A method, device, equipment and storage medium for monitoring the liquid level of a mud tank

Abstract

The embodiment of the present specification provides a kind of mud tank liquid level monitoring method, device, equipment and storage medium, wherein the method comprises: in the process of pumping drilling fluid in mud tank, the flowmeter signal of current time of mud tank is acquired;The flowmeter signal of current time is preprocessed, and the signal feature of current time is obtained;The signal feature of current time is input into the liquid level monitoring model trained using liquid level interface image, and the current liquid level interface state of drilling fluid in mud tank is obtained;When the current liquid level interface state is no liquid phase, automatically close liquid pump.The embodiment of the present specification can improve the accuracy of mud tank liquid level determination, improve work efficiency.

Description

Technical Field

[0001] This specification relates to the field of liquid level monitoring, and in particular, to a method, apparatus, equipment, and storage medium for monitoring the liquid level of a mud tank. Background Technology

[0002] The mud tank is the main carrier of drilling fluid and an important part of the drilling fluid circulation system, primarily used to store and transport drilling fluid. Drilling fluid, also known as drilling mud, refers to the fluid that continuously circulates in the borehole during oil drilling. Its main functions include lubricating the drill bit, stabilizing the wellbore, and carrying cuttings, ensuring safe and efficient drilling. Although drilling fluid containing cuttings returned from the bottom of the well can filter out most of the cuttings after treatment by purification equipment, some residue will still accumulate in the mud tank. As drilling progresses, the amount of sediment in the mud tank increases, and the actual volume of the mud tank decreases. At this point, the level gauge measures the sum of the volume of solid sediment and the volume of drilling fluid, which is greater than the actual volume of drilling fluid. This can lead to an incorrect judgment of the actual volume of the mud tank, causing workers to miss the pump shutdown time, allowing air to enter the pipeline and damage the equipment, thus affecting production efficiency.

[0003] Currently, relying entirely on experience to judge the liquid level in the mud tank leads to inaccurate judgment of the actual liquid level in the tank. This results in problems such as insufficient use of the mud tank, untimely dredging, and inappropriate timing of pump shutdown, which will affect subsequent processes and reduce work efficiency.

[0004] Therefore, there is an urgent need for a method to monitor the liquid level in mud tanks, which can improve the accuracy of mud tank level judgment and increase work efficiency. Summary of the Invention

[0005] The purpose of the embodiments in this specification is to provide a method, apparatus, equipment and storage medium for monitoring the liquid level of a mud tank, so as to improve the accuracy of mud tank liquid level judgment and improve work efficiency.

[0006] To achieve the above objectives, this specification provides a method for monitoring the liquid level in a mud tank, comprising:

[0007] During the process of pumping drilling fluid from the mud tank, the flow meter signal of the mud tank at the current moment is obtained;

[0008] The flow meter signal at the current moment is preprocessed to obtain the signal characteristics at the current moment;

[0009] The signal features at the current moment are input into the liquid level monitoring model trained using the liquid level interface image to obtain the current liquid level interface state of the drilling fluid in the mud tank.

[0010] When the current liquid level interface state is no liquid phase, the liquid pump is automatically shut off.

[0011] Preferably, the step of preprocessing the flow meter signal at the current moment to obtain the signal characteristics at the current moment further includes:

[0012] Remove the baseline drift of the flow meter signal at the current moment to obtain the waveform signal at the current moment without baseline drift;

[0013] Wavelet transform features are extracted from the waveform signal at the current moment to obtain the signal features at the current moment.

[0014] Preferably, the signal characteristics at the current moment are calculated using the following formula:

[0015]

[0016] Among them, WT f (a,τ) represents the signal characteristics at the current time, where a is the transform scale, τ is the time offset, and t is the time. Let f(t) be the fundamental decomposition function, and f(t) be the waveform signal at time t.

