CN114565032A - Fracturing sand blocking early warning method and device based on pressure data - Google Patents

Fracturing sand blocking early warning method and device based on pressure data Download PDF

Info

Publication number
CN114565032A
CN114565032A CN202210157287.3A CN202210157287A CN114565032A CN 114565032 A CN114565032 A CN 114565032A CN 202210157287 A CN202210157287 A CN 202210157287A CN 114565032 A CN114565032 A CN 114565032A
Authority
CN
China
Prior art keywords
time period
current time
rmse
segmentation
pressure data
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.)
Granted
Application number
CN202210157287.3A
Other languages
Chinese (zh)
Other versions
CN114565032B (en
Inventor
胡晓东
周福建
王天宇
刘健
罗英浩
易普康
陈超
梁天博
李奔
曲鸿雁
姚二冬
王博
刘雄飞
杨凯
左洁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China University of Petroleum Beijing
Original Assignee
China University of Petroleum Beijing
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China University of Petroleum Beijing filed Critical China University of Petroleum Beijing
Priority to CN202210157287.3A priority Critical patent/CN114565032B/en
Publication of CN114565032A publication Critical patent/CN114565032A/en
Application granted granted Critical
Publication of CN114565032B publication Critical patent/CN114565032B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • 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

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Animal Husbandry (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Agronomy & Crop Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Mining & Mineral Resources (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Measuring Fluid Pressure (AREA)

Abstract

The patent refers to the field of 'investigating or analysing materials by determining their chemical or physical properties'. Acquiring pressure data in fracturing construction; clustering the pressure data to obtain pressure data in a plurality of time periods; fitting the pressure data in each time period once, and judging whether the fitting result of each time period meets the preset effect or not; if yes, determining an early warning result of the current time period according to the fitting result; if not, segmenting the current time period again to obtain a plurality of time periods after segmentation again, and determining the early warning result of each time period after segmentation again. The method can improve the fracturing sand plugging early warning accuracy and reduce the labor consumption.

