Device and method for assessing the risk of sulfur deposition in the pipes of a high-sulfur gas field

Abstract

The application discloses a device and method for risk assessment of sulfur deposition in high-sulfur gas field pipelines, and belongs to the technical field of safety monitoring of oil and gas storage and transportation engineering. The device comprises a natural gas compressor, a variable volume gas tank, a temperature control system, a dosing pump, a transparent glass tube, an ultraviolet spectrophotometer, a dosing tank, a computer, a pressure sensor and a temperature sensor connected through multiple automatic valves. The method comprises the following steps: collecting sample gas into the variable volume gas tank; adjusting the temperature and pressure to the target working condition to promote sulfur precipitation; injecting a solvent to dissolve the sulfur and transfer it to the transparent glass tube for ultraviolet detection; and calculating the amount of sulfur precipitation and assessing the risk according to the detection results. The application realizes online and quantitative measurement and visual risk assessment of the sulfur precipitation potential of specific working points and the whole line of the pipeline under the condition of uninterrupted gas transmission, and solves the technical problems of lagging behind, relying on theoretical models and being unable to provide global early warning in the prior art.

Description

Technical Field

[0001] This invention relates to the field of safety monitoring technology for oil and gas storage and transportation engineering, specifically to an apparatus and method for assessing the risk of sulfur deposition in pipelines of high-sulfur gas fields. Background Technology

[0002] Natural gas, as an important energy source, often contains dissolved elemental sulfur in its high-sulfur gas fields, in addition to hydrogen sulfide. The solubility of sulfur in natural gas follows thermodynamic phase equilibrium principles and is a function of temperature, pressure, and gas composition. When natural gas flows in pipelines, due to factors such as undulating terrain, pressure reduction during throttling, and ambient temperature drops, its temperature and pressure continuously change, easily leading to a localized decrease in sulfur solubility. This causes sulfur to precipitate as solid elemental sulfur and deposit on the pipeline walls.

[0003] Sulfur deposition significantly reduces the effective flow area of ​​pipelines, increasing transport resistance and energy consumption; in severe cases, it can cause complete pipeline blockage, forcing production interruptions; the deposits can also induce localized corrosion, posing safety hazards. Therefore, accurate assessment of the risk of sulfur deposition in pipelines is crucial for implementing preventative maintenance and ensuring the safe and economical operation of pipelines.

[0004] Currently, the industry's assessment of sulfur deposition risk mainly relies on two technical approaches: The first category is physical detection methods based on post-construction sampling and offline analysis. A typical operation involves periodically or after a blockage occurs, using a pipeline cleaning machine to mechanically clean the pipeline, collecting the removed sediment, and then analyzing its sulfur content in a laboratory using techniques such as gravimetric analysis and spectrophotometry. This method has fundamental limitations: it is both delayed and destructive. It can only obtain the total amount of historical sediment, making it a form of "post-construction verification," and cannot provide early warning of ongoing sediment formation risks. Furthermore, the cleaning operation itself requires interrupting production and alters the existing state of the pipeline.

[0005] Information gaps: The results obtained are the cumulative amount of deposits in a certain section of the pipeline, completely losing the "dynamic correspondence between the deposition process and specific operating conditions (temperature, pressure)". It cannot answer the core engineering question of "under what specific temperature and pressure conditions is the sulfur precipitation potential greatest", and therefore cannot accurately locate the pipeline section with the highest risk.

[0006] The second category is prediction methods based on numerical simulation. This method establishes theoretical or empirical models of sulfur solubility in relation to temperature and pressure, and combines these with pipeline simulation software to calculate the temperature and pressure distribution along the pipeline to predict potential deposition locations. While this method achieves pre-determination, its reliability is fundamentally questionable: the accuracy of the prediction depends entirely on the precision of the solubility model (such as the Chrastil model or empirical charts) and the accuracy of the pipeline's thermo-hydraulic calculations. Factors such as changes in gas composition, the actual flow regime within the pipeline, and the influence of impurities can all introduce significant errors, leading to large deviations between the predicted results and actual operating conditions. Essentially, this method is a theoretical deduction and cannot verify and calibrate key parameters or the actual sulfur precipitation of natural gas under specific real-time operating conditions through online, direct measurement methods. This makes it difficult to assess the confidence level of the prediction results and limits its engineering guidance value.

[0007] Current technologies cannot quantitatively measure the "sulfur release potential" at specific operating points along the pipeline in real time, online, and without interrupting transportation. "Offline sampling analysis" loses operating condition information and is severely lagging; "numerical simulation prediction" lacks support from direct measured data. This contradiction leaves pipeline operators in a passive state of "blindly issuing warnings" or "remedial measures after the fact," unable to achieve proactive risk management based on accurate data. Summary of the Invention

[0008] The purpose of this invention is to provide an apparatus and method for assessing the risk of sulfur deposition in pipelines of high-sulfur gas fields, which solves the technical problem that existing technologies cannot measure the potential for sulfur precipitation in pipelines at specific temperature and pressure conditions online, in real time, and quantitatively without interrupting natural gas transportation.

