High-pressure low-permeability overflow risk early warning method, device and equipment and storage medium

Abstract

The embodiment of the invention relates to the technical field of oil and gas exploration and development, and provides a high-pressure low-permeability overflow risk early warning method and device, equipment and a storage medium. Inputting the real-time drilling data of the target well into a pre-trained overflow risk prediction model to obtain a first overflow risk prediction result of the target well, the first overflow risk prediction result comprising an overflow risk prediction type; if the overflow risk prediction type is a high-pressure low-permeability overflow risk, inputting the real-time drilling data into a pre-constructed high-pressure low-permeability gas logging mechanism model to obtain a second overflow risk prediction result, the high-pressure low-permeability gas logging mechanism model comprising a plurality of high-pressure low-permeability overflow early warning monitoring conditions; and performing high-pressure low-permeability overflow risk early warning on the target well according to the second overflow risk prediction result. According to the embodiment of the invention, the risk of high-pressure low-permeability overflow can be early warned in time.

Description

TECHNICAL FIELD

[0001] Embodiments of the present specification relate to the technical field of oil and gas exploration and development, and particularly to a high-pressure and low-permeability overflow risk early warning method, device, equipment and storage medium. BACKGROUND

[0002] During drilling, when the drilling fluid column pressure in the wellbore cannot offset the formation pore pressure, the formation fluid will invade the wellbore, causing the drilling fluid to automatically flow out of the wellhead, forming overflow. At this time, the formation fluid mixes with the drilling fluid, and the drilling fluid return increases significantly, and the drilling fluid tank liquid level rises. If it is not discovered and controlled in time, it is easy to cause blowout and even blowout out of control, causing immeasurable consequences to people's lives and property safety. Therefore, early prevention and discovery of overflow is the key to successful and effective control of blowout.

[0003] With the deepening of oil and gas exploration and development, the exploitation of oil and gas resources has shifted to low-permeability, unconventional, high-water-cut, abnormally high pressure and deep layers, and more and more overflow risk well gas logging data show high pressure and low permeability characteristics. Specifically, the fluid pressure in the real drilled formation pore has an equivalent density greater than or close to the sum of the designed mud density and the safety additional coefficient, but the formation permeability is low, the formation fluid invades the wellbore slowly but lasts for a long time, and the full-hydrocarbon and chromatographic component curves show that the base value of the long well section remains high without falling or the falling amplitude is small, showing a clear "tail" phenomenon. When drilling such formations, the existing technology only uses conventional single threshold warning methods such as drilling fluid tank liquid level height or outlet flow rate change for warning, or relies solely on manual monitoring. However, the above methods are too dependent on expert experience and can only warn and handle when the drilling fluid flow rate increases significantly, resulting in delayed warning and alarm, losing the significance of early warning and delaying the best opportunity for overflow disposal. Therefore, there is an urgent need for a high-pressure and low-permeability overflow risk early warning method to discover high-pressure and low-permeability overflow hazards in drilling in advance, thereby actively reducing risks early. SUMMARY

[0004] In view of the above problems of the prior art, the purpose of the embodiments of the present specification is to provide a high-pressure and low-permeability overflow risk early warning method, device, equipment and storage medium to solve the problem of not timely early warning of high-pressure and low-permeability overflow risk in the prior art.

[0005] To solve the above technical problems, the specific technical solutions of the embodiments of the present specification are as follows:

[0006] On the one hand, the embodiments of the present specification provide a high-pressure and low-permeability overflow risk early warning method, which comprises:

[0007] obtaining real-time drilling data of a target well;

[0008] inputting real-time drilling data of the target well into a pre-trained overflow risk prediction model to obtain a first overflow risk prediction result of the target well, the first overflow risk prediction result comprising an overflow risk prediction type;

[0009] if the overflow risk prediction type is a high-pressure low-permeability overflow risk, inputting the real-time drilling data into a pre-constructed high-pressure low-permeability gas logging mechanism model to obtain a second overflow risk prediction result, wherein the high-pressure low-permeability gas logging mechanism model comprises a plurality of high-pressure low-permeability overflow early warning monitoring conditions;

[0010] performing high-pressure low-permeability overflow risk early warning on the target well according to the second overflow risk prediction result.

[0011] Further, the overflow risk prediction model comprises an overflow feature extraction sub-model and an overflow risk prediction sub-model.

[0012] The inputting of the real-time drilling data of the target well into the pre-trained overflow risk prediction model to obtain the first overflow risk prediction result of the target well comprises:

[0013] inputting the real-time drilling data of the target well into the overflow feature extraction sub-model to obtain overflow feature parameters of the target well;

[0014] inputting the overflow feature parameters into the overflow risk prediction sub-model to obtain the first overflow risk prediction result of the target well.

