Early fault diagnosis method for rotating part of drill jumbo and related device
Through technical means such as wavelet denoising and normal cumulative distribution standardization, combined with multi-dimensional scaling method and singular value decomposition, an unsimilarity matrix is constructed, which realizes efficient and accurate diagnosis of early failures of rotating parts of rock drill trolleys, and solves the problems of long and low efficiency of diagnosis in the existing technology.
Patent Information
- Application Number
- CN202510639251.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-16
- Publication Date
- 2025-08-29
AI Technical Summary
The fault diagnosis of existing rock drilling trolley rotary components is time-consuming and inefficient, especially lacking effective diagnostic methods for early failures. The fault characteristics of the rotary components are difficult to identify in harsh environments, resulting in equipment shutdown and maintenance and economic losses.
By constructing a dissimilar matrix, the accurate diagnosis of early failures of the rotating components of the rock-drilling trolley is achieved by constructing a dissimilarity matrix.
It realizes efficient and accurate identification of early faults of rotating parts of rock drill trolleys, improves the recognition of fault feature extraction and diagnosis accuracy, and ensures the efficient development of tunnel operations.
Smart Images
Figure CN120561550A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of equipment fault diagnosis, and in particular to a method for diagnosing early faults of rotating components of a rock drilling rig and related devices. Background Art
[0002] Drilling rigs are essential equipment for tunneling and mining. Due to harsh and complex operating environments, impact, dust, and humidity, rotating components are prone to failure, resulting in equipment downtime for repairs, disrupting tunneling operations, and causing significant economic losses. Existing fault diagnosis methods for rotating components of drilling rigs are time-consuming and inefficient, particularly lacking effective diagnostic methods for early-stage faults. Currently, rotating components of drilling rigs are capable of collecting monitoring data, including vibration, temperature, and sound signals. However, due to the harsh operating environment of drilling rigs, fault signatures of rotating components can be lost in the noise of the monitoring data. Furthermore, noise comes from diverse sources, and the coupling relationship between noise and the signals being sensed is complex. Therefore, identifying and diagnosing early-stage faults is crucial for timely maintenance of rotating components and essential for efficient tunneling operations. However, the signatures of early-stage rotating component failures are not readily apparent and differ little from those extracted from monitoring signals during normal service, significantly increasing the difficulty of subsequent feature extraction and fault diagnosis. Summary of the Invention
[0003] The purpose of this application is to provide a method and related device for diagnosing early faults of rotating parts of a rock drilling rig, which can realize accurate diagnosis of different early faults of rotating parts.
[0004] To achieve the above objectives, this application provides the following solutions:
[0005] In a first aspect, the present application provides a method for diagnosing early faults of rotating components of a drilling rig, comprising:
[0006] The original monitoring data is subjected to wavelet denoising and normal cumulative distribution standardization in sequence to obtain standardized data; the original monitoring data is the monitoring data when the rotating parts of the drilling rig are not faulty;
[0007] Performing linear symbolization and phase space reconstruction on the standardized data to generate a plurality of embedded vector data samples;
[0008] For each embedded vector data sample, the discrete entropy of the embedded vector data sample is calculated using the Shannon entropy method;
[0009] Performing linear symbolization and phase space reconstruction on the denoised data and the denoised data with time delay to generate embedded vector data samples with time delay and embedded vector data samples without time delay; the denoised data is the original monitoring data that has completed wavelet denoising but has not been normalized by normal cumulative distribution;
[0010] Determining distance correlations of the embedded vector data samples according to the embedded vector data samples with time delay and the embedded vector data samples without time delay;
[0011] Based on the spatial distribution matrix, the spatial distribution positions of the test data samples are compared, and the early faults of the rotating components of the drilling rig are diagnosed based on the minimum Euclidean distance.
[0012] The spatial distribution matrix is obtained by multidimensional scaling and singular value decomposition of the dissimilarity matrix;
[0013] Based on the spatial distribution matrix, the spatial distribution positions of the test data samples are compared, and the early faults of the rotating components of the drilling rig are diagnosed based on the minimum Euclidean distance.
