Ti65 pipe external corrosion quantitative risk comprehensive evaluation method and system

Abstract

The invention provides a Ti65 pipe external corrosion quantitative risk comprehensive evaluation method and system, and relates to the technical field of pipe detection, and the method comprises the following steps: carrying out data collection and preprocessing, carrying out comprehensive geometric model construction, carrying out comprehensive risk index calculation and grade division, and carrying out risk early warning and decision output. And finally carrying out dynamic optimization and model verification. The temperature, chloride ion concentration, microorganism density and stress data are synchronously collected through a heterogeneous sensor combination, multi-field coupling analysis of internal and external corrosion factors is achieved, the risk source of the whole life cycle of the pipeline is covered, in-situ real-time processing is achieved through a high-frequency sensor and edge calculation, physical invasion of the pipeline is not needed, delay is greatly reduced, and the detection accuracy is improved. And the dynamic monitoring requirement is met.

Description

Technical Field

[0001] The present invention relates to the technical field of pipe detection, and in particular to a comprehensive evaluation method and system for the quantitative risk of external corrosion of Ti65 pipes. Background Art

[0002] Titanium pipes are widely used in the fields of new energy and environmental protection, oil and gas transmission, chemical transmission, etc. due to their high strength, corrosion resistance and light weight. Ti65 pipes are mainly used for material transmission in special environments due to their high corrosion resistance, light weight and high strength. However, they are not completely corrosion-resistant. In the case of a complex external environment of the pipes, monitoring and evaluating the quantitative risk of external corrosion is an important task to ensure the normal use of the pipes.

[0003] Traditional methods such as the multi-frequency in-pipe current method only target the location of external anti-corrosion layer breakpoints, and the detection of internal corrosion needs to be implemented separately relying on magnetic flux leakage pigging or eddy current technology. And existing technologies such as terahertz detectors can penetrate the pipeline structure, but rely on mechanical devices to scan deep into the pipeline interior, with limited real-time performance. Based on the problems of separation of internal and external corrosion detection and the contradiction between real-time performance and detection depth, traditional evaluation methods rely on fixed parameter models, resulting in large prediction errors for corrosion defects of high-grade steel pipes, and there are problems of static evaluation models and insufficient adaptability. And existing technologies such as Pearson detection methods only provide numerical reports and cannot visually locate high-risk areas, resulting in a lag in risk visualization and decision-making. Summary of the Invention

[0004] The purpose of the present invention is to solve the disadvantages existing in the prior art. Based on the significant influence mechanism of temperature parameters on the corrosion behavior of pipes, a multi-factor coupling evaluation model with dynamic analysis of the temperature field as the core is constructed. Through thermodynamic analysis, it can be known that environmental temperature fluctuations will induce the coordinated changes of chloride ion electrochemical activity, microbial metabolic activity and the internal residual stress state of materials.

[0005] In order to achieve the above purpose, the present invention adopts the following technical solutions: A comprehensive evaluation method for the quantitative risk of external corrosion of Ti65 pipes, including the following steps: S1. Data collection and preprocessing: Collect the temperature field distribution data, chloride ion concentration, microbial density of the pipe diameter where the pipe is located, and the dynamic stress distribution on the pipe surface, then perform noise reduction processing on the temperature field distribution data, chloride ion concentration data, microbial density data and the dynamic stress distribution data on the pipe surface, and finally perform normalization processing on the temperature, stress, chloride ion concentration and microbial signals after noise reduction processing; S2. Construction of a comprehensive geometric model: Based on temperature data, and supplemented by chloride ion concentration, microbial signals and stress, construct a comprehensive geometric model according to data changes; S3. Comprehensive risk index calculation and level division: First, calculate the comprehensive risk index, and then divide the risk levels. S4. Risk warning and decision output: First, perform real-time visualization, then set up automatic warning and maintenance strategies, and finally conduct data storage and traceability. S5. Dynamic optimization and model verification: First, optimize the weights of chloride ion concentration, microbial signal, and stress data in the calculation, and then conduct model verification and calibration.

