Logging curve abnormal value detection method and device, electronic equipment and medium

Abstract

The invention discloses a logging curve abnormal value detection method and device, electronic equipment and a medium. The method comprises the following steps: acquiring logging curve data; detecting the logging curve data by using a predetermined time sequence auto-encoder to obtain the abnormal degree of the logging curve data; and determining an abnormal value from the logging curve data according to the abnormal degree. According to the technical scheme, the detection precision and efficiency of the abnormal value in the logging curve data are improved, the efficiency and reliability of the oil field exploration and production process are improved, and more accurate data support is provided for oil field management and decision making.

Description

Technical Field

[0001] The present invention relates to the technical field of petroleum exploration and development, and in particular to a method, device, electronic equipment and medium for detecting abnormal values ​​of a logging curve. Background Art

[0002] Mud logging data plays a critical role in oilfield exploration and production. This data includes parameters such as inlet and outlet flow rates, bit pressure, torque, displacement, inlet and outlet temperatures, and total pool volume. This data is not only used to monitor and predict key conditions such as drill bit life, drill penetration, kicks, and lost circulation, but also plays a vital role in oilfield operations and production decisions.

[0003] A key issue often encountered when processing mud logging data is the presence of outliers. Outliers can arise from a variety of reasons, including instrument failure, formation inhomogeneities, and changing environmental conditions. These outliers can severely disrupt data accuracy and usability, necessitating an efficient and accurate method to detect and address these anomalies. Currently, outlier handling typically requires extensive manual intervention or the use of traditional statistical methods.

[0004] However, these methods cannot accurately detect outliers in logging curve data and have low detection efficiency. Summary of the Invention

[0005] The present invention provides a method, device, electronic equipment and medium for detecting abnormal values ​​in logging curves, which improve the detection accuracy and efficiency of abnormal values ​​in logging curve data.

[0006] According to one aspect of the present invention, a method for detecting abnormal values ​​in a logging curve is provided, the method comprising:

[0007] Obtain logging curve data;

[0008] Using a predetermined time series autoencoder to detect the logging curve data, and obtain the abnormality degree of the logging curve data;

[0009] According to the abnormality degree, an abnormal value is determined from the logging curve data.

[0010] According to another aspect of the present invention, a device for detecting abnormal values ​​of a logging curve is provided, the device comprising:

[0011] A logging curve data acquisition module, used to acquire logging curve data;

[0012] an abnormality degree obtaining module, configured to detect the logging curve data using a predetermined time series autoencoder to obtain the abnormality degree of the logging curve data;

[0013] An abnormal value determination module is used to determine abnormal values ​​from the logging curve data according to the abnormality degree.

[0014] According to another aspect of the present invention, an electronic device is provided, comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the method for detecting abnormal values ​​in mud logging curves according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, 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 a method for detecting abnormal values ​​in a mud logging curve according to any embodiment of the present invention when executed.

[0019] The technical solution of the embodiments of the present invention acquires mud logging data and then uses a predetermined time-series autoencoder to detect the data, determining the degree of abnormality in the logging data. Based on the degree of abnormality, outliers are then identified from the logging data. This technical solution improves the accuracy and efficiency of detecting outliers in mud logging data, enhances the efficiency and reliability of oilfield exploration and production processes, and provides more accurate data support for oilfield management and decision-making.

[0020] 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 invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 This is a flow chart of a method for detecting abnormal values ​​in a logging curve according to the first embodiment of the present invention;

[0023] Figure 2 This is a schematic diagram of the cleaning and fusion processing of the logging curve data provided in Example 1 of the present application;

[0024] Figure 3 This is a schematic diagram of the mud logging curve data before smoothing provided in Example 1 of the present application;

[0025] Figure 4 This is a schematic diagram of the smoothed logging curve data provided in Example 1 of the present application;

[0026] Figure 5 This is a schematic diagram of the principal component analysis method provided in Example 1 of the present application;

[0027] Figure 6 This is another schematic diagram of the principal component analysis method provided in Example 1 of the present application;

[0028] Figure 7 This is a schematic diagram of the temporal autoencoder model structure provided in Example 1 of the present application;

[0029] Figure 8 This is a schematic diagram of the reconstruction error of abnormal logging data provided in Example 1 of the present application;

[0030] Figure 9 This is a schematic diagram of the overall process of logging parameter anomaly detection provided in Example 1 of the present application;

[0031] Figure 10 2 is a schematic structural diagram of a logging curve abnormal value detection device provided according to the second embodiment of the present invention;

[0032] Figure 11 The present invention is a schematic structural diagram of an electronic device for implementing a method for detecting abnormal values ​​in a mud logging curve according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] 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.

