CN108765889B - Oil and gas production operation safety early warning method based on big data technology - Google Patents
Oil and gas production operation safety early warning method based on big data technology Download PDFInfo
- Publication number
- CN108765889B CN108765889B CN201810341724.0A CN201810341724A CN108765889B CN 108765889 B CN108765889 B CN 108765889B CN 201810341724 A CN201810341724 A CN 201810341724A CN 108765889 B CN108765889 B CN 108765889B
- Authority
- CN
- China
- Prior art keywords
- parameter
- early warning
- wellhead
- variance
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 37
- 238000005516 engineering process Methods 0.000 title claims abstract description 10
- 238000004458 analytical method Methods 0.000 claims description 62
- 230000002159 abnormal effect Effects 0.000 claims description 53
- 230000008569 process Effects 0.000 claims description 23
- 238000005457 optimization Methods 0.000 claims description 20
- 230000008859 change Effects 0.000 claims description 11
- 238000013024 troubleshooting Methods 0.000 claims description 6
- 238000011835 investigation Methods 0.000 claims description 5
- 230000004888 barrier function Effects 0.000 abstract description 8
- 238000007726 management method Methods 0.000 abstract description 3
- 238000012544 monitoring process Methods 0.000 description 5
- 238000012795 verification Methods 0.000 description 5
- 239000012530 fluid Substances 0.000 description 4
- 238000012790 confirmation Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 230000005465 channeling Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Animal Husbandry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Educational Administration (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Emergency Management (AREA)
- Measuring Fluid Pressure (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an oil and gas production operation safety early warning method based on big data technology, which comprises the following steps: A) setting a pre-judgment parameter; B) the data access module reads, analyzes and judges remote field parameter data in a period T in real time, wherein the field parameter data comprise wellhead instantaneous gas quantity, wellhead temperature and A annular pressure; C) establishing an early warning model according to the prejudgment parameters, bringing the field parameter data into the early warning model, and obtaining the parameters of the problems to be diagnosed; D) when the problem parameter to be diagnosed meets the requirement of the target parameter, pushing alarm information; E) and when the problem parameter to be diagnosed does not meet the target parameter requirement, carrying out the next pre-pushing alarm period T, and repeating the steps B) and C), and pushing alarm information until the problem parameter to be diagnosed meets the target parameter requirement. Compared with the prior art, the safety early warning method can predict the abnormity of the shaft safety barrier in advance, and effectively realizes the forward movement of the production operation safety management gateway.
Description
Technical Field
The invention relates to the technical field of three-high gas well safety production, in particular to an oil-gas production operation safety early warning method based on a big data technology.
Background
The abnormal annular pressure is a sign of damage of a shaft safety barrier, and once the shaft safety barrier of a high-pressure, high-yield and high-sulfur-content gas well (called as a three-high gas well for short), events such as formation fluid leakage, blowout and the like can be induced, so that the cluster death and group damage are easily caused. From the safety perspective, the information technology is utilized to monitor and track the change trend of each production parameter in real time, the damage symptoms of the shaft safety barrier are excavated, early warning is given at the early stage of the damage of the shaft safety barrier, and the method has important significance for preventing fluid leakage, gas channeling and blowout risks.
In recent years, the intrinsic safety of a shaft safety barrier is very important at home and abroad, and four methods for diagnosing whether the annular pressure is abnormal exist at home and abroad are summarized, wherein the four methods comprise fluid sample analysis, logging analysis, pressure relief and pressure recovery characteristics and a Distributed Control System (DCS System for short). The four analysis methods can reliably find the abnormal annular pressure phenomenon, but have certain defects. The fluid sample analysis, the engineering well logging, the annular pressure relief and the pressure recovery test are all offline analysis, and the annular abnormal pressure is difficult to find in real time; the DCS system monitors the annulus pressure condition in real time by setting an annulus pressure threshold, typically set at 80% of its allowable bearing capacity, when the DCS system alarms, the wellbore safety barrier may have been damaged to a dangerous state that is difficult to control and remedy.
