CN119047343B - Wellbore stability control method, device, equipment and storage medium for dynamically adjusting drilling fluid ratio - Google Patents
Wellbore stability control method, device, equipment and storage medium for dynamically adjusting drilling fluid ratio Download PDFInfo
- Publication number
- CN119047343B CN119047343B CN202411525891.2A CN202411525891A CN119047343B CN 119047343 B CN119047343 B CN 119047343B CN 202411525891 A CN202411525891 A CN 202411525891A CN 119047343 B CN119047343 B CN 119047343B
- Authority
- CN
- China
- Prior art keywords
- drilling fluid
- drilling
- data
- fluid ratio
- ratio
- 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
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B21/00—Methods or apparatus for flushing boreholes, e.g. by use of exhaust air from motor
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B44/00—Automatic control systems specially adapted for drilling operations, i.e. self-operating systems which function to carry out or modify a drilling operation without intervention of a human operator, e.g. computer-controlled drilling systems; Systems specially adapted for monitoring a plurality of drilling variables or conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0499—Feedforward networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Mining & Mineral Resources (AREA)
- Artificial Intelligence (AREA)
- Geology (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mechanical Engineering (AREA)
- Earth Drilling (AREA)
Abstract
本发明涉及一种钻井技术领域，是一种动态调整钻井液配比的井壁稳定控制方法、装置、设备及存储介质，包括获取当前的钻井环境数据和实时钻井数据，其中钻井环境数据包括钻井液性能数据、地质数据，其中实时钻井参数包括钻压、转速、泥浆泵排量；将当前的钻井环境数据和实时钻井数据输入钻井液配比控制模型组，得到最优的钻井液配比和钻井参数组合。本发明利用当前的钻井液性能数据、地质数据、实时钻井参数预测最优的钻井液配比和钻井参数组合，以适应当前的地质条件和钻井需求，增加钻井液的针对性，确保钻井液与井壁的紧密贴合和高度适配，避免钻井液与井壁贴合度低会导致钻井液无法有效支撑井壁，加剧井壁失稳的问题，提高井壁稳定性。
The present invention relates to a field of drilling technology, and is a wellbore stability control method, device, equipment and storage medium for dynamically adjusting the drilling fluid ratio, including obtaining current drilling environment data and real-time drilling data, wherein the drilling environment data includes drilling fluid performance data and geological data, wherein the real-time drilling parameters include drilling pressure, rotation speed, and mud pump displacement; the current drilling environment data and real-time drilling data are input into a drilling fluid ratio control model group to obtain an optimal drilling fluid ratio and drilling parameter combination. The present invention uses the current drilling fluid performance data, geological data, and real-time drilling parameters to predict the optimal drilling fluid ratio and drilling parameter combination to adapt to the current geological conditions and drilling requirements, increase the pertinence of the drilling fluid, ensure the close fit and high adaptability of the drilling fluid to the wellbore, avoid the problem that the drilling fluid cannot effectively support the wellbore due to the low fit between the drilling fluid and the wellbore, and aggravate the problem of wellbore instability, thereby improving the wellbore stability.
Description
Technical Field
The invention relates to the technical field of drilling, in particular to a well wall stability control method, device and equipment for dynamically adjusting the proportion of drilling fluid and a storage medium.
Background
With the continuous development of petroleum exploration and drilling technology, the requirements on the stability of the well wall are higher and higher. The instability of the well wall not only affects the drilling efficiency, but also can cause serious safety accidents, and the stability of the well wall is a key factor in the petroleum and natural gas drilling process. The instability of the well wall can cause a series of problems such as collapse of the well wall, lost circulation, sticking of the drill bit, etc., which not only increases the cost of drilling, but can also cause environmental pollution and safety hazards, and the drilling fluid plays a critical role in maintaining stability of the well wall because it can provide wellbore pressure, carry cuttings, cool the drill bit, and lubricate the drill string.
At present, the traditional drilling fluid proportion is often based on experience or a fixed formula, real-time adjustment cannot be carried out according to the actual state of a well wall in the drilling process, the single proportion mode cannot adapt to complex and changeable underground environments, and the performance of the drilling fluid cannot meet the requirement of well wall stability, so that the unmatched performance of the drilling fluid can aggravate well wall instability, the risk of drilling accidents is increased, and the drilling efficiency is reduced.
Specifically, different geological conditions, rock types and drilling depths are different from each other in performance requirements of drilling fluid, however, the conventional drilling fluid proportioning technology is often based on experience or a fixed formula, pertinence is lacking, close fitting and high adaptation of the drilling fluid and a well wall cannot be ensured, so that the drilling fluid cannot effectively support the well wall due to low fitting degree of the drilling fluid and the well wall, instability of the well wall is aggravated, meanwhile, the drilling efficiency is affected due to insufficient performance of the drilling fluid, and the drilling cost is increased.
The first existing published patent document, publication number CN115438090A, discloses a method and a system for analyzing and predicting the type of well wall instability based on the characteristics of a block dropping image, and belongs to the field of petroleum and natural gas drilling. According to the method, various block-dropping image characteristic data are firstly obtained, then data mining is carried out on the block-dropping image characteristic data to obtain a well-wall instability type analysis and prediction model, and finally the well-wall instability type is analyzed and predicted by utilizing the well-wall instability type analysis and prediction model. According to the invention, advanced data analysis means such as data mining are used to form a method for analyzing and predicting the type of the well wall instability based on the block dropping image characteristics based on the block dropping image characteristic data mining, so that the problem that the existing well wall instability type is difficult to be defined is solved, a more accurate and rapid classification and prediction method is provided for the well wall instability, and a basis is provided for forming a well wall stability control countermeasure.
The prior published patent document II, publication number CN104732064B, discloses a design method of oil-based drilling fluid parameters, which sequentially comprises the following steps of testing physical properties and structural properties of stratum rocks through experiments, establishing a comprehensive characterization model of typical minerals, pore structures of the stratum rocks and wettability of the oil-based drilling fluid parameters on the stratum rocks and an oil-based drilling fluid system according to the physical properties and the structural properties of the stratum rocks, drawing a relation diagram between the oil-based drilling fluid parameters and the wettability, establishing a well wall stability mechanical model of the stratum rocks and the oil-based drilling fluid system under the condition of the wettability, drawing a relation diagram between the oil-based drilling fluid parameters and the well wall stability, and determining the oil-based drilling fluid parameters according to the relation diagram between the oil-based drilling fluid parameters and the well wall stability. The window of the oil-based drilling fluid parameter designed by the invention is accurate and reasonable, the effect of keeping the stability of the well wall of the oil-based drilling fluid can be quantitatively evaluated, the occurrence of underground complex conditions is prevented, and the cost of the oil-based drilling fluid is reasonably controlled.
