A pipeline corrosion prediction method, system, terminal device and storage medium

Abstract

The present application relates to the field of detection of mining pipelines, and in particular to a pipeline corrosion prediction method, system, terminal device and storage medium. The method includes, if there are multiple factor types of target condition corrosion factors, then the target condition corrosion factors are divided into corrosion catalysis factors and additional corrosion factors according to a preset classification strategy, and the corrosion catalysis coefficient corresponding to the corrosion catalysis factor and the additional corrosion coefficient corresponding to the additional corrosion factor are calculated respectively; based on the medium corrosion coefficient, the corrosion catalysis coefficient and the additional corrosion coefficient, the internal corrosion coefficient corresponding to the pipeline is generated, and the first-level corrosion prediction model corresponding to the pipeline is established by combining the medium corrosion coefficient, the corrosion catalysis coefficient, the additional corrosion coefficient and the internal corrosion coefficient. The pipeline corrosion prediction method, system, terminal device and storage medium provided by the present application have the advantages of improving the corrosion prediction effect of mining emulsion transportation pipelines.

Description

Technical Field

[0001] The present application relates to the field of mining pipeline detection, and in particular to a pipeline corrosion prediction method, system, terminal equipment and storage medium. Background Art

[0002] Mining emulsion pipelines are piping systems used to transport mining emulsions. Mining emulsions are an emulsion formed by mixing pulverized coal with water or other additives. They are used in various aspects of coal mining industry production, such as coal mining, coal processing, and mine support. The primary function of mining emulsion pipelines is to transport mining emulsions from one location to another to meet the needs of coal mining production.

[0003] Corrosion prediction for mining emulsion pipelines is a technology that predicts internal corrosion by analyzing factors such as the pipeline's operating environment, material properties, and operating conditions. Its purpose is to identify the likelihood and extent of pipeline corrosion in advance so that appropriate measures can be taken to extend pipeline service life, reduce maintenance costs, and ensure safe operation.

[0004] In practical applications, the accuracy of pipeline corrosion prediction often requires verification through field testing or long-term observation, which consumes a lot of time and resources. As a result, there is a lack of effective corrosion prediction and analysis methods for new pipeline systems or special operating conditions, resulting in poor corrosion prediction results for mining emulsion pipelines. Summary of the Invention

[0005] In order to improve the corrosion prediction effect of mining emulsion transportation pipelines, the present application provides a pipeline corrosion prediction method, system, terminal equipment and storage medium.

[0006] In a first aspect, the present application provides a pipeline corrosion prediction method, comprising the following steps:

[0007] According to the characteristics of the pipeline's conveying medium, obtain the corresponding medium corrosion coefficient;

[0008] If the medium corrosion coefficient exceeds the preset pipeline corrosion threshold, determining whether there are conditional corrosion factors in the pipeline;

[0009] If the conditional corrosion factor exists in the pipeline, determining whether the corrosion parameter corresponding to the conditional corrosion factor exceeds a preset conditional corrosion parameter threshold;

[0010] If the corrosion parameter corresponding to the conditional corrosion factor exceeds the preset conditional corrosion parameter threshold, obtaining the corresponding target conditional corrosion factor, and determining whether the target conditional corrosion factor has multiple factor types;

[0011] If there are multiple factor types for the target condition corrosion factor, the target condition corrosion factor is divided into corrosion catalysis factors and additional corrosion factors according to a preset classification strategy, and the corrosion catalysis coefficient corresponding to the corrosion catalysis factor and the additional corrosion coefficient corresponding to the additional corrosion factor are calculated respectively;

[0012] Generate an internal corrosion coefficient corresponding to the pipeline according to the medium corrosion coefficient, the corrosion catalysis coefficient, and the additional corrosion coefficient, and establish a primary corrosion prediction model corresponding to the pipeline by combining the medium corrosion coefficient, the corrosion catalysis coefficient, the additional corrosion coefficient, and the internal corrosion coefficient;

[0013] Obtaining an internal corrosion parameter attribute table corresponding to the pipeline according to the primary corrosion prediction model, and determining whether there are associated parameter influencing factors corresponding to the internal corrosion parameters in the external environmental factors corresponding to the pipeline according to the internal corrosion parameter attribute table;

[0014] If the external environmental factors include the associated parameter influencing factors corresponding to the internal corrosion parameters, a secondary corrosion prediction model corresponding to the internal corrosion parameters is established by combining the associated parameter influencing factors and the corrosion correlation coefficients corresponding to the associated parameter influencing factors.

[0015] By adopting the above technical solution, first, according to the characteristics of the conveying medium in the pipeline, the most important medium corrosion coefficient of the pipeline can be obtained. On this basis, in order to conduct an in-depth analysis of the corrosion factors inside the pipeline, when the medium corrosion coefficient is abnormal, it is judged whether there are secondary pipeline corrosion or factors affecting the medium corrosion coefficient, namely conditional corrosion factors, in the pipeline. If so, the specific type of conditional corrosion factor and the corrosion influence coefficient are analyzed and calculated respectively, and a corresponding first-level corrosion prediction model is established. If it is analyzed according to the first-level corrosion prediction model that there are associated parameter influencing factors corresponding to the internal corrosion parameters in the external environmental factors corresponding to the pipeline, then in order to increase the comprehensive prediction of pipeline corrosion, the associated parameter influencing factors and the corrosion correlation coefficient corresponding to the associated parameter influencing factors are combined to establish a second-level corrosion prediction model corresponding to the internal corrosion parameters. Since the internal corrosion factors, external corrosion factors and internal and external interactive corrosion influencing factors of the pipeline are comprehensively analyzed, the corresponding corrosion prediction model is established, thereby improving the corrosion prediction effect of the mining emulsion conveying pipeline.

[0016] Optionally, if the corrosion parameter corresponding to the conditional corrosion factor exceeds the preset conditional corrosion parameter threshold, the corresponding target conditional corrosion factor is obtained, and after determining whether the target conditional corrosion factor has multiple factor types, the following steps are further included:

[0017] If the target condition corrosion factor has multiple factor types, determining whether there is a correlation between the multiple factor types corresponding to the target condition corrosion factors;

[0018] If there is a correlation between the multiple factor types and the target condition corrosion factors, then obtaining a corresponding target correlation group;

[0019] Outputting relevant attribute information corresponding to the target related group according to the correlation coefficient between the target condition corrosion factors in the target related group;

[0020] A conditional corrosion analysis report corresponding to the target conditional corrosion factor is generated by combining the target related group and the related attribute information corresponding to the target related group.

[0021] By adopting the above technical solution, the correlation between the corrosion factors of multiple types of target conditions is analyzed and grouped, which can more intuitively observe and analyze the related attribute information between the secondary corrosion factors in the pipeline. This helps to deeply understand the internal corrosion mechanism of the pipeline and thus improve the corrosion prediction effect of the pipeline.

[0022] Optionally, the generating of the conditional corrosion analysis report corresponding to the target conditional corrosion factor by combining the target related group and the related attribute information corresponding to the target related group includes the following steps:

[0023] Acquire a relevant category corresponding to the target related group according to the relevant attribute information;

[0024] Combining the target related groups according to the related categories to form corresponding related sets of the same category;

[0025] The correlation distribution diagram corresponding to the target conditional corrosion factor is generated as the conditional corrosion analysis report by combining the correlation sets of the same category and the correlation degree corresponding to the target correlation group in the correlation sets of the same category.

[0026] By adopting the above technical solution and classifying and combining the target related groups according to their relevant categories, we can better understand the differences and commonalities between different related groups. The conditional corrosion analysis report helps to further analyze and predict corrosion problems, thereby improving the corrosion prediction effect of pipelines.

[0027] Optionally, if the corrosion parameter corresponding to the conditional corrosion factor exceeds the preset conditional corrosion parameter threshold, the corresponding target conditional corrosion factor is obtained, and after determining whether the target conditional corrosion factor has multiple factor types, the following steps are further included:

[0028] If the target condition corrosion factor has a single factor type, determining whether the target condition corrosion factor has multiple sub-condition factors of the same type;

[0029] If the target condition corrosion factor has multiple similar sub-condition factors, periodic corrosion analysis is performed on the corrosion parameters corresponding to each of the similar sub-condition factors to generate a corresponding corrosion prediction curve;

[0030] The similar sub-condition factors and the corrosion prediction curves corresponding to the similar sub-condition factors are combined to generate a corresponding similar corrosion factor analysis table.

