Intelligent monitoring system and method for oil and gas recovery based on multiple parameters

Abstract

The present application relates to the field of safety monitoring technology, and more specifically discloses a multi-parameter-based intelligent monitoring system and method for oil and gas recovery, which integrates multiple sensors to monitor parameters such as pressure, flow, gas concentration and liquid level of the oil and gas recovery system, extracts feature vectors and uses classifiers to judge the eligibility of the oil and gas recovery process, so as to realize an efficient intelligent monitoring system for oil and gas recovery.

Description

Technical Field

[0001] The present application relates to the field of safety monitoring technology, and more specifically, to an intelligent monitoring system and method for oil and gas recovery based on multiple parameters. Background Art

[0002] During the loading process, the volatilized oil and gas generated by gasoline products escape to the top of the tank truck and are discharged into the atmosphere. The volatilized oil and gas are flammable and explosive. With high concentration, they form explosive gas with air and are distributed in the upper space of the tank truck and around the tank truck loading exhaust port. It is very easy to explode when encountering open flames, affecting production safety. Therefore, it is necessary to recover the volatilized oil and gas.

[0003] Oil and gas recovery refers to the use of high-tech energy-saving and environmentally friendly technologies to recover oil and gas in various links of oil processing at gas stations to prevent pollution and safety hazards caused by oil and gas volatilization, and to reduce economic losses by improving the utilization rate of oil and gas. In the oil and gas recovery process, it is necessary to determine the technical indicators and safety of the oil and gas recovery system through testing. Among them, the concentration of hydrocarbon components is a common oil and gas recovery standard. When detecting hydrocarbon gases, various related equipment and devices are required, which account for a large part of the cost of the detection system.

[0004] Therefore, a multi-parameter-based intelligent monitoring system and method for oil and gas recovery is desired. Summary of the invention

[0005] In order to solve the above technical problems, this application is proposed. The embodiment of this application provides an intelligent monitoring system and method for oil and gas recovery based on multiple parameters, which monitors the parameters of the oil and gas recovery system by integrating multiple sensors, extracts feature vectors and judges the eligibility of the oil and gas recovery process through a classifier.

[0006] Accordingly, according to one aspect of the present application, a multi-parameter-based intelligent monitoring system for oil and gas recovery is provided, comprising:

[0007] The oil and gas recovery process data acquisition module is used to extract the pressure value, liquid flow value, gas concentration value and liquid level value at multiple predetermined time points including the current time point during the oil and gas recovery process;

[0008] An oil and gas recovery process data processing module, used to extract a pressure characteristic vector, a liquid flow characteristic vector, a gas concentration characteristic vector and a liquid level characteristic vector from the pressure values, liquid flow values, gas concentration values ​​and liquid level values ​​at the plurality of predetermined time points, respectively;

[0009] An oil and gas recovery process data fusion module is used to fuse the pressure feature vector, the liquid flow feature vector, the gas concentration feature vector and the liquid level feature vector to obtain an oil and gas recovery process parameter feature matrix, and perform scattering response depth correlation optimization based on the category difference space on the oil and gas recovery parameter feature matrix to obtain an optimized oil and gas recovery parameter feature matrix;

[0010] The oil and gas recovery process result analysis module is used to pass the optimized oil and gas recovery process parameter feature matrix through a classifier to obtain a classification result, and the classification result is used to indicate whether the oil and gas recovery is qualified.

[0011] According to another aspect of the present application, a multi-parameter-based intelligent monitoring method for oil and gas recovery is provided, which includes:

[0012] Extract the pressure value, liquid flow value, gas concentration value and liquid level value at multiple predetermined time points including the current time point during the oil and gas recovery process;

[0013] Extracting a pressure feature vector, a liquid flow feature vector, a gas concentration feature vector and a liquid level feature vector from the pressure values, liquid flow values, gas concentration values ​​and liquid level values ​​at the plurality of predetermined time points respectively;

[0014] The pressure characteristic vector, the liquid flow characteristic vector, the gas concentration characteristic vector and the liquid level characteristic vector are integrated to obtain an oil and gas recovery process parameter characteristic matrix, and the oil and gas recovery parameter characteristic matrix is ​​optimized based on the scattering response depth correlation of the category difference space to obtain an optimized oil and gas recovery parameter characteristic matrix;

[0015] The optimized oil and gas recovery process parameter feature matrix is ​​passed through a classifier to obtain a classification result, and the classification result is used to indicate whether the oil and gas recovery is qualified.

[0016] Compared with the prior art, the present application provides a multi-parameter-based intelligent oil and gas recovery monitoring system and method, which integrates multiple sensors to monitor parameters such as pressure, flow, gas concentration and liquid level of the oil and gas recovery system, extracts feature vectors and judges the eligibility of the oil and gas recovery process through a classifier, so as to realize an efficient oil and gas recovery intelligent monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0018] Figure 1 It is a block diagram of an intelligent monitoring system for oil and gas recovery based on multiple parameters according to an embodiment of the present application.

[0019] Figure 2 It is a block diagram of an oil and gas recovery process data processing module in a multi-parameter-based oil and gas recovery intelligent monitoring system according to an embodiment of the present application.

