Drilling operation risk prediction method, system and equipment based on edge-cloud integration
Through the integrated drilling operation risk prediction method of edge and cloud, we can identify the on-site problems of drilling operations and determine the appropriate working mode, which realizes timely and accurate prediction of drilling operation risks, and solves the difficulty in ensuring timeliness and accuracy of risk prediction in the existing technology. The problem.
Patent Information
- Application Number
- CN202210052905.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-01-18
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2042-01-18
AI Technical Summary
The existing drilling operation risk prediction technology is difficult to ensure timeliness and accuracy, and cannot effectively respond to the risk warning needs in drilling projects.
Adopt a drilling operation risk prediction method based on edge-cloud, and determine the working mode by obtaining on-site data to identify problem types, processing urgency, processing accuracy, network quality and computing power consumption, and determine the working mode according to the edge-end independent working mode and the cloud-end independent working mode. The model and the edge-cloud collaborative working mode conduct risk prediction to achieve complementary advantages between edge-end and cloud prediction.
It improves the timeliness and accuracy of drilling operation risk prediction, and can make flexibly based on real-time conditions on site to adapt to risk prediction needs in different scenarios.
Smart Images

Figure CN114399209B_ABST
Abstract
Description
Technical Field
[0001] The present specification relates to the technical field of drilling operation risk prediction, and in particular, to a method, system and device for predicting drilling operation risks based on edge-cloud integration. Background Art
[0002] In the process of oil and gas extraction, drilling engineering is an important part of development and exploration, and compared with other projects, the risk factor of drilling engineering is very high. In the actual drilling process, if it is not handled properly, it may cause overflow, drill stuck, well collapse, well deviation, or even cause major accidents such as well leakage, blowout, and toxic and harmful gas leakage, which will pose a serious threat to the drilling process and construction personnel. Therefore, it is of great significance to warn of the risks of drilling operations.
[0003] At present, the main means of dealing with the risks of drilling operations are: analyzing safety risk factors, building a risk management evaluation index system, establishing a risk evaluation model, and finally building a safety risk prediction system for drilling engineering projects; and using the ability of artificial neural networks to process nonlinear information on a large scale to conduct complex process risk analysis and achieve risk prediction. However, these means of dealing with drilling operation risks are difficult to ensure the timeliness and accuracy of drilling operation risk prediction. Summary of the invention
[0004] The purpose of the embodiments of this specification is to provide a method, system and equipment for predicting drilling operation risks based on edge-cloud integration to improve the timeliness and accuracy of drilling operation risk prediction.
[0005] To achieve the above objectives, on the one hand, the embodiments of this specification provide a method for predicting drilling operation risks based on edge-cloud integration, including:
[0006] Obtain field return data from drilling operations;
[0007] Identify the type of drilling operation problem, processing urgency, processing accuracy, network quality, and computing power consumption according to the field return data;
[0008] Determine the working mode according to the problem type, the processing urgency, the processing accuracy, the network quality and the computing power consumption; the working mode includes an edge-end independent working mode, a cloud-end independent working mode and an edge-cloud collaborative working mode;
[0009] The operational risk of the drilling operation is predicted according to the determined working mode.
[0010] The edge-cloud integrated drilling operation risk prediction method of the embodiment of this specification, which identifies the problem type, processing urgency, processing accuracy, network quality and computing power consumption of the drilling operation problem according to the field return data, includes:
[0011] Comparing the value of the field returned data with the corresponding preset range, and determining whether there is a drilling operation problem based on the comparison result;
[0012] When there is a drilling operation problem, determine the problem type of the drilling operation problem;
[0013] By querying the corresponding relationship table between the problem type and the processing urgency, the processing urgency of the problem type is determined;
[0014] Determine the processing accuracy of the problem type by querying the corresponding relationship table between the problem type and the processing accuracy;
[0015] By querying the corresponding relationship table between the problem type and the computing power consumption, the computing power consumption of the problem type is determined;
[0016] The network quality between the edge terminal and the cloud is determined by the data volume, sending time and receiving time of the on-site return data.
[0017] The edge-cloud integrated drilling operation risk prediction method of the embodiment of this specification, wherein the working mode is determined according to the problem type, the processing urgency, the processing accuracy, the network quality and the computing power consumption, includes:
[0018] The weighted sum of the problem type, the processing urgency, the processing accuracy, the network quality and the computing power consumption is used as the processing level;
[0019] When the processing level reaches the processing level threshold, performing identification processing of the collaborative working mode;
[0020] When the processing level does not reach the processing level threshold, the recognition process of the independent working mode is performed.
[0021] The edge-cloud integrated drilling operation risk prediction method of the embodiment of this specification, the identification processing of executing the independent working mode includes:
[0022] Determine whether there is an idle edge end that meets the processing urgency and processing accuracy requirements of the problem type;
[0023] If there is an idle edge end that meets the processing urgency and processing accuracy requirements of the problem type, the independent working mode is selected as the edge end independent working mode;
[0024] If there is no idle edge terminal that meets the processing urgency and processing accuracy requirements of the problem type, the independent working mode is selected as the cloud independent working mode.
[0025] The edge-cloud integrated drilling operation risk prediction method of the embodiment of this specification, the identification and processing of executing the collaborative working mode, includes:
[0026] Determine the influence weights of the processing accuracy and the computing power consumption in the problem type respectively;
[0027] When the influence weight of the processing accuracy in the problem type is greater than the influence weight of the computing power consumption in the problem type, the edge-cloud collaborative working mode with accuracy priority is selected as the collaborative working mode;
[0028] When the influence weight of the processing accuracy in the problem type is not greater than the influence weight of the computing power consumption in the problem type, the collaborative working mode is selected as the edge-cloud collaborative working mode that prioritizes efficiency.