[0014] Optionally, for each embedded vector data sample, the discrete entropy of the embedded vector data sample is calculated using the Shannon entropy method, specifically including:
[0015] Determining a discrete pattern according to the time domain fluctuation of the embedded vector data sample;
[0016] Iterate over each embedded vector data sample to determine the frequency of occurrence of each discrete pattern;
[0017] According to the occurrence frequency of each discrete pattern, the discrete entropy of the embedded vector data sample is calculated using the Shannon entropy method.
[0018] Optionally, the calculation formula for the occurrence frequency of the discrete pattern is:
[0019]
[0020] in, is a discrete mode, N is the length of the embedded vector data sample, is the frequency of occurrence of discrete modes, m is the dimension of phase space reconstruction, and d is the time delay interval between two vector elements during phase space reconstruction.
[0021] Optionally, the discrete entropy of the embedded vector data sample is calculated as follows:
[0022]
[0023] Among them, c is the symbolization level parameter and x is the embedded vector data sample.
[0024] Optionally, the distance correlation of each embedded vector data sample is calculated as follows:
[0025]
[0026] Where X is the denoised data, X' is the denoised data with time delay, σ(X,X') is the distance covariance between X and X', σ(X) is the distance variance of X, and σ(X') is the distance variance of X'.
[0027] Optionally, the calculation formula of the spatial distribution matrix is:
[0028]
[0029] Where E is the scalar product matrix, ΓΛΓ T is the spatial distribution matrix, e ij is the matrix element of the scalar product matrix, n is the number of embedded vector data samples, Γ is the orthogonal matrix composed of eigenvectors, Λ is the diagonal matrix composed of eigenvalues, and T is the matrix transpose.
[0030] Optionally, the matrix elements are calculated as:
[0031]
[0032] Among them, d ij are the matrix elements of the dissimilarity matrix, i,j=1,2,…,n.
[0033] In a second aspect, the present application provides an early fault diagnosis device for rotating components of a drilling rig, comprising:
[0034] The data processing module is used to perform wavelet denoising and normal cumulative distribution standardization on the original monitoring data in sequence to obtain standardized data;
[0035] a first embedded vector data sample generating module, configured to perform linear symbolization and phase space reconstruction on the standardized data to generate a plurality of embedded vector data samples;
[0036] A discrete entropy calculation module is used to calculate the discrete entropy of each embedded vector data sample using the Shannon entropy method;
[0037] A second embedded vector data sample generation module is used to perform linear symbolization and phase space reconstruction on the denoised data and the denoised data with time delay to generate embedded vector data samples with time delay and embedded vector data samples without time delay; the denoised data is the original monitoring data that has undergone wavelet denoising but has not undergone normal cumulative distribution normalization;
[0038] A distance correlation module, configured to determine the distance correlation of each embedded vector data sample based on the embedded vector data sample with time delay and the embedded vector data sample without time delay;
[0039] The dissimilarity matrix module is used to compare the spatial distribution positions of test data samples based on the spatial distribution matrix and diagnose early faults of rotating components of the drilling rig based on the minimum Euclidean distance;
[0040] The spatial distribution matrix module is used to obtain the spatial distribution matrix through multidimensional scaling and singular value decomposition dissimilarity matrix;
[0041] The fault diagnosis module is used to compare the spatial distribution positions of the test data samples based on the spatial distribution matrix and diagnose the early faults of the rotating parts of the drilling rig based on the minimum Euclidean distance.
[0042] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any one of the above-mentioned methods for diagnosing early faults of rotating parts of a drilling rig.
[0043] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any one of the above-mentioned methods for diagnosing early faults of rotating parts of a drilling rig.
[0044] According to the specific embodiments provided in this application, this application discloses the following technical effects:
[0045] The present application provides a method for diagnosing early faults of rotating parts of a rock drilling rig and related devices. First, by performing a series of processing on the original monitoring data, including wavelet denoising, normal cumulative distribution standardization, linear symbolization, and phase space reconstruction steps, a feature vector that can reflect the operating status of the rotating part is generated. These feature vectors not only contain the discrete entropy information of the operating status of the rotating part, but also include the distance correlation between data samples, so that the operating status of the rotating part can be more comprehensively reflected. Then, by constructing a dissimilarity matrix and using multidimensional scaling and singular value decomposition methods, the feature vector is converted into a spatial distribution matrix, which realizes the spatial distribution description of the operating status of the rotating part. Finally, by comparing the spatial distribution positions of the test data samples and performing diagnosis based on the minimum Euclidean distance, accurate identification of early faults of the rotating part can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. 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 any creative work.
