CN111563648B - Drilling risk assessment method and device - Google Patents
Drilling risk assessment method and device Download PDFInfo
- Publication number
- CN111563648B CN111563648B CN202010228968.5A CN202010228968A CN111563648B CN 111563648 B CN111563648 B CN 111563648B CN 202010228968 A CN202010228968 A CN 202010228968A CN 111563648 B CN111563648 B CN 111563648B
- Authority
- CN
- China
- Prior art keywords
- data
- probability
- seismic
- seismic attribute
- risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005553 drilling Methods 0.000 title claims abstract description 107
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012502 risk assessment Methods 0.000 title claims abstract description 50
- 238000012549 training Methods 0.000 claims abstract description 13
- 238000013210 evaluation model Methods 0.000 claims abstract description 11
- 230000002159 abnormal effect Effects 0.000 claims description 33
- 230000001427 coherent effect Effects 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 abstract description 20
- 230000008569 process Effects 0.000 abstract description 19
- 238000011161 development Methods 0.000 abstract description 6
- 230000006872 improvement Effects 0.000 description 8
- 206010017076 Fracture Diseases 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000002547 anomalous effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Animal Husbandry (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Development Economics (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The embodiment of the specification provides a drilling risk assessment method and device. The method comprises the following steps: acquiring accident data and seismic attribute data of the finished drilling well; training a risk assessment model according to the accident data and the seismic attribute data; and evaluating the drilling risk by utilizing the risk evaluation model according to the seismic attribute data of the area to be drilled. By the well drilling risk assessment method, the seismic attributes of the completion well drilling area are combined, the data in the completion well drilling are effectively utilized, and the corresponding risk assessment model is obtained by calculation under the condition of combining the influence of the seismic attributes on well drilling accidents, so that the well drilling risk is quantitatively and accurately assessed, and the development of well drilling engineering in the subsequent process is facilitated.
Description
Technical Field
The embodiment of the specification relates to the technical field of geological exploration and development, in particular to a drilling risk assessment method and device.
Background
Drilling a well into the earth is inevitably involved in the course of geological exploration and development. However, fracture zones are often associated with the development of fractures in the formation, and the presence of the fracture zones provides natural leak-off pathways and changes the mechanical state of the rock around the well. If the drilling well is not processed, well drilling accidents such as well wall collapse, malignant well leakage and the like are easily caused in sequence in the drilling process, and the drilling well safety is seriously threatened, so that the drilling well production is hindered. Therefore, before drilling, it is of great importance to make an accurate assessment of the risk of drilling.
However, when the risk of drilling is evaluated before drilling, the correlation between the seismic attribute and the drilling risk is often ignored, and only the area with abnormal seismic attribute is qualitatively judged, so that the evaluation mode not only causes inaccuracy of the evaluation result, but also cannot provide more accurate evaluation result for the specific risk occurrence probability in the drilling process, thereby not well helping the drilling production in practical application. Therefore, there is a need for a method of accurately assessing drilling risk.
Disclosure of Invention
The purpose of the embodiments of the present specification is to provide a drilling risk assessment method and device, so as to solve the problem of how to accurately assess drilling risk.
In order to solve the above technical problem, a drilling risk assessment method and device provided by the embodiments of the present specification are implemented as follows:
a drilling risk assessment method, comprising:
acquiring accident data and seismic attribute data of the finished drilling well;
training a risk assessment model according to the accident data and the seismic attribute data;
and evaluating the drilling risk by utilizing the risk evaluation model according to the seismic attribute data of the area to be drilled.
A drilling risk assessment device, comprising:
the data acquisition module is used for acquiring accident data and seismic attribute data of the finished drilling well;
the model training module is used for training a risk assessment model according to the accident data and the seismic attribute data;
and the risk evaluation module is used for evaluating the drilling risk by utilizing the risk evaluation model according to the seismic attribute data of the area to be drilled.
