A method, device, equipment and medium for monitoring drilling conditions

Abstract

The present application discloses a method, device, equipment and medium for monitoring drilling conditions. Among them, the method reconstructs the time series data by inputting the time series data obtained by the target well in the target time period into a pre-trained time series autoencoder model, determines the reconstructed data corresponding to the time series data, and determines the first trend of the time series data based on the reconstructed data; fits each acquisition time node in the target time period and the time series data corresponding to each acquisition time node, determines the fitting result of the time series data, and determines the second trend of the time series data based on the fitting result; determines the working state of the target well according to the first trend and the second trend. This technical solution realizes real-time and accurate monitoring of drilling conditions by reconstructing and fitting the time series data respectively, thereby improving the safety and production efficiency of the drilling process.

Description

Technical Field

[0001] The present application relates to the field of exploration technology, and in particular to a method, device, equipment and medium for monitoring drilling conditions. Background Art

[0002] In the process of oil and gas exploration, production and drilling, the normal operation of drilling equipment and tools is crucial to ensure safety, improve production efficiency and reduce losses. However, due to complex underground geological conditions, wellbore structure, working environment and equipment wear, abnormal working conditions or equipment failures may occur at any time, bringing risks and challenges to the entire drilling process.

[0003] Traditional drilling condition monitoring methods are usually based on rule-based or threshold-based technologies, that is, abnormal conditions are detected according to pre-defined rules or set thresholds. In addition, the drilling process involves many drilling parameters and a complex working environment, such as the constantly changing drill bit status, underground geological conditions and fluid pressure, which makes traditional drilling condition monitoring methods have some limitations in processing. It is often difficult to capture hidden patterns and abnormal features in the data, so it is easy to produce false positives or false negatives, which brings certain risks and uncertainties to drilling work. Summary of the invention

[0004] The present application provides a method, device, equipment and medium for monitoring drilling conditions, which realizes real-time and accurate monitoring of drilling conditions by reconstructing and fitting time series data respectively, thereby improving the safety and production efficiency of the drilling process.

[0005] According to one aspect of the present application, a method for monitoring drilling conditions is provided, the method comprising:

[0006] Inputting the time series data acquired from the target well in the target time period into a pre-trained time series autoencoder model, reconstructing the time series data, determining reconstructed data corresponding to the time series data, and determining a first trend of the time series data based on the reconstructed data;

[0007] Fitting each acquisition time node within the target time period and the time series data corresponding to each acquisition time node, determining a fitting result of the time series data, and determining a second trend of the time series data based on the fitting result;

[0008] The operating status of the target well is determined according to the first trend and the second trend.

[0009] According to another aspect of the present application, a monitoring device for drilling conditions is provided, the device comprising:

[0010] A first trend determination module, configured to input the time series data acquired from the target well in the target time period into a pre-trained time series autoencoder model, reconstruct the time series data, determine reconstructed data corresponding to the time series data, and determine a first trend of the time series data based on the reconstructed data;

[0011] A second trend determination module is used to fit each acquisition time node within the target time period and the time series data corresponding to each acquisition time node, determine the fitting result of the time series data, and determine the second trend of the time series data based on the fitting result;

[0012] A working condition determination module is used to determine the working condition of the target well according to the first trend and the second trend.

[0013] According to another aspect of the present application, an electronic device is provided, the device comprising:

[0014] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for monitoring drilling conditions described in any embodiment of the present application.

[0015] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for monitoring drilling conditions described in any embodiment of the present application when executed.

[0016] The technical solution provided by the present application reconstructs the time series data acquired by the target well in the target time period into a pre-trained time series autoencoder model, determines the reconstructed data corresponding to the time series data, and determines the first trend of the time series data based on the reconstructed data; fits each acquisition time node in the target time period and the time series data corresponding to each acquisition time node, determines the fitting result of the time series data, and determines the second trend of the time series data based on the fitting result; determines the working state of the target well according to the first trend and the second trend. The technical solution reconstructs and fits the time series data respectively to achieve real-time and accurate monitoring of the drilling working conditions, thereby improving the safety and production efficiency of the drilling process.

