A hydraulic cylinder internal leakage fault diagnosis method and device

Abstract

This invention provides a method and apparatus for diagnosing internal leakage faults in hydraulic cylinders, relating to the field of signal processing technology. The method includes: acquiring pressure signals from the rodless chamber and the rod chamber; extracting time-domain feature values ​​from the rodless and rod chamber pressure signals respectively; performing dimensionality reduction on the time-domain feature values ​​using principal component analysis to select principal component time-domain feature values; constructing an internal leakage diagnostic model based on the principal component time-domain feature values ​​of the rodless and rod chamber pressure signals; estimating the parameters of the internal leakage diagnostic model using a binary value identification algorithm; and diagnosing internal leakage faults in the hydraulic cylinder based on the parameter-estimated internal leakage diagnostic model. This improves the accuracy of internal leakage fault identification, avoids the need for the hydraulic cylinder to stop normal operation during diagnosis, and enhances the real-time performance of internal leakage fault detection.

Description

Technical Field

[0001] This invention relates to the field of signal processing technology, and in particular to a method and apparatus for diagnosing internal leakage faults in hydraulic cylinders. Background Technology

[0002] Hydraulic systems, capable of delivering significant force and torque in a relatively small volume while generating minimal vibration and impact, play a crucial role in modern industrial production. Hydraulic cylinders are vital actuators within these systems; a malfunction can disrupt the entire system, leading to economic losses and potential hazards to operators. Internal leakage is a common failure mode in hydraulic cylinders, causing the pressure energy of the hydraulic oil to be converted into heat, resulting in elevated oil temperature and severely impacting the efficiency and performance of the hydraulic system.

[0003] Traditional diagnostic techniques mostly employ signal processing-based methods. One approach involves real-time acquisition of the pressure signal from the rodless chamber of a hydraulic cylinder, followed by wavelet transform to extract time-frequency features. Internal leakage is then detected by comparing normal and faulty features. Another method extracts the pressure signal features from the hydraulic cylinder inlet using wavelet decomposition, and then uses a backpropagation neural network to build a classifier, enabling intelligent identification of internal leakage faults in the hydraulic cylinder. Alternatively, principal component analysis combined with spectral clustering can effectively extract sensitive features of the pressure signal.

[0004] However, traditional diagnostic techniques require the hydraulic cylinder to stop working normally, and cannot monitor for internal leakage in real time; there is no suitable mathematical model for these signal characteristics, resulting in low accuracy in identifying internal leakage faults. Summary of the Invention

[0005] To address the technical problems of traditional diagnostic techniques requiring the hydraulic cylinder to stop normal operation and thus lacking real-time monitoring for internal leakage, and the absence of suitable mathematical models for these signal characteristics, resulting in low accuracy in identifying internal leakage faults, this invention provides a method and apparatus for diagnosing internal leakage faults in hydraulic cylinders.

[0006] The technical solutions provided by the embodiments of the present invention are as follows:

[0007] The first aspect of the present invention provides a method for diagnosing internal leakage faults in a hydraulic cylinder. The hydraulic cylinder comprises a cylinder barrel, a cylinder head, a piston, and a piston rod. The piston divides the cylinder barrel into two chambers: a rod chamber containing the piston rod and a rodless chamber without the piston rod. The method includes:

[0008] S1: Acquire pressure signals from the rodless chamber and the rod chamber;

[0009] S2: Extract the time-domain feature values ​​of the rodless cavity pressure signal and the rod cavity pressure signal respectively;

[0010] S3: The time-domain eigenvalues ​​are reduced in dimensionality using principal component analysis to select the principal component time-domain eigenvalues.

[0011] S4: Construct an internal leakage diagnostic model based on the principal component time-domain characteristic values ​​of the rodless cavity pressure signal and the rod cavity pressure signal;

[0012] S5: Parameter estimation of the internal leakage diagnostic model is performed using a binary value identification algorithm;

[0013] S6: Based on the internal leakage diagnostic model after parameter estimation, diagnose the internal leakage fault of the hydraulic cylinder.

[0014] A second aspect of the present invention provides a diagnostic device for internal leakage faults in a hydraulic cylinder, comprising:

[0015] The acquisition module is used to acquire pressure signals from the rodless chamber and the rod chamber.

[0016] An extraction module is used to extract the time-domain feature values ​​of the rodless cavity pressure signal and the rod cavity pressure signal, respectively.

[0017] The selection module is used to perform dimensionality reduction processing on the time-domain feature values ​​using principal component analysis to select the principal component time-domain feature values.

[0018] A construction module is used to construct an internal leakage diagnostic model based on the principal component time-domain feature values ​​of the rodless cavity pressure signal and the rod cavity pressure signal;

[0019] The estimation module is used to estimate the parameters of the internal leakage diagnostic model using a binary value identification algorithm;

[0020] The diagnostic module is used to diagnose the internal leakage fault of the hydraulic cylinder based on the internal leakage diagnostic model after parameter estimation.

[0021] A third aspect of the present invention provides a system for diagnosing internal leakage faults in a hydraulic cylinder, comprising:

[0022] processor;

[0023] The memory stores computer-readable instructions, which, when executed by a processor, implement a fault diagnosis method for internal leakage of a hydraulic cylinder, as described in the first aspect.