[0020] Figure 3 It is a block diagram of a pressure feature extraction unit in a multi-parameter-based intelligent monitoring system for oil and gas recovery according to an embodiment of the present application.

[0021] Figure 4 The present invention is a flowchart of an intelligent oil and gas recovery monitoring method based on multiple parameters according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] Various exemplary embodiments, features and aspects of the present application will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0023] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0024] In addition, in order to better illustrate the present application, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present application can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present application.

[0025] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0026] Figure 1 The figure shows a block diagram of a multi-parameter oil and gas recovery intelligent monitoring system according to an embodiment of the present application. Figure 1As shown, according to the multi-parameter-based intelligent monitoring system 100 for oil and gas recovery of the embodiment of the present application, it includes: an oil and gas recovery process data acquisition module 110, which is used to extract the pressure value, liquid flow value, gas concentration value and liquid level value of multiple predetermined time points including the current time point in the oil and gas recovery process; an oil and gas recovery process data processing module 120, which is used to extract the pressure feature vector, liquid flow feature vector, gas concentration feature vector and liquid level feature vector from the pressure value, liquid flow value, gas concentration value and liquid level value of the multiple predetermined time points respectively; an oil and gas recovery process data fusion module 130, which is used to fuse the pressure feature vector, the liquid flow feature vector, the gas concentration feature vector and the liquid level feature vector to obtain an oil and gas recovery process parameter feature matrix, and perform scattering response depth correlation optimization based on the category difference space on the oil and gas recovery parameter feature matrix to obtain an optimized oil and gas recovery parameter feature matrix; an oil and gas recovery process data analysis module 140, which is used to pass the optimized oil and gas recovery process parameter feature matrix through a classifier to obtain a classification result, and the classification result is used to indicate whether the oil and gas recovery is qualified.

[0027] In an embodiment of the present application, the oil and gas recovery process data acquisition module 110 is used to extract the pressure value, liquid flow value, gas concentration value and liquid level value at multiple predetermined time points including the current time point in the oil and gas recovery process. It should be understood that through the parameter values ​​at multiple time points, the operation of the oil and gas recovery system in different time periods can be dynamically monitored to capture changes and fluctuations in system operation. By comparing the parameter values ​​at different time points, the changing trend of system parameters over time can be analyzed to help predict possible problems or optimize system performance. Monitoring parameter values ​​at multiple time points can help detect abnormal situations, such as sudden pressure fluctuations, abnormal changes in liquid levels, etc., and take timely measures to avoid system failures. Data at multiple time points provides more comprehensive and complete system operation information, which helps to accurately evaluate the status and efficiency of the oil and gas recovery process. Therefore, extracting parameter values ​​at multiple time points can provide more data support and information, which is helpful for system monitoring, analysis and optimization.

[0028] In the embodiment of the present application, the oil and gas recovery process data processing module 120 is used to extract pressure feature vectors, liquid flow feature vectors, gas concentration feature vectors and liquid level feature vectors from the pressure values, liquid flow values, gas concentration values ​​and liquid level values ​​at the plurality of predetermined time points, respectively. It should be understood that the feature vectors of different parameters can capture the important features of the respective parameters, such as the changing trend of pressure, the volatility of liquid flow, the changing amplitude of gas concentration, etc., which helps to better understand the operation of the system. By extracting feature vectors, the dimension of the original data can be reduced, the data processing and analysis process can be simplified, while retaining key information, which helps to improve the calculation efficiency. Extracting the feature vectors of different parameters separately can more clearly show the association and influence between the parameters, and help identify the interaction between the parameters. After the feature vectors of different parameters are extracted separately, they can be used as the input of the classifier, so as to better classify and judge the oil and gas recovery process and improve the accuracy and reliability of the system. Therefore, extracting the feature vectors of different parameters from multiple time points respectively helps to comprehensively and accurately describe the operating status of the oil and gas recovery system, and provide more useful information for system monitoring, analysis and judgment.

[0029] Specifically, in one embodiment of the present application, Figure 2 The figure shows a block diagram of an oil and gas recovery process data processing module in an oil and gas recovery intelligent monitoring system based on multiple parameters according to an embodiment of the present application. Figure 2 As shown, in the above-mentioned multi-parameter-based intelligent monitoring system 100 for oil and gas recovery, the oil and gas recovery process data processing module 120 includes: a pressure feature extraction unit 121, used to extract the pressure feature vector from the pressure values ​​at the multiple predetermined time points; a liquid flow value feature extraction unit 122, used to extract the liquid flow feature vector from the liquid flow values ​​at the multiple predetermined time points; a gas concentration feature extraction unit 123, used to extract the gas concentration feature vector from the gas concentration values ​​at the multiple predetermined time points; and a liquid level feature extraction unit 124, used to extract the liquid level feature vector from the liquid level values ​​at the multiple predetermined time points.

