A hydrogen embrittlement risk early warning method, device, equipment, medium and product

Abstract

The application discloses a hydrogen embrittlement risk early warning method, device, equipment, medium and product. The hydrogen embrittlement risk early warning method comprises the following steps: obtaining a plurality of environmental factors of a working environment of a ring welding joint to be evaluated; the plurality of environmental factors comprise a service temperature, an equivalent stress and an environmental hydrogen parameter; the environmental factors are input into a pre-established multidimensional environmental spectrum to determine a hydrogen embrittlement risk grade corresponding to the environmental factors; wherein the multidimensional environmental spectrum is constructed based on a multivariate mathematical model containing at least one environmental factor interaction term, and is used for representing a spectrum of hydrogen embrittlement sensitivity prediction values changing with the environmental factors; the multidimensional environmental spectrum contains risk grade marks divided based on ranges to which the hydrogen embrittlement sensitivity prediction values belong; and in the case that the hydrogen embrittlement risk grade is higher than a set risk threshold, a risk early warning for the ring welding joint to be evaluated is initiated. The technical scheme of the embodiment of the application can improve the hydrogen embrittlement risk prediction accuracy.

Description

Technical Field

[0001] This invention relates to the field of materials safety assessment technology, and in particular to a method, apparatus, equipment, medium, and product for early warning of hydrogen embrittlement risk. Background Technology

[0002] Due to the uneven microstructure and properties of the weld, heat-affected zone, and base material, circumferential welded joints are prone to hydrogen embrittlement fracture under the combined action of stress and hydrogen atoms, which is a key risk point for the safe operation of equipment such as oil and gas pipelines and hydrogen energy storage and transportation.

[0003] Currently, hydrogen embrittlement sensitivity assessment mainly relies on two types of methods: one is based on slow strain rate tensile tests according to set standards, which are "single-point" tests under fixed environmental conditions. However, in real working conditions, multiple environmental factors such as temperature, stress, and hydrogen concentration are dynamically changing and coupled with each other. Single-point tests cannot reflect this nonlinear coupling effect, resulting in poor universality of the assessment results. The second is numerical simulation methods. However, existing models are usually based on simplified physical equations, treating the influence of multiple factors as a linear superposition. This makes it difficult to accurately characterize the complex interactions between temperature, stress, and chemical environment, and the prediction accuracy is often insufficient, leading to inaccurate or untimely warnings of hydrogen embrittlement risks. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, medium, and product for early warning of hydrogen embrittlement risk, in order to solve the problem of inaccurate or untimely early warning of hydrogen embrittlement.

[0005] According to one aspect of the present invention, a method for early warning of hydrogen embrittlement risk is provided, comprising: Multiple environmental factors of the working environment of the ring weld joint to be evaluated are obtained; the multiple environmental factors include service temperature, equivalent stress and environmental hydrogen parameters; The environmental factors are input into a pre-established multidimensional environmental spectrum to determine the hydrogen embrittlement risk level corresponding to the environmental factors. The multidimensional environmental spectrum is constructed based on a multivariate mathematical model containing at least one interaction term of environmental factors, and is used to characterize the variation of the hydrogen embrittlement sensitivity prediction value with the environmental factors; the multidimensional environmental spectrum includes risk level identifiers based on the range to which the hydrogen embrittlement sensitivity prediction value belongs. If the hydrogen embrittlement risk level is higher than the set risk threshold, a risk warning is issued for the ring weld joint to be evaluated.

[0006] According to another aspect of the present invention, a hydrogen embrittlement risk warning device is provided, comprising: The environmental factor acquisition module is used to acquire multiple environmental factors of the working environment of the ring weld joint to be evaluated; the multiple environmental factors include service temperature, equivalent stress and environmental hydrogen parameters; The hydrogen embrittlement risk level determination module is used to input the environmental factors into a pre-established multidimensional environmental spectrum and determine the hydrogen embrittlement risk level corresponding to the environmental factors. The multidimensional environmental spectrum is constructed based on a multivariate mathematical model containing at least one interaction term of environmental factors, and is used to characterize the variation of the hydrogen embrittlement sensitivity prediction value with the environmental factors; the multidimensional environmental spectrum includes risk level identifiers based on the range to which the hydrogen embrittlement sensitivity prediction value belongs. The risk warning module is used to initiate a risk warning for the ring weld joint to be evaluated when the hydrogen embrittlement risk level is higher than a set risk threshold.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a hydrogen embrittlement risk warning method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement a hydrogen embrittlement risk warning method according to any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer program product is provided, including a computer program that, when executed by a processor, implements a hydrogen embrittlement risk warning method according to any embodiment of the present disclosure.

[0010] The technical solution of this invention involves acquiring multiple environmental factors of the working environment of the ring weld joint to be evaluated. These environmental factors include service temperature, equivalent stress, and environmental hydrogen parameters. The environmental factors are then input into a pre-established multidimensional environmental spectrum to determine the hydrogen embrittlement risk level corresponding to each environmental factor. The multidimensional environmental spectrum is constructed based on a multivariate mathematical model containing at least one interaction term of the environmental factors, and is used to characterize the variation of the predicted hydrogen embrittlement sensitivity value with the environmental factors. Furthermore, the multidimensional environmental spectrum includes risk level identifiers based on the range of the predicted hydrogen embrittlement sensitivity value. Finally, if the hydrogen embrittlement risk level exceeds a set risk threshold, a risk warning is initiated for the ring weld joint to be evaluated, thereby improving the accuracy of hydrogen embrittlement risk prediction.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a hydrogen embrittlement risk warning method provided in Embodiment 1 of the present invention; Figure 2 This is a flowchart of a hydrogen embrittlement risk warning method provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of a hydrogen embrittlement risk warning device according to Embodiment 3 of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device that implements the hydrogen embrittlement risk warning method of the present invention. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] Example 1 Figure 1The flowchart of a hydrogen embrittlement risk early warning method provided in Embodiment 1 of the present invention is applicable to situations where a multidimensional environmental spectrum is constructed through a multivariate mathematical model containing interaction terms, and the hydrogen embrittlement risk level of the current environmental factor is determined in the multidimensional environmental spectrum. This method can be executed by a hydrogen embrittlement risk early warning device, which can be implemented in hardware and / or software and can be configured in various general-purpose computing devices. Figure 1 As shown, the method includes: S110. Obtain multiple environmental factors of the working environment of the ring weld joint to be evaluated.

[0017] Environmental factors refer to environmental variables that affect the hydrogen embrittlement sensitivity of the welded joint to be evaluated. Multiple environmental factors include service temperature, equivalent stress, and environmental hydrogen parameters.