[0015] Further, the inputting of the real-time drilling data into the pre-constructed high-pressure low-permeability gas logging mechanism model to obtain the second overflow risk prediction result comprises:

[0016] determining whether a difference between a well depth of the target well and a drill bit position is less than a preset threshold value;

[0017] if the difference between the well depth of the target well and the drill bit position is less than the preset threshold value, determining whether the target well is in a drilling fluid circulation state according to the real-time drilling data;

[0018] if the target well is in the drilling fluid circulation state, monitoring a gas logging peak value of the target well in a preset time interval and determining whether the gas logging peak value is greater than an average gas logging abnormal peak value of drilled wells in a same block;

[0019] if the gas logging peak value is greater than the average gas logging abnormal peak value of the drilled wells in the same block, monitoring a gas logging low value of the target well in the preset time interval and determining whether a gas logging peak-to-low ratio of the target well is greater than an average gas logging peak-to-low ratio of the drilled wells in the same block according to the gas logging low value and the gas logging peak value;

[0020] If yes, a second overflow risk prediction result of the target well is output as existing high-pressure low-permeability overflow risk.

[0021] Further, the inputting the real-time drilling data into the pre-constructed high-pressure low-permeability gas logging mechanism model further includes:

[0022] acquiring a gas logging peak value occurrence moment of the target well;

[0023] calculating a gas logging peak value duration of the target well according to a current moment;

[0024] determining a high-pressure low-permeability overflow risk grade of the target well according to the gas logging peak value duration.

[0025] Further, the high-pressure low-permeability overflow risk early warning of the target well according to the second overflow risk prediction result includes:

[0026] if the second overflow risk prediction result is the existing high-pressure low-permeability overflow risk, generating early warning information according to the real-time drilling data of the target well;

[0027] sending the early warning information to a target terminal and storing the early warning information to an overflow case database.

[0028] Further, after acquiring the real-time drilling data of the target well, the method further includes:

[0029] deleting irrelevant data and repeated data in the real-time drilling data to obtain first processing data;

[0030] performing smoothing filtering processing on the first processing data to obtain second processing data;

[0031] detecting whether the second processing data exists abnormal data, if yes, deleting the abnormal data and filling the deleted data by using a filling algorithm to obtain third processing data;

[0032] performing normalization processing on the third processing data to obtain preprocessed real-time drilling data.

[0033] On the other hand, an embodiment of the present specification provides a high-pressure low-permeability overflow risk early warning device, the device includes:

[0034] an acquisition module, configured to acquire real-time drilling data of a target well;

[0035] a first prediction module, configured to input the real-time drilling data of the target well into a pre-trained overflow risk prediction model to obtain a first overflow risk prediction result of the target well, the first overflow risk prediction result including an overflow risk prediction type;

[0036] a second prediction module, configured to input the real-time drilling data into a pre-constructed high-pressure and low-permeability gas well test mechanism model if the overflow risk prediction type is high-pressure and low-permeability overflow risk, to obtain a second overflow risk prediction result, wherein the high-pressure and low-permeability gas well test mechanism model comprises a plurality of high-pressure and low-permeability overflow early warning monitoring conditions;

[0037] a warning module, configured to perform high-pressure and low-permeability overflow risk early warning on the target well according to the second overflow risk prediction result.

[0038] In another aspect, the embodiments of the present specification also provide a computer device, comprising a memory, a processor, and a computer program stored in the memory, when the computer program is executed by the processor, instructions of any one of the above-mentioned methods are executed.

[0039] In another aspect, the embodiments of the present specification also provide a computer readable storage medium, having a computer program stored thereon, when the computer program is executed by a processor of a computer device, instructions of any one of the above-mentioned methods are executed.

[0040] In another aspect, the embodiments of the present specification also provide a computer program product, when the computer program product is executed by a processor of a computer device, instructions of any one of the above-mentioned methods are executed.

[0041] By adopting the above technical solutions, the high-pressure and low-permeability overflow risk early warning method provided by the embodiments of the present specification inputs the real-time drilling data of a target well into an overflow risk prediction model to obtain a first overflow risk prediction result, when the overflow risk prediction type in the first overflow risk prediction result is high-pressure and low-permeability overflow risk, the real-time drilling data is further input into a high-pressure and low-permeability gas well test mechanism model comprising a plurality of high-pressure and low-permeability overflow early warning monitoring conditions to obtain a second overflow risk prediction result, and finally, high-pressure and low-permeability overflow risk early warning is performed on the target well according to the second overflow risk prediction result. In this way, the real-time drilling data is input into the pre-trained overflow risk prediction model to quickly obtain the first overflow risk prediction result, when the prediction result is high-pressure and low-permeability overflow risk, the high-pressure and low-permeability gas well test mechanism model is immediately started for further prediction, which can timely issue an early warning before high-pressure and low-permeability overflow risk occurs, thereby improving the safety and reliability of drilling operations.

[0042] The above description is only a summary of some technical solutions of the embodiments of the present specification. In order to more clearly understand the technical means of some embodiments of the present specification, the embodiments can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the embodiments of the present specification more obvious and easy to understand, the following preferred embodiments are specifically described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present specification or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present specification, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0044] Figure 1 A schematic diagram of steps of a high-pressure low-permeability overflow risk early warning method in some embodiments of the present specification is shown.

[0045] Figure 2 A schematic diagram of a pre-processing flow of real-time drilling data in some embodiments of the present specification is shown.

[0046] Figure 3 A schematic diagram of an overflow risk prediction model structure in some embodiments of the present specification is shown.