[0030] Specifically, the pressure feature extraction unit 121 is used to extract the pressure feature vector from the pressure values ​​at the multiple predetermined time points. It should be understood that the pressure in the oil and gas recovery process is a key parameter, and its value changes over time. Extracting the pressure values ​​at multiple time points can realize dynamic monitoring of pressure changes and help the system understand the pressure fluctuations in real time. By extracting the pressure feature vector, the pressure change trend can be analyzed, including rising, falling, stable and other situations. This helps to predict possible problems or abnormal situations. Abnormal fluctuations in pressure values ​​may indicate problems with the system, such as leakage, blockage, etc. By extracting the pressure feature vector and performing abnormality detection, the system can promptly discover and handle abnormal situations to ensure the stability and safety of system operation. Extracting the pressure values ​​at multiple time points and generating feature vectors helps to ensure the integrity and accuracy of the data. Such a processing method can avoid the limitations of data at a single time point and improve the comprehensiveness of data analysis. In summary, extracting the pressure feature vector from the pressure values ​​at multiple predetermined time points can help the system comprehensively monitor the pressure situation in the oil and gas recovery process, analyze the data in real time, promptly discover problems and take corresponding measures to ensure the safe and efficient operation of the system.

[0031] further, Figure 3 The figure shows a block diagram of a pressure feature extraction unit in a multi-parameter oil and gas recovery intelligent monitoring system according to an embodiment of the present application. Figure 3 As shown, in the oil and gas recovery process data processing module 120 of the above-mentioned multi-parameter-based oil and gas recovery intelligent monitoring system 100, the pressure feature extraction unit 121 includes: a pressure arrangement vector subunit 1211, which is used to arrange the pressure values ​​of the multiple predetermined time points into a pressure input vector according to the time dimension; a pressure multi-scale extraction subunit 1212, which is used to obtain the pressure feature vector by passing the pressure input vector through a pressure value extractor based on a multi-scale neighborhood feature extraction module.

[0032] Specifically, the pressure arrangement vector subunit 1211 is used to arrange the pressure values ​​of the multiple predetermined time points into pressure input vectors according to the time dimension. It should be understood that arranging the pressure values ​​according to the time dimension can retain the time series information and reflect the trend of pressure changes over time. This is very important for monitoring pressure fluctuations, trends and periodic changes in the oil and gas recovery process. Arranging the pressure values ​​according to the time dimension can maintain the continuity of the data and ensure the order of the data in time. This helps to accurately analyze the changes and trends of the pressure values. By arranging the pressure values ​​according to the time dimension, the pressure feature vector can be better extracted, including the pressure values ​​at different time points, which helps the system to more accurately analyze and judge the pressure situation in the oil and gas recovery process. Arranging the pressure values ​​according to the time dimension into a pressure input vector can make data processing more convenient and efficient. This data structure is conducive to subsequent feature extraction, model training and data analysis. In summary, arranging the pressure values ​​of multiple predetermined time points into a pressure input vector according to the time dimension is to better retain the time series information, maintain data continuity, improve the accuracy of feature extraction and enhance the convenience of data processing, so as to effectively monitor and analyze the pressure situation in the oil and gas recovery process.

[0033] Correspondingly, the pressure multi-scale extraction subunit 1212 is used to obtain the pressure feature vector by passing the pressure input vector through a pressure value extractor based on a multi-scale neighborhood feature extraction module. It should be understood that the multi-scale neighborhood feature extraction module can capture the characteristics of pressure values ​​at different time scales. Pressure changes at different time scales may contain different information, and the changes in pressure parameters can be more comprehensively described through multi-scale feature extraction. Through multi-scale neighborhood feature extraction, pressure features at different scales can be extracted, thereby enhancing the expressive power of features. This helps to better capture the changing patterns and laws of pressure values. The pressure value extractor based on multi-scale neighborhood feature extraction can help the system extract pressure feature vectors more accurately, thereby improving the accuracy of the monitoring system's analysis and judgment of the oil and gas recovery process. Through multi-scale neighborhood feature extraction, the system can analyze the changes in pressure parameters more comprehensively and accurately, thereby improving the performance and reliability of the monitoring system.

[0034] Specifically, the pressure multi-scale extraction subunit includes: a first-scale pressure encoding secondary subunit, which is used to use the first convolution layer of the pressure extractor based on the multi-scale neighborhood feature extraction module to perform one-dimensional convolution encoding on the pressure input vector with a one-dimensional convolution kernel with a first scale to obtain a first-scale pressure feature vector, wherein the first convolution layer has a first one-dimensional convolution kernel with a first length; a second-scale pressure encoding secondary subunit, which is used to use the second convolution layer of the pressure extractor based on the multi-scale neighborhood feature extraction module to perform one-dimensional convolution encoding on the pressure input vector with a one-dimensional convolution kernel with a second scale to obtain a second-scale pressure feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; a multi-scale pressure cascade secondary subunit, which is used to cascade the first-scale pressure feature vector and the second-scale pressure feature vector to obtain the pressure feature vector.

