Remote monitoring method and system for oil field operation equipment

Abstract

The invention relates to a remote monitoring method and system for oil field operation equipment, and belongs to the technical field of oil field equipment monitoring, and the remote monitoring method comprises the steps: receiving the operation state data, collected in real time, of each key part of the oil field operation equipment; time sequence features related to the equipment state are extracted and subjected to normalization processing, and a time sequence feature set is generated; analyzing the time sequence feature set based on a health degree model, generating a health degree time sequence, performing dynamic segmentation analysis, and labeling abnormal features; performing long and short term trend analysis on the health degree time sequence based on a sliding window method, and calculating to obtain a trend analysis result; correlation analysis is carried out according to the trend analysis result and the abnormal features, and a comprehensive risk score is calculated; and matching a corresponding early warning level and a maintenance strategy according to the comprehensive risk score, and sending maintenance prompt information to a maintenance terminal. According to the invention, real-time remote monitoring of the operation state of the oil field equipment can be realized, and potential fault early warning can be carried out in advance.

Description

Technical Field

[0001] The present application relates to the technical field of oilfield equipment monitoring, and in particular to a remote monitoring method and system for oilfield operating equipment. Background Art

[0002] With the rapid development of the modern petroleum industry, the continuous expansion of oilfield operations and the complexity of equipment technology, the efficient management and stable operation of oilfield equipment have become important factors affecting the benefits of oil production. In oilfield operations, equipment usually works in harsh environments with high loads and high risks, such as high temperature, high pressure, strong corrosion and other working conditions. In particular, core equipment such as pumping units, compressors and centrifugal pumps need to operate continuously for a long time. Their operating status directly determines the production efficiency, economic benefits and safety level of the oilfield.

[0003] At present, in the oilfield operation environment, due to the wide distribution of equipment and complex operating conditions, when multiple devices are operated in coordination, the status changes between the devices may produce a chain reaction. Once a certain device fails, it may have a significant impact on the entire production system. Therefore, how to achieve real-time remote monitoring of the operating status of oilfield equipment and early warning of potential failures to ensure the safe and efficient operation of oilfield operation equipment is an important issue that needs to be solved urgently. Summary of the invention

[0004] In order to ensure the safe and stable operation of oilfield operating equipment, the present application provides a remote monitoring method and system for oilfield operating equipment.

[0005] In a first aspect, the present application provides a remote monitoring method for oilfield operation equipment, which adopts the following technical solution: A remote monitoring method for oilfield operation equipment, the remote monitoring method comprising: Receive real-time collected operating status data of various key parts of oilfield operating equipment; the operating status data includes vibration signals, temperature signals, current signals and pressure signals; Performing data preprocessing on the operating status data; Extracting time series features related to equipment status from preprocessed operating status data and performing normalization processing to generate a time series feature set; Analyzing the time series feature set based on a pre-built health model, calculating the health value of the time series feature at each time point, and generating a health time series of the oilfield operation equipment; Performing dynamic segmentation analysis on the health time series, marking the time series features whose health value drops beyond a preset threshold as abnormal features, and determining the severity level of the abnormal features according to the drop amplitude; Based on the sliding window method, the long-term and short-term trend analysis of the health time series is performed to calculate the trend analysis result; Perform correlation analysis based on the trend analysis results and the abnormal characteristics to calculate a corresponding comprehensive risk score; The corresponding warning level and maintenance strategy are matched according to the comprehensive risk score, and maintenance reminder information is sent to the maintenance terminal through the remote communication module.

[0006] By adopting the above technical solutions, real-time remote monitoring of performance degradation of oilfield operating equipment and generation of intelligent maintenance strategies are realized. By utilizing the calculation logic of health model and trend analysis, it is possible to comprehensively capture short-term fluctuations and long-term degradation trends of equipment, quantify equipment operation risks and trigger maintenance recommendations in a timely manner, thereby significantly improving oilfield equipment management efficiency, reducing maintenance costs and equipment failure risks, and providing reliable technical support for the safe and efficient operation of oilfield operating equipment.

[0007] Optionally, the calculation formula of the health model is: Among them, H(t) is the health value at time t, f i (t) is the normalized eigenvalue, α i is the feature weight, which indicates the influence of different features on the health status of the device.

