Operation and maintenance management system and device combining real-time data display and AI trend prediction

Abstract

The application discloses an operation and maintenance management system and device combining real-time data display and AI trend prediction, belongs to the technical field of oilfield gathering pipeline operation and maintenance management, and comprises a data acquisition module, a pipeline pairing module, an abnormal trend analysis and positioning module and a pipeline maintenance management module; the data acquisition module comprises ultrasonic thickness measurement sensors and humidity sensors, is used to acquire real-time thickness data and external soil humidity data of the oilfield gathering pipeline, and collects specification parameters of the oilfield gathering pipeline and transmits the specification parameters to subsequent modules. The operation and maintenance management system and device combining real-time data display and AI trend prediction construct an efficient and intelligent pipeline operation and maintenance management platform through combination of multi-sensor data acquisition, AI trend prediction, dynamic grouping management and intelligent maintenance management, and solve the problems of data lag, insufficient prediction capability and inflexible resource allocation in traditional oilfield gathering pipeline management.

Description

Technical Field

[0001] This invention belongs to the field of oilfield gathering and transportation pipeline operation and maintenance management technology, specifically an operation and maintenance management system and device that combines real-time data display and AI trend prediction. Background Technology

[0002] Oilfield gathering and transportation pipelines are an important part of oilfield surface engineering. They are mainly used to collect the mixture of crude oil, natural gas and produced water extracted from oil wells and transport it to centralized processing sites such as joint stations and processing plants for subsequent processing such as oil-gas-water separation, purification and processing. Therefore, the safe and stable operation of gathering and transportation pipelines is crucial in oilfield production and operation.

[0003] Traditional oilfield gathering and transportation pipeline operation and maintenance management often uses a uniform judgment standard to monitor pipeline corrosion. This can easily overlook potential anomalies under different actual operating conditions, making it impossible to accurately monitor and judge pipeline anomalies. This makes it difficult to achieve efficient pipeline operation and maintenance management. At the same time, it lacks the ability to dynamically adjust according to the real-time status of the pipeline, resulting in low efficiency in resource management and allocation, and problems with practicality and functionality.

[0004] In response to the above, this case proposes an operation and maintenance management system and device that combines real-time data display with AI trend prediction to solve the aforementioned technical problems. Summary of the Invention

[0005] This invention aims to at least solve one of the technical problems existing in the prior art. To this end, this invention proposes an operation and maintenance management system and device that combines real-time data display and AI trend prediction, thereby solving the aforementioned technical problem by improving detection and processing methods.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] An operation and maintenance management system that combines real-time data display and AI trend prediction includes a data acquisition module, a pipeline matching module, an anomaly trend analysis and location module, and a pipeline maintenance management module.

[0008] The data acquisition module includes an ultrasonic thickness sensor and a humidity sensor, used to collect real-time thickness data of the oilfield gathering and transportation pipeline and external soil humidity data, and to collect the specification parameters of the oilfield gathering and transportation pipeline and transmit them to subsequent modules.

[0009] The pipeline pairing module calculates the corrosion depth of different oilfield gathering and transportation pipelines based on the specifications and real-time thickness data of the oilfield gathering and transportation pipelines. Based on the corrosion depth of different oilfield gathering and transportation pipelines, it sets a grouping range to group the oilfield gathering and transportation pipelines to obtain secondary groups, and displays the oilfield gathering and transportation pipeline data in real time during transportation.

[0010] The abnormal trend analysis and location module, based on the abnormal corrosion depth growth and corrosion rate changes of oilfield gathering and transportation pipelines in different subgroups, uses the isolated forest method to predict the abnormal corrosion trend of pipelines to identify abnormal pipelines in the same group. At the same time, based on the soil moisture data outside the oilfield gathering and transportation pipelines, it analyzes the leaking oilfield gathering and transportation pipelines and locates the abnormal location.

[0011] The pipeline maintenance management module records and marks the abnormal locations of the identified abnormal oilfield gathering and transportation pipelines, and retransmits the grouping signal into the pipeline pairing module after the abnormal pipeline is maintained for pipeline regrouping.

[0012] Furthermore, the data acquisition module includes an ultrasonic thickness sensor and a humidity sensor, used to acquire real-time thickness data of the oilfield gathering and transportation pipeline and external soil moisture data, and to collect the specification parameters of the oilfield gathering and transportation pipeline and transmit them to subsequent modules, including the following steps:

[0013] Ultrasonic thickness sensors were installed at key locations on all oilfield gathering and transportation pipelines under its jurisdiction. These key locations included the pipeline inlet, pipeline outlet, pipeline middle, pipeline inlet to the middle half, and pipeline middle to the outlet half. Real-time thickness data of key locations on the oilfield gathering and transportation pipelines were collected. At the same time, humidity sensors were installed at equal intervals outside the oilfield gathering and transportation pipelines to collect real-time soil moisture data outside the pipelines.

[0014] Collect the wall thickness specifications and basic information of the oilfield gathering and transportation pipelines, and combine them with real-time thickness data of key locations of the oilfield gathering and transportation pipelines and soil moisture data outside the pipelines, and transmit them to subsequent modules.

