Drill bit working state monitoring method and device, electronic equipment and storage medium

Abstract

The application discloses a drill bit working state monitoring method and device, electronic equipment and a storage medium. The method comprises the following steps: obtaining at least two types of drill bit drilling data; inputting each drill bit drilling data into a pre-trained drill bit life monitoring model and a drill bit accident risk prediction model to obtain a drill bit life index output by the drill bit life monitoring model and an accident risk index output by the drill bit accident risk prediction model; and monitoring the drill bit working state according to the drill bit life index and the accident risk index. The technical scheme of the application can realize real-time monitoring of the drill bit working state, accurately locate the remaining life of the drill bit, early identify the safety risk of the drill bit, and improve the use efficiency of the drill bit.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oil drilling, and in particular to a drilling bit working state monitoring method and device, an electronic device, and a storage medium. BACKGROUND

[0002] With the development of oil drilling technology, the number of completed wells is increasing year by year, and the cost of drilling bits is increasing. In actual drilling operations, the working state of the drilling bit is mainly evaluated by two factors: the rated working time calibrated when the drilling bit is shipped, and the drilling time change trend and torque change during actual drilling. However, in actual drilling operations, there are still problems such as the incomplete performance of some drilling bits, the good degree of new drilling bits after being taken out of the well, and the increase in drilling bit cost, and the secondary engineering complexity or accidents caused by overuse of some drilling bits. For example, there are cases of drilling bit tooth loss, PDC (Polycrystalline Diamond Compact bit) bit wing loss, and roller bit roller loss, which delay the drilling operation cycle and increase the drilling cost. Therefore, there is an urgent need for a drilling bit working state real-time monitoring method to remotely evaluate the working state of the drilling bit in real time. SUMMARY

[0003] The present application provides a drilling bit working state monitoring method, device, electronic device, and storage medium to realize real-time monitoring of the working state of the drilling bit, accurately locate the remaining life of the drilling bit, early identify the safety risk of the drilling bit, and improve the use efficiency of the drilling bit.

[0004] In a first aspect, the present application provides a drilling bit working state monitoring method, which comprises:

[0005] obtaining drilling data of at least two types of drilling bits;

[0006] inputting the drilling data of each drilling bit into a pre-trained drilling bit life monitoring model and a drilling bit accident risk prediction model to obtain a drilling bit life index output by the drilling bit life monitoring model and an accident risk index output by the drilling bit accident risk prediction model;

[0007] monitoring the working state of the drilling bit according to the drilling bit life index and the accident risk index.

[0008] In a second aspect, the present application also provides a drilling bit working state monitoring device, which comprises:

[0009] a drilling bit drilling data acquisition module configured to obtain drilling data of at least two types of drilling bits;

[0010] a model prediction module, configured to input each drill bit drilling data into a pre-trained drill bit life monitoring model and a drill bit accident risk prediction model to obtain a drill bit life index output by the drill bit life monitoring model and an accident risk index output by the drill bit accident risk prediction model;

[0011] a drill bit working state monitoring module, configured to monitor the drill bit working state according to the drill bit life index and the accident risk index.

[0012] In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the drill bit working state monitoring method according to any of the embodiments of the present application when executing the program.

[0013] In a fourth aspect, a storage medium storing computer executable instructions is provided, and the computer executable instructions are used to execute the drill bit working state monitoring method according to any of the embodiments of the present application when executed by a computer processor.

[0014] The technical scheme of the embodiments of the present application, by collecting real-time drilling data of a drill bit, inputting each drill bit drilling data into a pre-trained drill bit life monitoring model and a drill bit accident risk prediction model to obtain a drill bit life index output by the drill bit life monitoring model and an accident risk index output by the drill bit accident risk prediction model, and monitoring the drill bit working state according to the drill bit life index and the accident risk index, solves the problem that the existing technology uses the rated working time of the drill bit when leaving the factory and the drilling time change trend and the torque change during actual drilling to monitor the drill bit working state, which is prone to the problems of not fully utilizing the efficiency of the drill bit or causing drill bit accidents due to overuse of the drill bit, realizes real-time monitoring of the drill bit working state, can accurately locate the remaining life of the drill bit, early identifies the safety risk of the drill bit, and improves the use efficiency of the drill bit.