[0029] The edge-cloud integrated drilling operation risk prediction method of the embodiment of this specification, the processing logic of the edge-cloud collaborative working mode with precision priority includes:
[0030] Predicting the operational risk of the drilling operation based on the edge to obtain a first prediction result, and predicting the operational risk of the drilling operation based on the cloud to obtain a second prediction result;
[0031] Calculating prediction evaluation index values of the first prediction result and the second prediction result respectively;
[0032] Determine whether the prediction evaluation index values of the first prediction result and the second prediction result have reached the index threshold;
[0033] When there is one that reaches the index threshold, the prediction result corresponding to the one with the larger prediction evaluation index value is taken as the final prediction result;
[0034] When no indicator threshold is reached, the drilling operation risk prediction algorithm on the edge and cloud is replaced and re-predicted.
[0035] The edge-cloud integrated drilling operation risk prediction method of the embodiment of this specification, the processing logic of the efficiency-first edge-cloud collaborative working mode includes:
[0036] Split the drilling operation problem into multiple prediction subtasks;
[0037] Distributing the multiple prediction subtasks to multiple edge terminals for parallel processing to obtain multiple prediction subresults;
[0038] Combine the multiple prediction sub-results into a complete prediction result
[0039] On the other hand, the embodiment of this specification also provides a drilling operation risk prediction system based on edge-cloud integration, including:
[0040] An acquisition module, used to acquire on-site return data of drilling operations;
[0041] An identification module, used to identify the problem type, processing urgency, processing accuracy, network quality and computing power consumption of the drilling operation problem according to the field return data;
[0042] A determination module, used to determine a working mode according to the problem type, the processing urgency, the processing accuracy, the network quality and the computing power consumption; the working mode includes an edge-end independent working mode, a cloud-end independent working mode and an edge-cloud collaborative working mode;
[0043] The prediction module is used to predict the operation risk of the drilling operation according to the determined working mode.
[0044] On the other hand, an embodiment of the present specification further provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein when the computer program is executed by the processor, the instructions of the above method are executed.
[0045] On the other hand, an embodiment of the present specification further provides a computer storage medium on which a computer program is stored. When the computer program is executed by a processor of a computer device, the instructions of the above method are executed.
[0046] It can be seen from the technical solutions provided in the above embodiments of this specification that the embodiments of this specification can identify the problem type, processing urgency, processing accuracy, network quality and computing power consumption of drilling operation problems based on the on-site return data of the drilling operation, and based on these parameters, decide on the appropriate working mode from the edge independent working mode, the cloud independent working mode and the edge-cloud collaborative working mode, and predict the operational risks of the drilling operation according to the determined working mode; the complementary advantages of edge prediction and cloud prediction are achieved, thereby improving the timeliness and accuracy of drilling operation risk prediction. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art description. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. In the drawings:
[0048] Figure 1 A structural block diagram of a drilling operation risk prediction system based on edge-cloud integration in some embodiments of this specification is shown;
[0049] Figure 2A flowchart of a drilling operation risk prediction method based on edge-cloud integration in some embodiments of this specification is shown;
[0050] Figure 3 Shows Figure 2 A flowchart showing the problem type, processing urgency, processing accuracy, network quality and computing power consumption of a drilling operation problem in the drilling operation risk prediction method shown;
[0051] Figure 4 Shows Figure 2 A flowchart of identifying working modes in the method for predicting drilling operation risks is shown;
[0052] Figure 5 Shows Figure 2 A flowchart showing identification of independent working modes in the method for predicting drilling operation risks;
[0053] Figure 6 Shows Figure 2 The flowchart of identifying edge-cloud collaborative working mode in the drilling operation risk prediction method shown;
[0054] Figure 7 Shows Figure 2 The processing logic flow chart of the edge-cloud collaborative working mode with accuracy priority in the drilling operation risk prediction method shown;
[0055] Figure 8 Shows Figure 2 The processing logic flow chart of the edge-cloud collaborative working mode with efficiency priority in the drilling operation risk prediction method shown;
[0056] Figure 9a A schematic diagram showing formation pore pressure and formation pore pressure equivalent density obtained based on edge end prediction of an example well 1 in an embodiment of this specification;
[0057] Figure 9b A schematic diagram showing the formation pore pressure and formation pore pressure equivalent density obtained based on edge end prediction of the example well 2 in an embodiment of the specification;
[0058] Fig.10a A schematic diagram showing the formation pore pressure of an example well 1 predicted based on cloud computing in an embodiment of this specification is shown;
[0059] Fig.10b A schematic diagram showing the formation pore pressure of an example well 2 predicted based on cloud computing in an embodiment of this specification is shown;
[0060] Fig.11 A structural block diagram of a drilling operation risk prediction system based on edge-cloud integration in some embodiments of this specification is shown;
[0061] Fig.12 The structure block diagram of the computer device in some embodiments of the present specification is shown.
[0062] [Description of Reference Numerals]
[0063] 10. Edge end;
[0064] 20. Cloud;
[0065] 111. Get module;
[0066] 112. Identification module;
[0067] 113. Determine the module;
[0068] 114. Prediction module;
[0069] 1202. Computer equipment;
[0070] 1204, processor;
[0071] 1206. Memory;
[0072] 1208, driving mechanism;
[0073] 1210, input / output interface;
[0074] 1212. Input device;
[0075] 1214. Output device;
[0076] 1216. Presentation equipment;
[0077] 1218. Graphical user interface;
[0078] 1220, network interface;
[0079] 1222, communication link;
[0080] 1224. Communication bus. DETAILED DESCRIPTION
[0081] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.