According to the technical scheme provided by the embodiment of the specification, when the drilling risk is evaluated, firstly, accident data and seismic attribute data of a finished drilling well are obtained, a risk evaluation model corresponding to the seismic attribute data is trained by combining the accident data and the seismic attribute data, and then the drilling risk evaluation is carried out on a to-be-drilled well area by using the risk evaluation model. In the evaluation process, the seismic attributes of the completed drilling area are combined, so that not only is the data in the completed drilling effectively utilized, but also the corresponding risk evaluation model is obtained by calculation under the condition of combining the influence of the seismic attributes on drilling accidents, thereby realizing quantitative and accurate evaluation on the drilling risks and being beneficial to the development of drilling engineering in the subsequent process.
Drawings
In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the specification, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for drilling risk assessment in accordance with an embodiment of the present disclosure;
FIG. 2 is a schematic diagram illustrating obtaining low frequency coherence property sample data according to an embodiment of the present disclosure;
FIG. 3 is a diagram illustrating a method for obtaining a one-dimensional low-frequency coherence property curve according to an embodiment of the present disclosure;
FIG. 4 is a block diagram of a drilling risk assessment device according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort shall fall within the protection scope of the present specification.
In order to solve the technical problem, the present specification proposes a drilling risk assessment method. As shown in fig. 1, the drilling risk assessment method specifically includes:
s110: acquiring accident data and seismic attribute data of the finished well.
The completed well is a production well or a measurement well or the like that has already been drilled. Preferably, in order to better combine the relation between the drilling accident and the seismic attribute, the drilling well with the accident can be selected as a finished drilling well, so that corresponding accident data can be better obtained for the finished drilling well, and further, the construction of a risk assessment model is realized in the subsequent steps.
The accident data is data corresponding to drilling accidents or abnormal situations occurring in the completed well. The accident data may be data corresponding to an abnormal condition in the drilling, such as a distribution condition of a fracture zone or a fracture zone in the drilling, or data corresponding to an accident occurring in the drilling, such as a lost circulation condition, a stuck drilling condition, and the like occurring in the drilling process. The accident data in practical application is not limited to the above examples, and will not be described herein.
To better correlate with seismic attributes, the incident data may include drilling incident location data when acquiring incident data corresponding to completed drilling. The drilling accident location data is data of locations where abnormal conditions or accidents occur in the finished drilling. After the drilling accident location data is acquired, seismic attribute data corresponding to the drilling accident location data can be acquired more conveniently.
The seismic attribute data is data corresponding to seismic attributes of the completed well. Seismic attributes are used to represent attributes of seismic waves in the earth formation and may be, for example, attributes of amplitude, frequency, phase, energy, waveform, wave impedance, wave velocity, correlation, and ratio. The seismic attribute data can represent the characteristic information of seismic waves, so that the characteristics of stratums corresponding to the seismic waves are reflected, and different types of geology are distinguished.
In some embodiments, the seismic attribute data may include at least one of coherence volume data, curvature volume data, and ant volume data.
The coherent volume data refers to a new data volume obtained by performing coherent processing on a three-dimensional seismic data volume, for example, the similarity between the waveform of a track where an analysis point is located and the waveform of an adjacent track in a time window at each identical point of each track can be solved in the three-dimensional data volume, and then a three-dimensional data volume representing coherence is formed and used as coherent volume data.
Curvature volume data is used primarily in three-dimensional data volumes to characterize the degree of deformation curvature at a point on the slice plane.
The ant body data is data which displays the fault outline and extracts the fault plane by using an ant tracking algorithm and three-dimensional seismic body data, thereby completing fault interpretation more clearly and intuitively.
The coherent volume data, the curvature volume data and the ant volume data are used as seismic attribute data, so that the seismic attribute data can be more fit with the characteristics of the stratum, and can be better matched with geological regions with different characteristics, and can be associated with accident data in the subsequent calculation process.
