A salt cavern gas storage safety monitoring method and system based on optical fiber sensing technology

Abstract

The present application relates to the technical field of salt cavern gas storage safety monitoring, and particularly relates to a salt cavern gas storage safety monitoring method and system based on optical fiber sensing technology. The method comprises the following steps: laying multiple optical fiber sensing networks, obtaining monitoring data of the salt cavern gas storage during operation through the optical fiber sensing networks; introducing a particle swarm algorithm to construct an optimal parameter screening model, determining hyperparameters of a time-frequency analysis algorithm based on the monitoring data and using the optimal parameter screening model; reconstructing the monitoring data through the time-frequency analysis algorithm to obtain reconstructed monitoring data, and analyzing monitoring indexes according to the reconstructed monitoring data; establishing a salt cavern gas storage safety operation alarm mechanism, and combining the monitoring indexes and the salt cavern gas storage safety operation alarm mechanism to complete the salt cavern gas storage safety monitoring work. The present application uses optical fiber sensing networks to accurately monitor the operation state of the gas storage in real time and comprehensively, and provides reliable protection for the safe operation of the salt cavern gas storage.

Description

Technical Field

[0001] This invention relates to the field of safety monitoring technology for salt cavern gas storage facilities, specifically to a safety monitoring method and system for salt cavern gas storage facilities based on fiber optic sensing technology. Background Technology

[0002] Global energy demand continues to rise, and the surge in fossil fuel consumption has led to massive carbon dioxide emissions. Supercritical carbon dioxide geological sequestration technology, as a method for long-term underground storage of carbon dioxide, is considered a key measure to mitigate carbon dioxide emissions. Salt caverns typically form deep underground salt layers. Having undergone long geological periods, they possess stable structures, and the low permeability of salt rock effectively prevents the leakage of supercritical carbon dioxide. In the supercritical state, carbon dioxide has a density similar to that of a liquid and a viscosity similar to that of a gas, making it highly fluid. Without a stable and well-sealed geological structure, leakage can easily occur. The geological stability of salt caverns allows them to hold supercritical carbon dioxide for extended periods, ensuring safe storage.

[0003] The storage and migration behavior of supercritical carbon dioxide in deep salt cavern gas storage exhibits significant unique characteristics. Its physicochemical properties, such as high diffusivity, phase sensitivity, strong solubility, and interaction with the salt rock-brine system, can profoundly impact the long-term stability, sealing, and safety of the storage facility. Injecting supercritical carbon dioxide into shallow-buried salt cavern gas storage facilities with thin salt layers, numerous interlayers, and low grades intensifies grain boundary slip and dislocation movement under high temperature and high pressure (typically >31.1℃, >7.38MPa), leading to increased creep rates, especially in interlayered salt rocks. This places stringent demands on the safe operation and monitoring of salt cavern gas storage facilities. Traditional monitoring methods, such as pressure monitoring and displacement monitoring, can only obtain localized and limited information, making it difficult to comprehensively and in real-time grasp the overall operational status of the salt cavern gas storage facility. Moreover, the accuracy and reliability of these methods are easily affected when facing complex geological environments. Therefore, there is an urgent need for an efficient, accurate, and comprehensive safety monitoring technology for salt cavern gas storage facilities to ensure their safe and stable operation. Summary of the Invention

[0004] To address the shortcomings of existing methods and the needs of practical applications, this invention aims to promptly detect safety hazards during the storage and operation of supercritical carbon dioxide in deep salt cavern gas storage facilities, and to solve the problem of real-time, comprehensive, and accurate monitoring of the storage facility's operational status, thus providing reliable assurance for the safe operation of salt cavern gas storage facilities. On one hand, this invention provides a safety monitoring method for salt cavern gas storage facilities based on fiber optic sensing technology, comprising the following steps: deploying multiple fiber optic sensor networks to obtain monitoring data during the operation of the salt cavern gas storage facility; introducing a particle swarm optimization algorithm to construct an optimal parameter selection model, and using the monitoring data to determine the hyperparameters of a time-frequency analysis algorithm based on the optimal parameter selection model; reconstructing the monitoring data using the time-frequency analysis algorithm to obtain reconstructed monitoring data, and analyzing monitoring indicators based on the reconstructed monitoring data; establishing a safety operation alarm mechanism for the salt cavern gas storage facility, and combining the monitoring indicators and the safety operation alarm mechanism to complete the safety monitoring work of the salt cavern gas storage facility.