[0035] Accordingly, in a specific example of the present application, the liquid flow value feature extraction unit 122 is used to extract the liquid flow feature vector from the liquid flow values ​​at the multiple predetermined time points. It should be understood that the liquid flow value changes over time, and by extracting the flow values ​​at multiple time points, the time series information of the liquid flow can be captured. This helps to understand the changing trend and periodicity of the liquid flow. Extracting the flow values ​​at multiple time points can provide more comprehensive information, covering the flow conditions in different time periods. This helps the system to analyze the characteristics of the liquid flow more comprehensively. By extracting the flow values ​​at multiple time points, trend analysis can be performed to identify the changing trends and laws of the liquid flow. This helps to predict future flow changes and make corresponding adjustments. The flow values ​​at multiple time points provide more data for anomaly detection. The system can identify abnormal situations by comparing the flow values ​​at different time points and take timely measures. By extracting the liquid flow values ​​at multiple time points and constructing the liquid flow feature vector, the system can more comprehensively and accurately describe the characteristics of the liquid flow, thereby improving the monitoring system's ability to analyze the liquid flow situation.

[0036] Specifically, the liquid flow value feature extraction unit includes: a liquid flow value arrangement vector subunit, which is used to arrange the liquid flow values ​​of the multiple predetermined time points into a liquid flow input vector according to the time dimension; and a liquid flow value multi-scale extraction subunit, which is used to pass the liquid flow input vector through a liquid flow extractor based on a multi-scale neighborhood feature extraction module to obtain the liquid flow feature vector.

[0037] Accordingly, in a specific example of the present application, the gas concentration feature extraction unit 123 is used to extract the gas concentration feature vector from the gas concentration values ​​at the multiple predetermined time points. It should be understood that by collecting the gas concentration values ​​at multiple predetermined time points, the trend of gas concentration changes over time can be obtained. The data at these time points can provide dynamic information about the change in gas concentration, which helps to fully understand the changing law of gas concentration. By processing and analyzing the gas concentration values ​​at multiple time points, characteristic information of gas concentration can be extracted. These features may include average value, volatility, trend direction, etc., which help to describe the overall characteristics of gas concentration. Integrating the gas concentration values ​​at multiple time points into a feature vector can comprehensively consider the information at different time points, thereby more comprehensively describing the state of gas concentration. This helps the system to conduct a comprehensive analysis and judgment of gas concentration. By extracting gas concentration feature vectors from multiple time points, the system can understand the changes in gas concentration more comprehensively and accurately, and provide more effective information for monitoring and control of the oil and gas recovery system.

[0038] Specifically, the gas concentration feature extraction unit includes: a gas concentration vector arrangement subunit, which is used to arrange the gas concentration values ​​of the multiple predetermined time points into a gas concentration input vector according to the time dimension; a gas concentration multi-scale extraction subunit, which is used to pass the gas concentration input vector through a gas concentration extractor based on a multi-scale neighborhood feature extraction module to obtain the gas concentration feature vector.

[0039] Accordingly, in a specific example of the present application, the liquid level feature extraction unit 124 is used to extract the liquid level feature vector from the liquid level values ​​at the multiple predetermined time points. It should be understood that the liquid level value changes over time. By extracting the liquid level values ​​at multiple time points, the change of the liquid level can be dynamically monitored, so as to better understand the operating status of the system. By analyzing the liquid level values ​​at multiple time points, the trend of liquid level changes can be revealed, which helps predict the future operating status of the system. Liquid level abnormalities may mean that there are problems with the system. By extracting the liquid level feature vector and performing anomaly detection, abnormalities in the operation of the system can be discovered in time. By extracting the liquid level feature vector, the integrity and accuracy of the data can be guaranteed, providing reliable data support for the analysis and evaluation of the operating status of the system. Therefore, extracting the liquid level feature vector from the liquid level values ​​at multiple predetermined time points helps in dynamic monitoring, trend analysis, anomaly detection and ensuring data integrity, and improves the comprehensiveness and accuracy of the monitoring system for liquid level parameters.

[0040] Specifically, the liquid level feature extraction unit includes: a liquid level arrangement vector subunit, used to arrange the liquid level values ​​of the multiple predetermined time points into a liquid level input vector according to the time dimension; a liquid level multi-scale extraction subunit, used to pass the liquid level input vector through a liquid level value extractor based on a multi-scale neighborhood feature extraction module to obtain the liquid level feature vector.

[0041] In the embodiment of the present application, the oil and gas recovery process data fusion module 130 is used to fuse the pressure feature vector, the liquid flow feature vector, the gas concentration feature vector and the liquid level feature vector to obtain the oil and gas recovery process parameter feature matrix, and perform scattering response depth correlation optimization based on the category difference space on the oil and gas recovery parameter feature matrix to obtain the optimized oil and gas recovery parameter feature matrix. It should be understood that the oil and gas recovery process involves multiple parameters, including pressure, liquid flow, gas concentration and liquid level. Fusion of the feature vectors of these parameters can achieve a comprehensive analysis of the entire process and a more comprehensive understanding of the system operation status. Different parameters provide different information dimensions, and fusion of this information can provide data from more angles, which helps to more comprehensively understand the characteristics and change laws of the oil and gas recovery process. By fusing the feature vectors of different parameters into a feature matrix, the influence of each parameter on the oil and gas recovery process can be comprehensively evaluated, helping the system to more accurately judge the eligibility of the oil and gas recovery process. Fusion of the feature vectors of different parameters into a feature matrix can provide a more comprehensive feature representation, which helps the system to comprehensively analyze and evaluate the parameters of the oil and gas recovery process. Therefore, fusing the pressure eigenvector, liquid flow eigenvector, gas concentration eigenvector and liquid level eigenvector to obtain the oil and gas recovery process parameter characteristic matrix can provide a more comprehensive and integrated data basis, which is helpful for the system to monitor, analyze and evaluate the oil and gas recovery process.