In some embodiments, the seismic attribute data may be acquired by collecting a three-dimensional post-stack seismic data volume corresponding to a work area where the completion well is located, marking a well trajectory of the completion well in the three-dimensional post-stack seismic data volume, extracting a one-dimensional seismic attribute curve from the three-dimensional post-stack seismic data volume along the well trajectory, and using data corresponding to the seismic attribute curve as seismic attribute data.
Based on the embodiment, after the three-dimensional post-stack seismic data volume is obtained according to the seismic attribute corresponding to the seismic attribute data in practical application, the data volume corresponding to the seismic attribute is screened out from the three-dimensional post-stack seismic data volume, and a one-dimensional attribute curve is extracted from the screened data volume based on the well trajectory of the finished well and is used as the seismic attribute data corresponding to the seismic attribute.
As shown in fig. 2, a volume extracted from the three-dimensional post-stack seismic data volume that corresponds to low frequency coherence properties and a well trajectory along a completed well in the low frequency coherence properties data volume. Corresponding one-dimensional attribute curves can be extracted from the low-frequency coherence attribute data volume according to the well track to serve as low-frequency coherence attribute sample data, and calculation in the subsequent process is carried out.
As shown in fig. 3, a one-dimensional property curve is extracted along the completed well trajectory in the low frequency coherence properties data volume. And taking the data corresponding to the one-dimensional attribute curve as low-frequency coherent attribute sample data to perform calculation in a subsequent process.
The process of respectively obtaining the low-frequency coherence attributes is only an exemplary illustration of obtaining the seismic attribute data, and does not limit the process of obtaining the seismic attribute data, and in practical application, the seismic attribute data may also be obtained by other methods according to production needs, which is not described herein again.
In some embodiments, seismic attribute data within a depth range may be averaged as a fixed seismic attribute data value within the depth range after the seismic attribute curve is acquired, taking into account the resolution characteristics of the seismic attribute data. For example, the depth range may be set to be 15 meters, and the average values of the attribute values corresponding to the seismic attribute curves in the depth range of 15 meters are respectively obtained and respectively used as the data values of the seismic attribute data corresponding to the depth range, so as to better quantify the data and facilitate the calculation in the subsequent process.
In some embodiments, after the seismic attribute data is acquired, the seismic attribute data may be further marked as normal seismic attribute data or abnormal seismic attribute data based on a preset determination condition. The normal seismic attribute data indicates that the data is within the defined normal range, and the abnormal seismic attribute data indicates that the data is not within the defined normal range. Accordingly, if a drilling accident or abnormal condition exists in the depth range, the probability of the accident occurring in the depth range can be considered as 100% in the subsequent calculation.
The preset judgment condition may be a threshold value set in advance according to regional geological experience and expert experience, and the normal or abnormal condition of the seismic attribute data is judged based on the threshold value.
The description is given by using a specific example, in the example, the seismic attributes include four attributes of a high-frequency coherence attribute, a low-frequency coherence attribute, a high-frequency maximum curvature attribute, and a low-frequency maximum curvature attribute, based on geological features in a work area corresponding to a finished drilling well and experience of an expert, preset judgment conditions are respectively set to a standard for judging that high-frequency coherence attribute sample data is abnormal seismic attribute data to be less than 0.6, a standard for judging that low-frequency coherence attribute sample data is abnormal seismic attribute data to be less than 0.65, a standard for judging that high-frequency maximum curvature attribute sample data is abnormal seismic attribute data to be greater than 0.08, and a standard for judging that low-frequency maximum curvature attribute sample data is abnormal seismic attribute data to be greater than 0.1. After the preset judgment condition is set, in practical application, normal seismic attribute data and abnormal seismic attribute data can be divided according to the value of the acquired seismic attribute data and the preset judgment condition.
S120: and training a risk assessment model according to the accident data and the seismic attribute data.