[0031] By adopting the above technical solution, the similar corrosion factor analysis table can integrate the information of each similar sub-condition factor, and compare and analyze their impact and trend on corrosion behavior. Through the generation of the similar corrosion factor analysis table, we can have a more comprehensive understanding of the role and importance of different similar sub-condition factors, provide guidance and decision-making basis for corrosion prediction and control, thereby improving the corrosion prediction effect of pipelines.

[0032] Optionally, if the target condition corrosion factor has multiple factor types, the target condition corrosion factor is divided into corrosion catalysis factors and additional corrosion factors according to a preset classification strategy, and the corrosion catalysis coefficient corresponding to the corrosion catalysis factor and the additional corrosion coefficient corresponding to the additional corrosion factor are calculated respectively, and the following steps are further included:

[0033] Performing time series analysis on the corrosion catalysis coefficient and the additional corrosion coefficient respectively to obtain corresponding change trend data;

[0034] According to the change trend data, a trend curve graph corresponding to the corrosion catalysis factor and the additional corrosion factor is generated.

[0035] By adopting the above technical solution, based on the change trend data obtained by time series analysis, we can more accurately understand the change trends of corrosion catalysis factors and additional corrosion factors. These data can reflect the intensity and development trend of corrosion catalysis and additional corrosion, providing an important reference basis for corrosion prediction, thereby improving the corrosion prediction effect of pipelines.

[0036] Optionally, after generating the trend curve graph corresponding to the corrosion catalytic factor and the additional corrosion factor according to the change trend data, the method further includes the following steps:

[0037] Identifying the trend curve graph, and obtaining a correlation between the corrosion catalysis coefficient and the additional corrosion coefficient;

[0038] If the correlation is positive, the corrosion catalysis rate corresponding to the corrosion catalysis coefficient and the additional corrosion rate corresponding to the additional corrosion coefficient are calculated respectively;

[0039] generating a corresponding target corrosion rate according to the corrosion catalysis rate and the medium corrosion coefficient;

[0040] The target corrosion rate and the additional corrosion rate are combined to generate a predicted corrosion analysis report corresponding to the pipeline.

[0041] By adopting the above technical solution, if there is a positive correlation between the corrosion catalysis coefficient and the additional corrosion coefficient, the influence between them can be quantified by calculating the corrosion catalysis rate and the additional corrosion rate. The corrosion catalysis rate can be used to evaluate the intensity of corrosion catalysis, while the additional corrosion rate can be used to evaluate the degree of additional corrosion, thereby providing more comprehensive data analysis support for pipeline corrosion prediction and improving the prediction effect of pipeline corrosion.

[0042] Optionally, after identifying the trend curve and obtaining the correlation between the corrosion catalysis coefficient and the additional corrosion coefficient, the method further includes the following steps:

[0043] If the correlation is negative, obtaining a balance coefficient corresponding to the corrosion catalysis coefficient and the additional corrosion coefficient;

[0044] According to the balance coefficient, obtaining the condition influencing parameter corresponding to the medium corrosion coefficient;

[0045] The internal corrosion coefficient corresponding to the pipeline is generated by combining the medium corrosion coefficient and the condition influencing parameters.

[0046] By adopting the above technical solution, based on the balance coefficient, condition influencing parameters and internal corrosion coefficient, we can gain an in-depth understanding of the mechanism and influencing factors of pipeline corrosion, provide comprehensive data support for pipeline corrosion prediction, and thus improve the prediction effect of pipeline corrosion.

[0047] In a second aspect, the present application provides a pipeline corrosion prediction system, comprising:

[0048] An acquisition module is used to obtain the corresponding medium corrosion coefficient according to the characteristics of the pipeline conveying medium;

[0049] A conditional corrosion identification module is used to determine whether there are conditional corrosion factors in the pipeline if the medium corrosion coefficient exceeds a preset pipeline corrosion threshold;

[0050] A conditional corrosion analysis module, if the conditional corrosion factor exists in the pipeline, the conditional corrosion analysis module is used to determine whether the corrosion parameter corresponding to the conditional corrosion factor exceeds a preset conditional corrosion parameter threshold;

[0051] a multi-factor analysis module, wherein if the corrosion parameter corresponding to the conditional corrosion factor exceeds the preset conditional corrosion parameter threshold, the multi-factor analysis module is used to obtain the corresponding target conditional corrosion factor and determine whether the target conditional corrosion factor has multiple factor types;

[0052] A classification calculation module, if the target condition corrosion factor has multiple factor types, the classification calculation module is used to divide the target condition corrosion factor into corrosion catalysis factors and additional corrosion factors according to a preset classification strategy, and respectively calculate the corrosion catalysis coefficient corresponding to the corrosion catalysis factor and the additional corrosion coefficient corresponding to the additional corrosion factor;

[0053] a first-level corrosion prediction module, configured to generate an internal corrosion coefficient corresponding to the pipeline based on the medium corrosion coefficient, the corrosion catalysis coefficient, and the additional corrosion coefficient, and to establish a first-level corrosion prediction model corresponding to the pipeline by combining the medium corrosion coefficient, the corrosion catalysis coefficient, the additional corrosion coefficient, and the internal corrosion coefficient;

[0054] an association analysis module, configured to obtain an internal corrosion parameter attribute table corresponding to the pipeline according to the primary corrosion prediction model, and determine, based on the internal corrosion parameter attribute table, whether there are associated parameter influencing factors corresponding to the internal corrosion parameters in the external environmental factors corresponding to the pipeline;

[0055] The secondary corrosion prediction module is used to establish a secondary corrosion prediction model corresponding to the internal corrosion parameter by combining the associated parameter influencing factor and the corrosion correlation coefficient corresponding to the associated parameter influencing factor if the associated parameter influencing factor corresponding to the internal corrosion parameter exists in the external environmental factors.

[0056] By adopting the above technical solution, first, according to the characteristics of the conveying medium in the pipeline, the most important medium corrosion coefficient of the pipeline can be obtained. On this basis, in order to conduct an in-depth analysis of the corrosion factors inside the pipeline, when the medium corrosion coefficient is abnormal, the conditional corrosion identification module is used to determine whether there are secondary pipeline corrosion or factors affecting the medium corrosion coefficient, namely conditional corrosion factors, in the pipeline. If so, the specific type of conditional corrosion factor and the corrosion influence coefficient are analyzed and calculated respectively by the conditional corrosion analysis module, and a corresponding first-level corrosion prediction model is established. If, according to the first-level corrosion prediction model, it is analyzed that there are associated parameter influencing factors corresponding to the internal corrosion parameters in the external environmental factors corresponding to the pipeline, then in order to increase the comprehensive prediction strength of pipeline corrosion, the second-level corrosion prediction module is combined with the associated parameter influencing factors and the corrosion correlation coefficient corresponding to the associated parameter influencing factors to establish a second-level corrosion prediction model corresponding to the internal corrosion parameters. Since the internal corrosion factors, external corrosion factors and internal and external interactive corrosion influencing factors of the pipeline are comprehensively analyzed, the corresponding corrosion prediction model is established, thereby improving the corrosion prediction effect of the mining emulsion conveying pipeline.

[0057] In a third aspect, the present application provides a terminal device that adopts the following technical solution:

[0058] A terminal device includes a memory and a processor. The memory stores computer instructions that can be run on the processor. When the processor loads and executes the computer instructions, the above-mentioned pipeline corrosion prediction method is adopted.

[0059] By adopting the above technical solution, the above pipeline corrosion prediction method is generated into computer instructions and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0060] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0061] A computer-readable storage medium stores computer instructions. When the computer instructions are loaded and executed by a processor, the above-mentioned pipeline corrosion prediction method is adopted.

[0062] By adopting the above technical solution, the above pipeline corrosion prediction method is generated into computer instructions and stored in a computer-readable storage medium so as to be loaded and executed by a processor. The computer-readable storage medium facilitates the reading and storage of computer instructions.

