Drilling winch fault diagnosis method and device based on self-adaption

Abstract

The invention discloses a drilling winch fault diagnosis method and device based on self-adaption, and relates to the technical field of deep learning, and the method comprises the steps: obtaining a vibration signal obtained through the measurement of a drilling winch; reconstructing the vibration signal to remove noise in the vibration signal to obtain a reconstructed signal; obtaining a pre-trained fault diagnosis model; and inputting the reconstructed signal into a pre-trained fault diagnosis model to obtain a fault probability value corresponding to the vibration signal. The noise in the vibration signal can be removed through reconstruction of the vibration signal, the precision of the vibration signal is improved, the reconstructed signal obtained after noise removal is input into the pre-trained fault diagnosis model to obtain a more accurate fault probability value, and whether the drilling winch has a fault or not can be judged in time according to the fault probability value. And the diagnosis efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of deep learning technology, and in particular to a fault diagnosis method and device for a drilling rig winch based on adaptation. Background Art

[0002] The winch of the drilling rig is one of the most important equipment in the oil drilling equipment, and plays an important role in the whole drilling process. Its working performance directly affects the drilling efficiency and cost. Considering the poor working conditions of the winch of the drilling rig, the possibility of failure is relatively high. Once a failure occurs, it will pose a major threat to the drilling equipment and personal safety. Therefore, the fault diagnosis of the winch of the drilling rig is particularly important.

[0003] At present, the maintenance of drilling rig winches is mostly done by on-site maintenance personnel who check the winches and evaluate the status of the winches based on years of on-site experience. When the on-site personnel are not enough to solve the problem, they may even have to shut down the machine to notify the equipment supplier for inquiry. With the experience of on-site maintenance personnel, it is very likely that the winch failure will not be discovered in time, leading to major accidents; in addition, shutting down the winch affects the work of the entire production line. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to provide a fault diagnosis method and device for a drilling rig winch based on adaptation, so as to accurately and timely detect faults of the drilling rig winch.

[0005] To achieve the above object, one aspect of an embodiment of the present application provides a fault diagnosis method for a drilling rig winch based on adaptation, the method comprising the following steps:

[0006] Obtaining a vibration signal measured on a drilling rig winch;

[0007] Reconstructing the vibration signal to remove noise in the vibration signal to obtain a reconstructed signal;

[0008] Get a pre-trained fault diagnosis model;

[0009] The reconstructed signal is input into the pre-trained fault diagnosis model to obtain a fault probability value corresponding to the vibration signal.

[0010] In some embodiments, before reconstructing the vibration signal, the method further includes a step of preprocessing the vibration signal, wherein the step of preprocessing the vibration signal includes:

[0011] Determine missing data in the vibration signal; calculate an average value of data on both sides of the missing data; and use the average value as the missing data to complete the vibration signal;

[0012] Deleting data in the vibration signal that exceeds a preset threshold;

[0013] Normalizing each data in the vibration signal;

[0014] The normalized calculation formula is:

[0015]

[0016] Wherein, xmax is the maximum value of each data in the vibration signal, xmin is the minimum value of each data in the vibration signal, and x′ is the normalized data value;

[0017] The reconstructing of the vibration signal comprises the following steps:

[0018] The preprocessed vibration signal is reconstructed.

[0019] In some embodiments, reconstructing the vibration signal to remove noise in the vibration signal to obtain a reconstructed signal includes the following steps:

[0020] Performing variational modal decomposition on the vibration signal to obtain a plurality of candidate modal components;

[0021] Selecting a target modal component from each of the candidate modal components according to the principle of maximum correlation coefficient;

[0022] reconstructing the target modal component into an initialization dictionary;

[0023] Processing the initialized dictionary using a K-singular value decomposition algorithm to obtain an overcomplete dictionary;

[0024] Selecting the optimal atom from the supercomplete dictionary through a kurtosis value curve;

[0025] Use orthogonal matching pursuit algorithm to construct sparse coefficients;

[0026] The product result of the optimal atom and the sparse coefficient is determined as the reconstructed signal.