The risk assessment model is used to determine the probability of a drilling event occurring based on seismic attributes. For example, when a high-frequency coherence property, a low-frequency coherence property, a high-frequency maximum curvature property, and a low-frequency maximum curvature property are selected as seismic properties, the calculated risk assessment model may be used to assess the probability of a drilling accident occurring when the four properties are normal or abnormal, respectively. For example, the high-frequency coherence property and the high-frequency maximum curvature property at a certain position are measured to be normal, the low-frequency coherence property and the low-frequency maximum curvature property are measured to be abnormal in the region to be drilled, and the risk occurrence probability of normal or abnormal conditions corresponding to the four seismic properties is determined in the risk assessment model, which can be used as the probability of occurrence of an accident after drilling at the position.
In some embodiments, the risk assessment model may be calculated prior to calculating a first prior probability corresponding to normal seismic sample attribute data and a second prior probability corresponding to abnormal seismic attribute data from the accident data and the seismic attribute data, respectively. The first prior probability represents the probability of a drilling accident occurring when the seismic sample attribute data is normal seismic sample attribute data; the second prior probability represents a probability of a drilling event occurring when the seismic sample attribute data is anomalous seismic sample attribute data.
After the first prior probability and the second prior probability are obtained through calculation, calculating the influence probability of the seismic attribute corresponding to the seismic attribute data according to the first prior probability and the second prior probability. And the seismic attribute influence probability represents the influence degree of the seismic attribute on the occurrence of the drilling accident.
In particular, a formula may be utilized
Calculating the influence probability of the seismic attribute, wherein A is abnormal seismic attribute data,
normal seismic attribute data, C accident data, P (C/A) second prior probability,
is the first prior probability, PiThe probability is influenced for the seismic attribute.
Using a specific example to illustrate, let A1Expressed as anomalous high frequency coherence property sample data, P (M1 | a) is obtained after calculation using data corresponding to the completed well1＝1)＝0.42，P(M＝1|A10) to 0.10, that is, the probability of the occurrence of the drilling accident is 0.42 when the high-frequency coherence property sample data is abnormal, and the probability of the occurrence of the drilling accident is 0.1 when the high-frequency coherence property sample data is normal. Reuse formula
And calculating to obtain the seismic attribute influence probability of the sample data corresponding to the high-frequency coherence attribute of 0.58.
After obtaining the seismic attribute impact probability, a risk assessment model corresponding to seismic attribute data may be calculated from the seismic attribute impact probability.
In some embodiments, the risk assessment model may be computed based on a Leaky noise-OR gate Bayesian network. The Noisy-OR gate Bayes network is a network for describing n binary variables AiInteraction model with child node C that produces a common effect. Each of the binary variables has only two states, which can be defined as a true value and a false value. The binary variable A can be applied to the embodimentiRespectively set as abnormal seismic attribute data a1,a2,...,anAnd a is given when each abnormal seismic attribute data is trueiFalse value is
I.e. abnormal seismic attribute data corresponding to aiNormal seismic attribute data corresponds to
The child node C may be configured to be incident data such that an association is made between the various seismic attribute data fields and the incident data. The Noisy-OR gate Bayes model requires that all variables are independent from each other, and in the embodiment, different seismic profile properties can be extracted by adopting different calculation principles for obtaining various seismic attributes, so that seismic attribute data corresponding to different seismic attributes have no causal connection and meet the model requirements.
In some embodiments, the risk assessment model may include a probability of risk occurrence corresponding to a particular number of seismic attributes. Specifically, the seismic attributes to be evaluated may be selected from the seismic attributes, and the risk occurrence probability corresponding to the seismic attributes to be evaluated may be calculated using the seismic attributes to be evaluated. And the risk occurrence probability corresponding to the seismic attribute to be evaluated is used for reflecting the probability of the drilling accident when the seismic attribute to be evaluated is abnormal.
