A method for real-time fiber optic monitoring of smart oil and gas wells

Abstract

This invention relates to a method for real-time fiber optic monitoring of intelligent oil and gas wells, specifically in the field of fiber optic monitoring technology. It utilizes fiber optic sensing technology to deploy optical fibers and various sensors to form a network covering oil and gas wells, enabling real-time monitoring of key locations within the wells. Remote data collection and analysis are achieved through fiber optic transmission. Compared to traditional manual data processing, this method utilizes a data monitoring center to analyze and process data parameters in real time, promptly identifying oil and gas well problems and taking appropriate measures. It provides higher sampling frequencies and more accurate data, enabling timely detection of downhole changes and anomalies. It reduces the number of sensors and the complexity of wiring, improving monitoring efficiency and reliability. By achieving long-distance monitoring, it can cover large oil and gas well areas, ensuring the quality and stability of monitoring signals, and promptly detecting anomalies for early warning and fault diagnosis.

Description

Technical Field

[0001] This invention relates to the field of fiber optic monitoring technology, and more specifically, to a method for real-time fiber optic monitoring of intelligent oil and gas wells. Background Technology

[0002] Traditional oil and gas well monitoring methods only install sensors at the wellhead for monitoring, which cannot provide a comprehensive understanding of the downhole conditions, resulting in inaccurate monitoring results and an inability to assess the production capacity and operating status of oil and gas wells. Furthermore, the use of manual operation limits the real-time nature and efficiency of monitoring data, and the manual collection, processing, and analysis can easily lead to data loss and analytical errors.

[0003] By utilizing fiber optic sensing technology to deploy optical fibers and various sensors to form a multi-network coverage of oil and gas wells, real-time monitoring of key locations in oil and gas wells can be achieved. Remote data collection and analysis can be realized through fiber optic transmission. Compared with traditional manual data processing, the data monitoring center can analyze and process data parameters in real time, promptly identify oil and gas well problems and take measures. Summary of the Invention

[0004] This invention addresses the technical problems existing in the prior art by providing a method for real-time monitoring of intelligent oil and gas wells using optical fiber. The method integrates an intelligent sensor network with optical fiber to monitor various key locations of the oil and gas well and the interior of the optical fiber, thereby solving the problems mentioned in the background art.

[0005] The technical solution of this invention to solve the above-mentioned technical problems is as follows: A method for real-time fiber optic monitoring of intelligent oil and gas wells, comprising the following steps:

[0006] 101. Install multiple sensors to form a smart sensor network, which is used to convert oil and gas well parameter information into optical signals. The optical signals are introduced into the sensor network using optical probes, and the optical signals are amplified, filtered and corrected through signal conditioning and amplification circuits.

[0007] 102. Establish a data monitoring center connected to the wellhead terminal, and use fiber optic communication technology to transmit data to the data monitoring center through fiber optic networks and sensor networks. Use wireless communication to realize real-time monitoring, acquisition and remote transmission of various key parameters of oil and gas wells.

[0008] 103. Process and analyze various key parameters of oil and gas wells, extract key monitoring indicators and features, transform the results of feature extraction into actual monitoring indicators, and use supervised learning to identify abnormal situations.

[0009] 104. Determine different levels of parameter indicators and set corresponding thresholds and evaluation criteria. Use the K-means clustering algorithm for classification. When the monitoring indicators reach or exceed the set thresholds, trigger the corresponding level of abnormal alarm mechanism.

[0010] 105. Obtain changes in optical signal transmission delay and reflection loss during optical fiber transmission, preset optical fiber transmission thresholds by using the specific time when the signal data is sent to the device and received, and establish an intelligent optical fiber sensing system to monitor optical fiber loss in real time.

[0011] 106. Real-time storage of monitoring data parameters, persistent storage of data using cloud storage, setting storage time intervals and data volume according to needs, controlling data size and storage cycle, and displaying different monitoring indicators and parameters in the form of charts and curves to intuitively show the status and changing trends of oil and gas wells.