[0005] This invention monitors various indicators of a salt cavern gas storage facility by deploying multiple fiber optic sensor networks. Then, it uses an optimized particle swarm optimization algorithm to quickly and accurately search for the optimal hyperparameters of the time-frequency analysis algorithm, thereby reconstructing the monitoring data to improve data accuracy. This effectively solves the problem of real-time, comprehensive, and accurate monitoring of the operating status of the gas storage facility, providing a reliable guarantee for the safe operation of the salt cavern gas storage facility.

[0006] Optionally, the introduction of particle swarm optimization to construct the optimal parameter selection model includes the following steps:

[0007] Based on the range of hyperparameter values, initial particles are set; an adaptive factor is introduced to improve the inertia coefficient of the particle swarm optimization algorithm; and the velocity update formula of the individual particles is improved based on their fitness values ​​during the iteration process. This invention improves the particle swarm optimization algorithm to construct an optimal parameter selection model, which helps subsequent steps to quickly and efficiently obtain the optimal time-frequency analysis algorithm to accurately reflect the state of the gas storage facility.

[0008] Optionally, setting the initial particles based on the range of hyperparameter values ​​includes the following steps:

[0009] The hyperparameters are normalized; the normalization result is decomposed based on the number of particles, and the initial particles are set according to the decomposition result. This invention normalizes the range of hyperparameter values ​​before decomposing them based on the number of particles, which enables a comprehensive and balanced distribution of initial particles in the solution space, thus improving the accuracy of the invention.

[0010] Optionally, the inertia coefficient of the particle swarm optimization algorithm, which is improved by introducing an adaptive factor, satisfies the following formula:

[0011]

[0012]

[0013] in, This represents the improved coefficient of inertia. This represents the adaptive factor of the i-th particle in the t-th iteration. Indicates the coefficient of inertia. Let represent the fitness value of the i-th particle in the t-th iteration. Let represent the fitness value of the optimal particle in the t-th iteration. This represents the fitness value of the best individual particle in the iteration history. This invention dynamically adjusts the inertia coefficient based on the particle's fitness value, which is beneficial for performing optimization iterations for each particle, thereby improving the efficiency of this invention.

[0014] Optionally, the velocity update formula for the individual particle is improved based on its fitness value during the iteration process, satisfying the following formula:

[0015]

[0016] in, This represents the velocity of the i-th particle in the (t+1)-th iteration. This represents the adaptive factor of the i-th particle in the t-th iteration. This represents the velocity of the i-th particle in the t-th iteration. Let represent the fitness value of the i-th particle in the t-th iteration. Let represent the fitness value of the optimal particle in the t-th iteration. This represents the fitness value of the best individual particle in the iteration history. This represents the position of the i-th particle in the t-th iteration. This represents the position of the best individual particle in the iteration history. This represents the position of the optimal particle at the t-th iteration. This invention uses an adaptive factor as a weighting factor for velocity, and then adaptively adjusts the movement vector based on the particle's fitness relative to the global and historical optimal particles, further improving the accuracy of this invention.

[0017] Optionally, determining the hyperparameters of the time-frequency analysis algorithm based on the monitoring data and using the optimal parameter screening model includes the following steps:

[0018] The optimal parameter selection model is determined to be stuck in an optimization deadlock; a swarm perturbation model is introduced, and the particle swarm is perturbed using the swarm perturbation model based on the determination result.

[0019] Optionally, the group perturbation model satisfies the following formula:

[0020]

[0021] in, This represents the position of the i-th particle after the perturbation. This represents the position of the i-th particle. This represents the coefficient of the Archimedes spiral. Represents a random number in the range [0,1]. This represents the fitness value of the i-th particle. This represents the fitness value of the best individual particle in the iteration history. Indicates the threshold for judgment. This represents the fitness value of the worst-performing particle. This indicates the position of the worst-performing particle. This invention distinguishes between particles far from and near the optimal particle, and then applies different perturbation strategies, which is beneficial for solving local optima problems.