[0034] 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.

[0035] Example 1

[0036] Figure 1 This is a flowchart of a method for detecting abnormal values ​​in a logging curve according to the first embodiment of the present invention. This embodiment is applicable to the case of detecting and processing abnormal values ​​in logging curve data. The method can be performed by a logging curve abnormal value detection device. The logging curve abnormal value detection device can be implemented in the form of hardware and / or software. The logging curve abnormal value detection device can be configured in a device. For example, the device can be a background server or other device with communication and computing capabilities. Figure 1 As shown, the method includes:

[0037] S110: Obtaining logging curve data.

[0038] The logging curve data includes time-series measurement values ​​of multiple parameters, such as inlet and outlet flow rates, bit pressure, torque, displacement, inlet and outlet temperatures, etc.

[0039] In this solution, logging tools and sensors are installed in each well in the oil field, and logging curve data is acquired based on the logging tools or sensors. The acquired logging curve data is transmitted to a central data storage facility through a data acquisition system.

[0040] Optionally, after obtaining the logging curve data, the method further includes:

[0041] The logging curve data is preprocessed to obtain preprocessed logging curve data; wherein the preprocessing includes at least one of data cleaning, data interpolation, data smoothing, and data dimensionality reduction.

[0042] In this plan, Figure 2 This is a schematic diagram of the cleaning and fusion processing of the logging curve data provided in Example 1 of the present application. Figure 2As shown, data cleaning: Data cleaning is to detect and correct sensor errors or abnormal data points. This involves checking whether the data falls within a predetermined reasonable range, such as whether the temperature is within a reasonable range, whether the flow rate conforms to physical laws, etc. The detection and repair of outliers can be accomplished through various statistical and machine learning methods. Data interpolation: There are missing data, which may be due to sensor failure, communication problems or other reasons. Interpolation is used to fill any missing data. The interpolation method can be selected according to the nature of the data, such as linear interpolation, spline interpolation, or time series-based interpolation methods. Data smoothing: Data often contains noise and fluctuations, which will affect the accuracy of subsequent analysis. Data smoothing is to remove these noise and fluctuations by applying filtering techniques or averaging methods to obtain a smoother data curve. Data dimensionality reduction analysis: When processing large-scale data, dimensionality reduction analysis can help reduce the complexity of the data while retaining the most important information.

[0043] For example, Figure 3 This is a schematic diagram of the mud logging curve data before smoothing provided in Example 1 of the present application; Figure 4 This is a schematic diagram of the smoothed logging curve data provided in Example 1 of this application. Figure 3 and Figure 4 As shown in Figure 2, smoothing the logging curve data helps ensure the accuracy and availability of the data, while improving the quality and feasibility of subsequent analysis.

[0044] In this embodiment, Figure 5 This is a schematic diagram of the principal component analysis method provided in Example 1 of this application. Figure 6 This is another schematic diagram of the principal component analysis method provided in Example 1 of the present application. Figure 5 and Figure 6 As shown, principal component analysis (PCA) can be used to transform high-dimensional data into a lower-dimensional representation that is easier to visualize and analyze.

[0045] Preprocessing of logging curve data helps ensure the accuracy and usability of data, while improving the quality and feasibility of subsequent analysis.

[0046] S120 , detecting the logging curve data using a predetermined time series autoencoder to obtain the abnormality degree of the logging curve data.

[0047] In this example, a time series autoencoder is used to learn the intrinsic feature representations of mud logging data. This approach encodes the data into a low-dimensional representation and then attempts to reconstruct it into the original data, enabling the model to capture the data's key characteristics and temporal patterns. Through repeated adjustments and optimization of the model, the training process enables the time series autoencoder to develop a high sensitivity to normal data patterns, enabling it to more accurately identify outliers, thereby improving data quality and reliability.

[0048] The abnormality degree can be represented by a number. By using a time series autoencoder to detect the logging curve data, the abnormality degree of the logging curve data can be output.

[0049] Optionally, the determination process of the time series autoencoder includes:

[0050] Obtaining the logging curve data to be trained;

[0051] Performing logging curve data detection tasks based on the time series autoencoder to be trained;

[0052] The parameters of the time series autoencoder to be trained are adjusted according to the logging curve data detection task to obtain a time series autoencoder.

[0053] In this plan, Figure 7 This is a schematic diagram of the temporal autoencoder model structure provided in Example 1 of the present application. Figure 7 As shown in the figure, the time series autoencoder model is constructed by learning the patterns and features of normal logging curve data, and the training process improves the model through multiple iterations and optimizations.