[0063] In summary, the present application includes at least one of the following beneficial technical effects: First, according to the characteristics of the conveying medium in the pipeline, the most important medium corrosion coefficient of the pipeline can be obtained. On this basis, in order to conduct an in-depth analysis of the corrosion factors inside the pipeline, when the medium corrosion coefficient is abnormal, it is judged whether there are secondary pipeline corrosion or factors affecting the medium corrosion coefficient, namely conditional corrosion factors, in the pipeline. If so, the specific type of conditional corrosion factor and the corrosion influence coefficient are analyzed and calculated respectively, and a corresponding first-level corrosion prediction model is established. If it is analyzed according to the first-level corrosion prediction model that there are associated parameter influencing factors corresponding to the internal corrosion parameters in the external environmental factors corresponding to the pipeline, then in order to increase the comprehensive prediction of pipeline corrosion, the associated parameter influencing factors and the corrosion correlation coefficient corresponding to the associated parameter influencing factors are combined to establish a second-level corrosion prediction model corresponding to the internal corrosion parameters. Since the internal corrosion factors, external corrosion factors and internal and external interactive corrosion influencing factors of the pipeline are comprehensively analyzed, the corresponding corrosion prediction model is established, thereby improving the corrosion prediction effect of the mining emulsion conveying pipeline. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a flow chart of steps S101 to S108 in a pipeline corrosion prediction method of the present application.

[0065] Figure 2 It is a flow chart of steps S201 to S204 in a pipeline corrosion prediction method of the present application.

[0066] Figure 3 It is a flow chart of steps S301 to S303 in a pipeline corrosion prediction method of the present application.

[0067] Figure 4 It is a flow chart of steps S401 to S403 in a pipeline corrosion prediction method of the present application.

[0068] Figure 5 This is a flow chart of steps S501 to S502 in a pipeline corrosion prediction method of the present application.

[0069] Figure 6 It is a flow chart of steps S601 to S604 in a pipeline corrosion prediction method of the present application.

[0070] Figure 7 This is a flow chart of steps S701 to S703 in a pipeline corrosion prediction method of the present application.

[0071] Figure 8 This is a module diagram of a pipeline corrosion prediction system of the present application.

[0072] Description of reference numerals:

[0073] 1. Acquisition module; 2. Conditional corrosion identification module; 3. Conditional corrosion analysis module; 4. Multi-factor analysis module; 5. Classification calculation module; 6. Primary corrosion prediction module; 7. Association module; 8. Secondary corrosion prediction module. DETAILED DESCRIPTION

[0074] The following is combined with Figure 1-8 This application is described in further detail.

[0075] The present application discloses a pipeline corrosion prediction method, such as Figure 1 As shown, the following steps are included:

[0076] S101. Obtain the corresponding medium corrosion coefficient according to the characteristics of the pipeline conveying medium;

[0077] S102. If the medium corrosion coefficient exceeds the preset pipeline corrosion threshold, determine whether there are conditional corrosion factors in the pipeline;

[0078] S103. If a conditional corrosion factor exists in the pipeline, determine whether the corrosion parameter corresponding to the conditional corrosion factor exceeds a preset conditional corrosion parameter threshold;

[0079] S104. If the corrosion parameter corresponding to the conditional corrosion factor exceeds the preset conditional corrosion parameter threshold, obtain the corresponding target conditional corrosion factor and determine whether the target conditional corrosion factor has multiple factor types;

[0080] S105. If the target condition corrosion factor has multiple factor types, classify the target condition corrosion factor into corrosion catalysis factors and additional corrosion factors according to a preset classification strategy, and calculate the corrosion catalysis coefficient corresponding to the corrosion catalysis factor and the additional corrosion coefficient corresponding to the additional corrosion factor respectively;

[0081] S106. Generate an internal corrosion coefficient corresponding to the pipeline based on the medium corrosion coefficient, corrosion catalysis coefficient, and additional corrosion coefficient. Combined with the medium corrosion coefficient, corrosion catalysis coefficient, additional corrosion coefficient, and internal corrosion coefficient, establish a primary corrosion prediction model corresponding to the pipeline.

[0082] S107. Obtain an internal corrosion parameter attribute table corresponding to the pipeline according to the primary corrosion prediction model, and determine whether there are associated parameter influencing factors corresponding to the internal corrosion parameters in the external environmental factors corresponding to the pipeline according to the internal corrosion parameter attribute table;

[0083] S108. If there are correlation parameter influencing factors corresponding to the internal corrosion parameters in the external environmental factors, then a secondary corrosion prediction model corresponding to the internal corrosion parameters is established by combining the correlation parameter influencing factors and the corrosion correlation coefficients corresponding to the correlation parameter influencing factors.

[0084] In practical applications, internal corrosion of mining emulsion pipelines is generally more damaging than external corrosion. Therefore, to improve the accuracy of pipeline corrosion prediction, we first analyze the main corrosion factors of pipelines.

[0085] Internal corrosion refers to the corrosion caused by the interaction between the internal surface of the pipeline and the conveying medium, primarily due to factors such as the chemical properties, temperature, and flow rate of the conveying medium. Internal corrosion can lead to thinning of the pipeline wall, the formation of corrosion pits, and the production of corrosion products, thereby reducing the strength and durability of the pipeline. Furthermore, because internal corrosion is difficult to detect promptly, by the time it is discovered, it is usually already at a certain level of corrosion, potentially requiring more frequent repairs and replacement of the pipeline.

[0086] In contrast, external corrosion refers to the corrosion caused by the interaction between the outer surface of a pipeline and the external environment (such as the atmosphere and soil). While external corrosion can also cause corrosion on the pipeline surface and produce corrosion products, its effects are more superficial than those of internal corrosion and generally do not directly impact the strength and durability of the pipeline. Furthermore, external corrosion is relatively easy to detect and can be minimized through regular visual inspections and protective measures.

[0087] In step S101, the characteristics of the transport medium refer to the features and properties of the material being transported within the mining emulsion pipeline. For example, the chemical properties of the transport medium, such as the chemical composition and reactivity of the emulsion, can affect the pipeline material and its corrosion behavior. Acidic emulsions can corrode pipelines, while emulsions containing flammable substances can cause fires or explosions.

[0088] To understand the characteristics of the medium being transported within a pipeline, a pH meter installed within the pipeline can be used to measure the pH value of the emulsion, which reflects the acidity or alkalinity of the emulsion. A densitometer installed within the pipeline can also be used to measure the density of the emulsion. By measuring the density of the medium being transported at different concentrations or temperatures, the density variation pattern of the medium can be understood.

[0089] Furthermore, the medium corrosion coefficient is a parameter that describes the degree of corrosion caused by the medium transported within the pipeline. It reflects the compatibility and interaction between the medium and the pipeline material. Different media may cause different degrees of corrosion to different pipeline materials. The medium corrosion coefficient can be used to assess the corrosion risk of the transported medium on the pipeline.

[0090] Specifically, data on the corrosion of different pipeline materials by the medium transported within the pipeline can be collected. This data can include corrosion rate, corrosion form, corrosion products, and more. Based on the collected corrosion data, the corresponding medium corrosion coefficient can be calculated. Generally speaking, the medium corrosion coefficient is a dimensionless indicator that can be expressed as the ratio of the medium corrosion rate to the corrosion rate of a standard medium.

[0091] In step S102, the preset pipeline corrosion threshold refers to the minimum value that the medium corrosion coefficient must meet when corrosion occurs, which is set according to factors such as pipeline material, medium characteristics and working conditions during the design or operation of the transmission pipeline.

[0092] Furthermore, if the current medium corrosion coefficient exceeds the preset pipeline corrosion threshold, it means that the conveying medium in the pipeline has begun to cause corrosion damage to the inner wall of the pipeline. In order to simultaneously analyze other minor corrosion factors in the pipeline, it is determined whether there are corresponding conditional corrosion factors in the pipeline. Conditional corrosion refers to the phenomenon that under specific environmental conditions, even if the medium itself is not highly corrosive, the pipeline material may corrode due to the influence of other factors.