[0018] The service temperature T refers to the temperature of the welded joint in its actual working environment, expressed in degrees Celsius (°C). Temperature directly affects the diffusion rate of hydrogen atoms in the material. Hydrogen atoms tend to accumulate at low temperatures, while diffusion accelerates at high temperatures, but this may also accelerate corrosion and hydrogen production. Its effect on hydrogen embrittlement is nonlinear and coupled with stress and the hydrogen environment; equivalent stress... The stress value, measured in megapascals (MPa), is the stress that the welded ring joint experiences under operating conditions. Stress causes lattice distortion, creating traps for hydrogen atoms. Higher stress leads to more significant hydrogen enrichment and accelerates crack propagation. Combined with temperature and the hydrogen environment, stress exacerbates hydrogen embrittlement. The environmental hydrogen parameter is a quantitative indicator of the welded ring joint's hydrogen supply capacity in its actual operating environment. This parameter can be either the environmental hydrogen concentration (CH) or the partial pressure of hydrogen sulfide (P), both measured in MPa. Both determine the amount of hydrogen supplied in the environment. Higher hydrogen sulfide partial pressure results in more hydrogen production from corrosion, while higher environmental hydrogen concentration provides a greater driving force for hydrogen intrusion into the material, forming the material basis for hydrogen embrittlement. The appropriate parameter must be selected based on the specific service environment (partial pressure of hydrogen sulfide for wet hydrogen sulfide environments, and environmental hydrogen concentration for high-pressure hydrogen environments). The selected environmental factors comprehensively cover the key influencing factors of hydrogen embrittlement, with values ​​closely aligned with engineering realities. This ensures that the experimental data and models reflect actual operating conditions, providing targeted support for subsequent evaluations.

[0019] The range of environmental factors is based on the actual service conditions of the welded joint, covering both extreme and normal conditions. For example, the service temperature of a petrochemical pipeline is -20℃ to 80℃, and the equivalent stress is 0 to 0.8. (To avoid exceeding the yield strength and causing plastic deformation), the partial pressure of hydrogen sulfide is 0.01 MPa to 0.5 MPa (corresponding to different operating conditions with different sulfur-containing media); the service temperature of the hydrogen energy storage tank is -40℃ to 60℃, and the equivalent stress is 0 to 0.7. The ambient hydrogen concentration is 90 vol% to 100 vol% (which meets the purity requirements of high-pressure hydrogen equipment).

[0020] In this embodiment of the invention, multiple environmental factors of the working environment of the ring weld joint to be evaluated, measured by sensors, are first acquired. These factors include service temperature, equivalent stress, and environmental hydrogen parameters (e.g., environmental hydrogen concentration or hydrogen sulfide partial pressure). Furthermore, the acquired environmental factors can be format-verified to ensure that the units of service temperature, equivalent stress, and environmental hydrogen concentration or hydrogen sulfide partial pressure conform to pre-set statistical units.

[0021] S120. Input the environmental factors into the pre-established multidimensional environmental spectrum to determine the hydrogen embrittlement risk level corresponding to the environmental factors.

[0022] The multidimensional environmental spectrum is a graph constructed based on a multivariate mathematical model containing at least one interaction term of environmental factors, used to characterize the variation of hydrogen embrittlement sensitivity prediction values ​​with the environmental factors; the multidimensional environmental spectrum includes risk level identifiers based on the range to which the hydrogen embrittlement sensitivity prediction values ​​belong.

[0023] A multidimensional environmental spectrum is a graph characterizing the variation of predicted hydrogen embrittlement sensitivity with environmental factors. Specifically, there can be multiple multidimensional environmental spectra. Each multidimensional environmental spectrum is constructed as follows: a coordinate system is established with one environmental factor as a fixed value and two other environmental factors as the x and y axes, respectively. Based on each coordinate point in the coordinate system (i.e., the combination of the other two environmental factors) and the fixed environmental factor, the corresponding predicted hydrogen embrittlement sensitivity value is calculated using a multivariate mathematical model. Then, a response surface and contour lines are constructed with the predicted hydrogen embrittlement sensitivity value as the response value.

[0024] For example, with the partial pressure of hydrogen sulfide as a fixed value (P=0.2 MPa), and the service temperature (T) and equivalent stress ( The x and y axes are used as the horizontal and vertical axes. Based on each coordinate point in the coordinate system (i.e., the combination of service temperature and equivalent stress) and a fixed value of hydrogen sulfide partial pressure, the corresponding predicted value of hydrogen embrittlement sensitivity is calculated through a multivariate mathematical model. A response surface (three-dimensional surface) is then constructed with the predicted hydrogen embrittlement sensitivity as the response value (vertical axis). This graph can visually demonstrate the changing trend of the predicted hydrogen embrittlement sensitivity under the coupled effect of service temperature and equivalent stress when the hydrogen sulfide partial pressure is fixed.

[0025] Using the horizontal axis of the response surface as the planar coordinate system, the predicted range of hydrogen embrittlement sensitivity is divided into multiple intervals, such as 0%–10%, 10%–25%, 25%–40%, and above 40%. Each interval is marked with a different color, and contour lines can be drawn based on the vertical coordinates of points on the 3D surface. These contour lines allow for quick location of the hydrogen embrittlement sensitivity intervals corresponding to different service temperatures and equivalent stress combinations, facilitating rapid lookup.

[0026] Furthermore, risk level markers based on the range of predicted hydrogen embrittlement sensitivity values ​​can be superimposed on the response surface or contour lines to obtain a multidimensional environmental spectrum. For example, the predicted hydrogen embrittlement sensitivity values ​​range from 0% to 10%, 10% to 25%, 25% to 40%, and above 40%, corresponding to risk levels 1, 2, 3, and 4, respectively, with each risk level having its own risk level marker.

[0027] Among them, the multivariate mathematical model is obtained by fitting test data on the hydrogen embrittlement sensitivity of ring welded joints under multiple sets of different environmental factors. It includes one or more environmental factor interaction terms to quantify the coupling effect between environmental factors.

[0028] In this embodiment of the invention, multiple environmental factors corresponding to the welded joint to be evaluated are input into a pre-established multidimensional environmental spectrum. The predicted hydrogen embrittlement sensitivity value corresponding to each environmental factor can be located on the response surface of the multidimensional environmental spectrum. Then, the risk level identifier corresponding to the current predicted hydrogen embrittlement sensitivity value is located in the multidimensional environmental spectrum, and the hydrogen embrittlement risk level corresponding to the environmental factor is determined based on the risk level identifier.

[0029] S130. If the hydrogen embrittlement risk level is higher than the set risk threshold, initiate a risk warning for the ring weld joint to be evaluated.

[0030] In this embodiment of the invention, the hydrogen embrittlement risk level of the ring weld joint to be evaluated is compared with a set risk threshold. If it is higher than the set risk threshold, a risk warning is issued for the ring weld joint to be evaluated. For example, if the hydrogen embrittlement risk level is equal to or higher than risk level 3, a risk warning is issued, which allows staff to be promptly informed of the hydrogen embrittlement risk of the ring weld joint to be evaluated.