[0009] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows: The device for assessing the risk of sulfur deposition in pipelines of high-sulfur gas fields includes a natural gas compressor, a variable volume gas tank, a temperature control system, a dosing pump, a transparent glass tube, an ultraviolet spectrophotometer, a dosing tank, a computer, a pressure sensor, a temperature sensor, and multiple automatic valves. The natural gas compressor is connected to the main gas transmission pipeline through a first automatic valve. The variable-volume gas tank is connected to the natural gas compressor via a second automatic valve and is housed within the temperature control system. The variable-volume gas tank contains the pressure sensor and temperature sensor, and is connected to the main gas pipeline via a third automatic valve, the dosing pump via a fourth automatic valve, and the transparent glass tube via a sixth automatic valve. The dosing pump is connected to the dosing tank via a fifth automatic valve. A portion of the transparent glass tube passes through the detection optical path of the ultraviolet spectrophotometer and is connected to the external pipeline via a seventh automatic valve. The computer is communicatively connected to the natural gas compressor, the volume adjustment mechanism of the variable volume gas tank, the temperature control system, the dosing pump, the ultraviolet spectrophotometer, the pressure sensor, the temperature sensor, and each of the automatic valves, and is used to control their operation and receive and process detection data.

[0010] Furthermore, the variable volume air box is made of a corrosion-resistant nickel-based alloy, and its volume adjustment range is 50mL to 1200mL.

[0011] Furthermore, the detection wavelength of the ultraviolet spectrophotometer is 250 nm to 270 nm.

[0012] Furthermore, the transparent glass tube is a pressure-resistant acrylic tube with a length-to-inner diameter ratio of 5:1 to 10:1.

[0013] In addition, the present invention also discloses a method for assessing the risk of sulfur deposition in pipelines of high-sulfur gas fields using the device described above, comprising the following steps: Sample gas collection and sealing steps: Open the first automatic valve, the second automatic valve and the third automatic valve, start the natural gas compressor, pump the natural gas sample gas in the gas transmission pipeline into and fill the variable volume gas box to the initial volume, and then close the relevant valves and the compressor to seal the sample gas of the set volume in the box; Operating condition simulation and sulfur precipitation steps: The temperature of the sample gas in the variable volume gas box is adjusted and stabilized to the target temperature by the temperature control system. At the same time, the internal pressure of the variable volume gas box is changed to the target pressure by adjusting the volume of the variable volume gas box, and maintained at the target temperature and pressure for a period of time, so that the elemental sulfur dissolved in the sample gas precipitates into solid sulfur. Solvent injection and sulfur dissolution steps: Open the fourth and fifth automatic valves, start the dosing pump, and inject a metered amount of solvent from the dosing tank into the variable volume gas tank to dissolve the solid sulfur that has been released, forming a sulfur-containing solution; Solution transfer step: Open the sixth and seventh automatic valves, and by changing the volume of the variable volume gas box, pressurize the sulfur-containing solution into and fill the transparent glass tube; Optical detection steps: Start the ultraviolet spectrophotometer and detect the absorbance of the sulfur-containing solution flowing through the transparent glass tube; Data processing and risk assessment steps: The computer calculates the sulfur concentration in the sulfur-containing solution based on the absorbance and the pre-stored absorbance-sulfur concentration relationship; then, based on the initial volume of the sample gas, the injected volume of the solvent, and the sulfur concentration, it calculates the total amount of solid sulfur precipitated from the sample gas under the target temperature and pressure conditions; by comparing the total amount of sulfur precipitated or the sulfur precipitation trend with the pre-stored sulfur solubility-temperature-pressure relationship for the gas composition of the pipeline, the sulfur deposition risk of the pipeline at the corresponding operating point is assessed.

[0014] Furthermore, in the solvent injection and sulfur dissolution steps, while injecting the solvent, the volume of the variable-volume gas box is adjusted to maintain its internal pressure essentially constant.

[0015] Furthermore, the solvent is carbon disulfide.

[0016] Furthermore, the target temperature is adjusted by controlling the temperature at 25°C through the temperature control system.

[0017] Furthermore, in the data processing and risk assessment steps, the computer pre-stores a graph showing the relationship between the solubility of sulfur in hydrogen sulfide-containing natural gas and pressure, which is used to determine, based on the measured amount of sulfur precipitation, areas in the pipeline below a specific pressure as high-risk locations for sulfur deposition.

[0018] Furthermore, the method is a continuous automated cyclic process. After one risk assessment process is completed, the variable volume air box and transparent glass tube are reset, and the next test can be started.

[0019] Furthermore, it also includes: A distributed temperature sensor array is deployed at multiple monitoring points along the main gas transmission pipeline to measure the temperature distribution along the pipeline in real time. ; A distributed pressure sensor array is deployed at multiple monitoring points along the main gas pipeline to measure the pressure distribution along the pipeline in real time. ; The computer is communicatively connected to the distributed temperature sensor array and the distributed pressure sensor array, and the computer has a pre-stored pipeline sulfur deposition risk mapping model based on physical information neural network. The pipeline sulfur deposition risk mapping model uses pipeline trajectory coordinates. Real-time temperature Real-time pressure mainstream hydrogen sulfide mole fraction in natural gas and the local flow velocity calculated from real-time flow data As input, sulfur supersaturation distribution Distribution of comprehensive sedimentary risk index As output; where A constant characterizing the overall properties of the current transported medium. These are the flow field parameters that vary along the flow path.