[0093] For example, humidity. In a high humidity environment, the moisture in the pipeline may react with the pipeline material to form corrosive substances, leading to increased corrosion; oxygen content. Oxygen is one of the common corrosion factors. If the oxygen content in the pipeline is high, it is easy to cause corrosion of the pipeline material; flow rate. High-speed flowing media may increase the scouring effect in the pipeline, causing greater corrosion of the pipeline material. In addition, suspended particles or solid particles in the fluid may also cause wear and corrosion to the pipeline material.

[0094] Specifically, when the corrosion coefficient of the medium in the pipeline exceeds the preset corrosion threshold, it indicates that the underlying corrosion factors already exist within the pipeline. This means that the exacerbation of medium corrosion is not only determined by the corrosive properties of the medium itself, but also influenced by other factors. Therefore, further analysis and evaluation of factors related to the pipeline environment and the medium are necessary.

[0095] For example, in mining emulsion pipelines, the effects of temperature and flow rate on corrosion are usually only considered when the medium corrosion coefficient is high. Specifically, when the medium corrosion coefficient is low, the effects of temperature and flow rate on corrosion may be negligible. However, when the medium corrosion coefficient is high, temperature and flow rate may have a significant impact on the corrosion rate. Generally speaking, when the medium corrosion coefficient reaches a certain threshold, the effects of temperature and flow rate on corrosion need to be considered. The determination of the specific threshold may be affected by many factors, such as the corrosion resistance of the pipeline material, the chemical properties of the conveying medium, and the operating conditions.

[0096] In practical applications, empirical or experimental evaluation can be used to determine when the effects of temperature and flow rate on corrosion need to be considered. The effects of temperature and flow rate on corrosion are interrelated, and they can exacerbate or slow down the corrosion rate. Therefore, when considering the effects of temperature and flow rate on corrosion, it is necessary to consider the combined effects of these two factors.

[0097] Furthermore, if the medium corrosion coefficient does not exceed the preset pipeline corrosion threshold, other corrosion factors in the pipeline are directly obtained and analyzed, and corresponding analysis results are obtained.

[0098] In step S103, the preset conditional corrosion parameter threshold is the minimum threshold standard of the conditional corrosion parameter allowed for the occurrence of corrosion effects, which is set in combination with factors such as the corrosion resistance of the pipeline material, medium characteristics, and working conditions.

[0099] Furthermore, if the corrosion parameter corresponding to the conditional corrosion factor exceeds the preset conditional corrosion parameter threshold, it indicates that the conditional corrosion factor in the current pipeline has begun to take effect, causing additional corrosion to the pipeline inner wall or catalyzing or inhibiting the corrosion coefficient of the medium. For example, high temperature environments may cause thermal oxidation corrosion, while high humidity may cause electrochemical corrosion.

[0100] Furthermore, if there are conditional corrosion factors inside the pipeline, the internal corrosion rate of the pipeline can be generated directly based on the medium corrosion coefficient of the medium transported in the pipeline.

[0101] In step S104, to further analyze the target corrosion factors that meet the requirements, it is determined whether the target corrosion factors contain multiple factor types. For example, the target corrosion factor is the flow rate of the medium transported within the pipeline, which can directly corrode the inner wall of the pipeline. Another example is temperature, which is a key factor affecting medium corrosion. Generally, the corrosion rate of the medium increases with increasing temperature. In high-temperature environments, the chemical reaction rate in the medium accelerates, leading to increased corrosion and indirectly affecting the inner wall of the pipeline.

[0102] Furthermore, if the corrosion parameter corresponding to the conditional corrosion factor does not exceed the preset conditional corrosion parameter threshold, the corrosion parameter corresponding to the monitoring conditional corrosion factor continues to be acquired in real time.

[0103] In step S105 , if the target condition corrosion factor has multiple factor types, in order to analyze the multiple types of target condition corrosion factors more specifically and normatively, the target condition corrosion factors are classified and analyzed according to a preset classification strategy.

[0104] The pre-defined classification strategy categorizes multiple factors based on their direct or indirect corrosion impact on the pipeline. Corrosion catalytic factors are the primary factors that cause changes in the medium's corrosion coefficient, including temperature, salinity, and oxygen content. These factors are typically the effects of the medium's inherent properties or environmental conditions. Additional corrosion factors, such as flow velocity, are factors unrelated to the medium's inherent properties that can directly cause additional corrosion on the pipeline's inner wall. These factors can increase the severity of corrosion.

[0105] Furthermore, based on experimental or empirical data on corrosion catalytic factors, the corresponding corrosion catalytic coefficient is calculated for each factor. The corrosion catalytic coefficient represents the degree to which that factor affects the corrosion rate corresponding to the medium's corrosion coefficient. For example, the change in the corrosion rate of the inner wall of a metal pipe at different temperatures can be used to convert the relationship between temperature and corrosion rate into a corrosion catalytic coefficient.

[0106] Secondly, similar to the corrosion catalysis coefficient, the additional corrosion coefficient corresponding to each additional corrosion factor can also be calculated based on experimental or empirical data. The additional corrosion coefficient represents the additional increase in the corrosion rate caused by the factor.

[0107] Specifically, the classification and calculation of corrosion catalytic factors and additional corrosion factors are intended to better understand the mechanisms and influencing factors of corrosion in pipeline media. By calculating the corrosion catalytic coefficient and additional corrosion coefficient, the contribution of each specific category of factors to the corrosion rate can be quantified, thereby better evaluating and predicting corrosion conditions in pipelines.

[0108] Furthermore, if the target condition corrosion factor has a single factor type, the target condition corrosion factor of the single factor type is directly confirmed, and the pipeline corrosion situation is analyzed and explained based on the properties of the target condition corrosion factor.

[0109] In step S106, the internal corrosion coefficient refers to the degree of internal corrosion of the pipeline. It is a comprehensive reflection of the medium corrosion coefficient, the corrosion catalysis coefficient, and the additional corrosion coefficient. The internal corrosion coefficient corresponding to the pipeline can be obtained by multiplying the medium corrosion coefficient with the corrosion catalysis coefficient and adding the additional corrosion coefficient.

[0110] Furthermore, the medium corrosion coefficient, corrosion catalysis coefficient, additional corrosion coefficient, and internal corrosion coefficient can be used as input variables, and the corrosion rate can be used as the output variable. By statistically analyzing multiple sample data, a regression model or artificial neural network model can be established to predict the corrosion rate of the pipeline.

[0111] Among them, by generating the internal corrosion coefficient and establishing a corrosion prediction model, the corrosion condition inside the pipeline can be better evaluated and predicted. The internal corrosion coefficient comprehensively considers the influence of the medium corrosion coefficient, the corrosion catalysis coefficient and the additional corrosion coefficient, and can more comprehensively describe the degree of internal corrosion of the pipeline. At the same time, the corrosion rate of the pipeline can be predicted based on different input variables, which helps to take corresponding maintenance and protection measures in a timely manner.

[0112] In step S107, an internal corrosion parameter attribute table corresponding to the pipeline is obtained based on the primary corrosion prediction model. By performing model prediction on a certain amount of sample data, the predicted corrosion rate of the pipeline under different internal corrosion parameter conditions is obtained. The internal corrosion parameter attribute table may include attributes such as the internal corrosion coefficient, medium corrosion coefficient, corrosion catalysis coefficient, and additional corrosion coefficient of the pipeline.

[0113] By analyzing the aforementioned internal corrosion parameter attribute table, it is possible to determine whether the external environmental factors corresponding to the pipeline contain factors influencing the associated parameters corresponding to the internal corrosion parameters. For example, if the internal corrosion parameter attribute table shows that the corrosion rate increases when the medium corrosion coefficient is high, this indicates that the medium properties in the external environmental factors may affect the internal corrosion parameters of the pipeline. For example, if the pipeline is frequently subjected to vibration and impact, the medium inside the pipeline will cause friction and collision with the pipeline surface, accelerating the occurrence of corrosion.

[0114] In step S108, a secondary corrosion prediction model can be established using methods such as multivariate regression, artificial neural networks, and support vector machines. The basic idea of ​​the model is to use existing sample data, take the internal corrosion parameters as target variables, and the factors affecting the associated parameters as independent variables, and predict the values ​​of the internal corrosion parameters by fitting and training the model.