By using a specific example for illustration, after the high-frequency coherence attribute, the low-frequency coherence attribute, the high-frequency maximum curvature attribute, and the low-frequency maximum curvature attribute are selected as seismic attributes, the high-frequency coherence attribute and the low-frequency coherence attribute can be selected as seismic attributes to be evaluated. After the influence probability of the attribute to be evaluated corresponding to the high-frequency coherence attribute and the low-frequency coherence attribute is obtained through calculation, the risk occurrence probability obtained through calculation based on the influence probability of the attribute to be evaluated is used for reflecting the probability of the drilling accident under the condition that only the high-frequency coherence attribute and the low-frequency coherence attribute are abnormal.
By the mode of selecting the seismic attributes to be evaluated and calculating the corresponding risk occurrence probability, the corresponding risk occurrence probability can be obtained according to various conditions in actual production, and therefore accurate evaluation can be performed on drilling risks by better combining with actual conditions.
In some embodiments, in order to avoid the influence of other environmental factors on the calculation result, a correction factor may be introduced, and the correction probability corresponding to the correction factor may be determined by combining the actual calculation result and the artificial experience determination. The correction factor may be a factor that may affect the calculation result, such as environment and calculation error, and the correction probability may be used to express the degree of the influence of the correction factor on the calculation result. For example, the correction probability may be set to 5%, and the wind direction occurrence probability may be calculated in accordance with the correction probability. By introducing the correction probability, factors such as environmental factors and the like which are difficult to uniformly and accurately calculate are summarized in the calculation process, and the accuracy of the calculation result is further ensured.
In particular, a formula may be utilized
Calculating the risk occurrence probability corresponding to the seismic attribute to be evaluated, wherein ALTo correct the factor, PLTo correct the probability, C is accident data, AsubFor seismic attributes to be evaluated, AiFor seismic attributes, PiAnd the influence probability of the attribute to be evaluated. Wherein A isiFor the total selected seismic attribute, AsubIs the seismic attribute selected in this calculation. For example, in AiWhen the high-frequency coherence property, the low-frequency coherence property, the high-frequency maximum curvature property and the low-frequency maximum curvature property are included, A can be setsubAnd correspondingly calculating the influence probability of the high-frequency coherent attribute and the low-frequency coherent attribute by using the attribute to be evaluated corresponding to the high-frequency coherent attribute and the low-frequency coherent attribute, so as to calculate the risk occurrence probability when the high-frequency coherent attribute and the low-frequency coherent attribute are abnormal.
S130: and evaluating the drilling risk by utilizing the risk evaluation model according to the seismic attribute data of the area to be drilled.
The seismic attribute data is measured in the area to be drilled. Preferably, seismic attribute measurement data corresponding to the corresponding seismic attributes can be measured in the area to be drilled according to the seismic attributes utilized in calculating the risk assessment model, so that redundant data acquisition is avoided, and the assessment process is accelerated.
In some embodiments, a risk occurrence probability corresponding to the seismic attribute data may be obtained as an evaluation risk probability. Specifically, for example, according to the measured seismic attribute data corresponding to the to-be-drilled area, a low-frequency coherence attribute is determined, and if the high-frequency maximum curvature attribute is abnormal, the risk occurrence probability corresponding to the low-frequency coherence attribute and the high-frequency maximum curvature attribute being abnormal can be obtained according to the risk assessment model calculated in the above steps, and the drilling risk is assessed by combining the risk occurrence probability.
In some embodiments, when evaluating the drilling risk, the seismic attribute data may be divided into several depth ranges according to predefined depth ranges based on the method in step S120, and the seismic attribute data in each depth range is averaged, and the probability of the drilling risk occurrence is determined by using the averaged value in combination with the risk evaluation model. And based on the steps, sequentially evaluating the drilling risks in each depth range divided in the area to be drilled, thereby finishing the evaluation of the drilling risks of the area to be drilled.