[0015] Furthermore, the pipeline pairing module calculates the corrosion depth of different oilfield gathering and transportation pipelines based on their specifications and real-time thickness data. Based on these corrosion depths, it sets grouping ranges to group the oilfield gathering and transportation pipelines into secondary groups and displays the data on the oilfield gathering and transportation pipelines during transportation in real time. The specific steps are as follows:

[0016] Based on PostgreSQL, archives for each oilfield gathering and transportation pipeline are established. The archives include basic information, number, wall thickness specifications, real-time thickness data at key locations, and humidity sensor locations for the oilfield gathering and transportation pipeline. Category groups are also established, including inlet group, outlet group, intermediate group, first half group, and last half group.

[0017] The corrosion depth of each key location in the gathering and transportation pipelines of different oil fields is calculated. Based on the corrosion depth data of each key location in the gathering and transportation pipelines of all subordinate oil fields, the division range is set and a subgroup is established in each category group. The pipeline files that meet the conditions are divided into the corresponding subgroup.

[0018] The system transmits real-time wall thickness data of key locations in the archives of various oilfield gathering and transportation pipelines to an external display for real-time data presentation.

[0019] Furthermore, the step of calculating the corrosion depth at various key locations of different oilfield gathering and transportation pipelines, and based on the corrosion depth data at various key locations of all subordinate oilfield gathering and transportation pipelines, setting a classification range, establishing subgroups within each category group, and classifying eligible pipeline files into the corresponding subgroups includes the following steps:

[0020] The corrosion depth at various key locations in the gathering and transportation pipelines of different oilfields is calculated, including the pipeline inlet, pipeline outlet, pipeline midpoint, the point from the inlet to the midpoint, and the point from the midpoint to the outlet midpoint. The algorithm formula is as follows:

[0021]

[0022] Where n represents the oilfield gathering and transportation pipeline number, and i represents the critical location of the oilfield gathering and transportation pipeline. The wall thickness specifications for the oilfield gathering and transportation pipeline with the designation number n are shown. This represents the real-time thickness data at the i-th critical location of the oilfield gathering and transportation pipeline, numbered n. The corrosion depth represents the i-th critical location in the oilfield gathering and transportation pipeline numbered n.

[0023] Obtain corrosion depth data for key locations on all subordinate oilfield gathering and transportation pipelines, including pipeline inlets, pipeline outlets, pipeline midpoints, the section from inlet to the midpoint, and the section from the midpoint to the outlet midpoint. Create datasets based on pipeline numbers for each location.

[0024]

[0025] Where H1, H2, H3, H4, and H5 represent the pipeline inlet corrosion depth dataset, the pipeline outlet corrosion depth dataset, the pipeline middle corrosion depth dataset, the pipeline inlet to the middle half corrosion depth dataset, and the pipeline middle to the outlet half corrosion depth dataset, respectively, and n represents the oilfield gathering and transportation pipeline number.

[0026] Sort the data in H1, H2, H3, H4, and H5 in ascending order. Based on the difference between the maximum and minimum corrosion depth values ​​in each dataset, obtain the interval of each dataset. Divide each dataset into N equal-width intervals. For corrosion depth values ​​in different datasets, divide the data into equal-width intervals within the corresponding dataset according to the size of the corrosion depth values.

[0027] Based on the equal-width intervals divided in H1, H2, H3, H4, and H5, a corresponding number of secondary groups are established in the inlet group, outlet group, middle group, first half group, and last half group, based on the number of equal-width intervals. The oilfield gathering and transportation pipeline files corresponding to the data in each equal-width interval are then divided into the secondary groups established for the corresponding equal-width intervals.

[0028] Furthermore, the abnormal trend analysis and location module, based on the abnormal corrosion depth growth and corrosion rate changes of oilfield gathering and transportation pipelines within different sub-groups, combines AI technology to predict abnormal corrosion trends in the pipelines to identify abnormal pipelines within the same group. Simultaneously, based on external soil moisture data of the oilfield gathering and transportation pipelines, it analyzes leaking oilfield gathering and transportation pipelines and locates the abnormal positions. The specific steps are as follows:

[0029] Data is extracted from the oilfield gathering and transportation pipeline archives in each subgroup. Based on the time interval T, the pipeline data in the subgroup is extracted P times consecutively to obtain the corrosion depth change and corrosion rate. AI technology is used to predict abnormal corrosion trends and identify abnormal pipelines.

[0030] Based on the operating time of the oilfield gathering and transportation pipeline, combined with the soil moisture data outside the pipeline, the leaking oilfield gathering and transportation pipeline was analyzed and identified, and the location of the pipeline anomaly was determined. The specific steps are as follows:

[0031] Based on the start-up and shutdown times of the oilfield gathering and transportation pipeline, external soil moisture data were collected at different sensors before and after pipeline operation, and the change in moisture was calculated.

[0032] Humidity change = Humidity after pipeline operation - Initial humidity;

[0033] If the humidity change exceeds the soil humidity change threshold during five consecutive pipeline operations, it indicates that the soil humidity data at the current sensor measurement location is abnormal, and the abnormal signal is transmitted to the subsequent modules.

[0034] Furthermore, the process of extracting data from the oilfield gathering and transportation pipeline archives within each secondary group involves extracting the pipeline data within the secondary group P times consecutively based on a time interval T, obtaining the changes in corrosion depth and corrosion rate, and combining this with AI technology to predict abnormal corrosion trends and identify abnormal pipelines. This includes the following steps:

[0035] Based on a time interval T, continuous data extraction is performed P times on the archives within each subgroup. The change in corrosion depth and corrosion rate of the corresponding oilfield gathering and transportation pipeline are calculated for each archive in each extraction. The specific algorithm formula is as follows:

[0036]

[0037] in, This represents the change in corrosion depth at the i-th critical location of the oilfield gathering and transportation pipeline numbered n within a single time interval T. These represent the corrosion depth at the i-th critical location of the oilfield gathering and transportation pipeline numbered n after time interval T and the corrosion depth at the i-th critical location of the oilfield gathering and transportation pipeline numbered n before time interval T, respectively.