The phenomenon of annulus pressure exists in most oil and gas wells of the continental shelf outside the United states, 11498 annulus pressure casing sections exist in 8122 wells in statistics, and 50% of the annulus pressure casing sections occur in an annular space between a production casing and an oil pipe, namely an A annular space. Annulus pressure a has three main sources: 1) annulus pressure caused by the heat effect of the shaft; 2) the leakage of the oil pipe or the wellhead causes the pressure of the annulus A; 3) failure of the production casing seal causes the annulus to be pressured. The annular pressure caused by the physical effect of the shaft refers to the annular pressure generated by thermal expansion caused by the continuous increase of the temperature of the shaft along with the increase of the gas amount, and belongs to normal pressure. And the annular pressure caused by the leakage of an oil pipe or a casing, unqualified cementing quality and damage of a cement sheath is abnormal pressure, namely the annular pressure caused by the damage of a shaft safety barrier. The method is used for determining the change rule of each working condition parameter when the annulus A is normally pressurized, and is a precondition for identifying the abnormal pressurized phenomenon. Summarizing the change rules of the instantaneous gas quantity, the wellhead temperature and the A annular pressure of the gas well under the five states of the well opening process, the stable production process, the production regulation process, the well closing process and the well closing period under the normal pressure state, as shown in the attached drawing 1, the quantitative relation among the instantaneous gas quantity, the wellhead temperature and the A annular pressure under the three states of the well opening process, the production regulation process and the well closing process is not clear, and the A annular abnormal pressure rule under the three states is difficult to quantitatively describe. Therefore, the invention relates to an early warning scheme for abnormal annulus pressure A under the condition of stable wellhead instantaneous gas quantity and wellhead temperature.
Disclosure of Invention
The invention is provided in view of the above problems in the prior art, and provides an oil and gas production operation safety early warning method which can realize real-time monitoring, accurate early warning and long early warning period.
The invention is realized by the following technical scheme: an oil and gas production operation safety early warning method based on big data technology comprises the following steps:
A) setting an analysis and judgment period T and confirming a pre-judgment parameter according to all historical abnormal samples of a certain block;
B) the data access module reads, analyzes and judges remote field parameter data in a period T in real time, wherein the field parameter data comprise wellhead instantaneous gas quantity, wellhead temperature and A annular pressure;
C) establishing an early warning model according to the prejudgment parameters, bringing the field parameter data into the early warning model, and obtaining the parameters of the problems to be diagnosed;
D) when the problem parameter to be diagnosed meets the requirement of the target parameter, pushing alarm information;
E) and when the problem parameter to be diagnosed does not meet the target parameter requirement, performing the next analysis and judgment period T, and repeating the steps B) and C), and pushing alarm information until the problem parameter to be diagnosed meets the target parameter requirement.
Further, the establishing of the early warning model comprises the following steps:
s101: the data access module reads data parameters of each time point in an analysis and judgment period T in the DCS, wherein the data parameters comprise wellhead instantaneous gas quantity, wellhead temperature and A annular pressure;
s102: respectively solving the variance S of the instantaneous gas quantity of the wellhead in the T time period1And wellhead temperature variance S2；
S103: if the instantaneous gas quantity variance S of the well head can not be satisfied simultaneously1<1And the temperature variance S of the well head2<2Reading the data parameters of the next analysis and judgment period T, namely repeating the steps S101 and S102 until the variance S of the instantaneous gas quantity of the wellhead1<1And the temperature variance S of the well head2<2；
S104: such as variance S of instantaneous gas quantity at well head1<1And the temperature variance S of the well head2<2Fitting the trend line of the annular pressure change A by adopting a least square method, and obtaining a fitting line formula y which is α t + β;
wherein,1is the variance limit value of the instantaneous gas quantity of the well head,2for wellhead temperature variance limit, α and β are constants confirmed by a least square method, y is an annular pressure parameter A, and T is a time parameter in an analysis judgment period T.
Preferably, the problem parameter to be diagnosed is α, and the target parameter requirement is α > 0.
Further, all historical abnormal samples of a certain block of the DCS are selected, annular pressure rise time of all the historical abnormal samples A in the block is counted, and the analysis and judgment period T is smaller than the minimum value of the annular pressure rise time of all the historical abnormal samples A in the block.
Preferably, all historical samples of the block are divided into a plurality of analysis and judgment periods T, wellhead instantaneous gas quantity variance is counted in the analysis and judgment periods T, and the wellhead instantaneous gas quantity variance limit value1And the minimum value of the variance of the instantaneous gas quantity of the wellhead in the plurality of analysis and judgment periods T is smaller than the minimum value of the variance of the instantaneous gas quantity of the wellhead in the plurality of analysis and judgment periods T.
Further, all historical samples of the block are divided into a plurality of analysis and judgment periods T, wellhead temperature variances within the analysis and judgment periods T are counted, and the wellhead temperature variance limit value2And the minimum value of the wellhead temperature variance in the plurality of analysis and judgment periods T is smaller than the minimum value of the wellhead temperature variances in the plurality of analysis and judgment periods T.
Further, the preset parameter is adjustable, and the preset parameter is a manual input parameter.
Preferably, the system further comprises a parameter optimization and adjustment module.