[0015] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0017] Figure 1This is a flow chart of a method for monitoring the working status of a drill bit provided in Example 1 of the present invention;

[0018] Figure 2 This is a flow chart of a method for monitoring the working status of a drill bit provided in the second embodiment of the present invention;

[0019] Figure 3 1 is a schematic structural diagram of a device for monitoring the working status of a drill bit provided in a third embodiment of the present invention;

[0020] Figure 4 This is a structural diagram of an electronic device provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention 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 numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof 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 clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] Example 1

[0024] Figure 1 A flowchart of a method for monitoring the working status of a drill bit is provided for the first embodiment of the present invention. This embodiment is applicable to situations where the working status of a drill bit is monitored during drilling operations. The method can be performed by a device for monitoring the working status of a drill bit. The device for monitoring the working status of a drill bit can be implemented in the form of hardware and / or software, and the device for monitoring the working status of a drill bit can be configured in an electronic device.

[0025] like Figure 1 As shown, the method includes:

[0026] S110, obtain at least two types of drill bit drilling data.

[0027] The drill bit drilling data is related data of drill bit drilling obtained in real time in a drilling operation. The types of drill bit drilling data include at least two of the following: drilling time, drilling pressure, torque, displacement, standpipe pressure, drilling fluid density, and drilling fluid viscosity.

[0028] In this embodiment, the specific types of drill bit drilling data can be determined according to the types of training data used when training the drill bit life monitoring model and the drill bit accident risk prediction model, and the specific types of drill bit drilling data and the number of different types are not limited in this embodiment.

[0029] In this embodiment, real-time drilling data of the drill bit is obtained to evaluate the working state of the drill bit in real time, so that the drill bit accident risk can be identified in time, thereby ensuring the safety of drilling.

[0030] S120, input each drill bit drilling data into the drill bit life monitoring model and the drill bit accident risk prediction model trained in advance to obtain a drill bit life index output by the drill bit life monitoring model and an accident risk index output by the drill bit accident risk prediction model.

[0031] The drill bit life monitoring model and the drill bit accident risk prediction model can be obtained by training a pre-set machine learning model. The types of machine learning models can include K-neighbors, Bayesian, logistic regression, decision tree, vector machine, neural network, etc. The types of machine learning models are not limited in this embodiment.

[0032] In this embodiment, the machine learning types of the drill bit life monitoring model and the drill bit accident risk prediction model can be the same or different, and the types of training data required for training the drill bit life monitoring model and the drill bit accident risk prediction model can be the same or different. For example, the related data of drilling time, standpipe pressure, torque, displacement, and rotary table speed in historical drill bit drilling data can be used as training data to train a neural network model to obtain a drill bit life monitoring model. The related data of drilling time, drilling pressure, torque, displacement, standpipe pressure, drilling fluid density, and drilling fluid viscosity in historical drill bit drilling data can be used as training data to train a logistic regression model to obtain a drill bit accident risk prediction model.

[0033] In the embodiment, the drill bit life monitoring model obtains a prediction result of the drill bit life, i.e., a drill bit life index, according to the input drill bit drilling data. The drill bit life index is used to measure the new degree and the remaining life of the drill bit, and can be set to be higher, the new degree of the drill bit is higher, and the remaining life is longer. The drill bit life index can be represented by a percentage, a decimal, etc. For example, the drill bit life index output by the drill bit life monitoring model can be 92.45%. The drill bit accident risk prediction model obtains a prediction result of the drill bit accident risk, i.e., an accident risk index, according to the input drill bit drilling data. The accident risk index is used to measure the probability of the drill bit safety accident, and can be set to be higher, the probability of the drill bit safety accident is higher, and the risk is greater. Similarly, the accident risk index can be represented by a percentage, a decimal, etc.

[0034] The drill bit life monitoring model and the drill bit accident risk prediction model are used to predict the life of the drill bit and the drill bit accident risk, respectively, and the drill bit life index and the accident risk index are comprehensively used to more accurately and comprehensively monitor the working state of the drill bit.

[0035] S130, according to the drill bit life index and the accident risk index, the working state of the drill bit is monitored.