Specifically, when the drilling risk is evaluated in combination with the risk occurrence probability, a risk threshold may be set for the risk occurrence probability, and when the risk occurrence probability exceeds the risk threshold, it is considered that the risk of an accident occurring when drilling is performed at the risk threshold is higher. For example, the risk threshold is set to 30%, and if the calculated corresponding risk occurrence probability of a certain place is 70%, the drilling risk is considered to be high, and in the actual drilling process, care should be taken to avoid drilling at the place.
By the drilling risk assessment method, when the drilling risk is assessed, a corresponding risk assessment model is established based on the drilling accident and the seismic attribute data, so that the relevance between the drilling accident and the seismic attribute data is considered by the risk assessment model. In addition, the specific risk occurrence probability is calculated through the risk assessment model, and the drilling process can be guided more intuitively. Therefore, the drilling risk assessment method accurately and quantitatively achieves the assessment of the drilling risk, and is beneficial to the development of drilling engineering in the subsequent process.
Based on the drilling risk assessment method, the specification also provides an embodiment of the drilling risk assessment device. As shown in fig. 4, the drilling risk assessment apparatus specifically includes:
a data acquisition module 410 for acquiring accident data and seismic attribute data corresponding to completed wells;
a model training module 420 for training a risk assessment model corresponding to the seismic attribute data in conjunction with the accident data and the seismic attribute data;
and the risk evaluation module 430 is used for evaluating the drilling risk by using the risk evaluation model according to the seismic attribute measurement data of the area to be drilled.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Language Description Language), traffic, pl (core unified Programming Language), HDCal, JHDL (Java Hardware Description Language), langue, Lola, HDL, laspam, hardbyscript Description Language (vhr Description Language), and the like, which are currently used by Hardware compiler-software (Hardware Description Language-software). It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
From the above description of the embodiments, it is clear to those skilled in the art that the present specification can be implemented by software plus a necessary general hardware platform. Based on such understanding, the technical solutions of the present specification may be essentially or partially implemented in the form of software products, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and include instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments of the present specification.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The description is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.
This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
While the specification has been described with examples, those skilled in the art will appreciate that there are numerous variations and permutations of the specification that do not depart from the spirit of the specification, and it is intended that the appended claims include such variations and modifications that do not depart from the spirit of the specification.
Claims (7)
1. A method of drilling risk assessment, comprising:
acquiring accident data and seismic attribute data of the finished drilling well;
marking the seismic attribute data as normal seismic attribute data or abnormal seismic attribute data based on a preset judgment condition;
training a risk assessment model according to the accident data and the seismic attribute data; wherein, include: respectively calculating a first prior probability corresponding to normal seismic attribute data and a second prior probability corresponding to abnormal seismic attribute data according to the accident data and the seismic attribute data; calculating the influence probability of the seismic attribute according to the first prior probability and the second prior probability; calculating a risk assessment model corresponding to seismic attribute data according to the seismic attribute influence probability; the calculating a probability of influence of the seismic attribute corresponding to the seismic attribute data according to the first prior probability and the second prior probability comprises: using formulas
Calculating the influence probability of the seismic attribute, wherein A is abnormal seismic attribute data,
normal seismic attribute data, C accident data, P (C/A) second prior probability,
is the first prior probability, PiInfluence probability for seismic attributes; training a risk assessment model according to the accident data and the seismic attribute data, comprising: calculating the risk occurrence probability corresponding to the seismic attribute to be evaluated according to the attribute influence probability to be evaluated; the calculating the risk occurrence probability corresponding to the seismic attribute to be evaluated according to the attribute influence probability to be evaluated comprises the following steps: using formulas
Calculating the risk occurrence probability corresponding to the seismic attribute to be evaluated, wherein ALTo correct the factor, PLTo correct the probability, C is accident data, AsubFor seismic attributes to be evaluated, AiFor seismic attributes, PiThe attribute influence probability to be evaluated is obtained;
and evaluating the drilling risk by utilizing the risk evaluation model according to the seismic attribute data of the area to be drilled.
