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

Abstract

The invention discloses an operation and maintenance management system and device combining real-time data display and AI trend prediction, and belongs to the technical field of oil field gathering and transportation pipeline operation and maintenance management, and the system comprises a data acquisition module, a pipeline pairing module, an abnormal trend analysis and positioning module, and a pipeline maintenance management module. And the data acquisition module comprises an ultrasonic thickness measuring sensor and a humidity sensor, and is used for acquiring real-time thickness data and external soil humidity data of the oil field gathering and transportation pipeline, collecting specification parameters of the oil field gathering and transportation pipeline and transmitting the specification parameters to subsequent modules. According to the operation and maintenance management system and device combining real-time data display and AI trend prediction, an efficient and intelligent pipeline operation and maintenance management platform is constructed by combining multi-sensor data acquisition, AI trend prediction, dynamic grouping management and intelligent maintenance management; the problems of data lag, insufficient prediction capability and inflexible resource allocation in traditional oil field gathering and transportation pipeline management are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of oilfield gathering and transportation pipeline operation and maintenance management, and specifically relates to an operation and maintenance management system and device that combines real-time data display with AI trend prediction. Background Art

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

[0003] Traditional oilfield gathering and transportation pipeline operation and maintenance management often uses a unified judgment standard to monitor pipeline corrosion, which easily ignores potential anomalies under different actual working conditions, resulting in the inability to accurately monitor and judge pipeline anomalies, making it difficult to achieve efficient pipeline operation and maintenance management. At the same time, there is a lack of the ability to dynamically adjust according to the real-time status of the pipeline, and the efficiency of resource management and allocation is low, resulting in problems of low 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 and AI trend prediction to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes an operation and maintenance management system and device that combines real-time data display with AI trend prediction, and solves the above technical problems by improving the detection method and processing method.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] An operation and maintenance management system that combines real-time data display and AI trend prediction, including data acquisition module, pipeline pairing module, abnormal trend analysis and positioning module, and pipeline maintenance management module;

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

[0009] The pipeline pairing module calculates the corrosion depths of different oilfield gathering and transportation pipelines based on the specification parameters of the oilfield gathering and transportation pipelines and the real-time thickness data of the oilfield gathering and transportation pipelines, and sets a grouping range to group the oilfield gathering and transportation pipelines based on the corrosion depths of different oilfield gathering and transportation pipelines to obtain secondary groups, and displays the oilfield gathering and transportation pipeline data in the transportation process in real time;

[0010] The abnormal trend analysis and positioning module predicts the abnormal corrosion trend of the pipelines based on the abnormal corrosion depth growth and corrosion rate changes of the oilfield gathering and transportation pipelines in different sub-groups through the isolation forest method to determine the abnormal pipelines in the same group. At the same time, according to the external soil moisture data of the oilfield gathering and transportation pipelines, the leaking oilfield gathering and transportation pipelines are analyzed and the abnormal positions are located;

[0011] The pipeline maintenance management module makes archive notes and abnormal position marks for the abnormal oilfield gathering and transportation pipelines determined, and retransmits the grouping signal to the pipeline pairing module to regroup the pipelines after the abnormal pipelines are maintained.

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

[0013] Ultrasonic thickness measuring sensors are installed at key locations of all oilfield gathering and transportation pipelines under its jurisdiction, including pipeline inlet, pipeline outlet, pipeline middle, pipeline inlet to halfway point, and pipeline middle to halfway point of outlet, to collect real-time thickness data of key locations of oilfield gathering and transportation pipelines. At the same time, humidity sensors are installed at equal intervals outside the oilfield gathering and transportation pipelines to collect real-time soil humidity data outside the pipelines.

[0014] Collect the wall thickness specification parameters and basic information of the oilfield gathering and transportation pipeline, and transmit them to the subsequent modules in combination with the real-time thickness data of key locations of the oilfield gathering and transportation pipeline and the soil moisture data outside the pipeline.

[0015] Furthermore, the pipeline pairing module calculates the corrosion depths of different oilfield gathering and transportation pipelines based on the specification parameters of the oilfield gathering and transportation pipelines and the real-time thickness data of the oilfield gathering and transportation pipelines, and sets the grouping range to group the oilfield gathering and transportation pipelines based on the corrosion depths of different oilfield gathering and transportation pipelines to obtain secondary groups, and displays the oilfield gathering and transportation pipeline data in the transportation process in real time, and the specific steps are as follows:

[0016] Based on PostgreSQL, archives of each oilfield gathering and transportation pipeline are established. The archives include basic information, serial numbers, wall thickness specification parameters, real-time thickness data of each key position, and humidity sensor location of the oilfield gathering and transportation pipeline. Category groups are established separately, including import group, export group, middle group, first half group, and last half group.