The two patent publications do not relate to a method for completing well wall stability control based on dynamic adjustment of drilling fluid proportion, and the second patent publication also uses a model to complete design of oil-based drilling fluid parameters, but the model and data used in the dynamic adjustment of drilling fluid process are different from those of the present invention.
Disclosure of Invention
The invention provides a well wall stability control method, device, equipment and storage medium for dynamically adjusting the proportion of drilling fluid, which overcomes the defects of the prior art, and can effectively solve the problems that the proportion of the traditional drilling fluid is often based on experience or a fixed formula, pertinence is lacking, the condition of low fitting degree of the drilling fluid and the well wall is easy to occur, the drilling fluid is easy to cause that the well wall cannot be effectively supported, and the well wall instability is aggravated.
The technical scheme of the invention is realized by the following measures that the well wall stability control method for dynamically adjusting the proportion of the drilling fluid comprises the following steps:
acquiring current drilling environment data and real-time drilling data, wherein the drilling environment data comprise drilling fluid data and geological data, and the real-time drilling data comprise weight on bit, rotating speed and slurry pump displacement;
The method comprises the steps of inputting current drilling environment data and real-time drilling data into a drilling fluid proportion control model group to obtain an optimal drilling fluid proportion and drilling parameter combination, wherein the drilling fluid proportion control model group comprises an associated prediction model and a collaborative optimization model, the associated prediction model is obtained by deep learning of a neural network through a plurality of first samples, each first sample comprises a drilling fluid proportion identification and drilling fluid proportion data and geological data, the collaborative optimization model is obtained by deep learning of the neural network through a plurality of second samples, and each second sample comprises an optimal drilling fluid proportion and drilling parameter combination identification and a drilling fluid proportion and corresponding drilling parameter combination.
The following are further optimizations and/or improvements to the above-described inventive solution:
The drilling fluid proportion control model group comprises an associated prediction model and a collaborative optimization model, the deep learning methods of the associated prediction model and the collaborative optimization model are the same as the neural network used by the deep learning, the types of samples used by the deep learning are different, and the deep learning method of the associated prediction model comprises the following steps:
A plurality of first samples are obtained and are divided into a training sample set, a verification sample set and a test sample set according to the proportion, wherein each first sample comprises a drilling fluid proportion mark, drilling fluid proportion data and geological data;
Training a multilayer feedforward neural network by using a training set, introducing a loss function during training, ending training when the value of the loss function is stable to obtain an associated prediction model, wherein the multilayer feedforward neural network comprises an input layer, a hidden layer and an output layer, the input layer receives drilling fluid data and geological data as input data, the hidden layer comprises one or more layers, nonlinearity is introduced through an activation function, the input data is processed and extracted by characteristics, and the output layer outputs predicted drilling fluid proportion;
And respectively verifying and testing the trained associated prediction model by using a verification set and a test set, optimizing model parameters of the associated prediction model, and outputting the associated prediction model meeting the test evaluation requirement.
The above-mentioned still include to drilling fluid ratio control model group output's optimal drilling fluid ratio and drilling parameter combination, carry out dynamic adjustment to drilling fluid ratio, include:
Confirming whether the received drilling fluid proportion is complete and accurate or not, and meeting the requirement of the current drilling operation;
In response, calculating the amount of various materials required by the drilling fluid according to the drilling fluid proportion and the current mud volume;
And (3) obtaining a performance test result of the drilling fluid, and reversely adjusting the proportion of the drilling fluid according to the performance test result until the performance test meets the requirements.
The drilling fluid performance test results comprise an oil-based drilling fluid system fluid loss performance evaluation result, an oil-based drilling fluid HTHP fluid loss performance evaluation result and a water-based drilling fluid rheological property evaluation result.
The method further comprises the step of reversely optimizing the drilling fluid proportion control model group according to the actual implementation result after dynamically adjusting the drilling fluid proportion, and comprises the following steps:
Monitoring and judging whether the performance of the drilling fluid or the underground key parameter is abnormal in real time, wherein the performance of the drilling fluid or the underground key parameter is data for using the drilling fluid after dynamic adjustment on a drilling site;
and if so, adjusting parameters of each model in the drilling fluid proportion control model group, and carrying out deep learning on the drilling fluid proportion control model group again.
The second technical scheme of the invention is realized by the following measures that the well wall stability control device for dynamically adjusting the proportion of the drilling fluid comprises:
the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit acquires current drilling environment data and real-time drilling data, the drilling environment data comprise drilling fluid data and geological data, and the real-time drilling data comprise drilling pressure, rotating speed and slurry pump displacement;
The ratio determining unit inputs the current drilling environment data and the real-time drilling data into a drilling fluid ratio control model group to obtain an optimal drilling fluid ratio and drilling parameter combination, wherein the drilling fluid ratio control model group comprises an associated prediction model and a collaborative optimization model, the associated prediction model is obtained by deep learning of a neural network through a plurality of first samples, each first sample comprises a drilling fluid ratio identification, drilling fluid data and geological data, the collaborative optimization model is obtained by deep learning of the neural network through a plurality of second samples, and each second sample comprises an optimal drilling fluid ratio identification and drilling parameter combination and a combination of the drilling fluid ratio and any corresponding drilling parameter.