Description

Fracturing sand blocking early warning method and device based on pressure data
Technical Field
The invention relates to the field of fracturing construction, in particular to a fracturing sand blocking early warning method and device based on pressure data.
Background
The world demand for oil and natural gas has been rising since the 21 st century, the oil and gas resources adopting conventional exploitation process means have been decreasing, and with the gradual deepening of exploration, the difficulty of development and production increase of conventional oil and gas resources has been increasing. According to relevant research and research, the reserves of unconventional oil and gas resources are abundant, and the strategic position of the resources of low-permeability oil and gas reservoirs is increasingly important in the face of huge energy requirements. Shale gas is listed as a new energy development key point at present, and an energy development plan is brought into consideration. The fracturing construction is one of the important means for exploiting unconventional oil and gas resources, and has wide application prospects in the aspects of oil and gas well yield increase and the like. In the fracturing construction process of a series of low-permeability oil and gas reservoirs such as shale gas, fracturing sand blocking is a main difficult problem influencing the fracturing effect and the cost benefit.
The fracturing sand blocking is a phenomenon that in a sand adding stage in a fracturing construction process, a propping agent is gathered around a fracturing well bottom or in a fracture to form blocking, so that the construction pressure is rapidly increased in a short time, and further the fracturing construction is difficult to continue. When sand blocking occurs, construction materials such as fracturing fluid and the like are wasted, a pipeline is damaged due to high pressure, equipment is damaged, the operation time is prolonged, the operation cost is increased, and stratum seepage can be caused to cause fracturing operation failure or even serious casualty accidents. Therefore, if the sand blockage early warning device can early warn the sand blockage in fracturing construction, effective countermeasures can be taken timely, and the sand blockage early warning device has important significance for avoiding the sand blockage.
At present, when sand blocking early warning is carried out on a fracturing site, pressure curve monitoring is carried out by manual naked eyes, whether sand blocking occurs or not is artificially analyzed according to experience and technical knowledge of experts, the mode requires engineering technical personnel to observe the pressure curve all the time in the construction process, and due to the fact that accurate auxiliary calculation is not carried out, the manual identification effect is different from person to person, the early warning accuracy is low, and manpower is consumed.
Therefore, a fracturing sand plugging early warning method based on pressure data is needed at present, the fracturing sand plugging early warning accuracy can be improved, and the labor consumption is reduced.
Disclosure of Invention
The embodiment of the invention aims to provide a fracturing sand blockage early warning method and device based on pressure data, so that the fracturing sand blockage early warning accuracy is improved, and the labor consumption is reduced.
In order to achieve the above object, in one aspect, an embodiment herein provides a fracturing sand plugging early warning method based on pressure data, including:
acquiring pressure data in fracturing construction;
clustering the pressure data to obtain pressure data in a plurality of time periods;
fitting the pressure data in each time period once, and judging whether the fitting result of each time period meets the preset effect;
if yes, determining an early warning result of the current time period according to the fitting result;
if not, segmenting the current time period again to obtain a plurality of time periods after segmentation again, and determining the early warning result of each time period after segmentation again.
Preferably, the segmenting the current time period again to obtain a plurality of time periods after the segmentation again, and determining the early warning result of each time period after the segmentation again further includes:
judging whether the total number of the pressure data in each time period after the re-segmentation is less than a set number or not;
if so, determining an early warning result of the current time period after the re-segmentation according to the fitting result of the current time period before the re-segmentation;
if not, fitting the pressure data in the current time period after the re-segmentation once, executing the step of judging whether the fitting result of each time period accords with the preset effect, and judging whether the fitting result of the current time period after the re-segmentation accords with the preset effect.
Preferably, the fitting the pressure data for each time period further comprises:
fitting the pressure data in each time period for one time to obtain fitting data in each time period;
and calculating the root mean square error of each time period according to the fitting data and the pressure data in each time period.
Preferably, the determining whether the fitting result of each time period meets the predetermined effect further includes:
comparing the root mean square error of each time period with a dynamic threshold corresponding to each time period;
if the root mean square error of the current time period is not greater than the dynamic threshold corresponding to the current time period, the fitting result of the current time period accords with the preset effect;
and if the root mean square error of the current time period is greater than the dynamic threshold corresponding to the current time period, the fitting result of the current time period is not in accordance with the preset effect.
Preferably, the step of fitting the pressure data in the current time period after the re-segmentation once and determining whether the fitting result of each time period meets the predetermined effect as described above includes:
updating the dynamic threshold of the current time period after the first root mean square error;
comparing the second root mean square error of the current time period after the segmentation with the dynamic threshold of the current time period after the segmentation;
if the second root mean square error of the current time period after the re-segmentation is not greater than the dynamic threshold of the current time period after the re-segmentation, the fitting result of the current time period after the re-segmentation accords with the preset effect;
and if the second root mean square error of the current time period after the re-segmentation is larger than the dynamic threshold of the current time period after the re-segmentation, the fitting result of the current time period after the re-segmentation does not accord with the preset effect.
Preferably, the updating the dynamic threshold of the current time period after the segmentation further includes:
updating the dynamic threshold for the current re-segmented time period by the following formula:
if RMSE < ═ RMSE _ Threshold0If RMSE _ Total is equal to RMSE _ Total0+rmse，
RMSE_Cnt＝RMSE_Cnt0+1；
RMSE_Avg0＝RMSE_Threshold0/n；
If RMSE _ Cnt is less than or equal to 0, RMSE _ Avg is equal to RMSE _ Avg0Otherwise, if the RMSE _ Cnt is greater than 0, RMSE _ Avg is equal to RMSE _ Total/RMSE _ Cnt (1- ω) + RMSE _ Avg0*ω；
RMSE_Threshold＝n*RMSE_Avg；
Wherein RMSE _ Threshold is an updated dynamic Threshold corresponding to a current time period after re-segmentation, and RMSE _ Threshold0The dynamic threshold value to be updated is corresponding to the current time period after the segmentation; rmse is the second of the current re-segmented time periodA root mean square error; RMSE _ Total0Is 0, RMSE _ Cnt0Is 0; n is any positive integer; ω is an attenuation coefficient and takes an arbitrary value between 0 and 1.
Preferably, the segmenting the current time period again to obtain a plurality of time periods after the segmentation again further includes:
performing quadratic fitting on pressure data in the current time period to obtain a quadratic polynomial, and determining a stagnation point of the quadratic polynomial;
and inserting the stagnation point as an interpolation into the current time period to obtain the stagnation point and the time period on the left side of the stagnation point, and the stagnation point and the time period on the right side of the stagnation point.
In another aspect, embodiments herein provide a fractured sand plugging early warning device based on pressure data, the device including:
the acquisition module is used for acquiring pressure data in fracturing construction;
the clustering module is used for clustering the pressure data to obtain pressure data in a plurality of time periods;
the judging module is used for fitting the pressure data in each time period once and judging whether the fitting result of each time period meets the preset effect or not;
if yes, determining an early warning result of the current time period according to the fitting result;
if not, segmenting the current time period again to obtain a plurality of time periods after segmentation again, and determining the early warning result of each time period after segmentation again.
In yet another aspect, embodiments herein also provide a computer device comprising a memory, a processor, and a computer program stored on the memory, the computer program, when executed by the processor, performing the instructions of any one of the methods described above.
In yet another aspect, embodiments herein also provide a computer-readable storage medium having stored thereon a computer program, which when executed by a processor of a computer device, performs the instructions of any one of the methods described above.