2. The method of claim 1, wherein the incident data includes incident location data;
the seismic attribute data comprising at least one of: coherent volume data, curvature volume data, ant volume data.
3. The method of claim 1, wherein the risk assessment model comprises a bayesian network.
4. The method of claim 1, wherein the risk assessment model includes a probability of risk occurrence corresponding to seismic attributes; before training a risk assessment model according to the accident data and the seismic attribute data, the method further comprises the following steps:
selecting seismic attributes to be evaluated from the seismic attributes;
and acquiring the influence probability of the attributes to be evaluated corresponding to the seismic attributes to be evaluated.
5. The method of claim 4, wherein said calculating a probability of occurrence of risk corresponding to said seismic attribute to be evaluated from said probability of influence of said attribute to be evaluated comprises:
and calculating the risk occurrence probability corresponding to the seismic attribute to be evaluated by combining the correction probability corresponding to the correction factor and the influence probability of the attribute to be evaluated.
6. The method of claim 4, wherein the assessing drilling risk using the risk assessment model based on seismic attribute data for the area to be drilled comprises:
acquiring risk occurrence probability corresponding to the seismic attribute data according to the risk assessment model as assessment risk probability;
evaluating a drilling risk based on the evaluation risk probability.
7. A drilling risk assessment device, comprising:
the data acquisition module is used for acquiring accident data and seismic attribute data of the finished drilling well;
the data marking module is used for marking the seismic attribute data as normal seismic attribute data or abnormal seismic attribute data based on a preset judgment condition;
the model training module is used for training a risk assessment model according to the accident data and the seismic attribute data; wherein, include: respectively calculating a first prior probability corresponding to normal seismic attribute data and a second prior probability corresponding to abnormal seismic attribute data according to the accident data and the seismic attribute data; calculating the influence probability of the seismic attribute according to the first prior probability and the second prior probability; calculating a risk assessment model corresponding to seismic attribute data according to the seismic attribute influence probability; the calculating a probability of influence of the seismic attribute corresponding to the seismic attribute data according to the first prior probability and the second prior probability comprises: using formulas
Calculating the influence probability of the seismic attribute, wherein A is abnormal seismic attribute data,
normal seismic attribute data, C accident data, P (C/A) second prior probability,
is the first prior probability, PiInfluence probability for seismic attributes; training a risk assessment model according to the accident data and the seismic attribute data, comprising: calculating the risk occurrence probability corresponding to the seismic attribute to be evaluated according to the attribute influence probability to be evaluated; the calculating the risk occurrence probability corresponding to the seismic attribute to be evaluated according to the attribute influence probability to be evaluated comprises the following steps: using formulas
Calculating the risk occurrence probability corresponding to the seismic attribute to be evaluated, wherein ALTo correct the factor, PLTo correct the probability, C is accident data, AsubFor seismic attributes to be evaluated, AiFor seismic attributes, PiThe attribute influence probability to be evaluated is obtained;
and the risk evaluation module is used for evaluating the drilling risk by utilizing the risk evaluation model according to the seismic attribute data of the area to be drilled.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010228968.5A CN111563648B (en) | 2020-03-27 | 2020-03-27 | Drilling risk assessment method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010228968.5A CN111563648B (en) | 2020-03-27 | 2020-03-27 | Drilling risk assessment method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111563648A CN111563648A (en) | 2020-08-21 |
| CN111563648B true CN111563648B (en) | 2021-03-02 |
Family
ID=72071496