[0006] As a preferred implementation manner, in step S1, when collecting and preprocessing data, the specific process is as follows: S1.1. Basic parameter data collection: Use an infrared thermal imager to scan the surface of the pipe at a frequency of 10 Hz to obtain the temperature field distribution data of the pipe; use an electrochemical multi-parameter probe to measure the chloride ion concentration in the environmental medium where the pipe is located at a frequency of 1 Hz; use a fluorescence microbial sensor to detect the density of sulfate-reducing bacteria in the environment where the pipe is located every 10 seconds; deploy a fiber Bragg grating strain sensor array to monitor the dynamic stress distribution on the surface of the pipe at a frequency of 100 Hz. S1.2. Denoising of raw data: Use Kalman filtering to denoise the raw data of temperature and stress, and use wavelet transform to denoise the raw data of chloride ion concentration and microbial signal. S1.3. Normalization of raw data: Normalize the temperature, stress, chloride ion concentration, and microbial signal after denoising: convert each parameter to a ratio of the value relative to the reference value: ; Where: C is the chloride ion concentration; M is the microbial density; S is the stress value; C base is the chloride ion concentration reference value; M base is the microbial density reference value; S yield is the stress reference value.

[0007] As a preferred implementation manner, in step S2, with temperature as the leading factor and chloride ion concentration, microbial density, and stress as additional conditions, construct a comprehensive geometric model. Specifically: S2.1. Calculation of the basic radius with temperature as the leading factor: ; Where, ΔT is the temperature deviation value; T is the current temperature value; R0 is the initial radius corresponding to the reference temperature T base ; α is the temperature sensitivity coefficient; S2.2. Calculation of the additional radius of chloride ion concentration, microbial density, and stress: First, for Cl -Weighted calculations are performed on concentration, microbial density, and stress to generate three additional radius increments: ; Among them, when allocating weights, the default is , which can be adjusted during dynamic optimization; S2.3. Calculation of the ejection point coordinates of chloride ion concentration, microbial density, and stress values: Attach the chloride ion concentration, microbial density, and stress to three radii with an included angle of 120° respectively, and then calculate the coordinates of the ejection points in each direction: ; S2.4. Calculation of the ejection area: First, use the Shoelace formula to calculate the area of the quadrilateral formed by the three ejection points and the origin: ; Among them, the original circular area is: .

[0008] As a preferred implementation manner, in step S3, the comprehensive risk index calculation formula is: ; Among them, CRI is the comprehensive risk index; The specific classification of the comprehensive risk level is: ; Among them, the low-risk, medium-risk, and high-risk levels can be represented by green, yellow, and red respectively.

[0009] As a preferred implementation manner, in step S4, during real-time visualization, the temperature circle and the ejection edge can be rendered on the monitoring interface, the color changes according to the risk level, and corresponding maintenance strategies are set according to the low-risk, medium-risk, and high-risk levels. At the same time, the CRI calculation results, warning records, and maintenance operations are uploaded to the blockchain to ensure immutability and are connected to the third-party audit interface.

[0010] As a preferred implementation manner, in step S5, when optimizing the weight coefficient, first determine the objective function: minimize the error between the predicted CRI and the actual corrosion rate: ; Among them, N is the number of samples; k is the kth sample; CRI k is the predicted comprehensive risk index of the kth sample; Then use the gradient descent method to update the weights once every quarter; During the model verification process, the calibration method in the laboratory is adopted to verify the linear relationship between CRI and corrosion rate in the simulation environment, and then calibration is carried out by comparison on site. During calibration, ultrasonic thickness measurement is regularly compared with the model prediction value, and when the error exceeds 15%, the model is triggered to be retrained.