According to the technical scheme provided by the embodiment, the embodiment of the invention has the advantages that the early warning accuracy is improved and the manpower consumption is reduced compared with the method for early warning the sand blockage occurrence by means of manual experience in the prior art by performing one-time fitting on the clustered pressure data and determining the early warning result according to the fitting result.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments or technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 shows a schematic flow chart of a fracturing sand plugging early warning method based on pressure data provided in an embodiment of the present disclosure;
fig. 2 is a sub-flow diagram illustrating a method for early warning of sand plugging in a fracture based on pressure data provided in an embodiment of the present disclosure;
FIG. 3 illustrates a flow diagram for re-segmentation provided by embodiments herein;
FIG. 4 illustrates a schematic flow chart for once fitting pressure data over each time period as provided by embodiments herein;
fig. 5 shows a schematic flow chart for determining a fitting result for each time period provided in an embodiment herein;
FIG. 6 illustrates another sub-flow schematic diagram of a method for early warning of sand plugging in a fracture based on pressure data provided by an embodiment of the present disclosure;
fig. 7 is a schematic block diagram illustrating a fractured sand plugging early warning device based on pressure data provided in an embodiment of the present disclosure;
fig. 8 shows a schematic structural diagram of a computer device provided in an embodiment herein.
Description of the symbols of the drawings:
100. an acquisition module;
200. a clustering module;
300. a judgment module;
802. a computer device;
804. a processor;
806. a memory;
808. a drive mechanism;
810. an input/output module;
812. an input device;
814. an output device;
816. a presentation device;
818. a graphical user interface;
820. a network interface;
822. a communication link;
824. a communication bus.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments herein without making any creative effort, shall fall within the scope of protection.
The fracturing sand blocking is a phenomenon that in a sand adding stage in a fracturing construction process, a propping agent is gathered around a fracturing well bottom or in a crack to form blocking, so that the construction pressure is sharply increased in a short time, and further the fracturing construction is difficult to continue. When sand blocking occurs, construction materials such as fracturing fluid and the like are wasted, a pipeline is damaged due to high pressure, equipment is damaged, the operation time is prolonged, the operation cost is increased, and stratum seepage can be caused to cause fracturing operation failure or even serious casualty accidents. Therefore, if the early warning can be carried out on the sand blockage in the fracturing construction, effective countermeasures can be taken in time, and the method has important significance for avoiding the sand blockage.
At present, when sand blocking early warning is carried out on a fracturing site, pressure curve monitoring is carried out by manual naked eyes, whether sand blocking occurs or not is artificially analyzed according to experience and technical knowledge of experts, the mode requires engineering technical personnel to observe the pressure curve all the time in the construction process, and due to the fact that accurate auxiliary calculation is not carried out, the manual identification effect is different from person to person, the early warning accuracy is low, and manpower is consumed.
In order to solve the above problems, embodiments herein provide a fracturing sand plugging early warning method based on pressure data. Fig. 1 is a schematic diagram of the steps of a method for early warning of sand plugging in fracturing based on pressure data provided in the embodiments herein, and the present specification provides the method operation steps as described in the embodiments or the flow charts, but more or less operation steps can be included based on conventional or non-creative labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an actual system or apparatus product executes, it can execute sequentially or in parallel according to the method shown in the embodiment or the figures.
Referring to fig. 1, a fracturing sand plugging early warning method based on pressure data includes:
s101: acquiring pressure data in fracturing construction;
s102: clustering the pressure data to obtain pressure data in a plurality of time periods;
s103: fitting the pressure data in each time period once, and judging whether the fitting result of each time period meets the preset effect;
s104: if yes, determining an early warning result of the current time period according to the fitting result;
s105: if not, segmenting the current time period again to obtain a plurality of time periods after segmentation again, and determining the early warning result of each time period after segmentation again.
In the sand adding stage in the fracturing construction process, sand needs to be introduced into the fracture formed by fracturing through the casing, and pressure data of the casing in the process is collected. If the pressure data rapidly and continuously rises in a short time, the probability of sand blockage is predicted to be very high, so that the pressure data can reflect the probability of sand blockage, and the sand blockage condition needs to be judged and early warned through the pressure data.
After the pressure data is obtained, in order to improve the accuracy of subsequent calculation, the pressure data with the sand concentration of 0 when sand and stone are just injected in the early stage of fracturing can be eliminated, the specific elimination method can synchronously obtain the sand concentration while obtaining the pressure data, and then the pressure data corresponding to the point with the sand concentration of 0 is eliminated.
In this embodiment, the pressure data may be clustered, and since the clustered pressure data in each class has continuity in the time dimension, that is, the pressure data in a certain time period is generally clustered into one class, and then the pressure data in a plurality of time periods is obtained, generally, each time period is about 15 s. It should be explained that, in the process of clustering the pressure data, there may be a case where there is only one pressure data in a class, and for this case, the default is the noise point of the pressure data bit, and the point is removed.
Specifically, the pressure data may be clustered by an ap (affinity propagation) clustering algorithm. The AP clustering algorithm is a clustering algorithm based on "information transfer" between data points, and the number of clusters need not be determined before running the algorithm. The AP algorithm will look for the cluster center point as a representative for each class, and that point is the actual point in the data set.
When fitting the pressure data in each time segment once, because two adjacent time segments after clustering are discontinuous, in order to prevent the data points at the end points of the two adjacent time segments from being lost due to clustering, the last data point of the previous time segment in the adjacent time segments after clustering is taken as the starting data point of the next time segment.
After the pressure data in each time period is fitted once, a fitting result corresponding to each time period can be obtained, wherein fitting can be performed through a least square method, a fitting line obtained in each time period after fitting is a fitting result, if fitting of the fitting line is accurate, a preset effect is achieved, and if the set of the fitting lines is inaccurate, the preset effect is not achieved.
If the fitting result meets the preset effect, the early warning result of the current time period can be determined according to the fitting result. If the fitting result does not accord with the preset effect, the current time period needs to be segmented again, and the early warning result of each time period after segmentation is determined.
According to the method, the clustered pressure data are fitted once, and the early warning result is determined according to the fitting result, so that the early warning accuracy is improved and the manpower consumption is reduced compared with a method for early warning the sand blockage by means of manual experience in the prior art.
Referring to fig. 2, in this embodiment, the segmenting the current time period again to obtain a plurality of re-segmented time periods, and determining the early warning result of each re-segmented time period further includes:
s201: judging whether the total number of the pressure data in each time period after the re-segmentation is less than a set number or not;
s202: if so, determining the early warning result of the current time period after the re-segmentation according to the fitting result of the current time period before the re-segmentation;
s203: if not, fitting the pressure data in the current time period after the re-segmentation once, executing the step of judging whether the fitting result of each time period accords with the preset effect, and judging whether the fitting result of the current time period after the re-segmentation accords with the preset effect.
The set number is the minimum number of data points necessary for the set segmentation, and can be 2, and if the total number of pressure data in the current time period after the segmentation is less than 2, the early warning result of the current time period after the segmentation is directly determined according to the fitting result before the segmentation, and least square fitting cannot be performed. The reason is that the total number of pressure data less than 2 is not representative, and the data amount is too small. And if the number of the pressure data in the current time period after the re-segmentation is not less than 2, performing one-time fitting on the pressure data in the current time period after the re-segmentation, and executing the steps from S103 to S105.