The following are further optimizations and/or improvements to the above-described inventive solution:
the above-mentioned proportion determination unit includes:
The model training module is used for training a drilling fluid proportion control model group, wherein the drilling fluid proportion control model group comprises an associated prediction model and a collaborative optimization model, the deep learning methods of the associated prediction model and the collaborative optimization model are the same as a neural network used for deep learning, sample types used for the deep learning of the associated prediction model and the collaborative optimization model are different, and the deep learning method of the associated prediction model comprises the following steps:
A plurality of first samples are obtained and are divided into a training sample set, a verification sample set and a test sample set according to the proportion, wherein each first sample comprises a drilling fluid proportion mark, drilling fluid proportion data and geological data;
Training a multilayer feedforward neural network by using a training set, introducing a loss function during training, ending training when the value of the loss function is stable to obtain an associated prediction model, wherein the multilayer feedforward neural network comprises an input layer, a hidden layer and an output layer, the input layer receives drilling fluid data and geological data as input data, the hidden layer comprises one or more layers, nonlinearity is introduced through an activation function, the input data is processed and extracted by characteristics, and the output layer outputs predicted drilling fluid proportion;
Respectively verifying and testing the trained associated prediction model by using a verification set and a test set, optimizing model parameters of the associated prediction model, and outputting the associated prediction model meeting test evaluation requirements;
and the proportion optimizing module inputs the current drilling environment data and the real-time drilling data into a drilling fluid proportion control model group to obtain the optimal drilling fluid proportion and drilling parameter combination.
The above further includes:
The ratio dynamic adjustment unit is used for dynamically adjusting the drilling fluid ratio according to the optimal drilling fluid ratio and drilling parameter combination output by the drilling fluid ratio control model group, and comprises the following steps:
Confirming whether the received drilling fluid proportion is complete and accurate or not, and meeting the requirement of the current drilling operation;
In response, calculating the amount of various materials required by the drilling fluid according to the drilling fluid proportion and the current mud volume;
obtaining a performance test result of the drilling fluid, and reversely adjusting the proportion of the drilling fluid according to the performance test result until the performance test meets the requirements;
The model reverse optimization unit, after carrying out dynamic adjustment to the drilling fluid proportion, reversely optimizes the drilling fluid proportion control model group according to the actual implementation result, and comprises:
Monitoring and judging whether the performance of the drilling fluid or the underground key parameter is abnormal in real time, wherein the performance of the drilling fluid or the underground key parameter is data for using the drilling fluid after dynamic adjustment on a drilling site;
and if so, adjusting parameters of each model in the drilling fluid proportion control model group, and carrying out deep learning on the drilling fluid proportion control model group again.
The third technical scheme of the invention is realized by the following measures that the electronic equipment comprises a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded and executed by the processor to realize the steps in the well wall stability control method for dynamically adjusting the proportion of drilling fluid.
The fourth technical scheme of the invention is realized by the following measures that a storage medium is stored with a computer program which can be read by a computer, and the computer program is set to execute the steps in a well wall stability control method for dynamically adjusting the proportion of drilling fluid when in operation.
According to the invention, the current drilling fluid data, geological data and real-time drilling data are utilized to dynamically predict the optimal drilling fluid proportion and drilling parameter combination so as to adapt to the current geological conditions and drilling requirements, thereby increasing the pertinence of the drilling fluid, ensuring the close fit and the high adaptation of the drilling fluid and the well wall, avoiding the problem that the drilling fluid cannot effectively support the well wall due to low fit degree of the drilling fluid and the well wall, increasing the stability of the well wall and reducing the risk of the instability of the well wall. Furthermore, the invention utilizes the correlation prediction model and the cooperative optimization model to carry out targeted adjustment on the drilling fluid proportion, and the correlation prediction model and the cooperative optimization model are obtained by deep learning on the neural network through different samples, so that the neural network can be continuously optimized and updated according to different geological conditions and drilling requirements, the neural network has high adaptability and stability, the drilling fluid proportion can be more accurately and dynamically adjusted, the correlation prediction model in the correlation prediction model and the cooperative optimization model outputs the predicted optimal drilling fluid proportion, the cooperative optimization model can analyze the optimal drilling fluid proportion and drilling parameter combination, unnecessary drilling fluid consumption is reduced, the drilling process is smoother and more efficient, the loss of drilling stopping, repairing and the like is reduced, the drilling cost is further reduced, and the economic benefit is improved. In addition, the invention can dynamically adjust the drilling fluid ratio by combining the corresponding drilling fluid performance according to the optimal drilling fluid ratio and drilling parameter combination output by the drilling fluid ratio control model group, so that the drilling fluid ratio meets the working condition requirement better.
Drawings
FIG. 1 is a schematic diagram of an implementation environment according to an embodiment of the present invention.
Fig. 2 is a schematic flow chart of a method for adjusting the proportion of drilling fluid according to an embodiment of the invention.
Fig. 3 is a schematic flow chart of a model deep learning method according to an embodiment of the present invention.
Fig. 4 is a schematic flow chart of a method for dynamically adjusting drilling fluid ratio again according to an embodiment of the present invention.
FIG. 5 is a schematic flow chart of a method for reversely optimizing a drilling fluid proportioning control model set according to an actual implementation result according to an embodiment of the present invention.
Fig. 6 is a schematic view of an apparatus according to an embodiment of the present invention.
Fig. 7 is a schematic view of an apparatus according to another embodiment of the present invention.
Detailed Description
The present invention is not limited by the following examples, and specific embodiments can be determined according to the technical scheme and practical situations of the present invention.
Those skilled in the art will appreciate that, unless specifically stated otherwise, a "module" or "unit" in an embodiment of the invention refers to a computer program or a portion of a computer program that has predetermined functions and that works in conjunction with other relevant portions to achieve the predetermined goals, and may be implemented in whole or in part using software, hardware (such as processing circuitry or memory), or a combination thereof. Also, a processor (or multiple processors or memories) may be used to implement one or more modules or units. Furthermore, each module or unit may be part of an overall module or unit that incorporates the functionality of the module or unit.
In addition, the "plurality" in the embodiments of the present invention means two or more, and the "first" and "second" and the like are used to distinguish the descriptions, and are not to be construed as implying relative importance.
At present, the traditional drilling fluid proportion is often based on experience or a fixed formula, real-time adjustment cannot be carried out according to the actual state of a well wall in the drilling process, the single proportion mode cannot adapt to complex and changeable underground environments, so that the performance of the drilling fluid cannot meet the requirement of well wall stability, and therefore, the mismatching of the performance of the drilling fluid can aggravate well wall instability, increase the risk of drilling accidents and reduce the drilling efficiency;
Specifically, different geological conditions, rock types and drilling depths are different from each other in performance requirements of drilling fluid, however, the conventional drilling fluid proportioning technology is often based on experience or a fixed formula, pertinence is lacking, close fitting and high adaptation of the drilling fluid and a well wall cannot be ensured, so that the drilling fluid cannot effectively support the well wall due to low fitting degree of the drilling fluid and the well wall, instability of the well wall is aggravated, meanwhile, the drilling efficiency is affected due to insufficient performance of the drilling fluid, and the drilling cost is increased. Therefore, the embodiment of the invention provides a well wall stability control method for dynamically adjusting the proportion of drilling fluid.