[0038]

[0039] Where, φ i n The corrosion depth change rate represents the rate of change of corrosion depth at the i-th critical location of the oilfield gathering and transportation pipeline numbered n within a single time interval T. Based on the corrosion depth change and corrosion rate extracted in P consecutive data sessions, the mean values ​​of different files within the same subgroup during the continuous data extraction process are calculated. and standard deviation Simultaneously, the mean change in total corrosion depth and the mean total corrosion rate μ of the secondary group after continuous extraction were calculated. C μ φ ;

[0040] Calculate the T-statistics of corrosion depth change and corrosion rate for each file in the secondary group, using the following formula:

[0041]

[0042] in, The statistic T represents the rate of change of corrosion depth at the i-th critical location of the oilfield gathering and transportation pipeline numbered n. The corrosion rate T statistic of the i-th critical location in the oilfield gathering and transportation pipeline with number n is used. Based on the degrees of freedom P-1 and a significance level of 0.05, the critical value Ω of the corrosion depth change rate is obtained by looking up the T distribution table. C With the critical value of corrosion rate Ω φ Determine the abnormality of the pipeline:

[0043] when or When this occurs, it indicates that the current file, compared to other files in its subgroup, exhibits an abnormal rate of change in corrosion depth or corrosion rate, and an abnormal signal is transmitted to the pipeline maintenance management module.

[0044] By combining the isolated forest method to summarize the data extracted from all key locations of the pipeline in 5 consecutive iterations, abnormal corrosion trends of the pipeline are predicted. The specific steps are as follows:

[0045] Corrosion rate data points were collected from 5P samples at different key locations of all pipelines under its jurisdiction. Random binary trees were constructed, and each tree recursively split the data points to the leaf nodes by randomly selecting a feature and a splitting value.

[0046] For each data point x z Calculate its average path length h(x) across all isolated trees. z ), and calculate the outlier score for each data point.

[0047]

[0048] Where c(5P) is the normalized path length, E(h(x) z )) represents data point x z Average path length across all isolated trees, based on anomaly score threshold outlier score for each data point Make a judgment:

[0049] when This indicates that the current data point is an outlier. The total number of outliers τ within the current 5P pipeline is calculated, and this is combined with the outlier count threshold θ. max With θ min Determine the current corrosion trend of the pipeline:

[0050] When τ < θ min When the current pipeline corrosion rate is abnormal, it indicates that the number of abnormal points is small and the corrosion trend is excellent.

[0051] When θ min ≤τ≤θ max When the current pipeline corrosion rate is abnormal, the number of abnormal points is normal and the corrosion trend is stable.

[0052] When τ>θ max When the value is high, it indicates that there are many abnormal points in the current pipeline corrosion rate, and the corrosion trend is dangerous.

[0053] Furthermore, the pipeline maintenance management module records and marks the abnormal locations of identified abnormal oilfield gathering and transportation pipelines. After maintenance of the abnormal pipelines, it retransmits the grouping signal into the pipeline pairing module for pipeline regrouping. The specific steps are as follows:

[0054] In response to abnormal soil moisture data, the locations of moisture sensors at the abnormal points are marked in red in the oilfield gathering and transportation pipeline archives.

[0055] For abnormal corrosion depth change rate or abnormal corrosion rate change rate, the relevant oilfield gathering and transportation pipeline files are marked in purple.

[0056] For oilfield gathering and transportation pipelines identified as having a risk of corrosion, the relevant oilfield gathering and transportation pipeline files are marked in yellow.

[0057] After abnormal pipeline maintenance, i.e. after all abnormal color marks are cleared, the grouping signal is retransmitted into the pipeline pairing module for oilfield gathering and transportation pipeline regrouping.

[0058] The operation and maintenance management device combining real-time data display and AI trend prediction is applied in the operation and maintenance management system combining real-time data display and AI trend prediction. It includes a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the operation and maintenance management system combining real-time data display and AI trend prediction as described in this invention.

[0059] Compared with the prior art, the beneficial effects of the present invention are:

[0060] 1. In this invention, by grouping and matching the corrosion depth of key locations in oilfield gathering and transportation pipelines, and combining the corrosion depth variation and corrosion rate of different subgroups, the pipelines under similar corrosion conditions are judged to be abnormal within the group, avoiding the potential omission of abnormalities under a unified judgment standard, and achieving more accurate corrosion monitoring and more efficient pipeline operation and maintenance management.

[0061] 2. In this invention, the pipeline pairing module calculates the corrosion depth and dynamically groups the pipelines, which can adjust the management strategy according to the real-time status of the pipelines, enabling the system to manage and allocate resources more efficiently. The pipeline maintenance management module retransmits the grouping signal after pipeline maintenance, realizing dynamic regrouping of the pipelines and ensuring that the status of the pipelines after maintenance can be updated to the system in a timely manner, avoiding monitoring loopholes caused by the lag in maintenance information.

[0062] 3. In this invention, the abnormal corrosion data of pipelines in different groups are judged based on the dynamic grouping results, the corrosion trend of each group of pipelines is analyzed in a targeted manner, the change law of corrosion rate is identified and normal corrosion and abnormal corrosion are distinguished, and the pipeline anomalies are monitored in combination with external soil moisture data, which enhances the practicality and functionality.