[0054] Specifically, data preparation involves dividing the training log data into a training set and a validation set. The training set is used for model training, while the validation set is used for model performance evaluation. The data is normalized to ensure that different parameter scales do not affect model performance. Model selection involves selecting an appropriate time series autoencoder model architecture. Preferably, a bidirectional long short-term memory time series autoencoder (BiLSTM-AE) is used for the time series autoencoder.

[0055] In this scheme, the parameters of the time series autoencoder to be trained are adjusted through the logging curve data detection task, and an optimized time series autoencoder can be obtained.

[0056] By training the time series autoencoder, it can more accurately identify outliers in logging curve data, thereby improving data quality and reliability.

[0057] Optionally, adjusting the parameters of the time series autoencoder to be trained according to the logging curve data detection task to obtain the time series autoencoder includes:

[0058] Determining a loss function for the logging curve data detection task;

[0059] The parameters of the time series autoencoder to be trained are adjusted according to the loss function to obtain a time series autoencoder.

[0060] In this embodiment, an appropriate loss function is defined to measure the performance of the model. In a time series autoencoder, the mean square error (MSE) or other applicable loss function is used to measure the accuracy of the model's reconstruction of the data.

[0061] Furthermore, we need to select appropriate training algorithms and hyperparameters, such as learning rate, batch size, and number of training epochs. We need to use an iterative approach when training the model to continuously improve the model’s performance.

[0062] In this solution, the validation set is used to evaluate model performance using metrics such as root mean square error (RMSE) and mean absolute error (MAE). If the model performs poorly, fine-tuning the model architecture or hyperparameters is necessary. Through repeated training and validation, the time series autoencoder model is continuously optimized to ensure it effectively captures the key features and patterns of the mud logging data.

[0063] in:

[0064]

[0065]

[0066]

[0067] Among them, n represents the number of samples, y i Represents the i-th sample of the actual observation value, y i The value of the i-th sample predicted by the model.

[0068] Once the time series autoencoder is trained, it will be used to monitor mud log data streams in real time. The goal is to use the trained autoencoder to detect and identify potential anomalies. When mud log data enters the model, the autoencoder attempts to reconstruct these data points into a curve that conforms to normal data patterns. By comparing the differences between the original and reconstructed data, the autoencoder can assess the degree of anomaly for each data point.

[0069] By training the time series autoencoder, it can more accurately identify outliers in logging curve data, thereby improving data quality and reliability.

[0070] S130. Determine an abnormal value from the logging curve data according to the abnormality degree.

[0071] Further, Figure 8 This is a schematic diagram of the abnormal logging data reconstruction error provided in Example 1 of the present application. Figure 8As shown in Figure 1, when mud log data is input into the model, the time series autoencoder's task is to attempt to reconstruct the original data using its internally learned data representation. Normally, the model is able to reconstruct the data relatively accurately because it has already learned the patterns and characteristics of normal data. However, when the mud log data contains outliers, these outliers can cause the reconstruction error to increase significantly. Because the goal of the time series autoencoder is to minimize the reconstruction error, outliers are typically detected as data points that cause the reconstruction error to exceed a certain threshold. In this way, the time series autoencoder can automatically identify data points that do not conform to the normal pattern, achieving highly accurate outlier detection.

[0072] Optionally, determining an abnormal value from the logging curve data according to the abnormality degree includes:

[0073] If the abnormality level is greater than or equal to a preset threshold, the logging curve data is determined to be an abnormal value.

[0074] The preset threshold may be determined based on statistical analysis, historical data, or business needs.

[0075] In this scheme, if the degree of abnormality of a data point exceeds a predetermined threshold, the model will mark it as an outlier; if the degree of abnormality of a data point does not exceed the predetermined threshold, it will be marked as a normal value.

[0076] Specifically, Figure 9 This is a schematic diagram of the overall process of logging parameter anomaly detection provided in Example 1 of the present application. Figure 9 As shown in the figure, real-time monitoring: the logging curve data stream is continuously input into the trained time series autoencoder model. The model needs to process this data efficiently to perform outlier detection in real time. Reconstruction and comparison: the autoencoder reconstructs each data sample through the process of encoding and decoding. Then, the difference between the original data sample and the reconstructed data sample is calculated, usually measured using a loss function. This difference value reflects the degree of deviation between the data sample and the normal pattern. Threshold setting: a threshold for outlier detection is predefined. This threshold can be determined based on statistical analysis, historical data or business needs. When the difference value exceeds this threshold, the data sample is marked as an anomaly. Outlier marking: once a data sample is marked as an anomaly, the system can trigger an alarm, record the abnormal event or take other appropriate actions. This helps operators to promptly detect and respond to potential problems, thereby improving the reliability and safety of oilfield operations.