[0008] Optionally, the steps of performing long-term and short-term trend analysis on the health time series based on a sliding window method and calculating the trend analysis result include: Performing segmentation processing on the health time series based on a preset short-term window and a preset long-term window respectively; Performing short-term trend analysis on the health time series within each of the preset short-term windows to obtain short-term trend data; wherein the short-term trend data includes a short-term trend slope and a short-term health average value; Performing a long-term trend analysis on the health time series within each of the preset long-term windows to obtain long-term trend data; wherein the long-term trend data includes a long-term trend slope and a long-term health average value; The short-term trend data and the long-term trend data are combined to obtain a trend analysis result.

[0009] By adopting the above technical solution, the short-term and long-term trend analysis of the health time series based on the sliding window method can be carried out to comprehensively evaluate the health status of oilfield operating equipment. In the short term, the system can timely capture sudden abnormalities and fluctuations of the equipment and provide early warnings; in terms of long-term trends, it can identify the continuous degradation trend of the equipment and help decision makers predict future failure risks. By combining short-term and long-term trend data, the system can comprehensively analyze the health status of the equipment, provide strong data support for equipment maintenance and optimization decisions, and ultimately improve the safety and operating efficiency of the equipment and reduce maintenance costs and failure risks.

[0010] Optionally, the calculation formula of the comprehensive risk score is: R(t)=β1S short +β2S long +γ·abnormality(t); In the above formula, S short is the short-term trend slope, S long is the long-term trend slope, abnormality(t) is the severity of the abnormal feature, and β1, β2, and γ are weight coefficients.

[0011] Optionally, after the step of sending the maintenance prompt information to the maintenance terminal through the remote communication module, the method further includes: Receiving a maintenance completion feedback signal sent by a maintenance terminal; In response to the maintenance completion feedback signal, obtaining the operating status data of the oilfield operation equipment after the maintenance is completed and analyzing it based on the health model to obtain a health time series after the maintenance is completed; Compare the health time series before and after maintenance, and calculate the maintenance effect score; Determine whether the maintenance effect score is lower than a preset score standard; If not, the maintenance effect is determined to be qualified, and the maintenance end information is fed back; If so, it is determined that the maintenance effect is unsatisfactory, and a maintenance verification message is sent to the management terminal.

[0012] By adopting the above technical solution, the system determines whether the maintenance effect is qualified according to the preset standards. If qualified, the maintenance is confirmed to be completed and feedback is given to relevant personnel. If unqualified, maintenance verification information is automatically generated and sent to the management terminal, realizing intelligent evaluation and timely feedback of equipment maintenance effects. While ensuring the long-term and stable operation of the equipment, it can improve the efficiency of equipment management and reduce the risk of equipment failure due to inadequate maintenance.

[0013] Optionally, the steps of comparing the health time series before maintenance and after maintenance to calculate the maintenance effect score include: According to the health time series before and after the maintenance, the health characteristic values ​​before and after the maintenance are calculated respectively; Based on the preset ideal health, the corresponding maintenance effect score E is calculated by combining the health characteristic values ​​before and after maintenance: In the above formula, H post H is the health characteristic value after maintenance is completed. pre is the health characteristic value before maintenance, H ideal To preset the ideal health level.

[0014] By adopting the above technical solution, the health time series before and after maintenance is converted into characteristic values, solving the problem of mismatch between the health time series and the specific values, while retaining the main trend information of the time series. Through the calculation and determination of maintenance effect scores, the system realizes the automatic analysis and feedback of maintenance effects, significantly improves the intelligence and accuracy of equipment management, and provides strong support for the long-term safe and efficient operation of equipment.

[0015] In the second aspect, the present application provides a remote monitoring system for oilfield operation equipment, which adopts the following technical solution: A remote monitoring system for oilfield operation equipment, the remote monitoring system comprising: An operation status data receiving module is used to receive the operation status data of each key part of the oilfield operation equipment collected in real time; the operation status data includes vibration signals, temperature signals, current signals and pressure signals; A data preprocessing module, used for performing data preprocessing on the operating status data; The time series extraction module is used to extract the time series features related to the equipment status from the pre-processed operation status data and perform normalization processing to generate a time series feature set; A health analysis module, used to analyze the time series feature set based on a pre-built health model, calculate the health value of the time series feature at each time point, and generate a health time series of the oilfield operation equipment; An abnormal feature identification module is used to perform dynamic segmentation analysis on the health time series, mark the time series features whose health value drops beyond a preset threshold as abnormal features, and determine the severity level of the abnormal features according to the drop amplitude; a trend analysis module is used to perform long-term and short-term trend analysis on the health time series based on a sliding window method, and calculate the trend analysis results; A comprehensive risk scoring module, used to perform correlation analysis based on the trend analysis results and the abnormal characteristics, and calculate the corresponding comprehensive risk score; The maintenance prompt module is used to match the corresponding warning level and maintenance strategy according to the comprehensive risk score, and send maintenance prompt information to the maintenance terminal through the remote communication module.