[0017] Calculate the corrosion depth of each key position of the gathering and transportation pipelines of different oil fields respectively. Based on the corrosion depth data of each key position of the gathering and transportation pipelines of all oil fields under its jurisdiction, set the division range to establish sub-groups in each category group, and divide the pipeline files that meet the conditions into the corresponding sub-groups;

[0018] Transmit the real-time wall thickness data of key locations in the archives of each oil field gathering and transportation pipeline to the external display for real-time data display.

[0019] Further, the corrosion depths of various key positions of the gathering and transportation pipelines of different oil fields are calculated respectively, and based on the corrosion depth data of various key positions of the gathering and transportation pipelines of all the oil fields under its jurisdiction, a division range is set to establish a secondary group in each category group, and the pipeline files that meet the conditions are divided into the corresponding secondary group, including the following steps:

[0020] The corrosion depth of each key position of the gathering and transportation pipelines of different oil fields is calculated separately, including the pipeline inlet, pipeline outlet, pipeline middle, pipeline inlet to half of the middle, and pipeline middle to half of the outlet. The algorithm formula is:

[0021]

[0022] Among them, n represents the number of the oilfield gathering and transportation pipeline, i represents the key position of the oilfield gathering and transportation pipeline, Represents the wall thickness specification parameters of the oil field gathering and transportation pipeline numbered n. represents the real-time thickness data of the i-th key position of the oil field gathering and transportation pipeline numbered n, Represents the corrosion depth of the i-th key position of the oil field gathering and transportation pipeline numbered n;

[0023] Obtain the corrosion depth data of all the gathering and transportation pipelines in the subordinate oil fields at key locations, including pipeline inlet, pipeline outlet, pipeline middle, pipeline inlet to halfway point, and pipeline middle to halfway point of the outlet, and establish data sets based on pipeline numbers:

[0024]

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

[0026] Arrange the data in H1, H2, H3, H4, and H5 in ascending order, obtain the interval of each data set based on the difference between the maximum and minimum corrosion depths in each data set, divide each data set into N equal-width intervals, and divide the data into equal-width intervals in the corresponding data set according to the corrosion depth values ​​in different data sets;

[0027] Based on the equal-width intervals divided in H1, H2, H3, H4, and H5, corresponding numbers of sub-groups are established in the import group, export group, middle group, first half group, and last half group based on the number of corresponding equal-width intervals, and the oilfield gathering and transportation pipeline files corresponding to the data in each equal-width interval are divided into the sub-groups established by the corresponding equal-width intervals.

[0028] Furthermore, the abnormal trend analysis and positioning module predicts the abnormal corrosion trend of the pipeline based on the abnormal corrosion depth growth and corrosion rate change of the oilfield gathering and transportation pipelines in different secondary groups, combined with AI technology, to determine the abnormal pipelines in the same group. At the same time, according to the external soil moisture data of the oilfield gathering and transportation pipelines, the leaking oilfield gathering and transportation pipelines are analyzed and the abnormal position is located. The specific steps are as follows:

[0029] Extract data from the oilfield gathering and transportation pipeline archives in each sub-group. Extract the pipeline data in the sub-group for P consecutive times based on the time interval T to obtain the corrosion depth change and corrosion rate. Combine AI technology to predict abnormal corrosion trends and determine abnormal pipelines.

[0030] Based on the operation time of the oilfield gathering and transportation pipeline, combined with the soil moisture data outside the oilfield gathering and transportation pipeline, the leaking oilfield gathering and transportation pipeline is analyzed and determined, and the abnormal position of the pipeline is located. The specific steps are as follows:

[0031] Based on the start and stop time of the oilfield gathering and transportation pipeline, the external soil moisture data of the oilfield gathering and transportation pipeline before and after the pipeline operation are collected at different sensors, and the humidity change is calculated:

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

[0033] When the humidity change during five consecutive pipeline operations is greater than the soil humidity change threshold, it means that the soil humidity data at the current sensor measurement location is abnormal, and the abnormal signal is transmitted to the subsequent module.

[0034] Furthermore, the data is extracted from the oilfield gathering and transportation pipeline archives in each secondary group, and the pipeline data in the secondary group is extracted for P consecutive times based on the time interval T, the corrosion depth change and the corrosion rate are obtained, and the abnormal corrosion trend is predicted by combining AI technology, and the abnormal pipeline is judged, including the following steps:

[0035] Based on the time interval T, the archives in each secondary group are continuously extracted P times, and the corrosion depth change and corrosion rate of the oilfield gathering and transportation pipeline corresponding to each archive are calculated respectively. The specific algorithm formula is:

[0036]

[0037] in, represents the change in corrosion depth at the i-th key position of the oilfield gathering and transportation pipeline numbered n within a single time interval T, They respectively represent the corrosion depth of the i-th key position of the oilfield gathering and transportation pipeline numbered n after the time interval T and the corrosion depth of the i-th key position of the oilfield gathering and transportation pipeline numbered n before the time interval T;

[0038]