[0047] Figure 4 A curve graph of training set accuracy, test set accuracy and loss value change of an overflow risk prediction model in each training cycle in some embodiments of the present specification is shown.

[0048] Figure 5 A schematic diagram of a flow of obtaining a second overflow risk prediction result in some embodiments of the present specification is shown.

[0049] Figure 6 A schematic diagram of a flow of determining a high-pressure low-permeability overflow risk level of the target well in some embodiments of the present specification is shown.

[0050] Figure 7 A schematic diagram of a structure of a high-pressure low-permeability overflow risk early warning device in some embodiments of the present specification is shown.

[0051] Figure 8 A schematic diagram of a structure of a computer device in the present specification is shown.

[0052] Explanation of drawing symbols:

[0053] 701, an acquisition module;

[0054] 702, a first prediction module;

[0055] 703, a second prediction module;

[0056] 704, an early warning module;

[0057] 802, a computer device;

[0058] 804, a processor;

[0059] 806, a memory;

[0060] 808, drive mechanism;

[0061] 810, input / output module;

[0062] 812, input device;

[0063] 814, output device;

[0064] 816, presentation device;

[0065] 818, graphical user interface;

[0066] 820, network interface;

[0067] 822, communication link;

[0068] 824, communication bus. DETAILED DESCRIPTION

[0069] The technical solutions in the embodiments of the present specification will be described clearly and completely below in combination with the drawings in the embodiments of the present specification. Obviously, the described embodiments are only part of the embodiments of the present specification, rather than all the embodiments. Based on the embodiments in the present specification, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present specification.

[0070] It should be noted that the terms "first", "second", and the like in the present specification and claims and the above-described drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or a chronological sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present specification described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, device, product, or apparatus that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products, or apparatuses.

[0071] To solve the above problems, the embodiments of the present specification provide a high-pressure low-permeability overflow risk early warning method, Figure 1is a schematic diagram of the steps of a high-pressure low-permeability overflow risk early warning method provided by the embodiments of the present specification. The present specification provides the method operation steps as described in the embodiments or flowcharts, but more or fewer operation steps can be included based on conventional or non-inventive labor. The order of steps listed in the embodiments is only one of the many step execution orders, and does not represent the only execution order. In actual system or device product execution, the method order shown in the embodiments or the drawings can be executed in sequence or in parallel. Specifically as shown in Figure 1 The method can include:

[0072] S101: Obtain real-time drilling data of a target well.

[0073] In the present embodiment, the target well refers to any designated well in a certain target oilfield block. By directly connecting the sensors or data acquisition systems at the drilling site, the key parameters during drilling are obtained in real time, ensuring the timeliness and accuracy of the data. The real-time drilling data includes drilling time, well depth, pump stroke speed, late well depth, bit position, hook height, hook load, total hydrocarbon value, methane value, and rotary table speed.

[0074] S102: Input the real-time drilling data of the target well into a pre-trained overflow risk prediction model to obtain a first overflow risk prediction result of the target well, the first overflow risk prediction result including an overflow risk prediction type.

[0075] In the present embodiment, the overflow risk prediction model is a neural network model trained based on a large amount of drilled well data in the oilfield block, which can identify the overflow risk prediction type corresponding to the drilling data based on the input real-time drilling data, including high-pressure low-permeability overflow risk, other cause overflow risk, and no overflow risk.

[0076] S103: If the overflow risk prediction type is high-pressure low-permeability overflow risk, input the real-time drilling data into a pre-constructed high-pressure low-permeability gas logging mechanism model to obtain a second overflow risk prediction result, wherein the high-pressure low-permeability gas logging mechanism model includes a plurality of high-pressure low-permeability overflow early warning monitoring conditions.

[0077] In the drilling process, more and more overflow risk well logging data shows the characteristics of high pressure and low permeability, which is specifically manifested as follows: the equivalent density corresponding to the fluid pressure in the actual drilled formation pore is greater than or close to the sum of the designed mud density and the safety additional coefficient, but the formation permeability is relatively low, the formation fluid invades the wellbore slowly but lasts for a long time, and the full hydrocarbon and chromatographic component curves show that the base value of a long well section remains high without falling or with a small falling range, and a significant "tail" phenomenon is presented. The occurrence of this phenomenon prompts the operating personnel to need to monitor the fluid dynamics in the wellbore in real time, and once an abnormality is found, the corresponding warning mechanism is started and the corresponding response measures are taken. In the embodiment, the high pressure and low permeability gas logging mechanism model is a high pressure and low permeability overflow judgment model constructed according to the "high value tailing" characteristics of high pressure and low permeability gas logging, which contains a plurality of high pressure and low permeability overflow warning monitoring conditions, and when the real-time drilling data meets the warning conditions, the model will trigger the corresponding warning mechanism.

[0078] S104: high pressure and low permeability overflow risk warning is performed on the target well according to the second overflow risk prediction result.