[0031] The technical solution of this invention involves acquiring multiple environmental factors of the working environment of the ring weld joint to be evaluated. These environmental factors include service temperature, equivalent stress, and environmental hydrogen parameters. The environmental factors are then input into a pre-established multidimensional environmental spectrum to determine the hydrogen embrittlement risk level corresponding to each environmental factor. The multidimensional environmental spectrum is constructed based on a multivariate mathematical model containing at least one interaction term of the environmental factors, and is used to characterize the variation of the predicted hydrogen embrittlement sensitivity value with the environmental factors. Furthermore, the multidimensional environmental spectrum includes risk level identifiers based on the range of the predicted hydrogen embrittlement sensitivity value. Finally, if the hydrogen embrittlement risk level exceeds a set risk threshold, a risk warning is initiated for the ring weld joint to be evaluated, thereby improving the accuracy of hydrogen embrittlement risk prediction.

[0032] Example 2 Figure 2This is a flowchart of a hydrogen embrittlement risk early warning method provided in Embodiment 2 of the present invention. This embodiment further refines the above embodiments, providing specific steps for inputting environmental factors into a pre-established multidimensional environmental spectrum to determine the hydrogen embrittlement risk level corresponding to the environmental factors, as well as specific steps for constructing the multidimensional environmental spectrum. Figure 2 As shown, the method includes: S210. Obtain multiple environmental factors of the working environment of the ring weld joint to be evaluated; the multiple environmental factors include service temperature, equivalent stress and environmental hydrogen parameters.

[0033] S220. Input the environmental factors into the pre-established multidimensional environmental spectrum, and determine the predicted value of the hydrogen embrittlement sensitivity corresponding to the environmental factors in the multidimensional environmental spectrum.

[0034] The multidimensional environmental spectrum is a graph constructed based on a multivariate mathematical model containing at least one interaction term of environmental factors, used to characterize the variation of hydrogen embrittlement sensitivity prediction values ​​with the environmental factors; the multidimensional environmental spectrum includes risk level identifiers based on the range to which the hydrogen embrittlement sensitivity prediction values ​​belong. In this embodiment of the invention, the environmental factors of the ring weld joint to be evaluated are input into a pre-established multidimensional environmental spectrum. The coordinate point that matches the current environmental factor is determined in the response surface of the multidimensional environmental spectrum, and the vertical coordinate value of the coordinate point is obtained, which is the predicted value of hydrogen embrittlement sensitivity.

[0035] In a specific example, the environmental factors obtained include the partial pressure of hydrogen sulfide, P = 0.3 MPa, the service temperature, T = 50°C, and the equivalent stress. =33 MPa. In the response surface of a multidimensional environmental spectrum with a fixed hydrogen sulfide partial pressure P = 0.3 MPa, the equivalent stress at an operating temperature T = 50℃ was determined. The vertical coordinate of the point with a pressure of 33 MPa is obtained, which is the predicted value of hydrogen embrittlement sensitivity.

[0036] Optionally, the multidimensional environmental spectrum can be constructed in the following manner: Hydrogen embrittlement susceptibility test data of ring welded joints under multiple environmental factors were obtained; the hydrogen embrittlement susceptibility test data included environmental factors and corresponding reduction of area loss rate of ring welded joints; the reduction of area loss rate was used to quantify hydrogen embrittlement susceptibility. Based on the hydrogen embrittlement sensitivity test data, a multivariate mathematical model is fitted between multiple environmental factors and the predicted values ​​of hydrogen embrittlement sensitivity; the multivariate mathematical model includes at least one environmental factor interaction term used to quantify the coupling relationship between environmental factors. Based on the aforementioned multivariate mathematical model, multiple multidimensional environmental spectra are generated; the multidimensional environmental spectra include the response surface and contour lines of the predicted hydrogen embrittlement sensitivity values ​​as a function of the environmental factors.

[0037] Optionally, the multivariate mathematical model is a multivariate quadratic regression model fitted based on the response surface methodology, and the multivariate quadratic regression model includes a first-order term, a second-order term, and an interaction term for the environmental factors.

[0038] In these two optional embodiments, a specific method for constructing a multidimensional environmental spectrum and the specific structure of the multivariate mathematical model are provided: First, based on hydrogen embrittlement sensitivity test data, a multivariate mathematical model is fitted between multiple environmental factors and predicted hydrogen embrittlement sensitivity values. The multivariate mathematical model includes at least one environmental factor interaction term used to quantify the coupling relationship between environmental factors. Then, based on the multivariate mathematical model, by fixing one environmental factor, predicted hydrogen embrittlement sensitivity values ​​associated with multiple combinations of the other two environmental factors are calculated, thereby generating multiple multidimensional environmental spectra based on the calculated values. The multidimensional environmental spectrum includes the response surface and contour lines of the predicted hydrogen embrittlement sensitivity values ​​as a function of the environmental factors.

[0039] In a specific example, taking the application scenario of a ring welded joint in a petrochemical pipeline (wet hydrogen sulfide environment) as an example: First, acquire experimental data covering the coupling space of multiple environmental factors to provide sufficient samples for subsequent modeling. The environmental factors selected are key influencing factors on hydrogen embrittlement sensitivity, including service temperature (T), equivalent stress (T), etc. These three environmental factors—temperature, hydrogen sulfide partial pressure (P), and hydrogen sulfide partial pressure—interact significantly in real-world operating conditions. For example, increased temperature accelerates hydrogen production from corrosion while potentially alleviating stress concentration.

[0040] The pre-designed experimental setup adopts the Box-Behnken design (BBD) from the response surface methodology. This design can cover the coupling space of the three environmental factors with fewer trials, avoiding the high cost of full factorial experiments. The specific environmental factor levels are set as follows: The service temperature T ranges from -20℃ to 80℃, divided into 5 levels (-20℃, 10℃, 40℃, 70℃, 80℃); equivalent stress. The value range is 0 to 0.8. ( To determine the yield strength of the circumferential weld joint material, in this embodiment the material is X80 steel. =555MPa), divided into 5 levels (0MPa, 111MPa, 222MPa, 333MPa, 444MPa); the partial pressure of hydrogen sulfide P ranges from 0.01MPa to 0.5MPa, divided into 5 levels (0.01MPa, 0.1MPa, 0.2MPa, 0.3MPa, 0.5MPa).

[0041] The test data were obtained through slow strain rate tensile tests, performed according to established standards. Test samples were taken from the heat-affected zone of the circumferential weld joint of X80 steel pipes and processed into... Three parallel specimens were prepared for each combination of environmental factors for tensile testing of round bars. The tensile rate was set to... This simulates the long-term service conditions of pipelines.