[0082] The risks of drilling projects are more serious, different, diverse, hidden and changeable, which makes accidents happen more frequently. In view of the fact that the existing single drilling operation risk assessment and early warning technology cannot guarantee the timeliness and accuracy of drilling operation risk prediction, the embodiment of this specification provides a drilling operation risk prediction solution based on edge-cloud integration.
[0083] Figure 1 A drilling operation risk prediction system based on edge-cloud integration in some embodiments of this specification is shown, which may include a cloud 20 and multiple edge terminals 10. Both the edge terminal 10 and the cloud 20 can independently perform drilling operation risk prediction, or they can collaboratively perform drilling operation risk prediction. Therefore, the edge-cloud integration in the embodiments of this specification refers to combining the edge terminal 10 and the cloud 20 to collaboratively perform drilling operation risk prediction. Among them, the edge terminal 10 refers to a local prediction terminal set at the drilling operation site. In some embodiments, the edge terminal 10 can be a computer device configured with drilling operation risk prediction software. The edge terminal 10 puts computing, storage, network and other resources into the on-site environment, so that drilling operation prediction can be realized in a timely manner; it is suitable for scenarios where drilling operation problems are relatively simple and processing timeliness requirements are high. The cloud 20 is a cloud server, which is a remote prediction terminal relative to the drilling operation site. Since the cloud 20 has higher computing and processing capabilities and more processing methods, its comprehensive performance is much stronger than the edge 10. In addition, in the application process, it has the characteristics of dynamic, autonomous, quantitative and flexible. It is suitable for scenes where drilling operation problems are more complicated and the processing timeliness requirements are relatively low. Therefore, the combination of the edge 10 and the cloud 20 can form complementary advantages, so that risk predictions for drilling operations can be made in a timely and accurate manner.
[0084] The embodiment of this specification provides a drilling operation risk prediction method based on edge-cloud integration, which can be applied to the above-mentioned drilling operation risk prediction system. Figure 2 As shown, in some embodiments, the edge-cloud integrated drilling operation risk prediction method may include the following steps:
[0085] Step 201: Acquire on-site return data of drilling operations.
[0086] Step 202: Identify the problem type, processing urgency, processing accuracy, network quality and computing power consumption of the drilling operation problem based on the field return data.
[0087] Step 203: determine the working mode according to the problem type, the processing urgency, the processing accuracy, the network quality and the computing power consumption; the working mode includes an edge independent working mode, a cloud independent working mode and an edge-cloud collaborative working mode.
[0088] Step 204: predicting the operational risk of the drilling operation according to the determined working mode.
[0089] In the edge-cloud integrated drilling operation risk prediction method of the embodiment of this specification, the problem type, processing urgency, processing accuracy, network quality and computing power consumption of the drilling operation problem can be identified based on the on-site return data of the drilling operation, and based on these parameters, a suitable working mode can be decided from the edge independent working mode, the cloud independent working mode and the edge-cloud collaborative working mode, and the operational risk of the drilling operation can be predicted according to the determined working mode; the complementary advantages of edge prediction and cloud prediction are realized, thereby improving the timeliness and accuracy of drilling operation risk prediction.
[0090] The field return data can reflect the real-time on-site status of the drilling operation. Therefore, based on the analysis of the field return data of the drilling operation, it is possible to predict and identify whether there are risk problems in the drilling operation. In some embodiments, the field return data may include but is not limited to drilling data, mud logging data, and well logging data. The drilling operation monitoring equipment can provide the field return data of the drilling operation to the drilling operation risk prediction system in real time, so that the drilling operation risk prediction system can obtain the field return data of the drilling operation in real time.
[0091] Research shows that the problem type, processing urgency, processing accuracy, network quality and computing power consumption of drilling operation problems can objectively and comprehensively characterize the on-site real-time status of drilling operations. Therefore, the problem type, processing urgency, processing accuracy, network quality and computing power consumption of drilling operation problems identified based on on-site return data can provide an objective and reliable reference basis for the subsequent decision-making of the most appropriate prediction and processing mode for different drilling operation problems.
[0092] The problem type characterizes the problem type and severity of the drilling operation problem; the problem type can be represented by a grade evaluation index, and the higher the grade, the more serious the problem. The processing urgency reflects the urgency of the drilling operation site to solve the drilling operation problem; the processing urgency can be represented by a grade evaluation index, and the higher the grade, the higher the urgency. The processing accuracy is the accuracy requirement required for the prediction results at the drilling operation site; the processing accuracy can be represented by a grade evaluation index, and the higher the grade, the higher the accuracy requirement. Network quality is a parameter that reflects the current communication quality between the edge and the cloud (including network bandwidth, network stability, etc.); network quality can be represented by a grade evaluation index, and the higher the grade, the better the network quality. Computing power consumption represents the computing power resources required to solve drilling operation problems; computing power consumption can be represented by a grade evaluation index, and the higher the grade, the greater the computing power consumption.
[0093] refer to Figure 3As shown, in some embodiments, identifying the problem type, processing urgency, processing accuracy, network quality, and computing power consumption of the drilling operation problem according to the field return data may include the following steps:
[0094] Step 301: Compare the value of the field returned data with the corresponding preset range to obtain a comparison result.
[0095] For example, in an exemplary embodiment, taking formation pore pressure as an example, the formation pore pressure in the field return data may be compared with a preset formation pore pressure range to obtain a comparison result.