[0079] With the technical scheme, the high pressure and low permeability overflow risk warning method provided by the embodiment of the present application inputs the real-time drilling data into the overflow risk prediction model based on the real-time drilling data of the target well, obtains the first overflow risk prediction result, when the overflow risk prediction type in the first overflow risk prediction result is high pressure and low permeability overflow risk, inputs the real-time drilling data into the high pressure and low permeability gas logging mechanism model containing a plurality of high pressure and low permeability overflow warning monitoring conditions, obtains the second overflow risk prediction result, and finally performs high pressure and low permeability overflow risk warning on the target well according to the second overflow risk prediction result. In this way, the real-time drilling data is input into the pre-trained overflow risk prediction model, the first overflow risk prediction result can be quickly obtained, when the prediction result is high pressure and low permeability overflow risk, the high pressure and low permeability gas logging mechanism model is immediately started for further prediction, the warning can be timely given before the high pressure and low permeability overflow risk occurs, and therefore the safety and reliability of the drilling operation are improved, the probability of accidents is reduced, unnecessary cost loss is reduced, and the safety and controllability of the overflow risk in the drilling process are ensured.

[0080] In the embodiment, due to the fact that data defects, abnormalities, repetitions and other problems caused by equipment failure, human error and the like are inevitable in the process of field data collection and transmission, the collected real-time drilling data needs to be preprocessed accordingly to ensure data quality, thereby providing a high-quality data basis for subsequent model prediction. Referring to Figure 2 The preprocessing of the real-time drilling data includes:

[0081] S201: irrelevant data and repeated data in the real-time drilling data are deleted to obtain first processing data;

[0082] S202: performing smoothing filtering processing on the first processing data to obtain second processing data;

[0083] S203: detecting whether the second processing data has abnormal data, if the abnormal data exists, deleting the abnormal data and filling the deleted data by using a filling algorithm to obtain third processing data;

[0084] S204: performing normalization processing on the third processing data to obtain preprocessed real-time drilling data.

[0085] It can be understood that the data repeated values and the abnormal values with small data quantity and without affecting the prediction results can be directly eliminated, and the abnormal values affecting the prediction results can be regarded as missing values and filled by using different filling methods to maintain data continuity and ensure data quality, such as weighted method, mean interpolation method, linear interpolation method, nearest neighbor interpolation method and the like. Moreover, the standardization and unification processing are performed for the phenomenon that the logging instrument types are various and the data units are not unified.

[0086] In the embodiment, the overflow risk prediction model includes an overflow feature extraction sub-model and an overflow risk prediction sub-model; the real-time drilling data of the target well is input into the pre-trained overflow risk prediction model to obtain a first overflow risk prediction result of the target well, which includes:

[0087] The real-time drilling data of the target well is input into the overflow feature extraction sub-model to obtain overflow feature parameters of the target well;

[0088] The overflow feature parameters are input into the overflow risk prediction sub-model to obtain the first overflow risk prediction result of the target well.

[0089] In the embodiment, first, the drilled well data in the oilfield block in recent years is obtained according to the drilled well log, well history and comprehensive logging and completion report, and the obtained drilled well data is marked with an overflow risk type, that is, an overflow risk type label is added to each data, the overflow risk type label includes high-pressure low-permeability overflow risk, other cause overflow risk and no overflow risk. The marked drilled well data is shuffled, and the marked drilled well data is divided into a training set and a training set according to a 7:3 ratio, which is used to train the overflow risk prediction model based on the full connection neural network, wherein the overflow risk prediction model based on the full connection neural network is as follows Figure 3As shown, assuming that the length of a single or column is usually not more than 30 meters, and there are 10 feature data for every 0.1 meter, therefore, preferably, every 25 m is taken as a deep well section, the number of input layer neurons is 2500 (25*0.1*10=2500), the number of hidden layers is 2 after parameter optimization by optuna, the number of neurons is 512, 108, the learning rate is 0.001, and the optimization function is SGD. Using the above model parameters and structure, the training is iterated 250 times, and the accuracy rate of the training set, the accuracy rate of the test set and the loss value change curve diagram in each training period are as follows Figure 4 As shown, from Figure 4 It can be seen from the above that, in this training process, the accuracy rates of the training set and the test set increase rapidly at first, then gradually stabilize, and finally are 78.97% and 78.93% respectively. The loss value of the training set is opposite to the trend of the accuracy rate, and finally is 0.0000104. Since the accuracy rates of the training set and the test set have the same trend and the values are not much different, and the accuracy rate of the test set is always increasing and finally stabilizes at about 78% with small fluctuations, it is considered that the model training does not have overfitting, has good generalization ability, and can be used to predict overflow risk according to drilling data.

[0090] In this embodiment, the overflow feature extraction sub-model extracts the feature parameters related to overflow by processing and analyzing the input real-time drilling data. The overflow risk prediction sub-model receives the feature parameters extracted from the overflow feature extraction sub-model as input, learns the relationship between the overflow events and the feature parameters in the historical data, and the model can evaluate the risk of new drilling data and output the first overflow risk prediction result.

[0091] In this embodiment, high-pressure low-permeability overflow risk sample data is selected from the drilled well data of the target oilfield block, the gas logging data in the high-pressure low-permeability overflow risk sample data is counted, the average gas logging data in the oilfield block is obtained, including full hydrocarbon average abnormal high value, methane average abnormal high value, full hydrocarbon peak low ratio, methane peak low ratio data, etc., and is recorded as TGavgmax, C1avgmax, TGratio and C1ratio respectively, wherein the gas logging peak low ratio refers to the ratio of the gas logging peak value to the gas logging minimum value. According to the above data, a "regional gas logging peak value database" and a "regional gas logging peak low ratio database" are established, which are used for subsequent overflow analogy monitoring of real-time drilling.