[0042] The experimental data is the reduction of area loss (RALoss), which is the core parameter for evaluating hydrogen embrittlement sensitivity. It is calculated using the formula RALouss = [(RAInert - RAH) / RAInert] × 100%. Here, RAInert is the reduction of area of ​​the sample in an inert environment (99.99% argon purity), and RAH is the reduction of area of ​​the sample in a wet hydrogen sulfide environment (saturated brine as electrolyte) with the corresponding hydrogen sulfide partial pressure and temperature. For example, in a certain set of tests, RAInert = 65% and RAH = 42%, then RALouss = (65-42) / 65 × 100% ≈ 35.38%, which is the hydrogen embrittlement sensitivity test data under this combination of environmental factors.

[0043] The reduction of area (RA) was measured as follows: After the test, a vernier caliper (accuracy 0.01 mm) was used to measure the original cross-sectional area (A0) and the minimum cross-sectional area after fracture (A_f) of the specimen. The reduction of area RA = (A0 - A_f) / A0 × 100%. For example, a specimen with an original diameter of 5 mm... The minimum diameter after fracture was 3.8 mm. , then RA=(19.63-11.34) / 19.63×100%≈42%; For each combination of environmental factors, the reduction of area (RAI) needs to be measured separately in inert and hydrogen environments. For example, the RAIInert of the X80 steel HAZ sample is 65% in an inert environment (argon) and RAH is 42% in an environment with a hydrogen sulfide partial pressure of 0.2 MPa and a service temperature of 40°C. Substituting these values ​​into the formula, we get: RAILoss = [(65-42) / 65] × 100% ≈ 35.38%.

[0044] If there is data dispersion among parallel samples, the average RALoss of the three parallel samples is taken as the final test data. For example, if the RALoss of the three parallel samples are 34.8%, 35.5%, and 35.9%, the average value is approximately 35.4% (34.8 + 35.5 + 35.9) / 3.

[0045] The above-mentioned technical means clarified the calculation steps and data processing methods for the section reduction rate loss rate, ensuring the uniformity and accuracy of the experimental data and providing reliable dependent variable data for subsequent modeling.

[0046] By reading the tensile data of each specimen in real time, the reduction of area (RALoss) is calculated and then combined with the corresponding environmental factors (such as T=40℃). =222MPa, P=0.2MPa) associated storage, for example, a total of 46 sets of valid experimental data (the number of standard experimental groups of BBD design three factors 5 levels).

[0047] Furthermore, by quantifying the coupling effects between environmental factors, the limitations of existing models, which can only linearly superimpose the effects of a single environmental factor, are addressed. A multiple quadratic regression model is chosen as the multivariate mathematical model because it can characterize the nonlinear effects of a single factor through quadratic terms and the coupling effects of multiple environmental factors through interaction terms, achieving a fitting accuracy that meets engineering requirements.

[0048] The form of the multiple quadratic regression model is: (i≠j), where, For environmental factors (T, (P, etc.) This is a linear term, representing the linear effect of a single environmental factor on hydrogen embrittlement sensitivity; This is a quadratic term, representing the nonlinear effect of a single environmental factor (such as the decrease in hydrogen embrittlement sensitivity after the temperature rises to a certain level). (i≠j) is an interaction term that characterizes the coupling effect of two environmental factors (such as the synergistic effect of temperature and stress).

[0049] Furthermore, when the environmental factor is T, Given P, the multiple quadratic regression model is fitted. The specific form of the multiple quadratic regression model is as follows: .

[0050] in, This is a constant term, representing the inherent basic brittleness level of the ring weld joint material itself under the mildest or most average operating conditions; The coefficients of the linear and quadratic terms, These are the coefficients of the environmental factor interaction terms, which are used to quantify coupling effects, for example, Characterizes the coupling effect between service temperature and equivalent stress.

[0051] Furthermore, based on the 46 sets of experimental data obtained (independent variable being T, ... The experimental data (with P as the dependent variable and RALoss as the dependent variable) were preprocessed to remove outliers. Then, response surface regression analysis was used, setting the model type to "quadratic polynomial," and the coefficients were calculated using the least squares method to obtain the fitted model: RALoss = 12.5 + 0.32T + 0.18 +5.6P +0.002T2 +0.0001 +3.2P 2 +0.001 +0.08TP +0.005 .

[0052] The fit was verified by the coefficient of determination R. 2 In this embodiment, R is determined to be... 2 =0.96, indicating that the model can explain 96% of the experimental data variation and has good fitting accuracy; the coefficients of the environmental factor interaction terms are all non-zero, proving that the coupling effect of service temperature and equivalent stress, and service temperature and hydrogen sulfide partial pressure are effectively quantified. The multiple quadratic regression model captures the nonlinear effects of single factors and the coupling effects of multiple factors through the combination of linear, quadratic, and interaction terms, achieving high fitting accuracy and reducing prediction bias compared to existing linear models.

[0053] Furthermore, the abstract multivariate mathematical model is transformed into an intuitive visual graph, solving the problem that engineers find it difficult to quickly understand the effects of multiple coupled factors. Based on the fitted multivariate quadratic regression model, two types of multidimensional environmental spectra can be generated: response surface plots and contour plots.

[0054] In another specific example, regarding the welded joint of a 304 stainless steel hydrogen energy storage tank, the environmental factors focus on the key influencing factors of the high-pressure hydrogen environment, specifically implemented as follows: Multiple environmental factors include service temperature (T), equivalent stress (T), etc. The ambient hydrogen concentration (CH) is used, where the ambient hydrogen concentration replaces the partial pressure of hydrogen sulfide, which is consistent with the service characteristics of a high-pressure hydrogen environment. The preset test design still adopts the BBD design, and the environmental factor levels are specifically set as follows: the value range of T is -40℃ to 60℃ (hydrogen energy storage tanks may face low temperature conditions), divided into 5 levels (-40℃, -10℃, 20℃, 50℃, 60℃); The value range is 0 to 0.7. (304 stainless steel) =205MPa), divided into 5 levels (0MPa, 41MPa, 82MPa, 123MPa, 143.5MPa); CH ranges from 90vol% to 100vol% (high pressure hydrogen purity requirement), divided into 5 levels (90vol%, 92.5vol%, 95vol%, 97.5vol%, 100vol%).

[0055] The specimens were taken from the weld zone (WM) of the circumferential weld joint of a 304 stainless steel storage tank, and the tensile rate was set to... The experiment simulated long-term static service of the storage tank. The inert environment was nitrogen (99.99% purity), and the hydrogen environment was high-pressure hydrogen at the corresponding concentration (5 MPa). The experimental data is still RALoss. For example, in a certain test group, RAInert=72% and RAH=51%, then RRALoss=(72-51) / 72×100%≈29.17%. The data acquisition module acquired a total of 46 sets of valid experimental data, which were stored in combination with environmental factors.

[0056] The multiple quadratic regression model in the coupling effect modeling module takes the following form: .

[0057] in, This is a constant term, representing the inherent basic brittleness level of the ring weld joint material itself under the mildest or most average operating conditions; The coefficients of the linear and quadratic terms, These are the coefficients of the environmental factor interaction terms, which are used to quantify coupling effects.