By integrating the above S101 to S203, it can be understood that if a time period a is obtained after clustering, and if the fitting result corresponding to a does not meet the predetermined effect, segmentation is performed again to obtain a1 and a2, and if the total number of the corresponding pressure data in a1 is 1, the early warning result of a1 needs to be determined according to the fitting result of a; and if the total number of the corresponding pressure data in the A2 is more than 2, judging whether the fitting result of the A2 meets the preset effect, and if not, performing re-segmentation … … on the A2 until the early warning result of the current time period can be determined.
The process is a cyclic process, the cyclic termination condition is that the fitting result of the current time period accords with the preset effect, and then the early warning result of the current time period is determined, or the total number of the pressure data of the current time period is less than 2, and the early warning result of the current time period is determined according to the fitting result before the current time period is segmented. It should be noted that, in the present embodiment, the segmentation is performed into two segments, but those skilled in the art will understand that multiple segments may be formed after the segmentation.
Referring to fig. 3, further, in this embodiment, the segmenting the current time segment again to obtain a plurality of segments further includes:
s301: performing quadratic fitting on the pressure data in the current time period to obtain a quadratic polynomial, and determining a stagnation point of the quadratic polynomial;
s302: and inserting the stagnation point as an interpolation into the current time period to obtain the stagnation point and the time period on the left side of the stagnation point, and the stagnation point and the time period on the right side of the stagnation point.
Specifically, the stagnation point is a point with a tangent line of 0, a quadratic polynomial is obtained by quadratic fitting pressure data in a current time period by using a least square method, a stagnation point in the quadratic polynomial is selected, the stagnation point is correspondingly inserted into the current time period, for example, coordinates corresponding to the stagnation point are (x, y), the stagnation point is inserted into an x-th time of the current time period, pressure data corresponding to the x-th time is y, and in order to ensure continuity between the time periods after re-segmentation, the stagnation point and the time period on the left side of the stagnation point, the stagnation point and the time period on the right side of the stagnation point need to be divided.
It should be noted that, if the stagnation point is exactly a certain pressure data in the current time period, the stagnation point does not need to be used as an interpolation for performing an interpolation operation, and the current time period is directly divided into the stagnation point and the time period on the left side of the stagnation point, and the stagnation point and the time period on the right side of the stagnation point.
Of course, the stagnation point may be exactly the boundary point of the current time period, and assuming that there are pressure data 1-10 in the current time period a, when the current time period a is re-segmented, the stagnation point is exactly the pressure data 10, and when the current time period is re-segmented, the segmentation is divided into a 1: 1-10, A2: 10, when the segmentation operation is performed circularly, the stagnation point of a1 is also 10, and a1 is divided into a 11: 1-10, A12: 10, falling into a dead cycle, in order to avoid the situation, if the stagnation point is exactly the boundary point of the current time period, stopping executing the cycle segmentation operation, directly determining the early warning result according to the fitting result before segmentation, namely stopping performing segmentation again on the a1, and determining the early warning result according to the fitting result of the a.
In addition, the stagnation point may not be in the range of the current time period, for example, in the process of obtaining a1 and a2 by subdividing the current time period a, the calculated stagnation point is not in the range of a, and at this time, the pre-warning result is directly determined according to the fitting result before the subdivision, that is, the re-segmentation of a1 is stopped, and the pre-warning result is determined according to the fitting result of a.
Referring to fig. 4, in the present embodiment, said fitting the pressure data for each time period further comprises:
s401: fitting the pressure data in each time period once to obtain fitting data in each time period;
s402: and calculating the root mean square error of each time period according to the fitting data and the pressure data in each time period.
Specifically, when the pressure data in each time period is subjected to primary fitting, the primary fitting is performed by adopting a least square method to obtain a first-order polynomial in the form of s1(x) Fitting the pressure data in each time period once to obtain parameters a and b, wherein the fitting data obtained after fitting once is the fitting determined by the parameters a and bA straight line. The fitting straight line is the fitting result, the root mean square error can measure the fitting effect of the fitting straight line, and if the root mean square error is too large, the fitting effect is poor.
The root mean square error in each time segment is calculated by the root mean square error formula:
Figure BDA0003512700930000101
wherein, yiTo fit the ith fit data on the straight line,
Figure BDA0003512700930000102
and (4) actual pressure data corresponding to the ith fitting data, wherein m is the total number of the pressure data in each time period, and rmse is the root mean square error.
And after the root mean square error of each time period is obtained through calculation, taking the root mean square error of each time period as a fitting result of the time period.
Referring to fig. 5, in this embodiment, the determining whether the fitting result of each time period meets the predetermined effect further includes:
s501: comparing the root mean square error of each time period with a dynamic threshold corresponding to each time period;
s502: if the root mean square error of the current time period is not greater than the dynamic threshold corresponding to the current time period, the fitting result of the current time period accords with the preset effect;
s503: and if the root mean square error of the current time period is greater than the dynamic threshold corresponding to the current time period, the fitting result of the current time period is not in accordance with the preset effect.
And if the fitting result of the current time period is in accordance with the preset effect, determining the early warning result of the current time period according to the root mean square error, and if the fitting result of the current time period is not in accordance with the preset effect, segmenting the current time period again.
If the current time period is the first time period, the dynamic threshold corresponding to the current time period is a value set according to an actual situation, and may be any value greater than 0 and less than 1, preferably 0.3-0.8, if the current time period is not the first time period, the dynamic threshold needs to be updated, and the dynamic threshold of the current time period is obtained according to the root mean square error of the previous time period corresponding to the current time period. For example, clustering results in time segments A, B, C (in chronological order), where A is the first time segment and B and C are not the first time segment.
Referring to fig. 6, in this embodiment, said performing a fitting on the pressure data in the current time period after the re-segmentation once, and performing the step of determining whether the fitting result of each time period meets the predetermined effect as described above, wherein the determining whether the fitting result of the current time period after the re-segmentation meets the predetermined effect includes:
s601: updating the dynamic threshold of the current time period after the segmentation again according to the first root mean square error of the current time period after the segmentation again;
s602: comparing the second root mean square error of the current time period after the segmentation with the dynamic threshold of the current time period after the segmentation;
s603: if the second root mean square error of the current time period after the re-segmentation is not greater than the dynamic threshold of the current time period after the re-segmentation, the fitting result of the current time period after the re-segmentation accords with the preset effect;
s604: and if the second root mean square error of the current time period after the re-segmentation is larger than the dynamic threshold of the current time period after the re-segmentation, the fitting result of the current time period after the re-segmentation does not accord with the preset effect.
It should be clear that the first root mean square error and the second root mean square error of the current time period after the re-segmentation are two values, the second root mean square error is the root mean square error calculated by the above formula (1) of the current time period after the re-segmentation, and the first root mean square error is the root mean square error of the previous time period or the mother time period of the current time period after the re-segmentation.