[0063] 4. In this invention, by combining AI technology to analyze the trend of pipeline corrosion rate, stable and unstable pipelines are identified, and pipelines under different abnormal conditions are distinguished and marked in the file, which facilitates the operation and maintenance management of oilfield gathering and transportation pipelines by managers, assists managers in making more scientific and accurate decisions, and improves operation and maintenance efficiency.

[0064] This invention provides an operation and maintenance management system and device that combines real-time data display and AI trend prediction. By combining multi-sensor data acquisition, AI trend prediction, dynamic group management and intelligent maintenance management, it constructs an efficient and intelligent pipeline operation and maintenance management platform, solving the problems of data lag, insufficient prediction capabilities and inflexible resource allocation in traditional oilfield gathering and transportation pipeline management. Attached Figure Description

[0065] Figure 1 This is a block diagram of the operation and maintenance management system that combines real-time data display and AI trend prediction according to the present invention. Detailed Implementation

[0066] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0067] Example 1:

[0068] like Figure 1 As shown, the operation and maintenance management system, which combines real-time data display and AI trend prediction, includes a data acquisition module, a pipeline matching module, an anomaly trend analysis and location module, and a pipeline maintenance management module.

[0069] The data acquisition module, including an ultrasonic thickness sensor and a humidity sensor, is used to collect real-time thickness data of the oilfield gathering and transportation pipeline and external soil moisture data, and to collect the specification parameters of the oilfield gathering and transportation pipeline and transmit them to subsequent modules, including the following steps:

[0070] Ultrasonic thickness sensors were installed at key locations on all oilfield gathering and transportation pipelines under its jurisdiction. These key locations included the pipeline inlet, pipeline outlet, pipeline middle, pipeline inlet to the middle half, and pipeline middle to the outlet half. Real-time thickness data of key locations on the oilfield gathering and transportation pipelines were collected. At the same time, humidity sensors were installed at equal intervals outside the oilfield gathering and transportation pipelines to collect real-time soil moisture data outside the pipelines.

[0071] It should be noted that by collecting data from ultrasonic thickness sensors at key locations of the subordinate oilfield gathering and transportation pipelines, dynamic grouping and anomaly detection can be performed on the subordinate oilfield gathering and transportation pipelines based on the corrosion status of different key locations. Humidity sensors are usually installed at 75 meters, but the distance can be increased or decreased according to actual usage needs. By adjusting the distance of the humidity sensors, the accuracy of external leakage detection can be increased or decreased.

[0072] Collect the wall thickness specifications and basic information of the oilfield gathering and transportation pipelines, and combine them with real-time thickness data of key locations of the oilfield gathering and transportation pipelines and soil moisture data outside the pipelines, and transmit them to subsequent modules.

[0073] It should be noted that the collected oilfield gathering and transportation pipeline wall thickness specifications, real-time thickness data at key locations of the oilfield gathering and transportation pipeline, and external soil moisture data can provide data support for subsequent module data processing to identify abnormal pipelines. Basic information includes the pipeline's location, length, name, etc.

[0074] The pipeline pairing module calculates the corrosion depth of different oilfield gathering and transportation pipelines based on their specifications and real-time thickness data. Based on these corrosion depths, it groups the pipelines into subgroups, setting grouping ranges to obtain secondary groups. The module then displays real-time data on the oilfield gathering and transportation pipelines during transportation. The specific steps are as follows:

[0075] Based on PostgreSQL, archives for each oilfield gathering and transportation pipeline are established. The archives include basic information, number, wall thickness specifications, real-time thickness data at key locations, and humidity sensor locations for the oilfield gathering and transportation pipeline. Category groups are also established, including inlet group, outlet group, intermediate group, first half group, and last half group.

[0076] The corrosion depth of each key location in the gathering and transportation pipelines of different oil fields is calculated. Based on the corrosion depth data of each key location in the gathering and transportation pipelines of all subordinate oil fields, the division range is set and a subgroup is established in each category group. The pipeline files that meet the conditions are divided into the corresponding subgroup.

[0077] It should be noted that the category groups, namely, the import group, the export group, the intermediate group, the first half group, and the last half group, correspond to the pipeline inlet, the pipeline outlet, the pipeline middle, the pipeline from the inlet to the middle half, and the pipeline from the middle to the outlet half, respectively.

[0078] The corrosion depth at various key locations in the gathering and transportation pipelines of different oilfields is calculated, including the pipeline inlet, pipeline outlet, pipeline midpoint, the point from the inlet to the midpoint, and the point from the midpoint to the outlet midpoint. The algorithm formula is as follows:

[0079]

[0080] Where n represents the oilfield gathering and transportation pipeline number, and i represents the critical location of the oilfield gathering and transportation pipeline. The wall thickness specifications for the oilfield gathering and transportation pipeline with the designation number n are shown. This represents the real-time thickness data at the i-th critical location of the oilfield gathering and transportation pipeline, numbered n. The corrosion depth represents the i-th critical location in the oilfield gathering and transportation pipeline numbered n.

[0081] It should be noted that i represents the critical location of the oilfield gathering and transportation pipeline, ranging from 1 to 5, which respectively represent the pipeline inlet, pipeline outlet, pipeline middle, pipeline inlet to the middle half, and pipeline middle to the outlet half. The corrosion depth of the critical location of the oilfield gathering and transportation pipeline is calculated separately, which can facilitate subsequent secondary grouping based on the critical location of the pipeline to identify abnormal pipelines.