[0017] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A flowchart of a method for monitoring drilling conditions provided in Example 1 of the present application;

[0020] Figure 2 A schematic diagram of the structure of a temporal autoencoder model provided in Example 1 of the present application;

[0021] Figure 3 A flowchart of a method for monitoring drilling conditions provided in Example 2 of the present application;

[0022] Figure 4 A flowchart of a method for monitoring drilling conditions provided in Example 3 of the present application;

[0023] Figure 5 A schematic diagram of the structure of a monitoring device for drilling conditions provided in Example 4 of the present application;

[0024] Figure 6 It is a structural schematic diagram of a device for implementing a method for monitoring drilling conditions in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", "third", "fourth", "target", "operation", "history", "preset", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] Embodiment 1

[0028] Figure 1 This is a flowchart of a method for monitoring drilling conditions provided in Example 1 of the present application. This embodiment is applicable to the case of real-time monitoring of the drilling process. The method can be executed by a monitoring device for drilling conditions. The monitoring device for drilling conditions can be implemented in the form of hardware and / or software. The monitoring device for drilling conditions can be configured in a device with data processing capabilities. Figure 1 As shown, the method includes:

[0029] S110, inputting the time series data obtained from the target well in the target time period into a pre-trained time series autoencoder model, reconstructing the time series data, determining the reconstructed data corresponding to the time series data, and determining the first trend of the time series data based on the reconstructed data.

[0030] The time series data may be drilling parameter data regularly acquired during the drilling process. Specifically, the acquisition process of the time series data may include but is not limited to the following steps A1-A5:

[0031] Step A1, deploy various sensors on the drilling equipment to measure multiple key drilling parameter data in real time, including but not limited to drilling pressure, torque, displacement, vibration signal, inlet and outlet density, inlet and outlet temperature, inlet and outlet conductivity, total pool volume, outlet flow, total hydrocarbon and drilling time, etc. It should be noted that the deployed sensors should have high-precision and high-frequency data acquisition capabilities to ensure that key timing information can be collected.

[0032] Step A2, regularly generate time series data from the data collected by each sensor and record them to ensure that no valuable information is lost and provide complete data for subsequent analysis and processing.

[0033] Step A3, storing the recorded time series data in a central data storage device for subsequent processing and analysis. It should be noted that data storage needs to consider data capacity, backup strategy and access rights to ensure data integrity, availability and security.

[0034] Step A4, data cleaning and preprocessing are performed on the stored time series data, such as detecting and correcting sensor errors or abnormal data points, interpolating values ​​or smoothing, to ensure the quality and consistency of the time series data to accurately reflect the actual situation during the drilling process.

[0035] Step A5: perform data standardization or normalization on the preprocessed time series data. Since different sensors may have different measurement units and measurement ranges, standardization or normalization is required to ensure that the scale between different drilling parameters does not affect subsequent analysis.

[0036] The time series autoencoder model can learn the patterns and features of normal operating data through deep learning technology. The time series autoencoder model may include an encoder part and a decoder part. The encoder part is used to convert the original time series data into low-dimensional data, and the decoder part is used to reconstruct the low-dimensional data into reconstructed data. Specifically, Figure 2 This is a schematic diagram of the structure of a temporal autoencoder model provided in Example 1 of the present application. Figure 2 As shown, A is the encoder part of the time series autoencoder model, B is the decoder part of the time series autoencoder model, a is the input time series data, b is the encoder core code, c is the low-dimensional space, d is the decoder core code, and e is the output reconstructed data.

[0037] Specifically, the training process of the time series autoencoder model may include but is not limited to the following steps B1-B5:

[0038] Step B1, select a suitable time series autoencoder model architecture according to the nature and complexity of the time series data. For example, long short-term memory time series autoencoder, variational autoencoder, etc. It should be noted that the model should be complex enough to capture the key features in the data, but not too complex to avoid overfitting.

[0039] Step B2, determining the loss function. In the present application, the mean square error can be used to measure the accuracy of the time series autoencoder model in reconstructing the time series data.

[0040] Step B3, obtain a time series data set under normal working conditions, and divide the time series data set into a training set and a validation set, the training set is used for model training, and the validation set is used to evaluate the performance of the model. It should be noted that at this stage, the data needs to be standardized or normalized to ensure that the scales of different parameters do not affect the learning process of the model.