[0012] In a preferred embodiment, in step 101, a smart sensor network is formed by installing multiple sensors, including temperature sensors, pressure sensors, and liquid level sensors, to provide comprehensive downhole environmental information parameters. The sensors collect analog electrical signals, which are converted into digital signals by an analog-to-digital converter. The digital signals are then converted into optical signals by an optical transmitter and transmitted to the sensor network via an optical probe, realizing the application of fiber optic sensing technology. A bandpass filter is installed to retain signals within a specific bandwidth through a specific frequency range. Operational amplifiers are used to increase the signal amplitude, thereby improving signal strength and sensitivity. A linear calibration algorithm is used based on a linear relationship, linearly representing the difference between the input signal and a known reference value, to fit and achieve a data acquisition calibration curve. The specific formula of the linear calibration algorithm is:

[0013] Y corrected =a*X+b

[0014] Where Y corrected X represents the calibration output signal, a represents the input signal, and b represents the calibration coefficients based on historical experimental data.

[0015] In a preferred embodiment, in step 102, a data monitoring center for the wellhead terminal is established using an optical fiber interface. The data monitoring center connects to various sensors, monitoring equipment, and a smart optical fiber communication system to collect data on key parameters of oil and gas wells, production equipment, and pipelines in real time, including temperature, pressure, flow rate, and liquid level. The data is transmitted to the data monitoring center via an optical fiber network and sensor network using optical fiber communication technology. The optical fiber communication technology uses optical fiber as the transmission medium and leverages the high bandwidth, low loss, strong anti-interference ability, and high security of optical fiber for high-speed, long-distance data transmission. Wireless LAN and LoRaWAN wireless communication technologies are used to connect devices and network nodes to a remote gateway, enabling real-time monitoring, acquisition, and remote transmission of various key parameters of the oil and gas well.

[0016] In a preferred embodiment, step 103 involves determining the variation range of multiple parameters and any existing anomalies, using correlation covariance analysis to analyze the relationship between different parameters, checking for correlations between abnormal parameters, and using the absolute value of the covariance to determine the closeness of the relationship between the parameter variables. The covariance measures the overall trend of change in different parameter variables, and its specific formula is as follows:

[0017]

[0018] Where COV(x,y) represents the absolute value of the covariance, x i y i This represents the i-th observation of different variables with the same parameters. This represents the sample mean of different variables with the same parameter, where n represents the total number of observations. Positive covariance indicates that the parameter variables have similar trends, while negative covariance indicates that the parameter variables have opposite trends. Utilizing the characteristics of a signal composed of multiple frequency sine waves, the frequency domain is transformed through Fourier transform to represent the superposition of sine waves of different frequencies. Periodicity, frequency correlation, and abnormal event features are extracted to obtain the energy distribution of different frequency components in the signal. A linear transformation function is established based on historical signal parameter data, and transformation is performed through the linear relationship between the features and monitoring indicator features. The specific formula for the linear transformation function is:

[0019] Y index =c*X c +d

[0020] Where Y index X represents the monitoring indicator. c The feature is represented by c and d, which represent the degree of influence of the feature on the monitoring index and the baseline value of the adjustment transformation function, respectively. The parameter signal is labeled and the training signal dataset is assigned. Supervised learning is used to label normal samples as positive and abnormal samples as negative. Supervised learning is trained through positive and negative sample sets so that it can learn the relationship between the features and labels of normal samples and judge abnormal parameter signal samples.

[0021] In a preferred embodiment, step 104 involves determining different levels of parameter indicators and setting corresponding thresholds and evaluation criteria. A clustering analysis algorithm is then used for classification. When a monitored indicator reaches or exceeds a set threshold, an abnormal alarm mechanism of the corresponding level is triggered. Specifically, this includes the following steps:

[0022] Step 1: Determine the different temperature parameter indicators and set thresholds and evaluation criteria, including temperature fluctuations within ±5℃ as excellent, ±5℃ to ±10℃ as good, ±10℃ to ±20℃ as average, and exceeding ±20℃ as unacceptable. Use the K-means clustering algorithm to randomly select K initial cluster centers, assign samples containing temperature parameters to the nearest cluster center, update the cluster centers, and calculate the average value of each cluster as the new cluster center. Repeat the assignment and update operation until the cluster centers no longer change and the maximum number of iterations is reached. Extract and group the temperature sample parameters in the dataset according to similarity, set good and average temperature fluctuations as normal working ranges, and set unacceptable temperature fluctuations as safe working ranges. When the well temperature exceeds the set normal working range, trigger a general-level abnormal alarm; when the well temperature exceeds the set safe working range, trigger an unacceptable-level abnormal alarm.