[0039] Among them, φ i n Represents the corrosion depth change rate of the i-th key position of the oil field gathering and transportation pipeline numbered n within a single time interval T. Based on the corrosion depth change and corrosion rate extracted for P consecutive times, the mean values ​​of different archives in the same sub-group during the continuous data extraction process are calculated respectively. and standard deviation At the same time, the mean value of the total corrosion depth change and the mean value of the total corrosion rate μ of the secondary groups after continuous extraction are calculated. C , μ φ ;

[0040] The T statistics of the corrosion depth change and corrosion rate of each file in the secondary group are calculated respectively, and the formula is:

[0041]

[0042] in, represents the statistic T of the corrosion depth change rate of the i-th key position of the oil field gathering and transportation pipeline numbered n, The corrosion rate T statistic of the i-th key position of the oil field gathering and transportation pipeline numbered n is obtained by searching the T distribution table based on the degree of freedom P-1 and the significance level 0.05 to obtain the critical value of the corrosion depth change rate Ω C and the critical value of corrosion rate Ω φ , determine the abnormal pipeline:

[0043] when or When , it means that the current file has an abnormal corrosion depth change rate or corrosion rate change rate compared with other files in the secondary group, and the abnormal signal is transmitted to the pipeline maintenance management module;

[0044] Combined with the isolation forest method, the data extracted from all key locations of the subordinate pipelines for 5P consecutive times are summarized to predict the abnormal corrosion trend of the pipelines. The specific steps are as follows:

[0045] Collect 5P corrosion rate data points collected at different key positions of all pipelines under its jurisdiction, and construct a random binary tree. Each tree recursively divides the data points into leaf nodes of the tree by randomly selecting a feature and randomly selecting a split value;

[0046] For each data point x z , calculate the average path length h(x z ), and calculate the anomaly score for each data point

[0047]

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

[0049] when Indicates that the current data point is an abnormal point. Count the total number of abnormal points τ in the current pipeline 5P, combined with the abnormal point number threshold θ max With θ min , determine the current pipeline corrosion trend:

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

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

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

[0053] Furthermore, the pipeline maintenance management module makes archive notes and abnormal position marks for the abnormal oilfield gathering and transportation pipelines determined, and retransmits the grouping signal to the pipeline pairing module to regroup the pipelines after the abnormal pipelines are maintained. The specific steps are as follows:

[0054] In response to abnormal soil moisture data, the humidity sensor locations at abnormal points are marked in red in the archives of the oilfield gathering and transportation pipelines;

[0055] For abnormal corrosion depth change rate or corrosion rate change rate, the relevant oilfield gathering and transportation pipeline files will be marked purple;

[0056] For oilfield gathering and transportation pipelines that are judged to be at risk of corrosion, the relevant oilfield gathering and transportation pipeline files will be marked in yellow;

[0057] After the abnormal pipeline is maintained, that is, after all abnormal color marks are cleared, the grouping signal is retransmitted into the pipeline pairing module to regroup the oilfield gathering and transportation pipelines.

[0058] The operation and maintenance management device combining real-time data display and AI trend prediction is applied to the operation and maintenance management system combining real-time data display and AI trend prediction, including a memory, a processor and a program stored in the memory and executable on the processor. When the processor executes the program, the steps in the operation and maintenance management system combining real-time data display and AI trend prediction as described in the present invention are implemented.

[0059] Compared with the prior art, the present invention has the following beneficial effects:

[0060] 1. In the present invention, by grouping and pairing the key positions of the oilfield gathering and transportation pipelines based on the corrosion depth, and combining the corrosion depth changes and corrosion rates of different secondary groups, the pipelines under similar corrosion conditions are judged for abnormalities within the group, thereby avoiding the occurrence of potential abnormalities ignored under a unified judgment standard, and achieving more accurate corrosion monitoring and more efficient pipeline operation and maintenance management;

[0061] 2. In the present invention, the corrosion depth is calculated and the pipelines are dynamically grouped through the pipeline pairing module, and the management strategy can be adjusted according to the real-time status of the pipeline, so that the system can manage and allocate resources more efficiently. The pipeline maintenance management module retransmits the grouping signal after the pipeline maintenance, realizes the dynamic regrouping of the pipeline, ensures that the status of the pipeline after maintenance can be updated to the system in time, and avoids monitoring loopholes caused by delayed maintenance information;

[0062] 3. In the present invention, by judging the abnormal corrosion data of pipelines in different groups based on the dynamic grouping results, the corrosion trend of each group of pipelines is analyzed in a targeted manner, the changing law of the corrosion rate is identified, and normal corrosion and abnormal corrosion are distinguished. At the same time, the external soil moisture data is combined to perform dual monitoring of pipeline anomalies, thereby enhancing practicality and functionality;

[0063] 4. In the present invention, the trend of pipeline corrosion rate is analyzed by combining AI technology, stable pipelines and unstable pipelines are determined, and pipelines under different abnormalities are distinguished and marked in the archives, which is convenient for managers to operate and maintain oilfield gathering and transportation pipelines, assist managers to make more scientific and accurate decisions, and improve operation and maintenance efficiency;