[0058] The fitted value is: RALouss = 8.2 + 0.25T + 0.31 +4.8CH +0.0015T 2 +0.0008 +2.1CH 2 +0.002 +0.05TCH +0.003 CH, coefficient of determination R 2 =0.95, interaction item , , All values ​​are non-zero, effectively quantifying the coupling effects between service temperature and equivalent stress, service temperature and ambient hydrogen concentration, and equivalent stress and ambient hydrogen concentration.

[0059] Furthermore, with a fixed environmental hydrogen concentration of CH=95 vol%, and T, Using the x and y axes as the horizontal and vertical axes, and RALoss as the vertical axis, a response surface plot is drawn. It can be observed that when low temperature (-40℃) and high stress (143.5MPa) are coupled, the surface rises significantly (RALoss≈42%), indicating that the hydrogen embrittlement sensitivity is extremely strong under this coupling state. The contour plot uses different colors to mark the RALoss intervals, which facilitates the rapid location of risks.

[0060] To assess the risk level, the user inputs the operating condition parameters to be assessed (T=-20℃, =123MPa, CH=97.5vol%), after locating on the contour map, RALoss≈39.2%, the risk level was determined to be level 3 (high risk area), and the warning result was output: "Hydrogen embrittlement risk level of the working condition to be evaluated: level 3 (high risk area), it is recommended to reduce stress or optimize hydrogen purity".

[0061] By setting the interaction term of environmental factors in the fitting of the multivariate mathematical model, the quantitative evaluation of the coupling effect of multiple environmental factors in this scenario was realized. This solved the problem that traditional tests could not cover the coupling conditions of low temperature, high pressure hydrogen, and high stress, and provided reliable support for the safe design of hydrogen energy equipment.

[0062] Optionally, based on a multivariate mathematical model, multiple multidimensional environmental spectra are generated, including: One of the multiple environmental factors is designated as a fixed term, and the remaining two environmental factors are used as the horizontal and vertical axes to construct a coordinate system. Based on the multivariate mathematical model, the predicted hydrogen embrittlement sensitivity values ​​corresponding to the coordinate points in the coordinate system are calculated, and a response surface and contour lines are constructed with the predicted hydrogen embrittlement sensitivity values ​​as the response values. The multidimensional environmental spectrum is obtained by superimposing risk level markers based on the range of predicted hydrogen embrittlement sensitivity values ​​onto the response surface or contour lines.

[0063] In this optional embodiment, a specific method for generating multiple multidimensional environmental spectra based on a multivariate mathematical model is provided: First, one of the multiple environmental factors is determined as a fixed term, and the remaining two environmental factors are used as the horizontal and vertical axes respectively to construct a coordinate system. Then, according to the multivariate mathematical model, the predicted value of hydrogen embrittlement sensitivity corresponding to the coordinate points in the coordinate system is calculated, and the predicted value of hydrogen embrittlement sensitivity is used as the vertical axis to construct a response surface and contour lines. The response surface is presented in three dimensions, which can intuitively observe the changing trend of hydrogen embrittlement sensitivity under the coupling effect of the other two environmental factors when one environmental factor is fixed (e.g., peak position, rising / falling slope); the contour line plot is presented in two dimensions, and the distribution density of hydrogen embrittlement sensitivity is reflected by the color gradient and the spacing between the contour lines (the denser the contour lines, the more drastic the change in hydrogen embrittlement sensitivity and the more significant the coupling effect).

[0064] Finally, to perform risk zoning, risk level labels based on the range of hydrogen embrittlement sensitivity prediction values ​​are superimposed on the response surface or contour lines to obtain the final multidimensional environmental spectrum.

[0065] In a specific example, the response surface plotting process is as follows: One environmental factor is fixed at an intermediate level, for example, P = 0.2 MPa, and the other two environmental factors T and... Using T and RALoss as the x and y axes respectively, and RALoss as the y-axis, calculate each T and RALoss according to the multivariate mathematical model. Combine the corresponding RALoss values ​​to plot a three-dimensional surface, which serves as the response surface plot. The three-dimensional surface can visually demonstrate the changing trend of hydrogen embrittlement sensitivity under the coupled effects of service temperature and equivalent stress when the hydrogen sulfide partial pressure is constant. For example, at T=40℃... At 222 MPa, a peak value appears on the surface, with RALoss = 35%, indicating that the hydrogen embrittlement sensitivity is highest under this coupling state.

[0066] The contour plot drawing process is as follows: using the horizontal and vertical coordinates (T and y) of the response surface plot... Using planar coordinates, the range of RALoss values ​​is divided into multiple intervals, such as 0%–10%, 10%–25%, 25%–40%, and above 40%. Each interval is marked with a different color, and color boundary lines (i.e., contour lines) are drawn based on the model calculation results. This map can quickly locate different (T, The combination of these parameters corresponds to the hydrogen embrittlement sensitivity range, facilitating quick engineering queries.

[0067] In addition, to make the risk zoning more intuitive, risk level labels based on the range of hydrogen embrittlement sensitivity prediction values ​​can be superimposed on the response surface and contour map to obtain a multidimensional environmental spectrum.

[0068] In a specific example, RALoss < 10% is a safe zone (risk level 1), 10% ≤ RALoss < 25% is a monitoring zone (risk level 2), 25% ≤ RALoss < 40% is a high-risk zone (risk level 3), and RALoss ≥ 40% is an extremely high-risk zone (risk level 4). These thresholds are stored in a risk configuration library. Based on these data ranges, risk level indicators are overlaid on the response surface and contour map. For example, on the contour map, the 10% threshold line is marked with a green line, the 25% threshold line with a blue line, and the 40% threshold line with a red line; the area within the green line is filled with light green (safe zone), the area between the green and blue lines is filled with light blue (monitoring zone), the area between the blue and red lines is filled with orange (high-risk zone), and the area outside the red line is filled with red (extremely high-risk zone).

[0069] The interface offers two display modes: "layered display" and "overlay display," which users can switch between. In layered display, the response surface / contour plot and the partitioned interface are shown separately, facilitating individual analysis of coupling patterns or risk zones. In overlay display, the partitioned interface is superimposed on the response surface / contour plot, allowing users to simultaneously observe the risk level corresponding to a specific coupling state (e.g., T=40℃, ...). The coordinate point with a pressure of 222 MPa is located in the orange area, which corresponds to a high-risk area.

[0070] Through the aforementioned technical means, the layered design enables the multidimensional environmental spectrum to have both analytical and application functions. Engineers can conduct in-depth research on the multi-factor coupling mechanism through the coupling layer, and quickly judge the risk of the working condition through the early warning layer, thereby improving the engineering practicality of the spectrum.