[0027] In some embodiments, the method further comprises the following steps:

[0028] Constructing a one-dimensional convolutional neural network model as the fault diagnosis model; wherein the one-dimensional convolutional neural network model includes an input layer, a plurality of convolutional layers and a pooling layer;

[0029] The fault diagnosis model is trained using the reconstructed signal and the fault probability value.

[0030] To achieve the above object, another aspect of the embodiment of the present application provides a fault diagnosis device for a drilling rig winch based on self-adaptation, the device comprising:

[0031] A signal acquisition unit, used to acquire a vibration signal measured from a drilling rig winch;

[0032] A signal reconstruction unit, used to reconstruct the vibration signal to remove noise in the vibration signal to obtain a reconstructed signal;

[0033] A model acquisition unit, used for acquiring a pre-trained fault diagnosis model;

[0034] The fault diagnosis unit is used to input the reconstructed signal into the pre-trained fault diagnosis model to obtain a fault probability value corresponding to the vibration signal.

[0035] In some embodiments, the device further includes a data preprocessing unit, and the data preprocessing unit includes:

[0036] A data completion unit, used to determine missing data in the vibration signal; calculate an average value of data on both sides of the missing data; and use the average value as the missing data to complete the vibration signal;

[0037] A data deleting unit, used to delete data in the vibration signal that exceeds a preset threshold;

[0038] A data normalization unit, used for normalizing each data in the vibration signal;

[0039] The normalized calculation formula is:

[0040]

[0041] Wherein, xmax is the maximum value of each data in the vibration signal, xmin is the minimum value of each data in the vibration signal, and x′ is the normalized data value;

[0042] The signal reconstruction unit comprises:

[0043] The signal reconstruction subunit is used to reconstruct the preprocessed vibration signal.

[0044] In some embodiments, the signal reconstruction unit includes:

[0045] A signal decomposition unit, used for performing variational modal decomposition on the vibration signal to obtain a plurality of candidate modal components;

[0046] A mode selection unit, used for selecting a target mode component from each of the candidate mode components according to a maximum correlation coefficient principle;

[0047] A first dictionary construction unit, configured to reconstruct the target modal component into an initialization dictionary;

[0048] A second dictionary construction unit is used to process the initialized dictionary using a K singular value decomposition algorithm to obtain an overcomplete dictionary;

[0049] An atom selection unit, used for selecting an optimal atom from the supercomplete dictionary through a kurtosis value curve;

[0050] A coefficient construction unit, used to construct sparse coefficients using an orthogonal matching pursuit algorithm;

[0051] A data multiplication unit is used to determine the product result of the optimal atom and the sparse coefficient as the reconstructed signal.

[0052] In some embodiments, the apparatus further comprises:

[0053] A model building unit, used to build a one-dimensional convolutional neural network model as the fault diagnosis model; wherein the one-dimensional convolutional neural network model includes an input layer, a plurality of convolutional layers and a pooling layer;

[0054] A model training unit is used to train the fault diagnosis model using the reconstructed signal and the fault probability value.

[0055] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the above-mentioned adaptive drilling rig winch fault diagnosis method.

[0056] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned adaptive-based fault diagnosis method for a drilling rig winch is implemented.

[0057] The embodiments of the present application include at least the following beneficial effects:

[0058] The present application can obtain the vibration signal obtained by measuring the winch of the drilling rig; reconstruct the vibration signal to remove the noise in the vibration signal to obtain a reconstructed signal; obtain a pre-trained fault diagnosis model; input the reconstructed signal into the pre-trained fault diagnosis model to obtain the fault probability value corresponding to the vibration signal. By reconstructing the vibration signal, the noise in it can be removed and the accuracy of the vibration signal can be improved. Then, the reconstructed signal obtained after removing the noise can be input into the pre-trained fault diagnosis model to obtain a more accurate fault probability value. According to the fault probability value, it is possible to timely determine whether the winch of the drilling rig has a fault, thereby improving the diagnostic efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0060] Figure 1 A flowchart of a fault diagnosis method for a drilling rig winch based on self-adaptation provided in an embodiment of the present application;

