Pipeline corrosion data acquisition and pipeline corrosion rate prediction model construction method

Abstract

The present invention relates to the technical field of pipeline corrosion data processing, and in particular to a method for acquiring pipeline corrosion data and constructing a pipeline corrosion rate prediction model. The pipeline corrosion data acquisition method of the present invention first acquires multiple typical corrosive soils; then, for each of the typical corrosive soils, multiple pipeline samples are buried; then, at predetermined time points, the pipeline samples are sequentially removed from the multiple typical corrosive soils; finally, for each of the typical corrosive soils, a maximum corrosion rate and multiple soil corrosion factors are respectively obtained as pipeline corrosion data, wherein the maximum corrosion rate is obtained based on the multiple pipeline samples removed from the typical corrosive soils. In an embodiment of the present invention, pipeline corrosion data is acquired using the samples and the corrosive soils, and a corrosion curve is fitted based on the existing data. The acquired corrosion data can accurately reflect the relationship between the dependent variable and the independent variable, and the acquired data is more accurate and reliable.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline corrosion data processing, and in particular to a method for acquiring pipeline corrosion data and constructing a pipeline corrosion rate prediction model. Background Art

[0002] Currently, there is little public research on the lifespan of metal pipes, particularly ductile iron pipes. As buried ductile iron pipes age, their outer coatings and pipe walls corrode. While minor corrosion has no impact on pipe performance, severe corrosion can have a significant impact, often causing perforations or even ruptures, resulting in significant economic losses and social impact. Therefore, it is crucial to systematically study the corrosion resistance of ductile iron pipes under varying soil conditions and assess their expected service life.

[0003] On the other hand, ductile iron pipe users need to select ductile iron pipe grades that meet the engineering design life requirements based on the specific soil corrosion environment. Therefore, it is urgent and important to study and evaluate the expected service life of ductile iron pipe systems.

[0004] Existing research on pipeline corrosion and lifespan focuses on steel pipe lifespan. This involves evaluating the remaining service life of steel pipes based on monitored corrosion rates after several years of operation in actual corrosive environments. Alternatively, the remaining service life is calculated using finite element software based on the geometric dimensions and shape of corrosion pits on the steel pipe's outer wall and stress analysis. However, research on the service life of ductile iron (ductile iron) pipes is virtually nonexistent. This is primarily due to the different composition of ductile iron pipes and their different corrosion patterns.

[0005] Since there are many factors that affect soil corrosivity, including soil texture, oxygen content, soil resistivity, Cl - 、SO4 2- , water content, pH value, salt content and other factors, so it is necessary to systematically study the corrosion factors of soil and the corrosion behavior of pipelines in the soil environment, and calculate and evaluate the corrosion of pipelines under given soil physical and chemical property parameters.

[0006] Based on this, it is necessary to develop and design a pipeline corrosion data acquisition method and a pipeline corrosion rate prediction method. Summary of the Invention

[0007] The embodiment of the present invention provides a method for acquiring pipeline corrosion data and constructing a pipeline corrosion rate prediction model, which is used to solve the problem in the prior art that inaccurate pipeline corrosion data acquisition leads to poor corrosion modeling effect.

[0008] In a first aspect, an embodiment of the present invention provides a pipeline corrosion data acquisition method, comprising:

[0009] obtaining a plurality of typical corrosive soils, wherein the typical corrosive soils have a corrosive effect on pipelines;

[0010] For each of the typical corrosive soils, multiple pipeline specimens are buried;

[0011] Taking out pipeline samples from the plurality of typical corrosive soils in sequence according to predetermined time points;

[0012] For each typical corrosive soil, a maximum corrosion rate and multiple soil corrosion factors are obtained as pipeline corrosion data, wherein the soil corrosion factors represent factors affecting the pipeline corrosion rate at the location where the pipeline is laid, and the maximum corrosion rate is obtained based on multiple pipeline samples taken from the typical corrosive soil.

[0013] In a possible implementation, for each typical corrosive soil, multiple pipeline specimens are buried, including:

[0014] The material base of the pipeline sample is a metal pipe, a zinc coating is sprayed on the outside of the metal pipe, and an organic finishing coating is sprayed on the zinc coating;

[0015] After the pipe samples are sealed and dried, they are placed horizontally at the bottom of the test pit in the order of their types. The intervals between the pipe samples and between the pipe samples and the edge of the test pit are greater than a preset value. Soil is spread on the pipe samples so that the soil around the front, back, left, right, top and bottom of the pipe samples is dense and has no gaps.

[0016] In one possible implementation, the intervals between the multiple predetermined time nodes are set in a gradually increasing pattern;

[0017] The maximum corrosion rates of several pipeline specimens taken from the typical corrosive soils include:

[0018] For each pipeline specimen, obtain the corrosion pit depth data of the deepest corrosion pit;

[0019] According to a predetermined time node, converting a plurality of corrosion pit depth data into maximum corrosion pit rate data at the corresponding time node;

[0020] According to multiple time nodes and multiple maximum corrosion pit rate data corresponding to the multiple time nodes, a corrosion rate expectation function is constructed. The corrosion rate expectation function is:

[0021] V=a·t b

[0022] Where V is the corrosion rate in a typical corrosive soil area, a is the leading constant, b is the trailing constant, and t is time.

[0023] In a possible implementation, after obtaining the maximum corrosion rate and multiple soil corrosion factors for each typical corrosive soil, the following steps are performed:

[0024] Obtaining measured corrosion rates of actual buried pipelines and multiple corrosion factors of actual buried soils;

[0025] Normalizing the corrosion rate expectation function and the measured corrosion rate of the actually buried pipeline to obtain the corrosion rate of the actually buried pipeline;

[0026] The corrosion rate of the actual buried pipeline and multiple corrosion factors of the soil in which the pipeline is actually buried are added to the pipeline corrosion data.