[0115] The pipeline corrosion prediction method provided in this embodiment first obtains the most important medium corrosion coefficient of the pipeline based on the characteristics of the conveying medium in the pipeline. On this basis, in order to conduct an in-depth analysis of the corrosion factors inside the pipeline, when the medium corrosion coefficient is abnormal, it is determined whether there are secondary pipeline corrosion or factors affecting the medium corrosion coefficient, namely conditional corrosion factors, in the pipeline. If so, the specific type of conditional corrosion factor and the corrosion influence coefficient are analyzed and calculated respectively, and a corresponding first-level corrosion prediction model is established. If, according to the first-level corrosion prediction model, it is analyzed that the external environmental factors corresponding to the pipeline also have associated parameter influencing factors corresponding to the internal corrosion parameters, in order to strengthen the comprehensive prediction of pipeline corrosion, the associated parameter influencing factors and the corrosion correlation coefficients corresponding to the associated parameter influencing factors are combined to establish a second-level corrosion prediction model corresponding to the internal corrosion parameters. Since the internal corrosion factors, external corrosion factors, and internal and external interactive corrosion influencing factors of the pipeline are comprehensively analyzed, a corresponding corrosion prediction model is established, thereby improving the corrosion prediction effect of the mining emulsion conveying pipeline.

[0116] In one implementation of this embodiment, Figure 2 As shown, in step S104, if the corrosion parameter corresponding to the conditional corrosion factor exceeds the preset conditional corrosion parameter threshold, the corresponding target conditional corrosion factor is obtained, and it is determined whether the target conditional corrosion factor has multiple factor types, and the following steps are also included:

[0117] S201. If the target condition corrosion factor has multiple factor types, determine whether there is a correlation between the target condition corrosion factors corresponding to the multiple factor types;

[0118] S202. If there is a correlation between multiple factor types and corresponding target condition corrosion factors, obtain the corresponding target correlation group;

[0119] S203. Output relevant attribute information corresponding to the target related group according to the correlation coefficient between the target condition corrosion factors in the target related group;

[0120] S204. Generate a conditional corrosion analysis report corresponding to the target conditional corrosion factor by combining the target related group and the related attribute information corresponding to the target related group.

[0121] The purpose of dividing the target-related groups in steps S201 and S202 is to better observe and analyze the specific correlation information between multiple factor types and target condition corrosion factors. Therefore, the target condition corrosion factors can be predicted and explained by analyzing the factor types in the target-related groups. Specifically, the value of the target condition corrosion factor can be predicted by statistical analysis and modeling of the factor types in the target-related groups, and the impact of the factor on the target condition corrosion can be explained.

[0122] For example, some metal pipes exhibit different corrosion behaviors at different pH values. At the same time, oxygen can increase the corrosion rate of metals, so there may be a certain degree of correlation between pH value and oxygen content.

[0123] The correlation coefficient is a statistical indicator that measures the degree of linear correlation between two variables. Commonly used correlation coefficients include the Pearson correlation coefficient and the Spearman rank correlation coefficient. For example, if correlation coefficient analysis reveals significant positive or negative correlations between multiple factor types and the target condition corrosion factor, then these related factor types can constitute the target correlation group.

[0124] Furthermore, if there is no correlation between the target condition corrosion factors corresponding to multiple factor types, the target condition corrosion factors are directly classified according to their similar attributes to form corresponding target classification groups.

[0125] In steps S203 and S204, relevant attribute information refers to the attributes or characteristics used to describe the relationships between target conditional corrosion factors. It can be used to measure and interpret the correlation between different factors, thereby better understanding and analyzing the factors influencing conditional corrosion. For example, relevant attribute information can be represented by a matrix consisting of correlation coefficients, showing the correlation between different target conditional corrosion factors. The correlation matrix provides a more intuitive understanding of the degree of association between various factors.

[0126] Furthermore, based on the aforementioned target correlation groups and the corresponding attribute information, the conditional corrosion analysis report can be generated to further analyze the specific correlation changes between the various factors in these target correlation groups and the impact of these correlation changes on the corresponding corrosion rate of the pipeline. This allows for further analysis of the likelihood and mechanism between these factors and their potential impact on corrosion.

[0127] The pipeline corrosion prediction method provided in this embodiment analyzes and groups the correlations between corrosion factors of multiple target conditions, which can more intuitively observe and analyze the related attribute information between secondary corrosion factors in the pipeline. This helps to deeply understand the internal corrosion mechanism of the pipeline, thereby improving the corrosion prediction effect of the pipeline.

[0128] In one implementation of this embodiment, Figure 3 As shown, step S204, that is, combining the target related group and the related attribute information corresponding to the target related group, generates a conditional corrosion analysis report corresponding to the target conditional corrosion factor, including the following steps:

[0129] S301. According to the relevant attribute information, obtain the relevant category of the corresponding target related group;

[0130] S302. Combine target related groups according to related categories to form corresponding related sets of the same category;

[0131] S303. Combine the correlation sets of the same category and the correlation levels of the corresponding target correlation groups in the correlation sets of the same category to generate a correlation distribution diagram corresponding to the target conditional corrosion factors as a conditional corrosion analysis report.

[0132] In steps S301 and S302, the correlation categories are classified based on the correlation between the target condition corrosion factors. For example, the target correlation groups corresponding to the positively correlated target condition corrosion factors can be classified into the same category to form corresponding same-category correlation sets, so as to better understand and analyze the relationship between them.

[0133] Furthermore, by analyzing the correlation coefficients in the target correlation group, the correlation categories can be determined. A specific method can be to set a threshold and classify factors with correlation coefficients greater than or equal to the threshold into the same category. For example, factors with correlation coefficients greater than 0.7 can be classified as strongly correlated, factors with correlation coefficients between 0.3 and 0.7 can be classified as moderately correlated, and factors with correlation coefficients less than 0.3 can be classified as weakly correlated.

[0134] In step S303, by calculating the correlation coefficient, i.e., the degree of correlation, between the target condition corrosion factors in each target correlation group in each of the aforementioned same-category correlation sets, a corresponding correlation distribution diagram can be drawn. The correlation distribution diagram can be in the form of a scatter plot, a heat map, or a bar chart to display the degree of correlation between different factors. For example, the degree of correlation includes strong correlation, moderate correlation, or weak correlation.

[0135] Among them, by generating relevant distribution maps and combining them with explanatory notes, the correlation between target conditional corrosion factors can be intuitively displayed, providing a deeper understanding and analysis, and providing visual support for conditional corrosion analysis reports.

[0136] The pipeline corrosion prediction method provided in this embodiment classifies and combines target related groups according to their related categories, which can better understand the differences and commonalities between different related groups. The conditional corrosion analysis report helps to further analyze and predict corrosion problems, thereby improving the corrosion prediction effect of pipelines.

[0137] In one implementation of this embodiment, Figure 4 As shown, in step S104, if the corrosion parameter corresponding to the conditional corrosion factor exceeds the preset conditional corrosion parameter threshold, the corresponding target conditional corrosion factor is obtained, and it is determined whether the target conditional corrosion factor has multiple factor types, and the following steps are also included:

[0138] S401. If the target condition corrosion factor has a single factor type, determine whether the target condition corrosion factor has multiple sub-condition factors of the same type;

[0139] S402. If the target corrosion factor has multiple similar sub-conditions, perform periodic corrosion analysis on the corrosion parameters corresponding to each similar sub-condition to generate a corresponding corrosion prediction curve;

[0140] S403. Combine the similar sub-condition factors and the corrosion prediction curves corresponding to the similar sub-condition factors to generate a corresponding similar corrosion factor analysis table.

[0141] In step S401, if the target corrosion factor is a single factor type, that is, only one factor unilaterally affects the corrosion behavior, in order to further analyze the target corrosion factor of this single factor type, it is determined whether there are multiple similar sub-condition factors within the target corrosion factor. Similar sub-condition factors refer to multiple target corrosion factors under a single factor type. For example, if the single factor type is a corrosion catalysis factor, the target corrosion factor may include multiple similar sub-condition factors such as oxygen content and temperature.

[0142] In steps S402 and S403, periodic corrosion analysis involves regular or periodic analysis and evaluation of the corrosion behavior of a specific conditional factor, i.e., the aforementioned sub-conditional factors. The purpose of this analysis is to determine the relationship between the conditional factor and corrosion and to predict the impact of the factor on corrosion behavior.