[0047] Figure 1 This is a diagram showing an application environment of a method for diagnosing early faults of rotating components of a drilling rig in one embodiment of the present application;
[0048] Figure 2 A schematic flow chart of a method for diagnosing early faults of rotating components of a drilling rig provided in one embodiment of the present application;
[0049] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0050] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.
[0051] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.
[0052] The embodiment of the present application provides a method for diagnosing early faults of rotating parts of a drilling rig, which can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the original monitoring data to the server 104. After the server 104 receives the original monitoring data, the server 104 performs wavelet denoising and normal cumulative distribution normalization on the original monitoring data in turn to obtain standardized data; the original monitoring data is the monitoring data when the rotating parts of the drilling rig do not fail; the standardized data is linearly symbolized and phase-space reconstructed to generate several embedded vector data samples; for each embedded vector data sample, the discrete entropy of the embedded vector data sample is calculated using the Shannon entropy method; the denoised data and the denoised data with time delay are linearly symbolized and phase-space reconstructed to generate embedded vectors with time delay. The method comprises the following steps: determining the distance correlation between the embedded vector data samples with time delay and the embedded vector data samples without time delay, comparing the spatial distribution positions of the test data samples based on the spatial distribution matrix, and diagnosing the early stage faults of the rotating components of the drilling rig based on the minimum Euclidean distance; obtaining the spatial distribution matrix by multidimensional scaling and singular value decomposition of the dissimilarity matrix; and diagnosing the early stage faults of the rotating components of the drilling rig based on the minimum Euclidean distance. The server 104 can feed back the obtained fault diagnosis results to the terminal 102. In addition, in some embodiments, a method for diagnosing the early stage faults of the rotating components of the drilling rig can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly process the original monitoring data, or the server 104 can obtain the original monitoring data from the data storage system and perform data processing on the original monitoring data.
[0053] Terminal 102 may include, but is not limited to, various desktop computers, laptops, smartphones, tablet computers, IoT devices, and portable wearable devices. IoT devices may include smart speakers, smart TVs, smart air conditioners, and smart car devices. Portable wearable devices may include smart watches, smart bracelets, and head-mounted devices. Server 104 may be implemented as a standalone server or a server cluster consisting of multiple servers, or may be a cloud server.
[0054] In an exemplary embodiment, a method for diagnosing early faults of rotating components of a drilling rig is provided. The method is executed by a computer device, specifically a computer device such as a terminal or a server, or a terminal and a server. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate the process, including the following steps 201 to 208.
[0055] Step 201, performing wavelet denoising and normal cumulative distribution normalization processing on the original monitoring data in sequence to obtain normalized data; the original monitoring data is the monitoring data when the rotating parts of the drilling rig are not faulty;
[0056] Step 202: performing linear symbolization and phase space reconstruction on the standardized data to generate a plurality of embedded vector data samples;
[0057] Step 203: For each embedded vector data sample, the discrete entropy of the embedded vector data sample is calculated using the Shannon entropy method;
[0058] Step 204: Linearly symbolize and reconstruct the phase space of the denoised data and the denoised data with time delay to generate embedded vector data samples with time delay and embedded vector data samples without time delay; the denoised data is the original monitoring data that has undergone wavelet denoising but has not been normalized using normal cumulative distribution.
[0059] Step 205: determining the distance correlation of each embedded vector data sample based on the embedded vector data sample with time delay and the embedded vector data sample without time delay;
[0060] Step 206 , comparing the spatial distribution positions of the test data samples based on the spatial distribution matrix, and diagnosing early faults of the rotating components of the drilling rig based on the minimum Euclidean distance;
[0061] Step 207, obtaining a spatial distribution matrix by multidimensional scaling and singular value decomposition of the dissimilarity matrix;
[0062] Step 208 : Based on the spatial distribution matrix, the spatial distribution positions of the test data samples are compared, and based on the minimum Euclidean distance, early faults of the rotating components of the drilling rig are diagnosed.