[0064] The present invention provides an operation and maintenance management system and device combining real-time data display and AI trend prediction, by combining multi-sensor data acquisition, AI trend prediction, dynamic grouping management and intelligent maintenance management, to build an efficient and intelligent pipeline operation and maintenance management platform, solving the problems of data lag, insufficient prediction ability and inflexible resource allocation in traditional oilfield gathering and transportation pipeline management. BRIEF DESCRIPTION OF THE DRAWINGS

[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 of the present invention. DETAILED DESCRIPTION

[0066] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] Embodiment 1:

[0068] like Figure 1 As shown, the operation and maintenance management system that combines real-time data display and AI trend prediction includes a data acquisition module, a pipeline pairing module, an abnormal trend analysis and positioning module, and a pipeline maintenance management module;

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

[0070] Ultrasonic thickness measuring sensors are installed at key locations of all oilfield gathering and transportation pipelines under its jurisdiction, including pipeline inlet, pipeline outlet, pipeline middle, pipeline inlet to halfway point, and pipeline middle to halfway point of outlet, to collect real-time thickness data of key locations of oilfield gathering and transportation pipelines. At the same time, humidity sensors are installed at equal intervals outside the oilfield gathering and transportation pipelines to collect real-time soil humidity data outside the pipelines.

[0071] It should be noted that by collecting data from ultrasonic thickness gauge sensors at key locations of the oilfield gathering and transportation pipelines, the oilfield gathering and transportation pipelines can be dynamically grouped and abnormalities determined based on the corrosion conditions of different key locations. Humidity sensors are usually set every 75 meters, and the distance can be increased or decreased according to actual usage needs. By adjusting the distance of the humidity sensor, the accuracy of external leakage determination can be increased or decreased.

[0072] Collect the wall thickness specification parameters and basic information of the oilfield gathering and transportation pipeline, and transmit them to the subsequent modules in combination with the real-time thickness data of key locations of the oilfield gathering and transportation pipeline and the soil moisture data outside the pipeline.

[0073] It should be noted that the collected wall thickness specification parameters of oilfield gathering and transportation pipelines, real-time thickness data at key locations of oilfield gathering and transportation pipelines, and soil moisture data outside pipelines can provide data support for the data processing of subsequent modules to determine abnormal pipelines. The basic information includes the location, length, name, etc. of the pipelines;

[0074] The pipeline pairing module calculates the corrosion depth of different oilfield gathering and transportation pipelines based on the specification parameters of the oilfield gathering and transportation pipelines and the real-time thickness data of the oilfield gathering and transportation pipelines. Based on the corrosion depth of different oilfield gathering and transportation pipelines, the grouping range is set to group the oilfield gathering and transportation pipelines to obtain secondary groups, and the oilfield gathering and transportation pipeline data in the transportation process is displayed in real time. The specific steps are as follows:

[0075] Based on PostgreSQL, archives of each oilfield gathering and transportation pipeline are established. The archives include basic information, serial numbers, wall thickness specification parameters, real-time thickness data of each key position, and humidity sensor location of the oilfield gathering and transportation pipeline. Category groups are established separately, including import group, export group, middle group, first half group, and last half group.

[0076] Calculate the corrosion depth of each key position of the gathering and transportation pipelines of different oil fields respectively. Based on the corrosion depth data of each key position of the gathering and transportation pipelines of all oil fields under its jurisdiction, set the division range to establish sub-groups in each category group, and divide the pipeline files that meet the conditions into the corresponding sub-groups;

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

[0078] The corrosion depth of each key position of the gathering and transportation pipelines of different oil fields is calculated separately, including the pipeline inlet, pipeline outlet, pipeline middle, pipeline inlet to half of the middle, and pipeline middle to half of the outlet. The algorithm formula is:

[0079]

[0080] Among them, n represents the number of the oilfield gathering and transportation pipeline, i represents the key position of the oilfield gathering and transportation pipeline, Represents the wall thickness specification parameters of the oil field gathering and transportation pipeline numbered n. represents the real-time thickness data of the i-th key position of the oil field gathering and transportation pipeline numbered n, Represents the corrosion depth of the i-th key position of the oil field gathering and transportation pipeline numbered n;

[0081] It should be noted that i represents the key position of the oilfield gathering and transportation pipeline, ranging from 1 to 5, representing the pipeline inlet, pipeline outlet, pipeline middle, pipeline inlet to half of the middle, and pipeline middle to half of the outlet, respectively. The corrosion depths of the key positions of the oilfield gathering and transportation pipeline are calculated respectively, which can facilitate the subsequent secondary grouping based on the key positions of the pipeline to determine abnormal pipelines.