Further, the parameter optimization and adjustment module comprises the following operation steps,
(1) setting preset parameters;
(2) sequentially operating the steps S102, S103 and S104, and when α is greater than 0, pushing early warning information and accumulating the total number of early warnings;
(3) arranging operators to carry out on-site investigation;
(4) if the on-site troubleshooting result is consistent with the early warning information, accumulating the accurate early warning number for one time; if the on-site troubleshooting result is inconsistent with the early warning information, accumulating an inaccurate early warning number;
(5) repeating the steps (2), (3) and (4) for N times, and counting the early warning accuracy;
(6) when the early warning accuracy reaches the target accuracy, stopping the parameter adjustment optimization process and setting required parameters;
(7) and (3) when the early warning accuracy rate does not reach the target accuracy rate, repeating the steps (1) and (5) until the early warning parameter accuracy rate reaches the target accuracy rate, stopping the parameter adjustment optimization process, and simultaneously setting required parameters.
The preset parameters comprise an analysis and judgment period T and a wellhead instantaneous gas volume variance limit value1Well head temperature variance limit2。
Preferably, when the derivative α of each analysis and judgment period T is greater than 0 after a plurality of analysis and judgment periods T are continued, the control system pushes the early warning information.
Compared with the prior art, the method and the device have the advantages that the monitoring parameters of the remote terminal are collected in real time, the monitoring parameters are analyzed according to the preset parameters, the abnormal pressure condition of the gas well in the stable production stage or the shut-in period can be accurately predicted, namely, whether the pressure of the annular space is abnormal or not can be accurately obtained according to the change of the A annular pressure (not reaching the annular pressure threshold value) in a certain period (the analysis and judgment period T), the abnormal pressure information of the gas well can be timely transmitted to the control terminal, the defect that the DCS is provided with the threshold value is avoided, the abnormality can be found and the early warning information can be pushed before the A annular pressure reaches the threshold value, so that field operators have sufficient time to process or timely process faults, the safety management gateway is effectively moved forward, the production and operation cost of the gas. The system is provided with a parameter optimization adjusting module, technicians can set (or automatically calculate through historical abnormal samples) preset parameters (including an analysis and judgment period) according to production experiences and combine on-site investigation of production operation, so that the early warning accuracy rate is obtained, and meanwhile, the technicians can continuously verify and optimize the parameters according to the experiences, so that the early warning rate is improved; that is to say, the parameter optimization adjustment module is arranged, so that a technician can automatically adjust the preset parameters according to production experience, for example, when a gas well and the like change, the technician can directly set the preset parameters without extracting historical abnormal sample information, and continuously verifies and optimizes the parameters in the use process, so as to obtain the preset parameters with high early warning accuracy.
Drawings
FIG. 1 is a diagram showing a variation law of parameters of a gas well under normal annulus pressure;
FIG. 2 is a schematic diagram of the warning logic for abnormal annulus pressure A;
FIG. 3 is a logic diagram of a parameter optimization adjustment module;
FIG. 4 is a preset parameter setting rule;
FIG. 5 is a flow chart of a verification analysis process of the early warning method;
FIG. 6 is a graph showing a variation trend of production parameters of an abnormal sample 1 during a stable production period;
FIG. 7 is a graph showing the variation trend of the production parameters during the shut-in period of the abnormal sample 2.
Detailed Description
For a better understanding and practice, the invention is described in detail below with reference to the accompanying drawings.
An oil and gas production operation safety early warning method based on big data technology comprises the following steps:
A) setting an analysis and judgment period T and setting a pre-judgment parameter, wherein the pre-judgment parameter comprises the analysis and judgment period T and a wellhead instantaneous gas volume variance limit value1Well head temperature variance limit2；
B) The data access module reads, analyzes and judges remote field parameter data in a period T in real time, wherein the field parameter data comprise wellhead instantaneous gas quantity, wellhead temperature and A annular pressure;
C) establishing an early warning model according to the prejudgment parameters, bringing the field parameter data into the early warning model, and obtaining the parameters of the problems to be diagnosed;
D) when the problem parameter to be diagnosed meets the requirement of the target parameter, pushing alarm information;
E) and when the problem parameter to be diagnosed does not meet the target parameter requirement, carrying out the next pre-pushing alarm period T, and repeating the steps B) and C), and pushing alarm information until the problem parameter to be diagnosed meets the target parameter requirement.