[0017] Preferably, the training method for the liquid level monitoring model includes:

[0018] A transparent observation window is provided along the axial direction of the mud tank, and a camera is used to capture video of the liquid level interface during the drilling fluid pumping process inside the mud tank based on the observation window.

[0019] Acquire the flow meter signal during the drilling fluid pumping process in the mud tank;

[0020] Extract the liquid level interface image at each moment from the liquid level interface video;

[0021] The liquid level interface image at each moment is regularized to obtain image information of a uniform specification for each moment;

[0022] The flow meter signal is preprocessed to obtain the signal characteristics at each time point;

[0023] Matching image information and signal features at the same time;

[0024] The liquid level monitoring model is trained using the matched image information and signal features to obtain a trained liquid level monitoring model.

[0025] Preferably, the step of training the liquid level monitoring model using the matched image information and signal features to obtain the trained liquid level monitoring model further includes:

[0026] The matched signal features are input into the liquid level monitoring model to obtain the predicted liquid level interface state of the drilling fluid in the mud tank.

[0027] The actual liquid level interface state of the drilling fluid in the mud tank is determined based on the matched image information.

[0028] The predicted liquid level interface state is compared with the actual liquid level interface state to obtain the comparison result;

[0029] Based on the comparison results, the liquid level monitoring model is iteratively optimized to obtain a trained liquid level monitoring model.

[0030] Preferably, after automatically shutting off the pump when the current liquid level interface state is no liquid phase, the method further includes:

[0031] Record the current level gauge reading to obtain the current solid phase reading;

[0032] Add the current solid phase reading to the total solid phase reading, and update the total solid phase reading;

[0033] If the updated total solids reading is greater than the set value, an alarm is issued to clean the solids deposits in the mud tank.

[0034] Preferably, after recording the current level gauge reading and obtaining the current solid phase reading, the method further includes:

[0035] Return the level gauge reading to zero;

[0036] After refilling the mud tank with drilling fluid, pump out the drilling fluid from the mud tank.

[0037] During the process of pumping drilling fluid from the mud tank, the flow meter signal of the mud tank is acquired;

[0038] The flow meter signal is denoised to obtain signal characteristics;

[0039] The signal features are input into the trained liquid level monitoring model to obtain the current liquid level interface state of the drilling fluid in the mud tank.

[0040] When the current liquid level interface state is no liquid phase, the liquid pump is automatically shut off;

[0041] Record the current level gauge reading to obtain the current solid phase reading;

[0042] Add the current solid phase reading to the total solid phase reading, and update the total solid phase reading;

[0043] Repeat the above steps until the updated total solids reading is greater than the set value, then issue an alarm to clean the solids deposits in the mud tank.

[0044] On the other hand, embodiments of this specification provide a liquid level monitoring device for a mud tank, the device comprising:

[0045] The acquisition module is used to acquire the flow meter signal of the mud tank at the current moment during the process of pumping drilling fluid into the mud tank;

[0046] The preprocessing module is used to preprocess the flow meter signal at the current moment to obtain the signal characteristics at the current moment;

[0047] The liquid level determination module is used to input the signal characteristics at the current moment into the liquid level monitoring model trained using the liquid level interface image to obtain the current liquid level interface state of the drilling fluid in the mud tank.

[0048] The pump shut-off module is used to automatically shut off the liquid pump when the current liquid level interface state is no liquid phase.

[0049] In another aspect, embodiments of this specification also provide a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the computer program, when executed by the processor, performs instructions of any of the methods described above.

[0050] In another aspect, embodiments of this specification also provide a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor of a computer device to perform instructions for any of the methods described above.

[0051] As can be seen from the technical solutions provided in the embodiments of this specification above, the embodiments of this specification propose a liquid level monitoring model. This model is trained using liquid level interface images. During training, the liquid level monitoring model matches the liquid level interface image with the flow meter signal. When the flow meter signal at the current moment is input to the liquid level monitoring model, the current liquid level interface state can be obtained. When the current liquid level interface state is no liquid phase, the pump will automatically shut down. The method in the embodiments of this specification has no lag, which can improve the accuracy of mud tank liquid level judgment and increase work efficiency.

