A method for assisting decision of pipeline detection and a storage medium

Abstract

The application discloses a kind of pipeline detection auxiliary decision-making method and storage medium, the pipeline detection auxiliary decision-making method includes the following steps: S1: constructs knowledge base, with each pipeline detection method Am's technical features, applicable scope is dimension, constructs pipeline detection method knowledge base;S2: based on the characteristic parameter Cn of the scene to be detected in pipeline detection process, and the pipeline detection method knowledge base constructed, to obtain the recommended pipeline detection method with parallel selection decision algorithm DPST calculation, and show to user.Through the pipeline detection auxiliary decision-making method of the application, pipeline detection technical personnel only need to input the relevant parameters of pipeline detection, can quickly select the technical method suitable for this detection condition, greatly improves the detection efficiency.

Description

Technical Field

[0001] This invention belongs to the field of pipeline detection technology, and particularly relates to an auxiliary decision-making method and storage medium for pipeline detection. Background Technology

[0002] With the acceleration of urban modernization, the number of buildings above ground has increased, the types of underground pipelines have also increased, and the distribution of pipelines has become denser. Underground pipelines, as the "neural network" of the city, play a vital role in the normal operation of modern cities and the normal functioning of people's lives. For a long time, they have been responsible for transmitting information, transporting energy, and discharging wastewater.

[0003] However, due to various reasons, many cities lack complete data on underground pipeline distribution and their pipeline records are not properly managed. Therefore, underground pipeline detection is crucial for the normal operation and expansion of cities. Currently, accurate and efficient underground pipeline detection remains a highly challenging task. The main methods currently used for pipeline detection include traditional borehole drilling, electromagnetic induction, ground-penetrating radar, and shallow seismic methods.

[0004] In actual pipeline detection, the choice of methods often relies on experience, which is highly subjective and blind. For example, the detection of metal pipelines often adopts electromagnetic induction methods, clamp methods, direct methods, or ground penetrating radar methods. These methods are not well integrated to form a complete and organic system, which greatly affects the quality of pipeline detection. Summary of the Invention

[0005] The purpose of this invention is to overcome the problems of existing technology by disclosing an auxiliary decision-making method and storage medium for pipeline detection. This invention achieves standardized and precise pipeline detection operations, avoids low-accuracy and low-efficiency detection operations by workers, and greatly improves detection efficiency.

[0006] On the one hand, the objective of this invention is achieved through the following technical solution:

[0007] A pipeline detection auxiliary decision-making method, comprising the following steps:

[0008] S1: Construct a knowledge base, using the technical characteristics and applicable scope of each pipeline detection method Am as dimensions;

[0009] S2: Based on the feature parameters Cn of the scene to be detected during pipeline detection, and the constructed pipeline detection method knowledge base, the recommended pipeline detection method is calculated using the parallel selection decision algorithm DPST and displayed to the user.

[0010] According to a preferred embodiment, step S2 specifically includes:

[0011] S21: Based on the feature parameters Cn of the scene to be detected and the applicable scope of each pipeline detection method Am in the pipeline detection method knowledge base, construct an applicability language matrix for each pipeline detection method for each feature parameter. Each column element in the applicability language matrix represents the applicability of a pipeline detection method for each feature parameter, and convert the constructed applicability language matrix into a numerical matrix.

[0012] In the applicability language matrix, if the pipeline detection method Am is adaptive for the feature parameter Cn, it is denoted as element A; if it is neutral, it is denoted as element N; and if it is not applicable, it is denoted as element I.

[0013] The numerical matrix transformation process involves replacing the elements A, N, and I of the applicability language matrix with the numbers 10, 1, and 0, respectively.

[0014] S22: Multiply the values ​​in each column of the obtained numerical matrix to obtain a single-row matrix 1; and take the logarithm of 10 for each element in the single-row matrix 1 to obtain matrix 2; the value of each element in matrix 2 represents the number of applicable conditions for each pipeline detection method, and an element value of infinite means that at least one inapplicable condition has been selected.