Example one
An oil and gas production operation safety early warning method based on big data technology comprises the following steps:
s101: confirming preset parameters according to all historical abnormal samples of a certain block of the DCS, namely the preset parameters comprise an analysis and judgment period T and a wellhead instantaneous gas volume variance limit value1Well head temperature variance limit2。
S102: selecting a first analysis judgment period T;
s103: the data access module reads data parameters of each time point in an analysis and judgment period T in the DCS, wherein the data parameters comprise wellhead instantaneous gas quantity, wellhead temperature and A annular pressure;
s104: respectively solving the variance S of the instantaneous gas quantity of the wellhead in the T time period1And wellhead temperature variance S2；
S105: if the instantaneous gas quantity variance S of the well head can not be satisfied simultaneously1<1And the temperature variance S of the well head2<2Reading the data parameters of the next analysis and judgment period T, namely repeating the steps S102 and S103 until the variance S of the instantaneous gas quantity of the wellhead1<1And the temperature variance S of the well head2<2；
S106: such as variance S of instantaneous gas quantity at well head1<1And the temperature variance S of the well head2<2Fitting the trend line of the change of the pressure of the annulus A by adopting a least square method, obtaining a fitting line formula y which is α t + β, and obtaining a derivative α of the trend line of the change of the pressure of the annulus A;
s107, if the derivative α is less than or equal to 0, reading the data parameter of the next analysis judgment period T, and repeating the steps S102, S103, S104 and S105 until the derivative α is greater than 0;
s108, if the derivative α is greater than 0, pushing early warning information;
wherein,1is the variance limit value of the instantaneous gas quantity of the well head,2for wellhead temperature variance limit, α and β are constants confirmed by a least square method, y is an annular pressure parameter A, and T is a time parameter in an analysis judgment period T.
In addition, the system also comprises a parameter optimization and adjustment module which plays a role in optimization and adjustment in a commissioning phase, and the parameter optimization and adjustment module comprises the following operation steps:
(1) setting preset parameters; the first preset parameter is confirmed according to all historical abnormal samples in a certain block of the DCS;
(2) sequentially operating the steps S102, S103 and S104, and when α is greater than 0, pushing early warning information and accumulating the total number of early warnings;
(3) arranging operators to carry out on-site investigation;
(4) if the on-site troubleshooting result is consistent with the early warning information, accumulating the accurate early warning number for one time; if the on-site troubleshooting result is inconsistent with the early warning information, accumulating an inaccurate early warning number;
(5) repeating the steps (2), (3) and (4) for N times, and counting the early warning accuracy;
(6) when the early warning accuracy reaches the target accuracy, stopping the parameter adjustment optimization process and setting required parameters;
(7) and (3) when the early warning accuracy rate does not reach the target accuracy rate, repeating the steps (1) and (5) until the early warning parameter accuracy rate reaches the target accuracy rate, stopping the parameter adjustment optimization process, and simultaneously setting required parameters.
Thirdly, the rule of the preset parameters is confirmed according to all historical abnormal samples of a certain block of the DCS, as shown in FIG. 3.
And (3) confirmation of the analysis and judgment period T: selecting all historical abnormal samples in a certain block of the DCS, counting the annular pressure rise time of all historical abnormal samples A in the block, wherein the analysis and judgment period T is smaller than the minimum value of the annular pressure rise time of all historical abnormal samples A in the block.
Variance limit of instantaneous gas quantity at well head1Confirmation of (2): dividing all historical samples of the block into a plurality of analysis and judgment periods T, counting wellhead instantaneous gas quantity variances within the analysis and judgment periods T, and limiting the wellhead instantaneous gas quantity variance1And the minimum value of the variance of the instantaneous gas quantity of the wellhead in the plurality of analysis and judgment periods T is smaller than the minimum value of the variance of the instantaneous gas quantity of the wellhead in the plurality of analysis and judgment periods T.
Well head temperature variance limit2Confirmation of (2): dividing all historical samples of the block into a plurality of analysis and judgment periods T, counting wellhead temperature variances within the analysis and judgment periods T, and limiting values of the wellhead temperature variances2And the minimum value of the wellhead temperature variance in the plurality of analysis and judgment periods T is smaller than the minimum value of the wellhead temperature variances in the plurality of analysis and judgment periods T.
In addition, the invention applies the following formula to establish the model.
(1) Variance calculation
The mean of a set of data represents the general level of the set of data, while the variance reflects the degree to which a set of data deviates from its mean. The variance is calculated as
The purpose of variance calculation in the scheme is to judge whether the instantaneous gas quantity is stable and the wellhead temperature is stable. Therefore, the x sequence in the formula is the wellhead instantaneous gas quantity and the wellhead temperature.
(2) Principle of least squares
Suppose that the real-time monitored A annular pressure data at different moments in a period of time is y0，y1…，yn. From these data an empirical formula between y and t is established, where a and b are undetermined constants.