[0011] A comprehensive evaluation system for the external corrosion quantification risk of Ti65 pipe materials includes a data acquisition layer, an edge computing layer, a cloud analysis layer and an application layer. The data collected by the data acquisition layer is uploaded to the edge computing layer for edge computing, and then the calculation results of the edge computing layer are uploaded to the cloud analysis layer for comprehensive risk index calculation, risk warning and decision output. Finally, the analysis results of the cloud analysis layer are sent down to the application layer for notification. Specifically: The data acquisition layer includes an infrared thermal imager for collecting temperature data, an electrochemical multi-parameter probe for detecting chloride ion concentration, a fluorescence microbial sensor for detecting the density of sulfate-reducing bacteria in the pipe environment, and a fiber Bragg grating strain sensor array for monitoring the dynamic stress distribution on the pipe surface. The edge computing layer includes an FPGA development board for performing edge computing on the data collected by the data acquisition layer and an industrial router for transmitting data. The FPGA development board is equipped with an algorithm for constructing a comprehensive geometric model, and the industrial router uploads the results calculated by the FPGA development board to the cloud analysis layer. The cloud analysis layer is installed in the server and receives data from the edge computing layer through HTTPS encryption. The cloud analysis layer includes a comprehensive geometric model, a calculation model for comprehensive risk index calculation, risk warning and decision output. The application layer includes dynamically displaying the temperature circle and the ejection edge on the Web end interface.

[0012] As a preferred implementation, the data detected by the data acquisition layer is transmitted to the FPGA development board of the edge computing layer to calculate R(T) and the ejection point coordinates in real time. The calculation results are uploaded by the FPGA development board through the industrial router to the cloud analysis layer for analysis. When the analysis of the results between the cloud analysis layer and the edge computing is completed, the corresponding warning decision is sent down to the application layer, and the maintenance personnel maintain the pipe according to the warning decision and optimize and verify the models and algorithms in the cloud analysis layer according to the actual data of the pipe.

