CN116066062A - Drilling sticking real-time early warning method based on parameter change trend abnormity diagnosis - Google Patents
Drilling sticking real-time early warning method based on parameter change trend abnormity diagnosis Download PDFInfo
- Publication number
- CN116066062A CN116066062A CN202111295151.0A CN202111295151A CN116066062A CN 116066062 A CN116066062 A CN 116066062A CN 202111295151 A CN202111295151 A CN 202111295151A CN 116066062 A CN116066062 A CN 116066062A
- Authority
- CN
- China
- Prior art keywords
- stuck
- stuck drill
- early warning
- real
- time
- 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.)
- Pending
Links
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21B—EARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
Abstract
The invention discloses a stuck drill real-time early warning method based on parameter change trend abnormity diagnosis, which determines key characterization parameters corresponding to stuck drill risks through expert knowledge judgment of stuck drill faults in the process of analyzing drilling operation, researches the change trend of the key characterization parameters of stuck drill occurrence sites and obtains corresponding change rules; on the basis, a stuck drill fault real-time early warning method based on engineering parameter change trend abnormity diagnosis is established, intelligent diagnosis of stuck drill faults is realized, the down-hole complex fault post-working diagnosis is updated to pre-early warning, and the diagnosis accuracy of abnormal working conditions is improved. The attack and application of the technology of the invention have important significance for improving the profit level of a deep shale gas drilling single well, reducing the complex and fault loss and improving the competitive power of teams in a work area.
Description
Technical Field
The invention relates to the field of drilling of deep shale gas complex stratum, in particular to a stuck drill real-time early warning method based on parameter variation trend abnormity diagnosis.
Background
During the drilling process, the phenomenon that the drilling tool is trapped in the well and cannot freely move due to various reasons is called sticking. The drilling tool cannot be lifted out of the well, even cannot be lowered or rotated, and some drilling tools cannot circulate drilling fluid, which is a common accident in drilling work.
The existing stuck drill fault identification mainly relies on an expert knowledge system or utilizes conventional logging data to analyze engineering anomalies, only a small amount of measurement and operation work is automatically completed by a computer, most of analysis and judgment are still completed manually, and due to individual knowledge, experience, responsibility and heart difference and other reasons, abnormal and complex drilling conditions cannot be found and processed in time, so that risks are increased; it is in fact impractical to require the operator to be attentively aware of the changes in the monitored data and to quickly ascertain the accident.
Therefore, the existing stuck drill identification technology is prominent in the problems of poor comprehensive utilization capability of monitoring information, insufficient time of risk early warning, strong subjectivity and the like.
Disclosure of Invention
The traditional stuck-at fault prediction method is excessively dependent on subjective judgment of an expert, and the prediction result is mostly qualitative or semi-quantitative. In view of the above, the invention provides a stuck drill real-time early warning method based on parameter change trend abnormity diagnosis, which realizes intelligent and real-time quantitative judgment of stuck drill faults and solves the problems of poor comprehensive utilization capability of monitoring information, insufficient in-time risk early warning, strong subjectivity and the like of the traditional prediction method.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a stuck drill real-time early warning method based on parameter variation trend abnormity diagnosis comprises the following steps:
s331, calculating a stuck drill key characterization parameter according to current and previous drilling real-time monitoring data, wherein the stuck drill key characterization parameter comprises: current mean movement deviation value Δm of several stuck indexes, and data regression slope absolute values of several previous time periods
S332, respectively determining whether the current average movement deviation value DeltaM of each drilling sticking index indicates a local increasing trend, and determining the absolute value of the data regression slope of a plurality of previous time periods
Sequentially increasing; if yes, the monitoring index probability of the corresponding stuck index is 1; if not, the monitoring index probability of the corresponding stuck index is 0;
s333, calculating a stuck risk index R according to the monitoring index probability of each stuck index and the weighting factors thereof sk 。
Preferably, in the step S331, a calculation formula of the average movement deviation Δm is as follows:
ΔM＝M α -M β (α＜β) (4)
wherein M is α And M β A moving average value of the current time t; alpha and beta are sliding window lengths; ΔM is an interpolation of the moving average at time t.