[0143] Furthermore, through the above-mentioned periodic corrosion analysis, the change data of the corresponding corrosion rate or corrosion degree of each similar sub-condition factor within a certain period can be obtained, and then these change data are plotted into a corresponding corrosion prediction curve. This corrosion prediction curve can reflect how the change of each similar sub-condition factor affects the corrosion behavior.

[0144] Next, in the Corrosion Factor Analysis Table, each of the aforementioned sub-factors and their corresponding corrosion prediction curves can be listed separately. Each row in the table represents a sub-factor of the same type, including the factor's name, characteristic description, and the corrosion prediction curve derived from the correlation analysis. The corrosion prediction curve can be presented graphically, using mathematical models, or other forms to more intuitively understand the relationship between factor changes and corrosion behavior.

[0145] In the pipeline corrosion prediction method provided in this embodiment, the similar corrosion factor analysis table can integrate the information of various similar sub-condition factors and compare and analyze their impact and trends on corrosion behavior. By generating the similar corrosion factor analysis table, a more comprehensive understanding of the role and importance of different similar sub-condition factors can be achieved, providing guidance and decision-making basis for corrosion prediction and control, thereby improving the corrosion prediction effect of pipelines.

[0146] In one implementation of this embodiment, Figure 5 As shown, in step S105, if the target condition corrosion factor has multiple factor types, the target condition corrosion factor is divided into corrosion catalysis factors and additional corrosion factors according to a preset classification strategy, and the corrosion catalysis coefficient corresponding to the corrosion catalysis factor and the additional corrosion coefficient corresponding to the additional corrosion factor are calculated respectively, and the following steps are also included:

[0147] S501. Perform time series analysis on the corrosion catalysis coefficient and the additional corrosion coefficient respectively to obtain corresponding change trend data;

[0148] S502. Generate trend curves corresponding to the corrosion catalytic factors and the additional corrosion factors based on the change trend data.

[0149] In steps S501 and S502, time series analysis refers to a method for analyzing and modeling a series of chronologically ordered data. It focuses on the patterns and trends of data changes over time, aiming to reveal the inherent relationships between data, predict future trends, and provide decision support.

[0150] Specifically, time series analysis refers to the temporal evolution of the additional corrosion impact of the corrosion catalytic coefficient and the additional corrosion coefficient. For example, the temporal evolution of the corrosion catalytic coefficient can be influenced by a variety of factors, including pipeline material, emulsion composition, and environmental conditions. Therefore, a specific time series analysis must be combined with actual application scenarios.

[0151] For example, the corrosion catalytic factor is the temperature inside the pipeline. Over a certain period of time, as the temperature gradually increases, the corrosion rate generated by the medium in the pipeline itself also increases by the same amount. This means that the corrosion catalytic coefficient corresponding to the corrosion catalytic factor is also increasing, and the corresponding change trend data shows an overall upward trend.

[0152] Furthermore, based on the results of the above trend analysis, plot the trend curves of the corrosion catalysis coefficient and the additional corrosion coefficient. The horizontal axis represents time, and the vertical axis represents the coefficient value. Data trends can be displayed using line graphs, curve graphs, and other formats.

[0153] The pipeline corrosion prediction method provided in this embodiment can more accurately understand the changing trends of corrosion catalysis factors and additional corrosion factors based on the changing trend data obtained by time series analysis. These data can reflect the intensity and development trend of corrosion catalysis and additional corrosion, providing an important reference basis for corrosion prediction, thereby improving the corrosion prediction effect of pipelines.

[0154] In one implementation of this embodiment, Figure 6 As shown, after step S502, i.e., generating trend curves corresponding to the corrosion catalytic factors and the additional corrosion factors according to the change trend data, the following steps are also included:

[0155] S601. Identify the trend curve and obtain the correlation between the corrosion catalysis coefficient and the additional corrosion coefficient;

[0156] S602. If the correlation is positive, respectively calculate the corrosion catalysis rate corresponding to the corrosion catalysis coefficient and the additional corrosion rate corresponding to the additional corrosion coefficient;

[0157] S603. Generate a corresponding target corrosion rate based on the corrosion catalysis rate and the medium corrosion coefficient;

[0158] S604. Generate a predicted corrosion analysis report corresponding to the pipeline by combining the target corrosion rate and the additional corrosion rate.

[0159] In steps S601 to S602, the correlation between the corrosion catalysis coefficient and the additional corrosion coefficient can be obtained by identifying the trend curve. If there is a positive correlation between the two coefficients, in order to further reflect the actual impact of the two on the internal corrosion of the pipeline, the corrosion catalysis rate and the additional corrosion rate can be further calculated.

[0160] For example, the corrosion catalysis rate can be calculated by the rate of change of the corrosion catalysis coefficient. If the change in the corrosion catalysis coefficient over time is ΔC and the time interval is Δt, then the corrosion catalysis rate is: Corrosion catalysis rate = ΔC / Δt. The additional corrosion rate can be calculated by the value of the additional corrosion coefficient. If the additional corrosion coefficient is A, then the additional corrosion rate is: Additional corrosion rate = A. In this embodiment, the corrosion catalysis rate represents the degree of change in the corrosion catalysis coefficient per unit time and can be used to evaluate the corrosion rate; the additional corrosion rate represents the contribution of the additional corrosion coefficient to corrosion and can be used to evaluate the rate of additional corrosion.

[0161] In steps S603 to S604, the target corrosion rate refers to the corrosion rate corresponding to the medium corrosion coefficient under the influence of the corrosion catalysis rate. Combined with the additional corrosion rate obtained above, the total corrosion rate of the corrosion in the pipeline can be obtained.

[0162] In the pipeline corrosion prediction method provided in this embodiment, if there is a positive correlation between the corrosion catalysis coefficient and the additional corrosion coefficient, the influence between them can be quantified by calculating the corrosion catalysis rate and the additional corrosion rate. The corrosion catalysis rate can be used to evaluate the intensity of corrosion catalysis, while the additional corrosion rate can be used to evaluate the degree of additional corrosion. This can provide more comprehensive data analysis support for pipeline corrosion prediction and improve the prediction effect of pipeline corrosion.

[0163] In one implementation of this embodiment, Figure 7 As shown, after step S601, i.e. identifying the trend curve and obtaining the correlation between the corrosion catalysis coefficient and the additional corrosion coefficient, the following steps are also included:

[0164] S701. If the correlation is negative, obtain the balance coefficient corresponding to the corrosion catalysis coefficient and the additional corrosion coefficient;

[0165] S702. According to the balance coefficient, obtain the conditional influencing parameters corresponding to the medium corrosion coefficient;

[0166] S703. Combine the medium corrosion coefficient and condition influencing parameters to generate the internal corrosion coefficient corresponding to the pipeline.

[0167] In steps S710 to S703, the balance coefficient is a numerical value used to describe the relationship between two variables. In corrosion analysis, the balance coefficient is used to measure the relationship between the corrosion catalysis coefficient and the additional corrosion coefficient. Specifically, when the balance coefficient is a positive value, it indicates that there is a positive correlation between the corrosion catalysis coefficient and the additional corrosion coefficient, which means that an increase in the corrosion catalysis coefficient will lead to an increase in the additional corrosion coefficient, thereby increasing the target corrosion rate. When the balance coefficient is a negative value, it indicates that there is a negative correlation between the corrosion catalysis coefficient and the additional corrosion coefficient. This means that an increase in the corrosion catalysis coefficient will lead to a decrease in the additional corrosion coefficient, thereby reducing the target corrosion rate.

[0168] It should be noted that the value of the balance coefficient indicates the degree of correlation between the two variables. A larger absolute value of the balance coefficient indicates a stronger correlation, while a smaller balance coefficient indicates a weaker correlation. The balance coefficient is only used to describe the relationship between the corrosion catalysis rate and the additional corrosion coefficient and cannot directly provide a specific value for the target corrosion rate. Generating the target corrosion rate still requires calculation based on the specific corrosion catalysis rate and medium corrosion coefficient.