[0071] In addition, considering that in existing technologies, experimental designs need to be manually formulated, experimental data is stored in a scattered manner, is easily lost and difficult to reuse, resulting in low efficiency in subsequent modeling, this embodiment provides a scheme for storing hydrogen embrittlement sensitivity test data. The test data is the reduction of area loss rate obtained through slow strain rate tensile tests, specifically implemented as follows: Using various experimental design algorithms such as response surface methodology and orthogonal experimental design, users can select the type of environmental factor (e.g., T, ...) through the system interface. The user selects factors such as P (value range, number of levels) to generate the corresponding experimental design scheme. For example, the user selects factor T (-20℃~80℃). (0~444MPa), P (0.01MPa~0.5MPa), number of levels 5, can generate 46 experimental schemes for BBD design, including factor combination, sample number and experimental sequence for each scheme. The scheme can be exported as a Portable Document Format (PDF) for experimental personnel to refer to.

[0072] Furthermore, a relational database was used to construct an associated structure of test item table, factor data table, and test result table. The test item table stores basic information such as test name, material type, joint type, and test standards; the factor data table stores the combination of environmental factors (T, T, T) for each test group. The test results table stores data such as the specific value and unit of P; the cross-sectional area reduction loss rate (RALoss), the average value of parallel samples, the test date, and the equipment number. After verification, the test data acquired by the data acquisition module is automatically written into the database, with the data retention period set to a preset number of years (e.g., 10 years) to meet engineering traceability requirements.

[0073] Simultaneously, it offers multi-condition combined search, allowing users to query test data by project name, material type, environmental factor range, and other criteria. For example, a user could search for "X80 steel, T=40℃±5℃, Given the experimental data of “222MPa±20MPa”, the unit quickly matches relevant data from the database and displays factor combinations, RALoss values, and experimental details.

[0074] The above methods enable the automated generation of experimental design schemes, reducing the time required for manual formulation. At the same time, they enable the structured storage of experimental data, preventing data loss and improving reusability. The retrieval function allows for quick location of the required data, facilitating subsequent model updates.

[0075] Optionally, if the hydrogen embrittlement sensitivity test data is updated, the multivariate mathematical model and multidimensional environmental spectrum are updated based on the updated hydrogen embrittlement sensitivity test data.

[0076] In this optional embodiment, to address the problem that existing models cannot be iteratively optimized once established, the operation of refitting to update the multivariate mathematical model and multidimensional environmental spectrum is initiated after supplementing the experimental data database with new experimental data. The specific implementation is as follows: When new test data is added to the database (such as test data for different materials or joint types, or extreme working condition data outside the original factor range), and the amount of new data is ≥5 sets, an update will be automatically triggered; users can also manually trigger an update (such as when the amount of new data is <5 sets).

[0077] The specific steps for updating the multivariate data model are as follows: First, merge the newly added experimental data with the original data, removing duplicate data and outliers; second, call the original fitting algorithm (least squares method) and recalculate the coefficients of the multivariate quadratic regression model based on the merged dataset; third, re-perform R... 2 F-test and residual analysis were used to ensure that the fitting accuracy of the updated model was not lower than that of the original model (R²). 2 ≥0.95); Fourth step, based on the updated model, redraw the response surface plot, contour plot, and hierarchical multidimensional environment spectrum to cover the range of factor combinations corresponding to the newly added data; Fifth step, send a model update notification to the user, informing them of the update time, the amount of new data, and changes in model accuracy (e.g., R...). 2 (Increased from 0.96 to 0.97). For example, with 46 sets of existing data and 8 sets of newly added experimental data on the X80 steel ring weld head base material (BM), after triggering the update, the data was merged into 54 sets, and the refitted model R... 2 =0.97, the coverage of the multidimensional environmental spectrum extends to the working condition range of the parent material.

[0078] Through the automatic updating mechanism of multivariate mathematical models and spectra, the device can adapt to the needs of different materials, different joint types, and different working conditions. As data accumulates, the accuracy of the model continues to improve, the scope of application continues to expand, and the service life and engineering value of the device are extended.

[0079] S230. Locate the risk level identifier corresponding to the predicted value of hydrogen embrittlement sensitivity in the multidimensional environmental spectrum, and determine the hydrogen embrittlement risk level corresponding to the environmental factor based on the risk level identifier.

[0080] In this embodiment of the invention, the risk level identifier corresponding to the predicted value of hydrogen embrittlement sensitivity is located in the multidimensional environmental spectrum. For example, if the determined hydrogen embrittlement risk level is between 25% and 40%, then the corresponding risk level identifier can be determined as risk level 3.

[0081] S240. If the hydrogen embrittlement risk level is higher than the set risk threshold, initiate a risk warning for the ring weld joint to be evaluated.

[0082] Optionally, after inputting the environmental factors into a pre-established multidimensional environmental spectrum and determining the hydrogen embrittlement risk level corresponding to the environmental factors, the method further includes: If the hydrogen embrittlement risk level is higher than the set risk threshold, determine the fixed and adjustment items among the multiple environmental factors based on the current operating conditions of the ring weld joint to be evaluated. Substitute the fixed term and the target hydrogen embrittlement sensitivity prediction value into the multivariate mathematical model, and calculate the adjustment value of the adjustment term in reverse.

[0083] In this optional embodiment, to address the issue of providing only early warnings without guidance, a specific step is provided after inputting the environmental factors into a pre-established multidimensional environmental spectrum and determining the hydrogen embrittlement risk level corresponding to the environmental factors: If the hydrogen embrittlement risk level is higher than a set risk threshold, an adjustment value for one or more of the environmental factors is output based on the multivariate mathematical model to reduce the risk level to a monitoring or safe zone. Specifically: First, when the hydrogen embrittlement risk level exceeds the set risk threshold, fixed and adjusted terms from multiple environmental factors are determined based on the current operating conditions of the welded joint to be evaluated. The fixed terms are determined based on engineering feasibility; for example, if the partial pressure of hydrogen sulfide in the current environment cannot be adjusted, it is considered a fixed term. Then, the fixed terms and the target predicted hydrogen embrittlement sensitivity are substituted into a multivariate mathematical model to calculate the adjustment values ​​for the adjusted terms.

[0084] In a specific example, the environmental factors to be considered include service conditions at T=50℃ and equivalent stress. =333MPa, hydrogen sulfide partial pressure P=0.3MPa, the calculated hydrogen embrittlement sensitivity prediction value is 38.6%, belonging to risk level 3, triggering reverse calculation. The target risk level for reverse calculation is risk level 1 or 2, that is, hydrogen embrittlement sensitivity prediction value <25%. The specific steps of reverse calculation are: First, fix some environmental factors (according to engineering feasibility, such as fixing P=0.3MPa if it cannot be adjusted); Second, set the target dependent variable value (RALoss=25%); Third, transform the multivariate mathematical model into a model concerning adjustable factors (T, The equation is: 25 = 12.5 + 0.32T + 0.18 +0.002T 2 +0.0001 +3.2×(0.3) 2 +0.001 +0.08T×0.3+0.005 ×0.3; Fourth step, solve the equation to obtain the adjustment values ​​of multiple sets of adjustment terms. These adjustments must meet the actual engineering requirements, such as adjusting T within the range of -20℃ to 80℃. The adjustment range is 0–444 MPa; the fifth step is to select the final adjustment scheme based on the difficulty and cost of operation, such as adjusting... =200MPa (originally 333MPa), T remains at 50℃, and the result is 23.8% when substituted into the model; or adjust T=30℃ (originally 50℃). Maintaining a pressure of 333 MPa, the calculated value is 24.2%.