[0041] Step B4, select the appropriate training algorithm and hyperparameters, such as learning rate, batch size, and number of training cycles. It is necessary to use an iterative approach when training the model to continuously improve the performance of the model. During the training process, the time series autoencoder will try to encode the logging data into a low-dimensional representation and partially reconstruct the original data through the decoder.

[0042] Step B5, through repeated training and verification, continuously optimize the time series autoencoder model to ensure that it can effectively capture the key features and patterns of time series data under normal working conditions, so that the time series autoencoder model can better restore the time series data under normal working conditions.

[0043] The first trend may be a change trend of the time series data predicted by the time series autoencoder model within the target time period. In the present application, the first trend of the time series data is determined based on the reconstructed data, and the reconstructed data and the time series data are compared to determine the first trend of the time series data according to the comparison result.

[0044] Optionally, determining the first trend of the time series data based on the reconstructed data includes: determining a reconstruction error corresponding to each time series data based on the reconstructed data and the time series data; and determining the first trend of the time series data based on the reconstruction error.

[0045] The reconstruction error may be the difference between the reconstructed data and the time series data. In the present application, if the reconstruction error is greater than zero, the first trend of the time series data is determined to be an upward trend; if the reconstruction error is less than zero, the first trend of the time series data is determined to be a downward trend.

[0046] Exemplarily, the time series data of the target well includes the total pool volume and the outlet flow rate, which are input into the time series autoencoder model to output the reconstructed data of the total pool volume and the reconstructed data of the outlet flow rate; the reconstruction error of the total pool volume and the reconstruction error of the outlet flow rate are calculated respectively. If the reconstruction error of the total pool volume is greater than zero and the reconstruction error of the outlet flow rate is greater than zero, it indicates that the total pool volume and the outlet flow rate of the target well are both on an upward trend.

[0047] S120, fitting each acquisition time node within the target time period and the time series data corresponding to each acquisition time node, determining a fitting result of the time series data, and determining a second trend of the time series data based on the fitting result.

[0048] Specifically, polynomial regression or linear regression can be used to fit each acquisition time node in the target time period and the time series data corresponding to each acquisition time node using the least squares method to obtain a fitting function of the time series data changing over time; if the main coefficient of the fitting function is positive, then the second trend of the time series data is determined to be an upward trend; otherwise, the second trend of the time series data is determined to be a downward trend.

[0049] For example, the fitting result of the total pool volume of the target well is: V=0.8t+6.4, where V represents the total pool volume and t represents the acquisition time node. The coefficient of the fitting result is 0.8, and it is determined that the second trend of the total pool volume of the target well is an upward trend.

[0050] S130. Determine the operating status of the target well according to the first trend and the second trend.

[0051] Among them, the working state can be divided into normal working state and abnormal working state. In this application, it can be determined whether the first trend and the second trend are consistent to avoid inaccurate working state prediction due to data anomalies; if the first trend and the second trend are inconsistent, return to step S110 to re-acquire the time series data and process it; if the first trend and the second trend are consistent, then based on the drilling principle, the trend of the time series data is identified to determine the working state corresponding to the current trend.

[0052] The embodiment of the present invention provides a method for monitoring drilling conditions, which reconstructs the time series data by inputting the time series data acquired by the target well in the target time period into a pre-trained time series autoencoder model, determines the reconstructed data corresponding to the time series data, and determines the first trend of the time series data based on the reconstructed data; fits each acquisition time node in the target time period and the time series data corresponding to each acquisition time node, determines the fitting result of the time series data, and determines the second trend of the time series data based on the fitting result; determines the working state of the target well according to the first trend and the second trend. This technical solution realizes real-time and accurate monitoring of drilling conditions by reconstructing and fitting the time series data respectively, avoids false alarms and missed alarms, and improves the safety and production efficiency of the drilling process.