[0036] In the embodiment, the drill bit drilling data can be collected in real time, and the drill bit life index and the accident risk index can be obtained in real time through the drill bit life monitoring model and the drill bit accident risk prediction model, so that the working state of the drill bit is monitored in real time. Specifically, whether the drill bit is in a normal drilling condition can be determined according to the fluctuation of the drill bit life index, and the drill bit parameters such as standpipe pressure, torque and rotating speed are adjusted. Whether there is a risk of drill bit safety accident can be determined according to the size of the accident risk index, and drill bit accident warning is performed in time.

[0037] Further, S130 can further include:

[0038] A1, if it is determined that the accident risk index is greater than or equal to a preset risk index threshold, a drill bit accident risk prompt is performed.

[0039] The preset risk index threshold is a preset value, and when the accident risk index is set to be higher, the probability of the drill bit safety accident is higher, the preset risk index threshold can be set to 20%, for example. When the accident risk index output by the drill bit accident risk prediction model is greater than or equal to 20%, it is considered that the risk of the drill bit safety accident is high at this time, and the drill bit accident risk prompt is performed. Specifically, the drill bit accident risk prompt can be performed in one or more of the following ways: a risk prompt is performed on a user interaction interface; an opening instruction is sent to an alarm lamp to make the alarm lamp flash; an opening instruction is sent to an alarm sound to make the alarm sound play a prompt sound; a risk prompt message is sent to a terminal device bound to the drill bit working state monitoring system, and the like. The specific implementation of the drill bit accident risk prompt is not limited in the embodiment.

[0040] A2, if it is determined that the accident risk index is less than the preset risk index threshold, the drill bit tripping time is determined according to the drill bit life index and the drill bit rated data.

[0041] The drill bit tripping time refers to the time when the drill bit is tripped out of the wellhead, and the drill bit rated data can include the rated drilling pressure, the rated working time, and the like. In the embodiment, the drill bit tripping time is determined according to the drill bit life index and the drill bit rated data. Specifically, when the accident risk index is less than the preset risk index threshold, the drill bit life index can be continuously monitored, and the drill bit life index threshold can be set in advance. For example, the drill bit life index threshold can be set to 5%, and the drill bit tripping time is determined by comprehensively considering the rated working time of the drill bit and the drill bit life index. The specific way of determining the drill bit tripping time according to the drill bit life index and the drill bit rated data is not limited in the embodiment.

[0042] In the embodiment, the drill bit tripping time is reasonably arranged, which can maximize the performance of the drill bit while avoiding the drill bit accident, thereby saving the drill bit cost and ensuring the drilling speed.

[0043] The technical scheme of the embodiment of the present application collects the real-time drilling data of the drill bit, inputs the drilling data of each drill bit into the drill bit life monitoring model and the drill bit accident risk prediction model which are obtained by pre-training, obtains the drill bit life index output by the drill bit life monitoring model and the accident risk index output by the drill bit accident risk prediction model, and monitors the working state of the drill bit according to the drill bit life index and the accident risk index. The way of monitoring the working state of the drill bit according to the rated working time of the drill bit when it leaves the factory and the drilling time change trend and the torque change during actual drilling in the prior art is prone to the problems that the drill bit does not fully exert its performance or the drill bit accident is caused by overuse of the drill bit. The real-time monitoring of the working state of the drill bit is realized, the remaining life of the drill bit can be accurately positioned, the safety risk of the drill bit can be identified early, and the use efficiency of the drill bit is improved.

[0044] Embodiment Two

[0045] Figure 2 A flowchart of a drill bit working state monitoring method provided for Embodiment Two of the present application, the present embodiment further specifies the training process of the drill bit life monitoring model and the drill bit accident risk prediction model, and the process of monitoring the drill bit working state according to the drill bit life index and the accident risk index on the basis of the above-mentioned embodiments.

[0046] As shown in Figure 2 , the method comprises:

[0047] S210, historical drill bit drilling data under drill bit drilling conditions and historical drill bit drilling data under drill bit accident conditions are determined.

[0048] The drill bit drilling conditions refer to the conditions under which the drill bit performs normal drilling operation, and the drill bit accident conditions refer to the conditions under which the drill bit has a safety accident, which can include the conditions such as the roller bit dropping a roller, the PDC bit breaking a blade, and the PDC bit dropping a tooth.