[0052] To make the above and other objects, features and advantages of this specification more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 A schematic flowchart of a method for monitoring the liquid level in a mud tank, as provided in an embodiment of this specification, is shown.

[0055] Figure 2 A schematic flowchart illustrating the process of obtaining signal characteristics at the current moment, provided in an embodiment of this specification, is shown.

[0056] Figure 3 A flowchart illustrating the training method for the liquid level monitoring model provided in the embodiments of this specification is shown.

[0057] Figure 4 A schematic diagram of the process for obtaining a trained liquid level monitoring model, as provided in the embodiments of this specification, is shown.

[0058] Figure 5 A schematic diagram of the process after the automatic shutdown of the liquid pump provided in the embodiments of this specification is shown;

[0059] Figure 6 A schematic diagram of the process after obtaining the current solid phase reading is shown in the embodiments of this specification;

[0060] Figure 7 This diagram illustrates a modular structure of a liquid level monitoring device for a mud tank, as provided in an embodiment of this specification.

[0061] Figure 8 A schematic diagram of the structure of a computer device provided in an embodiment of this specification is shown.

[0062] Explanation of symbols in the attached drawings:

[0063] 100. Acquisition Module;

[0064] 200. Preprocessing module;

[0065] 300. Liquid level determination module;

[0066] 400. Pump shut-off module;

[0067] 802. Computer equipment;

[0068] 804, Processor;

[0069] 806. Memory;

[0070] 808. Drive mechanism;

[0071] 810. Input / Output Module;

[0072] 812. Input devices;

[0073] 814. Output devices;

[0074] 816. Presentation equipment;

[0075] 818. Graphical User Interface;

[0076] 820. Network interface;

[0077] 822. Communication link;

[0078] 824. Communication bus. Detailed Implementation

[0079] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the embodiments of this specification.

[0080] In existing technologies, the liquid level in the mud tank is judged entirely by experience, which is inaccurate. This leads to problems such as insufficient use of the mud tank, untimely dredging, and inappropriate pump shutdown, which can affect subsequent processes and reduce work efficiency.

[0081] To address the aforementioned issues, this specification provides an embodiment of a method for monitoring the liquid level in a mud tank. Figure 1 This is a flowchart illustrating a method for monitoring the liquid level in a mud tank, as provided in an embodiment of this specification. This specification provides the operational steps of the method described in the embodiments or flowchart, but based on conventional or non-inventive methods, more or fewer operational steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual system or device products, the methods shown in the embodiments or accompanying drawings can be executed sequentially or in parallel.

[0082] It should be noted that the terms "first," "second," etc., in the description, claims, and accompanying drawings of the embodiments in this specification are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, apparatus, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0083] Reference Figure 1 This specification discloses a method for monitoring the liquid level in a mud tank, comprising:

[0084] S101: During the process of pumping drilling fluid from the mud tank, acquire the flow meter signal of the mud tank at the current moment;

[0085] S102: Preprocess the flow meter signal at the current moment to obtain the signal characteristics at the current moment;

[0086] S103: Input the signal features at the current moment into the liquid level monitoring model trained using the liquid level interface image to obtain the current liquid level interface state of the drilling fluid in the mud tank.

[0087] S104: When the current liquid level interface state is no liquid phase, the liquid pump is automatically shut off.

[0088] When the liquid level monitoring method in the embodiments of this specification is put into production and used in the oil drilling process, the mud tank contains drilling fluid. The drilling fluid needs to be pumped out by a pump and injected into the borehole. Since the drilling fluid is generally recycled, the drilling fluid returning from the bottom of the well contains rock cuttings. After the drilling fluid containing rock cuttings is injected into the mud tank, a large amount of sediment will be present in the mud tank. The drilling fluid in the mud tank can be pumped out again and injected into the borehole. However, due to the accumulation of sediment, the volume of drilling fluid in the mud tank is not equal to the volume of the mud tank. Therefore, it is impossible to estimate the volume of drilling fluid based on the volume of the mud tank in order to perform the pump shutdown operation.