[0042] Specifically, in one embodiment of the present application, the oil and gas recovery process data fusion module includes: a parameter arrangement unit, used to arrange the pressure characteristic vector, the liquid flow characteristic vector, the gas concentration characteristic vector and the liquid level characteristic vector according to the parameter dimension to obtain the oil and gas recovery process parameter input matrix; a spatial attention unit, used to pass the oil and gas recovery process parameter input matrix through the first convolutional neural network model of spatial attention to obtain the oil and gas recovery process parameter feature matrix.

[0043] Accordingly, in a specific example of the present application, the parameter arrangement unit is used to arrange the pressure characteristic vector, the liquid flow characteristic vector, the gas concentration characteristic vector and the liquid level characteristic vector according to the parameter dimension to obtain the oil and gas recovery process parameter input matrix. It should be understood that different parameter characteristic vectors represent different physical quantities in the oil and gas recovery process. Arranging them according to the parameter dimension can integrate this information together to form a comprehensive input matrix, which helps the system to comprehensively analyze the association and influence between different parameters. Arranging according to the parameter dimension can enable the system to uniformly process the characteristic vectors of different parameters, making subsequent analysis and processing more convenient and efficient. By arranging the characteristic vectors of different parameters according to the parameter dimension, the correlation and mutual influence between different parameters can be better captured, which helps the system to more comprehensively understand the relationship between various parameters in the oil and gas recovery process. Arranging the characteristic vectors of each parameter into the form of an input matrix meets the input requirements of models such as neural networks, which is conducive to subsequent model training and analysis. Therefore, arranging the pressure characteristic vector, the liquid flow characteristic vector, the gas concentration characteristic vector and the liquid level characteristic vector according to the parameter dimension to obtain the oil and gas recovery process parameter input matrix helps the system to integrate and comprehensively analyze multiple parameter information.

[0044] Accordingly, in a specific example of the present application, the spatial attention unit is used to pass the oil and gas recovery process parameter input matrix through the first convolutional neural network model of spatial attention to obtain the oil and gas recovery process parameter feature matrix. It should be understood that the convolutional neural network (CNN) is an effective deep learning model that can effectively extract features from input data. By passing the parameter input matrix into the first convolutional neural network model, the system can automatically learn and extract key features in the oil and gas recovery process, including the complex relationship between parameters such as pressure, liquid flow, gas concentration and liquid level. The spatial attention mechanism can help the network focus on important feature areas, reduce the impact of redundant information, and thus improve the characterization ability of features. Through the application of spatial attention, the system can pay more attention to the key parameters in the oil and gas recovery process and improve the effect of feature extraction. There may be complex correlations between the various parameters in the oil and gas recovery process. Through the learning ability of the convolutional neural network, the nonlinear relationship between these parameters can be better captured, thereby obtaining a more accurate and comprehensive oil and gas recovery process parameter feature matrix. Therefore, processing the oil and gas recovery process parameter input matrix through the first convolutional neural network model of spatial attention can help the system to better extract key features and capture the complex correlations between parameters, thereby obtaining a more effective oil and gas recovery process parameter feature matrix and improving the system's monitoring and analysis capabilities.

[0045] Accordingly, in a specific example of the present application, the optimization unit is used to optimize the oil and gas recovery parameter feature matrix based on the scattering response depth correlation of the category difference space to obtain the optimized oil and gas recovery parameter feature matrix. It should be understood that, in particular, in the technical solution of the present application, the oil and gas recovery parameter feature matrix is ​​a combination of feature information of multiple key parameters such as pressure, liquid flow, gas concentration and liquid level, which is used to judge whether the oil and gas recovery process is qualified. Improving the feature significance of the oil and gas recovery parameter feature matrix and avoiding feature redundancy are crucial to ensure the accuracy and efficiency of oil and gas recovery process monitoring. Specifically, significant features help to more accurately evaluate whether each parameter of the oil and gas recovery process meets the standard, thereby improving the accuracy of qualification judgment. Significant features can better identify abnormal situations that may occur in the oil and gas recovery process, help to find problems in time and take corresponding measures. The oil and gas recovery process may be affected by various factors, and significant features help the system maintain stable performance under these changes. In addition, removing redundant features can reduce the amount of model calculation, speed up data processing, and improve the real-time performance of oil and gas recovery monitoring. Avoiding feature redundancy helps to reduce the demand for computing resources and storage resources and reduce system operating costs. Redundant features may cause the model to overfit and affect its generalization ability under different oil and gas recovery conditions. Avoiding feature redundancy helps to improve the generalization performance of the model. At the same time, significant features help to achieve precise control of the oil and gas recovery process and ensure the stability and safety of the process. Through precise features, unnecessary energy and material waste can be reduced and resource utilization efficiency can be improved. Significant features and avoiding redundancy help reduce eligibility judgment errors caused by improper feature selection and improve the reliability of the system. Based on this, the oil and gas recovery parameter feature matrix is ​​optimized based on the scattering response deep correlation of the category difference space to obtain the optimized oil and gas recovery parameter feature matrix.