[0049] In the present embodiment, in order to make the robustness of the trained drill bit life monitoring model and drill bit accident risk prediction model better and the accuracy higher, when selecting the training data, the historical drill bit drilling data under drill bit drilling conditions and the historical drill bit drilling data under drill bit accident conditions are respectively determined, and as many different formations, different lithologies, different well types, different pressure systems, different drilling fluid systems, and different drilling parameters as possible are covered. At the same time, the historical drill bit drilling data under drill bit accident conditions are marked with drill bit accident types, and each historical drill bit drilling data is marked with drill bit life. Specifically, the drill bit life corresponding to the historical drill bit drilling data under drill bit accident conditions can be determined according to the running-in time and the accident time, and the drill bit life corresponding to the historical drill bit drilling data under drill bit drilling conditions can be obtained according to the running-in time, the tripping-out time, and the new or old degree of the drill bit evaluated at the tripping-out time.

[0050] Further, after the historical drill bit drilling data under drill bit drilling conditions and the historical drill bit drilling data under drill bit accident conditions are collected, each historical drill bit drilling data is preprocessed. Specifically, the data preprocessing can include data file format unification, data unit unification, data denoising, missing data completion, error data correction, etc., and the present embodiment does not limit the types and specific ways of data preprocessing.

[0051] S220, a pre-set machine learning model is trained according to the historical drill bit drilling data under drill bit drilling conditions, the historical drill bit drilling data under drill bit accident conditions, and the historical drill bit life corresponding to each historical drill bit drilling data, to obtain a drill bit life monitoring model.

[0052] Specifically, each historical bit drilling data and its corresponding historical bit life can be divided into a training set and a test set. The pre-set machine learning model is trained through the training set, and the model is continuously iteratively fitted and algorithm parameter optimized. The machine learning model is tested through the test set. The model accuracy is determined by comparing the predicted value of the bit life of the historical bit drilling data of the machine learning model with the actual historical bit life. The model is iteratively trained until the model accuracy or the number of iterations meets the model training requirements, and the bit life monitoring model is obtained.

[0053] Further, S220 can be implemented through the following steps:

[0054] B1. According to the correlation between different types of historical bit drilling data and the correlation between each type of historical bit drilling data and historical bit life, a first historical bit drilling data set is determined from each type of historical bit drilling data.

[0055] B2. According to the first historical bit drilling data set and the historical bit life corresponding to each historical bit drilling data in the first historical bit drilling data set, the pre-set machine learning model is trained to obtain the bit life monitoring model.

[0056] Specifically, for each type of historical bit drilling data, such as drilling time, drilling pressure, torque, displacement, standpipe pressure, drilling fluid density, and drilling fluid viscosity, its skewness, kurtosis, and value range are extracted, and the correlation between different types of historical bit drilling data and the correlation between different types of historical bit drilling data and historical bit life are determined. The correlation and correlation can be analyzed by using SPSS or other data analysis tools, which is not limited in the present embodiment.

[0057] Further, for different types of historical bit drilling data with high correlation, feature merging can be performed. For each type of historical bit drilling data after feature merging, a pre-set number of types of historical bit drilling data with high correlation with historical bit life are selected, or types of historical bit drilling data with correlation exceeding a pre-set correlation threshold are selected to determine the first historical bit drilling data set. For example, drilling time, drilling pressure, rotational speed, displacement, and torque can be added to the first historical bit drilling data set.

[0058] In the present embodiment, by analyzing the correlation and correlation of different types of historical bit drilling data, the number of features required by the trained model can be reduced, thereby reducing the order of magnitude of the bit drilling data input into the model and improving the prediction speed of the model.

[0059] Further, B2 can further include:

[0060] B21, training at least two machine learning models pre-set to obtain at least two candidate drill bit life monitoring models.

[0061] B22, in each candidate drill bit life monitoring model, determining a target drill bit life monitoring model.