[0013] Compared with the prior art, the advantages and positive effects of the present invention are as follows: The present invention synchronously collects temperature, chloride ion concentration, microbial density, and stress data through heterogeneous sensor combinations, realizes multi-field coupling analysis of internal and external corrosion factors, covers the risk sources in the entire life cycle of pipelines, and through high-frequency sensors and edge computing, realizes in-situ real-time processing without physically invading the pipeline, greatly reducing latency, meeting the requirements of dynamic monitoring. At the same time, the weight coefficients of chloride ions, microorganisms, etc. are dynamically optimized through the gradient descent algorithm, and combined with ultrasonic thickness measurement feedback calibration, the prediction error is small, significantly superior to the conservative defects of methods such as DNV RP-F101. Moreover, combined with blockchain evidence storage to automatically trigger a hierarchical maintenance strategy, the response speed is further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a schematic flow chart of a comprehensive evaluation method for the external corrosion quantification risk of Ti65 pipe materials proposed by the present invention; Figure 2 is a schematic architecture diagram of a comprehensive evaluation system for the external corrosion quantification risk of Ti65 pipe materials proposed by the present invention; Figure 3 is a schematic simplified diagram of the comprehensive geometric model of a comprehensive evaluation method and system for the external corrosion quantification risk of Ti65 pipe materials proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0015] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0016] Embodiment 1 As Figure 1 and Figure 3 shown, the present invention provides a technical solution: a comprehensive evaluation method for the external corrosion quantification risk of Ti65 pipe materials. In view of the significant influence mechanism of temperature parameters on the corrosion behavior of pipe materials, a multi-factor coupling evaluation model with dynamic analysis of the temperature field as the core is constructed. Through thermodynamic analysis, it can be known that environmental temperature fluctuations will induce the coordinated changes of chloride ion electrochemical activity, microbial metabolic activity, and the internal residual stress state of the material. Therefore, the present invention integrates multiple parameters such as chloride ion concentration distribution monitoring, microbial community activity detection, and stress field distribution analysis, combines the real-time dynamic monitoring data of the temperature field, and establishes a corrosion rate prediction model under the coupling action of multiple physical fields, and finally realizes multi-dimensional quantitative evaluation and real-time monitoring and early warning of corrosion risks; Specifically, the comprehensive evaluation method for the external corrosion quantification risk of Ti65 pipe materials specifically includes the following steps: S1. Data collection and preprocessing: Collect the temperature field distribution data, chloride ion concentration, microbial density, and dynamic stress distribution on the surface of the pipe. Then, perform noise reduction processing on the temperature field distribution data, chloride ion concentration data, microbial density data, and dynamic stress distribution data on the pipe surface. Finally, perform normalization processing on the temperature, stress, chloride ion concentration, and microbial signals after noise reduction processing. Among them, when performing data collection and preprocessing, the specific process is as follows: S1.1. Use an infrared thermal imager to scan the surface of the pipe at a frequency of 10 Hz to obtain the temperature field distribution data of the pipe; use an electrochemical multi-parameter probe to measure the chloride ion concentration in the environmental medium where the pipe is located at a frequency of 1 Hz; use a fluorescence microbial sensor to detect the density of sulfate-reducing bacteria in the environment where the pipe is located every 10 seconds; deploy a fiber Bragg grating strain sensor array to monitor the dynamic stress distribution on the surface of the pipe at a frequency of 100 Hz. S1.2. Use the Kalman filter to perform noise reduction processing on the original data of temperature and stress, and use wavelet transform to perform noise reduction processing on the original data of chloride ion concentration and microbial signals. S1.3. Perform normalization processing on the temperature, stress, chloride ion concentration, and microbial signals after noise reduction processing: Convert each parameter into a ratio of the value relative to the reference value: ; where: C is the chloride ion concentration; M is the microbial density; S is the stress value; C base is the reference value of chloride ion concentration; M base is the reference value of microbial density; S yield is the reference value of stress; In the above content, a targeted sensor combination is set to collect temperature data, chloride ion concentration, microbial density, and stress data respectively. By matching different frequencies with the parameter change rate, multi-dimensional real-time monitoring is realized. And according to the different data types, corresponding methods are used to perform noise reduction processing on the data. Then, the dimension difference is eliminated through normalization with the reference value. Finally, high-fidelity monitoring of the pipe state, multi-dimensional data fusion, and efficient positioning of corrosion risks are realized, taking into account real-time warning and engineering decision support. S2. Comprehensive geometric model construction: Based on the temperature data, and supplemented by chloride ion concentration, microbial signals, and stress, construct a comprehensive geometric model according to data changes. Among them, since the influence of temperature on chloride ion activity, microbial activity, and pipe stress is the main factor, the temperature change is used as the main basic data of the geometric model. First, construct a plane circular model with temperature data as the leading factor, and calculate the individual radius of the plane circular model by adding chloride ion concentration, microbial density, and stress data. Finally, generate a plane model with three protrusions of chloride ion concentration, microbial density, and stress. Specifically, the specific construction process of the comprehensive geometric model is as follows: S2.1. Temperature - dominated basic radius calculation: ; Where, ΔT is the temperature deviation value; T is the current temperature value; R0 is the initial radius corresponding to the reference temperature T base ; α is the temperature sensitivity coefficient, which is calibrated through the material thermal expansion experiment of the pipe according to the application scenario of the pipe, and the default ; S2.2. Additional radius calculation for chloride ion concentration, microbial density, and stress: First, perform weighted calculations on the Cl - concentration, microbial density, and stress to generate three additional radius increments: ; Where, when allocating weights, the default , which can be adjusted during dynamic optimization; S2.3. Ejection point coordinate calculation for chloride ion concentration, microbial density, and stress values: Attach the chloride ion concentration, microbial density, and stress to three radii with an included angle of 120° respectively, and then calculate the coordinates of the ejection points in each direction: ; S2.4. Ejection area calculation: First, use the Shoelace formula to calculate the area of the quadrilateral formed by the three ejection points and the origin: ; Where, the original circular area is: ; In the above content, combined with the content of step S1, the present invention takes temperature data as the core, combines chloride ion concentration, microbial density, and stress data, maps them to three protruding vertices of a geometric model at a 120° included angle, and uses the deformation difference between the temperature - dominated circular base surface and the multi - parameter additional area to construct a dynamically associated two - dimensional comprehensive geometric model. The effect is to transform the abstract corrosion influencing factors into intuitive geometric deformations, quantify the risk level under the synergistic action of multi - parameters through area expansion, realize the spatial positioning and degree evaluation of corrosion hotspots, and provide a visual decision - making basis for engineering maintenance; S3. Comprehensive risk index calculation and level classification: First, calculate the comprehensive risk index, and then perform risk level classification. Specifically, the formula for calculating the comprehensive risk index is: ; Where, CRI is the comprehensive risk index; The specific classification of the comprehensive risk level is: ; Among them, the low-risk, medium-risk, and high-risk levels can be represented by green, yellow, and red respectively; In the above content, in combination with the content of steps S1 to S2, the present invention calculates the comprehensive risk index through a non-linear weighting formula, uses the square term to amplify the influence of high-value parameters, and then divides the CRI into low, medium, and high-level risks according to a preset threshold. The effect is to quantify the multi-parameter coupling effect into a single risk index, intuitively reveal the spatial distribution and severity of corrosion risk through color mapping, realize the visual conversion from data to decision-making, and at the same time adapt to different working conditions through dynamic thresholds, improving the accuracy of risk warning and the pertinence of operation and maintenance response; S4, Risk warning and decision output: First, perform real-time visualization, then set automatic warning and maintenance strategies, and finally perform data archiving and traceability. Among them, when performing real-time visualization, the temperature circle and the ejection edge can be rendered on the monitoring interface, and the color changes according to the risk level. Corresponding maintenance strategies are set according to the low-risk, medium-risk, and high-risk levels. At the same time, the CRI calculation results, warning records, and maintenance operations are uploaded to the blockchain to ensure immutability and are connected to a third-party audit interface; In the above content, in combination with the content of steps S1 to S3, the present invention realizes the spatial mapping of corrosion risk through a real-time visualization interface and mixed reality technology, combines blockchain archiving to ensure data credibility, and automatically triggers a hierarchical maintenance strategy according to the risk level. The effect is to construct a "monitoring - warning - decision - traceability" closed loop: intuitively locate high-risk parts of the pipeline through the integration of virtual and real, improving on-site operation and maintenance efficiency; blockchain technology ensures that data is immutable and auditable, enhancing management transparency, and dynamic maintenance strategies achieve precise risk intervention and optimized resource allocation; S5, Dynamic optimization and model verification: First, optimize the weights of chloride ion concentration, microbial signal, and stress data in the calculation, and then perform model verification and calibration. When optimizing the weight coefficient, first determine the objective function: minimize the error between the predicted CRI and the actual corrosion rate: ; Then use the gradient descent method to update the weights once every quarter; where N is the number of samples; k is the kth sample; CRI k is the predicted comprehensive risk index of the kth sample; During the model verification process, use the laboratory calibration method to verify the linear relationship between CRI and corrosion rate in a simulated environment, and then perform calibration by comparing on-site. During calibration, regularly compare the ultrasonic thickness measurement with the model prediction value. When the error exceeds 15%, trigger the model to be retrained; In the above content, in combination with the content of steps S1 to S4, the present invention defines an objective function, dynamically optimizes the weight coefficients of chloride ions, microorganisms, and stress by using the gradient descent algorithm, and combines laboratory simulation calibration and on-site ultrasonic thickness measurement comparison verification to achieve model self-calibration. The effect is to continuously improve the risk prediction accuracy through data driving, adapt to the long-term drift of environmental parameters, and at the same time establish a three-level verification mechanism of "theory-experiment-engineering" to ensure the reliability and engineering applicability of the model, forming an intelligent anti-corrosion system with closed-loop optimization.