[0096] Step 302: determine whether there is a drilling operation problem based on the comparison result; if yes, execute step 303; otherwise, continue to obtain the on-site return data of the drilling operation (i.e. jump to execute the above step 201) to perform the next round of processing.
[0097] For instance, in an exemplary embodiment, taking formation pore pressure as an example, the formation pore pressure in the field return data can be compared with a preset formation pore pressure range. When the formation pore pressure in the field return data is higher than the upper limit of the formation pore pressure range, or lower than the lower limit of the formation pore pressure range, it indicates that there is a problem of abnormal formation pore pressure (a drilling operation problem).
[0098] Step 303: Determine the problem type of the drilling operation problem.
[0099] The problem type of the drilling operation problem can be determined based on the comparison object and the comparison result. For example, in an exemplary embodiment, taking the formation pore pressure as an example, when the formation pore pressure in the field return data is higher than the upper limit of the formation pore pressure range, the problem type can be that the formation pore pressure is too high, and the high level to which it belongs can be determined according to the degree of high (for example, the formation pore pressure is one level higher). When the formation pore pressure in the field return data is lower than the lower limit of the formation pore pressure range, the problem type can be that the formation pore pressure is too low, and the low level to which it belongs can be determined according to the degree of low (for example, the formation pore pressure is two levels lower).
[0100] Step 304a: Determine the processing urgency of the problem type by querying the corresponding relationship table between the problem type and the processing urgency.
[0101] Various problems that may occur in drilling operations can be counted in advance, and the urgency of handling can be preset for each problem according to the degree of impact or harm of the problem on the drilling operation, thereby forming a corresponding relationship table between the problem type and the urgency of handling. Based on the problem type determined in step 303, the corresponding relationship table between the problem type and the urgency of handling can be queried according to the problem type, that is, the urgency of handling corresponding to the problem type can be matched.
[0102] Step 304b: Determine the processing accuracy of the question type by querying the corresponding relationship table between the question type and the processing accuracy.
[0103] Various problems that may occur in drilling operations can be counted in advance, and processing accuracy can be preset for each problem according to the degree of impact or harm of the problem on the drilling operation, thereby forming a corresponding relationship table between problem type and processing accuracy. Based on the problem type determined in step 303, the corresponding relationship table between problem type and processing accuracy is queried according to the problem type, that is, the processing accuracy corresponding to the problem type can be matched.
[0104] Step 304c: determine the computing power consumption of the problem type by querying the corresponding relationship table between the problem type and the computing power consumption.
[0105] Various problems that may occur in drilling operations can be counted in advance, and the historical data of various problems can be used to preset the computing power consumption for each problem, thereby forming a corresponding relationship table between problem types and computing power consumption. Based on the problem type determined in step 303, the corresponding relationship table between problem type and computing power consumption is queried according to the problem type, that is, the computing power consumption corresponding to the problem type can be matched.
[0106] Step 304d: determine the network quality between the edge and the cloud based on the data volume, sending time, and receiving time of the on-site return data.
[0107] Of course, in other embodiments, the network between the edge and the cloud may be tested by a network quality testing tool to determine the network quality.
[0108] The above steps 304a to 304d may be executed in parallel to improve processing efficiency; they may also be executed sequentially as required, which is not limited in this specification.
[0109] refer to Figure 4 As shown, in some embodiments, determining the working mode according to the problem type, the processing urgency, the processing accuracy, the network quality and the computing power consumption may include the following steps:
[0110] Step 401: The weighted sum of the problem type, the processing urgency, the processing accuracy, the network quality and the computing power consumption is used as the processing level.
[0111] The processing level can comprehensively reflect the complexity of drilling operation problems. The higher the processing level, the higher the complexity. Therefore, the processing level can be used to decide the working mode for processing drilling operation problems. Among them, the weighted sum of problem type, processing urgency, processing accuracy, network quality and computing power consumption can be calculated according to the following formula:
[0112] Processing level = problem type (t) * weight a + processing accuracy (i) * weight b + processing urgency (e) * weight c + network quality (n) * weight d + computing power consumption (s) * weight f; where weight a, weight b, weight c, weight d and weight f can be preset, and the sum of the total weights is 1. The evaluation indicators of various parameters (such as problem type, processing accuracy, processing precision, etc.) are set to levels 1 to 10.
[0113] Step 402, determine whether the processing level reaches the processing level threshold; if the processing level reaches the processing level threshold, execute step 403; otherwise, execute step 404.
[0114] Step 403: When the processing level reaches the processing level threshold, the collaborative working mode recognition process is performed.
[0115] The higher the processing level, the more complex the problem; therefore, when the processing level reaches the preset processing level threshold, the collaborative working mode (i.e., the collaborative working mode between the edge and the cloud) can be selected. Since the collaborative working mode can be divided into multiple modes, it is necessary to further identify which collaborative working mode to adopt in order to facilitate the decision-making of the best collaborative working mode. Therefore, when the processing level reaches the preset processing level threshold, the identification processing of the collaborative working mode can be performed.
[0116] Step 404: When the processing level does not reach the processing level threshold, perform identification processing of the independent working mode.
[0117] The lower the processing level, the simpler the problem; therefore, when the processing level does not reach the preset processing level threshold, the independent working mode can be selected. Since the independent working mode can include the edge independent working mode and the cloud independent working mode, it is necessary to further identify which collaborative working mode to adopt in order to facilitate the decision-making of the best independent working mode; therefore, when the processing level does not reach the preset processing level threshold, the identification processing of the independent working mode can be performed.