[0046] Correspondingly, the optimization unit includes: a feature flattening subunit, used to perform feature flattening on the oil and gas recovery parameter feature matrix to obtain an oil and gas recovery parameter feature vector; a correlation optimization subunit, used to perform scattering response depth correlation optimization based on the category difference space on the oil and gas recovery parameter feature vector to obtain an optimized oil and gas recovery parameter feature vector; and a reverse feature aggregation subunit, used to perform reverse feature aggregation on the optimized oil and gas recovery parameter feature vector in the manner of feature flattening to obtain the optimized oil and gas recovery parameter feature matrix.

[0047] Further, the correlation optimization subunit includes: determining the mean value of the oil and gas recovery parameter feature vector; accumulating and summing the oil and gas recovery parameter feature vectors to obtain the sum value of the oil and gas recovery parameter feature vectors; subtracting the mean value of the oil and gas recovery parameter feature vector from the sum value of the oil and gas recovery parameter feature vector, dividing the result by a predetermined hyperparameter and then dividing the result by the length of the oil and gas recovery parameter feature vector to obtain a first quotient value; calculating an exponential function value with a natural constant as the base for the first quotient to obtain a first natural exponential function value; and multiplying the first natural exponential function value by the oil and gas recovery parameter feature vector at a position point to obtain an optimized oil and gas recovery parameter feature vector.

[0048] Specifically, the oil and gas recovery parameter feature matrix is ​​optimized based on the scattering response depth correlation of the category difference space to obtain the optimized oil and gas recovery parameter feature matrix, which can be described by formula, including: flattening the oil and gas recovery parameter feature matrix to obtain the oil and gas recovery parameter feature vector; optimizing the oil and gas recovery parameter feature vector based on the scattering response depth correlation of the category difference space according to the following formula to obtain the optimized oil and gas recovery parameter feature vector, wherein the formula is:

[0049]

[0050] Wherein, V1 represents the oil and gas recovery parameter characteristic vector, v i represents the eigenvalue of the i-th position of the oil and gas recovery parameter eigenvector, represents the mean value of the oil and gas recovery parameter feature vector, L represents the length of the oil and gas recovery parameter feature vector, ε represents a predetermined hyperparameter, ⊙ represents a point multiplication by position, and V1′ represents the optimized oil and gas recovery parameter feature vector;

[0051] The optimized oil and gas recovery parameter feature vector is subjected to reverse feature aggregation in the feature flattening manner to obtain the optimized oil and gas recovery parameter feature matrix.

[0052] Specifically, in order to improve the feature significance of the oil and gas recovery parameter feature matrix and avoid feature redundancy, in the technical solution of the present application, the oil and gas recovery parameter feature matrix is ​​optimized based on the scattering response depth correlation of the class difference space, and the global mean of the oil and gas recovery parameter feature matrix is ​​used as its dynamically formed deep anchoring feature, and a coherence attention response mechanism based on the deep anchoring feature is applied to the original feature distribution to perform position scattering response depth correlation correction in the class divergence space with depth difference, so that the original feature distribution has a highly significant depth correlation distribution characteristic, so as to improve the feature significance of the oil and gas recovery parameter feature matrix and avoid feature redundancy.

[0053] In the embodiment of the present application, the oil and gas recovery process data analysis module 140 is used to pass the optimized oil and gas recovery process parameter feature matrix through a classifier to obtain a classification result, and the classification result is used to indicate whether the oil and gas recovery is qualified. It should be understood that by inputting the extracted parameter feature matrix into the classifier for classification, the qualification of the oil and gas recovery process can be judged according to a predefined qualification standard or threshold. The classification result can intuitively indicate whether the oil and gas recovery process meets the set requirements. Using a classifier to automatically judge the qualification of the oil and gas recovery process can reduce the need for manual intervention and improve the automation and efficiency of the system. In this way, problems can be discovered in time and corresponding measures can be taken. The classifier can process the parameter feature matrix in real time and quickly give a judgment on the qualification of the oil and gas recovery process, so as to discover abnormal situations in time and take countermeasures to ensure the stable operation of the oil and gas recovery process. According to the classification results, the system can further analyze the reasons for non-compliance and provide a reference for subsequent optimization and improvement, thereby improving the efficiency and performance of the oil and gas recovery system. Therefore, the oil and gas recovery process parameter feature matrix is ​​passed through the classifier to obtain the classification result, which is used to indicate whether the oil and gas recovery is qualified, which helps to realize automated qualification judgment and real-time monitoring, thereby improving the operation efficiency and stability of the system.