Specifically, if a time period a is obtained after clustering, and if the fitting result corresponding to a does not meet the predetermined effect, segmentation is performed again to obtain a1 and a 2. Since the time period a is obtained after clustering, according to the above S401 to S503, the root mean square error of a is obtained, and the root mean square error of a is certainly larger than the dynamic threshold M0 of a (the fitting result does not meet the predetermined effect). For the first root mean square error of a1 obtained after a is re-segmented, since the first root mean square error is the root mean square error of the previous time period or the mother time period of the current time period after the re-segmentation, a is the mother time period of a1, and the root mean square error of the mother time period of a1 is the root mean square error of a, a dynamic threshold M1 corresponding to a1 is obtained by updating the dynamic threshold M0 with the root mean square error of a, and then the root mean square error (the second root mean square error of a1) calculated by a1 itself is compared with the dynamic threshold M1 corresponding to a1, so as to determine whether the fitting result corresponding to a1 meets the predetermined effect.
For the time period a2, the dynamic threshold needs to be updated according to the first root mean square error corresponding to the time period a2, that is, the dynamic threshold M1 needs to be updated, because the first root mean square error is the root mean square error of the previous time period or the parent time period of the current time period after the re-segmentation, a1 is the previous time period of a2, and at this time, the first root mean square error corresponding to a2 is the root mean square error calculated by the a1 itself. And updating the dynamic threshold M1 through the first root mean square error corresponding to A2 to obtain a dynamic threshold M2 corresponding to A2, then comparing the root mean square error calculated by A2, namely the second root mean square error of A2 with the dynamic threshold M2 corresponding to A2, and determining whether the fitting result corresponding to A2 meets the preset effect.
Therefore, if the current time period (a1) after re-segmentation is the first time period after re-segmentation of the corresponding parent time period (a), the first root mean square error of the current time period after re-segmentation is the root mean square error of the parent time period (a), and if the current time period (a2) after re-segmentation is not the first time period after re-segmentation of the corresponding parent time period (a), the first root mean square error of the current time period after re-segmentation is the root mean square error of the previous time period (a 1).
As can be seen from S501 to S503, if the time periods a and B are obtained after clustering, if a is the first time period and B is a time period after a in the time sequence, the dynamic threshold M0 of a is an arbitrary value greater than 0 and less than 1. Assuming that after a is divided into a1 and a2, a1 and a2 both meet a predetermined effect, at this time, the dynamic threshold of B needs to be updated according to the root mean square error of the previous time period of B, where the previous time period of B is a2, that is, the dynamic threshold of B is updated according to the root mean square error of a2, and actually, the root mean square error of a2 is the second root mean square error of a 2.
It should be noted that assuming that the fitting result corresponding to B does not meet the predetermined effect, segmentation is performed again to obtain B1 and B2. The previous period of B1 was B, and the previous period of B2 was B1.
From the above description it can be seen that: the method for updating the dynamic threshold of the time period after the re-segmentation is to update the dynamic threshold by using the root mean square error of the mother time period or the previous time period on the basis of the dynamic threshold of the mother time period or the previous time period. It should be clear that, for each current time segment (A, B or C) obtained after clustering, only the dynamic threshold of the first time segment (a1, B1 or C1) obtained after re-segmentation is obtained by updating the root mean square error of the parent time segment (A, B or C) on the basis of the parent time segment (a1 corresponding to A, B1 corresponding to B or C1 corresponding to C); and the dynamic threshold of the non-first time segment (A2, B2 or C2) in the time segments obtained after the re-segmentation is updated by the root mean square error of the previous time segment (A2 corresponds to A1, B2 corresponds to B1 or C2 corresponds to C1) on the basis of the previous time segment.
For the time segment B after the first time segment a after clustering, the dynamic threshold of B is updated by the root mean square error of the previous time segment (a2) on the basis of the previous time segment (a2) of B, if B is segmented into B1 and B2 again, the dynamic threshold of B1 is updated by the root mean square error of the mother time segment (B) on the basis of the mother time segment (B) of B1, and the dynamic threshold of B2 is updated by the root mean square error of the previous time segment (B1) on the basis of the previous time segment (B1) of B2.
In this embodiment, the updating the dynamic threshold for the current time period after re-segmentation further comprises:
updating the dynamic threshold for the current re-segmented time period by the following formula:
step 1:
if RMSE < ═ RMSE_Threshold0If the RMSE _ Total is equal to the RMSE _ Total0+rmse，RMSE_Cnt＝RMSE_Cnt0+1；
Step 2:
RMSE_Avg0＝RMSE_Threshold0/n；
and step 3:
if RMSE _ Cnt is less than or equal to 0, RMSE _ Avg is equal to RMSE _ Avg0Otherwise, if the RMSE _ Cnt is greater than 0, RMSE _ Avg is equal to RMSE _ Total/RMSE _ Cnt (1- ω) + RMSE _ Avg0*ω；
And 4, step 4:
RMSE_Threshold＝n*RMSE_Avg；
wherein RMSE _ Threshold is an updated dynamic Threshold corresponding to a current time period after re-segmentation, and RMSE _ Threshold0A dynamic Threshold value RMSE _ Threshold to be updated corresponding to the current time period after the segmentation0The initial value of (A) may be any value greater than 0 and less than 1, preferably 0.3 to 0.8; rmse is a first root mean square error of the current time period after the segmentation; RMSE _ Total0The RMSE _ Total is the RMSE _ Total of the previous time period or the mother time period corresponding to the current time period after the re-segmentation, and the initial value is 0; RMSE _ Cnt0The initial value of RMSE _ Cnt of the previous time period or the mother time period corresponding to the current time period after the re-segmentation is 0; n is any positive integer, preferably 1-5; ω is an attenuation coefficient and takes an arbitrary value between 0 and 1.
First, it should be clear that, in the above step 1-4, the dynamic threshold corresponding to the time period after the updating of the current re-segmentation in the above steps S601-S604 may be used, or the dynamic threshold corresponding to the current time period (not the first time period) after the updating of the cluster in the above steps S501-S503 may be used.
When the dynamic Threshold corresponding to the current time period (non-first time period) after clustering is updated in S501-S503, the difference from the updating of the dynamic Threshold of the time period after current re-segmentation is that, RMSE _ Threshold is the updated dynamic Threshold corresponding to the current time period, RMSE _ Threshold0For the dynamic threshold value to be updated corresponding to the current time period, RMSE is the root mean square error of the previous time period of the current time period, RMSE _ Total0RMSE of a previous time period corresponding to a current time period_Total，RMSE_Cnt0RMSE _ Cnt of a previous time period corresponding to the current time period; n is any positive integer, preferably 1-5; ω is an attenuation coefficient and takes an arbitrary value between 0 and 1.
If the dynamic Threshold of the current time period after the re-segmentation is updated, the dynamic Threshold to be updated corresponding to the current time period after the re-segmentation is the dynamic Threshold corresponding to the previous time period or the parent time period, and if the first time period a obtained after the clustering is subjected to the re-segmentation to obtain a1 and a2, when the dynamic Threshold of a1 is updated, for step 1, the RMSE _ Threshold at this time is used0As for the dynamic Threshold of the parent time segment a corresponding to the time segment a1, that is, any value greater than 0 and less than 1, preferably 0.3 to 0.8, as can be seen from S601 to S604, the first root mean square error is the root mean square error of the previous time segment of the current time segment after segmentation or the parent time segment, the first root mean square error RMSE of a1 is the root mean square error of a (parent time segment), the dynamic Threshold of a1 is updated through step 1, and finally the updated dynamic Threshold RMSE _ Threshold of a1 is obtained through step 4. Note that since A is the first time period, RMSE _ Total is 0 and RMSE _ Cnt is 0 when updating the dynamic threshold of A10Is 0.
Update A2 on A1 basis, RMSE _ Threshold at this time0Dynamic threshold for time period A1, RMSE _ Total0RMSE _ Total, RMSE _ Cnt, corresponding to A10For the RMSE _ Cnt corresponding to a1, the dynamic Threshold value of a2 is updated through step 1, and finally, an updated dynamic Threshold value RMSE _ Threshold of a2 is obtained through step 6.
If the dynamic Threshold of the clustered current time period (not the first time period) is updated, and the dynamic Threshold to be updated corresponding to the current time period is the dynamic Threshold corresponding to the previous time period, for example, a time period B (located after the first time period a) obtained after clustering, when the dynamic Threshold of B is updated, for step 1, the RMSE _ Threshold at this time is used0Dynamic threshold for previous time period A2, since RMSE is the root mean square error of the previous time period of the current time period (not the first time period) after clustering, B corresponds to RMSE is the root mean square error of A2, and RMSE _ Total0RMSE _ Total, RMSE _ Cnt, corresponding to A20And updating the dynamic Threshold value of B through step 1 for the RMSE _ Cnt corresponding to A2, and finally obtaining the updated dynamic Threshold value RMSE _ Threshold of B through step 4.