[0027] In one possible implementation, the corrosion rate expected function and the measured corrosion rate of the actually buried pipeline are normalized to obtain the actual corrosion rate of the buried pipeline.

[0028] The corrosion rate of the actual buried pipeline is obtained by normalizing the corrosion rate expectation function, the first formula, and the measured corrosion rate of the actual buried pipeline. The first formula is:

[0029]

[0030] Where V a is the normalized corrosion rate of the actual buried pipeline, t1 is the time node when the actual buried pipeline is sampled, V1 is the measured corrosion rate of the actual buried pipeline at the time node t1, and V0 is the long-term corrosion rate in highly corrosive soil areas.

[0031] In a second aspect, an embodiment of the present invention provides a method for constructing a pipeline corrosion rate prediction model, comprising:

[0032] Acquire a plurality of corrosion data, wherein the corrosion data includes a long-term average corrosion rate and a plurality of soil corrosion factors, and the plurality of corrosion data are acquired using the pipeline corrosion data acquisition method according to the first aspect or any possible implementation of the first aspect;

[0033] Constructing an initial model, wherein the initial model is constructed based on a neural network;

[0034] dividing the plurality of corrosion data into a training data set and a test data set;

[0035] Training step: inputting multiple corrosion data of the training data set into the initial model to train the initial model until the output error of the initial model is lower than a threshold;

[0036] Inputting multiple corrosion data of the test data set into the initial model, obtaining a test error of the initial model, and if the test error is higher than a threshold, adjusting the structure of the initial model and jumping to the training step.

[0037] In one possible implementation, the neural network model is an Elman neural network model, comprising: an input layer, a hidden layer, an output layer, and a receiving layer;

[0038] The number of nodes in the input layer is the same as the number of multiple soil corrosion factors in the corrosion data;

[0039] The output layer includes a long-term average corrosion rate output node, and the activation function of the long-term average corrosion rate output node is:

[0040] f(x)=kx+d

[0041] Wherein, f(x) is the activation function of the long-term average corrosion rate output node, k is the weight coefficient, and d is the first bias;

[0042] The number of nodes in the hidden layer is determined according to a first formula, the number of nodes in the input layer, and the number of nodes in the output layer. The first formula is:

[0043] S=(a0+b0)*0.4+c

[0044] Where S is the number of hidden layer nodes, a0 is the number of input layer nodes, b0 is the number of output layer nodes, and c is the second bias;

[0045] The adjusting the structure of the initial model includes increasing or decreasing the number of nodes in the hidden layer.

[0046] In a third aspect, an embodiment of the present invention provides an operation and maintenance device for power metering equipment, comprising:

[0047] a corrosion data acquisition module, configured to acquire a plurality of corrosion data, wherein the corrosion data includes a long-term average corrosion rate and a plurality of soil corrosion factors, wherein the plurality of corrosion data are acquired using the pipeline corrosion data acquisition method according to the first aspect or any possible implementation of the first aspect;

[0048] An initial model building module, used to build an initial model, wherein the initial model is built based on a neural network;

[0049] A data classification module, configured to divide the plurality of corrosion data into a training data set and a test data set;

[0050] A training module is used to implement a training step: inputting a plurality of corrosion data of the training data set into the initial model to train the initial model until an output error of the initial model is lower than a threshold;

[0051] as well as,

[0052] The testing module is used to input multiple corrosion data of the test data set into the initial model, obtain the test error of the initial model, and if the test error is higher than a threshold, adjust the structure of the initial model and jump to the training step.

[0053] In a fourth aspect, an embodiment of the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, it implements the steps of the method described in the second aspect or any possible implementation of the second aspect.

[0054] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the method described in the second aspect or any possible implementation of the second aspect.

[0055] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0056] An embodiment of the present invention discloses a pipeline corrosion data acquisition method. The method first acquires multiple typical corrosive soils, wherein the typical corrosive soils are corrosive to pipelines. Then, multiple pipeline samples are buried in each of the typical corrosive soils. Next, the pipeline samples are sequentially removed from the multiple typical corrosive soils at predetermined time points. Finally, for each of the typical corrosive soils, a maximum corrosion rate and multiple soil corrosion factors are obtained as pipeline corrosion data. The soil corrosion factors represent factors affecting the pipeline corrosion rate at the location where the pipeline is laid, and the maximum corrosion rate is obtained based on the multiple pipeline samples removed from the typical corrosive soils. The embodiment of the present invention acquires pipeline corrosion data using the samples and corrosive soils, and fits corrosion curves based on the existing data. Therefore, the acquired corrosion data can accurately reflect the relationship between the dependent variable and the independent variable, and the acquired data is more accurate and reliable.

[0057] The pipeline corrosion rate prediction model construction method of the embodiment of the present invention is constructed using a neural network model. The data obtained by the pipeline corrosion data implementation method of the present invention can predict the long-term corrosion rate based on the corrosion factors of the soil. Combined with the corrosion margin, the service life of the metal pipeline can be more accurately assessed. Therefore, pipelines that meet user needs can be designed based on soil properties to meet customer needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only 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 labor.

[0059] Figure 1 is a flow chart of a pipeline corrosion data acquisition method provided by an embodiment of the present invention;

[0060] Figure 2 This is a flow chart of a pipeline corrosion rate prediction model construction method provided by an embodiment of the present invention;

[0061] Figure 3 This is a basic structural diagram of the Elman neural network model provided by an embodiment of the present invention;

[0062] Figure 4 This is a functional block diagram of a pipeline corrosion rate prediction model building device provided by an embodiment of the present invention;

[0063] Figure 5 This is a functional block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in alternative embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0065] In order to make the objectives, technical solutions and advantages of the present invention more clear, the following will be described through specific implementation methods in conjunction with the accompanying drawings.