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010228968.5A Active CN111563648B (en) | 2020-03-27 | 2020-03-27 | Drilling risk assessment method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111563648B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113095593B (en) * | 2021-04-30 | 2023-09-19 | 中国石油大学(北京) | Method, device and equipment for determining well wall state of well drilling |
| CN114526052B (en) * | 2021-12-31 | 2023-09-19 | 中国石油天然气集团有限公司 | Risk prediction method and device for well drilling and completion engineering |
| CN117709729A (en) * | 2023-12-28 | 2024-03-15 | 中国铁道科学研究院集团有限公司 | Method for evaluating application risk of major engineering innovation result and electronic equipment |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110869814A (en) * | 2017-07-06 | 2020-03-06 | 雪佛龙美国公司 | System and method for full waveform inversion of seismic data |
-
2020
- 2020-03-27 CN CN202010228968.5A patent/CN111563648B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110869814A (en) * | 2017-07-06 | 2020-03-06 | 雪佛龙美国公司 | System and method for full waveform inversion of seismic data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111563648A (en) | 2020-08-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111563648B (en) | Drilling risk assessment method and device | |
| Zhou et al. | Classification of rockburst in underground projects: comparison of ten supervised learning methods | |
| Liu et al. | Tunnel boring machine vibration-based deep learning for the ground identification of working faces | |
| US20210232964A1 (en) | Method and Apparatus for Evaluating Quantum Gate in Superconducting Circuit, Device and Storage Medium | |
| CN109035730A (en) | It is a kind of to consider that the concrete dam that Service Environment influences damages dynamic warning method | |
| Abdulai et al. | Uncertainty and reliability analysis of open pit rock slopes: a critical review of methods of analysis | |
| Han et al. | In-situ stress inversion in Liard Basin, Canada, from caliper logs | |
| Zhao et al. | A hybrid recognition model of microseismic signals for underground mining based on CNN and LSTM networks | |
| CN117313506B (en) | Tunnel surrounding rock topology safety coefficient and stability calculation method | |
| Hu et al. | A Real‐Time Seismic Intensity Prediction Framework Based on Interpretable Ensemble Learning | |
| Wu et al. | An improved fractal prediction model for forecasting mine slope deformation using GM (1, 1) | |
| CN115267667B (en) | Underground high-precision positioning correction method, device, equipment and storage medium | |
| Alghalandis et al. | Similarity analysis of discrete fracture networks | |
| Gentili et al. | Forecasting strong subsequent earthquakes in California clusters by machine learning | |
| CN116992522A (en) | Deep foundation pit support structure deformation prediction method, device, equipment and storage medium | |
| Yan et al. | A novel method for identifying geomechanical parameters of rock masses based on a PSO and improved GPR hybrid algorithm | |
| CN111502647B (en) | Method and device for determining drilling geological environment factors and storage medium | |
| CN109948291A (en) | A kind of discontinuous boundary line direction-adaptive recognition methods of sand body | |
| CN105989095A (en) | Association rule significance test method and device capable of considering data uncertainty | |
| CN111553981B (en) | Three-dimensional geological modeling method and system based on modeling region classification | |
| CN114330442A (en) | Pipeline strain characteristic classification calculation method and system based on K-nearest neighbor method | |
| CN113946790A (en) | Method, system, equipment and terminal for predicting height of water flowing fractured zone | |
| CN113435059A (en) | Model establishing method, crack initiation event diagnosis method and device | |
| Meng et al. | Semi-supervised deep learning for recognizing construction activity types from vibration monitoring data | |
| CN113095593A (en) | Method, device and equipment for determining well wall state of drilling well |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240327 Address after: 100728 No. 22 North Main Street, Chaoyang District, Beijing, Chaoyangmen Patentee after: CHINA PETROLEUM & CHEMICAL Corp. Country or region after: China Patentee after: Sinopec Petroleum Engineering Technology Research Institute Co.,Ltd. Patentee after: China University of Petroleum (Beijing) Address before: 102206 Chunchao building, No.5 Baisha Road, Shahe Town, Changping District, Beijing Patentee before: SINOPEC Research Institute OF PETROLEUM ENGINEERING Country or region before: China Patentee before: China University of Petroleum (Beijing) |
|
| TR01 | Transfer of patent right |