[0020] Furthermore, the construction and training method of the pipeline sulfur deposition risk mapping model includes the following steps: Model building steps: Construct a multi-layer feedforward neural network ,in The neural network is a set of network weights and bias parameters. The input layer node corresponds to the input variable. Output layer nodes correspond to output variables ; Physical constraint embedding steps: Define the physical laws governing the sulfur deposition process within the pipeline, including the thermodynamic equation describing the sulfur solubility equilibrium and the conservation equation describing gas flow and heat transfer; sample these physical equations within the computational domain. residual at the location As a physical loss item; Data preparation steps: Obtain the training dataset ,in For the input feature vector, This is the corresponding label vector; The device for assessing the risk of sulfur deposition in pipelines of high-sulfur gas fields under different operating conditions Different mainstream temperament Sulfur precipitation amount measured under different flow conditions The conversion is obtained; According to the working conditions The corresponding historical pipeline inspection results or sedimentation event records are annotated; Model training steps: Constructing the total loss function ,in This is the data loss term, which measures the deviation between the neural network's predicted values ​​and the training data labels. This is the physical loss term, which is the sum of squares of the residuals from the physical equations; To balance the hyperparameters of the two loss weights, the gradient descent algorithm is used to optimize the parameters. Minimize the total loss function A well-trained pipeline sulfur deposition risk mapping model was obtained. , These are the optimal parameters.

[0021] Furthermore, a method for real-time mapping of sulfur deposition risk across the entire pipeline network in high-sulfur gas fields includes the following steps: Real-time data acquisition steps: The computer reads the measurement data from the distributed temperature sensor array and the distributed pressure sensor array in real time to obtain the temperature distribution along the pipeline. and pressure distribution Simultaneously, the molar fraction of hydrogen sulfide in the current mainstream natural gas in the pipeline was obtained. and the velocity distribution along the flow path calculated from the flow meter data. ; Risk mapping calculation steps: Set the discrete coordinate points along the pipeline. The corresponding points , , as well as The input is fed into the trained pipeline sulfur deposition risk mapping model. ; Model output steps: The pipeline sulfur deposition risk mapping model Output each coordinate point sulfur supersaturation and comprehensive sedimentation risk index Forming the pipeline along its length and distributed; Visualization and early warning steps: The computer is based on and The system generates a spatial distribution map of sulfur deposition risk in the pipeline and marks high-risk pipe sections. ,in, The preset risk index threshold is used; when a high-risk pipeline section is detected, an early warning signal is generated.

[0022] Furthermore, it also includes the online model update step: Calibration data acquisition steps: Periodically use the aforementioned device for assessing the risk of sulfur deposition in high-sulfur gas field pipelines to measure the amount of sulfur precipitation at key points in the pipeline under the current actual operating conditions, and obtain the measured amount of sulfur precipitation under the current operating conditions. And converted to measured supersaturation. ; Model fine-tuning steps: Mapping model with the pipeline sulfur deposition risk Predicted value at the corresponding point The comparison is performed, and if the deviation exceeds a preset threshold, then... As new data added to the training dataset, the pipeline sulfur deposition risk mapping model was improved. Perform incremental training and update the model parameters.

[0023] Compared with the prior art, the present invention has the following beneficial effects: Existing technologies cannot obtain sulfur precipitation data directly related to specific operating conditions while maintaining continuous pipeline transportation. This invention, through the coordinated control of a variable-volume gas tank and a temperature control system, can actively and precisely adjust the collected natural gas sample to any set target temperature and pressure, thereby realistically simulating the actual operating conditions at any point along the pipeline within a confined space. This directly enables quantitative measurement of sulfur precipitation potential under specific operating conditions, solving the core problems of information lag and lack of correlation in traditional methods.

[0024] This invention provides crucial empirical calibration data for numerical simulation prediction, significantly improving the reliability and credibility of risk assessment results. By using a UV spectrophotometer to perform high-precision detection of sulfur-containing solutions, combined with computer data processing, the total amount of solid sulfur precipitated under simulated conditions can be accurately calculated. This experimental result provides direct and quantifiable evidence for correcting and validating numerical simulation predictions based on thermodynamic models, upgrading risk assessment from relying on theoretical deductions to scientific judgment based on measured data, significantly enhancing its decision-making guidance significance.

[0025] This invention achieves fully automated and continuous operation, significantly improving the safety, convenience, and monitoring efficiency of on-site operations. The entire evaluation process, including sample gas collection, operating condition simulation, solvent injection, solution transfer, optical detection, and data analysis, is automatically controlled and executed by a computer according to programmed instructions. This not only reduces the technical requirements for operators and the exposure risks in high-pressure, sulfur-containing environments, but also makes programmable, periodic, and continuous risk monitoring of different locations on the pipeline a reality, providing dynamic data support for pipeline integrity management.