[0016] Optionally, the remote monitoring system further includes: A signal receiving module, used for receiving a maintenance completion feedback signal sent by a maintenance terminal; A health analysis module, configured to respond to the maintenance completion feedback signal, obtain the operating status data of the oilfield operation equipment after the maintenance is completed and analyze it based on the health model to obtain a health time series after the maintenance is completed; The maintenance effect scoring module is used to compare the health time series before and after maintenance to calculate the maintenance effect score; A judgment module is used to judge whether the maintenance effect score is lower than a preset score standard; if not, output a maintenance effect qualified result; if so, output a maintenance effect unqualified result; A maintenance feedback module, used for feeding back maintenance completion information in response to the qualified maintenance effect result; The maintenance verification module is used to send maintenance verification information to the management terminal in response to the unqualified maintenance effect result.

[0017] In a third aspect, the present application provides a computer device, which adopts the following technical solution: A computer device comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method as described in the first aspect.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any one of the methods in the first aspect.

[0019] To summarize, the present application includes at least one of the following beneficial technical effects: the present application can effectively evaluate the changing trend of the health status of the equipment, accurately capture the short-term fluctuations and long-term degradation of the equipment, realize efficient maintenance prompts and feedback, and provide strong technical support for the safety, continuity and economy of oilfield equipment, significantly reduce the risk of unplanned downtime, and improve the overall management efficiency and operational reliability of oilfield equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a first flow chart of a remote monitoring method according to one of the embodiments of the present application.

[0021] Figure 2This is a second flow chart of the remote monitoring method according to one of the embodiments of the present application.

[0022] Figure 3 It is a third flow chart of the remote monitoring method according to one of the embodiments of the present application.

[0023] Figure 4 This is a fourth flow chart of the remote monitoring method according to one of the embodiments of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-4 It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0025] The embodiment of the present application discloses a remote monitoring method for oilfield operation equipment.

[0026] Reference Figure 1 , a remote monitoring method for oilfield operation equipment, the remote monitoring method comprising: Step S101, receiving real-time collected operating status data of various key parts of oilfield operating equipment; Among them, the operating status data includes vibration signals, temperature signals, current signals and pressure signals; Specifically, sensors installed in key parts of oilfield equipment (such as the balance block, crank, connecting rod, bearing, etc. of the pumping unit, the piston, cylinder, valve, etc. of the compressor) can collect equipment operation status data in real time. Sensors can send physical signals such as vibration, temperature, current and pressure to the data receiving module through wireless networks. In addition, to ensure the integrity and validity of the data, a multi-channel data receiving architecture can be designed to support simultaneous collection of multiple devices to avoid signal congestion or loss.

[0027] Step S102, preprocessing the running status data; Among them, the data preprocessing steps include noise filtering and data alignment; specifically, a low-pass filter can be used to remove high-frequency noise, and outlier detection can be performed on the collected signal to remove abnormal data points that may appear during the collection process (such as extreme values ​​or equipment false alarm data); at the same time, the data streams collected by different sensors are aligned according to the timestamp to ensure that subsequent processing uses a unified time base to analyze multi-dimensional data features. For example, for vibration signals, fast Fourier transform (FFT) can be used to extract frequency domain features and remove irrelevant high-frequency signals.

[0028] Step S103, extracting time series features related to the equipment status from the pre-processed operating status data and performing normalization processing to generate a time series feature set; Among them, time series features can be extracted from the original data according to the data type. For example, for vibration signals, time domain features (such as mean, peak) and frequency domain features (such as main frequency, power spectrum) can be extracted; for temperature signals, the rate of change and extreme values ​​can be extracted to identify the risk of component overheating; for current signals, the mean and periodic fluctuation amplitude can be extracted to judge the load change of equipment; for pressure signals, the instantaneous value and change trend can be extracted to judge the sealing of the equipment.

[0029] Furthermore, the extracted eigenvalues ​​are normalized and mapped to the interval [0,1] to eliminate the influence of different physical dimensions, thereby generating a time series feature set, which is a set of normalized eigenvalues ​​changing over time.