[0118] refer to Figure 5 As shown, in some embodiments, performing the identification process of the independent working mode may include the following steps:
[0119] Step 501: Determine whether there is an idle edge end that meets the processing urgency and processing accuracy requirements of the problem type. If there is an idle edge end that meets the processing urgency and processing accuracy requirements of the problem type, execute step 502, otherwise execute step 503.
[0120] When the problem type is determined, an idle edge end whose processing performance meets both the processing urgency and processing accuracy requirements of the problem type can be found from all idle edge ends; when there are multiple idle edge ends that meet the processing urgency and processing accuracy requirements of the problem type, the idle edge end closest to the problem well is preferred to further improve the timeliness of the prediction. Among them, the idle edge end refers to: the edge end that is currently in an idle state; the problem well refers to the well where the problem occurs.
[0121] Step 502: If there is an idle edge terminal that meets the processing urgency and processing accuracy requirements of the problem type, select the independent working mode as the edge terminal independent working mode. Figure 9a and Figure 9b In the illustrated embodiment, the formation pore pressures of Example Well 1 and Example Well 2 predicted based on the edge end are respectively shown.
[0122] Since the edge is located at the drilling site, the prediction real-time performance of the edge is better than that of the cloud in relatively simple problem scenarios. Therefore, if there is an idle edge that meets the processing urgency and processing accuracy requirements of the problem type, the independent working mode is preferred as the edge independent working mode to improve the timeliness of the prediction.
[0123] Step 503: If there is no idle edge terminal that meets the processing urgency and processing accuracy requirements of the problem type, the independent working mode is selected as the cloud independent working mode. Fig.10a and Fig.10b In the illustrated embodiment, the formation pore pressures of Example Well 1 and Example Well 2 predicted based on the cloud are shown respectively.
[0124] When there is no idle edge terminal that meets the processing urgency and processing accuracy requirements of the problem type, the cloud-based independent working mode can be selected as a second choice to complete the operational risk prediction of the drilling operation in the independent working mode.
[0125] refer to Figure 6 As shown, in some embodiments, performing the identification process of the collaborative working mode may include the following steps:
[0126] Step 601: respectively determine the influence weights of the processing accuracy and the computing power consumption in the problem type.
[0127] For relatively complex drilling operation problems, there are also different processing accuracy requirements and processing urgency requirements. Among them, the impact weights corresponding to these requirements can be pre-configured, that is, different processing accuracy weights and processing urgency weights can be configured for different drilling operation problems, thereby forming a problem-weight correspondence table; therefore, by querying the problem-weight correspondence table based on the problem type, the impact weights of processing accuracy and computing power consumption in the problem type can be determined.
[0128] Step 602: determine whether the influence weight of the processing accuracy in the problem type is greater than the influence weight of the computing power consumption in the problem type; if it is, execute step 603; otherwise, execute step 604.
[0129] Step 603: When the influence weight of the processing accuracy in the problem type is greater than the influence weight of the computing power consumption in the problem type, select the edge-cloud collaborative working mode that prioritizes accuracy as the collaborative working mode.
[0130] For the same drilling operation problem, if its processing accuracy weight is greater than the processing urgency weight, it means that the drilling operation problem prioritizes meeting the processing accuracy requirements; therefore, the edge-cloud collaborative working mode with accuracy priority can be selected.
[0131] Step 604: When the influence weight of the processing accuracy in the problem type is not greater than the influence weight of the computing power consumption in the problem type, select the edge-cloud collaborative working mode that prioritizes efficiency as the collaborative working mode.
[0132] For the same drilling operation problem, if its processing accuracy weight is not greater than the processing urgency weight, it means that the drilling operation problem prioritizes meeting the processing urgency requirements; therefore, the edge-cloud collaborative working mode with efficiency priority can be selected.
[0133] refer to Figure 7 As shown, in some embodiments, the processing logic of the precision-first edge-cloud collaborative working mode may include the following steps:
[0134] Step 701: predict the operational risk of the drilling operation based on the edge to obtain a first prediction result, and predict the operational risk of the drilling operation based on the cloud to obtain a second prediction result.
[0135] In some embodiments, the prediction result may include a predicted value of the on-site return data within a prediction time range (eg, within the next 1 minute, 5 minutes, 10 minutes, etc.).
[0136] Step 702: Calculate prediction evaluation index values of the first prediction result and the second prediction result respectively.
[0137] In one embodiment, the prediction evaluation index value may be an index such as accuracy or precision.
[0138] Step 703, determine whether the prediction evaluation index values of the first prediction result and the second prediction result have reached the index threshold; if one has reached the index threshold, execute step 704; otherwise, execute step 706.
[0139] Determining whether the prediction evaluation index values of the first prediction result and the second prediction result have reached the index threshold is to determine whether the prediction evaluation index value of the first prediction result has reached the index threshold, and to determine whether the prediction evaluation index value of the second prediction result has reached the index threshold. The index threshold is a comparison benchmark set in advance according to the processing accuracy requirement.
[0140] Step 704: The prediction result corresponding to the one with the larger prediction evaluation index value is taken as the final prediction result.
[0141] When there is one that reaches the index threshold, it means that at least one of the prediction evaluation index value of the first prediction result and the prediction evaluation index value of the second prediction result has reached the index threshold; therefore, taking the prediction result corresponding to the larger prediction evaluation index value as the final prediction result can ensure that the final prediction result meets the processing accuracy requirements.
[0142] Step 705: Update the drilling operation risk prediction algorithm corresponding to the prediction evaluation index with the smaller value.