[0026] This invention integrates precise gas state control, in-situ dissolution of precipitates, optical quantitative detection, and intelligent risk assessment into a single unit. The core innovative component is the variable-volume gas tank, whose variable-volume design cleverly combines quantitative sampling, pressure regulation, process pressure holding, and liquid-driven functions, resulting in a compact system structure and smooth process flow. The entire technical solution is clearly defined and tightly integrated, ultimately outputting sulfur deposition risk criteria with clear engineering guidance, demonstrating strong practicality and ease of implementation and promotion. Attached Figure Description

[0027] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained from these drawings without creative effort.

[0028] Figure 1 This is a schematic diagram of the device structure described in this invention.

[0029] Figure 2 This is a graph showing the relationship between the solubility of sulfur in CS2 and its absorbance at a wavelength of 260 nm.

[0030] Figure 3 This is a graph showing the relationship between the solubility of sulfur in natural gas containing 15% H2S and pressure at 25℃.

[0031] Figure 4 This is a schematic diagram of the single-point sulfur deposition risk assessment process of the present invention.

[0032] Figure 5 This is a schematic diagram illustrating the construction and training process of the pipeline sulfur deposition risk mapping model of the present invention.

[0033] Figure label: 1 Natural gas compressor, 2 Variable volume gas tank, 3 Temperature control system, 4 Dosing pump, 5 Transparent glass tube, 6 Ultraviolet spectrophotometer, 7 Dosing tank, 8 Computer, 9 Pressure sensor, 10 Temperature sensor, 11 First automatic valve, 12 Second automatic valve, 13 Third automatic valve, 14 Fourth automatic valve, 15 Fifth automatic valve, 16 Sixth automatic valve, 17 Seventh automatic valve. Detailed Implementation

[0034] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the embodiments of the invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0035] In the description of the embodiments of the present invention, it should be understood that the terms "length", "vertical", "horizontal", "top", "bottom", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. They are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of the present invention.

[0036] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of embodiments of the present invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0037] In this embodiment of the invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a communication connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this embodiment of the invention according to the specific circumstances.

[0038] In embodiments of the present invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "over," and "on top" of the second feature includes the first feature being directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature includes the first feature being directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0039] The following disclosure provides many different implementations or examples for carrying out different structures of the embodiments of the present invention. To simplify the disclosure of the embodiments of the present invention, specific examples of components and arrangements are described below. Of course, these are merely examples and are not intended to limit the embodiments of the present invention. Furthermore, reference numerals and / or reference letters may be repeated in different examples of the embodiments of the present invention; such repetition is for simplification and clarity and does not in itself indicate a relationship between the various implementations and / or arrangements discussed.

[0040] The following is in conjunction with the appendix Figures 1-5 The embodiments of the present invention will be described in detail below.

[0041] Example 1: This example discloses an apparatus for assessing the risk of sulfur deposition in pipelines of high-sulfur gas fields, including a natural gas compressor 1, a variable volume gas tank 2, a temperature control system 3, a dosing pump 4, a transparent glass tube 5, an ultraviolet spectrophotometer 6, a dosing tank 7, a computer 8, a pressure sensor 9, a temperature sensor 10, and a first automatic valve 11 to a seventh automatic valve 17.

[0042] The inlet of the natural gas compressor 1 is connected to the main gas pipeline via a first automatic valve 11. The inlet of the variable-volume gas tank 2 is connected to the outlet of the natural gas compressor 1 via a second automatic valve 12. The variable-volume gas tank 2 is entirely placed within the constant-temperature chamber of the temperature control system 3. The tank body of the variable-volume gas tank 2 is made of corrosion-resistant nickel-based alloy, and it has a movable piston inside. The piston is driven by a stepper motor controlled by a computer 8, thereby achieving continuous adjustment of its volume from 50 mL to 1200 mL. A pressure sensor 9 and a temperature sensor 10 are installed on the top of the variable-volume gas tank 2 for real-time monitoring of the pressure and temperature of the gas inside the tank. The variable-volume gas tank 2 also has three outlets: the first outlet is connected to the main gas pipeline via a third automatic valve 13 for pressure balancing or venting; the second outlet is connected to the outlet of the dosing pump 4 via a fourth automatic valve 14; and the third outlet is connected to the inlet of the transparent glass tube 5 via a sixth automatic valve 16.

[0043] The inlet of the dosing pump 4 is connected to the dosing tank 7 via the fifth automatic valve 15. The dosing tank 7 contains the solvent carbon disulfide. The transparent glass tube 5 is made of high-pressure resistant plexiglass, with a length of 20 cm, an inner diameter of 2 cm, and an aspect ratio of 10:1. The middle section of the transparent glass tube 5 passes precisely through the sample detection optical path of the ultraviolet spectrophotometer 6. The outlet of the transparent glass tube 5 is connected to the external discharge pipeline via the seventh automatic valve 17.