The embodiment of the invention provides a well wall stability control method for dynamically adjusting drilling fluid ratio, which comprises the steps of obtaining a drilling fluid ratio control model set by deep learning a neural network, wherein the drilling fluid ratio control model set comprises a correlation prediction model and a cooperative optimization model, the correlation prediction model can mine the correlation between the drilling fluid ratio and the well wall stability, the optimal drilling fluid ratio is obtained by predicting the current drilling fluid data and geological data, the cooperative optimization model performs cooperative optimization on the drilling fluid ratio and drilling parameters, the optimal drilling fluid ratio and drilling parameter combination is obtained by outputting the optimal drilling fluid ratio and real-time drilling data output by the correlation prediction model, and the drilling fluid ratio is dynamically adjusted.
The method provided by the embodiment of the invention can relate to an artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) technology, and can be realized based on the artificial intelligence technology, for example, a deep learning mode is adopted, and a corresponding model is obtained by training a sample.
The machine learning (MACHINE LEARNING, ML) is a multi-domain interdisciplinary, and relates to a plurality of disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. It is specially studied how a computer simulates or implements learning behavior of a human to acquire new knowledge or skills, and reorganizes existing knowledge structures to continuously improve own performance. Machine learning is the core of artificial intelligence, a fundamental approach to letting computers have intelligence, which is applied throughout various areas of artificial intelligence.
Wherein, the deep learning (DL, deep Learning) refers to machine learning based on a deep neural network model and a method. The method is developed by combining contemporary big data and great calculation power development on the basis of algorithm models such as statistical machine learning, artificial neural network and the like, and the most important technical characteristics of deep learning are the capability of automatically extracting the characteristics.
Such machine learning and deep learning typically include neural networks, belief networks, reinforcement learning, transfer learning, induction learning, teaching learning, and the like.
In the process of training the neural network, the loss function hopes that the output of the neural network is as close to the value which is really expected to be predicted as possible, so the predicted value and the target value of the current network can be compared, and then the weight vector of each layer of the neural network is updated according to the difference condition between the predicted value and the target value (wherein an initialization process is usually performed before the first update, namely, each layer of the neural network is preconfigured with parameters) until the neural network can predict the target value or the value which is very close to the target value. Therefore, the "how to compare the difference between the predicted value and the target value" needs to be defined in advance at the time of deep learning, and is then a loss function (loss function).
Fig. 1 is a schematic diagram of an implementation environment provided by an embodiment of the present invention. The implementation environment may include a training device and a use device.
The training device and the using device are computer devices, alternatively, the computer devices are terminal devices, such as mobile phones, tablet computers, PCs (personal computers) and other electronic devices, or the computer devices are servers, which can be a server, a server cluster formed by a plurality of servers, or a cloud computing service center, and the embodiment of the invention is not limited to this.
The training device refers to a computer device with neural network training and learning capabilities. Optionally, the training device has a capability of acquiring a neural network and training and learning the neural network according to application requirements, for example, the training device acquires the neural network from other devices through a network and trains the neural network through training samples according to application requirements so that the neural network has the capability of acquiring the optimal drilling fluid proportion and drilling parameter combination, optionally, the training device has a neural network construction capability of constructing the neural network according to application requirements and trains and learns the neural network, for example, the training device constructs the neural network by itself in order to acquire the optimal drilling fluid proportion and drilling parameter combination according to drilling environment data and real-time drilling data, and trains and learns the neural network through the samples according to application requirements.
The use device refers to a computer device with a neural network use requirement, optionally, the use device obtains the neural network from other devices through a network according to the application requirement, for example, the use device has a requirement of optimal drilling fluid proportion and drilling parameter combination prediction, and can obtain the neural network for completing training and learning and predicting the optimal drilling fluid proportion and drilling parameter combination from other devices through the network, and uses the neural network to perform optimal drilling fluid proportion and drilling parameter combination prediction.
Based on this, the technical solution of the present invention will be described below with reference to several embodiments and drawings.
Embodiment 1. As shown in fig. 2, the embodiment of the invention discloses a borehole wall stability control method for dynamically adjusting the proportion of drilling fluid, which comprises the following steps:
step S110, current drilling environment data and real-time drilling data are acquired, wherein the drilling environment data comprise drilling fluid data and geological data, and the real-time drilling data comprise drilling pressure, rotating speed and mud pump displacement.
Specifically, the current drilling environment data and the real-time drilling data are acquired as follows:
(1) Determining a detection environment, positioning the detected well wall environment, and determining the current drilling fluid type, drilling equipment, drilling environment and geological data by combining drilling data, wherein the geological data comprise stratum type, rock mechanical parameters and the like;
(2) The method comprises the steps of acquiring drilling fluid performance data and real-time drilling data by using monitoring equipment (such as performance detection instruments and various sensors) installed on a drilling site, wherein the drilling fluid performance data comprise density, viscosity, API (application program interface) fluid loss and the like, and the real-time drilling data comprise temperature, weight on bit, rotating speed, slurry pump displacement and the like.
It should be noted that all the data acquired here need to be related to the stability of the well wall.
The sensors referred to above may include, but are not limited to:
The temperature sensor converts temperature into electric signal and outputs the electric signal by utilizing the characteristic that the material changes its resistance, capacitance or potential along with the change of temperature. Common temperature sensors include thermocouples, thermistors, and the like, which monitor downhole temperature changes in real time.
Pressure sensor, which is to realize pressure measurement based on piezoresistance effect, piezoelectricity effect or capacitance effect. The pressure sensor reflects the pressure change by measuring the resistance change of the piezoresistance element, the piezoelectric pressure sensor generates a voltage signal by utilizing the uneven phenomenon of charge distribution generated by the piezoelectric material after being stressed, and the capacitive pressure sensor reflects the pressure change by measuring the capacitance change and monitors the pressure change in the well, such as bottom hole pressure, well wall pressure and the like.