[0169] For example, the corrosion catalysis coefficient is K1, the additional corrosion coefficient is K2, and the balance coefficient is K. If there is a negative correlation between the two, the balance coefficient can be calculated using the following formula: K = K1 / K2. The medium corrosion coefficient is C, and the conditional influence parameter is P. If the medium corrosion coefficient is negatively correlated with the balance coefficient, the conditional influence parameter can be calculated using the following formula: P = K / C. Combining the medium corrosion coefficient and the conditional influence parameter, the corresponding internal corrosion coefficient of the pipeline is generated. If the internal corrosion coefficient is D, according to the definition, the internal corrosion coefficient can be calculated using the following formula: D = C * P. The generated internal corrosion coefficient can be used to assess the overall internal corrosion situation of the pipeline. A larger internal corrosion coefficient indicates a higher corrosion risk.

[0170] The pipeline corrosion prediction method provided in this embodiment can provide an in-depth understanding of the mechanism and influencing factors of pipeline corrosion based on the balance coefficient, condition influencing parameters and internal corrosion coefficient, provide comprehensive data support for pipeline corrosion prediction, and thus improve the prediction effect of pipeline corrosion.

[0171] The present application embodiment discloses a pipeline corrosion prediction system, such as Figure 8 Shown, including:

[0172] Acquisition module 1, used to obtain the corresponding medium corrosion coefficient according to the characteristics of the pipeline conveying medium;

[0173] Conditional corrosion identification module 2, if the medium corrosion coefficient exceeds the preset pipeline corrosion threshold, the conditional corrosion identification module 2 is used to determine whether there is a conditional corrosion factor in the pipeline;

[0174] Conditional corrosion analysis module 3, if there is a conditional corrosion factor in the pipeline, the conditional corrosion analysis module 3 is used to determine whether the corrosion parameter corresponding to the conditional corrosion factor exceeds a preset conditional corrosion parameter threshold;

[0175] Multi-factor analysis module 4, if the corrosion parameter corresponding to the conditional corrosion factor exceeds the preset conditional corrosion parameter threshold, then the multi-factor analysis module 4 is used to obtain the corresponding target conditional corrosion factor and determine whether the target conditional corrosion factor has multiple factor types;

[0176] Classification calculation module 5, if the target condition corrosion factor has multiple factor types, then the classification calculation module 5 is used to classify the target condition corrosion factor into corrosion catalysis factors and additional corrosion factors according to a preset classification strategy, and respectively calculate the corrosion catalysis coefficient corresponding to the corrosion catalysis factor and the additional corrosion coefficient corresponding to the additional corrosion factor;

[0177] The first-level corrosion prediction module 6 is used to generate the internal corrosion coefficient corresponding to the pipeline according to the medium corrosion coefficient, the corrosion catalysis coefficient and the additional corrosion coefficient, and to establish the first-level corrosion prediction model corresponding to the pipeline by combining the medium corrosion coefficient, the corrosion catalysis coefficient, the additional corrosion coefficient and the internal corrosion coefficient;

[0178] The correlation analysis module is used to obtain the internal corrosion parameter attribute table corresponding to the pipeline according to the first-level corrosion prediction model, and determine whether there are correlation parameter influencing factors corresponding to the internal corrosion parameters in the external environmental factors corresponding to the pipeline according to the internal corrosion parameter attribute table;

[0179] The secondary corrosion prediction module 8 is used to establish a secondary corrosion prediction model corresponding to the internal corrosion parameters by combining the associated parameter influencing factors and the corrosion correlation coefficients corresponding to the associated parameter influencing factors if there are associated parameter influencing factors corresponding to the internal corrosion parameters in the external environmental factors.

[0180] The pipeline corrosion prediction system provided in this embodiment first obtains the most important medium corrosion coefficient of the pipeline based on the characteristics of the conveying medium in the pipeline. On this basis, in order to conduct an in-depth analysis of the corrosion factors inside the pipeline, when the medium corrosion coefficient is abnormal, the conditional corrosion identification module 2 determines whether there is any secondary pipeline corrosion or factors affecting the medium corrosion coefficient, namely conditional corrosion factors, in the pipeline. If so, the conditional corrosion analysis module 3 analyzes and calculates the specific type of conditional corrosion factor and the corrosion influence coefficient, and establishes a corresponding first-level corrosion prediction model. If the first-level corrosion prediction model analyzes that the external environmental factors corresponding to the pipeline also contain associated parameter influencing factors corresponding to the internal corrosion parameters, in order to strengthen the comprehensive prediction of pipeline corrosion, the second-level corrosion prediction module 8 combines the associated parameter influencing factors and the corrosion correlation coefficients corresponding to the associated parameter influencing factors to establish a second-level corrosion prediction model corresponding to the internal corrosion parameters. Since the internal corrosion factors, external corrosion factors, and internal and external interactive corrosion influencing factors of the pipeline are comprehensively analyzed and the corresponding corrosion prediction model is established, the corrosion prediction effect of the mining emulsion conveying pipeline is improved.

[0181] It should be noted that the pipeline corrosion prediction system provided in the embodiment of the present application also includes various modules and / or corresponding sub-modules corresponding to the logical functions or logical steps of any of the above-mentioned pipeline corrosion prediction methods, achieving the same effects as the various logical functions or logical steps, and the details will not be repeated here.

[0182] An embodiment of the present application further discloses a terminal device, comprising a memory, a processor, and computer instructions stored in the memory and capable of running on the processor, wherein when the processor executes the computer instructions, any one of the pipeline corrosion prediction methods in the above embodiments is adopted.

[0183] Among them, the terminal device can be a computer device such as a desktop computer, a laptop computer or a cloud server, and the terminal device includes but is not limited to a processor and a memory. For example, the terminal device can also include input and output devices, network access devices and buses, etc.

[0184] Among them, the processor can adopt a central processing unit (CPU). Of course, according to actual usage, other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. can also be adopted. The general-purpose processor can adopt a microprocessor or any conventional processor, etc., and this application does not impose any restrictions on this.

[0185] Among them, the memory can be an internal storage unit of the terminal device, such as the hard disk or memory of the terminal device, or it can be an external storage device of the terminal device, such as a plug-in hard disk, smart memory card (SMC), secure digital card (SD) or flash memory card (FC) equipped on the terminal device, etc., and the memory can also be a combination of the internal storage unit and the external storage device of the terminal device. The memory is used to store computer instructions and other instructions and data required by the terminal device. The memory can also be used to temporarily store data that has been output or is to be output. This application does not impose any restrictions on this.

[0186] Among them, through this terminal device, any one of the pipeline corrosion prediction methods in the above embodiments is stored in the memory of the terminal device, and is loaded and executed on the processor of the terminal device for easy use.

[0187] An embodiment of the present application further discloses a computer-readable storage medium, and the computer-readable storage medium stores computer instructions, wherein when the computer instructions are executed by a processor, any one of the pipeline corrosion prediction methods in the above embodiments is adopted.

[0188] Among them, computer instructions can be stored in computer-readable media, computer instructions include computer instruction codes, computer instruction codes can be in source code form, object code form, executable files or certain middleware forms, etc. Computer-readable media include any entity or device that can carry computer instruction codes, recording media, USB flash drives, mobile hard drives, magnetic disks, optical disks, computer memories, read-only memories (ROMs), random access memories (RAMs), electrical carrier signals, telecommunication signals and software distribution media, etc. It should be noted that computer-readable media include but are not limited to the above-mentioned components.

[0189] Among them, through this computer-readable storage medium, any one of the pipeline corrosion prediction methods in the above embodiments is stored in the computer-readable storage medium, and is loaded and executed on the processor to facilitate the storage and application of the above method.