[0044] Computer 8 communicates with the natural gas compressor 1, the stepper motor driving the piston of the variable-volume gas tank 2, the temperature control system 3, the dosing pump 4, the ultraviolet spectrophotometer 6, the pressure sensor 9, the temperature sensor 10, and the first to seventh automatic valves via control circuits. It sends control commands to these components and receives their feedback signals and data. Computer 8 has a pre-stored standard curve database, including a standard curve of sulfur concentration-absorbance in carbon disulfide, and curves showing the relationship between the solubility of sulfur in natural gas of specific components and temperature and pressure.

[0045] In addition, this embodiment also discloses a method for assessing the risk of sulfur deposition in pipelines of high-sulfur gas fields. This method is applied to a high-sulfur natural gas pipeline where the natural gas pressure is approximately 30 MPa and the temperature is 50°C, with a hydrogen sulfide content of approximately 15% (volume fraction). The assessment objective is to simulate the risk of sulfur precipitation in the pipeline under operating conditions of 25°C and 5 MPa.

[0046] The specific steps are as follows: S1. Initial state preparation: Ensure that the natural gas compressor 1, temperature control system 3, dosing pump 4, and ultraviolet spectrophotometer 6 are in the off state, all automatic valves from the first to the seventh are closed, and the volume of the variable volume gas tank 2 is adjusted to the minimum (50mL).

[0047] S2. Sample Gas Collection and Sealing: The first automatic valve 11, the second automatic valve 12, and the third automatic valve 13 are opened sequentially, and then the natural gas compressor 1 is started. The computer 8 controls the piston movement of the variable-volume gas tank 2, expanding its volume to 200 mL, thereby introducing and filling the variable-volume gas tank 2 with the natural gas sample from the pipeline. Subsequently, the third automatic valve 13, the second automatic valve 12, and the first automatic valve 11 are closed sequentially, and the natural gas compressor 1 is shut down. At this point, 200 mL of natural gas sample is sealed within the variable-volume gas tank 2.

[0048] S3. Operating Condition Simulation and Elemental Sulfur Precipitation: The temperature control system 3 is activated and set to 25°C to cool the variable-volume gas tank 2 until the temperature sensor 10 reading stabilizes at 25°C. Then, the piston of the variable-volume gas tank 2 is controlled by the computer 8 to slowly expand its volume from 200 mL to 1200 mL. This isothermal expansion process causes the pressure inside the tank to gradually decrease from the initial high pressure (approximately 30 MPa). Finally, when the pressure sensor 9 reading stabilizes at 5 MPa and the temperature stabilizes at 25°C, the volume adjustment is stopped and maintained for 5 minutes, causing elemental sulfur dissolved in the natural gas to precipitate in solid form under this simulated operating condition.

[0049] S4. Solvent Injection and Sulfur Dissolution: While maintaining a pressure of 5 MPa within the variable-volume gas tank 2, open the fourth automatic valve 14 and the fifth automatic valve 15, and start the dosing pump 4. Pump the carbon disulfide solvent from the dosing tank 7 into the variable-volume gas tank 2 at a constant flow rate, injecting a total volume of 100 mL. Simultaneously with solvent injection, the volume of the variable-volume gas tank 2 is adjusted in real-time by the computer 8 (increasing slowly) to precisely counteract the compression of the gas phase space caused by the liquid entry, thereby ensuring that the pressure inside the tank remains stable at 5 MPa. After injection is complete, close the fifth automatic valve 15, the fourth automatic valve 14, and the dosing pump 4, allowing the solvent to fully contact and dissolve the precipitated solid sulfur.

[0050] S5. Transfer of sulfur-containing solution: Open the sixth automatic valve 16 and the seventh automatic valve 17. Under the control of the computer 8, the volume of the variable-volume gas box 2 is slowly reduced, and the carbon disulfide solution containing sulfur is smoothly injected into and fills the transparent glass tube 5.

[0051] S6. Optical Detection and Data Processing: Start the ultraviolet spectrophotometer 6 and detect the sulfur-containing solution flowing through the transparent glass tube 5. Measure its absorbance at a wavelength of 260 nm. Computer 8 retrieves the pre-stored sulfur concentration-absorbance standard curve and, based on the absorbance... Calculate the concentration of sulfur in the solution. The unit is milligrams per liter (mg / L).

[0052] Based on the known initial volume of the sample gas Injected solvent volume and the measured sulfur concentration Computer 8 first calculates the total mass of dissolved sulfur. : ; in, The unit is milligrams per liter (mg / L) ), The unit is liter ( ), Conversion factor from milligram to kilogram ( ).this This is equivalent to the total mass of solid sulfur that precipitates from 200 mL of sample gas. Therefore, the mass of sulfur precipitated per unit volume of sample gas under the simulated operating conditions (5 MPa, 25℃) can be calculated, i.e., the sulfur precipitation concentration. : ; in, The unit is cubic meters ( ).