Preferably, in the step S331, an average local slope
The calculation formula of (2) is as follows:
wherein the regressive slope value at the time t is denoted as K i,t Positive value is positive trend, negative value is negative trend, w i An exponential transition from 0 to 1 is represented as a logical function, the formula:
preferably, in the step S331, the drill sticking index includes: suspended weight, torque and vertical pressure;
in the step S333, the stuck drill risk index R sk The calculation formula of (2) is as follows:
R sk ＝w D P D +w T P T +w P P P
wherein R is sk Is a stuck drill risk index; p (P) D 、P T 、P P Monitoring index probabilities of the suspended weight, the torque and the vertical pressure respectively; w (w) D 、w T 、w P Weight factors, respectively, determined by expert experience or historical well risk analysis, w D +w T +w P ＝1。
Preferably, in the step S331, the plurality of previous time periods are six time periods of 0.5, 1, 1.5, 2, 2.5 and 3min before the current time t.
Preferably, after the step S333, the method further includes the steps of:
step S334, judging the stuck drill risk index R sk Whether the bit sticking alarm threshold value is larger than the bit sticking alarm threshold value; if yes, go to step S335;
step S335, an alarm is issued.
Preferably, before the step S331, the method further includes the steps of:
s311, performing wild point elimination processing on drilling real-time monitoring data, wherein the wild point elimination processing comprises the following steps:
for an unconfirmed rational number A of engineering parameter response at a certain moment, adopting the expectation of the unconfirmed rational number A
Instead of;
A＝[[min(X i ),max(X i )],p(x)]；(1≤i≤N) (1)
wherein X is i Is a log value at a depth; p (x) is the confidence distribution function A of the log.
Preferably, before the step S331, the method further includes the steps of:
s312, parameter normalization processing is carried out on the drilling real-time monitoring data, and the method comprises the following steps:
carrying out normalization processing on engineering parameters by adopting a maximum and minimum method:
wherein x is min 、x max Respectively minimum and maximum in the sequence.
Preferably, before the step S331, the method further includes the steps of:
s320, carrying out working condition identification on the drilling state according to the drilling real-time monitoring data, and judging whether the operation belongs to any instantaneous operation or not; if yes, go to step S321; if not, go to step S331;
step S321: the data is read from the next time step and the regression start is reset.
Preferably, before the step S331, the method further includes the steps of:
s100, inducing a stuck drill fault qualitative judgment method;
s200, determining key characterization parameters and change rules of the stuck drill fault.
According to the technical scheme, the drilling sticking real-time early warning method based on the parameter change trend abnormity diagnosis provided by the invention is characterized in that firstly, through the expert knowledge judgment of drilling sticking faults in the drilling operation process, the key characterization parameters corresponding to the drilling sticking risk are determined, the change trend of the key characterization parameters of the drilling sticking occurrence sites is researched, and the corresponding change rule is obtained; then, a stuck drill fault real-time early warning method based on engineering parameter change trend abnormity diagnosis is established on the basis, intelligent diagnosis of stuck drill faults is realized, the down-hole complex fault after-working diagnosis is updated to pre-early warning, and the diagnosis accuracy of abnormal working conditions is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows the change rules of the symptoms and characterization parameters of the stuck pipe according to the embodiment of the invention;
fig. 2 is a flow of real-time early warning of stuck drill based on abnormal diagnosis of parameter variation trend provided by the embodiment of the invention;
FIG. 3 is a schematic diagram of VDX (well engineering parameters) monitoring data for a certain period of time for a XX well provided by an embodiment of the invention;
FIG. 4 is a graph showing the average shift deviation values of engineering parameters over a certain period of time for a XX well provided by an embodiment of the present invention;
FIG. 5 is a simulation result of XX well stuck fault early warning provided by the embodiment of the invention.