[0077] Furthermore, over time, the model may need to be regularly updated to adapt to new data patterns and changes. This can be achieved by periodically retraining the model or employing incremental learning techniques.

[0078] By adopting time series autoencoder technology, we better adapt to the characteristics of time series logging data, capture the evolving trends and patterns of the data, reduce the complexity of outlier processing, and provide a more reliable data foundation, thereby enhancing the accuracy and reliability of decision-making. By improving data quality, automating processing, and considering time series data, we can optimize oilfield operations, reduce production risks, improve production efficiency, and reduce resource waste, ultimately contributing to the sustainable development of the oil industry.

[0079] Optionally, after determining the outliers from the logging curve data, the method further includes:

[0080] The outliers are marked.

[0081] In this scenario, outliers are marked or annotated so that they can be considered in subsequent data analysis or modeling. Marking outliers helps track the frequency and nature of unusual events, leading to a better understanding of the characteristics of a dataset. Detecting outliers triggers alerts or notifies relevant personnel. This approach allows for timely action to address anomalies, thereby mitigating potential risks.

[0082] In this embodiment, upon detecting an outlier, the system takes appropriate action based on the specific situation. For example, if the outlier has a minor impact on data quality, it can be fixed or ignored. If the outlier may indicate a device failure or other significant issue, the system can generate an alert so that engineers and operations staff can take timely action.

[0083] Specifically, data repair: If the impact of detected outliers on data quality is minimal and the correct value of the outlier can be reasonably estimated, the system may choose to repair these outliers. Repair methods may include using interpolation techniques to estimate the outliers or applying smoothing methods to adjust the outliers to make them closer to the normal pattern. Alarm generation: When outliers are detected that may indicate equipment failure, dangerous conditions, or other important issues, the system should generate alarms. These alarms typically notify engineers and operations personnel so that they can quickly take necessary actions. This includes checking equipment status, scheduling maintenance, emergency shutdowns, or executing other necessary emergency procedures. Data logging and analysis: Outliers often contain important information about potential problems. Therefore, the system should log outliers for further analysis and investigation. This helps identify potential root causes to avoid similar problems in the future. Manual intervention: Complex anomalies may require manual intervention by engineers and operations personnel. Based on the data and system-generated alarms, they can take appropriate actions to resolve the problem and ensure that oilfield operations return to normal.

[0084] By introducing efficient outlier detection and processing methods, the quality and reliability of logging curve data are significantly improved. By automatically identifying and processing outliers, logging data can more accurately reflect formation characteristics and oilfield production, thereby increasing data credibility and providing a more solid foundation for decision-making.

[0085] The technical solution of the embodiment of the present invention obtains the logging curve data, and then uses a predetermined time series autoencoder to detect the logging curve data to obtain the degree of abnormality of the logging curve data, and determines the abnormal value from the logging curve data based on the degree of abnormality. By implementing this technical solution, the quality and reliability of the logging curve data are significantly improved. By automatically identifying and processing abnormal values, the logging data can more accurately reflect the formation characteristics and oil field production conditions, thereby improving the credibility of the data and providing a more solid foundation for decision-making. Allowing automatic detection and processing of abnormal values ​​reduces the need for manual intervention. This is particularly beneficial for processing large-scale logging data, which not only improves processing efficiency, but also reduces potential risks caused by human errors. Automated processing can also monitor data streams in real time to ensure that abnormal situations can be detected and processed in a timely manner.

[0086] Example 2

[0087] Figure 10 Schematic diagram of a device for detecting abnormal values ​​of a logging curve according to the second embodiment of the present invention. Figure 10 As shown, the device includes:

[0088] The logging curve data acquisition module 1010 is used to acquire logging curve data;

[0089] The abnormality degree obtaining module 1020 is used to detect the logging curve data using a predetermined time series autoencoder to obtain the abnormality degree of the logging curve data;

[0090] The outlier determination module 1030 is configured to determine an outlier from the logging curve data according to the degree of anomaly.

[0091] Optionally, the abnormality degree obtaining module 1020 includes:

[0092] The submodule for acquiring the logging curve data to be trained is used to acquire the logging curve data to be trained;

[0093] A logging curve data detection task execution submodule is used to execute the logging curve data detection task based on the time series autoencoder to be trained;

[0094] The time series autoencoder obtaining submodule is used to adjust the parameters of the time series autoencoder to be trained according to the logging curve data detection task to obtain the time series autoencoder.