[0030] Step S104, analyzing the time series feature set based on the pre-built health model, calculating the health value of the time series feature at each time point, and generating a health time series of the oilfield operation equipment; Among them, the health model can calculate the health value of each time point point by point through feature weighted calculation, and combine them in chronological order to form a health time series.

[0031] Specifically, the calculation formula is: Among them, H(t) is the health value at time t, f i (t) is the normalized eigenvalue, α i is the feature weight, which indicates the influence of different features on the health status of the device.

[0032] It can be understood that the higher the health value, the better the device status. By providing a quantitative dynamic evaluation result for the device status, it is easy to observe the changing trend of the device health status.

[0033] Step S105, dynamically segmenting and analyzing the health time series, marking the time series features whose health values ​​drop beyond a preset threshold as abnormal features, and determining the severity level of the abnormal features according to the drop amplitude; Among them, the health time series is locally analyzed through the sliding window technology to identify the downward trend of the health value. When the health value drops by more than the preset threshold (such as the health value drops by more than 20%), the corresponding time point and related feature values ​​are marked as abnormal features, and the corresponding severity level is determined according to the decline. An abnormal descriptor (including abnormal time point, severity level and corresponding features) is generated, so as to accurately capture abnormal changes in equipment operation and provide input for subsequent risk analysis.

[0034] Step S106, performing long-term and short-term trend analysis on the health time series based on the sliding window method, and calculating the trend analysis result; Among them, long-term trend analysis is to calculate the health mean and slope over a long period of time to observe the trend of the overall performance of the equipment. Short-term trend analysis is to calculate the health mean and slope within a sliding window to capture changes in a short period of time (such as sudden anomalies).

[0035] Specifically, the selection of sliding window size depends on the specific monitoring requirements. The short-term window is suitable for trend analysis of rapid changes, and the long-term window is suitable for long-term degradation monitoring of equipment operating status.

[0036] It can be understood that by combining short-term and long-term trend results to determine whether the change in health is a persistent problem, multi-scale trend analysis can be used to identify short-term fluctuations and long-term degradation of equipment, providing a basis for risk scoring.

[0037] Step S107, performing correlation analysis based on the trend analysis results and the abnormal characteristics, and calculating the corresponding comprehensive risk score; wherein the calculation formula of the comprehensive risk score R(t) is: R(t)=β1S short +β2S long +γ·abnormality(t); In the above formula, S short is the short-term trend slope, S long is the long-term trend slope, abnormality(t) is the severity of the abnormal feature, and β1, β2, and γ are weight coefficients.

[0038] Step S108, matching the corresponding warning level and maintenance strategy according to the comprehensive risk score, and sending maintenance reminder information to the maintenance terminal through the remote communication module.

[0039] Among them, the risk maintenance rule base is queried, the warning level is divided according to the risk score, and the corresponding maintenance strategy (such as shutdown inspection, part replacement, lubrication or cleaning operation) is determined.

[0040] In some embodiments, the warning level can be configured based on a color coding system, such as yellow warning, orange warning and red warning; for yellow warning, the corresponding maintenance strategy is to record the event and recommend checking the operation record; for orange warning, the corresponding maintenance strategy is to generate a preventive maintenance plan, such as recommending lubrication, adjusting equipment parameters, etc.; for red warning, the corresponding maintenance strategy is to generate emergency maintenance instructions, such as replacing parts, shutting down operations, etc.

[0041] In the above implementation, real-time remote monitoring of performance degradation of oilfield operating equipment and generation of intelligent maintenance strategies are realized. By utilizing the calculation logic of health models and trend analysis, it is possible to comprehensively capture short-term fluctuations and long-term degradation trends of equipment, quantify equipment operation risks and trigger maintenance recommendations in a timely manner, thereby significantly improving oilfield equipment management efficiency, reducing maintenance costs and equipment failure risks, and providing reliable technical support for the safe and efficient operation of oilfield operating equipment.

[0042] Reference Figure 2 As an implementation of step S106, the steps of performing long-term and short-term trend analysis on the health time series based on the sliding window method and calculating the trend analysis result include: Step S201, segmenting the health time series based on a preset short-term window and a preset long-term window; Specifically, in the time series, based on the set time window size (short-term window and long-term window), the entire health time series is divided into multiple subsequences. Among them, the short-term window is generally short, such as a few hours to a few days, suitable for capturing sudden changes or short-term fluctuations in the device status; the long-term window is generally long, such as a few weeks to a few months, suitable for capturing the long-term trend or gradual degradation of the device. Each window corresponds to a time period, and the data in the window will be subjected to trend analysis in the next step.