Detailed Description
Drilling operation is a very complex system, and is influenced by a large number of geological or engineering and human operation factors; a large amount of drilling data can be obtained in real time in the drilling process, and the traditional drilling risk evaluation method only depends on expert experience to qualitatively judge underground abnormality and risk, so that the safety requirement of the current deep well complex stratum cannot be met. Aiming at the problem, the invention provides a stuck drill real-time early warning method based on parameter change trend abnormity diagnosis. According to the method, through expert knowledge judgment of stuck drill faults in the drilling operation process, key characterization parameters corresponding to stuck drill risks are determined, the variation trend of the key characterization parameters of stuck drill occurrence sites is researched, and corresponding variation rules are obtained; on the basis, a stuck drill fault real-time early warning method based on engineering parameter change trend abnormity diagnosis is established, intelligent diagnosis of stuck drill faults is realized, the down-hole complex fault post-working diagnosis is updated to pre-early warning, and the diagnosis accuracy of abnormal working conditions is improved. The attack and application of the technology of the invention have important significance for improving the profit level of a deep shale gas drilling single well, reducing the complex and fault loss and improving the competitive power of teams in a work area.
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The specific implementation steps are as follows:
step one, a stuck drill fault qualitative judgment method;
drilling practice shows that certain symptoms are generated before the occurrence of underground risks in the drilling operation process, and experienced drilling engineering technicians can qualitatively judge whether underground risks occur, severity of the risks and the like by monitoring the change of key engineering parameters. Early warning is carried out on the risks which possibly occur in the early stage of risk occurrence, so that the risks can be regulated and controlled in time. During drilling, the drilling tool in the well cannot be lifted up or lowered down, and even cannot be twisted seriously, which is a complex situation called stuck drill. The stuck drill is divided into sticking, collapse, sand bridge, diameter reduction, key groove, mud bag, falling object stuck drill and the like according to different production reasons. Different types of stuck drills correspond to different judging methods, and the stuck drill qualitative judging methods are summarized by combining on-site drilling practice and judging according to expert knowledge, as shown in table 1.
Table 1 qualitative judgment method for different types of stuck drills
Step two, determining key characterization parameters of stuck drilling faults and exploring a change rule:
although the reasons for the stuck fault induction are different and the types of stuck faults are different, after the stuck fault occurs, the drill bit or the drilling tool loses the free movement capability in the pit due to the stuck caused by any reason, and the rule of the stuck fault represented by the measured data of the comprehensive logging is consistent. Analyzing faults under working conditions such as drilling in the drilling process, up-and-down movement of a drilling tool and the like, and corresponding to changes of underground measured data after the faults occur. After a stuck drill fault occurs in the drilling process, the change rules of parameters such as rising during drilling, rising of rotating disc torque, rising of vertical pipe pressure, and lowering of rotating speed are adopted; after the drill sticking occurs in the process of the drill taking, the change rules of parameters such as the increase of hook load, the increase of torque, the increase of riser pressure, the decrease of rotating speed and the like are adopted; after the drill sticking occurs in the drill-down engineering, the characteristic is that the change rule of parameters such as hook load reduction, torque increase, rotation speed increase and the like is presented. Through expert knowledge summary of stuck drill faults, engineering parameters capable of representing stuck drill faults are as follows: hook load, vertical weight, torque, rate of penetration, rotary table rotational speed, weight on bit (as shown in table 2).