[0054] Specifically, in one embodiment of the present application, the oil and gas recovery process data analysis module includes: an oil and gas recovery parameter matrix expansion unit, which is used to expand the oil and gas recovery process parameter input matrix into an oil and gas recovery parameter classification feature vector according to a row vector or a column vector; an oil and gas recovery parameter fully connected encoding unit, which is used to use the fully connected layer of the classifier to fully connect the oil and gas recovery parameter classification feature vector to obtain an oil and gas recovery parameter fully connected encoded feature vector; an oil and gas recovery parameter probability acquisition unit, which is used to pass the oil and gas recovery parameter fully connected encoded feature vector through the Softmax classification function of the classifier to obtain a first probability belonging to qualified oil and gas recovery and a second probability belonging to unqualified oil and gas recovery; an oil and gas recovery parameter classification result determination unit, which is used to determine the classification result based on a comparison between the first probability and the second probability.

[0055] In summary, the multi-parameter-based intelligent oil and gas recovery monitoring system and method based on the embodiment of the present application integrates multiple sensors to monitor parameters such as pressure, flow, gas concentration and liquid level of the oil and gas recovery system, extracts feature vectors and uses a classifier to judge the eligibility of the oil and gas recovery process, so as to realize an efficient intelligent oil and gas recovery monitoring system.

[0056] As described above, the multi-parameter-based intelligent monitoring system for oil and gas recovery 100 according to the embodiment of the present application can be implemented in various terminal devices, such as a server of the multi-parameter-based intelligent monitoring system for oil and gas recovery, etc. In one example, the multi-parameter-based intelligent monitoring system for oil and gas recovery 100 can be integrated into the terminal device as a software module and / or a hardware module. For example, the multi-parameter-based intelligent monitoring system for oil and gas recovery 100 can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the multi-parameter-based intelligent monitoring system for oil and gas recovery 100 can also be one of the many hardware modules of the terminal device.

[0057] Alternatively, in another example, the multi-parameter-based intelligent monitoring system for oil and gas recovery 100 and the terminal device may also be separate devices, and the multi-parameter-based intelligent monitoring system for oil and gas recovery 100 may be connected to the terminal device via a wired and / or wireless network, and transmit interactive information in accordance with an agreed data format.

[0058] Figure 4 FIG. 1 is a flow chart of an intelligent oil and gas recovery monitoring method based on multiple parameters according to an embodiment of the present application. Figure 4 As shown, according to the multi-parameter-based intelligent monitoring method for oil and gas recovery in the embodiment of the present application, the method includes the following steps: S110, extracting the pressure values, liquid flow values, gas concentration values ​​and liquid level values ​​at multiple predetermined time points including the current time point during the oil and gas recovery process; S120, extracting the pressure feature vector, liquid flow feature vector, gas concentration feature vector and liquid level feature vector from the pressure values, liquid flow values, gas concentration values ​​and liquid level values ​​at the multiple predetermined time points respectively; S130, fusing the pressure feature vector, the liquid flow feature vector, the gas concentration feature vector and the liquid level feature vector to obtain an oil and gas recovery process parameter feature matrix, and performing scattering response deep correlation optimization based on the category difference space on the oil and gas recovery parameter feature matrix to obtain an optimized oil and gas recovery parameter feature matrix; S140, passing the optimized oil and gas recovery process parameter feature matrix through a classifier to obtain a classification result, and the classification result is used to indicate whether the oil and gas recovery is qualified.

[0059] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned multi-parameter-based intelligent monitoring method for oil and gas recovery have been referred to above. Figures 1 to 4 The description of the multi-parameter-based intelligent monitoring system for oil and gas recovery has been introduced in detail, and therefore, its repeated description will be omitted.

[0060] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0061] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0062] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0063] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0064] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0065] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0066] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An intelligent monitoring system for oil and gas recovery based on multiple parameters, characterized in that: include: The oil and gas recovery process data acquisition module is used to extract the pressure value, liquid flow value, gas concentration value and liquid level value at multiple predetermined time points including the current time point during the oil and gas recovery process; An oil and gas recovery process data processing module, used to extract a pressure characteristic vector, a liquid flow characteristic vector, a gas concentration characteristic vector and a liquid level characteristic vector from the pressure values, liquid flow values, gas concentration values ​​and liquid level values ​​at the plurality of predetermined time points, respectively; An oil and gas recovery process data fusion module is used to fuse the pressure feature vector, the liquid flow feature vector, the gas concentration feature vector and the liquid level feature vector to obtain an oil and gas recovery process parameter feature matrix, and perform scattering response depth correlation optimization based on the category difference space on the oil and gas recovery parameter feature matrix to obtain an optimized oil and gas recovery parameter feature matrix; An oil and gas recovery process result analysis module, used for passing the optimized oil and gas recovery process parameter feature matrix through a classifier to obtain a classification result, wherein the classification result is used to indicate whether the oil and gas recovery is qualified; Wherein, the oil and gas recovery process data fusion module includes: A parameter arrangement unit, used for arranging the pressure characteristic vector, the liquid flow characteristic vector, the gas concentration characteristic vector and the liquid level characteristic vector according to parameter dimensions to obtain an oil and gas recovery process parameter input matrix; A spatial attention unit, used for passing the oil and gas recovery process parameter input matrix through a first convolutional neural network model of spatial attention to obtain the oil and gas recovery process parameter feature matrix; An optimization unit, used for performing scattering response depth correlation optimization based on the category difference space on the oil and gas recovery parameter feature matrix to obtain the optimized oil and gas recovery parameter feature matrix; Wherein, the optimization unit comprises: A feature flattening subunit, used for flattening the oil and gas recovery parameter feature matrix to obtain an oil and gas recovery parameter feature vector; A correlation optimization subunit, used for performing scattering response depth correlation optimization based on the category difference space on the oil and gas recovery parameter feature vector to obtain an optimized oil and gas recovery parameter feature vector; A reverse feature aggregation subunit, used for performing reverse feature aggregation on the optimized oil and gas recovery parameter feature vector in the feature flattening manner to obtain the optimized oil and gas recovery parameter feature matrix; Wherein, the correlation optimization subunit includes: Determining a mean value of the oil and gas recovery parameter characteristic vector; Accumulating and summing the oil and gas recovery parameter characteristic vectors to obtain a total value of the oil and gas recovery parameter characteristic vectors; Subtracting the mean value of the oil and gas recovery parameter feature vector from the sum of the oil and gas recovery parameter feature vectors and dividing the sum by a predetermined hyperparameter and then by the length of the oil and gas recovery parameter feature vector to obtain a first quotient; Calculating an exponential function value with a natural constant as a base for the first quotient value to obtain a first natural exponential function value; The first natural exponential function value is multiplied by the oil and gas recovery parameter characteristic vector at each position point to obtain an optimized oil and gas recovery parameter characteristic vector.