[0062] Specifically, the types of machine learning models can include K-nearest neighbor, Bayesian, logistic regression, decision tree, vector machine, neural network, etc. In the embodiment, after determining the first historical drill bit drilling data set for performing the drill bit life monitoring model, different types of machine learning models are trained according to the first historical drill bit drilling data set, and in each candidate drill bit life monitoring model obtained by training, a final drill bit life monitoring model is selected. Specifically, the selection of the target drill bit life monitoring model can be based on factors such as model accuracy and prediction speed.

[0063] S230, training a machine learning model pre-set according to historical drill bit drilling data under drill bit drilling conditions, historical drill bit drilling data under drill bit accident conditions, and drill bit accident types corresponding to each historical drill bit drilling data under drill bit accident conditions, to obtain a drill bit accident risk prediction model.

[0064] Similarly, each historical drill bit drilling data and its corresponding drill bit accident type can be divided into a training set and a test set. The machine learning model pre-set is trained through the training set, and the model is continuously iteratively fitted and algorithm parameter optimized. The machine learning model is tested through the test set, the drill bit accident risk prediction value of the historical drill bit drilling data by the machine learning model is compared with the actual drill bit accident type under the drill bit accident condition, the model accuracy is determined, and the iteration is trained until the model accuracy or the iteration number meets the model training requirement, to obtain the drill bit accident risk prediction model.

[0065] Further, S230 can further include:

[0066] C1, according to the relevance between different types of historical drill bit drilling data and the correlation between each type of historical drill bit drilling data and the drill bit accident type, determining a second historical drill bit drilling data set in each type of historical drill bit drilling data.

[0067] C2, training a machine learning model pre-set according to the second historical drill bit drilling data set and the drill bit accident types corresponding to each historical drill bit drilling data under drill bit accident conditions in the second historical drill bit drilling data set, to obtain a drill bit accident risk prediction model.

[0068] Similarly, for each type of historical bit drilling data, the skewness, kurtosis, and value range are extracted, the correlation between different types of historical bit drilling data is determined, and the correlation between different types of historical bit drilling data and historical bit life is determined. For different types of historical bit drilling data with high correlation, feature merging can be performed. For each type of historical bit drilling data after feature merging, a preset number of types of historical bit drilling data with high correlation with bit accidents are selected, or types of historical bit drilling data with correlation exceeding a preset correlation threshold are selected, to determine a second historical bit drilling data set. The second historical bit drilling data set can be the same as or different from the first historical bit drilling data set.

[0069] Further, C2 can further include:

[0070] C21, training at least two machine learning models to obtain at least two candidate bit accident risk prediction models.

[0071] C22, determining a target bit accident risk prediction model from the candidate bit accident risk prediction models.

[0072] Similarly, different types of machine learning models are trained according to the second historical bit drilling data set, and a final bit accident risk prediction model is selected from the trained candidate bit accident risk prediction models. Specifically, the target bit accident risk prediction model can be selected according to model accuracy, prediction speed, and other factors.

[0073] S240, obtaining at least two types of bit drilling data.

[0074] S250, inputting each bit drilling data into a pre-trained bit life monitoring model and a bit accident risk prediction model to obtain a bit life index output by the bit life monitoring model and an accident risk index output by the bit accident risk prediction model.

[0075] S260, determining whether the accident risk index is greater than or equal to a preset risk index threshold, if yes, performing S270, otherwise performing S280.

[0076] S270, performing bit accident risk prompting.

[0077] S280, determining a bit tripping time according to the bit life index and bit rated data.

[0078] After the drill bit life monitoring model and the drill bit accident risk prediction model are trained, drill bit drilling data are collected in real time, and the drill bit drilling data are input into the drill bit life monitoring model and the drill bit accident risk prediction model respectively to obtain a drill bit life index and an accident risk index, and the drill bit state monitoring is performed in the manner described in the above embodiment, which will not be repeated here.

[0079] The technical scheme of the embodiment of the present application realizes real-time monitoring of the working state of the drill bit of different types, different models, different coefficients, different formations, different lithology, different well types, different pressure systems, different drilling fluid systems and different drilling parameters, improves the robustness of drill bit detection, determines the historical drill bit drilling data for training the drill bit life monitoring model and the historical drill bit drilling data for training the drill bit accident risk prediction model according to the correlation between different types of historical drill bit drilling data and the correlation between different types of historical drill bit drilling data and drill bit life and drill bit accidents, improves the model accuracy and prediction speed, trains a plurality of types of machine learning models according to the training data respectively, selects the optimal model as the final drill bit life monitoring model and drill bit accident risk prediction model, and further improves the model accuracy. According to the drill bit life monitoring model and the drill bit accident risk prediction model thus trained, the drill bit life index and the accident risk index are predicted, and the working state of the drill bit is monitored, which can accurately locate the remaining life of the drill bit, identify the safety risk of the drill bit early, and improve the use efficiency of the drill bit.