If a time period B (after the first time period A) obtained after clustering is segmented into B1 and B2, then when the dynamic Threshold of B1 is updated, for step 1, the RMSE _ Threshold at this time is0Is a dynamic threshold of the mother time segment B corresponding to B1, at this time, the first root mean square error is the root mean square error of the mother time segment of the current time segment after the segmentation, the first root mean square error RMSE of B1 is the root mean square error of the mother time segment B, RMSE _ Total0RMSE _ Total, RMSE _ Cnt corresponding to the parent time period B0And updating the dynamic Threshold value of B1 through step 1 for the RMSE _ Cnt corresponding to the parent time period B, and finally obtaining the updated dynamic Threshold value RMSE _ Threshold of B1 through step 4.
In the embodiment, the fitting result of the current time period meets a predetermined effect, and at this time, the early warning result of the current time period needs to be determined according to the fitting result, including the following two situations, if the current time period is a time period a obtained after clustering, that is, if the root mean square error of a is not greater than the dynamic threshold, the early warning result of a needs to be determined according to the fitting straight line of a; if the current time period is the time periods A1 and A2 obtained after the A is segmented, the second root mean square error of the A1 is not larger than the dynamic threshold of the A1, the early warning result of the A1 needs to be determined according to a straight line fitting the A1, the second root mean square error of the A2 is not larger than the dynamic threshold of the A2, and the early warning result of the A2 needs to be determined according to a straight line fitting the A2.
That is, in S402, the root mean square error of each time period is calculated according to the fitting data and the pressure data in each time period, and meanwhile, the slope of the fitting straight line of each time period is also calculated, the fitting straight line is the fitting result, and the early warning result is determined according to the slope of the fitting straight line.
The early warning results include the following conditions:
if k is more than 1, the risk grade is I grade: "high sand blocking risk", need to take immediate measures to prevent sand from blocking up appearing;
if k is more than 0.8 and less than or equal to 1, the risk level is II: the risk of sand blocking needs to closely observe the change of construction data and make timely response preparation;
(III) if k is more than 0 and less than or equal to 0.8 and RMSE '> RMSE _ Threshold', the risk level is level III: "low sand plugging risk", in this case, indicates that sand plugging does not occur, indicates that the construction pressure data fluctuates and pressure changes need to be concerned;
if k is more than 0 and less than or equal to 0.8 and RMSE '< ═ RMSE _ Threshold', or k is less than or equal to 0, the risk rating is IV: "No risk of sand blockage".
If the current time period is a time period A obtained after clustering, RMSE 'is the root mean square error of A, and RMSE _ Threshold' is the dynamic Threshold of A; if the current time period is the time period A1 or A2 obtained after the A is segmented, the RMSE 'is the second root mean square error of A1 or A2, and the RMSE _ Threshold' is the dynamic Threshold of A1 or A2.
Based on the fracturing sand plugging early warning method based on the pressure data, the embodiment of the invention also provides a fracturing sand plugging early warning device based on the pressure data. The apparatus may include systems (including distributed systems), software (applications), modules, components, servers, clients, etc. that employ the methods described herein in embodiments, in conjunction with any necessary apparatus to implement the hardware. Based on the same innovative concepts, embodiments herein provide an apparatus as described in the following embodiments. Since the implementation scheme of the apparatus for solving the problem is similar to that of the method, the specific apparatus implementation in the embodiment of the present disclosure may refer to the implementation of the foregoing method, and repeated details are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Specifically, fig. 7 is a schematic structural diagram of a module of an embodiment of the fracturing sand blockage warning device based on pressure data provided in the embodiment of the present disclosure, and referring to fig. 7, the fracturing sand blockage warning device based on pressure data provided in the embodiment of the present disclosure includes: the device comprises an acquisition module 100, a clustering module 200 and a judgment module 300.
The utility model provides a stifled early warning device of fracturing sand based on pressure data, the device includes:
the acquisition module 100 is used for acquiring pressure data in fracturing construction;
the clustering module 200 is configured to cluster the pressure data to obtain pressure data in a plurality of time periods;
the judging module 300 is configured to perform fitting on the pressure data in each time period once, and judge whether a fitting result in each time period meets a predetermined effect;
if yes, determining an early warning result of the current time period according to the fitting result;
if not, segmenting the current time period again to obtain a plurality of time periods after segmentation again, and determining the early warning result of each time period after segmentation again.
Referring to fig. 8, in an embodiment of the present disclosure, a computer device 802 is further provided based on the above-described method for early warning of sand plugging in fracturing based on pressure data, wherein the above-described method is executed on the computer device 802. Computer device 802 may include one or more processors 804, such as one or more Central Processing Units (CPUs) or Graphics Processors (GPUs), each of which may implement one or more hardware threads. The computer device 802 may also include any memory 806 for storing any kind of information, such as code, settings, data, etc., and in a particular embodiment a computer program on the memory 806 and executable on the processor 804, which computer program when executed by the processor 804 may perform instructions according to the above-described method.
For example, and without limitation, memory 806 may include any one or more of the following in combination: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any memory may use any technology to store information. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent fixed or removable components of computer device 802. In one case, when the processor 804 executes the associated instructions, which are stored in any memory or combination of memories, the computer device 802 can perform any of the operations of the associated instructions. The computer device 802 also includes one or more drive mechanisms 808, such as a hard disk drive mechanism, an optical disk drive mechanism, etc., for interacting with any memory.
Computer device 802 may also include an input/output module 810(I/O) for receiving various inputs (via input device 812) and for providing various outputs (via output device 814). One particular output mechanism may include a presentation device 816 and an associated graphical user interface 818 (GUI). In other embodiments, input/output module 810(I/O), input device 812, and output device 814 may also be excluded, as just one computer device in a network. Computer device 802 may also include one or more network interfaces 820 for exchanging data with other devices via one or more communication links 822. One or more communication buses 824 couple the above-described components together.
Communication link 822 may be implemented in any manner, such as over a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 822 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.
Corresponding to the methods in fig. 1-6, the embodiments herein also provide a computer-readable storage medium having stored thereon a computer program, which, when executed by a processor, performs the steps of the above-described method.
Embodiments herein also provide computer readable instructions, wherein when executed by a processor, a program thereof causes the processor to perform the method as shown in fig. 1-6.
It should be understood that, in various embodiments herein, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments herein.
It should also be understood that, in the embodiments herein, the term "and/or" is only one kind of association relation describing an associated object, meaning that three kinds of relations may exist. For example, a and/or B, may represent: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided herein, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electrical, mechanical or other form of connection.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments herein.
In addition, functional units in the embodiments herein may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present invention may be implemented in a form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The principles and embodiments of this document are explained herein using specific examples, which are presented only to aid in understanding the methods and their core concepts; meanwhile, for the general technical personnel in the field, according to the idea of this document, there may be changes in the concrete implementation and the application scope, in summary, this description should not be understood as the limitation of this document.