[0053] S7. Risk Assessment and System Reset: Computer 8 further retrieves a pre-stored sulfur solubility-pressure-temperature relationship diagram for the natural gas components in this pipeline. The calculated actual sulfur precipitation amount... The corresponding operating conditions (5 MPa, 25℃) and the relationship diagram were compared and analyzed to determine whether the operating point was in the supersaturated risk area for large-scale sulfur precipitation. After the assessment was completed, the computer 8 controlled the variable volume gas box 2 to restore its volume to the minimum, and closed the sixth automatic valve 16 and the seventh automatic valve 17. The device was then reset and prepared for the next test.

[0054] Example 2: This example expands the functionality and integrates the system based on the device for assessing sulfur deposition risk in pipelines of high-sulfur gas fields described in Example 1. It aims to solve the technical challenges in assessing sulfur deposition risk in pipelines, from "discrete point measurement" to "continuous full-domain assessment" and from "hysteresis analysis" to "real-time early warning".

[0055] In practical use, when the length is Along the main gas pipeline, every... Deploy a temperature-pressure integrated monitoring point, totaling The monitoring points form a distributed temperature sensor array and a distributed pressure sensor array.

[0056] The temperature sensor at each monitoring point has a measurement accuracy of [missing information]. The pressure sensor has a measurement accuracy of .

[0057] All monitoring points communicate with Computer 8 via Industrial Ethernet, with a data update frequency of [missing information]. The computer 8 is additionally equipped with a high-performance graphics processing unit for training and high-speed inference calculations of the physical information neural network model.

[0058] The model construction and training methods are as follows: The pipeline sulfur deposition risk mapping model is a machine learning model based on a physical information neural network. Its construction and training include the following specific steps: Step S31: Model building.

[0059] Build a fully connected deep neural network The parameter set is denoted as .

[0060] Normalize the input features: relative position along the path Normalized temperature ,in , The upper and lower limits of the possible operating temperature range of the pipeline, for example and Normalization pressure ,in , For example, the upper and lower limits of the pressure range. and Normalized hydrogen sulfide mole fraction ,in For design upper limits, for example (i.e., 30%); normalized flow rate ,in Design the flow velocity for the pipeline. The input vector is... Neural networks It contains multiple hidden layers (e.g., 5 layers), each containing a number of neurons (e.g., 128 neurons), and the hyperbolic tangent function is used as the activation function for the hidden layers. The output layer contains two neurons, each outputting the sulfur supersaturation level. and comprehensive sedimentation risk index .in, ; This represents the actual sulfur concentration. To balance solubility; for arrive The dimensionless number between these values ​​indicates that the higher the deposition risk, the greater the value.

[0061] Step S32: Physical constraint embedding.

[0062] In neural networks During training, the following physical constraints are embedded through the loss function: (1) Thermodynamic constraint: Equilibrium solubility of sulfur in natural gas Described using Chrastil form equations: ; in, This indicates the equilibrium solubility of sulfur, expressed in kilograms per cubic meter (kg / m³). ); This indicates the density of natural gas, expressed in kilograms per cubic meter (kilograms per cubic meter). ), based on the current temperature (Unit: degrees Celsius) ),pressure (Unit: megapascal) The composition of the gas was calculated using the AGA8 equation of state. , , These are empirical constants related to the gas composition, which can be obtained by fitting experimental data. This constraint encourages neural network predictions of supersaturation. Variations are within a physically reasonable range.

[0063] (2) Flow and heat transfer constraints: A simplified one-dimensional steady-state pipe flow equation is used to describe the pressure and temperature variation along the pipe: ; in, represents the Darcy coefficient, which is a dimensionless number; This indicates the gas flow rate, measured in meters per second (m / s). ); This indicates the inner diameter of the pipe, in meters (m). ), which are known parameters for pipeline design; This represents the overall heat transfer coefficient, expressed in watts per square meter per Kelvin (W / m²). The value can be calculated or estimated based on the pipe insulation material and environmental conditions. This indicates the ambient temperature, expressed in degrees Celsius. (This can be obtained from ambient temperature sensors along the route or by using meteorological data;) This indicates mass flow rate, measured in kilograms per second (kg / s). The value can be calculated based on the inlet flow meter reading and the gas density. This indicates the specific heat capacity at constant pressure, expressed in joules per kilogram per kelvin (kJ / kg). The values ​​can be obtained from a thermodynamic property database based on the current natural gas composition. This constraint ensures the accuracy of neural network predictions. , along The trend of directional change conforms to basic flow and heat transfer laws. Randomly generated within the computational domain. virtual coordinate points Calculate the sum of squared residuals of the above physical equations at these points to form the physical loss term. .

[0064] Step S33: Data preparation.

[0065] The training data comes from two parts: (1) Measured sulfur precipitation data: Using the apparatus of Example 1, sulfur precipitation data were obtained at different operating stages of the pipeline (corresponding to different mainstream gas chemistry). ) and under different flow conditions, targeting Group different temperatures ,pressure Flow rate Operating conditions were combined, and sulfur precipitation was measured to obtain... Following the method described in step S6 of Example 1, the actual sulfur concentration of natural gas under each operating condition is calculated. (unit: ).

[0066] Then, combine this with the equilibrium solubility estimated from the initial parameters under the corresponding operating conditions. The measured oversaturation label was obtained. .