[0082] Obtain corrosion depth data for key locations on all subordinate oilfield gathering and transportation pipelines, including pipeline inlets, pipeline outlets, pipeline midpoints, the section from inlet to the midpoint, and the section from the midpoint to the outlet midpoint. Create datasets based on pipeline numbers for each location.

[0083]

[0084] Where H1, H2, H3, H4, and H5 represent the pipeline inlet corrosion depth dataset, the pipeline outlet corrosion depth dataset, the pipeline middle corrosion depth dataset, the pipeline inlet to the middle half corrosion depth dataset, and the pipeline middle to the outlet half corrosion depth dataset, respectively, and n represents the oilfield gathering and transportation pipeline number.

[0085] Sort the data in H1, H2, H3, H4, and H5 in ascending order. Based on the difference between the maximum and minimum corrosion depth values ​​in each dataset, obtain the interval of each dataset. Divide each dataset into N equal-width intervals. For corrosion depth values ​​in different datasets, divide the data into equal-width intervals within the corresponding dataset according to the size of the corrosion depth values.

[0086] It should be noted that the value of the equal-width interval N needs to be determined based on the difference between the maximum and minimum values ​​in the actual dataset. It is usually set to 10, but can also be increased or decreased according to the actual situation. Increasing the number of equal-width intervals can improve the accuracy of subsequent abnormal pipeline identification.

[0087] Based on the equal-width intervals defined in H1, H2, H3, H4, and H5, a corresponding number of secondary groups are established in the inlet group, outlet group, intermediate group, first half group, and last half group, based on the number of equal-width intervals. The oilfield gathering and transportation pipeline files corresponding to the data in each equal-width interval are then assigned to the secondary groups established for that equal-width interval.

[0088] Transmits real-time wall thickness data of key locations in the archives of various oilfield gathering and transportation pipelines to an external display for real-time data display;

[0089] Example 2:

[0090] The anomaly trend analysis and location module, based on the abnormal corrosion depth growth and corrosion rate changes of oilfield gathering and transportation pipelines within different sub-groups, uses the isolated forest method to predict abnormal corrosion trends in pipelines to identify abnormal pipelines within the same group. Simultaneously, based on external soil moisture data of the oilfield gathering and transportation pipelines, it analyzes leaking oilfield gathering and transportation pipelines and locates the anomaly. The specific steps are as follows:

[0091] Data is extracted from the oilfield gathering and transportation pipeline archives in each subgroup. Based on the time interval T, the pipeline data in the subgroup is extracted P times consecutively to obtain the corrosion depth change and corrosion rate. AI technology is used to predict abnormal corrosion trends and identify abnormal pipelines.

[0092] It should be noted that the T-test is used to sample pipeline files within the same subgroup at multiple consecutive equal time intervals, and calculate the mean and standard deviation respectively. Based on this, abnormalities in the change of corrosion depth and corrosion rate are judged, thereby identifying potential problematic pipelines and taking corresponding measures. The value of P is usually set to 5.

[0093] Based on a time interval T, continuous data extraction is performed P times on the archives within each subgroup. The change in corrosion depth and corrosion rate of the corresponding oilfield gathering and transportation pipeline are calculated for each archive in each extraction. The specific algorithm formula is as follows:

[0094]

[0095] in, This represents the change in corrosion depth at the i-th critical location of the oilfield gathering and transportation pipeline numbered n within a single time interval T. These represent the corrosion depth at the i-th critical location of the oilfield gathering and transportation pipeline numbered n after time interval T and the corrosion depth at the i-th critical location of the oilfield gathering and transportation pipeline numbered n before time interval T, respectively.

[0096]

[0097] Where, φ i n The corrosion depth change rate represents the rate of change of corrosion depth at the i-th critical location of the oilfield gathering and transportation pipeline numbered n within a single time interval T. Based on the corrosion depth change and corrosion rate extracted in P consecutive data sessions, the mean values ​​of different files within the same subgroup during the continuous data extraction process are calculated. and standard deviation Simultaneously, the mean change in total corrosion depth and the mean total corrosion rate μ of the secondary group after continuous extraction were calculated. C μ φ ;

[0098] It should be noted that the time interval T is usually set to 48 hours, that is, data is collected once every two days, but it can also be adjusted according to the actual situation.

[0099] Calculate the T-statistics of corrosion depth change and corrosion rate for each file in the secondary group, using the following formula:

[0100]

[0101] in, The statistic T represents the rate of change of corrosion depth at the i-th critical location of the oilfield gathering and transportation pipeline numbered n. The corrosion rate T statistic of the i-th critical location in the oilfield gathering and transportation pipeline with number n is used. Based on the degrees of freedom P-1 and a significance level of 0.05, the critical value Ω of the corrosion depth change rate is obtained by looking up the T distribution table. C With the critical value of corrosion rate Ω φ Determine the abnormality of the pipeline:

[0102] when or When this occurs, it indicates that the current file, compared to other files in its subgroup, exhibits an abnormal rate of change in corrosion depth or corrosion rate, and an abnormal signal is transmitted to the pipeline maintenance management module.