[0023] Step 2: Determine the different pressure parameter indices and set thresholds and evaluation criteria, including pressure fluctuations within ±100 psi as excellent, ±100 psi to ±200 psi as good, ±200 psi to ±500 psi as average, and exceeding ±500 psi as unacceptable. Use the K-means clustering algorithm to randomly select K initial cluster centers, assign samples containing pressure parameters to the nearest cluster center, update the cluster centers, and calculate the average value of each cluster as the new cluster center. Repeat the assignment and update operation iteratively until the cluster centers no longer change and the maximum number of iterations is reached. Extract and group the pressure sample parameters in the dataset according to similarity, set good and average pressure fluctuations as normal working ranges, and set unacceptable pressure fluctuations as safe working ranges. When the well pressure exceeds the set normal working range, trigger a general-level abnormal alarm; when the well pressure exceeds the set safe working range, trigger an unacceptable-level abnormal alarm.

[0024] Step 3: Determine the different liquid level parameters and set thresholds and evaluation criteria, including liquid level fluctuations within ±10% as excellent, ±10% to ±20% as good, ±20% to ±50% as average, and exceeding ±50% as unqualified. Use the K-means clustering algorithm to randomly select K initial cluster centers, assign samples containing liquid level parameters to the nearest cluster center, update the cluster centers, and calculate the average value of each cluster as the new cluster center. Repeat the iterative assignment and update operation until the cluster centers no longer change and the maximum number of iterations is reached. Extract and group the liquid level sample parameters in the dataset according to similarity, set good and average liquid level fluctuations as normal working ranges, and set unqualified liquid level fluctuations as safe working ranges. When the liquid level in the well exceeds the set normal working range, a general-level abnormal alarm is triggered; when the liquid level in the well exceeds the set safe working range, an unqualified-level abnormal alarm is triggered.

[0025] Furthermore, the specific formula for updating the cluster centers in the K-means clustering algorithm is as follows:

[0026]

[0027] Where μ represents the i-th cluster center, x i Let N represent the feature values ​​of all samples in the i-th cluster, and let N represent the number of samples in the i-th cluster.

[0028] In a preferred embodiment, in step 105, the specific time when the signal data is sent to the device and received is used as the standard for judging the fiber optic transmission delay. The timestamps of the transmitted and received signals are recorded, and the time difference between the sending and receiving ends is calculated. The specific formula for this calculation is as follows:

[0029] ΔT=T1-T2

[0030] Where ΔT represents the time difference between the transmitter and receiver, T1 represents the timestamp of the transmitted signal, and T2 represents the timestamp of the received signal. The propagation time of the signal during optical fiber transmission is obtained. A preset threshold for the time from the transmitter to the receiver under normal conditions is used for comparison to determine the degree of optical signal transmission delay. The optical signal is transmitted through the downhole transmitter, and the returned reflected signal is received and analyzed. The reflection point in the optical fiber is determined by the reflection path. Spectral analysis provides information on the optical signal power spectral density, center wavelength, and bandwidth to determine the optical signal transmission quality and loss changes. The center wavelength of the optical signal is the main frequency of the optical signal and is used to monitor for losses and other interferences during transmission. Its specific formula is:

[0031]

[0032] Where λc represents the center wavelength, c represents the speed of light, and f represents the frequency of the optical signal, an intelligent optical fiber sensing system is established by integrating the changes in optical signal transmission delay and reflection loss during optical fiber transmission. The system calls upon an intelligent sensing network and combines optical fiber sensors and other sensors to monitor optical fiber transmission loss in real time.

[0033] In a preferred embodiment, step 106 involves real-time storage of detection data parameters, including historical data composed of temperature, pressure, liquid level, and corresponding alarm measures. This data is persistently stored using cloud storage and remotely accessed via a network for real-time monitoring, analysis, and retrieval. The storage time interval is set to every hour, and the amount of data stored is controlled according to requirements. The data size and storage period are controlled, and a storage limit is set for data compression. A line graph is used to display data changes over time, with different monitoring indicators and parameters as the y-axis and time as the x-axis, showing the data trend. A scatter plot is used to show the relationships between different indicators, with different indicators as the x-axis and y-axis, each data point representing a monitoring point in time. The correlation between indicators is observed through the distribution of scatter points. A heat map is used to show the spatial distribution changes of different indicators. Monitoring data from different locations are mapped onto a map or plan view, with color depth indicating data size. An abnormal alarm mechanism is invoked, presenting the corresponding level of abnormal alarms on a visualization terminal, intuitively displaying the status, trends, and anomaly repair suggestions of the oil and gas well.