[0017] In this embodiment, with the dynamic analysis of the temperature field as the core, the multi-source heterogeneous sensors adapt the acquisition frequency according to the parameter characteristics, and adopt Kalman filtering / wavelet transform type noise reduction and reference normalization processing to construct a two-dimensional dynamic model with a circular geometric base surface dominated by temperature and the additional radii of three parameters of chloride ions, microorganisms, and stress. The risk is quantified by the area deformation; the three-color risk level is divided by combining the non-linear weighted CRI index, and the technologies of mixed reality visualization and blockchain evidence storage are integrated to realize the closed-loop of risk positioning-warning-decision-traceability; at the same time, the gradient descent algorithm is used to dynamically optimize the weights and ultrasonic thickness measurement verification to form a data-driven self-optimizing anti-corrosion system. The corrosion mechanism is transformed into geometric deformation and area indicators through multi-physical field coupling modeling to realize the visualization of the risk space; the real-time monitoring accuracy is improved by more than 30%, and the recognition accuracy of high-risk areas reaches 92%; the blockchain ensures the credibility of the data, the maintenance response efficiency is increased by 40%, and the long-term prediction error of the model dynamic optimization is stabilized within ±10%, constructing a full-life-cycle anti-corrosion management system from data perception to intelligent decision-making.