Since the points are not in a straight line, we can only require choosing a and b such that f (t) α t + β at t0，t1…，tnFunction value of the position and real-time monitored A annular pressure data y0，y1…，ynThe phase difference being small, i.e. the deviation y is madei-f(ti) The method of selecting the constants a, b on the condition that the sum of squares of the deviations is minimal is called the least squares method (i ═ 0,1,2, …, n) is small. The constants a and b are therefore considered to be chosen such that the deviation M is minimal.
Taking M as a binary function of the arguments a and b, the problem can be solved by finding the minimum at those points of the function, and finding a and b based on the real-time monitored values of the annular pressure, to obtain a fitted trend line f (t) α t + β, α and β, as shown in equation (3).
Wherein α analyzes and judges the rising speed of the pressure in the annulus A in the period, and when α is larger than 0, the abnormal pressure in the annulus A is indicated.
Example two
The difference from the first embodiment is that: the preset parameters are manual input parameters.
In the actual production operation process, when the gas well is just put into use or in order to improve the efficiency, experienced technicians can directly set preset parameters, and then in the production operation process, continuous optimization and adjustment are carried out through the parameter optimization and adjustment module, so that the preset parameters with high early warning accuracy can be obtained.
The safety early warning scheme can be directly put into use by adopting manual parameter input without collecting historical abnormal data, and is particularly suitable for newly-exploited gas wells.
EXAMPLE III
The difference from the first embodiment or the second embodiment is that when a derivative α of each analysis and judgment period T is greater than 0 after a plurality of analysis and judgment periods T are continued, the control system pushes the early warning information.
Preferably, two analysis and judgment periods T are adopted, so that the workload of production operators can be effectively reduced, more accurate early warning can be realized, and the early warning error rate is reduced.
Use case
The inventor aims to verify the effect of the safety early warning method and goes to a development department of a certain project of the gas mine in the oil and gas field in southwest to carry out verification work, and the verification process is shown in figure 5. The method comprises the steps of firstly, collecting field production operation abnormal records through production daily reports to determine the name of a gas well with abnormal annulus pressure A, tracing the instantaneous gas quantity of a wellhead of a DCS system, the temperature of the wellhead and historical storage data of the annulus pressure A, then carrying out data preprocessing and data analysis, and finally carrying out verification analysis by taking early warning rules.
And (3) tracing production parameters of the DCS within the whole year from 5 months to 5 months in 2016 and 5 months in 2016, including wellhead instantaneous gas quantity, wellhead temperature and A annulus pressure, preprocessing the data and extracting two A annulus abnormal sample data of 008-H1 from the preprocessed data. Two abnormal sample production parameter profiles are plotted as shown in fig. 6 and 7.
exception sample data 2 describes: the A annular pressure value rises from 40.15MPa to 56.19MPa in the period of 2015 closing, 9 and 5 months, 2:30:00 to 2015, 9 and 9 months, 12:30:00, and the pressure value continuously and slowly rises for about 106 hours.
The safety early warning method and the traditional DCS system are compared and analyzed:
1) adopt present DCS system alarm strategy
A well site DCS system sets an A annular pressure alarm limit value to be 56MPa at present. The abnormal sample 1 does not reach the alarm limit value of the DCS, so the abnormal sample 1 is not found on the site; and the abnormal sample 2 reaches the alarm limit value of the DCS after the annular pressure rises for about 106 hours, and the alarm abnormal sample 2 is limited by the DCS and is found by field technicians.
2) The invention relates to a safety early warning method
The early warning rule is set to analyze and judge the period T to be 24 hours, the instantaneous gas volume and wellhead temperature data within 24 hours are statistically analyzed, the two parameters are known to be strictly stable according to the variance statistical value, then the annular pressure trend line A is fitted through the least square method, the derivative α of the annular pressure trend line A is obtained, the two abnormal samples are calculated to be larger than zero, and the two abnormal samples can be found after the annular pressure A abnormally rises for 24 hours through the early warning rule.
The safety early warning method is applied to test the abnormal annulus pressure phenomenon A of the abnormal sample 1; the abnormal band pressure phenomenon in the A annulus of the abnormal sample 2 is predicted 82 hours in advance. The verification and analysis results of the two abnormal samples of the gas well show that the gas well safety early warning rule based on data mining can predict the abnormal annular pressure phenomenon of the gas well.
It should be noted that, in this case, the process of collecting historical abnormal sample data in the DCS system to confirm the preset parameters and optimize the preset parameters is not described.