[0080] Embodiment three

[0081] Figure 3 A structural schematic diagram of a drill bit working state monitoring device provided by the third embodiment of the present application is shown in FIG. 3. Figure 3 As shown in FIG. 3, the device includes:

[0082] A drill bit drilling data acquisition module 310 is configured to acquire at least two types of drill bit drilling data.

[0083] A model prediction module 320 is configured to input each drill bit drilling data into a drill bit life monitoring model and a drill bit accident risk prediction model pre-trained to obtain a drill bit life index output by the drill bit life monitoring model and an accident risk index output by the drill bit accident risk prediction model.

[0084] A drill bit working state monitoring module 330 is configured to monitor the working state of the drill bit according to the drill bit life index and the accident risk index.

[0085] The technical scheme of the embodiment of the present application comprises the following steps: collecting real-time drilling data of a drill bit, inputting the drilling data of each drill bit into a drill bit life monitoring model and a drill bit accident risk prediction model which are obtained by pre-training, obtaining a drill bit life index output by the drill bit life monitoring model and an accident risk index output by the drill bit accident risk prediction model, and monitoring the working state of the drill bit according to the drill bit life index and the accident risk index. The present application solves the problem in the prior art that the working state of the drill bit is monitored according to the rated working time of the drill bit when it is delivered from the factory and the drilling time change trend and torque change condition during actual drilling, and the drill bit is not fully efficient or the drill bit is overused to cause a drill bit accident, and the present application realizes real-time monitoring of the working state of the drill bit, can accurately locate the remaining life of the drill bit, early identifies the safety risk of the drill bit, and improves the use efficiency of the drill bit.

[0086] On the basis of the above embodiment, the device further comprises:

[0087] The historical drill bit drilling data determination module is configured to determine historical drill bit drilling data under a drill bit drilling condition and historical drill bit drilling data under a drill bit accident condition.

[0088] The drill bit life monitoring model training module is configured to train a pre-set machine learning model according to the historical drill bit drilling data under the drill bit drilling condition, the historical drill bit drilling data under the drill bit accident condition, and historical drill bit lives corresponding to the historical drill bit drilling data, to obtain the drill bit life monitoring model.

[0089] The drill bit accident risk prediction model training module is configured to train a pre-set machine learning model according to the historical drill bit drilling data under the drill bit drilling condition, the historical drill bit drilling data under the drill bit accident condition, and drill bit accident types corresponding to the historical drill bit drilling data under the drill bit accident condition, to obtain the drill bit accident risk prediction model.

[0090] On the basis of the above embodiment, the drill bit life monitoring model training module comprises:

[0091] The first historical drill bit drilling data set determination unit is configured to determine a first historical drill bit drilling data set from the historical drill bit drilling data of different types according to the correlation between the historical drill bit drilling data of different types and the correlation between the historical drill bit drilling data of each type and the historical drill bit life.

[0092] The drill bit life monitoring model training unit is configured to train a pre-set machine learning model according to the first historical drill bit drilling data set and the historical drill bit life corresponding to each historical drill bit drilling data in the first historical drill bit drilling data set, to obtain the drill bit life monitoring model.

[0093] The drill bit accident risk prediction model training module comprises:

[0094] The second historical bit drilling data set determination unit is configured to determine a second historical bit drilling data set from different types of historical bit drilling data according to correlations between the different types of historical bit drilling data and correlations between the different types of historical bit drilling data and bit accident types.

[0095] The bit accident risk prediction model training unit is configured to train a pre-set machine learning model according to the second historical bit drilling data set and bit accident types corresponding to historical bit drilling data under bit accident working conditions in the second historical bit drilling data set, to obtain a bit accident risk prediction model.