[0061] Figure 2 An example flow chart of data preprocessing provided in an embodiment of the present application;

[0062] Figure 3 An example flow chart of reconstructing a vibration signal provided in an embodiment of the present application;

[0063] Figure 4 An example flowchart of building a model and training a model provided in an embodiment of the present application;

[0064] Figure 5 An example flow chart of a fault diagnosis method for a drilling rig winch based on self-adaptation provided in an embodiment of the present application;

[0065] Figure 6 A schematic structural diagram of a fault diagnosis device for a drilling rig winch based on self-adaptation provided in an embodiment of the present application;

[0066] Figure 7 A schematic diagram of the structure of a data preprocessing unit provided in an embodiment of the present application;

[0067] Figure 8 A schematic diagram of the structure of a signal reconstruction unit provided in an embodiment of the present application;

[0068] Fig. 9 A schematic structural diagram of another self-adaptive fault diagnosis device for a drilling rig winch provided in an embodiment of the present application;

[0069] Fig.10 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0071] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0072] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0073] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0074] Before describing the embodiments of the present application in detail, the related technologies involved in the embodiments of the present application are first described as follows:

[0075] At present, the core part of the fault diagnosis of drilling rig winch is the early signal acquisition, because the signals collected in the early stage are often affected by many external factors, which makes the collected drilling rig winch signals inconsistent with the actual situation. Therefore, early signal denoising is a focus of current research. Although the current noise processing method can process high-dimensional data and has strong robustness and high accuracy, it has the following shortcomings: 1. Efficiency problem: The method requires iterative solution, and each iteration requires calculation of a large amount of data, which takes a long time. 2. Affected by parameter selection: Some parameters in the method need to be manually selected, such as sparsity, dictionary size, number of iterations, etc. Different parameter selections may lead to different results. Inappropriate parameter selection may affect the performance and stability of the algorithm.

[0076] In summary, it is necessary to propose a solution to effectively remove the noise of the acquired signal and improve the diagnostic efficiency and accuracy.

[0077] The embodiment of the present application provides a fault diagnosis method and device for a drilling rig winch based on adaptation. The technical solution of the present application includes: obtaining a vibration signal measured from the drilling rig winch; reconstructing the vibration signal to remove the noise in the vibration signal to obtain a reconstructed signal; obtaining a pre-trained fault diagnosis model; inputting the reconstructed signal into the pre-trained fault diagnosis model to obtain a fault probability value corresponding to the vibration signal. By reconstructing the vibration signal, the noise therein can be removed and the accuracy of the vibration signal can be improved. Then, the reconstructed signal obtained after the noise is removed can be input into the pre-trained fault diagnosis model to obtain a more accurate fault probability value. According to the fault probability value, it is possible to timely determine whether the drilling rig winch has a fault, thereby improving the diagnostic efficiency.

[0078] The embodiment of the present application provides a fault diagnosis method based on an adaptive drilling winch, which relates to the field of deep learning technology. The fault diagnosis method based on an adaptive drilling winch provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server, and can also be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a vehicle-mounted terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements a fault diagnosis method based on an adaptive drilling winch, etc., but is not limited to the above forms.

[0079] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0080] Reference Figure 1 The embodiment of the present application provides a fault diagnosis method based on an adaptive drilling rig winch. The method may include but is not limited to S100 to S130, which are as follows:

[0081] S100: Obtain a vibration signal measured from a drilling rig winch.

[0082] As an optional implementation, in this embodiment, one or more acceleration sensors may be installed on the drilling rig winch, and the vibration signal generated by the drilling rig winch may be acquired by using the acceleration sensors.

[0083] To improve the subsequent processing efficiency, refer to Figure 2 Before S110, the embodiment of the present application may further include a step of preprocessing the vibration signal, specifically including S101 to S103:

[0084] S101: Determine missing data in the vibration signal; calculate the average value of data on both sides of the missing data; and use the average value as the missing data to complete the vibration signal;

[0085] S102: deleting data in the vibration signal that exceeds a preset threshold;

[0086] S103: normalizing each data in the vibration signal;

[0087] The normalized calculation formula is:

[0088]

[0089] Wherein, xmax is the maximum value of each data in the vibration signal, xmin is the minimum value of each data in the vibration signal, and x′ is the normalized data value;

[0090] The reconstructing of the vibration signal comprises the following steps:

[0091] The preprocessed vibration signal is reconstructed.