[0066] The following is a detailed description of an embodiment of the present invention. This example is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiment.

[0067] Figure 1 A flow chart of constructing a pipeline corrosion rate prediction model provided by an embodiment of the present invention.

[0068] like Figure 1 As shown, it shows a flow chart of the implementation method of the pipeline corrosion rate prediction model construction method provided by the first aspect of the embodiment of the present invention, which is detailed as follows:

[0069] In step 101, a plurality of typical corrosive soils are obtained, wherein the typical corrosive soils have a corrosive effect on pipelines.

[0070] In step 102, for each of the typical corrosive soils, a plurality of pipeline specimens are buried.

[0071] In some embodiments, burying a plurality of pipeline specimens for each typical corrosive soil comprises:

[0072] The material base of the pipeline sample is a metal pipe, a zinc coating is sprayed on the outside of the metal pipe, and an organic finishing coating is sprayed on the zinc coating;

[0073] After the pipe samples are sealed and dried, they are placed horizontally at the bottom of the test pit in the order of their types. The intervals between the pipe samples and between the pipe samples and the edge of the test pit are greater than a preset value. Soil is spread on the pipe samples so that the soil around the front, back, left, right, top and bottom of the pipe samples is dense and has no gaps.

[0074] For example, in some application scenarios, D1, D2, D3, ..., Dm typical corrosive soil areas are selected as metal pipe burial test sites, where m is 4 to 20. 4 to 15 test pits for burying samples are excavated in each area to prepare the required metal pipe samples.

[0075] The base material of the metal pipe sample is a metal pipe such as a ductile iron pipe or a steel pipe. First, a zinc coating is arc sprayed on the outside of the metal pipe. The unit weight of the zinc coating is 130g / m 2 ~200g / m 2 Then, an organic finishing coating is sprayed on the zinc coating, with a thickness of 70 to 150 microns. (The presence of the coating is not a necessary and sufficient condition, but only one of the factors).

[0076] The pipes were then processed into the required sample size in the workshop, with the sample size being a DN100×100mm pipe section. Three to ten parallel samples were prepared for each coating cycle, and the edges of the samples were sealed. The coated samples were dried for a week, allowing the coating to completely dry before packaging and transporting them to the aforementioned typical soil testing stations. The samples were unpacked and placed horizontally at the bottom of the test pit in the order of their type. They were secured with soil and compacted. The spacing between the samples and the edges of the test pit was greater than 150mm, and the soil around the front, back, left, right, top, and bottom of the samples was ensured to be dense and free of gaps. The excavated soil was then backfilled in the original order.

[0077] In step 103, pipeline samples are sequentially taken from the plurality of typical corrosive soils according to predetermined time points.

[0078] In step 104, for each typical corrosive soil, a maximum corrosion rate and a plurality of soil corrosion factors are obtained as pipeline corrosion data, wherein the soil corrosion factors represent factors affecting the pipeline corrosion rate at the location where the pipeline is laid, and the maximum corrosion rate is obtained based on a plurality of pipeline samples taken from the typical corrosive soil.

[0079] In some embodiments, the intervals between the predetermined time nodes are set in a gradually increasing pattern;

[0080] The maximum corrosion rates of several pipeline specimens taken from the typical corrosive soils include:

[0081] For each pipeline specimen, obtain the corrosion pit depth data of the deepest corrosion pit;

[0082] According to a predetermined time node, converting a plurality of corrosion pit depth data into maximum corrosion pit rate data at the corresponding time node;

[0083] According to multiple time nodes and multiple maximum corrosion pit rate data corresponding to the multiple time nodes, a corrosion rate expectation function is constructed. The corrosion rate expectation function is:

[0084] V=a·t b

[0085] Where V is the corrosion rate in a typical corrosive soil area, a is the leading constant, b is the trailing constant, and t is time.

[0086] For example, after burying the pipeline sample, excavation and testing are carried out sequentially according to a predetermined excavation cycle sequence, T1, T2, T3, ..., Tn. The excavation cycle n can be set to 3 to 12 cycles, following the principle of dense first and sparse later (regularly, the interval period gradually increases). It can be 0.082 years, 0.164 years, 0.247 years, or 7 years. Alternatively, it can be 0.082 years, 0.164 years, 0.247 years, 0.493 years, 1 year, and 7 years. After excavating the sample for each cycle, carefully remove the soil from the sample until it is completely removed. If the soil is strongly adhered and difficult to wipe off, gently rinse it with a soft plastic brush dipped in water to remove it. The sample is dried in a drying oven and removed after 24 hours. Samples are then processed and sampled at the location of the largest pitting pit. The maximum pit depth at the location of the largest pitting pit is measured using a scanning electron microscope (SEM).

[0087] Next, the maximum corrosion pit depth data of the samples at different periods T1, T2, T3, …, Tn are converted into the maximum corrosion rate data V1, V2, V3, …, Vn of the corresponding periods;

[0088] Using the maximum corrosion rate data of different corrosion cycles T1, T2, T3, ..., Tn at locations D1, D2, D3, ..., Dm, m equations of the form: V = a·t b The expected functional relationship of corrosion rate is shown in Figure 2, where V is the corrosion rate, t is the time, and a and b are constants.

[0089] The soil environment with the highest corrosion rate at each location under the longest period Tn condition is defined as the most severe corrosion environment, and its corrosion rate model is set as the reference model. For example, the corrosion rate at location D3 is the highest under Tn condition, and the corrosion rate model at location D3 is set as the reference model, and its corrosion rate under the longest period Tn condition is recorded as V0.