And the vibration sensor reflects the vibration state of the object by measuring parameters such as the frequency, the amplitude and the like of the vibration of the object. Common vibration sensors include piezoelectric, eddy current, etc., which monitor vibration of downhole equipment in real time, such as drilling machinery, pumps, etc.
In practical application, the selection and adjustment can be required according to specific requirements and scenes. Meanwhile, in order to realize real-time monitoring on the stability of the well wall, other sensors and monitoring equipment such as a liquid level sensor, a PH sensor and the like are also required to be combined.
Step S120, inputting current drilling environment data and real-time drilling data into a drilling fluid proportion control model group to obtain an optimal drilling fluid proportion and drilling parameter combination, wherein the drilling fluid proportion control model group comprises an associated prediction model and a collaborative optimization model, the associated prediction model is obtained by deep learning of a neural network by using a plurality of first samples, each first sample comprises a drilling fluid proportion identification, drilling fluid data and geological data, the collaborative optimization model is obtained by deep learning of the neural network by using a plurality of second samples, and each second sample comprises an optimal drilling fluid proportion and drilling parameter combination identification and a drilling fluid proportion and corresponding any drilling parameter combination.
In this embodiment, the drilling fluid ratio control model set includes an associated prediction model and a collaborative optimization model, and the associated prediction model and the collaborative optimization model use the same deep learning method and neural network although the types of samples used in the deep learning process are different, so in this embodiment, the deep learning process is illustrated by taking the deep learning method of the associated prediction model as an example, as shown in fig. 3, including:
Step S121, a plurality of first samples are obtained and are divided into a training sample set, a verification sample set and a test sample set according to proportion, wherein each first sample comprises a drilling fluid proportion mark, drilling fluid proportion data and geological data;
Each first sample comprises a drilling fluid proportion identifier, drilling fluid performance data and geological data, wherein the specific drilling fluid performance data and geological data are obtained by screening historical drilling fluid performance data and historical geological data corresponding to different drilling fluid proportions, data closely related to well wall stability are screened out, the drilling fluid performance data in the embodiment can comprise drilling fluid density, viscosity and API fluid loss, the geological data comprise stratum types and rock mechanical parameters, after screening, all the data are cleaned, tidied, abnormal values and missing values are removed, standardized or normalized, and corresponding data coding and conversion are further carried out according to input data requirements of a multilayer feedforward neural network.
Step S122, training the multi-layer feedforward neural network by utilizing a training set, introducing a loss function during training, ending training when the value of the loss function is stable, and obtaining a correlation prediction model, wherein the multi-layer feedforward neural network comprises an input layer, a hidden layer and an output layer, the input layer receives drilling fluid data and geological data as input data, the hidden layer comprises one or more layers, nonlinearity is introduced through an activation function, the input data is processed and extracted in characteristics, and the output layer outputs predicted drilling fluid proportion.
The structure of the multilayer feedforward neural network used for training is specifically as follows:
the multilayer feedforward neural network comprises an input layer, a hidden layer and an output layer;
the input layer receives drilling fluid data and geological data as input data;
Hidden layers (multiple hidden layers can be designed according to the complexity of the problem, each hidden layer comprises multiple neurons), nonlinearity is introduced through an activation function, input data is processed and characteristics are extracted, wherein the nonlinearity of the output of each neuron is usually generated through an activation function (such as ReLU, sigmoid or tanh), and the construction of one function is selected when the hidden layer is used;
the output layer outputs the predicted drilling fluid ratio.
Wherein, the formula of the multilayer feedforward neural network is as follows:
In the formula, Is an activation function, such as ReLU; is from the input layer or the first hidden layer From neuron to current layerWeights of individual neurons; is the first input layer or the last hidden layer The output of the individual neurons; Is the current layer Bias terms for the individual neurons; is the number of neurons in the input layer or in the previous hidden layer.
Input layerRepresenting drilling fluid data and geological data, and an output layerThen this represents the predicted drilling fluid formulation.
When the training set is used to train the multi-layer feedforward neural network, the multi-layer feedforward neural network can be trained by using an optimization algorithm such as a back propagation algorithm and gradient descent, and a proper loss function such as a Mean Square Error (MSE) is set to measure the difference between the model predicted value and the true value.
And step S123, verifying and testing the trained associated prediction model by using a verification set and a test set respectively, optimizing model parameters of the associated prediction model, and outputting the associated prediction model meeting test evaluation requirements.
The method comprises the steps of verifying the associated prediction model by using a verification set, adjusting model parameters of the associated prediction model (namely, optimizing weight and bias parameters of the multi-layer feedforward neural network), testing the associated prediction model by using a test set, and evaluating and analyzing test results, wherein the evaluation and analysis method comprises mean square error index (MSE), mean absolute error index (MAE), root mean square error index (RMSE), determining coefficient index (R2), ending all training steps when the evaluation results meet test evaluation requirements (namely, threshold conditions of evaluation and analysis indexes are set according to actual conditions), and carrying out training again after the weight and bias parameters of the multi-layer feedforward neural network are optimized when the evaluation results do not meet the test evaluation requirements.
In the embodiment, the collaborative optimization model balances optimization requirements among different drilling parameters through multi-objective optimization (such as a weighted loss function), realizes collaborative optimization of drilling fluid proportion and drilling parameters, and particularly utilizes a plurality of second samples to perform deep learning on a neural network to obtain the collaborative optimization model, wherein the process is the same as that in the steps S121-S122, and the difference is that each second sample comprises an identification of an optimal drilling fluid proportion and drilling parameter combination and a combination of the drilling fluid proportion and any drilling parameter corresponding to the optimal drilling fluid proportion, wherein the combination of the drilling fluid proportion and any drilling parameter corresponding to the optimal drilling fluid proportion is the combination of the drilling fluid proportion and any drilling parameter corresponding to the drilling parameter, and the combination of any drilling parameter corresponding to the drilling parameter is the drilling parameter approaching to the drilling parameter in the optimal drilling fluid proportion and drilling parameter combination.