[0092] As described above, for the high-pressure and low-permeability overflow, the gas logging data usually contains the feature of "high value tailing", when the overflow risk prediction model is used to predict that the target well may have the risk of high-pressure and low-permeability overflow, in order to further confirm and discover the overflow risk in time, the real-time drilling data of the target well needs to be monitored. In the embodiment, the real-time drilling data of the target well is input into the high-pressure and low-permeability gas logging mechanism model, and the real-time drilling data is compared with the monitoring and early warning conditions preset in the high-pressure and low-permeability gas logging mechanism model, when the real-time monitoring drilling data meets the early warning conditions, the model will trigger the corresponding early warning mechanism.

[0093] In the embodiment, the real-time drilling data is input into the high-pressure and low-permeability gas logging mechanism model, and the second overflow risk prediction result is obtained, including: Figure 5

[0094] S501: determining whether the difference between the well depth and the drill bit position of the target well is less than a preset threshold.

[0095] It can be understood that only when the difference between the well depth and the drill bit position is less than the preset threshold, the subsequent monitoring and analysis is performed, at this time, the drill bit is close to the well bottom, it is considered that the current is in the large drilling condition, the drill bit directly contacts the well bottom formation, which will damage the original structure of the formation, and the fluid (such as water, oil and natural gas) pressure, flow state and distribution in the formation will directly affect the drilling efficiency and safety, therefore, the real-time analysis of the formation pressure, permeability and other characteristics is needed to ensure that the drilling operation is within the controllable range. Preferably, in the embodiment, the preset threshold is 30 m.

[0096] S502: if the difference between the well depth and the drill bit position of the target well is less than the preset threshold, determining whether the target well is in the drilling fluid circulation state according to the real-time drilling data.

[0097] ​It can be understood that the drilling fluid circulation refers to a continuous flow process in which the drilling fluid is pumped from the ground to the bottom of the well through certain equipment and pipelines during drilling, and then returned to the ground from the bottom of the well, for pumping the drilling fluid (mud) from the ground to the inside of the drill string, and then sprayed through the drill bit nozzle to cool the drill bit, carry the drill cuttings back to the ground, and maintain the stability of the wellbore. If the drilling fluid circulation is interrupted, problems such as imbalance of well pressure and accumulation of rock cuttings may occur, thereby increasing the risk of well accidents. Therefore, it is required that in the interval [t-45, t], the working condition is always in the drilling fluid circulation state (i.e., pump impact velocity 1 or pump impact velocity 2 or pump impact velocity 3 is always in a state of >1), and the earliest data point (t-45) is more than 10 minutes away from the start of the current circulation opening pump time. Pump impact velocity 1, pump impact velocity 2 and pump impact velocity 3 refer to the impact or speed of different mud pumps (or drilling pumps) in the drilling fluid circulation system. It is required that the working condition is always in the drilling fluid circulation state in the interval [t-45, t], which means that at least one mud pump (pump impact velocity 1, pump impact velocity 2 or pump impact velocity 3) needs to be greater than 1 in this time interval, indicating that the mud pump is in working condition. The 45-minute time unit of historical backtracking can meet the detection time length of the drilling fluid invasion fluid change rule, and can fully consider the changes of underground conditions such as formation pressure and temperature, as well as the evolution trend of response characteristics such as gas logging, drilling fluid density and viscosity.

[0098] S503: If the target well is in the drilling fluid circulation state, the gas logging peak value of the target well in the preset time interval is monitored, and it is judged whether the gas logging peak value is greater than the average gas logging abnormal peak value of the drilled wells in the same block.

[0099] It can be understood that if the drilling fluid can circulate normally, it indicates that the drilling operation is in progress, and therefore subsequent gas logging monitoring can be continued. In this embodiment, the gas logging peak value (maximum value) in the interval [t-45, t] is first monitored and recorded, the time when the gas logging peak value appears is recorded as t1, the total hydrocarbon peak value is TGmax, and the methane peak value at this time is C1max. According to time, depth, total hydrocarbon peak value and methane peak value, a gas logging peak value database of the target well is established, and when TGmax>TGavgmax or C1max>C1avgmax, the record is made.

[0100] S504: If the gas logging peak value is greater than the average gas logging abnormal peak value of the drilled wells in the same block, the gas logging low value of the target well in the preset time interval is monitored, and it is judged whether the gas logging peak low ratio of the target well is greater than the average gas logging peak low ratio of the drilled wells in the same block according to the gas logging low value and the gas logging peak value.