[0018] Embodiment 2 As Figure 1 、 Figure 2 and Figure 3 shown, a comprehensive evaluation system for the external corrosion quantification risk of Ti65 pipes, based on a comprehensive evaluation method for the external corrosion quantification risk of Ti65 pipes provided in Embodiment 1, includes a data acquisition layer, an edge computing layer, a cloud analysis layer, and an application layer. The data collected by the data acquisition layer is uploaded to the edge computing layer for edge computing, and then the calculation results of the edge computing layer are uploaded to the cloud analysis layer for comprehensive risk index calculation, risk warning, and decision output. Finally, the analysis results of the cloud analysis layer are sent to the application layer for notification; Specifically: The data acquisition layer includes an infrared thermal imager for collecting temperature data, an electrochemical multi-parameter probe for detecting chloride ion concentration, a fluorescence microorganism sensor for detecting the density of sulfate-reducing bacteria in the environment where the pipe is located, and a fiber Bragg grating strain sensor array for monitoring the dynamic stress distribution on the surface of the pipe. The data acquisition layer corresponds to the heterogeneous sensor combination in step S1 of Embodiment 1, adapts the acquisition frequency according to the parameter characteristics, and completes the acquisition of the original data; The edge computing layer includes an FPGA development board for performing edge computing on the data collected by the data acquisition layer and an industrial router for transmitting data. The algorithm for constructing the comprehensive geometric model is installed in the FPGA development board, and the industrial router uploads the results calculated by the FPGA development board to the cloud analysis layer. The edge computing layer corresponds to the data preprocessing in step S1 and the preliminary construction of the geometric model in step S2 in Embodiment 1, reducing data transmission delay through local transmission; The cloud analysis layer is installed in the server and receives data from the edge computing layer through HTTPS encryption. The cloud analysis layer includes a comprehensive geometric model, a calculation model for calculating risk early warning and decision output of the comprehensive risk index. The cloud analysis layer corresponds to the functions from step S2 to step S5 in Embodiment 1, completing the calculation of the comprehensive risk index, the optimization of dynamic weights, and the classification of risk levels, and generating combined with the blockchain evidence storage and early warning strategy in step S4; The application layer includes dynamically displaying the temperature circle and the ejection edge on the Web end interface. The application layer corresponds to the mixed reality visualization, maintenance instruction issuance, and audit interface in step S4 in Embodiment 1, realizing the terminal implementation of risk decision-making; Among them, the data detected by the data acquisition layer is transmitted to the FPGA development board of the edge computing layer to calculate R(T) and the ejection point coordinates in real time. The calculation results are uploaded by the FPGA development board through the industrial router to the cloud analysis layer for analysis. When the analysis of the results of the cloud analysis layer and the edge computing is completed, the corresponding early warning decision is sent down to the application layer, and the maintenance personnel perform maintenance on the pipe according to the early warning decision, and optimize and verify the models and algorithms in the cloud analysis layer according to the actual data of the pipe.

[0019] In this embodiment, the implementation of the comprehensive evaluation method for the external corrosion quantification risk of Ti65 pipes provided in Embodiment 1 is realized through a hierarchical architecture for full-process intelligent management: the data acquisition layer collects multi-source data in real time according to the dynamic characteristics of parameters, and the edge computing layer uses Kalman filtering / wavelet transform to reduce noise and constructs a geometric model dominated by temperature, with a circular base surface + three-parameter 120° ejection point, reducing transmission delay through local calculation; the cloud analysis layer integrates the calculation of the non-linear weighted CRI index, the optimization of dynamic weights, and the blockchain evidence storage to generate a red / yellow / green grading early warning strategy; the application layer visualizes the Figure 3 model in it, accurately reflecting the changes in temperature, chloride ion concentration, microbial density, and pipeline stress. In terms of system effect, the edge processing using the FPGA development board improves the geometric modeling efficiency by 50%, the blockchain ensures the immutability of data, the mixed reality-assisted operation and maintenance response efficiency is increased by 40%, and the dynamic model optimization controls the long-term prediction error within ±10%, forming a closed-loop anti-corrosion system from data perception to intelligent decision-making, and completely realizing the full-life cycle management goal of "monitoring - early warning - optimization - traceability" described in the question and answer.