[0096] On the basis of the above embodiment, the bit life monitoring model training unit is specifically configured to:

[0097] train at least two pre-set machine learning models to obtain at least two candidate bit life monitoring models;

[0098] determine a target bit life monitoring model from the at least two candidate bit life monitoring models.

[0099] The bit accident risk prediction model training unit is specifically configured to:

[0100] train at least two pre-set machine learning models to obtain at least two candidate bit accident risk prediction models;

[0101] determine a target bit accident risk prediction model from the at least two candidate bit accident risk prediction models.

[0102] On the basis of the above embodiment, the types of the bit drilling data include at least two of drilling time, drilling pressure, torque, displacement, standpipe pressure, drilling fluid density, and drilling fluid viscosity.

[0103] On the basis of the above embodiment, the bit working state monitoring module 330 includes:

[0104] The accident risk prompting unit is configured to prompt a bit accident risk if the accident risk index is greater than or equal to a pre-set risk index threshold.

[0105] On the basis of the above embodiment, the bit working state monitoring module 330 includes:

[0106] The bit tripping time determination unit is configured to determine a bit tripping time according to the bit life index and bit rated data if the accident risk index is less than a pre-set risk index threshold.

[0107] The drill bit working state monitoring device provided by the embodiment of the present application can execute the drill bit working state monitoring method provided by any embodiment of the present application, has the function modules and beneficial effects corresponding to the execution method.

[0108] Embodiment four

[0109] Figure 4 A structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0110] As shown in Figure 4 The electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11, wherein the memory stores a computer program that can be executed by the at least one processor. The processor 11 can execute 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 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the 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.

[0111] A plurality of components in the electronic 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, a loudspeaker, etc.; a storage unit 18, such as a magnetic 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 electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0112] The processor 11 can be various general and / or special purpose processing components having 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 specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the drill bit working condition monitoring method.

[0113] In some embodiments, the drill bit working condition monitoring method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of the drill bit working condition monitoring method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the drill bit working condition monitoring method by any other suitable means, such as by means of firmware.

[0114] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0115] Computer programs used to implement the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed by the processor of the machine, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0116] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0117] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic 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 a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, 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, speech, or tactile input.

[0118] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can 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.

[0119] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can 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 large management difficulty and weak business scalability in traditional physical host and VPS service.

[0120] It should be understood that the various forms of flow shown above can be used to reorder, add or delete steps. For example, each step described in the present application can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which is not limited herein.

[0121] The above detailed description does not constitute a limitation on the scope of protection of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for monitoring the working status of a drill bit, characterized in that: include: obtaining at least two types of drill bit drilling data; Inputting the drilling data of each drill bit into a pre-trained drill bit life monitoring model and a drill bit accident risk prediction model to obtain a drill bit life index output by the drill bit life monitoring model and an accident risk index output by the drill bit accident risk prediction model; Monitoring the working status of the drill bit according to the drill bit life index and the accident risk index; The training process of the drill bit life monitoring model and the drill bit accident risk prediction model includes: Determine historical drill bit drilling data under a drill bit drilling condition and historical drill bit drilling data under a drill bit accident condition; Based on the historical drill bit drilling data under the drill bit drilling condition, the historical drill bit drilling data under the drill bit accident condition, and the historical drill bit life corresponding to each historical drill bit drilling data, the pre-set machine learning model is trained to obtain the drill bit life monitoring model, including: Determining a first historical drill bit drilling data set from each type of historical drill bit drilling data according to the correlation between different types of historical drill bit drilling data and the correlation between each type of historical drill bit drilling data and the historical drill bit life; Training a pre-set machine learning model based on the first historical drill bit drilling data set and the historical drill bit life corresponding to each historical drill bit drilling data in the first historical drill bit drilling data set to obtain a drill bit life monitoring model; Based on the historical drill bit drilling data under the drill bit drilling condition, the historical drill bit drilling data under the drill bit accident condition, and the drill bit accident type corresponding to each historical drill bit drilling data under the drill bit accident condition, a pre-set machine learning model is trained to obtain a drill bit accident risk prediction model, including: Determining a second historical drill bit drilling data set from each type of historical drill bit drilling data according to the correlation between different types of historical drill bit drilling data and the correlation between each type of historical drill bit drilling data and the type of drill bit accident; According to the second historical drill bit drilling data set and the drill bit accident types corresponding to each historical drill bit drilling data under the drill bit accident working condition in the second historical drill bit drilling data set, the pre-set machine learning model is trained to obtain a drill bit accident risk prediction model.