[0082] Obtain the corrosion depth data of all the gathering and transportation pipelines in the subordinate oil fields at key locations, including pipeline inlet, pipeline outlet, pipeline middle, pipeline inlet to halfway point, and pipeline middle to halfway point of the outlet, and establish data sets based on pipeline numbers:

[0083]

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

[0085] Arrange the data in H1, H2, H3, H4, and H5 in ascending order, obtain the interval of each data set based on the difference between the maximum and minimum corrosion depths in each data set, divide each data set into N equal-width intervals, and divide the data into equal-width intervals in the corresponding data set according to the corrosion depth values ​​in different data sets;

[0086] It should be noted that the value of the equal-width interval N needs to be determined according to the difference between the maximum value and the minimum value in the actual data set, and is usually set to 10. It can also be increased or decreased according to actual conditions. By increasing the number of equal-width intervals, the accuracy of subsequent abnormal pipeline judgment can be improved.

[0087] Based on the equal-width intervals divided in H1, H2, H3, H4, and H5, corresponding numbers of sub-groups are established in the import group, export group, middle group, first half group, and last half group respectively based on the number of corresponding equal-width intervals, and the oilfield gathering and transportation pipeline files corresponding to the data in each equal-width interval are divided into the sub-groups established by the corresponding equal-width intervals.

[0088] Transmit the real-time wall thickness data of key locations in the archives of each oil field gathering and transportation pipeline to the external display for real-time data display;

[0089] Embodiment 2:

[0090] The abnormal trend analysis and positioning module predicts the abnormal corrosion trend of the pipelines based on the abnormal corrosion depth growth and corrosion rate changes of the oilfield gathering and transportation pipelines in different sub-groups through the isolation forest method to determine the abnormal pipelines in the same group. At the same time, according to the external soil moisture data of the oilfield gathering and transportation pipelines, the leaking oilfield gathering and transportation pipelines are analyzed and the abnormal positions are located. The specific steps are as follows:

[0091] Extract data from the oilfield gathering and transportation pipeline archives in each sub-group. Extract the pipeline data in the sub-group for P consecutive times based on the time interval T to obtain the corrosion depth change and corrosion rate. Combine AI technology to predict abnormal corrosion trends and determine abnormal pipelines.

[0092] It should be noted that the T test is used to sample the pipeline files in the same secondary group multiple times at equal time intervals, and the mean and standard deviation are calculated respectively. Based on this, the abnormal changes in corrosion depth and corrosion rate are judged to identify potential problem pipelines and take corresponding measures. The value of P is usually set to 5.

[0093] Based on the time interval T, the archives in each secondary group are continuously extracted P times, and the corrosion depth change and corrosion rate of the oilfield gathering and transportation pipeline corresponding to each archive are calculated respectively. The specific algorithm formula is:

[0094]

[0095] in, represents the change in corrosion depth at the i-th key position of the oilfield gathering and transportation pipeline numbered n within a single time interval T, They respectively represent the corrosion depth of the i-th key position of the oilfield gathering and transportation pipeline numbered n after the time interval T and the corrosion depth of the i-th key position of the oilfield gathering and transportation pipeline numbered n before the time interval T;

[0096]

[0097] Among them, φ i n Represents the corrosion depth change rate of the i-th key position of the oil field gathering and transportation pipeline numbered n within a single time interval T. Based on the corrosion depth change and corrosion rate extracted for P consecutive times, the mean values ​​of different archives in the same sub-group during the continuous data extraction process are calculated respectively. and standard deviation At the same time, the mean value of the total corrosion depth change and the mean value of the total corrosion rate μ of the secondary groups after continuous extraction are 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 every two days, and can also be adjusted according to actual conditions.

[0099] The T statistics of the corrosion depth change and corrosion rate of each file in the secondary group are calculated respectively, and the formula is:

[0100]

[0101] in, represents the statistic T of the corrosion depth change rate of the i-th key position of the oil field gathering and transportation pipeline numbered n, The corrosion rate T statistic of the i-th key position of the oil field gathering and transportation pipeline numbered n is obtained by searching the T distribution table based on the degree of freedom P-1 and the significance level 0.05 to obtain the critical value of the corrosion depth change rate Ω C and the critical value of corrosion rate Ω φ , determine the abnormal pipeline:

[0102] when or When , it means that the current file has an abnormal corrosion depth change rate or corrosion rate change rate compared with other files in the secondary group, and the abnormal signal is transmitted to the pipeline maintenance management module;

[0103] It should be noted that, under the same corrosion situation grouping condition, the T test is used to continuously sample the pipeline files in the same secondary group at equal time intervals, calculate the mean and standard deviation, and judge the abnormal situation of the corrosion depth change and the corrosion rate change rate based on this. The abnormal corrosion change judgment of pipelines under the same or similar corrosion conditions can be carried out specifically, avoiding the limitation of judging pipeline abnormalities based on the overall threshold, enhancing the accuracy of abnormal judgment, and judging the abnormal corrosion depth change rate and corrosion rate of the pipeline at the same time, so as to identify potential abnormal pipelines in the same secondary group.