[0022] Optionally, the time-frequency analysis algorithm includes one of an ensemble empirical mode decomposition algorithm, an empirical mode decomposition algorithm, or a variational mode decomposition algorithm. This invention employs multiple time-frequency analysis methods, which further improves the accuracy of the invention.

[0023] Optionally, the step of analyzing monitoring indicators based on the reconstructed monitoring data includes the following steps:

[0024] The gas storage chamber shrinkage rate is obtained through inversion analysis based on the reconstructed monitoring data; the height of the gas-halogen interface is located using temperature gradients and Raman scattering abrupt change points based on the reconstructed monitoring data; and the carbon dioxide phase is identified through the reconstructed monitoring data. This invention obtains multiple monitoring indicators through the analysis of reconstructed monitoring data, effectively improving the comprehensiveness of the monitoring capabilities of this invention.

[0025] Secondly, to efficiently execute the safety monitoring method for salt cavern gas storage based on fiber optic sensing technology provided by this invention, this invention also provides a safety monitoring system for salt cavern gas storage based on fiber optic sensing technology, including a processor, an input device, an output device, and a memory. The processor, input device, output device, and memory are interconnected. The memory stores a computer program containing program instructions. The processor is configured to call the program instructions to execute the safety monitoring method for salt cavern gas storage based on fiber optic sensing technology as described in the first aspect of this invention. The safety monitoring system for salt cavern gas storage based on fiber optic sensing technology of this invention has a compact structure and stable performance, and can stably execute the safety monitoring method for salt cavern gas storage based on fiber optic sensing technology provided by this invention, further improving the overall applicability and practical application capability of this invention. Attached Figure Description

[0026] Figure 1A flowchart illustrating a safety monitoring method for salt cavern gas storage based on fiber optic sensing technology, provided in an embodiment of the present invention;

[0027] Figure 2 This is a framework diagram of a safety monitoring system for a salt cavern gas storage facility based on fiber optic sensing technology, provided as an embodiment of the present invention. Detailed Implementation

[0028] Specific embodiments of the present invention will now be described in detail. It should be noted that the embodiments described herein are for illustrative purposes only and are not intended to limit the invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be apparent to those skilled in the art that these specific details are not necessary to practice the invention. In other instances, well-known circuits, software, or methods have not been specifically described to avoid obscuring the invention.

[0029] Throughout this specification, references to "an embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with that embodiment or example is included in at least one embodiment of the invention. Therefore, the phrases "in an embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily refer to the same embodiment or example. Furthermore, specific features, structures, or characteristics can be combined in one or more embodiments or examples in any suitable combination and / or sub-combination. Moreover, those skilled in the art will understand that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale.

[0030] Please see Figure 1 To promptly identify potential safety hazards during the storage and operation of supercritical carbon dioxide in deep salt cavern gas storage facilities, and to address the issue of real-time, comprehensive, and accurate monitoring of the storage facility's operational status to provide reliable assurance for its safe operation, this invention provides a safety monitoring method for salt cavern gas storage facilities based on fiber optic sensing technology. Figure 1 As shown, in one embodiment, the method includes the following steps:

[0031] S1. Deploy multiple fiber optic sensor networks to obtain monitoring data during the operation of the salt cavern gas storage facility.

[0032] Supercritical carbon dioxide diffuses into the caprock (such as mudstone), lowering the capillary pressure threshold and creating permeability channels. When supercritical carbon dioxide is injected into salt cavern gas storage facilities, the salt rock experiences intensified grain boundary slip and dislocation movement under high temperature and pressure, leading to an increased creep rate and consequently an increased cavity volume shrinkage rate, potentially causing ground subsidence. Furthermore, long-term shrinkage may reduce the effective volume of the gas storage facility, necessitating frequent adjustments to the injection and production plan.

[0033] Furthermore, the periodic injection and extraction of supercritical carbon dioxide can cause pressure fluctuations within the reservoir, leading to stress redistribution in the salt rock mass and shear stress concentration in the caprock and surrounding rock. This increases the risk of fracture expansion around the salt cavern, potentially forming a network of interconnected fractures and inducing microseismic activity.

[0034] Furthermore, carbon dioxide dissolves in brine to form carbonic acid, which further corrodes the salt rock, accelerates fracture development, and increases the electrochemical corrosion rate of metal casing (such as carbon steel), leading to damage to the wellbore integrity.