2. The method according to claim 1, characterized in that The pre-set machine learning model is trained to obtain a drill bit life monitoring model, including: Training at least two pre-set machine learning models to obtain at least two candidate drill bit life monitoring models; Determining a target drill bit life monitoring model among candidate drill bit life monitoring models; The pre-set machine learning model is trained to obtain a drill bit accident risk prediction model, including: Training at least two pre-set machine learning models to obtain at least two candidate drill bit accident risk prediction models; Among the candidate drill bit accident risk prediction models, a target drill bit accident risk prediction model is determined.

3. The method according to claim 1, characterized in that The types of the drill bit drilling data include at least two of the following: drilling time, bit weight, torque, displacement, standing pressure, drilling fluid density, and drilling fluid viscosity.

4. The method according to claim 1, wherein Monitoring the working status of the drill bit according to the drill bit life index and the accident risk index includes: If it is determined that the accident risk index is greater than or equal to the preset risk index threshold, a drill bit accident risk warning is issued.

5. The method according to claim 4, characterized in that Monitoring the working status of the drill bit according to the drill bit life index and the accident risk index further includes: If it is determined that the accident risk index is less than a preset risk index threshold, the drill bit start-up time is determined according to the drill bit life index and drill bit rated data.

6. A monitoring device for the working status of a drill bit, characterized in that: include: A drill bit drilling data acquisition module, used to acquire at least two types of drill bit drilling data; A model prediction module is used to input the drilling data of each drill bit into a pre-trained drill bit life monitoring model and a drill bit accident risk prediction model to obtain a drill bit life index output by the drill bit life monitoring model and an accident risk index output by the drill bit accident risk prediction model; a drill bit working status monitoring module, configured to monitor the working status of the drill bit according to the drill bit life index and the accident risk index; A historical drill bit drilling data determination module is used to determine the historical drill bit drilling data under the drill bit drilling working condition and the historical drill bit drilling data under the drill bit accident working condition; A drill bit life monitoring model training module is used to train a pre-set machine learning model based on historical drill bit drilling data under drill bit drilling conditions, historical drill bit drilling data under drill bit accident conditions, and historical drill bit life corresponding to each historical drill bit drilling data to obtain a drill bit life monitoring model; The drill bit life monitoring model training module includes: a first historical drill bit drilling data set determining unit, configured to determine a first historical drill bit drilling data set from each type of historical drill bit drilling data based on correlations between different types of historical drill bit drilling data and correlations between each type of historical drill bit drilling data and historical drill bit life; a drill bit life monitoring model training unit, configured to train a preset machine learning model based on the first historical drill bit drilling data set and the historical drill bit life corresponding to each historical drill bit drilling data in the first historical drill bit drilling data set to obtain a drill bit life monitoring model; A drill bit accident risk prediction model training module is used to train a pre-set machine learning model based on historical drill bit drilling data under drill bit drilling conditions, historical drill bit drilling data under drill bit accident conditions, and drill bit accident types corresponding to each historical drill bit drilling data under drill bit accident conditions to obtain a drill bit accident risk prediction model; The drill bit accident risk prediction model training module includes: a second historical drill bit drilling data set determining unit, configured to determine a second historical drill bit drilling data set from each type of historical drill bit drilling data based on correlations between different types of historical drill bit drilling data and correlations between each type of historical drill bit drilling data and a type of drill bit accident; The drill bit accident risk prediction model training unit is used to train a pre-set machine learning model based on the second historical drill bit drilling data set and the drill bit accident type corresponding to each historical drill bit drilling data under the drill bit accident working condition in the second historical drill bit drilling data set to obtain a drill bit accident risk prediction model.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for monitoring the working status of the drill bit as described in any one of claims 1 to 5 is implemented.

8. A storage medium storing computer executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, they are used to execute the method for monitoring the working status of a drill bit as described in any one of claims 1 to 5.

Images