[0104] Combined with the isolation forest method, the data extracted from all key locations of the subordinate pipelines for 5P consecutive times are summarized to predict the abnormal corrosion trend of the pipelines. The specific steps are as follows:

[0105] Collect 5P corrosion rate data points collected at different key positions of all pipelines under its jurisdiction, and construct a random binary tree. Each tree recursively divides the data points into leaf nodes of the tree by randomly selecting a feature and randomly selecting a split value;

[0106] For each data point x z , calculate the average path length h(x z ), and calculate the anomaly score for each data point

[0107]

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

[0109] when Indicates that the current data point is an abnormal point. Count the total number of abnormal points τ in the current pipeline 5P, combined with the abnormal point number threshold θ max With θ min , determine the current pipeline corrosion trend:

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

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

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

[0113] It should be noted that the total number of abnormal points in 5P is determined by the isolation forest method. Based on the number of abnormal points, the corrosion rate state of the current pipeline can be determined. The abnormal score threshold The value of is between 0.5 and 1, usually set to 0.7, and the threshold value of the number of outliers θ max With θ min P and c(5P) is the normalized path length

[0114] Based on the operation time of the oilfield gathering and transportation pipeline, combined with the soil moisture data outside the oilfield gathering and transportation pipeline, the leaking oilfield gathering and transportation pipeline is analyzed and determined, and the abnormal position of the pipeline is located. The specific steps are as follows:

[0115] Based on the start and stop time of the oilfield gathering and transportation pipeline, the external soil moisture data of the oilfield gathering and transportation pipeline before and after the pipeline operation are collected at different sensors, and the humidity change is calculated:

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

[0117] When the humidity change during five consecutive pipeline operations is greater than the soil humidity change threshold, it means that the soil humidity data at the current sensor measurement location is abnormal, and the abnormal signal is transmitted to the subsequent module.

[0118] It should be noted that the soil moisture change threshold needs to be determined based on the normal soil moisture change at different sensor locations. Based on the soil moisture change, it can assist in determining the abnormality of the oilfield gathering and transportation pipeline, and cooperate with the corrosion abnormality determination to provide double protection for the oilfield gathering and transportation pipeline.

[0119] The pipeline maintenance management module makes archive notes and abnormal position marks for the abnormal oilfield gathering and transportation pipelines, and retransmits the grouping signal to the pipeline pairing module for pipeline regrouping after the abnormal pipeline maintenance. The specific steps are as follows:

[0120] In response to abnormal soil moisture data, the humidity sensor locations at abnormal points are marked in red in the archives of the oilfield gathering and transportation pipelines;

[0121] For abnormal corrosion depth change rate or corrosion rate change rate, the relevant oilfield gathering and transportation pipeline files will be marked purple;

[0122] For oilfield gathering and transportation pipelines that are judged to be at risk of corrosion, the relevant oilfield gathering and transportation pipeline files will be marked in yellow;

[0123] After the abnormal pipeline is maintained, that is, after all abnormal color marks are cleared, the grouping signal is retransmitted into the pipeline pairing module to regroup the oilfield gathering and transportation pipelines.

[0124] Embodiment 3:

[0125] An operation and maintenance management device combining real-time data display and AI trend prediction is applied to an operation and maintenance management system combining real-time data display and AI trend prediction, including a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps in the operation and maintenance management system combining real-time data display and AI trend prediction of the present invention are implemented.

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

[0127] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An operation and maintenance management system that combines real-time data display and AI trend prediction, characterized by: Including data acquisition module, pipeline pairing module, abnormal trend analysis and positioning module, pipeline maintenance management module; The data acquisition module includes an ultrasonic thickness sensor and a humidity sensor, which are used to collect real-time thickness data of the oilfield gathering and transportation pipeline and external soil humidity data, and collect specification parameters of the oilfield gathering and transportation pipeline and transmit them to subsequent modules; The pipeline pairing module calculates the corrosion depths of different oilfield gathering and transportation pipelines based on the specification parameters of the oilfield gathering and transportation pipelines and the real-time thickness data of the oilfield gathering and transportation pipelines, and sets a grouping range to group the oilfield gathering and transportation pipelines based on the corrosion depths of different oilfield gathering and transportation pipelines to obtain secondary groups, and displays the oilfield gathering and transportation pipeline data in the transportation process in real time; The abnormal trend analysis and positioning module predicts the abnormal corrosion trend of the pipelines based on the abnormal corrosion depth growth and corrosion rate changes of the oilfield gathering and transportation pipelines in different sub-groups through the isolation forest method to determine the abnormal pipelines in the same group. At the same time, according to the external soil moisture data of the oilfield gathering and transportation pipelines, the leaking oilfield gathering and transportation pipelines are analyzed and the abnormal positions are located; The pipeline maintenance management module makes archive notes and abnormal position marks for the abnormal oilfield gathering and transportation pipelines determined, and retransmits the grouping signal to the pipeline pairing module to regroup the pipelines after the abnormal pipelines are maintained.