[0092] It can be understood that the vibration signal can be a signal that is continuous in time. During collection, interference factors may cause the corresponding signal to not be collected within a certain time period, resulting in data missing. Therefore, this embodiment can determine the position of the missing data in the vibration signal, and then determine the duration corresponding to the missing data. At the positions on both sides of the missing data, data with the same duration as the missing data are selected respectively, and then the average value of the data on both sides is calculated, and then the average value is used to replace the missing data to complete the vibration signal.

[0093] Although the vibration signal may include a signal generated when a drilling rig winch fails, the vibration signal of the failure is still within the value range that the drilling rig winch may generate. Therefore, this embodiment can pre-set a threshold value based on the data range, that is, a preset threshold value, and then compare whether the value of each data in the vibration signal exceeds the preset threshold value. If so, it means that the data is an abnormal value, and the abnormal value is deleted.

[0094] S110: reconstructing the vibration signal to remove noise in the vibration signal to obtain a reconstructed signal.

[0095] It can be understood that this embodiment can decompose and reconstruct the vibration signal, and then remove the noise existing in the vibration signal during the reconstruction process to obtain a reconstructed signal with less noise.

[0096] As a further optional embodiment, refer to Figure 3 , S110 may include S111 to S117:

[0097] S111: performing variational modal decomposition on the vibration signal to obtain a plurality of candidate modal components;

[0098] S112: selecting a target modal component from each of the candidate modal components according to a maximum correlation coefficient principle;

[0099] S113: reconstructing the target modal component into an initialization dictionary;

[0100] S114: Processing the initialized dictionary using a K singular value decomposition algorithm to obtain an overcomplete dictionary;

[0101] S115: selecting an optimal atom from the supercomplete dictionary through a kurtosis value curve;

[0102] S116: constructing sparse coefficients using an orthogonal matching pursuit algorithm;

[0103] S117: Determine the product of the optimal atom and the sparse coefficient as the reconstructed signal.

[0104] The vibration signal is reconstructed through variational mode decomposition (VMD), K-singular value decomposition (KSVD) algorithm and orthogonal matching pursuit (OMP) algorithm to remove noise interference in the vibration signal and obtain the reconstructed signal.

[0105] Furthermore, the embodiment of the present application can also reconstruct the preprocessed vibration signal to remove noise and obtain a corresponding reconstructed signal.

[0106] S120: Obtain a pre-trained fault diagnosis model.

[0107] Specifically, the fault diagnosis model of this embodiment may be a deep learning model and may be pre-trained.

[0108] S130: Inputting the reconstructed signal into the pre-trained fault diagnosis model to obtain a fault probability value corresponding to the vibration signal.

[0109] Specifically, in this embodiment, a probability threshold may be preset. When the fault probability value output by the fault diagnosis model exceeds the probability threshold, it can be considered that the reconstructed signal includes a signal generated when the drilling rig winch fails, that is, the drilling rig winch has a fault.

[0110] Reference Figure 4 , the embodiment of the present application may further include the following steps:

[0111] S140: Constructing a one-dimensional convolutional neural network model as the fault diagnosis model; wherein the one-dimensional convolutional neural network model includes an input layer, several convolutional layers and a pooling layer.

[0112] It can be understood that the deep learning model used in this embodiment can be a one-dimensional convolutional neural network model, that is, a one-dimensional convolutional neural network model is constructed as a fault diagnosis model.

[0113] Exemplarily, the one-dimensional convolutional neural network model of this embodiment may include three convolutional layers.

[0114] S150: Training the fault diagnosis model using the reconstructed signal and the fault probability value.

[0115] To improve the timeliness of the fault diagnosis model, this embodiment can use the reconstructed signal and the corresponding fault probability value as training data to retrain the fault diagnosis model, thereby reducing the overfitting of the fault diagnosis model and thus reducing the accuracy of fault diagnosis.