[0034] The beneficial effects of this invention are: This invention utilizes fiber optic sensing technology to monitor various parameters of oil and gas wells in real time, providing higher sampling frequency and more accurate data, enabling timely capture of changes and anomalies downhole, reducing the number of sensors and the complexity of wiring, improving monitoring efficiency and reliability, achieving long-distance monitoring to cover a large oil and gas well area, ensuring the quality and stability of monitoring signals, timely detection of anomalies and early warning and fault diagnosis. Attached Figure Description

[0035] Figure 1 This is a system flowchart of the present invention. Detailed Implementation

[0036] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0037] In the description of this application, 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 indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0038] In the description of this application, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0039] Example 1

[0040] This embodiment provides, for example Figure 1 The method for real-time fiber optic monitoring of intelligent oil and gas wells, as shown, specifically includes the following steps:

[0041] 101. Install multiple sensors to form a smart sensor network, which is used to convert oil and gas well parameter information into optical signals. The optical signals are introduced into the sensor network using optical probes, and the optical signals are amplified, filtered and corrected through signal conditioning and amplification circuits.

[0042] Furthermore, a smart sensor network is constructed by installing multiple sensors, including temperature sensors, pressure sensors, and liquid level sensors, to provide comprehensive downhole environmental information parameters. Analog electrical signals from the sensors are collected and converted into digital signals by an analog-to-digital converter. The digital signals are then converted into optical signals by an optical transmitter and transmitted to the sensor network via an optical probe, realizing the application of fiber optic sensing technology. A bandpass filter is installed to retain signals within a specific bandwidth through a specific frequency range. Operational amplifiers are used to increase the signal amplitude, thereby improving signal strength and sensitivity. A linear calibration algorithm, based on a linear relationship, linearly represents the difference between the input signal and a known reference value, and fits a data acquisition calibration curve. The specific formula of the linear calibration algorithm is as follows:

[0043] Y corrected =a*X+b

[0044] Where Y corrected X represents the calibration output signal, a represents the input signal, and b represents the calibration coefficients based on historical experimental data.

[0045] 102. Establish a data monitoring center connected to the wellhead terminal, and use fiber optic communication technology to transmit data to the data monitoring center through fiber optic network and sensor network. Use wireless communication to realize real-time monitoring, acquisition and remote transmission of various key parameters of oil and gas wells.

[0046] Furthermore, a data monitoring center is established using fiber optic interfaces to connect to the wellhead terminal. This data monitoring center connects to various sensors, monitoring equipment, and a smart fiber optic communication system to collect data on key parameters of oil and gas wells, production equipment, and pipelines in real time, including temperature, pressure, flow rate, and liquid level. The data is transmitted to the data monitoring center via fiber optic networks and sensor networks using fiber optic communication technology. The fiber optic communication technology uses optical fiber as the transmission medium and leverages the high bandwidth, low loss, strong anti-interference ability, and high security of optical fiber for high-speed, long-distance data transmission. Wireless LAN and LoRaWAN wireless communication technologies are used to connect devices and network nodes to a remote gateway, enabling real-time monitoring, acquisition, and remote transmission of various key parameters of oil and gas wells.

[0047] 103. Process and analyze various key parameters of oil and gas wells, extract key monitoring indicators and features, transform the results of feature extraction into actual monitoring indicators, and use threshold detection to identify abnormal situations.

[0048] Furthermore, the range of variation for various parameters and any existing anomalies are determined. Correlation covariance analysis is used to analyze the relationships between different parameters, examining the correlation between abnormal parameters. The absolute value of the covariance is used to determine the degree of closeness of the relationship between the parameter variables. The covariance measures the overall trend of change of different parameter variables, and its specific formula is as follows:

[0049]

[0050] Where COV(x,y) represents the absolute value of the covariance, x i y i This represents the i-th observation of different variables with the same parameters. This represents the sample mean of different variables with the same parameter, where n represents the total number of observations. Positive covariance indicates that the parameter variables have similar trends, while negative covariance indicates that the parameter variables have opposite trends. Utilizing the characteristics of a signal composed of multiple frequency sine waves, the frequency domain is transformed through Fourier transform to represent the superposition of sine waves of different frequencies. Periodicity, frequency correlation, and abnormal event features are extracted to obtain the energy distribution of different frequency components in the signal. A linear transformation function is established based on historical signal parameter data, and transformation is performed through the linear relationship between the features and monitoring indicator features. The specific formula for the linear transformation function is:

[0051] Y index =c*X c +d

[0052] Where Y index X represents the monitoring indicator. cThe feature is represented by c and d, which represent the degree of influence of the feature on the monitoring index and the baseline value of the adjustment transformation function, respectively. The parameter signal is labeled and the training signal dataset is assigned. Supervised learning is used to label normal samples as positive and abnormal samples as negative. Supervised learning is trained through positive and negative sample sets so that it can learn the relationship between the features and labels of normal samples and judge abnormal parameter signal samples.

[0053] 104. Determine different levels of parameter indicators and set corresponding thresholds and evaluation criteria. Use the K-means clustering algorithm for classification. When the monitoring indicators reach or exceed the set thresholds, trigger the corresponding level of abnormal alarm mechanism.

[0054] Furthermore, the specific steps include:

[0055] Step 1: Determine the different temperature parameter indicators and set thresholds and evaluation criteria, including temperature fluctuations within ±5℃ as excellent, ±5℃ to ±10℃ as good, ±10℃ to ±20℃ as average, and exceeding ±20℃ as unacceptable. Use the K-means clustering algorithm to randomly select K initial cluster centers. Assign samples containing temperature parameters to the nearest cluster center, update the cluster centers, and calculate the average value of each cluster as the new cluster center. Repeat the iterative assignment and update operation until the cluster centers no longer change and the maximum number of iterations is reached. The specific formula for updating the cluster centers in the K-means clustering algorithm is as follows:

[0056]

[0057] Where μ represents the i-th temperature cluster center, x i denoted as , where N represents the feature values ​​of all temperature samples in the i-th cluster, and N represents the number of samples in the i-th temperature cluster. The temperature sample parameters in the dataset are extracted and grouped according to similarity. Good and normal temperature fluctuations are set as the normal working range, and unqualified temperature fluctuations are set as the safe working range. When the temperature inside the well exceeds the set normal working range, a normal level abnormal alarm is triggered. When the temperature inside the well exceeds the set safe working range, an unqualified level abnormal alarm is triggered.

[0058] Step 2: Determine the different pressure parameter indices and set thresholds and evaluation criteria, including pressure fluctuations within ±100 psi as excellent, ±100 psi to ±200 psi as good, ±200 psi to ±500 psi as average, and exceeding ±500 psi as unacceptable. Use the K-means clustering algorithm to randomly select K initial cluster centers. Assign samples containing pressure parameters to the nearest cluster center, update the cluster centers, and calculate the average value of each cluster as the new cluster center. Repeat the iterative assignment and update operation until the cluster centers no longer change and the maximum number of iterations is reached. The specific formula for updating the cluster centers using the K-means clustering algorithm is as follows:

[0059]

[0060] Where ω represents the i-th pressure cluster center, y i Let M represent the feature values ​​of all pressure samples in the i-th cluster, and M represent the number of samples in the i-th pressure cluster. The pressure sample parameters in the dataset are extracted and grouped according to similarity. Good and normal pressure fluctuations are set as normal working ranges, and unqualified pressure fluctuations are set as safe working ranges. When the well pressure exceeds the set normal working range, a normal level abnormal alarm is triggered. When the well pressure exceeds the set safe working range, an unqualified level abnormal alarm is triggered.

[0061] Step 3: Determine the different liquid level parameters and set thresholds and evaluation criteria, including: liquid level fluctuation within ±10% is excellent, ±10% to ±20% is good, ±20% to ±50% is average, and exceeding ±50% is unacceptable. Use the K-means clustering algorithm to randomly select K initial cluster centers. Assign samples containing liquid level parameters to the nearest cluster center, update the cluster centers, and calculate the average value of each cluster as the new cluster center. Repeat the iterative assignment and update operation until the cluster centers no longer change and the maximum number of iterations is reached. The specific formula for updating the cluster centers in the K-means clustering algorithm is as follows:

[0062]

[0063] Where λ represents the i-th liquid level cluster center, z i denoted as , where represents the feature value of all liquid level samples in the i-th cluster, and O represents the number of samples in the i-th liquid level cluster. The liquid level sample parameters in the dataset are extracted and grouped according to similarity. Good and normal liquid level fluctuations are set as the normal working range, and unqualified liquid level fluctuations are set as the safe working range. When the liquid level in the well exceeds the set normal working range, a normal level abnormal alarm is triggered. When the liquid level in the well exceeds the set safe working range, an unqualified level abnormal alarm is triggered.