Compared with the prior art, the method and the device have the advantages that the monitoring parameters of the remote terminal are collected in real time, the monitoring parameters are analyzed according to the preset parameters, the abnormal pressure condition of the gas well in the stable production stage or the shut-in period can be accurately predicted, namely, whether the pressure of the annular space is abnormal or not can be accurately obtained according to the change of the A annular pressure (not reaching the annular pressure threshold value) in a certain period (the analysis and judgment period T), the abnormal pressure information of the gas well can be timely transmitted to the control terminal, the defect that the DCS is provided with the threshold value is avoided, the abnormality can be found and the early warning information can be pushed before the A annular pressure reaches the threshold value, so that field operators have sufficient time to process or timely process faults, the safety management gateway is effectively moved forward, the production and operation cost of the gas. The system is provided with a parameter optimization adjusting module, technicians can set (or automatically calculate through historical abnormal samples) preset parameters (including an analysis and judgment period) according to production experiences and combine on-site investigation of production operation, so that the early warning accuracy rate is obtained, and meanwhile, the technicians can continuously verify and optimize the parameters according to the experiences, so that the early warning rate is improved; that is to say, the parameter optimization adjustment module is arranged, so that a technician can automatically adjust the preset parameters according to production experience, for example, when a gas well and the like change, the technician can directly set the preset parameters without extracting historical abnormal sample information, and continuously verifies and optimizes the parameters in the use process, so as to obtain the preset parameters with high early warning accuracy.
The present invention is not limited to the above-described embodiments, and various modifications and variations of the present invention are intended to be included within the scope of the claims and the equivalent technology of the present invention if they do not depart from the spirit and scope of the present invention.
Claims (4)
1. An oil and gas production operation safety early warning method based on big data technology comprises the following steps:
A) setting preset parameters including analysis and judgment period T and wellhead instantaneous gas volume variance limit value1Well head temperature variance limit2；
B) The data access module reads, analyzes and judges remote field parameter data in a period T in real time, wherein the field parameter data comprise wellhead instantaneous gas quantity, wellhead temperature and A annular pressure;
C) establishing an early warning model according to preset parameters, bringing the field parameter data into the early warning model, and obtaining a problem parameter to be diagnosed, wherein the problem parameter to be diagnosed is α, and the target parameter requirement is α > 0;
D) when the problem parameter to be diagnosed meets the requirement of the target parameter, pushing alarm information;
E) when the parameter of the problem to be diagnosed does not meet the requirement of the target parameter, performing the next analysis and judgment period T, and repeating the steps B) and C), and when a plurality of analysis and judgment periods T are continuous and the derivative α of each analysis and judgment period T is greater than 0, controlling the system to push early warning information;
the early warning model establishment method comprises the following steps:
s101: selecting all historical abnormal samples in a certain block of the DCS, and counting the annular pressure rise time of all historical abnormal samples A in the block, wherein the analysis and judgment period T is less than the minimum value of the annular pressure rise time of all historical abnormal samples A in the block; the data access module reads data parameters of each time point in an analysis and judgment period T in the DCS, wherein the data parameters comprise wellhead instantaneous gas quantity, wellhead temperature and A annular pressure; dividing all historical samples of the block into a plurality of analysis and judgment periods T, counting wellhead instantaneous gas quantity variance and wellhead temperature variance in the plurality of analysis and judgment periods T, and limiting the wellhead instantaneous gas quantity variance1The variance of the instantaneous gas quantity of the wellhead is smaller than the minimum value of the variance of the instantaneous gas quantity of the wellhead in the plurality of analysis and judgment periods T; the wellhead temperature variance limit2Less than the minimum value of the wellhead temperature variance in the plurality of analysis and judgment periods T;
s102: respectively solving the variance S of the instantaneous gas quantity of the wellhead in the T time period1And wellhead temperature variance S2；
S103: if the instantaneous gas quantity variance S of the well head can not be satisfied simultaneously1<1And the temperature variance S of the well head2<2Reading the data parameters of the next analysis and judgment period T, namely repeating the steps S101 and S102 until the variance S of the instantaneous gas quantity of the wellhead1<1And the temperature variance S of the well head2<2；
S104: such as variance S of instantaneous gas quantity at well head1<1And the temperature variance S of the well head2<2Fitting the trend line of the annular pressure change A by adopting a least square method, and obtaining a fitting line formula y which is α t + β;
wherein,1is the variance limit value of the instantaneous gas quantity of the well head,2for wellhead temperature variance limit, α and β are constants confirmed by a least square method, y is an annular pressure parameter A, and T is a time parameter in an analysis judgment period T.
2. The safety precaution method according to claim 1, characterized by: the preset parameters are adjustable and are manual input parameters.