The invention discloses a well wall stability control method for dynamically adjusting the proportion of drilling fluid, which utilizes the current drilling fluid data, geological data and real-time drilling data to dynamically predict the optimal proportion of the drilling fluid and drilling parameter combination so as to adapt to the current geological conditions and drilling requirements, thereby increasing the pertinence of the drilling fluid, ensuring the close fit and the high adaptation of the drilling fluid and the well wall, avoiding the problem that the drilling fluid cannot effectively support the well wall due to low fit degree of the drilling fluid and the well wall, exacerbating the problem of well wall instability, improving the stability of the well wall and reducing the risk of well wall instability. Furthermore, the invention utilizes the correlation prediction model and the cooperative optimization model to carry out targeted adjustment on the drilling fluid proportion, and the correlation prediction model and the cooperative optimization model are obtained by deep learning on the neural network through different samples, so that the neural network can be continuously optimized and updated according to different geological conditions and drilling requirements, the neural network has high adaptability and stability, the drilling fluid proportion can be more accurately and dynamically adjusted, the correlation prediction model in the correlation prediction model and the cooperative optimization model outputs the predicted optimal drilling fluid proportion, the cooperative optimization model can analyze the optimal drilling fluid proportion and drilling parameter combination, unnecessary drilling fluid consumption is reduced, the drilling process is smoother and more efficient, the loss of drilling stopping, repairing and the like is reduced, the drilling cost is further reduced, and the economic benefit is improved.
Embodiment 2. As shown in FIG. 4, the embodiment of the invention discloses a well wall stability control method for dynamically adjusting the proportion of drilling fluid, which is a further optimization of the above embodiment, and further comprises the steps of dynamically adjusting the proportion of drilling fluid by aiming at the optimal combination of the proportion of drilling fluid and drilling parameters output by a drilling fluid proportion control model group, and comprises the following steps:
Step S210, confirming whether the received drilling fluid proportion is complete and accurate, and meeting the requirement of the current drilling operation.
In response to step S220, the amount of various materials required for the drilling fluid is calculated based on the drilling fluid formulation and the current mud volume.
Specifically, if the received drilling fluid proportion is confirmed to be complete and accurate and meets the requirement of the current drilling operation, the batching work is carried out, namely after material preparation and batching equipment inspection are completed, the optimal drilling fluid proportion and the current mud volume output by the drilling fluid proportion control model group are calculated, and the quantity of various materials required by the drilling fluid is calculated.
For example, the optimal drilling fluid proportions output by the drilling fluid proportion control model group comprise water, bentonite, calcined soda and other additives, and the proportion of each additive in the drilling fluid, wherein the other additives comprise an additive 1 and an additive 2, and the corresponding process for calculating the amount of various materials required by the drilling fluid according to the drilling fluid proportions and the current mud volume is as follows:
the drilling fluid is prepared from water, bentonite, sodium carbonate and additive 1, wherein the additive is 2=45:50:2:1:2 (for example only);
the current mud volume is V;
The amounts of the various materials required for the drilling fluid are as follows:
and step S230, obtaining a performance test result of the drilling fluid, and reversely adjusting the proportion of the drilling fluid according to the performance test result until the performance test meets the requirements.
Specifically, the performance test of the drilling fluid is set according to requirements, for example, the performance test of the drilling fluid includes the tests of solid phase content, specific gravity, funnel viscosity, water loss, mud cake thickness, sand content, pH value and the like, the performance test process of the drilling fluid is the existing known technology, and the drilling fluid performance test results obtained in the embodiment can include, but are not limited to, the oil-based drilling fluid system fluid loss performance evaluation result, the oil-based drilling fluid HTHP fluid loss performance evaluation result, and the water-based drilling fluid rheological performance evaluation result, and are specifically selected according to the type (oil-based or water-based) of the drilling fluid.
The evaluation processes corresponding to the evaluation results of the fluid loss performance of the base drilling fluid system, the evaluation results of the fluid loss performance of the oil-based drilling fluid HTHP and the evaluation results of the fluid rheological property of the water-based drilling fluid are as follows:
(1) The method comprises the following specific processes of measuring the fluid loss volume of the oil-based drilling fluid containing the polymer anti-multivalent cation treating agent prepared by a solution method by adopting a medium-pressure fluid loss meter:
And pouring 150 mL of prepared drilling fluid into a medium-pressure filtrate reducer, placing a gasket and special filter paper, covering a cover, screwing and sealing, and recording the volume of filtrate in 30 minutes under the output pressure of 0.69MPa, wherein the unit is mL of medium-pressure API filtrate loss of the drilling fluid.
(2) Evaluation of HTHP fluid loss properties of oil-based drilling fluids 150 mL of the prepared drilling fluids were poured into a mud cup, fitted with special filter papers for testing HTHP fluid loss, sealed, and placed in a high temperature high pressure filtration instrument (MJ-71, modern oil technology development Co.). After the temperature is raised to 150 ℃, connecting an upper pressure valve rod and a back pressure valve rod, keeping the upper pressure to be 4.2 MPa, keeping the back pressure to be 0.7 MPa, recording the filtrate volume of the filtrate loss 30 min, and multiplying the filtrate volume by 2 to obtain the HTHP filtrate loss.
(3) Evaluation of rheological Properties of Water-based drilling fluids drilling fluid rheological reference data include apparent viscosity, plastic viscosity and dynamic and static shear forces. After stirring the water-based drilling fluid at a high frequency rotation speed of 12000 rpm for 20 min, values of phi 600 and phi 300 are measured by using a six-speed rotational viscometer with reference to standard GB/T16782-1997, and values of phi 3 are respectively left stand for 10s and 10min after stirring at 600rpm for 1min, and Apparent Viscosity (AV), plastic Viscosity (PV) and dynamic shear force (YP) of the water-based drilling fluid are calculated by using the following formulas.
(A) Apparent viscosity AV (unit mpa·s) =0.511×Φ600
(B) Plastic viscosity PV (unit mpa.s) =Φ600- Φ300
(C) Kinetic shear force (unit Pa) yp=0.511 x (Φ300-PV)
(D) Primary cutting (Taq) =0.511×Φ3 (standing for 10 s)
End cut (τend) =0.511×Φ3 (rest 10 min)
Embodiment 3. As shown in FIG. 5, the embodiment of the invention discloses a well wall stability control method for dynamically adjusting the proportion of drilling fluid, which is a further optimization of the above embodiment, and further comprises the steps of reversely optimizing a drilling fluid proportion control model group according to the actual implementation result after dynamically adjusting the proportion of the drilling fluid, and comprises the following steps:
step S310, monitoring and judging whether the performance of the drilling fluid or the underground key parameters are abnormal in real time, wherein the performance of the drilling fluid or the underground key parameters are data for using the drilling fluid after dynamic adjustment in a drilling site.