[0035] Therefore, based on the operational safety risk assessment requirements of the gas storage facility, a spiral BOTDA optical fiber is laid along the ground surface, and a three-dimensional FBG array is embedded in the inner wall of the cavity. At the same time, DTS-Raman composite optical fibers are vertically suspended, a DAS optical fiber ring network is laid along the fracture zone, and a high-pressure resistant MEMS optical fiber sensor array is deployed in the gas storage facility to monitor indicators such as ground subsidence, cavity deformation, gas-halogen interface, temperature, pressure, and sealing.

[0036] Specifically, the fiber optic sensor network is precisely laid according to the design plan in locations such as the cavity walls, surrounding rock, and key connection points. During the laying process, it is ensured that the fiber optic sensor network is in close contact with the monitored object to guarantee effective signal acquisition.

[0037] It is understandable that a distributed fiber optic sensor network can comprehensively monitor the cavity walls, surrounding rock, and key connection points of a salt cavern gas storage facility, acquiring real-time information on changes in various physical quantities such as temperature, strain, and pressure, and promptly grasping the operational status of the salt cavern gas storage facility. The fiber optic sensor system has a simple structure, long service life, and can meet the long-term safety monitoring needs of salt cavern gas storage facilities, reducing maintenance costs.

[0038] Meanwhile, fiber optic sensing technology boasts extremely high measurement accuracy, enabling precise detection of minute changes in physical quantities. This effectively improves the accuracy of safety monitoring in salt cavern gas storage facilities and reduces the rate of missed detections of potential safety hazards. Furthermore, fiber optic sensors are unaffected by electromagnetic interference and can operate stably in complex underground environments, ensuring the reliability and stability of monitoring signals.

[0039] By setting preset safety thresholds to construct an alarm mechanism for the safe operation of salt cavern gas storage facilities, and analyzing alarm index values ​​based on real-time monitoring data, early warning signals can be issued in a timely and accurate manner, providing operators with sufficient time to take measures and effectively preventing the occurrence of safety accidents.

[0040] Furthermore, a high-performance fiber optic signal acquisition card was selected as the signal acquisition device, and the acquisition frequency was set, preferably 10Hz, to ensure real-time capture of changes in physical quantities during the operation of the salt cavern gas storage facility. Wavelength division multiplexing (WDM) technology was employed to transmit optical signals of different wavelengths in the same optical fiber, improving fiber utilization. During signal transmission, an optical amplifier was placed at regular intervals to enhance signal strength and ensure stable signal transmission.

[0041] S2. Introduce the particle swarm optimization algorithm to construct an optimal parameter screening model. Based on the monitoring data, use the optimal parameter screening model to determine the hyperparameters of the time-frequency analysis algorithm.

[0042] Specifically, the time-frequency analysis algorithm includes one of the following: ensemble empirical mode decomposition algorithm, empirical mode decomposition algorithm, or variational mode decomposition algorithm. By using multiple time-frequency analysis algorithms, various reconstructed monitoring data can be obtained, further improving the accuracy of the data.

[0043] In the embodiments, the hyperparameters of the time-frequency analysis algorithm include the number of decompositions and the penalty factor.

[0044] An appropriate number of decompositions allows for the accurate decomposition of fiber optic sensing monitoring signals from salt cavern gas storage facilities into a corresponding number of intrinsic mode function (IMF) components, based on the actual physical processes and characteristics. For example, if the number of decompositions is too small, complex signal characteristics cannot be fully analyzed, potentially missing crucial information such as minute cavity deformations and localized temperature anomalies. Conversely, too many decompositions introduce redundant components, interfering with the assessment of the true state. The optimal number of decompositions ensures that each IMF component carries unique and valuable information about the gas storage facility's operational status, such as stress changes in specific locations and temperature field alterations caused by gas leaks, providing a reliable foundation for subsequent analysis.