[0067] (2) Historical risk label data: Collect historical data on this pipeline or similar pipelines. The internal inspection or cleaning report, based on the severity and location of the sediment, is quantified into a risk index label by expert experience. Values ​​are taken from the set These represent no risk, low risk, medium risk, and high risk, respectively.

[0068] By merging the two sets of data, the total is: training sample set ,in , .

[0069] Step S34: Model Training. Define the total loss function: ; Among them, data loss Calculate neural network predictions Mean squared error between the label and the target label. The hyperparameters used to balance the physical loss weights, and to balance the data fitting with the constraints of physical laws, can be determined through cross-validation methods, for example... Using the Adam optimizer, set the initial learning rate to... The batch size is 32, and the neural network is trained iteratively multiple times (e.g., 50,000 times) until the loss function converges. After training, the optimal parameters are saved. A well-trained pipeline sulfur deposition risk mapping model was obtained. .

[0070] Step S35: Real-time mapping and early warning.

[0071] The computer reads data from all distributed sensors synchronously once per second, and obtains the data along the path through linear interpolation. points and The flow velocity distribution along the pipe is calculated by combining real-time flow meter data with a pipe model. Obtain the current mainstream hydrogen sulfide mole fraction output by the pipeline gas chromatography-mass spectrometry analyzer. The normalized feature vector at each interpolation point enter ,exist The entire line is obtained through internal parallelism. and distributed.

[0072] The computer monitor displays a color-mapped pipeline risk diagram, for example, using red to represent... High-risk areas, represented by yellow. The medium-risk segment, represented by green. The low-risk section. When a section of pipeline is continuous When a second is deemed high-risk, the system triggers a level one audible and visual alarm.

[0073] Step S36: Online model update.

[0074] The device of Example 1 is used regularly every month, in the current The highest predicted value Field measurements were conducted at each location to obtain new measured supersaturation levels. If the absolute error between the measured supersaturation and the model prediction is... The absolute error is greater than a preset threshold (e.g.) ), then the new data point Add to the training dataset with a small learning rate (e.g., the initial learning rate of 1 / 3). )right conduct Incremental training enables online fine-tuning of model parameters and continuous performance optimization.

[0075] This embodiment works in conjunction with the basic device described in Embodiment 1, resulting in the following significant improvements: By expanding risk assessment from discrete "points" to continuous "lines" and "surfaces," an intuitive full-pipeline risk heat map is generated, achieving a leap from "local diagnosis" to "global situational awareness." This solves the core pain point that traditional point measurement methods cannot locate the highest-risk pipe sections along the entire pipeline.

[0076] This embodiment assesses a fundamental improvement in reliability. The physical information neural network integrates first-principles physical laws with multi-source empirical measurement data (operating conditions, gas quality, flow velocity), making the model's predictions physically plausible even in data-sparse regions (such as pipe sections not directly measured), significantly improving the confidence of extrapolated predictions. Measured data shows that the high-risk pipe sections identified by this method ( The spatial overlap between the actual cleaning and the medium-to-heavy sedimentary sections found reached over 88%, which is a significant improvement over the traditional pure numerical simulation method (average overlap of about 65%).

[0077] This embodiment revolutionizes the timeliness of early warnings, with a trained model exhibiting extremely fast inference speeds, supporting online risk monitoring with second-level updates. Based on a dynamic risk map, this method can provide early warnings of localized flow anomalies caused by sulfur deposition on average more than 120 hours in advance, offering ample time for preventative intervention. In contrast, traditional differential pressure monitoring methods typically only issue alerts in the later stages of blockage formation.

[0078] This embodiment uses continuously measured data provided by the basic equipment to update the model online, enabling the system to adapt to time-varying factors such as pipeline aging, gas quality changes, and flow velocity fluctuations. Simultaneously, the model input incorporates features characterizing gas quality and flow state, making it suitable not only for learning historical data from a single pipeline but also for learning from other pipelines with different gas quality and flow states. The potential for pipeline migration applications under various operating conditions constitutes an intelligent core for pipeline integrity management with continuous learning and adaptability.