[0053] Embodiment 2

[0054] Figure 3 This is a flow chart of a method for monitoring drilling conditions provided in Example 2 of the present application. This embodiment is optimized based on the above embodiment. Figure 3 As shown, the method of this embodiment specifically includes the following steps:

[0055] S210, inputting the time series data obtained from the target well in the target time period into a pre-trained time series autoencoder model, reconstructing the time series data, determining the reconstructed data corresponding to the time series data, and determining the first trend of the time series data based on the reconstructed data.

[0056] S220: Fit each acquisition time node within the target time period and the time series data corresponding to each acquisition time node, determine a fitting result of the time series data, and determine a second trend of the time series data based on the fitting result.

[0057] S230, determining a first comparison result between the first trend and a preset abnormal operating condition trend, and determining a second comparison result between the second trend and a preset abnormal operating condition trend.

[0058] Among them, the preset abnormal operating condition trend can be data obtained based on drilling principles and historical experience. For example, when the preset abnormal operating condition is overflow risk, the corresponding trend is: drilling time is on a downward trend, total hydrocarbons are on an upward trend, inlet and outlet density is on a downward trend, inlet and outlet temperature is on an upward trend, inlet and outlet conductivity is on a downward trend, total pool volume is on an upward trend, and outlet flow rate is on an upward trend. For another example, when the preset abnormal operating condition is leakage risk, the corresponding trend is: drilling time is on a downward trend, total hydrocarbons are on a downward trend, inlet and outlet density is on a downward trend, total pool volume is on a downward trend, and outlet flow rate is on a downward trend.

[0059] Among them, the first comparison result and the second comparison result are used to determine whether the time series data meets the preset abnormal operating condition trend. If the comparison is consistent, it is determined whether the time series data meets the preset abnormal operating condition trend. If the comparison is inconsistent, it is determined that the time series data does not meet the preset abnormal operating condition trend.

[0060] S240: Determine the operating status of the target well according to the first comparison result and the second comparison result.

[0061] Specifically, by determining whether the first comparison result and the second comparison result are consistent, a comprehensive evaluation of the target well operating state can be achieved to ensure the accuracy of the judgment of the target well operating state.

[0062] Optionally, the operating status of the target well is determined based on the first comparison result and the second comparison result, including: if the first comparison result and the second comparison result are both consistent, then according to the reconstructed data and the timing data, a reconstruction error corresponding to each timing data is determined; and according to the reconstruction error and a preset error threshold, the operating status of the target well is determined.

[0063] Among them, the preset error threshold can be used to limit the fluctuation range of the time series data trend.

[0064] It is understandable that the larger the reconstruction error, the greater the change in the time series data, and the more obvious the fluctuation of the trend; and in the drilling process, the time series data itself has a certain volatility. Therefore, this application limits the reconstruction error by presetting the error threshold to ensure the accuracy of determining the working state of the target well.

[0065] For example, the outlet flow rate is used as an example for explanation. Assuming that the preset error threshold of the outlet flow rate is 0.005, if the absolute value of the reconstruction error is less than 0.005, it is determined that the outlet flow rate in this time period is within the normal fluctuation range, and the operating state of the target well is normal; if the absolute value of the reconstruction error is greater than or equal to 0.005, the change trend of the outlet flow rate in this time period can be regarded as an abnormal trend for operating state judgment.

[0066] The embodiment of the present invention provides a method for monitoring drilling conditions. The method reconstructs the time series data obtained by the target well in the target time period into a pre-trained time series autoencoder model, determines the reconstructed data corresponding to the time series data, and determines the first trend of the time series data based on the reconstructed data; fits each acquisition time node in the target time period and the time series data corresponding to each acquisition time node, determines the fitting result of the time series data, and determines the second trend of the time series data based on the fitting result; determines the first comparison result between the first trend and the preset abnormal working condition trend, and determines the second comparison result between the second trend and the preset abnormal working condition trend; determines the working condition of the target well according to the first comparison result and the second comparison result. The technical scheme compares the first trend reconstructed by the time series autoencoder model with the preset abnormal working condition trend, and compares the second trend fitted by the time series data with the preset abnormal working condition trend, and determines the working condition of the target well by comprehensively considering the comparison results of the two, thereby improving the accuracy of judging abnormal working conditions, thereby improving the safety of drilling work and reducing the maintenance cost of drilling equipment.