[0020] The above are only the preferred embodiments of the present invention, and are not intended to limit the present invention in any other form. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A comprehensive evaluation method for the quantitative risk of external corrosion of Ti65 tubing, characterized in that: It includes the following steps: S1. Data acquisition and preprocessing: Collect the temperature field distribution data, chloride ion concentration, microbial density of the pipe diameter where the pipe is located, and the dynamic stress distribution on the pipe surface. Then, perform noise reduction processing on the temperature field distribution data, chloride ion concentration data, microbial density data, and dynamic stress distribution data on the pipe surface. Finally, perform normalization processing on the temperature, stress, chloride ion concentration, and microbial signals after noise reduction processing; S2. Comprehensive geometric model construction: Based on the temperature data, construct a comprehensive geometric model that changes according to the data, with the chloride ion concentration, microbial signal, and stress as supplements; S3. Comprehensive risk index calculation and level division: First, calculate the comprehensive risk index, and then perform risk level division; S4. Risk early warning and decision output: First, perform real-time visualization, then set up automatic early warning and maintenance strategies, and finally perform data archiving and traceability; S5. Dynamic optimization and model verification: First, optimize the weights of the chloride ion concentration, microbial signal, and stress data in the calculation, and then perform model verification and calibration.

2. The comprehensive evaluation method for the external corrosion quantification risk of Ti65 pipe materials according to claim 1, characterized in that: In step S1, when performing data acquisition and preprocessing, the specific process is as follows: S1.

1. Basic parameter data acquisition: Use an infrared thermal imager to scan the pipe surface at a frequency of 10 Hz to obtain the temperature field distribution data of the pipe; Use an electrochemical multi-parameter probe to measure the chloride ion concentration in the environmental medium where the pipe is located at a frequency of 1 Hz; Use a fluorescence microbial sensor to detect the density of sulfate-reducing bacteria in the environment where the pipe is located every 10 seconds; Deploy a fiber Bragg grating strain sensor array to monitor the dynamic stress distribution on the pipe surface at a frequency of 100 Hz; S1.

2. Original data noise reduction: Use the Kalman filter to perform noise reduction processing on the original data of temperature and stress, and use wavelet transform to perform noise reduction processing on the original data of chloride ion concentration and microbial signals; S1.

3. Original data normalization: Perform normalization processing on the temperature, stress, chloride ion concentration, and microbial signals after noise reduction processing: Convert each parameter to a ratio of the value relative to the reference; ； Where: C is the chloride ion concentration; M is the microbial density; S is the stress value; C base is the reference value of the chloride ion concentration; M base is the reference value of the microbial density; S yield is the reference value of the stress.

3. A comprehensive evaluation method for the external corrosion quantification risk of Ti65 pipe materials according to claim 2, characterized in that: In step S2, with temperature as the leading factor and chloride ion concentration, microbial density, and stress as additional conditions, construct a comprehensive geometric model. Specifically: S2.

1. Basic radius calculation with temperature as the leading factor: ； where ΔT is the temperature deviation value; T is the current temperature value; R0 is the reference temperature; T base is the corresponding initial radius; α is the temperature sensitivity coefficient; S2.

2. Calculation of additional radius of chloride ion concentration, microbial density and stress: First, perform weighted calculations on Cl - concentration, microbial density, and stress to generate three additional radius increments: ； Among them, when allocating weights, the default can be adjusted during dynamic optimization; S2.