[0045] The penalty factor controls the degree of constraint on the bandwidth of each mode. When the penalty factor is optimal, the resulting IMF components have good characteristics. On the one hand, it balances the frequency distribution between modes, avoiding mode aliasing, i.e., signal components with different physical meanings are incorrectly mixed in a single IMF component. For example, in monitoring salt cavern gas storage facilities, it prevents signal feature confusion caused by cavity deformation and pressure changes, ensuring that each IMF component clearly corresponds to a specific physical change. On the other hand, it ensures the stability of the decomposition results, reduces abnormal decomposition caused by signal fluctuations or noise interference, and ensures that the decomposition results truly reflect the actual operating status of the salt cavern gas storage facility.

[0046] High-quality IMF components are obtained by optimizing the number of decompositions and the penalty factor, which can more accurately extract physical quantity features such as temperature, strain, and pressure. This facilitates accurate judgment of feature changes and reduces false alarms and false negatives. For example, when a certain area of ​​a salt cavern gas storage facility experiences strain changes due to an abnormal increase in pressure, an early warning can be triggered in a timely and accurate manner, providing strong support for ensuring the safe and stable operation of the salt cavern gas storage facility.

[0047] Furthermore, the introduction of the particle swarm optimization algorithm to construct the optimal parameter selection model includes the following steps:

[0048] S21. Set the initial particles according to the range of hyperparameter values.

[0049] First, normalize the hyperparameters.

[0050] The range of the number of decompositions is usually determined based on the specific signal characteristics and analysis requirements, generally between 2 and 10. For fiber optic sensing signals from salt cavern gas storage facilities, the initial range of the number of decompositions can be set to [3, 8]. This is because too few decompositions cannot fully analyze the complex features of the signal, while too many may introduce redundant information.

[0051] The penalty factor typically ranges from 100 to 2000, depending on the noise level and complexity of the signal. For monitoring signals from salt cavern gas storage facilities, if the noise is relatively low, the value is between 200 and 800; if the noise is high, a larger value may be needed to suppress the noise effect, with a range of [200, 1000].

[0052] Normalizing hyperparameters facilitates the unified processing and comparison of different parameters during model training and optimization, improving the stability and convergence speed of the algorithm. Furthermore, limiting the value range to [0,1] helps avoid numerical computation problems caused by excessively large or small parameter values.

[0053] Next, based on the particle number decomposition and normalization results, the initial particles are set according to the decomposition results.

[0054] Particle swarm optimization (PSO) requires setting a swarm size parameter, i.e., the number of particles. A larger number of particles allows for a wider search space coverage, enabling a more comprehensive exploration of the solution space and increasing the likelihood of finding the global optimum. However, this also increases computational cost and time. Conversely, a smaller number of particles results in faster computation, but may lead to premature convergence and getting trapped in local optima. The number of particles is typically determined based on the problem's complexity, the size of the search space, and computational capabilities, generally ranging from 20 to 100.

[0055] Specifically, the normalized hyperparameters are divided equally according to the number of particles, and the combination of all the hyperparameter division points is the initial particle set.

[0056] S22. Introduce an adaptive factor to improve the inertia coefficient of the particle swarm algorithm.

[0057] In this embodiment, the introduced adaptive factor improves the inertia coefficient of the particle swarm optimization algorithm, satisfying the following formula:

[0058]

[0059]

[0060] in, This represents the improved coefficient of inertia. This represents the adaptive factor of the i-th particle in the t-th iteration. Indicates the coefficient of inertia. Let represent the fitness value of the i-th particle in the t-th iteration. Let represent the fitness value of the optimal particle in the t-th iteration. This represents the fitness value of the best individual particle in the iteration history.

[0061] In this embodiment, the fitness value of an individual particle refers to the minimum value of the envelope entropy of the IMF component decomposed by the particle-corresponding time-frequency analysis algorithm. Envelope entropy reflects the sparsity of the signal; the less noise contained in the IMF component, the smaller the envelope entropy value will be.

[0062] S23. Based on the fitness value of the individual particle during the iteration process, improve the velocity update formula of the individual particle.

[0063] Specifically, the improved velocity update formula for a particle, based on its fitness value during the iteration process, satisfies the following formula:

[0064]

[0065] in, This represents the velocity of the i-th particle in the (t+1)-th iteration. This represents the adaptive factor of the i-th particle in the t-th iteration. This represents the velocity of the i-th particle in the t-th iteration. Let represent the fitness value of the i-th particle in the t-th iteration. Let represent the fitness value of the optimal particle in the t-th iteration. This represents the fitness value of the best individual particle in the iteration history. This represents the position of the i-th particle in the t-th iteration. This represents the position of the best individual particle in the iteration history. This represents the position of the optimal particle in the t-th iteration.