Table 2 engineering parameters characterizing stuck pipe faults
Thirdly, a stuck drill early warning method based on parameter change trend abnormity diagnosis comprises the following steps:
drilling engineering is a hidden underground engineering, and the accident process is difficult to directly observe, but a great deal of field practice and related research show that: when the drilling accident is handled, the rules of the drilling tool can be found according to the change characteristics shown by the related signals (such as vertical pressure, suspended weight, mechanical drilling speed, change of drilling fluid inlet and outlet flow, change of friction resistance when the drilling tool moves up and down and rotates and the like) measured by the sensor. The trend of the stuck fault corresponding to the fault symptoms and signals needs to be determined by analyzing the measured data in a certain time period, rather than a single value at the current time point. The abnormal change of the parameter is reflected in the curve morphology, i.e. an increase or decrease in the slope of the curve (or tangent). When the stuck drill is generated, the outstanding appearance is that the suspended weight, the torque and the vertical pressure are subjected to floating change. And through automatic monitoring of time series suspended weight, torque and vertical pressure changes, the real-time early warning of the stuck drill fault is realized. The algorithm mainly comprises the following steps:
(1) Wild point rejection
The burrs or abrupt changes of the engineering parameter curves may be abnormal jumps or indeed downhole conditions. For abnormal jitter, burrs or mutations should be removed; for abrupt changes in downhole conditions, it should be preserved. If the measured value in a certain segment or the average value in the segment is simply taken, the influence of the abnormal value cannot be eliminated. The rational number method is not known to be able to identify outliers and truth mutation problems well.
Assuming that the engineering parameter response is an unknown rational number a at a certain moment, as shown in formula (1):
A＝[[min(X i ),max(X i )],p(x)]；(1≤i≤N) (1)
wherein X is i Is a log value at a depth; p (x) is the confidence distribution function of the log values.
Comparing outliers and truth mutations: if X i Is an outlier, it is isolated and has very little data in its neighborhood that is close to its value; if true mutation, then at X i More data is in the neighborhood of the number value. It is considered that X i The more data in the neighborhood that is close to it, the more X i Is high in reliabilityOn the contrary X i The reliability of (2) is small. The confidence distribution function is:
wherein n is i X represents i Intra-neighborhood |X i -X j The I is less than or equal to lambda; (i-delta < j < i+delta) contains X j Is a number of (3).
Thus, the expected unknown rational number A can be used
Instead, outlier rejection is implemented.
(2) Parameter normalization
And carrying out data normalization processing on engineering parameters, so as to avoid the problem of increased prediction result errors caused by large orders of magnitude difference of input data and output data. Normalization processing is carried out by adopting a maximum and minimum method:
wherein x is min 、x max Respectively minimum and maximum in the sequence.
(3) Drilling sticking early warning algorithm based on parameter change trend abnormity diagnosis
For the increasing trend shown by engineering parameters, introducing the deviation of a moving average value, and calculating the formula as follows:
ΔM＝M α -M β (α＜β) (4)
wherein M is α And M β Is the moving average of time t; alpha and beta are sliding window lengths; ΔM is an interpolation of the moving average at time t.
The average value of the short sliding window moves faster than the average value of the long sliding window. At the same time, when the moving average value of the shorter window is larger than that of the longer window, the delta M is a positive value to indicate that the data is in an increasing trend; conversely, ΔM tends to decrease when it is negative. The above technique is applicable only to quantifying increasing and decreasing trends of data, and in order to quantify anomalies in the trend of data changes, linear regression is applied to real-time data analysis, and the slope value of the regression at time t is recorded as
Positive values are positive trends and negative values are negative trends. The calculation formula of the average local slope is
Wherein w is i An exponential transition from 0 to 1 is represented as a logical function, the formula:
wherein lambda is 1 、λ 2 Respectively, controlling the position and sharpness of the transition lambda 1 ＝0.5-α，λ 2 ＝0.1；w i For the weighting factor of data point i before time step t, the weighting factor is close to 0 when i=t- α, and close to 1 when t- α < i+.ltoreq.t.