[0143] By updating the drilling operation risk prediction algorithm corresponding to the smaller prediction evaluation index value, the accuracy of drilling operation risk prediction can be improved. For example, in the prediction of formation pore pressure during drilling operations, if the prediction result obtained by the edge using the Eaton method is not as accurate as the prediction result obtained by the cloud using other algorithms (such as intelligent prediction algorithms pre-trained based on machine learning models such as decision trees, random forests, neural networks, deep learning, and reinforcement learning algorithms), the cloud can call the Eaton method from the algorithm database, continuously optimize the parameters of the Eaton method, so that the prediction result of the optimized Eaton method has the smallest error with the prediction result of the cloud, and return the optimized Eaton method to the edge to replace the previous Eaton method of the edge.
[0144] Step 706: Replace the drilling operation risk prediction algorithm on the edge and cloud, and then jump to step 701.
[0145] In the embodiments of this specification, considering that the performance of the edge end is relatively weak, the edge end may be configured with only one drilling operation risk prediction algorithm; or for each drilling operation problem, the edge end may be configured with only one corresponding drilling operation risk prediction algorithm. Considering that the performance of the cloud end is relatively strong, for each drilling operation problem, the cloud end may be configured with multiple drilling operation risk prediction algorithms, thereby forming an algorithm database; different drilling operation risk prediction algorithms may have different prediction performance in different application scenarios; the same drilling operation risk prediction algorithm may also have different prediction performance before and after parameter adjustment.
[0146] Therefore, when no one reaches the index threshold, in order to improve the prediction accuracy of subsequent predictions, the drilling operation risk prediction algorithm on the edge and cloud can be replaced. Specifically, the cloud can replace the default drilling operation risk prediction algorithm for the drilling operation problem, and return the replaced default drilling operation risk prediction algorithm to the edge, so that the edge can also make corresponding changes. Of course, in other embodiments, the edge and cloud can also be replaced with different drilling operation risk prediction algorithms; for example, the edge is replaced by the Eaton method with the Bowers method or the Dc index method, etc.; the cloud is replaced by a prediction model based on decision tree pre-training with a prediction model based on neural network pre-training.
[0147] refer to Figure 8 As shown, in some embodiments, the processing logic of the efficiency-first edge-cloud collaborative working mode may include the following steps:
[0148] Step 801: split the drilling operation problem into multiple prediction subtasks.
[0149] The purpose of splitting a drilling operation problem into multiple prediction subtasks is to facilitate subsequent parallel processing. Of course, when there are multiple drilling operation problems, multiple drilling operation problems can also be assigned to multiple edge terminals for parallel processing.
[0150] Step 802: Distribute the multiple prediction subtasks to multiple edge terminals for parallel processing to obtain multiple prediction subresults.
[0151] Step 803: Combine the multiple prediction sub-results into a complete prediction result.
[0152] In this way, through parallel processing, the time consumption of drilling operation risk prediction can be greatly shortened, thereby further improving the timeliness and efficiency of drilling operation risk prediction.
[0153] Although the process flows described above include multiple operations that occur in a particular order, it should be clearly understood that the processes may include more or fewer operations, which may be performed sequentially or in parallel (eg, using parallel processors or a multi-threaded environment).
[0154] In the embodiment of the present specification, predicting the operational risk of the drilling operation according to the determined working mode in step 204 is to predict the operational risk of the drilling operation according to the drilling operational risk prediction algorithm corresponding to the selected working mode. For example, when the selected working mode is the edge end independent working mode, the selected edge end can predict the operational risk of the drilling operation based on the pre-configured drilling operational risk prediction algorithm.
[0155] Corresponding to the above-mentioned edge-cloud integrated drilling operation risk prediction method, the embodiment of this specification also provides a drilling operation risk prediction system based on edge-cloud integration, referring to Fig.11 As shown, the edge-cloud integrated drilling operation risk prediction system may include:
[0156] The acquisition module 111 can be used to acquire the on-site return data of the drilling operation;
[0157] An identification module 112 may be used to identify the problem type, processing urgency, processing accuracy, network quality and computing power consumption of the drilling operation problem according to the field return data;
[0158] The determination module 113 may be used to determine a working mode according to the problem type, the processing urgency, the processing accuracy, the network quality, and the computing power consumption; the working mode includes an edge-end independent working mode, a cloud-end independent working mode, and an edge-cloud collaborative working mode;
[0159] The prediction module 114 may be used to predict the operational risk of the drilling operation according to the determined working mode.
[0160] In the edge-cloud integrated drilling operation risk prediction system of the embodiment of this specification, the problem type, processing urgency, processing accuracy, network quality and computing power consumption of the drilling operation problem identified according to the field return data include:
[0161] Comparing the value of the field returned data with the corresponding preset range, and determining whether there is a drilling operation problem based on the comparison result;
[0162] When there is a drilling operation problem, determine the problem type of the drilling operation problem;
[0163] By querying the corresponding relationship table between the problem type and the processing urgency, the processing urgency of the problem type is determined;
[0164] Determine the processing accuracy of the problem type by querying the corresponding relationship table between the problem type and the processing accuracy;
[0165] By querying the corresponding relationship table between the problem type and the computing power consumption, the computing power consumption of the problem type is determined;
[0166] The network quality between the edge terminal and the cloud is determined by the data volume, sending time and receiving time of the on-site return data.