[0089] If a level sensor is used to monitor the level in the mud tank to guide pump shutdown, the sensor is located inside the mud tank. Since the mud tank contains a liquid-solid mixture, it is impossible to clearly determine whether there is still drilling fluid in the mud tank, resulting in inaccurate monitoring results and an inability to accurately guide pump shutdown.

[0090] If a flow meter is used to monitor the flow rate to guide pump shutdown, the flow meter is located outside the mud tank and installed on the pipe connecting to the mud tank. When the flow meter reading is 0, there is no drilling fluid left in the mud tank, and air has entered the pipe. Air entering the pipe can damage the drilling equipment. Therefore, the flow meter has a lag and cannot accurately guide pump shutdown.

[0091] The embodiments in this specification take into account the above-mentioned problems in the prior art, namely, that because there are both solid sediments and drilling fluid in the mud tank, it is impossible to accurately determine the level of drilling fluid in the mud tank, and thus it is impossible to accurately guide the pump shutdown.

[0092] This specification presents a liquid level monitoring model, which is trained using liquid level interface images. During training, the model matches the liquid level interface image with flow meter signals. When the flow meter signal is input to the model at the current moment, the current liquid level interface state can be determined. If the current liquid level interface state is no liquid phase, the pump will automatically shut down. The method described in this specification has no lag, improving the accuracy of mud tank liquid level judgment and increasing work efficiency.

[0093] The method described in this specification can be executed in a programmable logic controller (PLC). The PLC is electrically connected to the flow meter and the pump, respectively. It receives the flow meter signal at the current moment from the flow meter, and after obtaining the current liquid level interface state of the drilling fluid in the mud tank based on the flow meter signal, if the current liquid level interface state is no liquid phase, it sends a shutdown command to the pump to guide the pump to be shut down. Specifically, the electrical signal can be transmitted through the RS-485 communication protocol.

[0094] During the pumping of drilling fluid from the mud tank, it is necessary to continuously acquire the flow meter signal of the mud tank at the current moment. After preprocessing the flow meter signal at the current moment, it is input into the liquid level monitoring model to obtain the current liquid level interface state of the drilling fluid in the mud tank, which is either liquid or no liquid phase. When the current liquid level interface state is no liquid phase, it guides the pump shutdown operation.

[0095] Among them, reference Figure 2 The step of preprocessing the flow meter signal at the current moment to obtain the signal characteristics at the current moment further includes:

[0096] S201: Remove the baseline drift of the flow meter signal at the current moment to obtain a waveform signal at the current moment without baseline drift;

[0097] S202: Extract wavelet transform features from the waveform signal at the current moment to obtain the signal features at the current moment.

[0098] Baseline drift removal aims to eliminate physical noise from the flowmeter, which is generated due to factors such as the flowmeter's connection method. Wavelet transform feature extraction converts the time-domain signal into a frequency-domain signal, facilitating subsequent feature extraction of the waveform signal.

[0099] Specifically, the signal characteristics at the current moment can be calculated using the following formula:

[0100]

[0101] Among them, WT f (a,τ) represents the signal characteristics at the current time, where a is the transform scale, τ is the time offset, and t is the time. Let f(t) be the fundamental decomposition function, and f(t) be the waveform signal at time t.