[0066] Furthermore, the step of determining the hyperparameters of the time-frequency analysis algorithm based on the monitoring data and using the optimal parameter screening model includes the following steps:

[0067] S24. Determine that the optimal parameter screening model has fallen into an optimization deadlock.

[0068] Specifically, a threshold A is set for the number of consecutive iterations. If the global optimal solution is not updated or the change in the objective function value is less than a preset minimum value in A consecutive iterations, the algorithm is considered to be stuck in an optimization deadlock. In other embodiments, this can also be determined by statistical diversity indicators, analyzing particle states, and observing iteration curves.

[0069] S25. Introduce a swarm perturbation model and use the swarm perturbation model to perturb the particle swarm based on the judgment results.

[0070] Specifically, the group disturbance model satisfies the following formula:

[0071]

[0072] in, This represents the position of the i-th particle after the perturbation. This represents the position of the i-th particle. This represents the coefficient of the Archimedes spiral. Represents a random number in the range [0,1]. This represents the fitness value of the i-th particle. This represents the fitness value of the best individual particle in the iteration history. Indicates the threshold for judgment. This represents the fitness value of the worst-performing particle. This indicates the position of the worst-performing particle.

[0073] The threshold is used to determine the distance between the current particle and the optimal particle, and its value can be selected based on the range of the fitness function.

[0074] S3. The monitoring data is reconstructed using the time-frequency analysis algorithm to obtain reconstructed monitoring data, and the monitoring indicators are analyzed based on the reconstructed monitoring data.

[0075] Based on a time-frequency analysis algorithm employing optimal hyperparameters, the monitoring data is decomposed in the time domain to obtain K corresponding modal components. Then, according to the relationships between components within different frequency ranges and the differences in characteristics between each modal component and the original signal in the time domain, it is further divided into several sub-frequency bands. The MPE algorithm is used to calculate the MPE of these decomposed modal components, and a specific MPE value is determined for each modal component. If the MPE value of a modal component is not less than a preset value, it is determined to be a noise function; if the MPE value is less than the preset value, it is determined to be a noise-free function. Then, the modal components with MPE values ​​less than the preset value are reconstructed and combined to obtain the reconstructed monitoring data.

[0076] Furthermore, the analysis of monitoring indicators based on the reconstructed monitoring data includes the following steps:

[0077] S31. Obtain the gas storage cavity shrinkage rate based on the inversion analysis of the reconstructed monitoring data.

[0078] In this embodiment, the cavity deformation vector is calculated based on the cavity stress monitoring data, and then the current cavity volume shrinkage threshold is obtained. The volume of the salt cavern gas storage cavity is then periodically detected, and the cavity volume shrinkage rate is calculated in combination with the cavity monitoring data.

[0079] In other embodiments, the change in brine pressure in the cavity can be used to analyze the volume shrinkage deformation of the cavity, and the main creep parameters of the salt layer creep constitutive equation in the gas storage area can be inverted and analyzed to obtain the cavity shrinkage rate.

[0080] S32. Based on the reconstructed monitoring data, the height of the gas-halogen interface is located using the temperature gradient and Raman scattering abrupt change point.

[0081] Specifically, Raman scattered light in the backscattered light of the optical fiber is used as the signal demodulation light, and the temperature parameter is obtained by calculating the ratio of the intensity of Stokes light to that of anti-Stokes light.

[0082] The collected temperature data is processed and analyzed to plot temperature gradient curves. Abrupt changes in the temperature gradient curves are then identified, representing potential locations of the gas-liquid interface. Based on the location of these abrupt changes, and considering downhole geological and fluid distribution characteristics, the precise height of the gas-halogen interface is further determined.

[0083] S33. Identify the carbon dioxide phase using the reconstructed monitoring data.

[0084] Tiny temperature and pressure fluctuations near the critical point of carbon dioxide can lead to abrupt phase changes. Pressure and temperature data are extracted from the reconstructed monitoring data, and the phase state of carbon dioxide is determined based on the pressure and temperature.