[0103] It should be noted that, under the same corrosion condition grouping conditions, the T-test is used to sample pipeline files within the same subgroup at multiple consecutive equal time intervals, calculate the mean and standard deviation, and use this to identify anomalies in the corrosion depth and corrosion rate changes. This allows for targeted identification of abnormal corrosion changes in pipelines under the same or similar corrosion conditions, avoiding the limitations of judging pipeline anomalies based on an overall threshold, and enhancing the accuracy of anomaly identification. At the same time, identifying anomalies in the corrosion depth and corrosion rate changes of pipelines can help identify potentially abnormal pipelines within the same subgroup.

[0104] By combining the isolated forest method to summarize the data extracted from all key locations of the pipeline in 5 consecutive iterations, abnormal corrosion trends of the pipeline are predicted. The specific steps are as follows:

[0105] Corrosion rate data points were collected from 5P samples at different key locations of all pipelines under its jurisdiction. Random binary trees were constructed, and each tree recursively split the data points to the leaf nodes by randomly selecting a feature and a splitting value.

[0106] For each data point x z Calculate its average path length h(x) across all isolated trees. z ), and calculate the outlier score for each data point.

[0107]

[0108] Where c(5P) is the normalized path length, E(h(x) z )) represents data point x z Average path length across all isolated trees, based on anomaly score threshold outlier score for each data point Make a judgment:

[0109] when This indicates that the current data point is an outlier. The total number of outliers τ within the current 5P pipeline is calculated, and this is combined with the outlier count threshold θ. max With θ min Determine the current corrosion trend of the pipeline:

[0110] When τ < θ min When the current pipeline corrosion rate is abnormal, it indicates that the number of abnormal points is small and the corrosion trend is excellent.

[0111] When θ min ≤τ≤θ max When the current pipeline corrosion rate is abnormal, the number of abnormal points is normal and the corrosion trend is stable.

[0112] When τ>θ max When the value is high, it indicates that there are many abnormal points in the current pipeline corrosion rate, and the corrosion trend is dangerous.

[0113] It should be noted that the isolation forest method is used to determine the total number of outliers within 5P. Based on the number of outliers, the current corrosion rate status of the pipeline can be determined, and an anomaly score threshold can be established. The value ranges from 0.5 to 1, and is usually set to 0.7. The outlier threshold θ max With θ min P and c(5P) is the standardized path length.

[0114] Based on the operating time of the oilfield gathering and transportation pipeline, combined with the soil moisture data outside the pipeline, the leaking oilfield gathering and transportation pipeline was analyzed and identified, and the location of the pipeline anomaly was determined. The specific steps are as follows:

[0115] Based on the start-up and shutdown times of the oilfield gathering and transportation pipeline, external soil moisture data were collected at different sensors before and after pipeline operation, and the change in moisture was calculated.

[0116] Humidity change = Humidity after pipeline operation - Initial humidity;

[0117] If the humidity change exceeds the soil humidity change threshold during five consecutive pipeline operations, it indicates that the soil humidity data at the current sensor measurement location is abnormal, and the abnormal signal is transmitted to the subsequent modules.

[0118] It should be noted that the threshold for soil moisture change needs to be determined based on the normal soil moisture change at different sensor locations. Soil moisture change can help determine anomalies in oilfield gathering and transportation pipelines, and together with corrosion anomaly determination, provide dual protection for oilfield gathering and transportation pipelines.

[0119] The pipeline maintenance management module records and marks the abnormal locations of identified abnormal oilfield gathering and transportation pipelines. After maintenance of the abnormal pipelines, it retransmits the grouping signal into the pipeline pairing module for pipeline regrouping. The specific steps are as follows:

[0120] In response to abnormal soil moisture data, the locations of moisture sensors at the abnormal points are marked in red in the oilfield gathering and transportation pipeline archives.

[0121] For abnormal corrosion depth change rate or abnormal corrosion rate change rate, the relevant oilfield gathering and transportation pipeline files are marked in purple.

[0122] For oilfield gathering and transportation pipelines identified as having a risk of corrosion, the relevant oilfield gathering and transportation pipeline files are marked in yellow.

[0123] After abnormal pipeline maintenance, i.e. after all abnormal color marks are cleared, the grouping signal is retransmitted into the pipeline pairing module for oilfield gathering and transportation pipeline regrouping.

[0124] Example 3:

[0125] An operation and maintenance management device that combines real-time data display and AI trend prediction is applied in an operation and maintenance management system that combines real-time data display and AI trend prediction. It includes a memory, a processor, and a program stored on the memory and executable on the processor. When the processor executes the program, it implements the steps in the operation and maintenance management system that combines real-time data display and AI trend prediction of the present invention.

[0126] In the embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of the method in this embodiment according to actual needs.