[0043] Step S202, performing short-term trend analysis on the health time series within each preset short-term window to obtain short-term trend data; wherein the short-term trend data includes a short-term trend slope and a short-term health average value; Specifically, the data in each short-term window usually includes several continuous health data points. In some embodiments, a time series analysis method (such as least squares fitting, linear regression, difference method, etc.) can be used to perform trend analysis on the data in the short-term window. The linear regression method is used to calculate the changing trend of the health data in the short-term window to obtain the short-term trend slope, which represents the rate of change of the health of the device in the short-term window (i.e., the rate at which the health increases or decreases). At the same time, the mean of the health values ​​in the window is calculated to reflect the average health status of the device in this time period.

[0044] Step S203, performing a long-term trend analysis on the health time series within each preset long-term window to obtain long-term trend data; wherein the long-term trend data includes a long-term trend slope and a long-term health average value; Specifically, the health data in each long-term window usually includes health changes over a longer period of time. In some embodiments, linear regression or time series analysis methods can be used to perform trend analysis on the data in the long-term window to calculate the long-term change trend of the equipment health. Through linear regression analysis, the rate of change of the health data in the long-term window (i.e., the long-term trend slope) is calculated to reflect the degradation or improvement trend of the equipment health in the long-term operation. At the same time, the mean of the health in the window is calculated to reflect the overall health status of the equipment in the long term.

[0045] Step S204, combining the short-term trend data and the long-term trend data to obtain trend analysis results.

[0046] Among them, the short-term trend data is combined with the long-term trend data for analysis to comprehensively evaluate the operating status of the equipment. If the short-term trend slope shows a rapid decline, while the long-term trend slope remains stable or slightly declines, it may indicate that the equipment has a temporary failure or abnormal fluctuation, and an immediate inspection is required; if the long-term trend slope continues to decline, it may indicate that the equipment has long-term degradation and maintains a trend of low health value, and in-depth maintenance should be carried out.

[0047] In the above implementation, the short-term and long-term trend analysis of the health time series based on the sliding window method can comprehensively evaluate the health status of oilfield operating equipment. In the short term, the system can timely capture sudden abnormalities and fluctuations of the equipment and provide early warnings; in terms of long-term trends, it can identify the continuous degradation trend of the equipment and help decision makers predict future failure risks. By combining short-term and long-term trend data, the system can comprehensively analyze the health status of the equipment, provide strong data support for equipment maintenance and optimization decisions, and ultimately improve the safety and operating efficiency of the equipment and reduce maintenance costs and failure risks.

[0048] Reference Figure 3 As a further implementation of the remote monitoring method, after the step of sending the maintenance prompt information to the maintenance terminal through the remote communication module, it also includes: Step S301, receiving a maintenance completion feedback signal sent by a maintenance terminal; Among them, the maintenance completion feedback signal is usually transmitted from the maintenance terminal to the system through the remote communication module, indicating that the equipment maintenance has been completed, the status of the equipment has been restored or necessary repairs have been made.

[0049] Step S302, in response to the maintenance completion feedback signal, obtaining the operating status data of the oilfield operation equipment after the maintenance is completed and analyzing it based on the health model to obtain a health time series after the maintenance is completed; The system re-collects the equipment's operating status data through deployed sensors and remote communication modules to ensure that the equipment status data after maintenance is obtained. The acquired post-maintenance data is input into the health model to calculate the health value. The calculation method of the model is the same as the previous steps. The signal characteristics of the key parts of each device (such as frequency domain analysis of vibration signals, temperature change rate, etc.) are used to analyze the equipment health status and obtain a new health time series.

[0050] Step S303, comparing the health time series before and after maintenance, and calculating the maintenance effect score; Among them, the health time series before maintenance is compared and analyzed with the health time series after maintenance. Specifically, the improvement effect of the equipment can be evaluated by calculating the difference in health values ​​and the changing trend of the health curve.

[0051] For example, by calculating the difference between the health values ​​before and after maintenance, or calculating the fluctuation range of health within the same time window, a preliminary evaluation index of the maintenance effect can be obtained. In addition, by comparing the changing trend of health before and after maintenance, it can be checked whether the maintenance has improved the stability of the health of the equipment and whether it has returned to the expected normal level.