Claims (10)

1. A fracturing sand blocking early warning method based on pressure data is characterized by comprising the following steps:
acquiring pressure data in fracturing construction;
clustering the pressure data to obtain pressure data in a plurality of time periods;
fitting the pressure data in each time period once, and judging whether the fitting result of each time period meets the preset effect;
if yes, determining an early warning result of the current time period according to the fitting result;
if not, segmenting the current time period again to obtain a plurality of time periods after segmentation again, and determining the early warning result of each time period after segmentation again.
2. The fracturing sand plugging early warning method based on pressure data as claimed in claim 1, wherein said re-segmenting the current time period to obtain a plurality of re-segmented time periods, and determining the early warning result of each re-segmented time period further comprises:
judging whether the total number of the pressure data in each time period after the re-segmentation is less than a set number or not;
if so, determining an early warning result of the current time period after the re-segmentation according to the fitting result of the current time period before the re-segmentation;
if not, fitting the pressure data in the current time period after the re-segmentation once, executing the step of judging whether the fitting result of each time period accords with the preset effect, and judging whether the fitting result of the current time period after the re-segmentation accords with the preset effect.
3. A method for early warning of fractured sand plugging based on pressure data as recited in claim 2 wherein the fitting the pressure data in each time period once further comprises:
fitting the pressure data in each time period for one time to obtain fitting data in each time period;
and calculating the root mean square error of each time period according to the fitting data and the pressure data in each time period.
4. The method for early warning of fractured sand plugging based on pressure data as claimed in claim 3, wherein the step of judging whether the fitting result of each time period meets the preset effect further comprises the following steps:
comparing the root mean square error of each time period with a dynamic threshold corresponding to each time period;
if the root mean square error of the current time period is not greater than the dynamic threshold corresponding to the current time period, the fitting result of the current time period accords with the preset effect;
and if the root mean square error of the current time period is greater than the dynamic threshold corresponding to the current time period, the fitting result of the current time period is not in accordance with the preset effect.
5. The fracturing sand plugging early warning method based on pressure data as claimed in claim 4, wherein the step of fitting the pressure data in the current time period after the re-segmentation once, and determining whether the fitting result of each time period meets the predetermined effect as above, the step of determining whether the fitting result of the current time period after the re-segmentation meets the predetermined effect comprises:
updating the dynamic threshold of the current time period after the segmentation again according to the first root mean square error of the current time period after the segmentation again;
comparing the second root mean square error of the current time period after the segmentation with the dynamic threshold of the current time period after the segmentation;
if the second root mean square error of the current time period after the re-segmentation is not greater than the dynamic threshold of the current time period after the re-segmentation, the fitting result of the current time period after the re-segmentation accords with the preset effect;
and if the second root mean square error of the current time period after the re-segmentation is larger than the dynamic threshold of the current time period after the re-segmentation, the fitting result of the current time period after the re-segmentation does not accord with the preset effect.
6. The method of claim 5, wherein updating the dynamic threshold for the current time period after re-staging further comprises:
updating the dynamic threshold for the current re-segmented time period by the following formula:
if RMSE < ═ RMSE _ Threshold0If the RMSE _ Total is equal to the RMSE _ Total0+rmse，RMSE_Cnt＝RMSE_Cnt0+1；
RMSE_Avg0＝RMSE_Threshold0/n；
If RMSE _ Cnt is less than or equal to 0, RMSE _ Avg is equal to RMSE _ Avg0Otherwise, if the RMSE _ Cnt is greater than 0, RMSE _ Avg is equal to RMSE _ Total/RMSE _ Cnt (1- ω) + RMSE _ Avg0*ω；
RMSE_Threshold＝n*RMSE_Avg；
Wherein RMSE _ Threshold is an updated dynamic Threshold corresponding to a current time period after re-segmentation, and RMSE _ Threshold0The dynamic threshold value to be updated is corresponding to the current time period after the segmentation; rmse is a first root mean square error of the current time period after the segmentation; RMSE _ Total0Is 0, RMSE _ Cnt0Is 0; n is any positive integer; ω is an attenuation coefficient and takes an arbitrary value between 0 and 1.
7. The fracturing sand plugging early warning method based on pressure data as claimed in claim 1, wherein said re-segmenting the current time period to obtain a plurality of re-segmented time periods further comprises:
performing quadratic fitting on the pressure data in the current time period to obtain a quadratic polynomial, and determining a stagnation point of the quadratic polynomial;
and inserting the stagnation point as an interpolation into the current time period to obtain the stagnation point and the time period on the left side of the stagnation point, and the stagnation point and the time period on the right side of the stagnation point.
8. The utility model provides a stifled early warning device of fracturing sand based on pressure data which characterized in that the device includes:
the acquisition module is used for acquiring pressure data in fracturing construction;
the clustering module is used for clustering the pressure data to obtain pressure data in a plurality of time periods;
the judging module is used for fitting the pressure data in each time period once and judging whether the fitting result of each time period meets the preset effect or not;
if yes, determining an early warning result of the current time period according to the fitting result;
if not, segmenting the current time period again to obtain a plurality of time periods after segmentation again, and determining the early warning result of each time period after segmentation again.
9. A computer device comprising a memory, a processor, and a computer program stored on the memory, wherein the computer program, when executed by the processor, performs the instructions of the method of any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor of a computer device, is adapted to carry out the instructions of the method according to any one of claims 1-7.
CN202210157287.3A 2022-02-21 2022-02-21 Fracturing sand blocking early warning method and device based on pressure data Active CN114565032B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210157287.3A CN114565032B (en) 2022-02-21 2022-02-21 Fracturing sand blocking early warning method and device based on pressure data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210157287.3A CN114565032B (en) 2022-02-21 2022-02-21 Fracturing sand blocking early warning method and device based on pressure data