[0127] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. An operation and maintenance management system that combines real-time data display with AI trend prediction, characterized in that: It includes a data acquisition module, a pipeline pairing module, an anomaly trend analysis and location module, and a pipeline maintenance and management module; The data acquisition module includes an ultrasonic thickness sensor and a humidity sensor, used to collect real-time thickness data of the oilfield gathering and transportation pipeline and external soil humidity data, and to collect the specification parameters of the oilfield gathering and transportation pipeline and transmit them to subsequent modules. The pipeline pairing module calculates the corrosion depth of different oilfield gathering and transportation pipelines based on the specifications and real-time thickness data of the oilfield gathering and transportation pipelines. Based on the corrosion depth of different oilfield gathering and transportation pipelines, it sets a grouping range to group the oilfield gathering and transportation pipelines to obtain secondary groups, and displays the oilfield gathering and transportation pipeline data in real time during transportation. The abnormal trend analysis and location module, based on the abnormal corrosion depth growth and corrosion rate changes of oilfield gathering and transportation pipelines within different sub-groups, uses the isolated forest method to predict abnormal corrosion trends in pipelines to identify abnormal pipelines within the same group. Simultaneously, based on external soil moisture data of the oilfield gathering and transportation pipelines, it analyzes leaking oilfield gathering and transportation pipelines and locates the abnormal positions. The specific steps are as follows: Data was extracted from the oilfield gathering and transportation pipeline archives within each secondary group, based on time intervals. Continuous processing of pipeline data within the secondary group The process involves two extractions to obtain changes in corrosion depth and corrosion rate. AI technology is then used to predict abnormal corrosion trends and identify abnormal pipelines. The steps include: Based on time interval Continuous data extraction is performed on the files within each subgroup. Each extraction process calculates the change in corrosion depth and corrosion rate for each oilfield gathering and transportation pipeline corresponding to each file. The specific algorithm formula is as follows: ； in, Represents a single time interval Internal number is The first oilfield gathering and transportation pipeline The change in corrosion depth at key locations, They represent time intervals respectively The following number is The first oilfield gathering and transportation pipeline Corrosion depth and time interval at key locations The previous number is The first oilfield gathering and transportation pipeline Corrosion depth at key locations; ； in, Represents a single time interval Internal number is The first oilfield gathering and transportation pipeline The rate of change of corrosion depth at key locations, based on continuous The changes in corrosion depth and corrosion rate extracted each time were used to calculate the mean values ​​of different files within the same secondary group during the continuous data extraction process. , and standard deviation , Simultaneously, the mean change in total corrosion depth and the mean total corrosion rate of the secondary groups after continuous extraction were calculated. , ; Calculate the T-statistics of corrosion depth change and corrosion rate for each file in the secondary group, using the following formula: ； ； in, Representative number is The first oilfield gathering and transportation pipeline The corrosion depth change rate T-statistic at key locations. Representative number is The first oilfield gathering and transportation pipeline Corrosion rate T statistics at key locations, based on degrees of freedom With a significance level of 0.05, the critical value of the rate of change of corrosion depth was obtained by referring to the T-distribution table. With the critical value of corrosion rate Determine the abnormality of the pipeline: when > or > When this occurs, it indicates that the current file, compared to other files in its subgroup, exhibits an abnormal rate of change in corrosion depth or corrosion rate, and an abnormal signal is transmitted to the pipeline maintenance management module. Combining the isolated forest method to continuously analyze all critical locations of the subordinate pipelines The extracted data are summarized to predict abnormal corrosion trends in the pipeline. The specific steps are as follows: Collect data from different key locations of all subordinate pipelines. The corrosion rate data points collected each time are used to construct a random binary tree. Each tree recursively splits the data points to the leaf nodes of the tree by randomly selecting a feature and a random splitting value. For each data point Calculate its average path length across all isolated trees. And calculate the outlier score for each data point. : ； in, To standardize path length, For data points Average path length across all isolated trees, based on anomaly score threshold outlier score for each data point Make a judgment: when > This indicates that the current data point is an outlier, and statistics are being compiled for the current pipeline. Total number of internal outliers Combined with the threshold for the number of outliers and Determine the current corrosion trend of the pipeline: when < When the current pipeline corrosion rate is abnormal, it indicates that the number of abnormal points is small and the corrosion trend is excellent. when ≤ ≤ When the current pipeline corrosion rate is abnormal, the number of abnormal points is normal and the corrosion trend is stable. when > When the corrosion rate is abnormal, it indicates that there are many points with abnormal corrosion rates in the pipeline, and the corrosion trend is dangerous. The pipeline maintenance management module records and marks the abnormal locations of the identified abnormal oilfield gathering and transportation pipelines, and retransmits the grouping signal into the pipeline pairing module after the abnormal pipeline is maintained for pipeline regrouping.

2. The operation and maintenance management system combining real-time data display and AI trend prediction as described in claim 1, characterized in that: The data acquisition module includes an ultrasonic thickness sensor and a humidity sensor, used to acquire real-time thickness data of the oilfield gathering and transportation pipeline and external soil moisture data, and to collect the specification parameters of the oilfield gathering and transportation pipeline and transmit them to subsequent modules, including the following steps: Ultrasonic thickness sensors were installed at key locations on all oilfield gathering and transportation pipelines under its jurisdiction. These key locations included the pipeline inlet, pipeline outlet, pipeline middle, pipeline inlet to the middle half, and pipeline middle to the outlet half. Real-time thickness data of key locations on the oilfield gathering and transportation pipelines were collected. At the same time, humidity sensors were installed at equal intervals outside the oilfield gathering and transportation pipelines to collect real-time soil moisture data outside the pipelines. Collect the wall thickness specifications and basic information of the oilfield gathering and transportation pipelines, and combine them with real-time thickness data of key locations of the oilfield gathering and transportation pipelines and soil moisture data outside the pipelines, and transmit them to subsequent modules.