[0116] Next, the solution of the embodiment of the present application will be described in detail and explained in conjunction with specific application examples:

[0117] In order to solve the problems existing in the related technology, the present embodiment provides an adaptive drilling rig winch fault diagnosis method based on adaptation and deep learning to improve the fault diagnosis accuracy of the drilling rig winch.

[0118] Next, we will combine Figure 5 The solution of this embodiment is described. Specifically, this embodiment may include the following steps:

[0119] Step 1: Send the existing fault diagnosis model to the edge device through the cloud.

[0120] Specifically, the fault data of the drilling rig winch collected in the cloud is used to train a deep learning model to form a fault diagnosis model, and the fault diagnosis model is sent to the edge side device.

[0121] Step 2: Analyze the common faults of the drilling rig winch, determine the common fault types of the drilling rig winch, determine the vibration signal that can reflect the fault status of the drilling rig winch, process the fault vibration signal of the drilling rig winch through the edge side equipment, and then collect it.

[0122] Specifically, the basic faults of the drilling rig winch are: internal noise; main brake failure; structural damage; abnormal anti-collision crane device; through consulting the data, it is known that the most common faulty parts in the drilling rig winch are bearings, pins, and brake discs. Because the distribution of colors in the time-frequency diagram of different states is related to the fault state, the size of the energy spectrum density in the time-frequency diagram is determined by the distribution of colors. The vibration amplitude of the fault vibration signal is different, and its color distribution is also different. Therefore, the distribution of energy spectrum density can show the characteristics of the fault.

[0123] Because the amplitude of the time domain analysis waveform is different under different operating conditions, fault diagnosis can be performed based on the vibration degree of the vibration signal. However, vibration signals often exhibit unstable and nonlinear characteristics, which affect the accuracy of fault diagnosis. Therefore, preprocessing operations must be performed on existing vibration signals to improve the accuracy of subsequent fault diagnosis.

[0124] The fault vibration signal of the drilling rig winch is processed by the edge side device and then collected, including: installing a plurality of acceleration sensors on the edge side device to collect the vibration signal of the drilling rig winch, and sequentially performing data missing processing, outlier processing and normalization processing on the collected vibration signal;

[0125] Missing data is handled by filling in the missing data with the average value on both sides;

[0126] Outlier processing is to discard outliers;

[0127] Normalization processing uses the maximum and minimum values ​​for normalization, and the normalization calculation formula is:

[0128]

[0129] Among them, xmax is the maximum value of each data in the vibration signal, xmin is the minimum value of each data in the vibration signal, and x′ is the normalized data value, and the numerical range is [0,1].

[0130] The above steps belong to the preprocessing steps. After the preprocessing is completed, the normalized vibration signal is reconstructed through VMD decomposition, KSVD algorithm and OMP algorithm to remove the noise interference in the vibration signal, and then the processed signal is used as the reconstructed signal.

[0131] Specifically, the vibration signal is reconstructed through VMD decomposition, KSVD algorithm and OMP algorithm, including:

[0132] The preprocessed vibration signal is used as the input signal y. First, the vibration signal is decomposed into different modal components IMF through VMD decomposition. The modal components are reconstructed to form an initialization dictionary d as the input of the KSVD algorithm. Then, the initialization dictionary d is processed by the KSVD algorithm to form an over-complete dictionary D. Assuming that the over-complete dictionary D is an m*n matrix, that is, the over-complete dictionary D has m atoms, the atoms are selected to construct an optimal dictionary D', and then a sparse coefficient x is constructed through the OMP algorithm. The reconstructed signal is y=D'×x.

[0133] Specifically, VMD is decomposed into different modal components to reconstruct the initialization dictionary d. First, the number of VMD decompositions and the regularization parameter are set as the input of VMD decomposition. The correlation coefficients between the modal components generated after VMD decomposition are calculated. According to the correlation coefficient curve, the retained components are determined as atoms in the initialization dictionary d, and then the atoms are reconstructed into the dictionary d.