[0085] Finally, an adjustment report is output, which includes the name of the adjustment item, the original value, the adjusted value, the predicted value of hydrogen embrittlement sensitivity after adjustment, and implementation recommendations. For example, "Reducing the equivalent stress to 200 MPa can be achieved by optimizing the pipeline support structure at a lower cost."

[0086] Through the above steps, reverse calculation achieves a closed loop of risk assessment and solution optimization. The output adjustment value is scientific and feasible, and can effectively reduce hydrogen embrittlement risk to the target level. Compared with manual trial and error, it shortens the time for developing risk reduction solutions.

[0087] The technical solution of this invention acquires multiple environmental factors of the working environment of the ring weld joint to be evaluated, including service temperature, equivalent stress, and environmental hydrogen parameters. These environmental factors are then input into a pre-established multidimensional environmental spectrum. The predicted hydrogen embrittlement sensitivity value corresponding to each environmental factor is determined within the multidimensional environmental spectrum. The risk level identifier corresponding to the predicted hydrogen embrittlement sensitivity value is located within the multidimensional environmental spectrum. Based on the risk level identifier, the hydrogen embrittlement risk level corresponding to each environmental factor is determined. Finally, if the hydrogen embrittlement risk level exceeds a set risk threshold, a risk warning is initiated for the ring weld joint to be evaluated, thereby improving the accuracy of hydrogen embrittlement risk prediction.

[0088] Example 3 Figure 3 This is a schematic diagram of a hydrogen embrittlement risk warning device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: The environmental factor acquisition module 310 is used to acquire multiple environmental factors of the working environment of the ring weld joint to be evaluated; the multiple environmental factors include service temperature, equivalent stress and environmental hydrogen parameters; The hydrogen embrittlement risk level determination module 320 is used to input the environmental factors into a pre-established multidimensional environmental spectrum and determine the hydrogen embrittlement risk level corresponding to the environmental factors. The multidimensional environmental spectrum is constructed based on a multivariate mathematical model containing at least one interaction term of environmental factors, and is used to characterize the variation of the hydrogen embrittlement sensitivity prediction value with the environmental factors; the multidimensional environmental spectrum includes risk level identifiers based on the range to which the hydrogen embrittlement sensitivity prediction value belongs. The risk warning module 330 is used to initiate a risk warning for the ring weld joint to be evaluated when the hydrogen embrittlement risk level is higher than a set risk threshold.

[0089] The technical solution of this invention involves acquiring multiple environmental factors of the working environment of the ring weld joint to be evaluated. These environmental factors include service temperature, equivalent stress, and environmental hydrogen parameters. The environmental factors are then input into a pre-established multidimensional environmental spectrum to determine the hydrogen embrittlement risk level corresponding to each environmental factor. The multidimensional environmental spectrum is constructed based on a multivariate mathematical model containing at least one interaction term of the environmental factors, and is used to characterize the variation of the predicted hydrogen embrittlement sensitivity value with the environmental factors. Furthermore, the multidimensional environmental spectrum includes risk level identifiers based on the range of the predicted hydrogen embrittlement sensitivity value. Finally, if the hydrogen embrittlement risk level exceeds a set risk threshold, a risk warning is initiated for the ring weld joint to be evaluated, thereby improving the accuracy of hydrogen embrittlement risk prediction.

[0090] Optionally, the hydrogen embrittlement risk early warning device also includes a multi-dimensional environmental spectrum construction module for constructing a multi-dimensional environmental spectrum, including: The test data acquisition unit is used to acquire hydrogen embrittlement susceptibility test data of the ring weld joint under multiple environmental factors; the hydrogen embrittlement susceptibility test data includes environmental factors and the corresponding reduction of area loss rate of the ring weld joint; the reduction of area loss rate is used to quantify hydrogen embrittlement susceptibility. The model fitting unit is used to fit a multivariate mathematical model between multiple environmental factors and predicted values ​​of hydrogen embrittlement sensitivity based on the hydrogen embrittlement sensitivity test data; the multivariate mathematical model includes at least one environmental factor interaction term used to quantify the coupling relationship between environmental factors. A multidimensional environmental spectrum construction unit is used to generate multiple multidimensional environmental spectra based on the multivariate mathematical model; the multidimensional environmental spectrum includes the response surface and contour lines of the hydrogen embrittlement sensitivity prediction value as a function of the environmental factors.

[0091] Optionally, the multivariate mathematical model is a multivariate quadratic regression model fitted based on the response surface methodology, and the multivariate quadratic regression model includes a first-order term, a second-order term, and an interaction term for the environmental factors.

[0092] Optionally, the hydrogen embrittlement risk level determination module 320 is specifically used for: The environmental factors are input into a pre-established multidimensional environmental spectrum, and the predicted value of hydrogen embrittlement sensitivity corresponding to the environmental factors is determined in the multidimensional environmental spectrum. Locate the risk level identifier corresponding to the predicted hydrogen embrittlement sensitivity value in the multidimensional environmental spectrum, and determine the hydrogen embrittlement risk level corresponding to the environmental factor based on the risk level identifier.

[0093] Optionally, the hydrogen embrittlement risk warning device also includes: The adjustment item determination module is used to determine the fixed items and adjustment items among the multiple environmental factors after inputting the environmental factors into a pre-established multidimensional environmental spectrum and determining the hydrogen embrittlement risk level corresponding to the environmental factors. If the hydrogen embrittlement risk level is higher than a set risk threshold, the module determines the fixed items and adjustment items among the multiple environmental factors according to the current working condition of the ring weld joint to be evaluated. The adjustment value calculation module is used to substitute the fixed term and the target hydrogen embrittlement sensitivity prediction value into the multivariate mathematical model to calculate the adjustment value of the adjustment term in reverse.

[0094] Optional, multidimensional environmental spectrum building blocks, specifically used for: One of the multiple environmental factors is designated as a fixed term, and the remaining two environmental factors are used as the horizontal and vertical axes to construct a coordinate system. Based on the multivariate mathematical model, the predicted hydrogen embrittlement sensitivity values ​​corresponding to the coordinate points in the coordinate system are calculated, and a response surface and contour lines are constructed with the predicted hydrogen embrittlement sensitivity values ​​as the response values. The multidimensional environmental spectrum is obtained by superimposing risk level markers based on the range of predicted hydrogen embrittlement sensitivity values ​​onto the response surface or contour lines.