[0167] In the edge-cloud integrated drilling operation risk prediction system of the embodiment of this specification, the working mode is determined according to the problem type, the processing urgency, the processing accuracy, the network quality and the computing power consumption, including:
[0168] The weighted sum of the problem type, the processing urgency, the processing accuracy, the network quality and the computing power consumption is used as the processing level;
[0169] When the processing level reaches the processing level threshold, performing identification processing of the collaborative working mode;
[0170] When the processing level does not reach the processing level threshold, the recognition process of the independent working mode is performed.
[0171] In the edge-cloud integrated drilling operation risk prediction system of the embodiment of this specification, the identification process of executing the independent working mode includes:
[0172] Determine whether there is an idle edge end that meets the processing urgency and processing accuracy requirements of the problem type;
[0173] If there is an idle edge end that meets the processing urgency and processing accuracy requirements of the problem type, the independent working mode is selected as the edge end independent working mode;
[0174] If there is no idle edge terminal that meets the processing urgency and processing accuracy requirements of the problem type, the independent working mode is selected as the cloud independent working mode.
[0175] In the edge-cloud integrated drilling operation risk prediction system of the embodiment of this specification, the identification and processing of executing the collaborative working mode includes:
[0176] Determine the influence weights of the processing accuracy and the computing power consumption in the problem type respectively;
[0177] When the influence weight of the processing accuracy in the problem type is greater than the influence weight of the computing power consumption in the problem type, the edge-cloud collaborative working mode with accuracy priority is selected as the collaborative working mode;
[0178] When the influence weight of the processing accuracy in the problem type is not greater than the influence weight of the computing power consumption in the problem type, the collaborative working mode is selected as the edge-cloud collaborative working mode that prioritizes efficiency.
[0179] In the edge-cloud integrated drilling operation risk prediction system of the embodiment of this specification, the processing logic of the edge-cloud collaborative working mode with accuracy priority includes:
[0180] Predicting the operational risk of the drilling operation based on the edge to obtain a first prediction result, and predicting the operational risk of the drilling operation based on the cloud to obtain a second prediction result;
[0181] Calculating prediction evaluation index values of the first prediction result and the second prediction result respectively;
[0182] Determine whether the prediction evaluation index values of the first prediction result and the second prediction result have reached the index threshold;
[0183] When there is one that reaches the index threshold, the prediction result corresponding to the one with the larger prediction evaluation index value is taken as the final prediction result;
[0184] When no indicator threshold is reached, the drilling operation risk prediction algorithm on the edge and cloud is replaced and re-predicted.
[0185] In the edge-cloud integrated drilling operation risk prediction system of the embodiment of this specification, the processing logic of the efficiency-first edge-cloud collaborative working mode includes:
[0186] Split the drilling operation problem into multiple prediction subtasks;
[0187] Distributing the multiple prediction subtasks to multiple edge terminals for parallel processing to obtain multiple prediction subresults;
[0188] The multiple prediction sub-results are combined into a complete prediction result.
[0189] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.
[0190] The embodiments of this specification also provide a computer device. Fig.12As shown, in some embodiments of the present specification, the computer device 1202 may include one or more processors 1204, such as one or more central processing units (CPUs) or graphics processing units (GPUs), and each processing unit may implement one or more hardware threads. The computer device 1202 may also include any memory 1206, which is used to store any kind of information such as code, settings, data, etc. In a specific embodiment, the computer program on the memory 1206 and can be run on the processor 1204, when the computer program is run by the processor 1204, the instructions of the drilling operation risk prediction method based on edge cloud integration described in any of the above embodiments can be executed. Non-limiting, for example, the memory 1206 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any memory can use any technology to store information. 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 1202. In one embodiment, when the processor 1204 executes the associated instructions stored in any memory or combination of memories, the computer device 1202 can perform any operation of the associated instructions. The computer device 1202 also includes one or more drive mechanisms 1208 for interacting with any memory, such as a hard disk drive mechanism, an optical disk drive mechanism, etc.
[0191] The computer device 1202 may also include an input / output interface 1210 (I / O) for receiving various inputs (via input devices 1212) and for providing various outputs (via output devices 1214). A specific output mechanism may include a presentation device 1216 and an associated graphical user interface 1218 (GUI). In other embodiments, the input / output interface 1210 (I / O), input device 1212, and output device 1214 may not be included, and the computer device 1202 may be used as a computer device in a network. The computer device 1202 may also include one or more network interfaces 1220 for exchanging data with other devices via one or more communication links 1222. One or more communication buses 1224 couple the components described above together.
[0192] The communication link 1222 may be implemented in any manner, for example, 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 link 1222 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc. governed by any protocol or combination of protocols.
[0193] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products of some embodiments of the present specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processor to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processor generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0194] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processor to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0195] These computer program instructions can also be loaded onto a computer or other programmable data processor so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0196] In a typical configuration, a computer device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0197] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0198] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computer device. As defined in this specification, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.
[0199] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, the embodiments of this specification may take the form of complete hardware embodiments, complete software embodiments or embodiments combining software and hardware. Moreover, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0200] The present specification embodiments may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present specification embodiments may also be practiced in distributed computing environments where tasks are performed by remote processors connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0201] It should also be understood that in the embodiments of this specification, the term "and / or" is only a description of the association relationship of the associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.
[0202] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. In the description of this specification, the description of the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of this specification. In this specification, the schematic representation of the above terms does not necessarily target the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, in the absence of contradiction, a person skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.