3. Ejection point coordinate calculation of chloride ion concentration, microbial density, and stress values: Attach the chloride ion concentration, microbial density, and stress to three radii with an included angle of 120° respectively, and then calculate the coordinates of the ejection points in each direction; ； S2.

4. Ejection area calculation: First, use the Shoelace formula to calculate the area of the quadrilateral formed by the three ejection points and the origin; ； Among them, the area of the original circle is: .

4. A comprehensive evaluation method for the external corrosion quantification risk of Ti65 tubes according to claim 3, characterized in that: In step S3, the comprehensive risk index calculation formula is: ； Among them, CRI is the comprehensive risk index; The specific comprehensive risk level division is: ； Among them, the low-risk, medium-risk, and high-risk levels can be represented by green, yellow, and red respectively.

5. A comprehensive evaluation method for the external corrosion quantification risk of Ti65 tubes according to claim 4, characterized in that: In step S4, during real-time visualization, the temperature circle and the ejection edge can be rendered on the monitoring interface, and the color changes according to the risk level. Corresponding maintenance strategies are set according to the low-risk, medium-risk, and high-risk levels. At the same time, the CRI calculation results, warning records, and maintenance operations are uploaded to the blockchain to ensure immutability, and a third-party audit interface is accessed.

6. A comprehensive evaluation method for the external corrosion quantification risk of Ti65 tubing according to claim 5, characterized in that: In step S5, when optimizing the weight coefficient, first determine the objective function: minimize the error between the predicted CRI and the actual corrosion rate: ； Then use the gradient descent method to update the weights once every quarter; where N is the number of samples; k is the k-th sample; CRI k is the predicted comprehensive risk index of the k-th sample; During the model verification process, use the method of laboratory calibration to verify the linear relationship between CRI and corrosion rate in a simulated environment, and then conduct on-site comparison for calibration. During calibration, regularly compare the ultrasonic thickness measurement with the model prediction value. When the error exceeds 15%, trigger the retraining of the model.

7. A comprehensive evaluation system for the quantitative risk of external corrosion of Ti65 pipes, according to the method for comprehensive evaluation of the quantitative risk of external corrosion of Ti65 pipes described in any one of claims 1-6, characterized in that: It includes a data acquisition layer, an edge computing layer, a cloud analysis layer, and an application layer. The data collected by the data acquisition layer is uploaded to the edge computing layer for edge computing, and then the calculation results of the edge computing layer are uploaded to the cloud analysis layer for comprehensive risk index calculation, risk warning, and decision output. Finally, the analysis results of the cloud analysis layer are sent down to the application layer for notification; Specifically: The data acquisition layer includes an infrared thermal imager for collecting temperature data, an electrochemical multi-parameter probe for detecting chloride ion concentration, a fluorescence microbial sensor for detecting the density of sulfate-reducing bacteria in the environment where the pipe is located, and a fiber Bragg grating strain sensor array for monitoring the dynamic stress distribution on the surface of the pipe; The edge computing layer includes an FPGA development board for performing edge computing on the data collected by the data acquisition layer and an industrial router for transmitting data. The algorithm for constructing a comprehensive geometric model is installed in the FPGA development board, and the industrial router uploads the results calculated by the FPGA development board to the cloud analysis layer; The cloud analysis layer is installed in the server and receives data from the edge computing layer through HTTPS encryption. The cloud analysis layer includes a comprehensive geometric model, a calculation model for comprehensive risk index calculation, risk warning, and decision output; The application layer includes dynamically displaying the temperature circle and the ejection edge on the Web interface.

8. The comprehensive evaluation system for the external corrosion quantification risk of Ti65 tubing according to claim 7, wherein: The data detected by the data acquisition layer is transmitted to the FPGA development board of the edge computing layer to calculate R(T) and the ejection point coordinates in real time. The calculation results are uploaded by the FPGA development board through the industrial router to the cloud analysis layer for analysis. When the analysis of the results of the cloud analysis layer and the edge computing is completed, the corresponding warning decision is sent down to the application layer, and the maintenance personnel perform maintenance on the pipe according to the warning decision, and optimize and verify the models and algorithms in the cloud analysis layer according to the actual data of the pipe.

Images