[0095] Optionally, the temporal autoencoder obtains a submodule, specifically used for:

[0096] Determining a loss function for the logging curve data detection task;

[0097] The parameters of the time series autoencoder to be trained are adjusted according to the loss function to obtain a time series autoencoder.

[0098] Optionally, the outlier determination module 1030 is specifically configured to:

[0099] If the abnormality level is greater than or equal to a preset threshold, the logging curve data is determined to be an abnormal value.

[0100] Optionally, the device further includes:

[0101] The outlier marking module is used to mark the outlier.

[0102] Optionally, the device further includes:

[0103] A preprocessing module is used to preprocess the logging curve data to obtain preprocessed logging curve data; wherein the preprocessing includes at least one of data cleaning, data interpolation, data smoothing and data dimensionality reduction.

[0104] A logging curve outlier detection device provided by an embodiment of the present invention can execute a logging curve outlier detection method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects of the execution method.

[0105] Example 3

[0106] Figure 11 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic 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 invention described and / or claimed herein.

[0107] like Figure 11As shown, 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. The memory stores a computer program that can be executed by the at least one processor. 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 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0108] Multiple 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, speakers, 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 via a computer network such as the Internet and / or various telecommunication networks.

[0109] The processor 11 can be any general-purpose and / or specialized processing component 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 specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for detecting outliers in mud logging curves.

[0110] In some embodiments, a mud log outlier detection method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the mud log outlier detection method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to execute the mud log outlier detection method in any other suitable manner (e.g., via firmware).

[0111] Various embodiments of the systems and techniques described 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), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes 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.

[0112] Computer programs for implementing the methods of the present invention 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, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0113] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0114] To provide interaction with a user, the systems and techniques described herein 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 pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic 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).

[0115] The systems and techniques described herein can be implemented in a computing system that includes back-end 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 front-end components (e.g., a user computer with a graphical user interface or 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 back-end components, middleware components, 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.

[0116] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0117] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0118] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for detecting abnormal values ​​of a logging curve, characterized in that: include: Obtain logging curve data; Using a predetermined time series autoencoder to detect the logging curve data, and obtain the abnormality degree of the logging curve data; According to the abnormality degree, an abnormal value is determined from the logging curve data.

2. The method according to claim 1, characterized in that The determination process of the temporal autoencoder includes: Obtaining the logging curve data to be trained; Performing logging curve data detection tasks based on the time series autoencoder to be trained; The parameters of the time series autoencoder to be trained are adjusted according to the logging curve data detection task to obtain a time series autoencoder.

3. The method according to claim 2, characterized in that Adjusting the parameters of the time series autoencoder to be trained according to the logging curve data detection task to obtain the time series autoencoder includes: Determining a loss function for the logging curve data detection task; The parameters of the time series autoencoder to be trained are adjusted according to the loss function to obtain a time series autoencoder.

4. The method according to claim 1, wherein Determining an abnormal value from the logging curve data according to the abnormality degree includes: If the abnormality level is greater than or equal to a preset threshold, the logging curve data is determined to be an abnormal value.

5. The method according to claim 1, wherein After determining the outliers from the mud logging data, the method further includes: The outliers are marked.

6. The method according to claim 1, characterized in that After acquiring the logging curve data, the method further includes: The logging curve data is preprocessed to obtain preprocessed logging curve data; wherein the preprocessing includes at least one of data cleaning, data interpolation, data smoothing, and data dimensionality reduction.

7. A device for detecting abnormal values ​​of a logging curve, characterized in that: include: A logging curve data acquisition module, used to acquire logging curve data; an abnormality degree obtaining module, configured to detect the logging curve data using a predetermined time series autoencoder to obtain the abnormality degree of the logging curve data; An abnormal value determination module is used to determine abnormal values ​​from the logging curve data according to the abnormality degree.

8. The device according to claim 7, characterized in that Abnormality degree obtaining module, including: The submodule for acquiring the logging curve data to be trained is used to acquire the logging curve data to be trained; A logging curve data detection task execution submodule is used to execute the logging curve data detection task based on the time series autoencoder to be trained; The time series autoencoder obtaining submodule is used to adjust the parameters of the time series autoencoder to be trained according to the logging curve data detection task to obtain the time series autoencoder.

9. An electronic device, characterized in that: The electronic 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 detecting abnormal values ​​in mud logging curves according to any one of claims 1 to 6.

10. 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 a logging curve abnormal value detection method according to any one of claims 1 to 6 when executed.

Images