[0063] In an exemplary embodiment, Figure 2 As shown, when executing steps 201-208, the specific steps may be as follows:
[0064] Step 1: Select appropriate wavelet basis functions and wavelet decomposition layers, perform wavelet denoising on the collected original monitoring data samples of the rotating parts of the drilling rig, and obtain denoised data.
[0065] Step 2: Use the normal cumulative distribution function to denoise the data Standardize and obtain standardized data
[0066] Step 3: Select the appropriate symbolization level parameter c and perform linear symbolization on the standardized data to obtain symbolized data
[0067] Step 4: Select the appropriate phase space reconstruction dimension m and time delay τ, perform phase space reconstruction on the symbolic data, and obtain a series of embedded vector data samples.
[0068] For example, consider a data sample X(t)={x(t1),x(t2),...,x(t N )}, from which N-(m-1)τ vectors can be extracted as follows:
[0069]
[0070] Step 5: For each embedding vector data sample Consider its time domain fluctuation as a discrete pattern Traverse all the obtained embedded vector data samples, calculate the frequency of occurrence of each discrete pattern, and calculate the discrete entropy of each embedded vector data sample in the form of Shannon entropy.
[0071] Specifically, for discrete mode The formula for calculating the frequency of occurrence is:
[0072]
[0073] The calculation formula of discrete entropy is:
[0074]
[0075] Where, is a discrete mode, N is the length of the embedded vector data sample, is the frequency of occurrence of discrete patterns, m is the phase space reconstruction dimension, d is the time delay interval between two vector elements during phase space reconstruction, c is the symbolization level parameter, and x is the embedded vector data sample.
[0076] Step 6: For each denoised but unnormalized embedding vector data sample (denoised data) X=(x1,x2,x3,...,x N ) and the denoised data with time delay X′=(x 1+Δt , x 2+Δt , x3+Δt ,...,x N+Δt ) Repeat step 4 to reconstruct the phase space and obtain the respective embedded vector data samples.
[0077] Step 7: Based on the embedded vector data samples with time delay and the embedded vector data samples without time delay, calculate the distance covariance and their respective distance variance statistics, and calculate the distance correlation of each data sample in the form of Pearson correlation coefficient. The formula is as follows:
[0078]
[0079] Where, the distance covariance between X and X' is: The distance variances of X and X' are:
[0080] Among them, the matrix A is obtained by the following equation:
[0081]
[0082] Where a ij =|X i -X j | is the Euclidean distance between every two elements in the sample, is the row arithmetic mean, is the column arithmetic mean, is the arithmetic mean of all elements. For matrix B, it can also be obtained by a definition similar to that of A.
[0083] Step 9: Use the dissimilarity matrix as the input of the multidimensional scaling method and calculate its corresponding scalar product matrix E = (e ij ) n , the matrix elements are expressed as:
[0084]
[0085] Step 10: Perform singular value decomposition on the scalar product matrix to obtain the spatial distribution matrix of all data samples:
[0086]
[0087] Where Γ is an orthogonal matrix composed of eigenvectors, Λ is a diagonal matrix composed of eigenvalues, and T is the matrix transpose.
[0088] Step 11: For the spatial distribution matrices obtained from the labeled monitoring data samples (training set) and the unlabeled monitoring data samples (test set), the spatial distribution of the labeled data samples and the test data samples are compared and matched to achieve identification and diagnosis of different faults.
[0089] Specifically, by traversing all training set data samples, each data sample will be output as a data point in space, and the distribution range of different categories of data in space can be obtained. Subsequently, for a test data sample, the Euclidean distance between the output spatial data point position and the spatial distribution range of all the above categories of data will be calculated. The category corresponding to the spatial distribution with the minimum distance is the category to which the test data sample belongs.