[0064] 105. Obtain changes in optical signal transmission delay and reflection loss during optical fiber transmission, preset optical fiber transmission thresholds by using the specific time when the signal data is sent to the device and received, and establish an intelligent optical fiber sensing system to monitor optical fiber loss in real time.

[0065] Furthermore, the specific time when the signal data is sent to the device and received is used as the standard for judging the fiber optic transmission delay. The timestamps of the transmitted and received signals are recorded, and the time difference between the sending and receiving ends is calculated. The specific formula for this calculation is as follows:

[0066] ΔT=T1-T2

[0067] Where ΔT represents the time difference between the transmitter and receiver, T1 represents the timestamp of the transmitted signal, and T2 represents the timestamp of the received signal. The propagation time of the signal during optical fiber transmission is obtained. A preset threshold for the time from the transmitter to the receiver under normal conditions is used for comparison to determine the degree of optical signal transmission delay. The optical signal is transmitted through the downhole transmitter, and the returned reflected signal is received and analyzed. The reflection point in the optical fiber is determined by the reflection path. Spectral analysis provides information on the optical signal power spectral density, center wavelength, and bandwidth to determine the optical signal transmission quality and loss changes. The center wavelength of the optical signal is the main frequency of the optical signal and is used to monitor for losses and other interferences during transmission. Its specific formula is:

[0068]

[0069] Where λc represents the center wavelength, c represents the speed of light, and f represents the frequency of the optical signal, an intelligent optical fiber sensing system is established by integrating the changes in optical signal transmission delay and reflection loss during optical fiber transmission. The system calls upon an intelligent sensing network and combines optical fiber sensors and other sensors to monitor optical fiber transmission loss in real time.

[0070] 106. Real-time storage of monitoring data parameters, persistent storage of data using cloud storage, setting storage time intervals and data volume according to needs, controlling data size and storage cycle, and displaying different monitoring indicators and parameters in the form of charts and curves to intuitively show the status and changing trends of oil and gas wells;

[0071] Furthermore, real-time storage of detection data parameters, including temperature, pressure, liquid level, and corresponding alarm measures, constitutes historical data. This data is persistently stored using cloud storage and remotely accessed via the network for real-time monitoring, analysis, and retrieval. Storage intervals are set to every hour and the amount of data stored, controlling the data size and storage period. Storage limits are set for data compression. Line charts are used to display data changes over time, with different monitoring indicators and parameters as the y-axis and time as the x-axis, showing data trends. Scatter plots are used to show the relationships between different indicators, using different indicators as the x and y axes, with each data point representing a specific time point. The distribution of scatter points allows observation of the correlation between indicators. Heat maps are used to display the spatial distribution of different indicators, mapping monitoring data from different locations onto a map or plan view, using color intensity to represent data magnitude. An anomaly alarm mechanism is invoked, presenting corresponding levels of anomaly alarms on a visualization terminal, intuitively displaying the status, trends, and anomaly repair suggestions of the oil and gas well.

[0072] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0073] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0074] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0075] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0076] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0077] 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.

[0078] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for real-time fiber optic monitoring of intelligent oil and gas wells, characterized in that, Specifically, the following steps are included:

101. Install multiple sensors to form a smart sensor network, which is used to convert oil and gas well parameter information into optical signals. The optical signals are introduced into the sensor network using optical probes, and the optical signals are amplified, filtered and corrected through signal conditioning and amplification circuits.

102. Establish a data monitoring center connected to the wellhead terminal, and use fiber optic communication technology to transmit data to the data monitoring center through fiber optic network and sensor network. Use wireless communication to realize real-time monitoring, acquisition and remote transmission of various key parameters of oil and gas wells.

103. Process and analyze various key parameters of oil and gas wells, extract key monitoring indicators and features, transform the results of feature extraction into actual monitoring indicators, and use supervised learning to identify abnormal situations.