[0015] S23: Based on the number of adaptation conditions of each pipeline detection method in the pipeline detection method knowledge base, matrix 3 is established. Each element in matrix 2 is divided by the corresponding element in matrix 3. The final matrix result determines the applicability of each pipeline detection method.

[0016] According to a preferred embodiment, the recommended order is determined by how close the corresponding element of each pipeline detection method is to 1 in the final matrix, and the pipeline detection method with an element of 1 in the final matrix is ​​the first recommended pipeline detection method.

[0017] According to a preferred embodiment, the characteristic parameter Cn includes: pipeline type, pipeline size, pipeline burial depth, and pipeline material.

[0018] According to a preferred embodiment, in step S1, the pipeline detection methods Am include: electromagnetic induction method, ground-penetrating radar method, DC resistance method, shallow seismic method, magnetic method, infrared thermal radiation method, and microgravity method.

[0019] According to a preferred embodiment, the electromagnetic induction method includes: power frequency method, direct method, clamp method, induction method, and tracer method;

[0020] The shallow seismic methods include: reflection wave method, refraction wave method, and surface wave method;

[0021] The magnetic methods include: magnetic field strength method and magnetic gradient method.

[0022] On the other hand, the present invention also discloses:

[0023] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned decision support method.

[0024] The aforementioned main solution of the present invention and its various further alternative solutions can be freely combined to form multiple solutions, all of which are solutions that can be adopted and are claimed by the present invention. Those skilled in the art, after understanding the solution of the present invention, will realize that there are many combinations based on existing technology and common knowledge, all of which are technical solutions to be protected by the present invention, and will not be exhaustively listed here.

[0025] The beneficial effects of this invention are as follows: Through the auxiliary decision-making method and readable storage medium for pipeline detection of this invention, pipeline detection technicians only need to input the relevant parameters of pipeline detection to quickly select the technical method suitable for the current detection conditions, which greatly improves the detection efficiency. Detailed Implementation

[0026] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0027] Example 1

[0028] This invention discloses an auxiliary decision-making method for pipeline detection, which includes the following steps:

[0029] Step S1: Construct a knowledge base. Based on the technical characteristics and applicable scope of each pipeline detection method Am, construct a knowledge base for pipeline detection methods.

[0030] Step S2: Based on the feature parameters Cn of the scene to be detected during pipeline detection, and the constructed pipeline detection method knowledge base, the recommended pipeline detection method is calculated using the parallel selection decision algorithm DPST and displayed to the user.

[0031] Preferably, step S1, constructing a pipeline detection method knowledge base, specifically includes:

[0032] First, for the currently commonly used single-line detection methods, a detailed applicability evaluation was conducted using numerical simulation and field testing methods from the dimensions of technical characteristics and applicable scope, and the main applicable scope and advantages and disadvantages of each method were obtained (as shown in Table 1). Then, a knowledge base was established based on the evaluation parameters and evaluation results of the methods, and the technical combination for this pipeline detection was given through decision-making algorithm.

[0033] The specific technologies evaluated include traditional drilling methods, pipe and cable locators, E-line locator method, metal detectors, Electronic Marker System (EMS), conductivity method, ground-penetrating radar method, acoustic emission method, resistivity method, infrared thermal imaging method, microgravity method, frequency meter method, high-density resistivity method, and transient surface wave method. Table 1 shows the evaluation results of some pipeline detection methods.

[0034] Table 1: Evaluation Results of Some Detection Technologies

[0035]

[0036]

[0037]

[0038] Preferably, step S2 specifically includes:

[0039] Step S21: Based on the feature parameters Cn of the scene to be detected and the applicable scope of each pipeline detection method Am in the pipeline detection method knowledge base, construct an applicability language matrix for each pipeline detection method for each feature parameter. Each column element in the applicability language matrix represents the applicability of a pipeline detection method for each feature parameter, and convert the constructed applicability language matrix into a numerical matrix.