[0090] The present application also provides an application scenario, which applies the above-mentioned method for diagnosing early faults of rotating components of a rock drilling rig. Specifically, the method for diagnosing early faults of rotating components of a rock drilling rig provided in this embodiment can be applied in a mining operation environment.
[0091] Based on the same inventive concept, embodiments of the present application also provide a device for implementing the aforementioned method for diagnosing early faults of rotating components of a drilling rig. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more data processing device embodiments provided below can be found in the aforementioned method for diagnosing early faults of rotating components of a drilling rig, and will not be further elaborated here.
[0092] In an exemplary embodiment, a method for early fault diagnosis of a rotating component of a drilling rig is provided, comprising:
[0093] The data processing module is used to perform wavelet denoising and normal cumulative distribution standardization on the original monitoring data in sequence to obtain standardized data;
[0094] a first embedded vector data sample generating module, configured to perform linear symbolization and phase space reconstruction on the standardized data to generate a plurality of embedded vector data samples;
[0095] A discrete entropy calculation module is used to calculate the discrete entropy of each embedded vector data sample using the Shannon entropy method;
[0096] A second embedded vector data sample generation module is used to perform linear symbolization and phase space reconstruction on the denoised data and the denoised data with time delay to generate embedded vector data samples with time delay and embedded vector data samples without time delay; the denoised data is the original monitoring data that has undergone wavelet denoising but has not undergone normal cumulative distribution normalization;
[0097] A distance correlation module, configured to determine the distance correlation of each embedded vector data sample based on the embedded vector data sample with time delay and the embedded vector data sample without time delay;
[0098] The dissimilarity matrix module is used to compare the spatial distribution positions of test data samples based on the spatial distribution matrix and diagnose early faults of rotating components of the drilling rig based on the minimum Euclidean distance;
[0099] The spatial distribution matrix module is used to obtain the spatial distribution matrix through multidimensional scaling and singular value decomposition dissimilarity matrix;
[0100] The fault diagnosis module is used to compare the spatial distribution positions of the test data samples based on the spatial distribution matrix and diagnose the early faults of the rotating parts of the drilling rig based on the minimum Euclidean distance.
[0101] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store fault diagnosis results. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for early fault diagnosis of rotating parts of a drilling rig is implemented.
[0102] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.
[0103] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.
[0104] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.
[0105] 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, and the collection, use and processing of relevant data must comply with relevant regulations.
[0106] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0107] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.
[0108] In summary, this application has the following technical effects:
[0109] Compared with the existing technology, the method provided by the present application has the advantages of high recognition of early fault feature extraction and high fault identification accuracy. Since the present application adopts a feature extraction method that combines discrete entropy and distance correlation, it characterizes the analytical properties and statistical characteristics of the monitoring signal of the rotating parts of the drilling rig, reveals its potential structure, intrinsic properties and evolution laws, and can efficiently extract the characteristics of early faults. Secondly, the present application adopts a fault identification method based on multidimensional scaling method. This method takes into account the global structural relationship between monitoring data. Therefore, it can retain the original relationship between data to the greatest extent while achieving classification, thereby improving the accuracy and authenticity of fault identification and classification.
[0110] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0111] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.
Claims
1. A method for diagnosing early faults of rotating parts of a drilling rig, characterized in that: include: The original monitoring data is subjected to wavelet denoising and normal cumulative distribution standardization in sequence to obtain standardized data; the original monitoring data is the monitoring data when the rotating parts of the drilling rig are not faulty; Performing linear symbolization and phase space reconstruction on the standardized data to generate a plurality of embedded vector data samples; For each embedded vector data sample, the discrete entropy of the embedded vector data sample is calculated using the Shannon entropy method; Performing linear symbolization and phase space reconstruction on the denoised data and the denoised data with time delay to generate embedded vector data samples with time delay and embedded vector data samples without time delay; the denoised data is the original monitoring data that has completed wavelet denoising but has not been normalized by normal cumulative distribution; Determining distance correlations of the embedded vector data samples according to the embedded vector data samples with time delay and the embedded vector data samples without time delay; Based on the spatial distribution matrix, the spatial distribution positions of the test data samples are compared, and the early faults of the rotating components of the drilling rig are diagnosed based on the minimum Euclidean distance. The spatial distribution matrix is obtained by multidimensional scaling and singular value decomposition of the dissimilarity matrix; Based on the spatial distribution matrix, the spatial distribution positions of the test data samples are compared, and the early faults of the rotating components of the drilling rig are diagnosed based on the minimum Euclidean distance.