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

3. The operation and maintenance management system combining real-time data display and AI trend prediction according to claim 2, characterized in that: The pipeline pairing module calculates the corrosion depths of different oilfield gathering and transportation pipelines based on the specification parameters of the oilfield gathering and transportation pipelines and the real-time thickness data of the oilfield gathering and transportation pipelines, and sets the grouping range to group the oilfield gathering and transportation pipelines based on the corrosion depths of different oilfield gathering and transportation pipelines to obtain secondary groups, and displays the oilfield gathering and transportation pipeline data in the transportation process in real time. The specific steps are as follows: Based on PostgreSQL, archives of each oilfield gathering and transportation pipeline are established. The archives include basic information, serial numbers, wall thickness specification parameters, real-time thickness data of each key position, and humidity sensor location of the oilfield gathering and transportation pipeline. Category groups are established separately, including import group, export group, middle group, first half group, and last half group. Calculate the corrosion depth of each key position of the gathering and transportation pipelines of different oil fields respectively. Based on the corrosion depth data of each key position of the gathering and transportation pipelines of all oil fields under its jurisdiction, set the division range to establish sub-groups in each category group, and divide the pipeline files that meet the conditions into the corresponding sub-groups; Transmit the real-time wall thickness data of key locations in the archives of each oil field gathering and transportation pipeline to the external display for real-time data display.

4. The operation and maintenance management system combining real-time data display and AI trend prediction according to claim 3 is characterized in that: The method of calculating the corrosion depth of each key position of the gathering and transportation pipelines of different oil fields respectively, and setting the division range to establish a secondary group in each category group based on the corrosion depth data of each key position of the gathering and transportation pipelines of all oil fields under its jurisdiction, and dividing the pipeline files that meet the conditions into the corresponding secondary group, includes the following steps: The corrosion depth of each key position of the gathering and transportation pipelines of different oil fields is calculated separately, including the pipeline inlet, pipeline outlet, pipeline middle, pipeline inlet to half of the middle, and pipeline middle to half of the outlet. The algorithm formula is: Among them, n represents the number of the oilfield gathering and transportation pipeline, i represents the key position of the oilfield gathering and transportation pipeline, Represents the wall thickness specification parameters of the oil field gathering and transportation pipeline numbered n. represents the real-time thickness data of the i-th key position of the oil field gathering and transportation pipeline numbered n, Represents the corrosion depth of the i-th key position of the oil field gathering and transportation pipeline numbered n; Obtain the corrosion depth data of all the gathering and transportation pipelines in the subordinate oil fields at key locations, including pipeline inlet, pipeline outlet, pipeline middle, pipeline inlet to halfway point, and pipeline middle to halfway point of the outlet, and establish data sets based on pipeline numbers: Among them, H1, H2, H3, H4, and H5 represent the pipeline inlet corrosion depth dataset, pipeline outlet corrosion depth dataset, pipeline middle corrosion depth dataset, pipeline inlet to the middle half of the corrosion depth dataset, and pipeline middle to the outlet half of the corrosion depth dataset, respectively. n represents the oilfield gathering and transportation pipeline number. Arrange the data in H1, H2, H3, H4, and H5 in ascending order, obtain the interval of each data set based on the difference between the maximum and minimum corrosion depths in each data set, divide each data set into N equal-width intervals, and divide the data into equal-width intervals in the corresponding data set according to the corrosion depth values ​​in different data sets; Based on the equal-width intervals divided in H1, H2, H3, H4, and H5, corresponding numbers of sub-groups are established in the import group, export group, middle group, first half group, and last half group based on the number of corresponding equal-width intervals, and the oilfield gathering and transportation pipeline files corresponding to the data in each equal-width interval are divided into the sub-groups established by the corresponding equal-width intervals.

5. The operation and maintenance management system combining real-time data display and AI trend prediction according to claim 1, characterized in that: The abnormal trend analysis and positioning module predicts the abnormal corrosion trend of the pipeline based on the abnormal corrosion depth growth and corrosion rate change of the oilfield gathering and transportation pipelines in different secondary groups, combined with AI technology to determine the abnormal pipelines in the same group. At the same time, according to the external soil moisture data of the oilfield gathering and transportation pipelines, the leaking oilfield gathering and transportation pipelines are analyzed and the abnormal position is located. The specific steps are as follows: Extract data from the oilfield gathering and transportation pipeline archives in each sub-group. Extract the pipeline data in the sub-group for P consecutive times based on the time interval T to obtain the corrosion depth change and corrosion rate. Combine AI technology to predict abnormal corrosion trends and determine abnormal pipelines. Based on the operation time of the oilfield gathering and transportation pipeline, combined with the soil moisture data outside the oilfield gathering and transportation pipeline, the leaking oilfield gathering and transportation pipeline is analyzed and determined, and the abnormal position of the pipeline is located. The specific steps are as follows: Based on the start and stop time of the oilfield gathering and transportation pipeline, the external soil moisture data of the oilfield gathering and transportation pipeline before and after the pipeline operation are collected at different sensors, and the humidity change is calculated: Humidity change = humidity after pipeline operation ends - initial humidity; When the humidity change during five consecutive pipeline operations is greater than the soil humidity change threshold, it means that the soil humidity data at the current sensor measurement location is abnormal, and the abnormal signal is transmitted to the subsequent module.