It should be noted that, whether the drilling fluid performance or the underground key parameter is abnormal is monitored and judged in real time, that is, the drilling fluid performance and the underground key parameter obtained by the drilling monitoring device are communicated with the existing drilling monitoring device, and after the drilling fluid obtained by the optimal drilling fluid proportioning after the drilling fluid proportioning control model set and the dynamic adjustment treatment according to the embodiment and the drilling parameter matched with the drilling fluid proportioning control model set are input.
And step S320, in response to the answer, the parameters of each model in the drilling fluid proportion control model group are adjusted, deep learning is conducted on the drilling fluid proportion control model group again, and in response to the answer, the step S310 is continuously returned to monitor.
It should be understood that, in the embodiment of the present invention, parameters of each model in the drilling fluid ratio control model set are adjusted, and a process of performing deep learning on the drilling fluid ratio control model set again is the same as the model deep learning method corresponding to the foregoing, which is not described herein.
Embodiment 4. As shown in FIG. 6, the embodiment of the invention discloses a borehole wall stability control device for dynamically adjusting the proportion of drilling fluid, which comprises:
And the acquisition unit acquires current drilling environment data and real-time drilling data, wherein the drilling environment data comprises drilling fluid data and geological data, and the real-time drilling data comprises drilling pressure, rotating speed and slurry pump displacement.
The ratio determining unit inputs the current drilling environment data and the real-time drilling data into a drilling fluid ratio control model group to obtain an optimal drilling fluid ratio and drilling parameter combination, wherein the drilling fluid ratio control model group comprises an associated prediction model and a collaborative optimization model, the associated prediction model is obtained by deep learning of a neural network through a plurality of first samples, each first sample comprises a drilling fluid ratio identification, drilling fluid data and geological data, the collaborative optimization model is obtained by deep learning of the neural network through a plurality of second samples, and each second sample comprises an optimal drilling fluid ratio identification and drilling parameter combination and a combination of the drilling fluid ratio and any corresponding drilling parameter.
Wherein the proportioning determining unit comprises:
(1) The model training module is used for training a drilling fluid proportion control model group, wherein the drilling fluid proportion control model group comprises an associated prediction model and a collaborative optimization model, the deep learning methods of the associated prediction model and the collaborative optimization model are the same as a neural network used for deep learning, sample types used for the deep learning of the associated prediction model and the collaborative optimization model are different, and the deep learning method of the associated prediction model comprises the following steps:
A plurality of first samples are obtained and are divided into a training sample set, a verification sample set and a test sample set according to the proportion, wherein each first sample comprises a drilling fluid proportion mark, drilling fluid proportion data and geological data;
Training a multilayer feedforward neural network by using a training set, introducing a loss function during training, ending training when the value of the loss function is stable to obtain an associated prediction model, wherein the multilayer feedforward neural network comprises an input layer, a hidden layer and an output layer, the input layer receives drilling fluid data and geological data as input data, the hidden layer comprises one or more layers, nonlinearity is introduced through an activation function, the input data is processed and extracted by characteristics, and the output layer outputs predicted drilling fluid proportion;
And respectively verifying and testing the trained associated prediction model by using a verification set and a test set, optimizing model parameters of the associated prediction model, and outputting the associated prediction model meeting the test evaluation requirement.
It should be understood that, in the model training module in the embodiment of the present invention, the correlation prediction model and the collaborative optimization model are obtained by training using a plurality of first samples and a plurality of second samples through the same deep learning method as described above, so that the deep learning process of the collaborative optimization model is not described herein.
(2) And the proportion optimizing module inputs the current drilling environment data and the real-time drilling data into a drilling fluid proportion control model group to obtain the optimal drilling fluid proportion and drilling parameter combination.
The method comprises the steps of inputting current drilling fluid data and geological data into a correlation prediction model to obtain an optimal drilling fluid ratio, and inputting the optimal drilling fluid ratio and real-time drilling data into a collaborative optimization model to obtain an optimal drilling fluid ratio and drilling parameter combination.
Embodiment 5. As shown in FIG. 7, the embodiment of the invention discloses a borehole wall stability control device for dynamically adjusting the proportion of drilling fluid, which comprises:
And the acquisition unit acquires current drilling environment data and real-time drilling data, wherein the drilling environment data comprises drilling fluid data and geological data, and the real-time drilling data comprises drilling pressure, rotating speed and slurry pump displacement.
The ratio determining unit inputs the current drilling environment data and the real-time drilling data into a drilling fluid ratio control model group to obtain an optimal drilling fluid ratio and drilling parameter combination, wherein the drilling fluid ratio control model group comprises an associated prediction model and a collaborative optimization model, the associated prediction model is obtained by deep learning of a neural network through a plurality of first samples, each first sample comprises a drilling fluid ratio identification, drilling fluid data and geological data, the collaborative optimization model is obtained by deep learning of the neural network through a plurality of second samples, and each second sample comprises an optimal drilling fluid ratio identification and drilling parameter combination and a combination of the drilling fluid ratio and any corresponding drilling parameter.
The ratio dynamic adjustment unit is used for dynamically adjusting the drilling fluid ratio according to the optimal drilling fluid ratio and drilling parameter combination output by the drilling fluid ratio control model group, and comprises the following steps:
Confirming whether the received drilling fluid proportion is complete and accurate or not, and meeting the requirement of the current drilling operation;
In response, calculating the amount of various materials required by the drilling fluid according to the drilling fluid proportion and the current mud volume;
And (3) obtaining a performance test result of the drilling fluid, and reversely adjusting the proportion of the drilling fluid according to the performance test result until the performance test meets the requirements.
