtained based on the internal detector, and obtaining the excavation data of the pipeline; constructing a detection probability calculation model, and obtaining the model parameters of the detection probability calculation model based on the detection data and the excavation data; adjusting the detection probability calculation model according to the model parameters; and verifying the internal detector according to the adjusted detection probability calculation model.
[0138] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.
[0139] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the detection probability verification method of the internal detector provided by the above methods, and the method includes: obtaining detection data of the pipeline obtained based on the internal detector, and obtaining excavation data of the pipeline; constructing a detection probability calculation model, and obtaining model parameters of the detection probability calculation model based on the detection data and the excavation data; adjusting the detection probability calculation model according to the model parameters; and verifying the internal detector according to the adjusted detection probability calculation model.
[0140] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the detection probability verification method of the internal detector provided by the above-mentioned methods, the method comprising: obtaining detection data of the pipeline obtained based on the internal detector, and obtaining excavation data of the pipeline; constructing a detection probability calculation model, and obtaining model parameters of the detection probability calculation model based on the detection data and the excavation data; adjusting the detection probability calculation model according to the model parameters; and verifying the internal detector according to the adjusted detection probability calculation model.
[0141] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0142] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A detection probability verification method for an internal detector, It is characterized in that include: Acquiring detection data of the pipeline based on the internal detector, and acquiring excavation data of the pipeline; Constructing a detection probability prediction calculation model, and obtaining model parameters of the detection probability prediction calculation model based on the detection data and the excavation data; According to the model parameters, adjusting the detection probability prediction calculation model; The internal detector is verified based on the adjusted detection probability prediction calculation model.
2. The detection probability verification method of the internal detector according to claim 1, It is characterized in that The step of obtaining the detection data of the pipeline based on the internal detector and obtaining the excavation data of the pipeline includes: Identify the pipeline used to perform the test; Conduct defect detection on pipelines based on internal detectors and analyze to obtain detection data; Defect excavation is performed on the pipeline according to the detection data, and real defect data of the pipeline is collected to obtain excavation data.
3. The detection probability verification method of the internal detector according to claim 1, It is characterized in that The constructing of the detection probability prediction calculation model and obtaining the model parameters of the detection probability prediction calculation model based on the detection data and the excavation data include: According to the logarithmic logic of multiple parameters, a multi-parameter detection probability prediction calculation model is constructed, wherein the input quantity of the detection probability prediction calculation model includes at least the depth, length and width of the defect; The parameters in the multi-parameter detection probability prediction calculation model are predicted based on the detection data and the excavation data to obtain estimated values of the parameters in the detection probability prediction calculation model.
4. The detection probability verification method of the internal detector according to claim 3, It is characterized in that The step of predicting the parameters in the multi-parameter detection probability prediction calculation model according to the detection data and the excavation data to obtain estimated values of the parameters in the detection probability prediction calculation model includes: Comparing the detection data with the excavation data to obtain a detection result corresponding to each defect; A likelihood function including each parameter in the detection probability prediction calculation model is constructed, and each parameter in the likelihood function is estimated according to the detection result using a maximum likelihood estimation algorithm to obtain estimated values of the parameters of the detection probability prediction calculation model.
5. The detection probability verification method of the internal detector according to claim 4, It is characterized in that The comparing the detection data with the excavation data to obtain the detection status corresponding to each defect includes: Matching the detection data with the excavation data to obtain the detection status of the defects contained in the excavation data, wherein the detection status includes detected and undetected; The defects are marked according to the detection status, and a detection result of each defect is determined, wherein the detection result includes defect information of the defect and the detection status, and the defect information includes at least the depth, length and width of the defect.
6. The detection probability verification method of the internal detector according to claim 1, It is characterized in that The step of verifying the internal detector according to the adjusted detection probability prediction calculation model includes: Obtaining the factory detection probability of the internal detector; Simplifying the detection probability prediction calculation model to obtain a detection probability prediction model with the independent variable being the defect size relationship, wherein the size relationship is a power relationship between the depth, length, width of the defect and the corresponding parameter estimation value; According to the factory detection probability and the simplified detection probability prediction calculation model, a calculated value of the size relationship of the defects that can be detected in the pipeline is calculated; Comparing the calculated value of the detectable defect size relationship with a target calculated value of the defect size of the target defect to be verified, calculated based on the size relationship, to verify the internal detector; If the target calculated value is greater than or equal to the calculated value, then it is determined that the verification is passed; If the target calculated value is less than the calculated value, it is determined that the verification fails.
7. The detection probability verification method of the internal detector according to claim 6, It is characterized in that After calculating the calculated value of the size relationship of the detectable defects in the pipeline according to the factory detection probability and the simplified detection probability prediction calculation model, the method further includes: Determining a parameter in the defect size of the target defect as a fixed parameter, and obtaining a two-dimensional curve of the defect size based on the calculated value and the fixed parameter; According to the defect size and the fixed parameters, the size coordinates of the target defect are obtained; The internal detector is verified based on the comparison between the size coordinates and the two-dimensional curve.
8. A detection probability verification device for an internal detector, It is characterized in that include: A data acquisition module, used to acquire detection data of the pipeline based on the internal detector, and to acquire excavation data of the pipeline; A parameter determination module constructs a detection probability prediction calculation model and obtains model parameters of the detection probability prediction calculation model based on the detection data and the excavation data; A model adjustment module, used to adjust the detection probability prediction calculation model according to the model parameters; A verification processing module is used to verify the internal detector according to the adjusted detection probability prediction calculation model.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the program, it implements the detection probability verification method of the internal detector as described in any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the detection probability verification method of the internal detector as claimed in any one of claims 1 to 7 is implemented.