[0067] Embodiment 3

[0068] Figure 4 This is a flow chart of a method for monitoring drilling conditions provided in Example 3 of the present application. This embodiment is optimized based on the above embodiment. Figure 4 As shown, the method of this embodiment specifically includes the following steps:

[0069] S310, inputting the time series data obtained from the target well in the target time period into a pre-trained time series autoencoder model, reconstructing the time series data, determining the reconstructed data corresponding to the time series data, and determining the first trend of the time series data based on the reconstructed data.

[0070] S320: Fit each acquisition time node within the target time period and the time series data corresponding to each acquisition time node, determine a fitting result of the time series data, and determine a second trend of the time series data based on the fitting result.

[0071] S330. Determine the operating status of the target well according to the first trend and the second trend.

[0072] S340. Determine, based on the operating data of the target well, an operating time period in which the target well is in an operating condition.

[0073] The operating conditions may be operations performed by the staff on the drilling equipment during the drilling process, for example, pump start or pump stop operations on the drilling equipment. The operating data may be data information corresponding to the operating conditions, including operating time, operating parameters, and operating instructions.

[0074] Since the operation of the drilling equipment during the drilling process may also cause abnormal changes in the time series data, the present application processes the operation data of the target well to determine the operation time period when the target well is in the operation condition.

[0075] S350. Correct the operating state according to the target time period and the operating time period to determine the corrected operating state of the target well.

[0076] In the present application, the target time period can be compared with the operation time period to determine whether there is an operation time period within the target time period; if so, the operating state obtained in step S30 is corrected; if not, the operating state obtained in step S30 is used as the final operating state.

[0077] In addition, the operation time period may be first marked into the time series data according to the operation data, and then the marked time series data may be subsequently processed and analyzed.

[0078] For example, if a well has an abnormal condition within a target time period, first determine whether the time period with the abnormal condition is an operating time period; if so, correct the abnormal condition to a normal condition; if not, do not perform correction processing.

[0079] Based on the above embodiment, optionally, before determining the operation time period of the target well according to the operation data of the target well, the method further includes: acquiring an operation condition trend of the time series data corresponding to the operation condition.

[0080] Specifically, the operating condition trend corresponding to each operating condition may be determined by analyzing the time series data corresponding to the historical operating conditions.

[0081] For example, when the drilling equipment performs the pump-on operation, the corresponding operating condition trends are: the drilling time is on a downward trend, the total hydrocarbon is on a downward trend, the inlet and outlet density is on a downward trend, the total pool volume is on a downward trend, and the outlet flow rate is on a downward trend.

[0082] Furthermore, the operating condition is corrected according to the target time period and the operating time period to determine the corrected operating condition of the target well, including: if the target time period is in the operating time period, determining a third comparison result between the first trend and the operating condition trend, and determining a fourth comparison result between the second trend and the operating condition trend; and correcting the operating condition according to the third comparison result and the fourth comparison result to determine the corrected operating condition of the target well.

[0083] Specifically, the first trend can be compared with the operating condition trend to determine whether the third comparison result is consistent; and the second trend can be compared with the operating condition trend to determine whether the fourth comparison result is consistent; if the third comparison result and the fourth comparison result are both consistent, it means that the abnormal fluctuation of the time series data within the target time period is caused by the operation, and the operating condition state is corrected to the normal condition at this time; if the third comparison result and / or the fourth comparison result are inconsistent, it means that the abnormal fluctuation of the time series data within the target time period is not caused by the operation, and may be caused by a failure of the drilling equipment or other abnormal conditions, and the operating condition state is not corrected at this time.

[0084] The embodiment of the present application provides a method for monitoring drilling conditions, which inputs the time series data acquired by the target well in the target time period into a pre-trained time series autoencoder model, reconstructs the time series data, determines the reconstructed data corresponding to the time series data, and determines the first trend of the time series data based on the reconstructed data; fits each acquisition time node in the target time period and the time series data corresponding to each acquisition time node, determines the fitting result of the time series data, and determines the second trend of the time series data based on the fitting result; determines the operating state of the target well according to the first trend and the second trend; determines the operating time period in which the target well is in the operating condition according to the operating data of the target well; corrects the operating state according to the target time period and the operating time period, and determines the corrected operating state of the target well. This technical solution determines whether there is a real abnormal condition in the time series data by analyzing and comparing the operating condition trend, improves the accuracy of abnormal condition detection, and ensures that false alarms are reduced during actual operating conditions, thereby reducing unnecessary intervention and work interruption.