3. The safety precaution method according to any one of claims 1 to 2, characterized by: the device also comprises a parameter optimization and adjustment module.
4. The safety precaution method of claim 3, wherein: the parameter optimization adjustment module comprises the following operation steps,
(1) setting preset parameters;
(2) sequentially operating the steps S102, S103 and S104, and when α is greater than 0, pushing early warning information and accumulating the total number of early warnings;
(3) arranging operators to carry out on-site investigation;
(4) if the on-site troubleshooting result is consistent with the early warning information, accumulating the accurate early warning number for one time; if the on-site troubleshooting result is inconsistent with the early warning information, accumulating an inaccurate early warning number;
(5) repeating the steps (2), (3) and (4) for N times, and counting the early warning accuracy;
(6) when the early warning accuracy reaches the target accuracy, stopping the parameter adjustment optimization process and setting required parameters;
(7) and (3) when the early warning accuracy rate does not reach the target accuracy rate, readjusting the preset parameters, repeating the steps (1) and (5), stopping the parameter adjustment optimization process until the early warning parameter accuracy rate reaches the target accuracy rate, and simultaneously setting the required parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810341724.0A CN108765889B (en) | 2018-04-17 | 2018-04-17 | Oil and gas production operation safety early warning method based on big data technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810341724.0A CN108765889B (en) | 2018-04-17 | 2018-04-17 | Oil and gas production operation safety early warning method based on big data technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108765889A CN108765889A (en) | 2018-11-06 |
| CN108765889B true CN108765889B (en) | 2020-08-04 |
Family
ID=64010662
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810341724.0A Active CN108765889B (en) | 2018-04-17 | 2018-04-17 | Oil and gas production operation safety early warning method based on big data technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108765889B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109681196B (en) * | 2018-12-05 | 2023-01-24 | 中国石油化工股份有限公司 | Low-pressure shale gas well intermittent production management method and system |
| CN110148285B (en) * | 2019-05-15 | 2021-04-02 | 山东云科汉威软件有限公司 | Intelligent oil well parameter early warning system based on big data technology and early warning method thereof |
| CN112540235B (en) * | 2019-09-20 | 2023-02-17 | 中国石油化工股份有限公司 | Method and system for correcting lightning early warning threshold value and early warning evaluation method and system |
| CN114764966A (en) * | 2021-01-14 | 2022-07-19 | 新智数字科技有限公司 | Oil-gas well trend early warning method and device based on joint learning |
| CN113159608B (en) * | 2021-05-06 | 2022-04-22 | 广东鹰视能效科技有限公司 | Early warning abnormity processing method and system based on early warning identification |
| CN113256942B (en) * | 2021-05-18 | 2022-10-28 | 中海石油深海开发有限公司 | Advanced early warning method and device for abnormal event, electronic equipment and medium |
| CN113553724A (en) * | 2021-07-30 | 2021-10-26 | 中国石油化工股份有限公司 | A wellbore abnormality analysis and processing system in the production process of shale gas wells |
Family Cites Families (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5275040A (en) * | 1990-06-29 | 1994-01-04 | Anadrill, Inc. | Method of and apparatus for detecting an influx into a well while drilling |
| US7644290B2 (en) * | 2003-03-31 | 2010-01-05 | Power Measurement Ltd. | System and method for seal tamper detection for intelligent electronic devices |
| CN101967971B (en) * | 2010-08-23 | 2013-02-06 | 陈东 | Ternary fluid non-separation on-line measurement instrument |
| CN101976494B (en) * | 2010-08-26 | 2013-06-26 | 中国石油集团川庆钻探工程有限公司 | Logging real-time data acquisition and synchronous early warning method |
| US9671524B2 (en) * | 2011-12-31 | 2017-06-06 | Saudi Arabian Oil Company | Real-time dynamic data validation methods for intelligent fields |
| CN202882897U (en) * | 2012-10-10 | 2013-04-17 | 中国石油化工股份有限公司 | Downhole data collecting device |
| CN103726834B (en) * | 2012-10-10 | 2017-05-31 | 北京格瑞迪斯石油技术有限公司 | A kind of sustained casing pressure diagnosis device and method |
| CN103337000B (en) * | 2013-07-18 | 2016-06-15 | 中国石油化工股份有限公司 | A kind of safe monitoring and pre-alarming method of oil-gas gathering and transportation system |