[0102] In the embodiments described in this specification, reference is made to Figure 3 The training method for the liquid level monitoring model includes:

[0103] S301: A transparent observation window is provided along the axial direction of the mud tank, and a video of the liquid level interface during the drilling fluid pumping process in the mud tank is obtained by a camera based on the observation window;

[0104] S302: Acquire the flow meter signal during the drilling fluid pumping process in the mud tank;

[0105] S303: Extract the liquid level interface image at each moment from the liquid level interface video;

[0106] S304: Perform regularization processing on the liquid level interface image at each moment to obtain image information of a uniform specification for each moment;

[0107] S305: Preprocess the flow meter signal to obtain the signal characteristics at each moment;

[0108] S306: Match image information and signal features at the same time;

[0109] S307: The liquid level monitoring model is trained using the matched image information and signal features to obtain a trained liquid level monitoring model.

[0110] The mud tanks used in S301-S307 are experimental equipment. A transparent observation window needs to be installed along the axial direction of the mud tank to facilitate the acquisition of video of the drilling fluid level interface during the pumping process via a camera. Simultaneously, the flow meter signal also needs to be acquired. The level interface video is a video of the drilling fluid in the mud tank from the start to the end of pumping. The level interface image at each moment in the video needs to be extracted, and the images are regularized to obtain image information of uniform specifications. The flow meter signal also requires preprocessing; the specific preprocessing steps can be referred to in S201-S202 to obtain the signal characteristics at each moment.

[0111] Furthermore, image information and signal features at the same time are matched to establish a correspondence between image information and signal features in the time dimension. At each time, there is a unique matching image information and a unique signal feature. The liquid level monitoring model is trained using the matched image information and signal features.

[0112] In the embodiments described in this specification, reference is made to Figure 4 The step of training the liquid level monitoring model using the matched image information and signal features to obtain the trained liquid level monitoring model further includes:

[0113] S401: Input the matched signal features into the liquid level monitoring model to obtain the predicted liquid level interface state of the drilling fluid in the mud tank;

[0114] S402: Determine the actual liquid level interface state of the drilling fluid in the mud tank based on the matched image information;

[0115] S403: Compare the predicted liquid level interface state with the actual liquid level interface state to obtain a comparison result;

[0116] S404: Iteratively optimize the liquid level monitoring model based on the comparison results to obtain a trained liquid level monitoring model.

[0117] The matched image information and signal features correspond to the same moment in time. Inputting the matched signal features into the liquid level monitoring model yields the predicted liquid level interface state. The matched image information can be segmented using edge segmentation to determine whether the actual liquid level interface state is characterized by the presence or absence of a liquid phase. The liquid level monitoring model is optimized by comparing the two results, resulting in a well-trained model. Both the predicted and actual liquid level interface states include both the presence and absence of a liquid phase. When determining the actual liquid level interface state after liquid-solid segmentation, machine recognition can be used. Machine recognition can either involve manually labeling the data to build a dataset before machine recognition, or it can be performed directly by humans.

[0118] Since the liquid level interface image inside the mud tank cannot be obtained in actual applications, the embodiments of this specification input the flow meter signal into the liquid level monitoring model trained using the liquid level interface image to obtain the current liquid level interface state of the drilling fluid in the mud tank, so as to operate the pump shutdown. However, as drilling fluid is injected into the mud tank, the drilling fluid is pumped out and used, and after use, the drilling fluid is recycled and injected back into the mud tank. The above process is continuously repeated, and the solid phase deposits in the mud tank increase. When there are too many solid phase deposits, they need to be cleaned.

[0119] To facilitate the cleaning work, refer to Figure 5 The step of automatically shutting off the pump when the current liquid level interface state is no liquid phase further includes:

[0120] S501: Record the current level gauge reading to obtain the current solid phase reading;

[0121] S502: Add the current solid phase reading to the total solid phase reading and update the total solid phase reading;

[0122] S503: If the updated total solids reading is greater than the set value, an alarm is issued to clean the solids deposits in the mud tank.

[0123] The initial solids reading is 0. After the drilling fluid is first injected into the mud tank for pumping, the pump is automatically shut off, and the total solids reading is 0. The current solids reading A is added to 0 to update the total solids reading to A. If the total solids reading is greater than the set value, an alarm is triggered to remind personnel to clean the solids deposits in the mud tank. The set value can be set according to actual conditions, and this manual does not limit it.