Publications (2)

Publication Number Publication Date
CN114565032A true CN114565032A (en) 2022-05-31
CN114565032B CN114565032B (en) 2023-04-18

Family

ID=81713090

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210157287.3A Active CN114565032B (en) 2022-02-21 2022-02-21 Fracturing sand blocking early warning method and device based on pressure data

Country Status (1)

Country Link
CN (1) CN114565032B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115410347A (en) * 2022-10-31 2022-11-29 四川宏华电气有限责任公司 Intelligent early warning and regulating method for sand blocking in fracturing process

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104716903A (en) * 2015-03-17 2015-06-17 上海交通大学 Automatic segmentation polynomial fitting method applicable to photovoltaic array output characteristic curve
CN106969812A (en) * 2017-04-05 2017-07-21 深圳市美好创亿医疗科技有限公司 Flow sensor calibration method and system
CN107145693A (en) * 2017-06-27 2017-09-08 中国航空工业集团公司沈阳飞机设计研究所 The dynamic measurement method of the irregular fuel tank fuel quantity of aircraft
CN107587870A (en) * 2017-09-11 2018-01-16 中国石油大学(北京) Shale gas fracturing work down-hole accident monitors and method for early warning and system
CN110533163A (en) * 2019-08-02 2019-12-03 中国石油集团长城钻探工程有限公司 Sand plugging after fracturing method for early warning based on long Memory Neural Networks in short-term
CN110766054A (en) * 2019-09-23 2020-02-07 东软集团股份有限公司 Early warning method and device for fracturing sand plugging, storage medium and equipment
CN110955648A (en) * 2019-12-18 2020-04-03 重庆大学 Non-equidistant time sequence monitoring data normalization mapping processing method
CN113239030A (en) * 2021-05-20 2021-08-10 国网山东省电力公司潍坊供电公司 Smart power grid monitoring data storage method based on discrete data curve fitting
CN113435725A (en) * 2021-06-21 2021-09-24 国网宁夏电力有限公司信息通信公司 Power grid host dynamic threshold setting method based on FARIMA-LSTM prediction
CN113687411A (en) * 2021-09-03 2021-11-23 西南石油大学 Earth stress azimuth prediction method based on microseism

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104716903A (en) * 2015-03-17 2015-06-17 上海交通大学 Automatic segmentation polynomial fitting method applicable to photovoltaic array output characteristic curve
CN106969812A (en) * 2017-04-05 2017-07-21 深圳市美好创亿医疗科技有限公司 Flow sensor calibration method and system
CN107145693A (en) * 2017-06-27 2017-09-08 中国航空工业集团公司沈阳飞机设计研究所 The dynamic measurement method of the irregular fuel tank fuel quantity of aircraft
CN107587870A (en) * 2017-09-11 2018-01-16 中国石油大学(北京) Shale gas fracturing work down-hole accident monitors and method for early warning and system
CN110533163A (en) * 2019-08-02 2019-12-03 中国石油集团长城钻探工程有限公司 Sand plugging after fracturing method for early warning based on long Memory Neural Networks in short-term
CN110766054A (en) * 2019-09-23 2020-02-07 东软集团股份有限公司 Early warning method and device for fracturing sand plugging, storage medium and equipment
CN110955648A (en) * 2019-12-18 2020-04-03 重庆大学 Non-equidistant time sequence monitoring data normalization mapping processing method
CN113239030A (en) * 2021-05-20 2021-08-10 国网山东省电力公司潍坊供电公司 Smart power grid monitoring data storage method based on discrete data curve fitting
CN113435725A (en) * 2021-06-21 2021-09-24 国网宁夏电力有限公司信息通信公司 Power grid host dynamic threshold setting method based on FARIMA-LSTM prediction
CN113687411A (en) * 2021-09-03 2021-11-23 西南石油大学 Earth stress azimuth prediction method based on microseism

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
HAIBO LIANG等: "An Sand Plug of Fracturing Intelligent Early Warning Model Embedded in Remote Monitoring System", 《IEEE ACCESS》 *
代海洋: "压裂砂堵实时监测与预警系统研究与应用", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115410347A (en) * 2022-10-31 2022-11-29 四川宏华电气有限责任公司 Intelligent early warning and regulating method for sand blocking in fracturing process

Also Published As

Publication number Publication date
CN114565032B (en) 2023-04-18

Similar Documents

Publication Publication Date Title
WO2020192675A1 (en) Productivity prediction method for fractured horizontal well in tight oil reservoir
EP1984860B1 (en) Methods, systems, and computer-readable media for fast updating of oil and gas field production models with physical and proxy simulators
CN114565032B (en) Fracturing sand blocking early warning method and device based on pressure data
EP1982046A1 (en) Methods, systems, and computer-readable media for real-time oil and gas field production optimization using a proxy simulator
CN104346511B (en) A kind of deposit dynamic monitoring method and device
CN110533163A (en) Sand plugging after fracturing method for early warning based on long Memory Neural Networks in short-term
US11222387B2 (en) Method and system for processing and generating a building report
CN114398786B (en) Fracturing construction pressure prediction model establishing method and device and prediction method and device
CN111369056B (en) Geological disaster prediction method and electronic equipment
CA2873717A1 (en) Method and system of displaying a graphical representation of hydrocarbon production parameters
WO2024098950A1 (en) Hydrodynamic model parameter optimization method and apparatus, and water level and flow change process simulation method and apparatus
CN111434886A (en) Mechanical drilling speed calculation method and device for drilling process
CA3127234C (en) Industrial machine optimization
CN107780926B (en) Borehole section shape measuring method, device and terminal
CN114565004A (en) Method and device for eliminating abnormal scattered points of power curve of wind turbine generator
CN115719031A (en) Fracturing sand plugging prediction model establishing method, prediction method and prediction device
CN110874686B (en) Underground risk discrimination method
US20230146355A1 (en) Constructing derivative profiles from discrete pressure data of transient well tests
CN116561942B (en) Method and device for correcting topology data of urban drainage system
Al-Jasmi et al. Gas Lift Smart Flow Integrates Quality and Control Data for Diagnostic and Optimization in Real Time
CN114169600A (en) Reservoir oil content prediction model establishing method, prediction method and prediction device
CN114722347A (en) Determination method, early warning method and device for comprehensive friction coefficient of friction resistance torque
Sayung et al. Samarang Integrated Operations IO: Real Time Integration of Wells and Field for Gas Lift Surveillance and Optimization Using Analytical Integrated Modelling Approach
CN115544740A (en) Oil well segmentation clustering method and device, computer equipment and storage medium
CN115730510A (en) Method for establishing and applying ancient water depth prediction model based on well logging curve

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