[0134] Specifically, the atoms of the overcomplete dictionary D are selected according to the optimal principle of kurtosis value. First, the kurtosis value of the atoms in the overcomplete dictionary D is calculated. According to the kurtosis value curve, the threshold t is set. When the kurtosis value is greater than t, the atom is retained. When it is less than t, the atom is removed. In this way, the optimal atom in the overcomplete dictionary D is selected and the optimal atom is reconstructed to form the optimal atom D'.

[0135] Step 3: Use the fault diagnosis model to perform fault detection on the collected drilling rig winch vibration signal, output the diagnosis results and fault data, and upload them to the cloud.

[0136] Step 4: Train the fault diagnosis model based on the diagnosis results and fault data through the cloud, update the trained fault diagnosis model and send it to the edge device.

[0137] Specifically, a one-dimensional convolutional neural network model is built, including an input layer, three convolutional layers and a pooling layer. The vibration signal is feature extracted through the one-dimensional convolutional neural network, and finally the probability value of the fault vibration signal is output as the recognition result.

[0138] Specifically, the learning rate has a certain influence on the diagnostic accuracy of the fault diagnosis model. If the learning rate is too small, the gradient will descend slowly, the running speed of the fault diagnosis model will also slow down, and it is easy to fall into the local optimal point; if the learning rate is too large, the gradient will descend too quickly, causing the objective function to swing back and forth near the optimal point and fail to find the optimal point. The accuracy results of the fault diagnosis model at different learning rates are shown in Table 1:

[0139] Table 1

[0140] Learning Rate Accuracy / % 0.05 95.22 0.02 95.14 0.003 98.57 0.01 88.57

[0141] It can be seen from Table 1 that the accuracy rate reaches stability after 100 iterations under different learning rates, and when the learning rate is 0.003, the diagnostic accuracy of the fault diagnosis model reaches the best.

[0142] Repeat the above steps to diagnose the fault.

[0143] According to the above, the learning rate of the fault diagnosis model is set to 0.003, and the reconstructed signal processed by the KSVD algorithm and the OMP algorithm and the data not processed by the two algorithms are used as inputs respectively. After the fault diagnosis model, the accuracy of fault diagnosis is shown in Table 2:

[0144] Table 2

[0145] method Average accuracy / % KSVD+Deep Learning 95.54 Deep Learning 90.67 KSVD+OMP+Deep Learning 98.46

[0146] It can be seen from the data in Table 2 that the accuracy of deep learning without processing is low, and although the accuracy of simply using the KSVD algorithm to process the original data is high, it is not as high as the accuracy of processing with the KSVD algorithm and the OMP algorithm together, that is, the fault diagnosis model of this embodiment obtains a higher fault diagnosis accuracy.

[0147] The beneficial effects of this embodiment include:

[0148] This embodiment can perform preprocessing operations on the collected vibration signal, and then remove the noise of the preprocessed vibration signal through VMD decomposition, KSVD algorithm and OMP algorithm to obtain a reconstructed signal, and then use the fault diagnosis model to diagnose whether there is a fault in the drilling rig winch according to the reconstructed signal. Compared with the existing technology, this embodiment improves the accuracy of diagnosis; and adopts a combination of cloud processing and deep learning to meet the real-time requirements, save storage space, and greatly improve computing power.

[0149] Reference Figure 6 The embodiment of the present application further provides a fault diagnosis device based on adaptive drilling winch, which can implement the above-mentioned fault diagnosis method based on adaptive drilling winch, and the device includes:

[0150] A signal acquisition unit, used to acquire a vibration signal measured from a drilling rig winch;

[0151] A signal reconstruction unit, used to reconstruct the vibration signal to remove noise in the vibration signal to obtain a reconstructed signal;

[0152] A model acquisition unit, used for acquiring a pre-trained fault diagnosis model;

[0153] The fault diagnosis unit is used to input the reconstructed signal into the pre-trained fault diagnosis model to obtain a fault probability value corresponding to the vibration signal.