And respectively selecting 0.5, 1, 1.5, 2, 2.5 and 3min before the t moment to perform parameter change trend analysis, and if the slope is always increased and the data regression slope is greater than 0 within 0.5min before the t moment, indicating that the engineering parameter has abnormal increase trend. Such as: in the process of tripping, the regression slope of the data in 0.5, 1, 1.5, 2, 2.5 and 3min before the moment t of the suspension weight measurement parameter is increased all the time within 6 time periods, and the regression slope of the data in 0.5min before the moment t is greater than 0, so that the early warning of the blocking of the drilling is generated. Similarly, the stuck drill fault can be judged according to the torque and vertical pressure change rule. The stuck risk index may be calculated by assigning different weighting factors to probability values of the sling load monitoring indicator, the torque monitoring indicator, and the vertical pressure monitoring indicator. The stuck risk index value is between 0 and 1, and represents the probability of occurrence of a well stuck event, and the calculation formula is as follows:
R sk ＝w D P D +w T P T +w P P P (7)
wherein R is sk Is a stuck drill risk index; p (P) D 、P T 、P P Monitoring index probabilities of the suspended weight, the torque and the vertical pressure respectively; w (w) D 、w T 、w P As a weighting factor, determined by expert experience or historical well risk analysis.
The flow of the stuck fault early warning algorithm is shown in fig. 2, and the specific steps are as follows:
1) Firstly, removing abnormal points from real-time data before using a stuck drill monitoring algorithm, identifying the drilling state through real-time drilling parameters, and judging whether the operation belongs to any transient activity; the pretreatment process can establish a reasonable starting point for risk early warning and avoid false alarms caused by transient operation or abnormal points.
2) Calculating a stuck critical characterization parameter based on the data of the current and previous time steps: deviation of the sling weight, torque, vertical pressure moving average and local trend characteristics of 0.5, 1, 1.5, 2, 2.5 and 3min before the moment t. If the average movement deviation value indicates a local increasing trend and the absolute value of the regression slope of the data is always increased in 6 time periods, the drill sticking early warning is made according to the judgment criteria of the drill sticking faults under different working conditions.
3) The final stuck drill risk index can be obtained by allocating different weighting factors to the obtained probability values; and comparing the risk index with a stuck alarm threshold, and giving an alarm signal if the risk index exceeds the threshold. The stuck alarm threshold is set according to software early warning results and field condition comparison analysis.
Step four, training and optimizing an early warning model:
in order to verify the reliability of the algorithm, a large amount of historical data of the drilled well is selected, and the model is verified and trained by combining corresponding underground working conditions. XX well is selected as an example for analysis and figure 3 is monitoring data of drilling engineering parameters (torque, sling weight, vertical pressure) over a certain period of time.
By calculating the mean shift deviation of the engineering parameters over a certain period of time for the XX well, it can be seen from figure 4: after 2500s, the sliding average value of the long and short windows has obvious deviation, which indicates that engineering parameters fluctuate. Further, calculating the monitoring parameters of the suspended weight and the torque after 2500s, and local slopes in time periods of 0.5, 1, 1.5, 2, 2.5 and 3min before each moment, wherein when the suspended weight and the torque meet the requirement that the data regression slope is always increased in 6 time periods, and the data regression slope is larger than 0 in 0.5min before the moment t, the drilling sticking early warning occurs, and the early warning result is shown in figure 5. Looking up XX well Shi Baogao, and at 2600s, a scratch is made and then a stuck fault occurs. The example analysis shows that: the real-time early warning model of the stuck drill fault built in the method is accurate and reliable, early warning information can be given out at the early stage of the occurrence of the stuck drill risk, and corresponding measures can be taken in time to avoid the occurrence of the stuck drill.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A drilling sticking real-time early warning method based on parameter variation trend abnormity diagnosis is characterized by comprising the following steps:
s331, calculating a stuck drill key characterization parameter according to current and previous drilling real-time monitoring data, wherein the stuck drill key characterization parameter comprises: current mean movement deviation value Δm of several stuck indexes, and data regression slope absolute values of several previous time periods
S332, respectively determining whether the current average movement deviation value DeltaM of each drilling sticking index indicates a local increasing trend, and determining the absolute value of the data regression slope of a plurality of previous time periods
Sequentially increasing; if yes, the monitoring index probability of the corresponding stuck index is 1; if not, the monitoring index probability of the corresponding stuck index is 0;
s333, calculating a stuck risk index R according to the monitoring index probability of each stuck index and the weighting factors thereof sk 。
2. The method for early warning stuck drill based on the abnormal diagnosis of the parameter variation trend according to claim 1, wherein in the step S331, the calculation formula of the average movement deviation Δm is as follows:
ΔM＝M α -M β (α＜β) (4)
wherein M is α And M β A moving average value of the current time t; alpha and beta are sliding window lengths; ΔM is an interpolation of the moving average at time t.