[0101] It can be understood that the fluid pressure in the high-pressure low-permeability formation is high, and the fluid flow is slow, which increases the risk of overflow. The gas logging peak value as a direct indicator of monitoring the release of formation fluid can reflect the activity and pressure state of the fluid in the formation. When the gas logging peak value abnormally rises or frequently occurs, it may indicate that there is high-pressure fluid in the formation and the flow is abnormal, which may increase the safety risk in the drilling process, such as blowout, lost circulation, etc. When the gas logging peak value of the target well is greater than the average gas logging abnormal peak value, it may indicate that there is abnormal gas release in the target well, which needs to be further monitored. In this embodiment, the gas logging low value of the target well in the interval [t-45, t] is monitored, and the time of the gas logging low value at this moment is recorded as t2, the total hydrocarbon minimum value is TGmin, and the methane minimum value is C1min. When TGmax / TGmin>TGratio, C1max / C1min>C1ratio, it is recorded. This is because under the background of high-pressure low-permeability formation, the gas logging data curve shows that the gas logging rises from the base value to the peak value and does not fall for a long time, or the falling amplitude is small, and the gas logging anomaly shows a obvious "tail" phenomenon, and the gas logging peak low ratio is used to ensure that the gas logging value is high. Finally, the gas logging peak low ratio database of the target well is established according to the time, well depth, total hydrocarbon minimum value, methane minimum value, total hydrocarbon peak low ratio, and methane peak low ratio, so that subsequent technical personnel can review according to the data, and provide data support for subsequent drilling optimization.

[0102] S505: If yes, output the second overflow risk prediction result of the target well as existing high-pressure low-permeability overflow risk.

[0103] It can be understood that in the high-pressure low-permeability formation, due to the low permeability of the formation, the fluid flow is slow, so when the drilling fluid circulates, the fluid in the formation may be difficult to quickly discharge, thereby increasing the risk of overflow. The gas logging peak low ratio can be used as an important indicator for evaluating this overflow risk. When the gas logging peak low ratio abnormally rises, it may indicate that there is high-pressure fluid in the formation, and corresponding measures need to be taken to reduce the risk of overflow. If the gas logging peak low ratio of the target well is greater than the average gas logging peak low ratio of the drilled wells in the same block, it indicates that there is abnormal gas release in the high-pressure low-permeability reservoir in the target well, thereby existing high-pressure overflow risk.

[0104] In this embodiment, referring to Figure 6 , the inputting the real-time drilling data into the pre-constructed high-pressure low-permeability gas logging mechanism model further includes:

[0105] S601: Obtain the time when the gas logging peak value of the target well occurs;

[0106] S602: Calculate the gas logging peak value duration of the target well according to the current time;

[0107] S603: determining the high-pressure and low-permeability overflow risk level of the target well according to the gas logging peak duration.

[0108] It can be understood that the duration of the gas logging peak is obtained by subtracting the time point at which the gas logging peak first appears from the current time, and this time length can reflect the activity and duration of the release of formation fluid, thereby indirectly indicating the risk of high-pressure and low-permeability overflow. The gas logging peak duration is compared with preset risk level thresholds. These thresholds are usually based on factors such as geological characteristics, drilling experience, safety standards, etc. The length of the gas logging peak duration is closely related to the high-pressure and low-permeability overflow risk level. The longer the gas logging peak duration, the more active the release of fluid in the formation, and the higher the risk of high-pressure and low-permeability overflow. Therefore, according to the length of the gas logging peak duration, the high-pressure and low-permeability overflow risk level of the target well can be preliminarily evaluated, thereby providing guidance for subsequent drilling operations and safety measures. Preferably, in the present embodiment, when the gas logging peak duration is greater than 30 minutes, it indicates that the risk of high-pressure and low-permeability overflow during drilling is high, and a warning information is issued.

[0109] In the present embodiment, the high-pressure and low-permeability overflow risk warning of the target well according to the second overflow risk prediction result comprises:

[0110] If the second overflow risk prediction result is that there is a high-pressure and low-permeability overflow risk, a warning information is generated according to the real-time drilling data of the target well;

[0111] The warning information is sent to a target terminal and stored in an overflow case database.

[0112] Specifically, in the present embodiment, when it is predicted by the high-pressure and low-permeability gas logging mechanism model that the target well has a high-pressure and low-permeability overflow risk, the data such as the warning time, the well depth at the warning time, and the drill bit position are provided to the front-end display, and an overflow risk warning is issued. The warning information can be described as "high-pressure and low-permeability gas logging anomaly is obvious, pay attention to prevent overflow". The warning information of this time is stored in the overflow case database, and a query interface is developed by the back-end developer, the front-end calls the interface and displays the warning information on the page, thereby facilitating the engineering and technical personnel to formulate targeted drilling disposal measures. Preferably, the warning interface example can be as shown in Table 1:

[0113] Table 1

[0114]

[0115] In the drilling process, when the gas logging peak duration exceeds the preset threshold, a warning mechanism can be triggered to remind the drilling engineer to take timely measures to deal with the possible high-pressure low-permeability overflow risk. This warning mechanism helps to discover potential safety hazards in advance, avoids accidents, and ensures the safety and smooth progress of drilling operations. In this way, through the above scheme, the present embodiment of the present specification first analyzes a large number of case wells and real-time drilling risks, and reflects the well invasion process of high-pressure low-permeability through the gas logging data characteristics. The overflow risk is easy to identify, the operability is strong, the early warning accuracy is high, and it is worth popularizing to various oil and gas fields. Secondly, the regional big data analysis and real-time drilling data are combined to realize the joint driving of mechanism and data, predict whether high-pressure low-permeability overflow characteristics will appear in the current drilling operation, realize real early warning, and realize full-process automation and digitization. At the same time, it reduces the intensity of the field staff and provides timely and effective analysis results support, assists in field decision-making, improves the efficiency of complex accident disposal, and ensures drilling safety.