[0090] In some embodiments, after step 104, the following steps are included:

[0091] Obtaining measured corrosion rates of actual buried pipelines and multiple corrosion factors of actual buried soils;

[0092] Normalizing the corrosion rate expectation function and the measured corrosion rate of the actually buried pipeline to obtain the corrosion rate of the actually buried pipeline;

[0093] The corrosion rate of the actual buried pipeline and multiple corrosion factors of the soil in which the pipeline is actually buried are added to the pipeline corrosion data.

[0094] In some embodiments, normalizing the corrosion rate expectation function and the measured corrosion rate of the actually buried pipeline to obtain the corrosion rate of the actually buried pipeline includes:

[0095] The corrosion rate of the actual buried pipeline is obtained by normalizing the corrosion rate expectation function, the first formula, and the measured corrosion rate of the actual buried pipeline. The first formula is:

[0096]

[0097] Where V a is the normalized corrosion rate of the actual buried pipeline, t1 is the time node when the actual buried pipeline is sampled, V1 is the measured corrosion rate of the actual buried pipeline at the time node t1, and V0 is the long-term corrosion rate in highly corrosive soil areas.

[0098] For example, in the acquisition of pipeline corrosion data, corrosion data obtained in the field can also be applied to increase the quantity and provide the necessary conditions for building a more accurate corrosion model.

[0099] For example, the corrosion rate V1 of pipeline excavation tests conducted in different locations such as location A in year t1 is normalized to the corrosion rate data under the longest period Tn. The normalization method is:

[0100]

[0101] V a is the normalized corrosion rate of the actual buried pipeline, t1 is the time node when the actual buried pipeline is sampled, V0 is the corrosion rate corresponding to the longest time node in the highly corrosive soil area, and V1 is the corrosion rate of the actual buried pipeline at the time node t1.

[0102] Finally, the normalized corrosion rate and the corrosion factors of the soil in Site A (such as physical and chemical indicators) are taken as part of the pipeline corrosion data and added to the pipeline corrosion data.

[0103] like Figure 2 As shown, in a second aspect, an embodiment of the present invention provides a method for constructing a pipeline corrosion rate prediction model, comprising:

[0104] Step 201: Acquire a plurality of corrosion data, wherein the corrosion data includes a long-term average corrosion rate and a plurality of soil corrosion factors, and the plurality of corrosion data are acquired using the pipeline corrosion data acquisition method according to the first aspect or any possible implementation of the first aspect;

[0105] Step 202: constructing an initial model, wherein the initial model is constructed based on a neural network;

[0106] Step 203: dividing the plurality of corrosion data into a training data set and a test data set;

[0107] Step 204, a training step: inputting a plurality of corrosion data of the training data set into the initial model to train the initial model until an output error of the initial model is lower than a threshold;

[0108] Step 205: Input multiple corrosion data of the test data set into the initial model to obtain the test error of the initial model. If the test error is higher than a threshold, adjust the structure of the initial model and jump to the training step.

[0109] In some embodiments, the neural network model is an Elman neural network model, comprising: an input layer, a hidden layer, an output layer, and a receiving layer;

[0110] The number of nodes in the input layer is the same as the number of multiple soil corrosion factors in the corrosion data;

[0111] The output layer includes a long-term average corrosion rate output node, and the activation function of the long-term average corrosion rate output node is:

[0112] f(x)=kx+d

[0113] Wherein, f(x) is the activation function of the long-term average corrosion rate output node, k is the weight coefficient, and d is the first bias;

[0114] The number of nodes in the hidden layer is determined according to a first formula, the number of nodes in the input layer, and the number of nodes in the output layer. The first formula is:

[0115] S=(a0+b0)*0.4+c

[0116] Where S is the number of hidden layer nodes, a0 is the number of input layer nodes, b0 is the number of output layer nodes, and c is the second bias;

[0117] The adjusting the structure of the initial model includes increasing or decreasing the number of nodes in the hidden layer.

[0118] For example, soil corrosion factors generally include some physical and chemical factors, such as soil resistivity, redox potential, Cl - 、SO4 2- , water content, pH value, and salt content are input into the model as dependent variables to obtain the expected long-term average corrosion rate.

[0119] In some application scenarios, the prediction model is built based on the Elman neural network model, which is generally divided into four layers: input layer, hidden layer (intermediate layer), receiving layer and output layer. Figure 3As shown, the connections between the input, hidden, and output layers are similar to those of a feedforward network. The Elman neural network is a typical dynamic neural network. Building on the basic structure of a BP network, it stores internal states to map dynamic features, enabling the system to adapt to time-varying characteristics. Due to the small number of training samples, relatively large errors in predictions are possible. This can be avoided by increasing the sample size and removing erroneous data beforehand.

[0120] In the embodiment of the present invention, a network model net is established by using a computer, and the hierarchical structure of the net model includes an input layer, a hidden layer, a receiving layer and an output layer;

[0121] In terms of node setting, first determine the number of influencing factor nodes a0 in the input layer, such as the seven soil corrosion factors (soil resistivity, redox potential, Cl - 、SO4 2- , water content, pH value, salt content), at this time a0=7, that is, a0 corresponding factors are selected from soil corrosion factors.

[0122] Then determine the node number b0 of the output layer, such as the long-term average corrosion rate value of ductile iron pipes, where b0 = 1 (b0 is a defined value, meaning the output data port is 1, a fixed value).