3. The method for real-time early warning of stuck drill based on abnormal parameter variation trend diagnosis according to claim 1, wherein in step S331, the average local slope is
The calculation formula of (2) is as follows:
wherein the regressive slope value at the time t is denoted as K i,t Positive value is positive trend, negative value is negative trend, w i Is a logic function, and represents exponential transformation from 0 to 1, and the formula is：
4. The method for real-time early warning of stuck drill based on abnormal parameter variation trend diagnosis according to claim 1, wherein in the step S331, the stuck drill indicator comprises: suspended weight, torque and vertical pressure;
in the step S333, the stuck drill risk index R sk The calculation formula of (2) is as follows:
R sk ＝w D P D +w T P T +w P P P
wherein R is sk Is a stuck drill risk index; p (P) D 、P T 、P P Monitoring index probabilities of the suspended weight, the torque and the vertical pressure respectively; w (w) D 、w T 、w P Weight factors, respectively, determined by expert experience or historical well risk analysis, w D +w T +w P ＝1。
5. The method for real-time early warning of stuck drill based on abnormal parameter trend diagnosis according to claim 1, wherein in the step S331, the plurality of previous time periods are six time periods of 0.5, 1, 1.5, 2, 2.5 and 3min before the current time t.
6. The method for real-time early warning of stuck drill based on abnormal parameter variation trend diagnosis according to claim 1, further comprising the steps of, after step S333:
step S334, judging the stuck drill risk index R sk Whether the bit sticking alarm threshold value is larger than the bit sticking alarm threshold value; if yes, go to step S335;
step S335, an alarm is issued.
7. The method for real-time early warning of stuck drill based on abnormal parameter variation trend diagnosis according to claim 1, further comprising the steps of, before step S331:
s311, performing wild point elimination processing on drilling real-time monitoring data, wherein the wild point elimination processing comprises the following steps:
for an unconfirmed rational number A of engineering parameter response at a certain moment, adopting the expectation of the unconfirmed rational number A
Instead of;
A＝[[min(X i ),max(X i )],p(x)]；(1≤i≤N) (1)
wherein X is i Is a log value at a depth; p (x) is the confidence distribution function A of the log.
8. The method for real-time early warning of stuck drill based on abnormal parameter variation trend diagnosis according to claim 1, further comprising the steps of, before step S331:
s312, parameter normalization processing is carried out on the drilling real-time monitoring data, and the method comprises the following steps:
carrying out normalization processing on engineering parameters by adopting a maximum and minimum method:
wherein x is min 、x max Respectively minimum and maximum in the sequence.
9. The method for real-time early warning of stuck drill based on abnormal parameter variation trend diagnosis according to claim 1, further comprising the steps of, before step S331:
s320, carrying out working condition identification on the drilling state according to the drilling real-time monitoring data, and judging whether the operation belongs to any instantaneous operation or not; if yes, go to step S321; if not, go to step S331;
step S321: the data is read from the next time step and the regression start is reset.