[0052] Step S304, determine whether the maintenance effect score is lower than the preset score standard; if not, jump to step S305; if yes, jump to step S306; Among them, the maintenance effect score is compared with the preset scoring standard to determine whether the maintenance has achieved the expected effect. For example, the preset scoring standard may stipulate that the improvement of equipment health must exceed a certain threshold, or the health volatility must be reduced to below a certain value. If the effect score is lower than the preset standard, it means that the maintenance has not achieved the expected effect and re-inspection or repair may be required.

[0053] Step S305, determine that the maintenance effect is qualified, and feedback maintenance completion information; Among them, when the maintenance effect score meets the preset standard, the system confirms that the maintenance effect is qualified and feedbacks the "maintenance end" information to the maintenance terminal or management personnel, indicating that the equipment has resumed normal operation, the maintenance work has been completed, and the equipment can continue to be put into use.

[0054] Step S306, determining that the maintenance effect is unqualified, and sending maintenance verification information to the management terminal.

[0055] If the maintenance effect score is lower than the preset standard, the system determines that the maintenance effect is unqualified, and then generates "maintenance verification information" and sends it to the management terminal held by the manager through the remote communication module. After receiving this information, the manager can further check the problem based on the current status and historical data of the equipment and decide whether to arrange maintenance again or other remedial measures.

[0056] It is understandable that through the automated verification and feedback mechanism, the system can promptly detect maintenance failures and issue warnings to managers through clear feedback, ensuring quality control of equipment maintenance work and safeguarding the normal operation of equipment.

[0057] In the above implementation mode, the system determines whether the maintenance effect is qualified according to the preset standards. If qualified, the system confirms the completion of maintenance and feedback is given to relevant personnel. If unqualified, the system automatically generates maintenance verification information and sends it to the management terminal, thereby realizing intelligent evaluation and timely feedback of equipment maintenance effects. While ensuring the long-term stable operation of the equipment, it can improve the efficiency of equipment management and reduce the risk of equipment failure due to inadequate maintenance.

[0058] Reference Figure 4 As an implementation method of step S303, the steps of comparing the health time series before maintenance and after maintenance, and calculating the maintenance effect score include: Step S401, calculating the health characteristic values ​​before and after maintenance respectively according to the health time series before and after maintenance; In some embodiments, whether it is the health time series before or after maintenance, health characteristic values ​​that can reflect the overall trend can be extracted, such as the time series mean, the time series weighted mean, the time series peak, the time series end value, etc.

[0059] It is understandable that if the health time series fluctuates violently, the weighted mean or final value can be used as the representative value to reduce the impact of noise on the score calculation; if the health time series shows a relatively smooth trend (such as gradual increase or decrease), the time series mean can be used directly. If the health of the equipment fluctuates greatly before and after maintenance, the segmented mean method can be used to divide the time series into multiple intervals, calculate the characteristic values ​​separately, and take the weighted result as the final value.

[0060] Step S402, based on the preset ideal health, the corresponding maintenance effect score E is calculated by combining the health characteristic values ​​before and after maintenance: In the above formula, H post H is the health characteristic value after maintenance is completed. pre is the health characteristic value before maintenance, Hideal To preset the ideal health level.

[0061] In the above implementation, the health time series before and after maintenance is converted into characteristic values, which solves the problem of mismatch between the health time series and the specific values, while retaining the main trend information of the time series. Through the calculation and determination of maintenance effect scores, the system realizes the automatic analysis and feedback of maintenance effects, significantly improves the intelligence and accuracy of equipment management, and provides strong support for the long-term safe and efficient operation of equipment.

[0062] The embodiment of the present application also discloses a remote monitoring system for oilfield operation equipment.

[0063] A remote monitoring system for oilfield operation equipment, the remote monitoring system comprising: The operating status data receiving module is used to receive the operating status data of each key part of the oilfield operation equipment collected in real time; the operating status data includes vibration signals, temperature signals, current signals and pressure signals; A data preprocessing module, used for preprocessing the running status data; The time series extraction module is used to extract the time series features related to the equipment status from the pre-processed operation status data and perform normalization processing to generate a time series feature set; The health analysis module is used to analyze the time series feature set based on the pre-built health model, calculate the health value of the time series feature at each time point, and generate the health time series of oilfield operation equipment; The abnormal feature recognition module is used to perform dynamic segmentation analysis on the health time series, mark the time series features whose health value drops beyond a preset threshold as abnormal features, and determine the severity level of the abnormal features according to the drop amplitude; The trend analysis module is used to perform long-term and short-term trend analysis on the health time series based on the sliding window method and calculate the trend analysis results; The comprehensive risk scoring module is used to perform correlation analysis based on trend analysis results and abnormal characteristics and calculate the corresponding comprehensive risk score; The maintenance reminder module is used to match the corresponding warning level and maintenance strategy according to the comprehensive risk score, and send maintenance reminder information to the maintenance terminal through the remote communication module.