[0154] Reference Figure 7 In some embodiments, the device further comprises a data preprocessing unit, wherein the data preprocessing unit comprises:

[0155] A data completion unit, used to determine missing data in the vibration signal; calculate an average value of data on both sides of the missing data; and use the average value as the missing data to complete the vibration signal;

[0156] A data deleting unit, used to delete data in the vibration signal that exceeds a preset threshold;

[0157] A data normalization unit, used for normalizing each data in the vibration signal;

[0158] The normalized calculation formula is:

[0159]

[0160] Wherein, xmax is the maximum value of each data in the vibration signal, xmin is the minimum value of each data in the vibration signal, and x′ is the normalized data value;

[0161] The signal reconstruction unit comprises:

[0162] The signal reconstruction subunit is used to reconstruct the preprocessed vibration signal.

[0163] Reference Figure 8 In some embodiments, the signal reconstruction unit comprises:

[0164] A signal decomposition unit, used for performing variational modal decomposition on the vibration signal to obtain a plurality of candidate modal components;

[0165] A mode selection unit, used for selecting a target mode component from each of the candidate mode components according to a maximum correlation coefficient principle;

[0166] A first dictionary construction unit, configured to reconstruct the target modal component into an initialization dictionary;

[0167] A second dictionary construction unit is used to process the initialized dictionary using a K singular value decomposition algorithm to obtain an overcomplete dictionary;

[0168] An atom selection unit, used for selecting an optimal atom from the supercomplete dictionary through a kurtosis value curve;

[0169] A coefficient construction unit, used to construct sparse coefficients using an orthogonal matching pursuit algorithm;

[0170] A data multiplication unit is used to determine the product result of the optimal atom and the sparse coefficient as the reconstructed signal.

[0171] Reference Fig. 9 In some embodiments, the device further comprises:

[0172] A model building unit, used to build a one-dimensional convolutional neural network model as the fault diagnosis model; wherein the one-dimensional convolutional neural network model includes an input layer, a plurality of convolutional layers and a pooling layer;

[0173] A model training unit is used to train the fault diagnosis model using the reconstructed signal and the fault probability value.

[0174] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0175] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned adaptive-based fault diagnosis method for a drilling rig winch when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.

[0176] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0177] See also Fig.10 , Fig.10 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0178] The processor 1001 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0179] The memory 1002 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1002 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1002, and the processor 1001 calls and executes the fault diagnosis method of the drilling rig winch based on the adaptive embodiment of the present application;

[0180] Input / output interface 1003, used to implement information input and output;

[0181] The communication interface 1004 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0182] A bus 1005 , which transmits information between various components of the device (e.g., the processor 1001 , the memory 1002 , the input / output interface 1003 , and the communication interface 1004 );

[0183] The processor 1001 , the memory 1002 , the input / output interface 1003 and the communication interface 1004 are connected to each other in communication within the device via the bus 1005 .

[0184] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned adaptive-based fault diagnosis method for a drilling rig winch is implemented.

[0185] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0186] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0187] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0188] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0189] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0190] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0191] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising 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.

[0192] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0193] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0194] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0195] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0196] If the integrated unit is implemented in the form of 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 solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes multiple instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store programs.

[0197] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A fault diagnosis method for a drilling rig winch based on self-adaptation, characterized in that: The method comprises the following steps: Obtaining a vibration signal measured on a drilling rig winch; Reconstructing the vibration signal to remove noise in the vibration signal to obtain a reconstructed signal; Get a pre-trained fault diagnosis model; The reconstructed signal is input into the pre-trained fault diagnosis model to obtain a fault probability value corresponding to the vibration signal.

2. A fault diagnosis method for a drilling rig winch based on self-adaptation according to claim 1, characterized in that: Before reconstructing the vibration signal, the method further includes a step of preprocessing the vibration signal, and the step of preprocessing the vibration signal includes: Determine missing data in the vibration signal; calculate an average value of data on both sides of the missing data; and use the average value as the missing data to complete the vibration signal; Deleting data in the vibration signal that exceeds a preset threshold; Normalizing each data in the vibration signal; The normalized calculation formula is: Wherein, xmax is the maximum value of each data in the vibration signal, xmin is the minimum value of each data in the vibration signal, and x′ is the normalized data value; The reconstructing of the vibration signal comprises the following steps: The preprocessed vibration signal is reconstructed.