[0123] Next, determine the range of the number of hidden layer nodes. The rule for determining the number of hidden layer nodes is:

[0124] S=(a0+b0)*0.4+c

[0125] Where S is the number of hidden layer nodes, a0 is the number of input layer nodes, b0 is the number of output layer nodes, the constant c = 2 to 9, and the number of hidden layer nodes after calculation is in the range of [m1, m2].

[0126] Next, build the network, debug and train the network, determine the number of hidden layer nodes is m1, and the hidden layer function is

[0127]

[0128] or

[0129]

[0130] The output layer function is:

[0131] f(x)=kx+d

[0132] Among them, a′ is a positive real number, and the determination of d and k values ​​is to determine the parameters of the model.

[0133] Finally, set the network learning rate to 0.1-0.001, the number of network training times to 1000-100000, and the error to 0.1-0.0001 and start network training.

[0134] When the set error is reached within the set number of training times, the network training is completed. After testing and verification, the network parameters can be saved. Otherwise, return to the network establishment step, add 1 to the number of hidden layer nodes, and rebuild the network, hidden layer function, and output layer function until the network converges successfully and the network parameters are saved after testing and verification. The saved network is named net1.

[0135] Based on the corrosion prediction model, the pipeline life and the allowable working pressure of the pipeline for a specified number of years can be predicted. The application of the model is described below with three embodiments.

[0136] Example 1:

[0137] Firstly, four typical corrosive soil areas in my country, A, B, C, and D, were selected as experimental sites for burying ductile iron pipes. The maximum pitting depth data of the excavated test samples were collected according to excavation cycles of 1 month, 2 months, 3 months, and 84 months.

[0138] After SEM testing, it was found that the corrosion rate of site D was the highest among sites A, B, C, and D, with a maximum value of 141.17 μm / a, recorded as V0. Therefore, a corrosion rate prediction model was established with site D as the most severe corrosion model. The specific data are shown in Table 1.

[0139] Table 1 Corrosion rate of buried soil samples at site D

[0140]

[0141] The fitted model is:

[0142] V=207.289t -0.229

[0143] The corrosion rates of the excavated pipelines at site E for 15 years, site F for 16.2 years, site G for 16.2 years, and site H for 6 years are 19.80, 37.60, 33.13, and 1200.00 μm / a, respectively. b ) formula, the 7-year corrosion rates of sites E, F, G, and H were 25.10, 48.45, 42.69, and 1231.81 μm / a, respectively.

[0144] The training data sequence is shown in Table 2.

[0145] Table 2 Training data sequence table

[0146]

[0147] The test data series is shown in Table 3.

[0148] Table 3 Test data sequence table

[0149]

[0150] Use computers to build a network model net, where the model layers include input layer, hidden layer and output layer;

[0151] Determine the number of influencing factor nodes in the input layer to be 6, namely 6 soil corrosion factors (soil resistivity, Cl - 、SO4 2- , water content, pH value, salt content), at this time a0=6;

[0152] Determine the number of nodes b0 in the output layer, which is the long-term average corrosion rate of ductile iron pipes. In this case, b0 = 1. Determining the number of nodes in the hidden layer is another very important step in neural network design. The complexity of this problem has made it difficult to find a good analytical formula so far. In this example, we use the formula:

[0153] S=(a0+b0)*0.4+c

[0154] The number of hidden layer nodes was determined to be between 3 and 12. Then, experiments were conducted on the number of hidden layer nodes from 3 to 12. By comparing the network training results, the number of hidden layer neurons corresponding to the optimal combination of network training error and network training times was selected, as shown in Table 4.

[0155] Table 4 Iterative training of different numbers of nodes in the hidden layer of neural prediction network

[0156]

[0157] As shown in Table 1, the average number of network iterations decreases significantly with increasing hidden layer nodes. However, further increasing the number of nodes does not significantly improve the average number of network iterations. Considering that a greater number of hidden nodes leads to poorer generalization, i.e., poorer recognition of new samples, and considering the number of successful convergences, the maximum number of iterations, and the minimum number of iterations, the number of hidden layer nodes S = 4 was selected for the neural network.

[0158] After many debugging tests, the hidden layer function is determined to be

[0159]

[0160] Determine the output layer function: f(x) = 4x + 6

[0161] Set the network learning rate to 0.05, the number of network training times to 10,000, and the error to 0.01 before starting network training.

[0162] When the error reaches 0.01 within 10,000 training times, the network training is completed. After testing and verification, the network parameters are saved as net2.

[0163] In the established network net2, input the soil physical and chemical properties parameters under the given soil conditions at location u, such as soil resistivity of 44Ω·cm, Cl - The content is 1.6780%, SO4 2- The content is 0.1561%, the water content is 23.95%, the pH value is 8.67, and the salt content is 2.9660%. The expected corrosion rate of the ductile iron pipe calculated using net2 is 15.29μm / a.

[0164] The corrosion allowance calculation formula for pipelines provides a method for determining the corrosion allowance of pipelines based on the minimum wall thickness of the pipeline, the actual allowable working pressure, the safety factor, the outer diameter, and the tensile strength of the pipeline material. The corrosion allowance calculation formula for pipelines is:

[0165]

[0166] Where h is the corrosion allowance of the pipeline, e min is the minimum wall thickness of the pipe, PFA 实际 is the actual allowable working pressure, SF is the safety factor of the actual allowable working pressure, DE is the outer diameter of the pipe, R m is the tensile strength of the pipe material.

[0167] Using the corrosion allowance calculation formula for pipelines, the corrosion allowance for DN100C-grade pipelines under an allowable working pressure of 10 bar is 2.58 mm.