[0124] In the embodiments described in this specification, reference is made to Figure 6 After recording the current level gauge reading and obtaining the current solid phase reading, the method further includes:

[0125] S601: Zero the level gauge reading;

[0126] S602: After refilling the mud tank with drilling fluid, pump out the drilling fluid from the mud tank;

[0127] S603: Acquire the flow meter signal of the mud tank during the process of pumping drilling fluid from the mud tank;

[0128] S604: Denoise the flow meter signal to obtain signal characteristics;

[0129] S605: Input the signal features into the trained liquid level monitoring model to obtain the current liquid level interface state of the drilling fluid in the mud tank;

[0130] S606: When the current liquid level interface state is no liquid phase, the liquid pump is automatically shut off;

[0131] S607: Record the current level gauge reading to obtain the current solid phase reading;

[0132] S608: Add the current solid phase reading to the total solid phase reading and update the total solid phase reading;

[0133] S609: Repeat S601-S608 as above until the updated total solids reading is greater than the set value, then issue an alarm to clean the solids deposits in the mud tank.

[0134] It should be noted that after each injection of drilling fluid into the mud tank for pumping, the pump will automatically shut off and the above steps S601-S609 will be circulated to update the total solids reading. Before each injection of drilling fluid into the mud tank for pumping, the level gauge reading must be zeroed. The level gauge is an instrument installed in the mud tank to detect the liquid level. After zeroing it, the reading of the level gauge after the pump is automatically shut off is the current volume of solids deposited in the mud tank. Only in this way can the total solids reading be accurately calculated.

[0135] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the acquisition, storage, use, and processing of data in the technical solutions described in the embodiments of this application all comply with the provisions of relevant laws and regulations.

[0136] Based on the above-described method for monitoring the liquid level of a mud tank, this specification also provides a corresponding device for monitoring the liquid level of a mud tank. The device may include a system (including a distributed system), software (application), module, component, server, client, etc., using the method described in the embodiments of this specification, combined with necessary hardware implementation. Based on the same innovative concept, the devices in one or more embodiments provided in this specification are as described in the following embodiments. Since the implementation schemes and methods for solving the problem are similar, the implementation of specific devices in the embodiments of this specification can refer to the implementation of the aforementioned method, and repeated details will not be repeated. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0137] Specifically, Figure 7 This is a schematic diagram of the module structure of one embodiment of the liquid level monitoring device for a mud tank provided in this specification. (Refer to...) Figure 7 As shown in the embodiments of this specification, a liquid level monitoring device for a mud tank includes: an acquisition module 100, a preprocessing module 200, a liquid level determination module 300, and a pump shut-off module 400.

[0138] The acquisition module 100 is used to acquire the flow meter signal of the mud tank at the current moment during the process of pumping drilling fluid into the mud tank;

[0139] The preprocessing module 200 is used to preprocess the flow meter signal at the current moment to obtain the signal characteristics at the current moment;

[0140] The liquid level determination module 300 is used to input the signal characteristics at the current moment into the liquid level monitoring model trained using the liquid level interface image to obtain the current liquid level interface state of the drilling fluid in the mud tank.

[0141] The pump shut-off module 400 is used to automatically shut off the liquid pump when the current liquid level interface state is no liquid phase.