[0203] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A drilling operation risk prediction method based on edge-cloud integration, characterized in that: include: Obtain field return data from drilling operations; Identify the type of drilling operation problem, processing urgency, processing accuracy, network quality, and computing power consumption according to the field return data; Determining a working mode according to the problem type, the processing urgency, the processing accuracy, the network quality and the computing power consumption, including: taking the weighted sum of the problem type, the processing urgency, the processing accuracy, the network quality and the computing power consumption as the processing level; when the processing level reaches the processing level threshold, performing identification processing of the collaborative working mode; when the processing level does not reach the processing level threshold, performing identification processing of the independent working mode; the independent working mode includes an edge-end independent working mode and a cloud-end independent working mode, and the collaborative working mode includes an edge-cloud collaborative working mode; predicting the operational risk of the drilling operation according to the determined working mode; The identification process of executing the independent working mode includes: Determine whether there is an idle edge end that meets the processing urgency and processing accuracy requirements of the problem type; If there is an idle edge end that meets the processing urgency and processing accuracy requirements of the problem type, the independent working mode is selected as the edge end independent working mode; If there is no idle edge terminal that meets the processing urgency and processing accuracy requirements of the problem type, the independent working mode is selected as the cloud independent working mode; The identification process of executing the collaborative working mode includes: Determine the influence weights of the processing accuracy and the computing power consumption in the problem type respectively; When the influence weight of the processing accuracy in the problem type is greater than the influence weight of the computing power consumption in the problem type, the edge-cloud collaborative working mode with accuracy priority is selected as the collaborative working mode; When the influence weight of the processing accuracy in the problem type is not greater than the influence weight of the computing power consumption in the problem type, the collaborative working mode is selected as the edge-cloud collaborative working mode that prioritizes efficiency.
2. The method for predicting drilling operation risks based on edge-cloud integration according to claim 1, characterized in that: The identifying the problem type, processing urgency, processing accuracy, network quality and computing power consumption of the drilling operation problem according to the field return data includes: Comparing the value of the field returned data with the corresponding preset range, and determining whether there is a drilling operation problem based on the comparison result; When there is a drilling operation problem, determine the problem type of the drilling operation problem; By querying the corresponding relationship table between the problem type and the processing urgency, the processing urgency of the problem type is determined; Determine the processing accuracy of the problem type by querying the corresponding relationship table between the problem type and the processing accuracy; By querying the corresponding relationship table between the problem type and the computing power consumption, the computing power consumption of the problem type is determined; The network quality between the edge terminal and the cloud is determined by the data volume, sending time and receiving time of the on-site return data.
3. The method for predicting drilling operation risks based on edge-cloud integration according to claim 1, characterized in that: The processing logic of the precision-first edge-cloud collaborative working mode includes: Predicting the operational risk of the drilling operation based on the edge to obtain a first prediction result, and predicting the operational risk of the drilling operation based on the cloud to obtain a second prediction result; Calculating prediction evaluation index values of the first prediction result and the second prediction result respectively; Determine whether the prediction evaluation index values of the first prediction result and the second prediction result have reached the index threshold; When there is a person who reaches the index threshold, the prediction result corresponding to the person with the larger prediction evaluation index value is used as the final prediction result, and the drilling operation risk prediction algorithm corresponding to the person with the smaller prediction evaluation index value is updated; When no indicator threshold is reached, the drilling operation risk prediction algorithm on the edge and cloud is replaced and re-predicted.
4. The method for predicting drilling operation risks based on edge-cloud integration according to claim 1, characterized in that: The processing logic of the efficiency-first edge-cloud collaborative working mode includes: Split the drilling operation problem into multiple prediction subtasks; Distributing the multiple prediction subtasks to multiple edge terminals for parallel processing to obtain multiple prediction subresults; The multiple prediction sub-results are combined into a complete prediction result.
5. A drilling operation risk prediction system based on edge-cloud integration, characterized in that: include: An acquisition module, used to acquire on-site return data of drilling operations; An identification module, used to identify the problem type, processing urgency, processing accuracy, network quality and computing power consumption of the drilling operation problem according to the field return data; A determination module, used to determine the working mode according to the problem type, the processing urgency, the processing accuracy, the network quality and the computing power consumption, including: taking the weighted sum of the problem type, the processing urgency, the processing accuracy, the network quality and the computing power consumption as the processing level; when the processing level reaches the processing level threshold, performing the identification processing of the collaborative working mode; when the processing level does not reach the processing level threshold, performing the identification processing of the independent working mode; the independent working mode includes the edge independent working mode and the cloud independent working mode, and the collaborative working mode includes the edge-cloud collaborative working mode; A prediction module, used for predicting the operation risk of the drilling operation according to the determined working mode; The identification process of executing the independent working mode includes: Determine whether there is an idle edge end that meets the processing urgency and processing accuracy requirements of the problem type; If there is an idle edge end that meets the processing urgency and processing accuracy requirements of the problem type, the independent working mode is selected as the edge end independent working mode; If there is no idle edge terminal that meets the processing urgency and processing accuracy requirements of the problem type, the independent working mode is selected as the cloud independent working mode; The identification process of executing the collaborative working mode includes: Determine the influence weights of the processing accuracy and the computing power consumption in the problem type respectively; When the influence weight of the processing accuracy in the problem type is greater than the influence weight of the computing power consumption in the problem type, the edge-cloud collaborative working mode with accuracy priority is selected as the collaborative working mode; When the influence weight of the processing accuracy in the problem type is not greater than the influence weight of the computing power consumption in the problem type, the collaborative working mode is selected as the edge-cloud collaborative working mode that prioritizes efficiency.
6. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: When the computer program is executed by the processor, the computer program executes the instructions of the method according to any one of claims 1 to 4.
7. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor of a computer device, the computer program executes the instructions of the method according to any one of claims 1 to 4.