104. Determine different levels of parameter indicators and set corresponding thresholds and evaluation criteria. Use the K-means clustering algorithm for classification. When the monitoring indicators reach or exceed the set thresholds, trigger the corresponding level of abnormal alarm mechanism.

105. Obtain changes in optical signal transmission delay and reflection loss during optical fiber transmission, preset optical fiber transmission thresholds by using the specific time when the signal data is sent to the device and received, and establish an intelligent optical fiber sensing system to monitor optical fiber loss in real time.

106. Real-time storage of monitoring data parameters, persistent storage of data using cloud storage, setting storage time intervals and data volume according to needs, controlling data size and storage cycle, and displaying different monitoring indicators and parameters in the form of charts and curves to intuitively show the status and changing trends of oil and gas wells.

2. The method for real-time monitoring of intelligent oil and gas wells using optical fiber according to claim 1, characterized in that: In step 101, a smart sensor network and an analog-to-digital converter are used for signal conversion, and a calibration curve is obtained by fitting a linear calibration algorithm. The specific formula of the linear calibration algorithm is as follows: in Indicates the calibration output signal. Indicates the input signal. This represents the calibration coefficient based on historical experimental data.

3. The method for real-time monitoring of intelligent oil and gas wells using optical fiber according to claim 1, characterized in that: In step 102, a data monitoring center for connecting wellhead terminals is established using an optical fiber interface. Various sensors, monitoring devices, and a smart optical fiber communication system are connected through the data monitoring center. Wireless LAN and LoRaWAN wireless communication technologies are used to connect devices and network nodes to a remote gateway, enabling real-time monitoring, acquisition, and remote transmission of various key parameters of oil and gas wells.

4. The method for real-time monitoring of intelligent oil and gas wells using optical fiber according to claim 1, characterized in that: In step 103, the variation range of various parameters and existing anomalies are determined. The relationship between different parameters is analyzed using correlation covariance analysis. A linear transformation function is established based on historical signal parameter data, and transformation is performed through the linear relationship between features and monitoring indicator features. The specific formula for the covariance is: in Represents the absolute value of the covariance. This represents the i-th observation of different variables with the same parameters. This represents the sample mean of different variables with the same parameter. Representing the total number of observations, the specific formula for the linear transformation function is: in Indicates monitoring indicators, Indicates features, These represent the degree of influence of the feature on the monitoring indicator and the benchmark value for adjusting the transformation function, respectively.

5. The method for real-time monitoring of intelligent oil and gas wells using optical fiber according to claim 1, characterized in that: In step 104, the parameter indicators include temperature parameter indicators, pressure parameter indicators, and liquid level parameter indicators. Different levels of temperature, pressure, and liquid level parameter indicators are determined, and corresponding thresholds and evaluation standards are set. K-means clustering algorithm is used for classification. When the monitoring indicators reach or exceed the set thresholds, the corresponding level of abnormal alarm mechanism is triggered.

6. The method for real-time monitoring of intelligent oil and gas wells using optical fiber according to claim 5, characterized in that: The specific formula for updating the cluster centers in the K-means clustering algorithm is as follows: in Let i represent the i-th cluster center. This represents the feature values ​​of all samples in the i-th cluster. This represents the number of samples in the i-th cluster.

7. The method for real-time monitoring of intelligent oil and gas wells using optical fiber according to claim 1, characterized in that: In step 105, an intelligent fiber optic sensing system is established by integrating changes in optical signal transmission delay and reflection loss during the fiber optic transmission process. This system utilizes an intelligent sensor network, combining fiber optic sensors and other sensors to monitor fiber optic transmission loss in real time. The optical signal transmission delay is calculated by determining the time difference between the transmitting and receiving ends, using the following formula: in This represents the time difference between the sending and receiving ends. Indicates the timestamp of the sent signal. This represents the timestamp of the received signal. The optical signal loss uses the center wavelength as a standard, and its specific formula is as follows: in Indicates the center wavelength. Represents the speed of light. This indicates the frequency of the optical signal.

8. The method for real-time monitoring of intelligent oil and gas wells using optical fiber according to claim 1, characterized in that: In the 106, cloud storage is used for persistent data storage, remote access is made through the network, and data can be monitored, analyzed and retrieved in real time. The status, trend and abnormal repair suggestions of oil and gas wells are displayed intuitively through various visualization forms, and the corresponding level of abnormal alarm is presented on the visualization terminal.

Images