[0142] Reference Figure 8As shown, based on the above-described method for monitoring the liquid level of a mud tank, one embodiment of this specification also provides a computer device 802, wherein the above method operates on the computer device 802. The computer device 802 may include one or more processors 804, such as one or more central processing units (CPUs) or graphics processing units (GPUs), each processing unit capable of implementing one or more hardware threads. The computer device 802 may also include any memory 806 for storing any kind of information such as code, settings, data, etc. In one specific embodiment, a computer program is stored on the memory 806 and can run on the processor 804. When the computer program is run by the processor 804, it can execute instructions according to the above method. Non-limitingly, for example, the memory 806 may include any type of RAM, any type of ROM, flash memory, hard disk, optical disk, etc. More generally, any memory can use any technology to store information. Further, any memory can provide volatile or non-volatile retention of information. Further, any memory can represent a fixed or removable component of the computer device 802. In one scenario, when processor 804 executes associated instructions stored in any memory or combination of memories, computer device 802 can perform any operation of the associated instructions. Computer device 802 also includes one or more drive mechanisms 808 for interacting with any memory, such as hard disk drive mechanisms, optical disk drive mechanisms, etc.

[0143] Computer device 802 may also include an input / output module 810 (I / O) for receiving various inputs (via input device 812) and providing various outputs (via output device 814). A specific output mechanism may include a presentation device 816 and an associated graphical user interface 818 (GUI). In other embodiments, the input / output module 810 (I / O), input device 812, and output device 814 may be omitted, and the device may function solely as a computer device within a network. Computer device 802 may also include one or more network interfaces 820 for exchanging data with other devices via one or more communication links 822. One or more communication buses 824 couple the components described above together.

[0144] Communication link 822 can be implemented in any way, such as via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, or any combination thereof. Communication link 822 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0145] Corresponding to Figures 1-6In addition to the methods described above, embodiments of this specification also provide a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the methods described above.

[0146] This specification also provides computer-readable instructions, wherein when a processor executes the instructions, the program therein causes the processor to perform the following... Figures 1 to 6 The method shown.

[0147] It should be understood that in the various embodiments of this specification, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this specification.

[0148] It should also be understood that, in the embodiments of this specification, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the embodiments of this specification, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0149] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this specification can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the embodiments in this specification.

[0150] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0151] In the several embodiments provided in this specification, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, or they may be electrical, mechanical, or other forms of connection.

[0152] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments described in this specification, depending on actual needs.

[0153] Furthermore, the functional units in the various embodiments of this specification can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0154] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this specification, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this specification. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0155] This specification uses specific embodiments to illustrate the principles and implementation methods of the embodiments. The above description of the embodiments is only for the purpose of helping to understand the methods and core ideas of the embodiments in this specification. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the embodiments in this specification. Therefore, the content of this specification should not be construed as a limitation on the embodiments in this specification.

Claims

1. A method for monitoring the liquid level in a mud tank, characterized in that, include: During the process of pumping drilling fluid from the mud tank, the flow meter signal of the mud tank at the current moment is obtained; The flow meter signal at the current moment is preprocessed to obtain the signal characteristics at the current moment; The signal features at the current moment are input into the liquid level monitoring model trained using the liquid level interface image to obtain the current liquid level interface state of the drilling fluid in the mud tank. When the current liquid level interface state is no liquid phase, the liquid pump is automatically shut off; The liquid level monitoring model is obtained through the following steps: A transparent observation window is provided along the axial direction of the mud tank, and a camera is used to capture video of the liquid level interface during the drilling fluid pumping process inside the mud tank based on the observation window. Acquire the flow meter signal during the drilling fluid pumping process in the mud tank; Extract the liquid level interface image at each moment from the liquid level interface video; The liquid level interface image at each moment is regularized to obtain image information of a uniform specification for each moment; The flow meter signal is preprocessed to obtain the signal characteristics at each time point; Matching image information and signal features at the same time; The liquid level monitoring model is trained using the matched image information and signal features to obtain a trained liquid level monitoring model; The step of training the liquid level monitoring model using the matched image information and signal features to obtain the trained liquid level monitoring model further includes: The matched signal features are input into the liquid level monitoring model to obtain the predicted liquid level interface state of the drilling fluid in the mud tank. The actual liquid level interface state of the drilling fluid in the mud tank is determined based on the matched image information. The predicted liquid level interface state is compared with the actual liquid level interface state to obtain the comparison result; Based on the comparison results, the liquid level monitoring model is iteratively optimized to obtain a trained liquid level monitoring model.