6. The operation and maintenance management system combining real-time data display and AI trend prediction according to claim 5, characterized in that: The data is extracted from the oilfield gathering and transportation pipeline archives in each secondary group, and the pipeline data in the secondary group is extracted for P consecutive times based on the time interval T, so as to obtain the corrosion depth change and corrosion rate, and the abnormal corrosion trend is predicted by combining AI technology, and the abnormal pipeline is judged, including the following steps: Based on the time interval T, the archives in each secondary group are continuously extracted P times, and the corrosion depth change and corrosion rate of the oilfield gathering and transportation pipeline corresponding to each archive are calculated respectively. The specific algorithm formula is: in, represents the change in corrosion depth at the i-th key position of the oilfield gathering and transportation pipeline numbered n within a single time interval T, They respectively represent the corrosion depth of the i-th key position of the oilfield gathering and transportation pipeline numbered n after the time interval T and the corrosion depth of the i-th key position of the oilfield gathering and transportation pipeline numbered n before the time interval T; in, Represents the corrosion depth change rate of the i-th key position of the oil field gathering and transportation pipeline numbered n within a single time interval T. Based on the corrosion depth change and corrosion rate extracted for P consecutive times, the mean values ​​of different archives in the same sub-group during the continuous data extraction process are calculated respectively. and standard deviation At the same time, the mean value of the total corrosion depth change and the mean value of the total corrosion rate μ of the secondary group after continuous extraction are calculated. C , μ φ ; The T statistics of the corrosion depth change and corrosion rate of each file in the secondary group are calculated respectively, and the formula is: in, represents the statistic T of the corrosion depth change rate of the i-th key position of the oil field gathering and transportation pipeline numbered n, The corrosion rate T statistic of the i-th key position of the oil field gathering and transportation pipeline numbered n is obtained by searching the T distribution table based on the degree of freedom P-1 and the significance level 0.05 to obtain the critical value of the corrosion depth change rate Ω C and the critical value of corrosion rate Ω φ , determine the abnormal pipeline: when or When , it means that the current file has an abnormal corrosion depth change rate or corrosion rate change rate compared with other files in the secondary group, and the abnormal signal is transmitted to the pipeline maintenance management module; Combined with the isolation forest method, the data extracted from all key locations of the subordinate pipelines for 5P consecutive times are summarized to predict the abnormal corrosion trend of the pipelines. The specific steps are as follows: Collect 5P corrosion rate data points collected at different key positions of all pipelines under its jurisdiction, and construct a random binary tree. Each tree recursively divides the data points into leaf nodes of the tree by randomly selecting a feature and randomly selecting a split value; For each data point x z , calculate the average path length h(x z ), and calculate the anomaly score for each data point Where c(5P) is the normalized path length, E(h(x z )) is the data point x z Average path length among all isolated trees, based on anomaly score threshold Anomaly score for each data point Make a judgment: when Indicates that the current data point is an abnormal point. Count the total number of abnormal points τ in the current pipeline 5P, combined with the abnormal point number threshold θ max With θ min , determine the current pipeline corrosion trend: When τ<θ min When , it means that the number of abnormal points of the current pipeline corrosion rate is small and the corrosion trend is excellent; When θ min ≤τ≤θ max When , it means that the number of abnormal points of the current pipeline corrosion rate is normal and the corrosion trend is stable; When τ>θ max When , it means that there are many abnormal points of corrosion rate in the current pipeline, and the corrosion trend is dangerous.

7. The operation and maintenance management system combining real-time data display and AI trend prediction according to claim 6, characterized in that: The pipeline maintenance management module makes archive notes and abnormal position marks for the abnormal oilfield gathering and transportation pipelines, and retransmits the grouping signal to the pipeline pairing module for pipeline regrouping after the abnormal pipeline maintenance. The specific steps are as follows: In response to abnormal soil moisture data, the humidity sensor locations at abnormal points are marked in red in the archives of the oilfield gathering and transportation pipelines; For abnormal corrosion depth change rate or corrosion rate change rate, the relevant oilfield gathering and transportation pipeline files will be marked purple; For oilfield gathering and transportation pipelines that are judged to be at risk of corrosion, the relevant oilfield gathering and transportation pipeline files will be marked in yellow; After the abnormal pipeline is maintained, that is, after all abnormal color marks are cleared, the grouping signal is retransmitted into the pipeline pairing module to regroup the oilfield gathering and transportation pipelines.

8. The operation and maintenance management device combining real-time data display and AI trend prediction is characterized in that: The device is applied to an operation and maintenance management system combining real-time data display and AI trend prediction, and includes a memory and a processor: a memory for non-transitory storage of computer readable instructions; a processor for executing the computer-readable instructions; Wherein, when the computer-readable instructions are executed by the processor, the system described in any one of claims 1-7 is executed.

Images