[0040] In the applicability language matrix, the pipeline detection method Am is denoted as element A if it is adaptive to the feature parameter Cn, as element N if it is neutral, and as element I if it is not applicable.

[0041] The numerical matrix transformation process involves replacing the elements A, N, and I of the applicability language matrix with the numbers 10, 1, and 0, respectively.

[0042] For example, given four feature parameters C1, C2, C3, and C4 of a scene to be detected (such as pipeline type, size, burial depth, material, etc.) and three detection methods to choose from, A1, A2, and A3, the decision-making process can be represented as follows:

[0043]

[0044] A: Applicable N: Neutral 1: Not Applicable

[0045] Step S22: Multiply the values ​​in each column of the obtained numerical matrix to obtain a single-row matrix 1. Since multiplication is a combination of 0, 1, and 10, the result of multiplication is always 0 or 10 to the power of x.

[0046] Then, take the logarithm of 10 for each element in the single-row matrix 1 to obtain matrix 2. The value of each element in matrix 2 represents the number of applicable conditions for each pipeline detection method. An element value of infinity indicates that at least one inapplicable condition has been selected.

[0047] Specifically, for the case where there are four feature parameters C1, C2, C3, and C4, and three detection methods to be selected, namely A1, A2, and A3, the matrix transformation process is as follows:

[0048]

[0049] In matrix 2, the element corresponding to detection method A1 is 3, indicating that detection method A1 satisfies 3 of the 4 feature parameters and 1 of them are neutral; the element corresponding to detection method A2 is -∞, indicating that detection method A2 selects at least one inapplicable condition for the 4 feature parameters; and the element corresponding to detection method A3 is 2, indicating that detection method A3 satisfies 2 of the 4 feature parameters and 2 of them are neutral.

[0050] S23: Based on the number of adaptation conditions of each pipeline detection method in the pipeline detection method knowledge base, matrix 3 is established. Each element in matrix 2 is divided by the corresponding element in matrix 3. The final matrix result determines the applicability of each pipeline detection method.

[0051] Specifically, for the case where there are four feature parameters C1, C2, C3, and C4, and three detection methods to be selected, namely A1, A2, and A3, the final matrix acquisition process is as follows:

[0052]

[0053] In matrix 3, the element corresponding to detection method A1 has a value of 3, indicating that detection method A1 has only 3 optimal conditions in the pipeline detection method knowledge base. Finally, the element corresponding to detection method A1 in the matrix is ​​either 1 or 100%, meaning that all four feature parameters are satisfied with the optimal conditions of detection method A1.

[0054] In matrix 3, the element corresponding to detection method A3 has a value of 3, indicating that detection method A3 has only 3 optimal conditions in the pipeline detection method knowledge base. Finally, the element corresponding to detection method A3 in the matrix is ​​67%, meaning that for the 4 feature parameters, the optimal conditions for detection method A3 are satisfied in 2 / 3 of the cases.

[0055] Preferably, the recommended order, i.e., the reliability, is determined by how close the corresponding element of each pipeline detection method is to 1 in the final matrix. Furthermore, the pipeline detection method whose corresponding element in the final matrix is ​​1 is the first recommended pipeline detection method.

[0056] Example 2

[0057] Based on Embodiment 1, this embodiment also discloses a computer-readable storage medium. A computer program is stored thereon, which, when executed by a processor, implements the decision support method disclosed in Embodiment 1.

[0058] With the auxiliary decision-making method and readable storage medium for pipeline detection of the present invention, pipeline detection technicians only need to input the relevant parameters of pipeline detection to quickly select the technical method suitable for the current detection conditions, which greatly improves the detection efficiency.

[0059] Application Cases

[0060] Taking a large-sized, deeply buried non-metallic pipeline made of PVC as an example, the method of this invention is used to select the most suitable method from three underground pipeline detection methods: active source surface wave method, ground-penetrating radar method, and micro-motion detection method.

[0061] The specific steps are as follows:

[0062] (1) Establish a knowledge base for pipeline detection methods, mainly providing the applicability of three methods to current pipeline detection factors. Detailed information is shown in Table 2.