10. The method for real-time early warning of stuck drill based on abnormal parameter variation trend diagnosis according to claim 1, further comprising the steps of, before step S331:
s100, inducing a stuck drill fault qualitative judgment method;
s200, determining key characterization parameters and change rules of the stuck drill fault.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111295151.0A CN116066062A (en) | 2021-11-03 | 2021-11-03 | Drilling sticking real-time early warning method based on parameter change trend abnormity diagnosis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111295151.0A CN116066062A (en) | 2021-11-03 | 2021-11-03 | Drilling sticking real-time early warning method based on parameter change trend abnormity diagnosis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116066062A true CN116066062A (en) | 2023-05-05 |
Family
ID=86177419
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111295151.0A Pending CN116066062A (en) | 2021-11-03 | 2021-11-03 | Drilling sticking real-time early warning method based on parameter change trend abnormity diagnosis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116066062A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116304958A (en) * | 2023-05-22 | 2023-06-23 | 山东中都机器有限公司 | Intelligent monitoring system and method for underground water treatment abnormality |
| CN116696286A (en) * | 2023-07-17 | 2023-09-05 | 大庆石油管理局有限公司 | Bottom driving tower type oil pumping machine |
-
2021
- 2021-11-03 CN CN202111295151.0A patent/CN116066062A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116304958A (en) * | 2023-05-22 | 2023-06-23 | 山东中都机器有限公司 | Intelligent monitoring system and method for underground water treatment abnormality |
| CN116304958B (en) * | 2023-05-22 | 2023-08-22 | 山东中都机器有限公司 | Intelligent monitoring system and method for underground water treatment abnormality |
| CN116696286A (en) * | 2023-07-17 | 2023-09-05 | 大庆石油管理局有限公司 | Bottom driving tower type oil pumping machine |
| CN116696286B (en) * | 2023-07-17 | 2023-11-21 | 大庆石油管理局有限公司 | Bottom driving tower type oil pumping machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116066062A (en) | Drilling sticking real-time early warning method based on parameter change trend abnormity diagnosis | |
| CN109508827B (en) | Drilling accident early warning method based on time recursion neural network | |
| CA2640727C (en) | Methods, systems, and computer-readable media for real-time oil and gas field production optimization using a proxy simulator | |
| CN108663995B (en) | Method and device for detecting abnormal trend of industrial process variable | |
| CN105089620B (en) | Monitoring system, the method and device of bit freezing | |
| CN110110740B (en) | Drilling process working condition identification method based on multi-time scale features and neural network | |
| CN110795853B (en) | Early overflow horizon while-drilling identification method in oil and gas drilling process | |
| CN114444823A (en) | Method and system for predicting lost circulation risk in drilling operation process | |
| GB2419983A (en) | Predict performance of drill bit employing multivariate least-squares model | |
| CN113062731A (en) | Intelligent identification method for complex working conditions under drilling well | |
| CN115841247A (en) | Digital drilling risk monitoring method and device | |
| Zhang et al. | A hierarchical early kick detection method using a cascaded GRU network | |
| CN113775327B (en) | Method, device, equipment, well drilling and storage medium for detecting well drilling abnormality | |
| CN115640759A (en) | Drill jamming early warning method and system based on machine learning | |
| CN113685166B (en) | Drilling accident early warning method and system | |
| CN114169656A (en) | Drilling stuck risk early warning method and system based on adjacent well historical data | |
| CN113868951A (en) | Method for intelligently judging optimal drilling short-start time | |
| CN114991757A (en) | Formation pressure measurement and recording integrated monitoring method and system while drilling | |
| CN109308570B (en) | Underground complex working condition identification method, device and system | |
| CN116701952B (en) | Knowledge-graph-based underground complex working condition identification method | |
| CN114970921A (en) | Early warning method and system for severity of drilling blockage | |
| CN108533244B (en) | Method and system for automatically identifying downhole state of drilling well | |
| CN117094236B (en) | High-precision calibration method for deep water drilling gas invasion data analysis | |
| CN117420150B (en) | Analysis and prediction system and prediction method based on drilling parameters | |
| RU2735794C1 (en) | Method for prediction of sticking of drilling pipes |
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 |