2. The method for diagnosing early faults of rotating parts of a drilling rig according to claim 1, characterized in that: For each embedded vector data sample, the discrete entropy of the embedded vector data sample is calculated using the Shannon entropy method, specifically including: Determining a discrete pattern according to the time domain fluctuation of the embedded vector data sample; Iterate over each embedded vector data sample to determine the frequency of occurrence of each discrete pattern; According to the occurrence frequency of each discrete pattern, the discrete entropy of the embedded vector data sample is calculated using the Shannon entropy method.
3. The method for early fault diagnosis of rotating parts of a drilling rig according to claim 1, characterized in that: The calculation formula for the occurrence frequency of the discrete mode is: in, is a discrete mode, N is the length of the embedded vector data sample, is the frequency of occurrence of discrete modes, m is the dimension of phase space reconstruction, and d is the time delay interval between two vector elements during phase space reconstruction.
4. The method for diagnosing early faults of rotating parts of a drilling rig according to claim 3, characterized in that: The calculation formula of the discrete entropy of the embedded vector data sample is: Among them, c is the symbolization level parameter and x is the embedded vector data sample.
5. The method for early fault diagnosis of rotating parts of a drilling rig according to claim 1, characterized in that: The calculation formula for the distance correlation of each embedded vector data sample is: Where X is the denoised data, X' is the denoised data with time delay, σ(X,X') is the distance covariance between X and X', σ(X) is the distance variance of X, and σ(X') is the distance variance of X'.
6. The method for diagnosing early faults of rotating parts of a drilling rig according to claim 1, characterized in that: The calculation formula of the spatial distribution matrix is: Where E is the scalar product matrix, ΓΛΓ T is the spatial distribution matrix, e ij is the matrix element of the scalar product matrix, n is the number of embedded vector data samples, Γ is the orthogonal matrix composed of eigenvectors, Λ is the diagonal matrix composed of eigenvalues, and T is the matrix transpose.
7. The method for diagnosing early faults of rotating parts of a drilling rig according to claim 6, characterized in that: The matrix elements are calculated as follows: Among them, d ij are the matrix elements of the dissimilarity matrix, i,j=1,2,…,n.
8. An early fault diagnosis device for rotating parts of a drilling rig, characterized in that: include: The data processing module is used to perform wavelet denoising and normal cumulative distribution standardization on the original monitoring data in sequence to obtain standardized data; a first embedded vector data sample generating module, configured to perform linear symbolization and phase space reconstruction on the standardized data to generate a plurality of embedded vector data samples; A discrete entropy calculation module is used to calculate the discrete entropy of each embedded vector data sample using the Shannon entropy method; A second embedded vector data sample generation module is used to perform linear symbolization and phase space reconstruction on the denoised data and the denoised data with time delay to generate embedded vector data samples with time delay and embedded vector data samples without time delay; the denoised data is the original monitoring data that has undergone wavelet denoising but has not undergone normal cumulative distribution normalization; A distance correlation module, configured to determine the distance correlation of each embedded vector data sample based on the embedded vector data sample with time delay and the embedded vector data sample without time delay; The dissimilarity matrix module is used to compare the spatial distribution positions of test data samples based on the spatial distribution matrix and diagnose early faults of rotating components of the drilling rig based on the minimum Euclidean distance; The spatial distribution matrix module is used to obtain the spatial distribution matrix through multidimensional scaling and singular value decomposition dissimilarity matrix; The fault diagnosis module is used to compare the spatial distribution positions of the test data samples based on the spatial distribution matrix and diagnose the early faults of the rotating parts of the drilling rig based on the minimum Euclidean distance.
9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a method for diagnosing early faults of rotating parts of a drilling rig according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, a method for diagnosing early faults of rotating parts of a drilling rig according to any one of claims 1 to 7 is implemented.