[0095] Optionally, the hydrogen embrittlement risk warning device also includes: The environmental spectrum update module is used to update the multivariate mathematical model and the multidimensional environmental spectrum based on the updated hydrogen embrittlement sensitivity test data when the hydrogen embrittlement sensitivity test data is updated.

[0096] The hydrogen embrittlement risk warning device provided in the embodiments of the present invention can execute the hydrogen embrittlement risk warning method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0097] In the technical solution of this invention, the information collected is information and data authorized by the user or fully authorized by all parties. The collection, storage, use, processing, transmission, provision, disclosure and application of related data all comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse.

[0098] Example 4 According to embodiments of the present invention, the present invention also provides an electronic device, a readable storage medium, and a computer program product.

[0099] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, application processors, blade application processors, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0100] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0101] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0102] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the hydrogen embrittlement risk warning method.

[0103] In some embodiments, the hydrogen embrittlement risk warning method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the hydrogen embrittlement risk warning method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the hydrogen embrittlement risk warning method by any other suitable means (e.g., by means of firmware).

[0104] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0105] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or application.

[0106] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0107] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0108] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data application processors), or computing systems that include middleware components (e.g., application application processors), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0109] A computing system can include clients and applications. Clients and applications are generally geographically separated and typically interact via a communication network. The client-application relationship is established by computer programs running on the respective computers and having a client-application relationship with each other. An application can be a cloud application, also known as a cloud computing application or cloud server, which is a hosting product within the cloud computing application ecosystem. It addresses the shortcomings of traditional physical servers and VPS applications, such as high management difficulty and weak business scalability.

[0110] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0111] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for early warning of hydrogen embrittlement risk, characterized in that, include: Obtain multiple environmental factors of the working environment of the ring weld joint to be evaluated; The multiple environmental factors include service temperature, equivalent stress, and environmental hydrogen parameters; The environmental factors are input into a pre-established multidimensional environmental spectrum to determine the hydrogen embrittlement risk level corresponding to the environmental factors. The multidimensional environmental spectrum is constructed based on a multivariate mathematical model containing at least one interaction term of environmental factors, and is used to characterize the variation of the hydrogen embrittlement sensitivity prediction value with the environmental factors; the multidimensional environmental spectrum includes risk level identifiers based on the range to which the hydrogen embrittlement sensitivity prediction value belongs. If the hydrogen embrittlement risk level is higher than the set risk threshold, a risk warning is issued for the ring weld joint to be evaluated.

2. The method according to claim 1, characterized in that, The multidimensional environmental spectrum is constructed in the following manner: Hydrogen embrittlement susceptibility test data of ring welded joints under multiple environmental factors were obtained; the hydrogen embrittlement susceptibility test data included environmental factors and corresponding reduction of area loss rate of ring welded joints; the reduction of area loss rate was used to quantify hydrogen embrittlement susceptibility. Based on the hydrogen embrittlement sensitivity test data, a multivariate mathematical model is fitted between multiple environmental factors and the predicted values ​​of hydrogen embrittlement sensitivity; the multivariate mathematical model includes at least one environmental factor interaction term used to quantify the coupling relationship between environmental factors. Based on the aforementioned multivariate mathematical model, multiple multidimensional environmental spectra are generated; The multidimensional environmental spectrum includes the response surface and contour lines of the predicted hydrogen embrittlement sensitivity values ​​as a function of the environmental factors.

3. The method according to claim 2, characterized in that, The multivariate mathematical model is a multivariate quadratic regression model fitted based on the response surface methodology. The multivariate quadratic regression model includes a first-order term, a second-order term, and an interaction term for the environmental factors.

4. The method according to claim 1, characterized in that, The environmental factors are input into a pre-established multidimensional environmental spectrum to determine the hydrogen embrittlement risk level corresponding to the environmental factors, including: The environmental factors are input into a pre-established multidimensional environmental spectrum, and the predicted value of hydrogen embrittlement sensitivity corresponding to the environmental factors is determined in the multidimensional environmental spectrum. Locate the risk level identifier corresponding to the predicted hydrogen embrittlement sensitivity value in the multidimensional environmental spectrum, and determine the hydrogen embrittlement risk level corresponding to the environmental factor based on the risk level identifier.

5. The method according to claim 1, characterized in that, After inputting the environmental factors into a pre-established multidimensional environmental spectrum and determining the hydrogen embrittlement risk level corresponding to the environmental factors, the process further includes: If the hydrogen embrittlement risk level is higher than the set risk threshold, determine the fixed and adjustment items among the multiple environmental factors based on the current operating conditions of the ring weld joint to be evaluated. Substitute the fixed term and the target hydrogen embrittlement sensitivity prediction value into the multivariate mathematical model, and calculate the adjustment value of the adjustment term in reverse.

6. The method according to claim 2, characterized in that, Based on the aforementioned multivariate mathematical model, multiple multidimensional environmental spectra are generated, including: One of the multiple environmental factors is designated as a fixed term, and the remaining two environmental factors are used as the horizontal and vertical axes to construct a coordinate system. Based on the multivariate mathematical model, the predicted hydrogen embrittlement sensitivity values ​​corresponding to the coordinate points in the coordinate system are calculated, and a response surface and contour lines are constructed with the predicted hydrogen embrittlement sensitivity values ​​as the response values. The multidimensional environmental spectrum is obtained by superimposing risk level markers based on the range of predicted hydrogen embrittlement sensitivity values ​​onto the response surface or contour lines.

7. The method according to claim 2, characterized in that, Also includes: If the hydrogen embrittlement sensitivity test data is updated, the multivariate mathematical model and multidimensional environmental spectrum are updated based on the updated hydrogen embrittlement sensitivity test data.

8. A hydrogen embrittlement risk early warning device, characterized in that, include: The environmental factor acquisition module is used to acquire multiple environmental factors of the working environment of the ring weld joint to be evaluated; the multiple environmental factors include service temperature, equivalent stress and environmental hydrogen parameters; The hydrogen embrittlement risk level determination module is used to input the environmental factors into a pre-established multidimensional environmental spectrum and determine the hydrogen embrittlement risk level corresponding to the environmental factors. The multidimensional environmental spectrum is constructed based on a multivariate mathematical model containing at least one interaction term of environmental factors, and is used to characterize the variation of the hydrogen embrittlement sensitivity prediction value with the environmental factors; the multidimensional environmental spectrum includes risk level identifiers based on the range to which the hydrogen embrittlement sensitivity prediction value belongs. The risk warning module is used to initiate a risk warning for the ring weld joint to be evaluated when the hydrogen embrittlement risk level is higher than a set risk threshold.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the hydrogen embrittlement risk warning method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the hydrogen embrittlement risk warning method according to any one of claims 1-7.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the hydrogen embrittlement risk warning method according to any one of claims 1-7.

Images