3. The fault diagnosis method of a drilling rig winch based on self-adaptation according to claim 1, characterized in that: The step of reconstructing the vibration signal to remove noise from the vibration signal to obtain a reconstructed signal comprises the following steps: Performing variational modal decomposition on the vibration signal to obtain a plurality of candidate modal components; Selecting a target modal component from each of the candidate modal components according to the principle of maximum correlation coefficient; reconstructing the target modal component into an initialization dictionary; Processing the initialized dictionary using a K-singular value decomposition algorithm to obtain an overcomplete dictionary; Selecting the optimal atom from the supercomplete dictionary through a kurtosis value curve; Use orthogonal matching pursuit algorithm to construct sparse coefficients; The product result of the optimal atom and the sparse coefficient is determined as the reconstructed signal.

4. A fault diagnosis method for a drilling rig winch based on self-adaptation according to any one of claims 1 to 3, characterized in that: The method further comprises the following steps: Constructing a one-dimensional convolutional neural network model as the fault diagnosis model; wherein the one-dimensional convolutional neural network model includes an input layer, a plurality of convolutional layers and a pooling layer; The fault diagnosis model is trained using the reconstructed signal and the fault probability value.

5. A fault diagnosis device for a drilling rig winch based on self-adaptation, characterized in that: The device comprises: A signal acquisition unit, used to acquire a vibration signal measured from a drilling rig winch; A signal reconstruction unit, used to reconstruct the vibration signal to remove noise in the vibration signal to obtain a reconstructed signal; A model acquisition unit, used for acquiring a pre-trained fault diagnosis model; The fault diagnosis unit is used to input the reconstructed signal into the pre-trained fault diagnosis model to obtain a fault probability value corresponding to the vibration signal.

6. The fault diagnosis device based on adaptive drilling rig winch according to claim 5, characterized in that: The device further includes a data preprocessing unit, and the data preprocessing unit includes: A data completion unit, used to determine missing data in the vibration signal; calculate an average value of data on both sides of the missing data; and use the average value as the missing data to complete the vibration signal; A data deleting unit, used to delete data in the vibration signal that exceeds a preset threshold; A data normalization unit, used for normalizing each data in the vibration signal; The normalized calculation formula is: Wherein, xmax is the maximum value of each data in the vibration signal, xmin is the minimum value of each data in the vibration signal, and x′ is the normalized data value; The signal reconstruction unit comprises: The signal reconstruction subunit is used to reconstruct the preprocessed vibration signal.

7. The fault diagnosis device based on adaptive drilling rig winch according to claim 5, characterized in that: The signal reconstruction unit comprises: A signal decomposition unit, used for performing variational modal decomposition on the vibration signal to obtain a plurality of candidate modal components; A mode selection unit, used for selecting a target mode component from each of the candidate mode components according to a maximum correlation coefficient principle; A first dictionary construction unit, configured to reconstruct the target modal component into an initialization dictionary; A second dictionary construction unit is used to process the initialized dictionary using a K singular value decomposition algorithm to obtain an overcomplete dictionary; An atom selection unit, used for selecting an optimal atom from the supercomplete dictionary through a kurtosis value curve; A coefficient construction unit, used to construct sparse coefficients using an orthogonal matching pursuit algorithm; A data multiplication unit is used to determine the product result of the optimal atom and the sparse coefficient as the reconstructed signal.

8. A fault diagnosis device based on adaptive drilling rig winch according to any one of claims 5 to 7, characterized in that: The device also includes: A model building unit, used to build a one-dimensional convolutional neural network model as the fault diagnosis model; wherein the one-dimensional convolutional neural network model includes an input layer, a plurality of convolutional layers and a pooling layer; A model training unit is used to train the fault diagnosis model using the reconstructed signal and the fault probability value.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the adaptive drilling rig winch fault diagnosis method as described in any one of claims 1 to 4 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the fault diagnosis method of a drilling rig winch based on adaptation as claimed in any one of claims 1 to 4 is implemented.

Images