2. The multi-parameter-based intelligent monitoring system for oil and gas recovery according to claim 1 is characterized in that: The oil and gas recovery process data processing module includes: A pressure feature extraction unit, configured to extract the pressure feature vector from the pressure values ​​at the plurality of predetermined time points; A liquid flow value feature extraction unit, used to extract the liquid flow feature vector from the liquid flow values ​​at the plurality of predetermined time points; A gas concentration feature extraction unit, configured to extract the gas concentration feature vector from the gas concentration values ​​at the plurality of predetermined time points; The liquid level feature extraction unit is used to extract the liquid level feature vector from the liquid level values ​​at the plurality of predetermined time points.

3. The multi-parameter-based intelligent monitoring system for oil and gas recovery according to claim 2 is characterized in that: The pressure feature extraction unit comprises: A pressure arranging vector subunit, used for arranging the pressure values ​​of the plurality of predetermined time points into a pressure input vector according to a time dimension; The pressure multi-scale extraction subunit is used to obtain the pressure feature vector by passing the pressure input vector through a pressure value extractor based on a multi-scale neighborhood feature extraction module.

4. The multi-parameter-based intelligent monitoring system for oil and gas recovery according to claim 3 is characterized in that: The liquid flow value feature extraction unit comprises: A liquid flow value arranging vector subunit, used for arranging the liquid flow values ​​of the plurality of predetermined time points into a liquid flow input vector according to a time dimension; The liquid flow value multi-scale extraction subunit is used to pass the liquid flow input vector through a liquid flow extractor based on a multi-scale neighborhood feature extraction module to obtain the liquid flow feature vector.

5. The multi-parameter-based intelligent monitoring system for oil and gas recovery according to claim 4 is characterized in that: The gas concentration feature extraction unit comprises: A gas concentration arranging vector subunit, used to arrange the gas concentration values ​​of the plurality of predetermined time points into a gas concentration input vector according to a time dimension; The gas concentration multi-scale extraction subunit is used to pass the gas concentration input vector through a gas concentration extractor based on a multi-scale neighborhood feature extraction module to obtain the gas concentration feature vector.

6. The multi-parameter-based intelligent monitoring system for oil and gas recovery according to claim 5 is characterized in that: The liquid level feature extraction unit comprises: A liquid level arrangement vector subunit, used for arranging the liquid level values ​​of the plurality of predetermined time points into a liquid level input vector according to a time dimension; The liquid level multi-scale extraction subunit is used to obtain the liquid level feature vector by passing the liquid level input vector through a liquid level value extractor based on a multi-scale neighborhood feature extraction module.

7. A multi-parameter-based intelligent monitoring method for oil and gas recovery, using the multi-parameter-based intelligent monitoring system for oil and gas recovery according to claim 1, characterized in that: include: Extract the pressure value, liquid flow value, gas concentration value and liquid level value at multiple predetermined time points including the current time point during the oil and gas recovery process; Extracting a pressure feature vector, a liquid flow feature vector, a gas concentration feature vector and a liquid level feature vector from the pressure values, liquid flow values, gas concentration values ​​and liquid level values ​​at the plurality of predetermined time points respectively; The pressure characteristic vector, the liquid flow characteristic vector, the gas concentration characteristic vector and the liquid level characteristic vector are integrated to obtain an oil and gas recovery process parameter characteristic matrix, and the oil and gas recovery parameter characteristic matrix is ​​optimized based on the scattering response depth correlation of the category difference space to obtain an optimized oil and gas recovery parameter characteristic matrix; The optimized oil and gas recovery process parameter feature matrix is ​​passed through a classifier to obtain a classification result, and the classification result is used to indicate whether the oil and gas recovery is qualified.

Images