[0116] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties. The acquisition, storage, use, processing, etc. of data in the technical solutions described in the embodiments of the present application comply with relevant regulations.

[0117] Based on the high-pressure low-permeability overflow risk early warning method described above, the present embodiment of the present specification also provides a high-pressure low-permeability overflow risk early warning device. The device can include a system (including a distributed system), software (application), module, component, server, client, etc. using the method described in the present embodiment, and a device combining necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided by the present embodiment is described in the following embodiments. Since the implementation scheme of the device to solve the problem is similar to the method, the implementation of the specific device of the present embodiment can be referred to the implementation of the foregoing method, and the repeated parts will not be described. The term "unit" or "module" used below can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware is also possible and is conceived.

[0118] Specifically, Figure 7 is a module structure schematic diagram of one embodiment of a high-pressure low-permeability overflow risk early warning device provided by the present embodiment, referring to Figure 7 , the high-pressure low-permeability overflow risk early warning device provided by the present embodiment comprises:

[0119] The acquisition module 701 is configured to acquire real-time drilling data of a target well.

[0120] The first prediction module 702 is configured to input the real-time drilling data of the target well into a pre-trained overflow risk prediction model to obtain a first overflow risk prediction result of the target well, the first overflow risk prediction result including an overflow risk prediction type.

[0121] The second prediction module 703 is configured to, if the overflow risk prediction type is a high-pressure low-permeability overflow risk, input the real-time drilling data into a pre-constructed high-pressure low-permeability gas logging mechanism model to obtain a second overflow risk prediction result, wherein the high-pressure low-permeability gas logging mechanism model includes a plurality of high-pressure low-permeability overflow early warning monitoring conditions.

[0122] The early warning module 704 is configured to perform high-pressure low-permeability overflow risk early warning on the target well according to the second overflow risk prediction result.

[0123] The beneficial effects achieved by the device provided by the embodiments of the present specification are consistent with the beneficial effects achieved by the above method, which will not be repeated here.

[0124] Referring to Figure 8 Based on the above-mentioned high-pressure low-permeability overflow risk early warning method, an embodiment of the present specification further provides a computer device 802, wherein the above-mentioned method runs on the computer device 802. The computer device 802 can include one or more processors 804, such as one or more central processing units (CPUs), each of which can implement one or more hardware threads. The computer device 802 can also include any memory 806 for storing any kind of information, such as code, settings, data, etc. Without limitation, for example, the memory 806 can include any one or a combination of the following: any type of RAM, any type of ROM, a flash memory device, a hard disk, an optical disk, etc. More generally, any memory can store information using any technology. Further, any memory can provide volatile or non-volatile retention of information. Further, any memory can represent a fixed or removable component of the computer device 802. In one case, the computer device 802 can perform any operation of the associated instructions when the processor 804 executes the associated instructions stored in any memory or combination of memories. The computer device 802 also includes one or more drive mechanisms 808, such as a hard disk drive mechanism, an optical disk drive mechanism, etc., for interacting with any memory.

[0125] The computer device 802 can also include input / output module(s) 810 (I / O) for receiving various inputs (via input device(s) 812) and for providing various outputs (via output device(s) 814). One particular output mechanism can include a presentation device 816 and associated graphical user interface (GUI) 818. In other embodiments, the input / output module(s) 810 (I / O), input device(s) 812, and output device(s) 814 can not be included, and the computer device 802 can merely be a computer device in a network.

[0126] The communication links 822 can be implemented in any manner, such as through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication links 822 can include any combination of hardwired links, wireless links, routers, gateway functionality, name servers, etc., governed by any protocol or combination of protocols.

[0127] Corresponding to the method as shown in Figures 1-2 , Figures 5-6 The computer program stored in the computer readable storage medium is run by the processor to execute the steps of the method.

[0128] The computer readable instructions are executed by the processor, and the program in the computer readable instructions causes the processor to execute the method as shown in Figures 1-2 , Figures 5-6 .

[0129] The computer program product includes at least one instruction or at least one program, which is loaded and executed by the processor to implement the method as shown in Figures 1-2 , Figures 5-6 .

[0130] It should be understood that the size of the sequence number of the above-mentioned processes in various embodiments of the present specification does not mean the order of execution, and the execution order of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present specification.

[0131] It should also be understood that, in the embodiments of the specification, the term "and / or" is merely an association relationship of the associated objects, which means that there can be three relationships. For example, A and / or B can represent three cases: A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in the specification generally represents an "or" relationship between the front and rear associated objects.

[0132] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the specification can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been described in the above description in general terms. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the specification.

[0133] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0134] In several embodiments provided in the specification, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed mutual objects can be indirect coupling or communication connection through some interfaces, devices or units, and can also be electrical, mechanical or other forms of connection.