3. The operation and maintenance management system combining real-time data display and AI trend prediction as described in claim 2, characterized in that: The pipeline pairing module calculates the corrosion depth of different oilfield gathering and transportation pipelines based on their specifications and real-time thickness data. Based on these corrosion depths, it groups the oilfield gathering and transportation pipelines into subgroups, and then displays the data on the oilfield gathering and transportation pipelines during transportation in real time. The specific steps are as follows: based on Files are created for each oilfield gathering and transportation pipeline. The files include basic information, number, wall thickness specifications, real-time thickness data at key locations, and humidity sensor locations for each oilfield gathering and transportation pipeline. Category groups are also created for each category, including inlet group, outlet group, intermediate group, first half group, and last half group. The corrosion depth of each key location in the gathering and transportation pipelines of different oil fields is calculated. Based on the corrosion depth data of each key location in the gathering and transportation pipelines of all subordinate oil fields, the division range is set and a subgroup is established in each category group. The pipeline files that meet the conditions are divided into the corresponding subgroup. The system transmits real-time wall thickness data of key locations in the archives of various oilfield gathering and transportation pipelines to an external display for real-time data presentation.

4. The operation and maintenance management system combining real-time data display and AI trend prediction as described in claim 3, characterized in that: The process involves calculating the corrosion depth at various key locations of gathering and transportation pipelines in different oilfields, and based on the corrosion depth data at various key locations of gathering and transportation pipelines in all subordinate oilfields, setting a classification range and establishing subgroups within each category group. Pipeline files meeting the criteria are then assigned to the corresponding subgroups. This includes the following steps: The corrosion depth at various key locations in the gathering and transportation pipelines of different oilfields is calculated, including the pipeline inlet, pipeline outlet, pipeline midpoint, the point from the inlet to the midpoint, and the point from the midpoint to the outlet midpoint. The algorithm formula is as follows: ； in, Represents the oilfield gathering and transportation pipeline number. Represents a key location in the oilfield gathering and transportation pipeline. Representative number is Oilfield gathering and transportation pipeline wall thickness specifications, Representative number is The first oilfield gathering and transportation pipeline Real-time thickness data at key locations, Representative number is The first oilfield gathering and transportation pipeline Corrosion depth at key locations; Obtain corrosion depth data for key locations on all subordinate oilfield gathering and transportation pipelines, including pipeline inlets, pipeline outlets, pipeline midpoints, the section from inlet to the midpoint, and the section from the midpoint to the outlet midpoint. Create datasets based on pipeline numbers for each location. ； ； ； ； ； in, These represent the corrosion depth datasets for the pipeline inlet, outlet, middle, mid-section, and mid-sections of the pipeline, respectively. Represents the oilfield gathering and transportation pipeline number; right The data in the dataset is sorted in ascending order. Based on the difference between the maximum and minimum corrosion depths in each dataset, an interval is obtained for each dataset, and each dataset is then divided into... For each equal-width interval, the data in different datasets is divided into equal-width intervals according to the size of the corrosion depth value. based on The equal-width intervals are divided into the inlet group, outlet group, middle group, first half group, and last half group. Based on the number of equal-width intervals, a corresponding number of secondary groups are established. The oilfield gathering and transportation pipeline files corresponding to the data in each equal-width interval are then divided into the secondary groups established for the corresponding equal-width intervals.

5. The operation and maintenance management system combining real-time data display and AI trend prediction as described in claim 1, characterized in that: The abnormal trend analysis and location module, based on the abnormal corrosion depth growth and corrosion rate changes of oilfield gathering and transportation pipelines within different sub-groups, combines AI technology to predict abnormal corrosion trends in the pipelines to identify abnormal pipelines within the same group. Simultaneously, based on external soil moisture data of the oilfield gathering and transportation pipelines, it analyzes leaking oilfield gathering and transportation pipelines and locates the abnormal positions. Based on the operating time of the oilfield gathering and transportation pipeline, combined with the soil moisture data outside the pipeline, the leaking oilfield gathering and transportation pipeline was analyzed and identified, and the location of the pipeline anomaly was determined. The specific steps are as follows: Based on the start-up and shutdown times of the oilfield gathering and transportation pipeline, external soil moisture data were collected at different sensors before and after pipeline operation, and the change in moisture was calculated. ； If the humidity change exceeds the soil humidity change threshold during five consecutive pipeline operations, it indicates that the soil humidity data at the current sensor measurement location is abnormal, and the abnormal signal is transmitted to the subsequent modules.

6. The operation and maintenance management system combining real-time data display and AI trend prediction as described in claim 5, characterized in that: The pipeline maintenance management module records and marks the abnormal locations of identified abnormal oilfield gathering and transportation pipelines. After maintenance of the abnormal pipelines, it retransmits the grouping signal into the pipeline pairing module for pipeline regrouping. The specific steps are as follows: In response to abnormal soil moisture data, the locations of moisture sensors at the abnormal points are marked in red in the oilfield gathering and transportation pipeline archives. For abnormal corrosion depth change rate or abnormal corrosion rate change rate, the relevant oilfield gathering and transportation pipeline files are marked in purple. For oilfield gathering and transportation pipelines identified as having a risk of corrosion, the relevant oilfield gathering and transportation pipeline files are marked in yellow. After abnormal pipeline maintenance, i.e. after all abnormal color marks are cleared, the grouping signal is retransmitted into the pipeline pairing module for oilfield gathering and transportation pipeline regrouping.

7. An operation and maintenance management device that combines real-time data display with AI trend prediction, characterized in that, The device is used in an operation and maintenance management system that combines real-time data display and AI trend prediction, and includes a memory and a processor: Memory is used to store computer-readable instructions in a non-transitory manner. Processor, for executing the computer-readable instructions; When the computer-readable instructions are executed by the processor, they perform the system according to any one of claims 1-6.

Images