The model reverse optimization unit, after carrying out dynamic adjustment to the drilling fluid proportion, reversely optimizes the drilling fluid proportion control model group according to the actual implementation result, and comprises:
Monitoring and judging whether the performance of the drilling fluid or the underground key parameter is abnormal in real time, wherein the performance of the drilling fluid or the underground key parameter is data for using the drilling fluid after dynamic adjustment on a drilling site;
and if so, adjusting parameters of each model in the drilling fluid proportion control model group, and carrying out deep learning on the drilling fluid proportion control model group again.
Embodiment 6. The embodiment of the invention discloses a storage medium, wherein a computer program which can be read by a computer is stored on the storage medium, and the computer program is set to execute a well wall stability control method for dynamically adjusting the proportion of drilling fluid when running.
The storage medium may include, but is not limited to, a usb disk, a read-only memory, a removable hard disk, a magnetic disk, or an optical disk, etc., which may store a computer program.
Embodiment 7 of the invention discloses an electronic device, which comprises a processor and a memory, wherein a computer program is stored in the memory, and the computer program is loaded and executed by the processor to realize a well wall stability control method for dynamically adjusting the proportion of drilling fluid.
The processor may be a Central Processing Unit (CPU), a general purpose processor, a digital signal processor DSP, ASIC, FPGA, or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. Combinations of computing functions may also be implemented, for example, as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, or the like. The memory may include, but is not limited to, a U disk, a read only memory, a removable hard disk, a magnetic or optical disk, and the like, various media in which computer programs may be stored.
It will be apparent to those skilled in the art that embodiments of the present invention may provide a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The scheme in the embodiment of the invention can be realized by adopting various computer languages, such as object-oriented programming language Java, an transliteration script language JavaScript and the like.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is merely specific embodiments of the present invention with better adaptability and implementation effect, but the protection scope of the present invention is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present invention, and therefore, the equivalent changes according to the claims of the present invention still fall within the scope of the present invention.
Claims (8)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411525891.2A CN119047343B (en) | 2024-10-30 | 2024-10-30 | Wellbore stability control method, device, equipment and storage medium for dynamically adjusting drilling fluid ratio |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411525891.2A CN119047343B (en) | 2024-10-30 | 2024-10-30 | Wellbore stability control method, device, equipment and storage medium for dynamically adjusting drilling fluid ratio |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119047343A CN119047343A (en) | 2024-11-29 |
| CN119047343B true CN119047343B (en) | 2025-02-07 |
Family
ID=93579836
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411525891.2A Active CN119047343B (en) | 2024-10-30 | 2024-10-30 | Wellbore stability control method, device, equipment and storage medium for dynamically adjusting drilling fluid ratio |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119047343B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115438823A (en) * | 2021-06-02 | 2022-12-06 | 中国石油化工股份有限公司 | Borehole wall instability mechanism analysis and prediction method and system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108414405B (en) * | 2017-02-09 | 2020-08-21 | 中国石油化工股份有限公司 | Method for evaluating action rule of surfactant in drilling fluid in shale microcracks |
| CN112143469B (en) * | 2020-10-10 | 2022-04-08 | 西南石油大学 | Drilling fluid for improving stratum pressure bearing capacity and preparation method and application thereof |
| CN117910330A (en) * | 2022-10-08 | 2024-04-19 | 中国石油天然气集团有限公司 | Petroleum drilling progress prediction model building method, progress prediction method and device |
-
2024
- 2024-10-30 CN CN202411525891.2A patent/CN119047343B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115438823A (en) * | 2021-06-02 | 2022-12-06 | 中国石油化工股份有限公司 | Borehole wall instability mechanism analysis and prediction method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119047343A (en) | 2024-11-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110795878B (en) | Tunnel water inflow prediction method | |
| KR102170765B1 (en) | Method for creating a shale gas production forecasting model using deep learning | |
| Majidi et al. | Fingerprint of mud losses into natural or induced fractures | |
| Hu et al. | Comprehensive investigation of leakage problems for concrete gravity dams with penetrating cracks based on detection and monitoring data: a case study | |
| Li et al. | A data-driven field-scale approach to estimate the permeability of fractured rocks | |
| Zhang et al. | Estimation of fracture stiffness, in situ stresses, and elastic parameters of naturally fractured geothermal reservoirs | |
| Abdulmalek et al. | New approach to predict fracture pressure using functional networks | |
| Gravdal et al. | Wired drill pipe telemetry enables real-time evaluation of kick during managed pressure drilling | |
| CN102606136B (en) | Logging-while-drilling value response law simulated experimental device | |
| Ataei et al. | Rate transient analysis RTA and its application for well connectivity analysis: an integrated production driven reservoir characterization and a case study | |
| Unneland et al. | Permanent gauge pressure and rate measurements for reservoir description and well monitoring: field cases | |
| CN119047343B (en) | Wellbore stability control method, device, equipment and storage medium for dynamically adjusting drilling fluid ratio | |
| Zakeri et al. | Validation and extension of soil response framework for fatigue analysis of offshore wells and piles | |
| Stranne et al. | Conductive heat flow and nonlinear geothermal gradients in marine sediments—observations from Ocean Drilling Program boreholes | |
| Carlsen et al. | Simultaneous continuous monitoring of the drilling-fluid friction factor and density | |
| Pozdniakov et al. | Use of groundwater level fluctuations near an operating water supply well to estimate aquifer transmissivity | |
| Zhang et al. | An ANN-based soft-sensor to estimate the sand content of drilling fluid | |
| CN111706323A (en) | A Fine Interpretation Evaluation Method for Flooded Layers Based on Integrated GWO-LSSVM Algorithm | |
| Ng et al. | Development of groundwater level fluctuation response system subjected to rainfall for slope stability forecasting | |
| Chen et al. | GINI coefficient: An effective way to evaluate inflow profile equilibrium of horizontal wells in Shengli Oil Field | |
| Kovacevic et al. | The use of neural networks to develop CPT correlations for soils in northern Croatia | |
| Hadibeik et al. | Petrophysical properties of unconventional low-mobility reservoirs (shale gas and heavy oil) by using newly developed adaptive testing approach | |
| CN115929285A (en) | A Method of Geothermal Gradient Prediction Based on Lagrangian Support Vector Machine Algorithm | |
| Pan et al. | Pressure Transient and Production Data Analysis of Horizontal Well in Unconsolidated Formation in Frade, Brazil | |
| Langaas et al. | Tidal pressure response and surveillance of water encroachment |
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 |