[0168] Then the expected service life of ductile iron pipe is L = 2.58 / 0.01529 = 167.4 years;

[0169] The calculation formula for the allowable working pressure for a predetermined period of time provides a method for determining the allowable working pressure for a predetermined period of time based on the expected long-term average corrosion rate, the minimum wall thickness of the pipeline, the tensile strength of the pipeline material, and the outer diameter of the pipeline. The calculation formula for the allowable working pressure for a predetermined period of time is:

[0170]

[0171] Where p is the allowable working pressure in T0 years, e min is the minimum wall thickness of the pipeline, V3 is the expected long-term average corrosion rate, R m is the tensile strength of the pipe material, and DE is the outer diameter of the pipe.

[0172] Calculate the allowable working pressure p of a DN100 C-grade pipe after a given 100 years; use the allowable working pressure calculation formula for a predetermined number of years

[0173]

[0174] The final output is that the expected service life of the DN100C grade pipeline is 167.4 years, given that the allowable working pressure p of the pipeline after 100 years is 35.3 bar.

[0175] Example 2:

[0176] Firstly, four typical corrosive soil areas in my country, D1, D2, D3 and D4, were selected as experimental sites for burying ductile iron pipes. The maximum pitting depth data of the excavated test samples were collected according to excavation cycles of 0.082 years, 0.164 years, 0.247 years, 0.493 years, 1 year and 7 years.

[0177] SEM testing revealed that among locations D1, D2, D3, and D4, location D4 had the highest corrosion rate, reaching a maximum value of 141.17 μm / a, denoted as V0. Therefore, a corrosion rate prediction model was established using location D4 as the most severely corroded model. The specific data is as follows.

[0178] Table 5 Corrosion rate of bare ductile iron pipe (with pitting) samples buried in soil at location D4

[0179]

[0180] The fitting results are:

[0181] V=205.731t -0.231

[0182] The corrosion rates of the excavated pipelines at D5, D6, D7, and D8 for 15 years, 16.2 years, 16.2 years, and 6 years are 19.80, 37.60, 33.13, and 1200.00 μm / a, respectively. b ) formula, the 7-year corrosion rates of sites D5, D6, D7, and D8 were 25.40, 49.09, 43.26, and 1245.60 μm / a, respectively.

[0183] Then, we collected and analyzed data from other on-site excavated pipelines, using data from 25 locations as training data and data from 5 locations as test data.

[0184] Use computers to build a network model net, the model layer includes input layer, hidden layer, receiving layer and output layer;

[0185] The number of influencing factor nodes in the input layer is determined to be 7, namely 7 soil corrosion factors (soil resistivity, redox potential, Cl - 、SO4 2- , water content, pH value, salt content), at this time a0=7;

[0186] Determine the number of nodes b0 in the output layer, which is the long-term average corrosion rate of ductile iron pipes. In this case, b0 = 1.

[0187] According to the formula:

[0188] S=(a0+b0)*0.4+c

[0189] The number of hidden layer nodes was determined to be between 4 and 15. Then, experiments were conducted on the number of hidden layer nodes from 4 to 15. By comparing the network training results, the number of 12 hidden layer neurons corresponding to the optimal combination of network training error and network training times was selected;

[0190] After many debugging tests, the hidden layer function is determined to be

[0191]

[0192] Where e is a natural constant and a′ is a positive real number.

[0193] Determine the output layer function as:

[0194] f(x)=3.5x+7

[0195] Set the network learning rate to 0.03, the number of network training times to 20,000, and the error to 0.001 before starting network training.

[0196] When the error reaches 0.001 within 20,000 training times, the network training is completed. After testing and verification, the network parameters are saved as net3.

[0197] The physical and chemical properties of the soil at the given location w were input into the established network, such as soil resistivity of 59660 Ω·cm, redox potential of 558.0 mV, Cl - The content is 0.0014%, SO4 2- The content is 0.0010%, the water content is 11.3%, the pH value is 6.9, and the salt content is 0.02%. The expected corrosion rate of the ductile iron pipe is calculated using net3 to be 27.73μm / a.

[0198] The corrosion allowance calculation formula for pipelines provides a method for determining the corrosion allowance of pipelines based on the minimum wall thickness of the pipeline, the actual allowable working pressure, the safety factor, the outer diameter, and the tensile strength of the pipeline material. The corrosion allowance calculation formula for pipelines is:

[0199]

[0200] Where h is the corrosion allowance of the pipeline, e min is the minimum wall thickness of the pipe, PFA 实际 is the actual allowable working pressure, SF is the safety factor of the actual allowable working pressure, DE is the outer diameter of the pipe, R m is the tensile strength of the pipe material.

[0201] Using the corrosion allowance calculation formula for pipelines, the corrosion allowance of DN600 K9 grade pipelines under the condition of an allowable working pressure of 16 bar is calculated to be 4.39 mm;

[0202] Then the expected service life of the ductile iron pipe is L = 4.39 / 0.02773 = 158.3 years;

[0203] The calculation formula for the allowable working pressure for a predetermined period of time provides a method for determining the allowable working pressure for a predetermined period of time based on the expected long-term average corrosion rate, the minimum wall thickness of the pipeline, the tensile strength of the pipeline material, and the outer diameter of the pipeline. The calculation formula for the allowable working pressure for a predetermined period of time is:

[0204]

[0205] Where p is the allowable working pressure in T0 years, e min is the minimum wall thickness of the pipeline, V3 is the expected long-term average corrosion rate, R m is the tensile strength of the pipe material, and DE is the outer diameter of the pipe.

[0206] Calculate the allowable working pressure of DN600 K9 grade pipeline after 60 years; use the allowable working pressure calculation formula for the predetermined working period to calculate that the allowable working pressure of DN600 K9 grade pipeline after 60 years of operation is 2.81 MPa, or 28.1 bar.