[0085] Embodiment 4

[0086] Figure 5 This is a schematic diagram of the structure of a monitoring device for drilling conditions provided in Example 4 of the present application. Figure 5As shown, the device comprises:

[0087] A first trend determination module 410 is used to input the time series data acquired from the target well in the target time period into a pre-trained time series autoencoder model, reconstruct the time series data, determine reconstructed data corresponding to the time series data, and determine a first trend of the time series data based on the reconstructed data;

[0088] A second trend determination module 420 is used to fit each acquisition time node within the target time period and the time series data corresponding to each acquisition time node, determine a fitting result of the time series data, and determine a second trend of the time series data based on the fitting result;

[0089] The operating state determination module 430 is used to determine the operating state of the target well according to the first trend and the second trend.

[0090] The embodiment of the present invention provides a monitoring device for drilling conditions, which reconstructs the time series data by inputting the time series data acquired by the target well in the target time period into a pre-trained time series autoencoder model, determines the reconstructed data corresponding to the time series data, and determines the first trend of the time series data based on the reconstructed data; fits each acquisition time node in the target time period and the time series data corresponding to each acquisition time node, determines the fitting result of the time series data, and determines the second trend of the time series data based on the fitting result; determines the working state of the target well according to the first trend and the second trend. This technical solution realizes real-time and accurate monitoring of drilling conditions by reconstructing and fitting the time series data respectively, thereby improving the safety and production efficiency of the drilling process.

[0091] Furthermore, the operating state determination module 430 includes:

[0092] an abnormal operating condition trend comparison unit, configured to determine a first comparison result between the first trend and a preset abnormal operating condition trend, and to determine a second comparison result between the second trend and a preset abnormal operating condition trend;

[0093] A working condition determination unit is used to determine the working condition of the target well according to the first comparison result and the second comparison result.

[0094] Furthermore, the operating state determination unit includes:

[0095] a reconstruction error determination subunit, configured to determine, if both the first comparison result and the second comparison result are consistent, a reconstruction error corresponding to each of the time series data according to the reconstructed data and the time series data;

[0096] The operating state determination subunit is used to determine the operating state of the target well according to the reconstruction error and a preset error threshold.

[0097] Furthermore, the first trend determination module 410 includes:

[0098] A reconstruction error determination unit, configured to determine a reconstruction error corresponding to each of the time series data according to the reconstructed data and the time series data;

[0099] The first trend determining unit is used to determine a first trend of the time series data according to the reconstruction error.

[0100] Furthermore, the device also includes:

[0101] an operating time period determination module, configured to determine an operating time period in which the target well is in an operating condition according to the operating data of the target well after determining the operating condition of the target well according to the first trend and the second trend;

[0102] The operating state correction module is used to correct the operating state according to the target time period and the operation time period, and determine the corrected operating state of the target well.

[0103] Furthermore, the device also includes:

[0104] The operating condition trend acquisition module is used to acquire the operating condition trend of the time series data corresponding to the operating condition before determining the operating time period of the target well according to the operating data of the target well.

[0105] Furthermore, the operating state correction module includes:

[0106] an operating condition trend comparison unit, configured to determine a third comparison result between the first trend and the operating condition trend, and determine a fourth comparison result between the second trend and the operating condition trend, if the target time period is within the operating time period;

[0107] A working condition correction unit is used to correct the working condition according to the third comparison result and the fourth comparison result, and determine the working condition correction state of the target well.

[0108] A drilling condition monitoring device provided in an embodiment of the present application can execute a drilling condition monitoring method provided in any embodiment of the present application, and has functional modules and beneficial effects corresponding to the execution method.

[0109] Embodiment 5

[0110] Figure 6A schematic diagram of a device 10 that can be used to implement an embodiment of the present application is shown. The device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0111] like Figure 6 As shown, the device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0112] A number of components in the device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0113] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for monitoring drilling conditions.