[0085] S4. Establish a safety operation alarm mechanism for salt cavern gas storage facilities. Combine the monitoring indicators and the safety operation alarm mechanism for salt cavern gas storage facilities to complete the safety monitoring work of salt cavern gas storage facilities.

[0086] Based on the impact of ground subsidence, cavity deformation, gas-halogen interface, temperature, pressure and sealing on the safe operation of the gas storage facility, an alarm mechanism for the safe operation of the salt cavern gas storage facility and corresponding monitoring index thresholds are designed, and then early warning is issued by monitoring indicators analyzed based on the reconstructed monitoring data.

[0087] In this embodiment, the safety operation alarm mechanism for the salt cavern gas storage facility includes:

[0088] Level 1 (Yellow): Cavity contraction rate > 0.1% / month or pressure fluctuation > 10%;

[0089] Level 2 (Orange): Daily migration of the gas-halogen interface >1m or a sudden increase in the frequency of micro-seismic events;

[0090] Level 3 (Red): The fissure has been penetrated or carbon dioxide is leaking.

[0091] Please see Figure 2 In this embodiment, to efficiently execute the safety monitoring method for salt cavern gas storage based on fiber optic sensing technology provided by this invention, the present invention also provides a safety monitoring system for salt cavern gas storage based on fiber optic sensing technology, comprising: an input device, an output device, a processor, and a memory, wherein the input device, output device, processor, and memory are interconnected, and the memory contains program instructions for the steps of the safety monitoring method for salt cavern gas storage based on fiber optic sensing technology. The safety monitoring system for salt cavern gas storage based on fiber optic sensing technology of this invention has a compact structure and stable performance, and can stably execute the safety monitoring method for salt cavern gas storage based on fiber optic sensing technology of this invention, further enhancing the overall applicability and practical application capability of this invention.

[0092] In embodiments, the processor may be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. Input devices can be used to acquire data information. Output devices can be used to output the results obtained by storing program instructions contained in a computer program in the memory provided by this invention. The memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of the memory may also include non-volatile random access memory.

[0093] In one possible implementation, the memory may include a stored program area and a stored data area. The stored program area may store the operating system and applications required for at least one function; the stored data area may store data created during use. Furthermore, the memory may include read-only memory and random access memory, providing instructions and data to the processor. A portion of the memory may also include NVRAM. The memory stores the operating system and operating instructions, executable modules, or data structures, or subsets thereof, or extended sets thereof. The operating instructions may include various operation instructions for implementing various operations. The operating system may include various system programs for implementing various basic tasks and handling hardware-based tasks.

[0094] The embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described safety monitoring method for salt cavern gas storage based on fiber optic sensing technology.

[0095] The storage medium can include various media that can store program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0096] In summary, this invention monitors various indicators of a salt cavern gas storage facility by deploying multiple fiber optic sensor networks, and then uses an optimized particle swarm optimization algorithm to quickly and accurately search for the optimal hyperparameters of the time-frequency analysis algorithm. This process reconstructs the monitoring data to improve accuracy, effectively solving the problem of real-time, comprehensive, and accurate monitoring of the gas storage facility's operational status and providing reliable assurance for the safe operation of the salt cavern gas storage facility.

[0097] Therefore, this invention effectively overcomes the various shortcomings of the prior art and has high industrial application value.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the present invention.

Claims

1. A safety monitoring method for salt cavern gas storage facilities based on fiber optic sensing technology, characterized in that, The safety monitoring method for salt cavern gas storage based on fiber optic sensing technology includes the following steps: Multiple fiber optic sensor networks are deployed to obtain monitoring data during the operation of the salt cavern gas storage facility. A particle swarm optimization algorithm is introduced to construct an optimal parameter screening model. Based on the monitoring data, the hyperparameters of the time-frequency analysis algorithm are determined using the optimal parameter screening model. The monitoring data is reconstructed using the time-frequency analysis algorithm to obtain reconstructed monitoring data, and monitoring indicators are analyzed based on the reconstructed monitoring data. Establish a safety operation alarm mechanism for salt cavern gas storage facilities, and combine the aforementioned monitoring indicators with the safety operation alarm mechanism for salt cavern gas storage facilities to complete the safety monitoring work of salt cavern gas storage facilities; The analysis of monitoring indicators based on the reconstructed monitoring data includes the following steps: The gas storage cavity shrinkage rate was obtained by inversion analysis based on the reconstructed monitoring data. Based on the reconstructed monitoring data, the height of the gas-halogen interface is located using temperature gradient and Raman scattering abrupt change points. The phase state of carbon dioxide is identified through the reconstructed monitoring data.