[0207] Example 3

[0208] The soil physical and chemical properties of the soil environment in the XX region provided by X Water Company are as follows: soil resistivity is 16980Ω·cm, redox potential is 156.8mV, Cl - The content is 0.325%, SO4 2- The content is 0.782%, the water content is 8.6%, the pH value is 8.3, the salt content is 0.916%, and the allowable working pressure of the transported water is 10 bar. DN100 ductile iron pipe is selected, and the expected service life is 100 years. Please select the appropriate pipe for the customer.

[0209] The calculation and evaluation method net4 was established using the method of the present invention, and the expected corrosion rate of ductile iron pipes was calculated to be 21.87 μm / a.

[0210] The corrosion allowance calculation formula for pipelines provides a method for determining the corrosion allowance of pipelines based on the minimum wall thickness of the pipeline, the actual allowable working pressure, the safety factor, the outer diameter, and the tensile strength of the pipeline material. The corrosion allowance calculation formula for pipelines is:

[0211]

[0212] Where h is the corrosion allowance of the pipeline, e min is the minimum wall thickness of the pipe, PFA 实际 is the actual allowable working pressure, SF is the safety factor of the actual allowable working pressure, DE is the outer diameter of the pipe, R m is the tensile strength of the pipe material.

[0213] Using the corrosion allowance calculation formula for pipelines, the corrosion allowance of DN100 C-grade pipelines under an allowable working pressure of 10 bar is calculated to be 2.58 mm; therefore, the expected service life of the ductile iron pipeline is L = 2.58 / 0.02187 = 117.9 years.

[0214] The above calculation and evaluation show that the use requirements can be met by selecting DN100 C-grade pipes instead of thicker K9-grade pipes, which saves metal resources, saves energy and reduces carbon emissions while meeting user requirements.

[0215] The pipeline corrosion data acquisition method of the present invention first acquires multiple typical corrosive soils, wherein the typical corrosive soils are corrosive to pipelines. Multiple pipeline samples are then buried in each of the typical corrosive soils. The pipeline samples are then sequentially removed from the multiple typical corrosive soils at predetermined time points. Finally, for each of the typical corrosive soils, a maximum corrosion rate and multiple soil corrosion factors are obtained as pipeline corrosion data. The soil corrosion factors represent factors affecting the pipeline corrosion rate at the location where the pipeline is laid, and the maximum corrosion rate is obtained based on the multiple pipeline samples removed from the typical corrosive soils. This embodiment of the present invention acquires pipeline corrosion data using the samples and corrosive soils, and fits corrosion curves based on the existing data. Therefore, the acquired corrosion data accurately reflects the relationship between the dependent and independent variables, making the data more accurate and reliable.

[0216] The pipeline corrosion rate prediction model construction method of the embodiment of the present invention is constructed using a neural network model. The data obtained by the pipeline corrosion data implementation method of the present invention can predict the long-term corrosion rate based on the corrosion factors of the soil. Combined with the corrosion margin, the service life of the metal pipeline can be more accurately assessed. Therefore, pipelines that meet user needs can be designed based on soil properties to meet customer needs.

[0217] It should be understood that the size of the serial numbers of each step in the above embodiment does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0218] The following is an embodiment of the device of the present invention. For details not described in detail, reference may be made to the corresponding method embodiment described above.

[0219] Figure 4 This is a functional block diagram of the power metering equipment operation and maintenance device provided by the embodiment of the present invention, referring to Figure 4 The power metering equipment operation and maintenance device 4 includes: a corrosion data acquisition module 401 , an initial model construction module 402 , a data classification module 403 , a training module 404 and a testing module 405 .

[0220] A corrosion data acquisition module 401 is configured to acquire a plurality of corrosion data, wherein the corrosion data includes a long-term average corrosion rate and a plurality of soil corrosion factors, and the plurality of corrosion data is acquired using the pipeline corrosion data acquisition method according to any one of claims 1 to 5;

[0221] An initial model building module 402 is used to build an initial model, wherein the initial model is built based on a neural network;

[0222] A data classification module 403 is configured to classify the plurality of corrosion data into a training data set and a test data set;

[0223] The training module 404 is configured to implement a training step of inputting a plurality of corrosion data of the training data set into the initial model to train the initial model until an output error of the initial model is lower than a threshold;

[0224] The testing module 405 is used to input multiple corrosion data of the test data set into the initial model, obtain the test error of the initial model, and if the test error is higher than a threshold, adjust the structure of the initial model and jump to the training step.

[0225] Figure 5 : is a functional block diagram of an electronic device provided by an embodiment of the present invention. Figure 5As shown, the electronic device 5 of this embodiment includes: a processor 500 and a memory 501, wherein the memory 501 stores a computer program 502 that can be run on the processor 500. When the processor 500 executes the computer program 502, the steps in the above-mentioned power metering device operation and maintenance method and embodiment are implemented, such as Figure 2 Steps 201 to 205 are shown.

[0226] Illustratively, the computer program 502 may be divided into one or more modules / units, and the one or more modules / units are stored in the memory 501 and executed by the processor 500 to implement the present invention.

[0227] The electronic device 5 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 5 may include, but is not limited to, a processor 500 and a memory 501. Those skilled in the art will understand that Figure 5 It is only an example of the electronic device 5 and does not constitute a limitation of the electronic device 5. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0228] The processor 500 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0229] The memory 501 may be an internal storage unit of the electronic device 5, such as a hard disk or memory of the electronic device 5. The memory 501 may also be an external storage device of the electronic device 5, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 5. Furthermore, the memory 501 may include both an internal storage unit of the electronic device 5 and an external storage device. The memory 501 is used to store the computer program and other programs and data required by the electronic device. The memory 501 may also be used to temporarily store data that has been output or is about to be output.