[0079] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0080] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. It should be noted that any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A device for assessing the risk of sulfur deposition in pipelines of high-sulfur gas fields, comprising a natural gas compressor, a variable-volume gas tank, a temperature control system, a dosing pump, a transparent glass tube, an ultraviolet spectrophotometer, a dosing tank, a computer, a pressure sensor, a temperature sensor, and multiple automatic valves, characterized in that: The natural gas compressor is connected to the main gas transmission line via a first automatic valve; The variable-volume gas tank is connected to the natural gas compressor via a second automatic valve and is housed within the temperature control system. The variable-volume gas tank contains the pressure sensor and temperature sensor, and is connected to the main gas pipeline via a third automatic valve, the dosing pump via a fourth automatic valve, and the transparent glass tube via a sixth automatic valve. The dosing pump is connected to the dosing tank via a fifth automatic valve. A portion of the transparent glass tube passes through the detection optical path of the ultraviolet spectrophotometer and is connected to the external pipeline via a seventh automatic valve. The computer is communicatively connected to the natural gas compressor, the volume adjustment mechanism of the variable volume gas tank, the temperature control system, the dosing pump, the ultraviolet spectrophotometer, the pressure sensor, the temperature sensor, and each of the automatic valves, for controlling actions and receiving and processing detection data; The computer has a pre-stored standard curve database, including a standard curve of sulfur concentration-absorbance in carbon disulfide, and curves showing the relationship between sulfur solubility in natural gas of specific components and temperature and pressure. The entire evaluation process, including sample gas acquisition, operating condition simulation, solvent injection, solution transfer, optical detection, and data analysis, is automatically controlled and executed by the computer according to program instructions. It also includes a distributed temperature sensor array, deployed at multiple monitoring points along the main gas pipeline, for real-time measurement of temperature distribution along the pipeline; and a distributed pressure sensor array, deployed at multiple monitoring points along the main gas pipeline, for real-time measurement of pressure distribution along the pipeline. The computer is communicatively connected to the distributed temperature sensor array and the distributed pressure sensor array, and the computer has a pre-stored pipeline sulfur deposition risk mapping model based on a physical information neural network. The pipeline sulfur deposition risk mapping model takes pipeline coordinates, real-time temperature, real-time pressure, the mainstream hydrogen sulfide mole fraction in natural gas, and local flow velocity calculated from real-time flow data as inputs, and outputs sulfur supersaturation distribution and comprehensive deposition risk index distribution.

2. The apparatus for assessing the risk of sulfur deposition in pipelines of high-sulfur gas fields according to claim 1, characterized in that, The variable-volume gas box is made of a corrosion-resistant nickel-based alloy, and its volume adjustment range is 50mL to 1200mL.

3. The apparatus for assessing the risk of sulfur deposition in pipelines of high-sulfur gas fields according to claim 1, characterized in that, The detection wavelength of the ultraviolet spectrophotometer is from 250 nm to 270 nm.

4. The apparatus for assessing the risk of sulfur deposition in pipelines of high-sulfur gas fields according to claim 1, characterized in that, The transparent glass tube is a pressure-resistant acrylic tube with a length-to-inner diameter ratio of 5:1 to 10:

1.

5. A method for assessing the risk of sulfur deposition in pipelines of high-sulfur gas fields using the apparatus described in any one of claims 1 to 4, characterized in that, Includes the following steps: Sample gas collection and sealing steps: Open the first automatic valve, the second automatic valve and the third automatic valve, start the natural gas compressor, pump the natural gas sample gas in the gas transmission pipeline into and fill the variable volume gas box to the initial volume, and then close the relevant valves and the compressor to seal the sample gas of the set volume in the box; Operating condition simulation and sulfur precipitation steps: The temperature of the sample gas in the variable volume gas box is adjusted and stabilized to the target temperature by the temperature control system. At the same time, the internal pressure of the variable volume gas box is changed to the target pressure by adjusting the volume of the variable volume gas box, and maintained at the target temperature and pressure for a period of time, so that the elemental sulfur dissolved in the sample gas precipitates into solid sulfur. Solvent injection and sulfur dissolution steps: Open the fourth and fifth automatic valves, start the dosing pump, and inject a metered amount of solvent from the dosing tank into the variable volume gas tank to dissolve the solid sulfur that has been released, forming a sulfur-containing solution; Solution transfer step: Open the sixth and seventh automatic valves, and by changing the volume of the variable volume gas box, pressurize the sulfur-containing solution into and fill the transparent glass tube; Optical detection steps: Start the ultraviolet spectrophotometer and detect the absorbance of the sulfur-containing solution flowing through the transparent glass tube; Data processing and risk assessment steps: The computer calculates the sulfur concentration in the sulfur-containing solution based on the absorbance and the pre-stored absorbance-sulfur concentration relationship; then, based on the initial volume of the sample gas, the injected volume of the solvent, and the sulfur concentration, it calculates the total amount of solid sulfur precipitated from the sample gas under the target temperature and pressure conditions; by comparing the total amount of solid sulfur precipitated with the pre-stored sulfur solubility-temperature-pressure relationship for the gas composition of the pipeline, the sulfur deposition risk of the pipeline at the corresponding operating point is assessed.

6. The method according to claim 5, characterized in that, During the solvent injection and sulfur dissolution steps, the volume of the variable-volume gas box is adjusted simultaneously with the solvent injection to maintain its internal pressure at a substantially constant level.

7. The method according to claim 5, characterized in that, The solvent is carbon disulfide.

8. The method according to claim 5, characterized in that, The target temperature is adjusted by controlling the temperature at 25°C through the temperature control system.

9. The method according to claim 5, characterized in that, In the data processing and risk assessment steps, the computer pre-stores a graph showing the relationship between the solubility of sulfur in hydrogen sulfide-containing natural gas and pressure. This graph is used to determine, based on the measured amount of sulfur precipitation, areas in the pipeline below a specific pressure as high-risk locations for sulfur deposition.

10. The method according to claim 5, characterized in that, The method is a continuous automated cyclic process. After one risk assessment process is completed, the variable volume air box and transparent glass tube are reset, and the next test can be started.

Images