[0064] In the above implementation, real-time dynamic monitoring of equipment performance is achieved through multi-dimensional data collection, preprocessing, time series feature extraction, health analysis, and accurate identification of abnormal features of the operating status of oilfield operating equipment. Based on the long-term and short-term trend analysis and comprehensive risk scoring module of the sliding window method, the system can effectively evaluate the changing trend of the equipment health status, accurately capture the short-term fluctuations and long-term degradation of the equipment, and achieve efficient maintenance prompts and feedback, providing strong technical support for the safety, continuity and economy of oilfield equipment, significantly reducing the risk of unplanned downtime, and improving the overall management efficiency and operational reliability of oilfield equipment.

[0065] As a further implementation of the remote monitoring system, the remote monitoring system further includes: A signal receiving module, used for receiving a maintenance completion feedback signal sent by a maintenance terminal; A health analysis module is used to respond to the maintenance completion feedback signal, obtain the operating status data of the oilfield operation equipment after the maintenance is completed, and analyze it based on the health model to obtain the health time series after the maintenance is completed; The maintenance effect scoring module is used to compare the health time series before and after maintenance to calculate the maintenance effect score; The judgment module is used to judge whether the maintenance effect score is lower than the preset score standard; if not, output the maintenance effect qualified result; if so, output the maintenance effect unqualified result; A maintenance feedback module is used to feedback maintenance completion information in response to a qualified maintenance result; The maintenance verification module is used to send maintenance verification information to the management terminal in response to an unqualified maintenance effect result.

[0066] A remote monitoring system for oilfield operating equipment in an embodiment of the present application can implement any of the above-mentioned remote monitoring methods, and the specific working process of each module in the remote monitoring system can refer to the corresponding process in the above-mentioned method embodiment.

[0067] In the several embodiments provided in this application, it should be understood that the provided methods and systems can be implemented in other ways. For example, the system embodiments described above are only illustrative; for example, the division of a certain module is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0068] The embodiment of the present application also discloses a computer device.

[0069] The computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, a remote monitoring method for oilfield operation equipment as described above is implemented.

[0070] The embodiment of the present application also discloses a computer-readable storage medium.

[0071] A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any one of the above-mentioned remote monitoring methods for oilfield operation equipment.

[0072] Among them, computer-readable storage media can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus or device; the program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0073] It should be noted that in the above embodiments, the description of each embodiment has different emphases, and for the parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0074] The above are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

Claims

1. A remote monitoring method for oilfield operation equipment, characterized in that: The remote monitoring method comprises: Receive real-time collected operating status data of various key parts of oilfield operating equipment; the operating status data includes vibration signals, temperature signals, current signals and pressure signals; Performing data preprocessing on the operating status data; Extracting time series features related to equipment status from preprocessed operating status data and performing normalization processing to generate a time series feature set; Analyzing the time series feature set based on a pre-built health model, calculating the health value of the time series feature at each time point, and generating a health time series of the oilfield operation equipment; Performing dynamic segmentation analysis on the health time series, marking the time series features whose health value drops beyond a preset threshold as abnormal features, and determining the severity level of the abnormal features according to the drop amplitude; Based on the sliding window method, the long-term and short-term trend analysis of the health time series is performed to calculate the trend analysis result; Perform correlation analysis based on the trend analysis results and the abnormal characteristics to calculate a corresponding comprehensive risk score; The corresponding warning level and maintenance strategy are matched according to the comprehensive risk score, and maintenance reminder information is sent to the maintenance terminal through the remote communication module.

2. A remote monitoring method for oilfield operation equipment according to claim 1, characterized in that: The calculation formula of the health model is: Among them, H(t) is the health value at time t, f i (t) is the normalized eigenvalue, α i is the feature weight, which indicates the influence of different features on the health status of the device.