[0135] The units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments of the specification.

[0136] In addition, each functional unit in each embodiment of the specification can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above integrated unit can be realized in the form of hardware or software functional unit.

[0137] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the specification or the part of the prior art that essentially contributes, or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the specification. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0138] The principles and implementation manners of the specification are described in the specific embodiments in the specification, and the above embodiment description is only used to help understand the method and its core idea of the specification; meanwhile, for those skilled in the art, according to the idea of the specification, the specific implementation manners and application ranges will have changes, and the above description should not be understood as a limitation of the specification.

Claims

1. A method for early warning of high-pressure, low-permeability overflow risks, characterized in that, The method includes: Obtain real-time drilling data for the target well; The real-time drilling data of the target well is input into a pre-trained overflow risk prediction model to obtain the first overflow risk prediction result of the target well. The first overflow risk prediction result includes the overflow risk prediction type. If the overflow risk prediction type is high pressure low permeability overflow risk, then the real-time drilling data is input into the pre-constructed high pressure low permeability gas detection mechanism model to obtain the second overflow risk prediction result, wherein the high pressure low permeability gas detection mechanism model includes several high pressure low permeability overflow early warning monitoring conditions. Based on the second overflow risk prediction results, a high-pressure, low-permeability overflow risk warning is issued for the target well.

2. The method according to claim 1, characterized in that, The overflow risk prediction model includes an overflow feature extraction sub-model and an overflow risk prediction sub-model; The step of inputting real-time drilling data of the target well into a pre-trained overflow risk prediction model to obtain the first overflow risk prediction result of the target well includes: The real-time drilling data of the target well is input into the overflow feature extraction sub-model to obtain the overflow feature parameters of the target well; The overflow characteristic parameters are input into the overflow risk prediction sub-model to obtain the first overflow risk prediction result of the target well.

3. The method according to claim 1, characterized in that, The step of inputting the real-time drilling data into a pre-constructed high-pressure, low-permeability gas detection mechanism model to obtain the second overflow risk prediction result includes: Determine whether the difference between the target well depth and the drill bit position is less than a preset threshold; If the difference between the depth of the target well and the position of the drill bit is less than a preset threshold, then it is determined whether the target well is in the drilling fluid circulation state based on the real-time drilling data. If the target well is in the drilling fluid circulation state, the gas measurement peak value of the target well within the preset time interval is monitored to determine whether the gas measurement peak value is greater than the average abnormal gas measurement peak value of the drilled wells in the same block. If the gas measurement peak value is greater than the average abnormal gas measurement peak value of drilled wells in the same block, the low gas measurement value of the target well within the preset time interval is monitored, and the gas measurement peak-to-low ratio of the target well is determined based on the low gas measurement value and the gas measurement peak value to determine whether it is greater than the average gas measurement peak-to-low ratio of drilled wells in the same block. If so, the second overflow risk prediction result of the target well is output as having a high-pressure, low-permeability overflow risk.

4. The method according to claim 3, characterized in that, The step of inputting the real-time drilling data into a pre-constructed high-pressure, low-permeability gas detection mechanism model also includes: Obtain the time when the gas logging peak value of the target well occurs; Calculate the duration of the gas measurement peak value of the target well based on the current time. The high-pressure, low-permeability overflow risk level of the target well is determined based on the duration of the gas measurement peak.

5. The method according to claim 3, characterized in that, The step of providing a high-pressure, low-permeability overflow risk warning for the target well based on the second overflow risk prediction result includes: If the second overflow risk prediction result indicates the existence of high-pressure, low-permeability overflow risk, then an early warning message is generated based on the real-time drilling data of the target well. The warning information is sent to the target terminal and stored in the overflow case database.

6. The method according to claim 1, characterized in that, After acquiring the real-time drilling data of the target well, the process further includes: Irrelevant and duplicate data are removed from the real-time drilling data to obtain the first processed data; The first processed data is subjected to a smoothing filter to obtain the second processed data; The system detects whether there is abnormal data in the second processed data. If there is abnormal data, the abnormal data is deleted and the deleted data is filled using a filling algorithm to obtain the third processed data. The third processing data is normalized to obtain preprocessed real-time drilling data.

7. A high-pressure, low-permeability overflow risk early warning device, characterized in that, The device includes: The acquisition module is used to acquire real-time drilling data of the target well; The first prediction module is used to input the real-time drilling data of the target well into a pre-trained overflow risk prediction model to obtain the first overflow risk prediction result of the target well. The first overflow risk prediction result includes the overflow risk prediction type. The second prediction module is used to input the real-time drilling data into a pre-built high-pressure low-permeability gas detection mechanism model if the overflow risk prediction type is high-pressure low-permeability overflow risk, and obtain the second overflow risk prediction result. The high-pressure low-permeability gas detection mechanism model includes several high-pressure low-permeability overflow early warning monitoring conditions. The early warning module is used to provide early warning of high-pressure, low-permeability overflow risk to the target well based on the second overflow risk prediction result.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes at least one instruction or at least one program segment, said at least one instruction or said at least one program segment being loaded and executed by a processor to implement the method as claimed in any one of claims 1 to 6.

Images