| CN106227167A (en) * | 2013-12-30 | 2016-12-14 | 中国石油天然气股份有限公司 | Early warning method for running state of oil and gas production equipment |
| CN103745103B (en) * | 2013-12-31 | 2017-01-04 | 中国石油天然气股份有限公司 | Method and device for determining annular leakage rate of oil casing of gas well |
| CN105649609B (en) * | 2014-11-13 | 2018-09-04 | 中国石油天然气股份有限公司 | Method and system for acquiring annulus working pressure value of high-pressure gas well A |
| CN105717888B (en) * | 2014-12-05 | 2018-04-20 | 克拉玛依红有软件有限责任公司 | A kind of intelligent early-warning system |
| CN204759416U (en) * | 2015-05-12 | 2015-11-11 | 强艳玲 | Gas production curve is synthesized to gas well and analytic system thereof |
| CN105089591B (en) * | 2015-06-19 | 2017-09-01 | 中国石油天然气股份有限公司 | Method for determining annular gas-liquid interface of steam injection well |
| CN105785950B (en) * | 2016-04-13 | 2018-08-24 | 浙江大学 | A kind of landfill gas optimization of collection control system based on high in the clouds |
| CN106382102B (en) * | 2016-11-24 | 2019-01-18 | 西南石油大学 | A kind of overflow early warning method based on clustering algorithm |
| CN107390661B (en) * | 2017-08-28 | 2019-05-24 | 南京富岛信息工程有限公司 | A kind of method for early warning of process flow industry process abnormal state |
-
2018
- 2018-04-17 CN CN201810341724.0A patent/CN108765889B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| 《气井油管气渗引起的环空带压值预测模型研究》;严茂森;《气井油管气渗引起的环空带压值预测模型研究》;20170607;第44页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108765889A (en) | 2018-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108765889B (en) | Oil and gas production operation safety early warning method based on big data technology | |
| US9968899B1 (en) | Catalyst transfer pipe plug detection | |
| US10684631B2 (en) | Measuring and determining hot spots in slide valves for petrochemical plants or refineries | |
| US10754359B2 (en) | Operating slide valves in petrochemical plants or refineries | |
| US10739798B2 (en) | Incipient temperature excursion mitigation and control | |
| CN112943181B (en) | Intelligent gas well valve adjusting system | |
| US8201624B2 (en) | Clustered wellhead trunkline protection and testing system with ESP speed controller and emergency isolation valve | |
| CA2810721C (en) | Clustered wellhead trunkline protection and testing system with esp speed controller and emergency isolation valve | |
| US20180046155A1 (en) | Identifying and implementing refinery or petrochemical plant process performance improvements | |
| US20080208429A1 (en) | Systems and methods for steam turbine remote monitoring, diagnosis and benchmarking | |
| WO2008079799A2 (en) | Method and system for automated choke control on a hydrocarbon producing well | |
| WO2008014349A1 (en) | Method and system for detecting abnormal operation in a process plant | |
| CN116658492B (en) | Intelligent powered catwalk and method thereof | |
| AU2017208692A1 (en) | Method and apparatus for automated pressure integrity testing (apit) | |
| CN117291582A (en) | Industrial production interconnection monitoring system based on data analysis | |
| CN111720296A (en) | Steam feed pump equipment abnormal state early warning method based on self-encoder | |
| US10953377B2 (en) | Delta temperature control of catalytic dehydrogenation process reactors | |
| US20090125206A1 (en) | Automatic detection and notification of turbine internal component degradation | |
| Shoukas et al. | Analysis of fault data collected from automated fault detection and diagnostic products for packaged rooftop units | |
| CN116955955A (en) | Pipeline defect model prediction method, system, terminal equipment and storage medium | |
| CN115436051B (en) | Hydraulic support pressure abnormality identification method | |
| CN117371990A (en) | Hydropower plant tool intelligent management platform based on Internet of things | |
| CN105117985A (en) | Systematization method for equipment defect management for oil refining enterprises | |
| CN117669381A (en) | Long-distance heat supply pipeline safe operation method integrating dynamic simulation and real-time monitoring | |
| CN118835969A (en) | Intelligent monitoring and automatic regulating and controlling method for oil well steam channeling prevention |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201130 Address after: 100000 Beijing City, Xicheng District shop kang six Patentee after: CHINA NATIONAL PETROLEUM Corp. Patentee after: CHINA NATIONAL PETROLEUM CORPORATION SAFETY AND ENVIRONMENTAL TECHNOLOGY RESEARCH INSTITUTE Co.,Ltd. Address before: 102200 Building 1, 1 the Yellow River North Street, Changping District, Beijing. Patentee before: CHINA NATIONAL PETROLEUM CORPORATION SAFETY AND ENVIRONMENTAL TECHNOLOGY RESEARCH INSTITUTE Co.,Ltd. |