3. A remote monitoring method for oilfield operation equipment according to claim 1, characterized in that: The steps of performing long-term and short-term trend analysis on the health time series based on the sliding window method and calculating the trend analysis result include: Performing segmentation processing on the health time series based on a preset short-term window and a preset long-term window respectively; Performing short-term trend analysis on the health time series within each of the preset short-term windows to obtain short-term trend data; wherein the short-term trend data includes a short-term trend slope and a short-term health average value; Performing a long-term trend analysis on the health time series within each of the preset long-term windows to obtain long-term trend data; wherein the long-term trend data includes a long-term trend slope and a long-term health average value; The short-term trend data and the long-term trend data are combined to obtain a trend analysis result.

4. A remote monitoring method for oilfield operation equipment according to claim 3, characterized in that: The calculation formula of the comprehensive risk score is: R(t)=β1S short +β2S long +γ·abnormality(t); In the above formula, S short is the short-term trend slope, S long is the long-term trend slope, abnormality(t) is the severity of the abnormal feature, and β1, β2, and γ are weight coefficients.

5. A remote monitoring method for oilfield operation equipment according to any one of claims 1 to 4, characterized in that: After the step of sending the maintenance prompt information to the maintenance terminal through the remote communication module, the method further includes: Receiving a maintenance completion feedback signal sent by a maintenance terminal; In response to the maintenance completion feedback signal, obtaining the operating status data of the oilfield operation equipment after the maintenance is completed and analyzing it based on the health model to obtain a health time series after the maintenance is completed; Compare the health time series before and after maintenance, and calculate the maintenance effect score; Determine whether the maintenance effect score is lower than a preset score standard; If not, the maintenance effect is determined to be qualified, and the maintenance end information is fed back; If so, it is determined that the maintenance effect is unsatisfactory, and a maintenance verification message is sent to the management terminal.

6. A remote monitoring method for oilfield operation equipment according to claim 5, characterized in that: The steps of comparing the health time series before and after maintenance and calculating the maintenance effect score include: According to the health time series before and after the maintenance, the health characteristic values ​​before and after the maintenance are calculated respectively; Based on the preset ideal health, the corresponding maintenance effect score E is calculated by combining the health characteristic values ​​before and after maintenance: In the above formula, H post H is the health characteristic value after maintenance is completed. pre is the health characteristic value before maintenance, H ideal To preset the ideal health level.

7. A remote monitoring system for oilfield operation equipment, characterized in that: The remote monitoring system comprises: An operation status data receiving module is used to receive the operation status data of each key part of the oilfield operation equipment collected in real time; the operation status data includes vibration signals, temperature signals, current signals and pressure signals; A data preprocessing module, used for performing data preprocessing on the operating status data; The time series extraction module is used to extract the time series features related to the equipment status from the pre-processed operation status data and perform normalization processing to generate a time series feature set; A health analysis module, used to analyze the time series feature set based on a pre-built health model, calculate the health value of the time series feature at each time point, and generate a health time series of the oilfield operation equipment; An abnormal feature identification module is used to perform dynamic segmentation analysis on the health time series, mark the time series features whose health value drops beyond a preset threshold as abnormal features, and determine the severity level of the abnormal features according to the drop amplitude; a trend analysis module is used to perform long-term and short-term trend analysis on the health time series based on a sliding window method, and calculate the trend analysis results; A comprehensive risk scoring module, used to perform correlation analysis based on the trend analysis results and the abnormal characteristics, and calculate the corresponding comprehensive risk score; The maintenance prompt module is used to match the corresponding warning level and maintenance strategy according to the comprehensive risk score, and send maintenance prompt information to the maintenance terminal through the remote communication module.

8. A remote monitoring system for oilfield operation equipment according to claim 7, characterized in that: The remote monitoring system also includes: A signal receiving module, used for receiving a maintenance completion feedback signal sent by a maintenance terminal; A health analysis module, configured to respond to the maintenance completion feedback signal, obtain the operating status data of the oilfield operation equipment after the maintenance is completed and analyze it based on the health model to obtain a health time series after the maintenance is completed; The maintenance effect scoring module is used to compare the health time series before and after maintenance to calculate the maintenance effect score; A judgment module is used to judge whether the maintenance effect score is lower than a preset score standard; if not, output a maintenance effect qualified result; if so, output a maintenance effect unqualified result; A maintenance feedback module, used for feeding back maintenance completion information in response to the qualified maintenance effect result; The maintenance verification module is used to send maintenance verification information to the management terminal in response to the unqualified maintenance effect result.

9. A computer device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 6.

Images