[0230] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the implementation method can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method implementation method, and will not be repeated here.

[0231] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0232] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0233] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0234] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of this embodiment.

[0235] In addition, the functional units in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0236] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned implementation method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various methods and device implementation methods. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0237] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. 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. 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 various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A pipeline corrosion data acquisition method, characterized in that: include: obtaining a plurality of typical corrosive soils, wherein the typical corrosive soils have a corrosive effect on pipelines; For each of the typical corrosive soils, multiple pipeline specimens are buried; Taking out pipeline samples from the plurality of typical corrosive soils in sequence according to predetermined time points; The soil corrosion factor characterizes the factors affecting the pipeline corrosion rate at the location where the pipeline is laid. For each typical corrosive soil, the maximum corrosion rate and multiple soil corrosion factors are obtained as pipeline corrosion data, including: For each pipeline specimen, obtain the corrosion pit depth data of the deepest corrosion pit; According to a predetermined time node, converting a plurality of corrosion pit depth data into maximum corrosion pit rate data at the corresponding time node; According to multiple time nodes and multiple maximum corrosion pit rate data corresponding to the multiple time nodes, a corrosion rate expectation function is constructed. The corrosion rate expectation function is: V=a·t b Where V is the corrosion rate in a typical corrosive soil area, a is the leading constant, b is the trailing constant, and t is time; Obtaining measured corrosion rates of actual buried pipelines and multiple corrosion factors of actual buried soils; Normalization is performed based on the corrosion rate expectation function, the first formula, and the measured corrosion rate of the actually buried pipeline to obtain the actual corrosion rate of the buried pipeline. The first formula is: Where V a is the normalized corrosion rate of the actual buried pipeline, t1 is the time point when the actual buried pipeline is sampled, V1 is the measured corrosion rate of the actual buried pipeline at time point t1, and V0 is the long-term corrosion rate in highly corrosive soil areas; The corrosion rate of the actual buried pipeline and multiple corrosion factors of the soil in which the pipeline is actually buried are added to the pipeline corrosion data.

2. The pipeline corrosion data acquisition method according to claim 1, characterized in that: For each of the typical corrosive soils, multiple pipeline specimens were buried, including: The material base of the pipeline sample is a metal pipe, a zinc coating is sprayed on the outside of the metal pipe, and an organic finishing coating is sprayed on the zinc coating; After the pipe samples are sealed and dried, they are placed horizontally at the bottom of the test pit in the order of their types. The intervals between the pipe samples and between the pipe samples and the edge of the test pit are greater than a preset value. Soil is spread on the pipe samples so that the soil around the front, back, left, right, top and bottom of the pipe samples is dense and has no gaps.

3. The pipeline corrosion data acquisition method according to claim 1 or 2, characterized in that: The intervals between the multiple predetermined time nodes are set in a gradually increasing pattern.

4. A pipeline corrosion rate prediction model construction method, characterized in that: include: Acquire a plurality of corrosion data, wherein the corrosion data includes a long-term average corrosion rate and a plurality of soil corrosion factors, and the plurality of corrosion data are acquired using the pipeline corrosion data acquisition method according to any one of claims 1 to 3; Constructing an initial model, wherein the initial model is constructed based on a neural network; dividing the plurality of corrosion data into a training data set and a test data set; Training step: inputting multiple corrosion data of the training data set into the initial model to train the initial model until the output error of the initial model is lower than a threshold; Inputting multiple corrosion data of the test data set into the initial model, obtaining a test error of the initial model, and if the test error is higher than a threshold, adjusting the structure of the initial model and jumping to the training step.

5. The pipeline corrosion rate prediction model construction method according to claim 4, characterized in that: The neural network model is an Elman neural network model, including: an input layer, a hidden layer, an output layer and a receiving layer; The number of nodes in the input layer is the same as the number of multiple soil corrosion factors in the corrosion data; The output layer includes a long-term average corrosion rate output node, and the activation function of the long-term average corrosion rate output node is: f(x)=kx+d Wherein, f(x) is the activation function of the long-term average corrosion rate output node, k is the weight coefficient, and d is the first bias; The number of nodes in the hidden layer is determined according to a first formula, the number of nodes in the input layer, and the number of nodes in the output layer. The first formula is: S=(a0+b0)*0.4+c Where S is the number of hidden layer nodes, a0 is the number of input layer nodes, b0 is the number of output layer nodes, and c is the second bias; The adjusting the structure of the initial model includes increasing or decreasing the number of nodes in the hidden layer.

6. A pipeline corrosion rate prediction model construction device, characterized in that: For implementing the pipeline corrosion rate prediction model construction method according to any one of claims 4-5, the pipeline corrosion rate prediction model construction device comprises: a corrosion data acquisition module, configured to acquire a plurality of corrosion data, wherein the corrosion data includes a long-term average corrosion rate and a plurality of soil corrosion factors, and the plurality of corrosion data are acquired using the pipeline corrosion data acquisition method according to any one of claims 1 to 5; An initial model building module, used to build an initial model, wherein the initial model is built based on a neural network; A data classification module, configured to divide the plurality of corrosion data into a training data set and a test data set; A training module is used to implement a training step: inputting a plurality of corrosion data of the training data set into the initial model to train the initial model until an output error of the initial model is lower than a threshold; as well as, The testing module is used to input multiple corrosion data of the test data set into the initial model, obtain the test error of the initial model, and if the test error is higher than a threshold, adjust the structure of the initial model and jump to the training step.

7. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 4 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 4 to 5 are implemented.

Images