[0063] Table 2. Pipeline Detection Technology Knowledge Base

[0064]

[0065] (2) Taking pipeline detection factors, including pipeline type, pipeline size, pipeline burial depth, and pipeline material, as input parameters, the adaptability numerical matrices of each parameter for the three detection methods A1, A2, and A3 can be obtained according to Table 2:

[0066]

[0067] (3) Obtain matrix 2 using numerical matrix.

[0068]

[0069] (4) Based on the number of applicable parameters contained in the four types of pipeline detection parameters corresponding to the three detection methods in Table 2, matrix 3 is obtained. Among them, the total number of applicable conditions for method A1 is 4, the total number of applicable conditions for method A2 is 3, and the total number of applicable conditions for method A3 is 4.

[0070] Dividing matrix 2 by matrix 3 yields the final calculated matrix. Based on the final matrix, the most suitable technology for this pipeline detection is A3 (i.e., micro-motion detection method), and the second choice is A1 (i.e., active source detection method).

[0071]

[0072] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A decision-making auxiliary method for pipeline detection, characterized in that, The auxiliary decision-making method for pipeline detection includes the following steps: S1: Construct a knowledge base, using the technical characteristics and applicable scope of each pipeline detection method Am as dimensions; S2: Based on the feature parameters Cn of the scene to be detected during pipeline detection, and the constructed pipeline detection method knowledge base, the recommended pipeline detection method is calculated using the parallel selection decision algorithm DPST and displayed to the user; Step S2 specifically includes: S21: Based on the feature parameters Cn of the scene to be detected and the applicable scope of each pipeline detection method Am in the pipeline detection method knowledge base, construct an applicability language matrix for each pipeline detection method for each feature parameter. Each column element in the applicability language matrix represents the applicability of a pipeline detection method for each feature parameter, and convert the constructed applicability language matrix into a numerical matrix. In the applicability language matrix, if the pipeline detection method Am is adaptive for the feature parameter Cn, it is denoted as element A; if it is neutral, it is denoted as element N; and if it is not applicable, it is denoted as element I. The numerical matrix transformation process involves replacing the elements A, N, and I of the applicability language matrix with the numbers 10, 1, and 0, respectively. S22: Multiply the values ​​in each column of the obtained numerical matrix to obtain a single-row matrix 1; and take the logarithm of 10 for each element in the single-row matrix 1 to obtain matrix 2; the value of each element in matrix 2 represents the number of applicable conditions for each pipeline detection method, and an element value of infinite means that at least one inapplicable condition has been selected. S23: Based on the number of adaptation conditions of each pipeline detection method in the pipeline detection method knowledge base, establish matrix 3. Divide each element in matrix 2 by the corresponding element in matrix 3. The result of the final matrix determines the applicability of each pipeline detection method.

2. The auxiliary decision-making method for pipeline detection as described in claim 1, characterized in that, In step S23, the recommended order is determined by how close the corresponding element of each pipeline detection method is to 1 in the final matrix, and the pipeline detection method with an element of 1 in the final matrix is ​​the first recommended pipeline detection method.

3. The auxiliary decision-making method for pipeline detection as described in claim 1, characterized in that, The characteristic parameter Cn includes: pipeline type, pipeline size, pipeline burial depth, and pipeline material.

4. The auxiliary decision-making method for pipeline detection as described in claim 1, characterized in that, In step S1, the pipeline detection methods Am include: electromagnetic induction method, ground-penetrating radar method, DC resistance method, shallow seismic method, magnetic method, infrared thermal radiation method, and microgravity method.

5. The auxiliary decision-making method for pipeline detection as described in claim 4, characterized in that, The electromagnetic induction methods include: power frequency method, direct method, clamp method, induction method, and tracer method; The shallow seismic methods include: reflection wave method, refraction wave method, and surface wave method; The magnetic methods include: magnetic field strength method and magnetic gradient method.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the decision support method as described in any one of claims 1-4.

Images