[0114] In some embodiments, the method for monitoring drilling conditions may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for monitoring drilling conditions described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for monitoring drilling conditions in any other appropriate manner (e.g., by means of firmware).

[0115] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0116] The computer programs for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer programs are executed by the processor, the functions / operations specified in the flow charts and / or block diagrams are implemented. The computer programs may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0117] In the context of the present application, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device or equipment. A computer readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. A more specific example of a machine readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0118] To provide interaction with a user, the systems and techniques described herein can be implemented on a device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0119] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0120] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0121] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution of this application can be achieved, and this document is not limited here.

[0122] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for monitoring drilling conditions, characterized in that: The method comprises: Inputting the time series data acquired from the target well in the target time period into a pre-trained time series autoencoder model, reconstructing the time series data, determining reconstructed data corresponding to the time series data, and determining a first trend of the time series data based on the reconstructed data; Fitting each acquisition time node within the target time period and the time series data corresponding to each acquisition time node, determining a fitting result of the time series data, and determining a second trend of the time series data based on the fitting result; Determining the operating state of the target well according to the first trend and the second trend; Wherein, determining the operating state of the target well according to the first trend and the second trend includes: Determine a first comparison result between the first trend and a preset abnormal operating condition trend, and determine a second comparison result between the second trend and a preset abnormal operating condition trend; Determining the operating state of the target well according to the first comparison result and the second comparison result; Wherein, determining the first trend of the time series data based on the reconstructed data includes: Determining a reconstruction error corresponding to each of the time series data according to the reconstructed data and the time series data; A first trend of the time series data is determined based on the reconstruction error.

2. The method according to claim 1, characterized in that Determining the operating state of the target well according to the first comparison result and the second comparison result includes: If the first comparison result and the second comparison result are both consistent, determining a reconstruction error corresponding to each of the time series data according to the reconstructed data and the time series data; The operating state of the target well is determined according to the reconstruction error and a preset error threshold.

3. The method according to claim 1, characterized in that After determining the operating state of the target well according to the first trend and the second trend, the method further includes: Determining, based on the operation data of the target well, an operation time period in which the target well is in an operation condition; The operating state is corrected according to the target time period and the operating time period to determine the corrected operating state of the target well.

4. The method according to claim 3, characterized in that Before determining the operation time period of the target well according to the operation data of the target well, the method further includes: An operating condition trend of the time series data corresponding to the operating condition is obtained.

5. The method according to claim 4, characterized in that Correcting the operating state according to the target time period and the operating time period to determine the corrected operating state of the target well includes: If the target time period is within the operating time period, determining a third comparison result between the first trend and the operating condition trend, and determining a fourth comparison result between the second trend and the operating condition trend; The operating state is corrected according to the third comparison result and the fourth comparison result, and the corrected operating state of the target well is determined.

6. A drilling condition monitoring device, characterized in that: The device comprises: A first trend determination module, configured to input the time series data acquired from the target well in the target time period into a pre-trained time series autoencoder model, reconstruct the time series data, determine reconstructed data corresponding to the time series data, and determine a first trend of the time series data based on the reconstructed data; A second trend determination module is used to fit each acquisition time node within the target time period and the time series data corresponding to each acquisition time node, determine the fitting result of the time series data, and determine the second trend of the time series data based on the fitting result; A working state determination module, used for determining the working state of the target well according to the first trend and the second trend; Wherein, the operating state determination module includes: an abnormal operating condition trend comparison unit, configured to determine a first comparison result between the first trend and a preset abnormal operating condition trend, and to determine a second comparison result between the second trend and a preset abnormal operating condition trend; an operating state determining unit, configured to determine the operating state of the target well according to the first comparison result and the second comparison result; Wherein, the first trend determination module includes: A reconstruction error determination unit, configured to determine a reconstruction error corresponding to each of the time series data according to the reconstructed data and the time series data; The first trend determining unit is used to determine a first trend of the time series data according to the reconstruction error.

7. An electronic device, characterized in that: The device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for monitoring drilling conditions according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for monitoring drilling conditions according to any one of claims 1-5 when executed.

Images