2. The method according to claim 1, characterized in that, The step of preprocessing the flow meter signal at the current moment to obtain the signal characteristics at the current moment further includes: Remove the baseline drift of the flow meter signal at the current moment to obtain the waveform signal at the current moment without baseline drift; Wavelet transform features are extracted from the waveform signal at the current moment to obtain the signal features at the current moment.

3. The method according to claim 2, characterized in that, The signal characteristics at the current moment are calculated using the following formula: ； in, WT f ( a , τ () represents the signal characteristics at the current moment. a To change the scale, τ For time domain offset, t For a moment, The fundamental decomposition function, f ( t ) represents the waveform signal at time t.

4. The method according to claim 1, characterized in that, The step of automatically shutting off the pump when the current liquid level interface state is no liquid phase further includes: Record the current level gauge reading to obtain the current solid phase reading; Add the current solid phase reading to the total solid phase reading, and update the total solid phase reading; If the updated total solids reading is greater than the set value, an alarm is issued to clean the solids deposits in the mud tank.

5. The method according to claim 4, characterized in that, After recording the current liquid level gauge reading and obtaining the current solid phase reading, the process further includes: Return the level gauge reading to zero; After refilling the mud tank with drilling fluid, pump out the drilling fluid from the mud tank. During the process of pumping drilling fluid from the mud tank, the flow meter signal of the mud tank is acquired; The flow meter signal is denoised to obtain signal characteristics; The signal features are input into the trained liquid level monitoring model to obtain the current liquid level interface state of the drilling fluid in the mud tank. When the current liquid level interface state is no liquid phase, the liquid pump is automatically shut off; Record the current level gauge reading to obtain the current solid phase reading; Add the current solid phase reading to the total solid phase reading, and update the total solid phase reading; The process involves cyclically recording the current level gauge reading and obtaining the current solid phase reading. Once the updated total solid phase reading exceeds the set value, an alarm is issued to clean the solid phase deposits in the mud tank.

6. A liquid level monitoring device for a mud tank, characterized in that, The device includes: The acquisition module is used to acquire the flow meter signal of the mud tank at the current moment during the process of pumping drilling fluid into the mud tank; The preprocessing module is used to preprocess the flow meter signal at the current moment to obtain the signal characteristics at the current moment; The liquid level determination module is used to input the signal characteristics at the current moment into the liquid level monitoring model trained using the liquid level interface image to obtain the current liquid level interface state of the drilling fluid in the mud tank. The pump shut-off module is used to automatically shut off the liquid pump when the current liquid level interface state is no liquid phase. The liquid level determination module is further configured to: 1) install a transparent observation window along the axial direction of the mud tank; 2) acquire video of the liquid level interface during the drilling fluid pumping process within the mud tank via a camera using the observation window; 3) acquire flow meter signals during the drilling fluid pumping process within the mud tank; 4) extract liquid level interface images at each moment from the liquid level interface video; 5) perform regularization processing on the liquid level interface images at each moment to obtain uniform image information for each moment; 6) preprocess the flow meter signals to obtain signal characteristics at each moment; 7) match the image information and signal characteristics at the same moment; and 8) use the matched image information and signal characteristics to... The process of training a liquid level monitoring model to obtain a trained liquid level monitoring model further includes: inputting the matched signal features into the liquid level monitoring model to obtain the predicted liquid level interface state of the drilling fluid in the mud tank; determining the actual liquid level interface state of the drilling fluid in the mud tank based on the matched image information; comparing the predicted liquid level interface state with the actual liquid level interface state to obtain a comparison result; and iteratively optimizing the liquid level monitoring model based on the comparison result to obtain a trained liquid level monitoring model.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, When the computer program is run by the processor, it executes the instructions of the method according to any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is run by the processor of the computer device, it executes the instructions of the method according to any one of claims 1-5.

Images