[0190] The above are all preferred embodiments of the present application, and are not intended to limit the scope of protection of the present application. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A pipeline corrosion prediction method, characterized in that: The following steps are involved: According to the characteristics of the pipeline's conveying medium, obtain the corresponding medium corrosion coefficient; If the medium corrosion coefficient exceeds the preset pipeline corrosion threshold, determining whether there are conditional corrosion factors in the pipeline; If the conditional corrosion factor exists in the pipeline, determining whether the corrosion parameter corresponding to the conditional corrosion factor exceeds a preset conditional corrosion parameter threshold; If the corrosion parameter corresponding to the conditional corrosion factor exceeds the preset conditional corrosion parameter threshold, obtaining the corresponding target conditional corrosion factor, and determining whether the target conditional corrosion factor has multiple factor types; If there are multiple factor types for the target condition corrosion factor, the target condition corrosion factor is divided into corrosion catalysis factors and additional corrosion factors according to a preset classification strategy, and the corrosion catalysis coefficient corresponding to the corrosion catalysis factor and the additional corrosion coefficient corresponding to the additional corrosion factor are calculated respectively; Generate an internal corrosion coefficient corresponding to the pipeline according to the medium corrosion coefficient, the corrosion catalysis coefficient, and the additional corrosion coefficient, and establish a primary corrosion prediction model corresponding to the pipeline by combining the medium corrosion coefficient, the corrosion catalysis coefficient, the additional corrosion coefficient, and the internal corrosion coefficient; Obtaining an internal corrosion parameter attribute table corresponding to the pipeline according to the primary corrosion prediction model, and determining whether there are associated parameter influencing factors corresponding to the internal corrosion parameters in the external environmental factors corresponding to the pipeline according to the internal corrosion parameter attribute table; If the external environmental factors include the associated parameter influencing factors corresponding to the internal corrosion parameters, a secondary corrosion prediction model corresponding to the internal corrosion parameters is established by combining the associated parameter influencing factors and the corrosion correlation coefficients corresponding to the associated parameter influencing factors.

2. A pipeline corrosion prediction method according to claim 1, characterized in that: If the corrosion parameter corresponding to the conditional corrosion factor exceeds the preset conditional corrosion parameter threshold, the corresponding target conditional corrosion factor is obtained, and after determining whether the target conditional corrosion factor has multiple factor types, the following steps are also included: If the target condition corrosion factor has multiple factor types, determining whether there is a correlation between the multiple factor types and the target condition corrosion factors; If there is a correlation between the multiple factor types and the target condition corrosion factors, then obtaining a corresponding target correlation group; Outputting relevant attribute information corresponding to the target related group according to the correlation coefficient between the target condition corrosion factors in the target related group; A conditional corrosion analysis report corresponding to the target conditional corrosion factor is generated by combining the target related group and the related attribute information corresponding to the target related group.

3. A pipeline corrosion prediction method according to claim 2, characterized in that: The generating of the conditional corrosion analysis report corresponding to the target conditional corrosion factor by combining the target related group and the related attribute information corresponding to the target related group comprises the following steps: Acquire a relevant category corresponding to the target related group according to the relevant attribute information; Combining the target related groups according to the related categories to form corresponding related sets of the same category; The correlation sets of the same category and the correlation levels of the target correlation groups in the correlation sets of the same category are combined to generate a correlation distribution diagram corresponding to the target conditional corrosion factors as the conditional corrosion analysis report.

4. A pipeline corrosion prediction method according to claim 1, characterized in that: If the corrosion parameter corresponding to the conditional corrosion factor exceeds the preset conditional corrosion parameter threshold, the corresponding target conditional corrosion factor is obtained, and after determining whether the target conditional corrosion factor has multiple factor types, the following steps are also included: If the target condition corrosion factor has a single factor type, determining whether the target condition corrosion factor has multiple sub-condition factors of the same type; If the target condition corrosion factor has multiple similar sub-condition factors, periodic corrosion analysis is performed on the corrosion parameters corresponding to each of the similar sub-condition factors to generate a corresponding corrosion prediction curve; The similar sub-condition factors and the corrosion prediction curves corresponding to the similar sub-condition factors are combined to generate a corresponding similar corrosion factor analysis table.

5. A pipeline corrosion prediction method according to claim 1, characterized in that: If the target condition corrosion factor has multiple factor types, the target condition corrosion factor is divided into corrosion catalysis factors and additional corrosion factors according to a preset classification strategy, and the corrosion catalysis coefficient corresponding to the corrosion catalysis factor and the additional corrosion coefficient corresponding to the additional corrosion factor are calculated respectively, and the following steps are also included: Performing time series analysis on the corrosion catalysis coefficient and the additional corrosion coefficient respectively to obtain corresponding change trend data; According to the change trend data, a trend curve graph corresponding to the corrosion catalysis factor and the additional corrosion factor is generated.

6. A pipeline corrosion prediction method according to claim 5, characterized in that: After generating the trend curve graph corresponding to the corrosion catalytic factor and the additional corrosion factor according to the change trend data, the following steps are also included: Identifying the trend curve graph, and obtaining a correlation between the corrosion catalysis coefficient and the additional corrosion coefficient; If the correlation is positive, the corrosion catalysis rate corresponding to the corrosion catalysis coefficient and the additional corrosion rate corresponding to the additional corrosion coefficient are calculated respectively; generating a corresponding target corrosion rate according to the corrosion catalysis rate and the medium corrosion coefficient; The target corrosion rate and the additional corrosion rate are combined to generate a predicted corrosion analysis report corresponding to the pipeline.

7. A pipeline corrosion prediction method according to claim 6, characterized in that: After identifying the trend curve and obtaining the correlation between the corrosion catalysis coefficient and the additional corrosion coefficient, the following steps are also included: If the correlation is negative, obtaining a balance coefficient corresponding to the corrosion catalysis coefficient and the additional corrosion coefficient; According to the balance coefficient, obtaining the condition influencing parameter corresponding to the medium corrosion coefficient; The internal corrosion coefficient corresponding to the pipeline is generated by combining the medium corrosion coefficient and the condition influencing parameters.

8. A pipeline corrosion prediction system, characterized in that: include: An acquisition module (1) is used to acquire a corresponding medium corrosion coefficient according to the characteristics of the medium transported by the pipeline; A conditional corrosion identification module (2) is used to determine whether a conditional corrosion factor exists in the pipeline if the medium corrosion coefficient exceeds a preset pipeline corrosion threshold; A conditional corrosion analysis module (3), if the conditional corrosion factor exists in the pipeline, the conditional corrosion analysis module (3) is used to determine whether the corrosion parameter corresponding to the conditional corrosion factor exceeds a preset conditional corrosion parameter threshold; A multi-factor analysis module (4) is used to obtain the corresponding target conditional corrosion factor if the corrosion parameter corresponding to the conditional corrosion factor exceeds the preset conditional corrosion parameter threshold, and to determine whether the target conditional corrosion factor has multiple factor types; A classification calculation module (5), if the target condition corrosion factor has multiple factor types, the classification calculation module (5) is used to divide the target condition corrosion factor into a corrosion catalysis factor and an additional corrosion factor according to a preset classification strategy, and respectively calculate the corrosion catalysis coefficient corresponding to the corrosion catalysis factor and the additional corrosion coefficient corresponding to the additional corrosion factor; A primary corrosion prediction module (6) is used to generate an internal corrosion coefficient corresponding to the pipeline based on the medium corrosion coefficient, the corrosion catalysis coefficient and the additional corrosion coefficient, and to establish a primary corrosion prediction model corresponding to the pipeline by combining the medium corrosion coefficient, the corrosion catalysis coefficient, the additional corrosion coefficient and the internal corrosion coefficient; an association analysis module, configured to obtain an internal corrosion parameter attribute table corresponding to the pipeline according to the primary corrosion prediction model, and determine, based on the internal corrosion parameter attribute table, whether there are associated parameter influencing factors corresponding to the internal corrosion parameters in the external environmental factors corresponding to the pipeline; A secondary corrosion prediction module (8) is used to establish a secondary corrosion prediction model corresponding to the internal corrosion parameter by combining the associated parameter influencing factor and the corrosion correlation coefficient corresponding to the associated parameter influencing factor if the associated parameter influencing factor corresponding to the internal corrosion parameter exists in the external environmental factor.

9. A terminal device comprising a memory and a processor, characterized in that: The memory stores computer instructions that can be run on the processor. When the processor loads and executes the computer instructions, a pipeline corrosion prediction method according to any one of claims 1 to 7 is adopted.

10. A computer-readable storage medium storing computer instructions, wherein: When the computer instructions are loaded and executed by the processor, a pipeline corrosion prediction method according to any one of claims 1 to 7 is adopted.

Images