2. The safety monitoring method for salt cavern gas storage based on fiber optic sensing technology according to claim 1, characterized in that, The introduction of particle swarm optimization (PSO) algorithm to construct the optimal parameter selection model includes the following steps: Set the initial particles according to the range of hyperparameter values; An adaptive factor is introduced to improve the inertia coefficient of the particle swarm optimization algorithm; Based on the fitness value of an individual particle during the iteration process, the velocity update formula for that individual particle is improved.

3. The safety monitoring method for salt cavern gas storage based on fiber optic sensing technology according to claim 2, characterized in that, The step of setting the initial particles based on the range of hyperparameter values ​​includes the following steps: Normalize the hyperparameters; Based on the particle number decomposition and normalization results, the initial particles are set according to the decomposition results.

4. The safety monitoring method for salt cavern gas storage based on fiber optic sensing technology according to claim 2, characterized in that, The inertia coefficient of the particle swarm optimization algorithm, which is improved by introducing an adaptive factor, satisfies the following formula: in, This represents the improved coefficient of inertia. Indicates the first t During the nth iteration i The adaptive factor of an individual particle. Indicates the coefficient of inertia. Indicates the first t During the nth iteration i The fitness value of an individual particle. Indicates the first t The fitness value of the optimal particle in the next iteration. This represents the fitness value of the best individual particle in the iteration history.

5. The safety monitoring method for salt cavern gas storage based on fiber optic sensing technology according to claim 2, characterized in that, The improved velocity update formula for individual particles, based on their fitness values ​​during the iteration process, satisfies the following formula: in, Indicates the first t At the +1st iteration, the... i The velocity of individual particles, Indicates the first t During the nth iteration i The adaptive factor of an individual particle. Indicates the first t During the nth iteration i The velocity of individual particles, Indicates the first t During the nth iteration i The fitness value of an individual particle. Indicates the first t The fitness value of the optimal particle in the next iteration. This represents the fitness value of the best individual particle in the iteration history. Indicates the first t During the nth iteration i The position of the individual particle. This represents the position of the best individual particle in the iteration history. Indicates the first t The position of the optimal individual particle at the next iteration.

6. The safety monitoring method for salt cavern gas storage based on fiber optic sensing technology according to claim 1, characterized in that, The process of determining the hyperparameters of the time-frequency analysis algorithm based on the monitoring data and using the optimal parameter screening model includes the following steps: The optimal parameter selection model is determined to be stuck in an optimization deadlock. A swarm perturbation model is introduced, and the particle swarm is perturbed using the swarm perturbation model based on the judgment results.

7. The safety monitoring method for salt cavern gas storage based on fiber optic sensing technology according to claim 6, characterized in that, The group disturbance model satisfies the following formula: in, Indicates the number of disturbances after the first disturbance. i The position of the individual particle. Indicates the first i The position of the individual particle. This represents the coefficient of the Archimedes spiral. Represents a random number in the range [0,1]. Indicates the first i The fitness value of an individual particle. This represents the fitness value of the best individual particle in the iteration history. Indicates the threshold for judgment. This represents the fitness value of the worst-performing particle. This indicates the position of the worst-performing particle.

8. The safety monitoring method for salt cavern gas storage based on fiber optic sensing technology according to claim 1, characterized in that, The time-frequency analysis algorithm includes one of the following: ensemble empirical mode decomposition algorithm, empirical mode decomposition algorithm, or variational mode decomposition algorithm.

9. A safety monitoring system for salt cavern gas storage based on fiber optic sensing technology, characterized in that, The safety monitoring system for salt cavern gas storage based on fiber optic sensing technology includes: an input device, an output device, a processor, and a memory. The input device, output device, processor, and memory are interconnected. The memory includes program instructions, which are used to execute the safety monitoring method for salt cavern gas storage based on fiber optic sensing technology according to any one of claims 1-8.

Images