[0024] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for diagnosing internal leakage faults in a hydraulic cylinder as described in the first aspect.

[0025] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0026] In this invention, pressure signals from the rodless chamber and the rod chamber are acquired, and time-domain feature values ​​of the pressure signals are extracted respectively. These time-domain feature values ​​provide a direct representation of the equipment's operational status. Principal component analysis (PCA) is used to reduce the dimensionality of the time-domain feature values, selecting principal components. PCA identifies the main directions of change in the data, retaining the most important information while removing redundant information, thus improving the accuracy of internal leakage fault identification. A binary value identification algorithm is used to estimate the parameters of the internal leakage diagnostic model. This algorithm continuously optimizes the parameter estimation sequence until a termination condition is met, resulting in more accurate system parameter estimates. Based on the internal leakage diagnostic model with the estimated parameters, internal leakage faults in the hydraulic cylinder are diagnosed, improving the accuracy of internal leakage fault identification and avoiding the need for the hydraulic cylinder to stop normal operation during diagnosis, thereby enhancing the real-time performance of internal leakage fault detection. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 A flowchart illustrating a method for diagnosing internal leakage faults in a hydraulic cylinder, provided in an embodiment of the present invention;

[0029] Figure 2 This is a schematic flowchart illustrating an internal leakage diagnosis method provided in an embodiment of the present invention.

[0030] Figure 3 This is a schematic diagram of the structure of a hydraulic cylinder internal leakage fault diagnosis device provided in an embodiment of the present invention;

[0031] Figure 4 This is a schematic diagram of the internal leakage fault diagnosis system for a hydraulic cylinder provided in an embodiment of the present invention. Detailed Implementation

[0032] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0033] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0034] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, their intended meanings are consistent. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, their intended meanings are consistent.

[0035] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0036] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0037] Reference manual attached Figure 1 The diagram shows a flowchart of a method for diagnosing internal leakage faults in a hydraulic cylinder according to an embodiment of the present invention.

[0038] Reference manual attached Figure 2 The diagram illustrates a flowchart of an internal leakage diagnosis provided by an embodiment of the present invention.

[0039] This invention provides a method for diagnosing internal leakage faults in hydraulic cylinders. This method can be implemented by a hydraulic cylinder internal leakage fault diagnosis device, which can be a terminal or a server.

[0040] A hydraulic cylinder consists of a cylinder barrel, a cylinder head, a piston, and a piston rod. The piston divides the cylinder barrel into two chambers: the chamber with the piston rod and the chamber without the piston rod.

[0041] The troubleshooting process for internal leakage faults in hydraulic cylinders may include the following steps:

[0042] S1: Acquire pressure signals from the rodless chamber and the rod chamber.

[0043] S2: Extract the time-domain feature values ​​of the rodless cavity pressure signal and the rod cavity pressure signal, respectively.

[0044] Optionally, the time-domain feature values ​​specifically include:

[0045] Maximum value, minimum value, average value, peak value, root square magnitude, standard deviation, root mean square, mean square deviation, variance, skewness, kurtosis, peak factor, impulse factor, margin factor and / or waveform factor.

[0046] It should be noted that the calculation of time-domain features is relatively simple and easy to understand, and can intuitively represent the state information during the operation of the equipment.

[0047] In this invention, extracting the time-domain feature values ​​of the rodless cavity pressure signal and the rod cavity pressure signal can intuitively reflect the status information of the equipment. It has the advantages of being simple and easy to understand, having rich feature values, and high computational efficiency, which helps to monitor and analyze the operation of the equipment.

[0048] S3: Principal component analysis is used to reduce the dimensionality of the time-domain eigenvalues ​​and select the principal component time-domain eigenvalues.

[0049] Principal Component Analysis (PCA) is a commonly used multivariate data analysis method that aims to reduce the dimensionality of data and reveal its internal structure. Its main idea is to project the original data into a new coordinate system through a linear transformation, maximizing the variance of the projected data. In this new coordinate system, the dimensions of the data are made as independent as possible, thus reducing the correlation between data points.

[0050] It should be noted that the extracted feature values ​​are numerous and contain a significant amount of redundant information, making model building and computation inconvenient. Principal component analysis (PCA) can effectively identify the main feature components, achieving dimensionality reduction. Furthermore, PCA can identify the main directions of change in the data, retaining the most important information while removing redundant information, making the data simpler and easier to process.

[0051] In one possible implementation, S3 specifically includes:

[0052] S301: Store the extracted time-domain feature values ​​as an m×n dimensional feature matrix:

[0053]

[0054] Where X represents the characteristic matrix, a mn Let m represent the nth feature of the mth sample, where m represents the total number of samples and n represents the total number of time-domain feature values.

[0055] S302: Calculate the mean of the dataset in each column of the feature matrix.

[0056] S303: Perform zero-mean normalization on the feature matrix based on the mean of each column of the dataset.

[0057]

[0058] Where X0 represents the feature matrix after zero-mean normalization, un This represents the mean of the dataset in column n.

[0059] In this invention, by performing zero-mean processing, these problems can be effectively avoided, ensuring the stability and reliability of the model.

[0060] Furthermore, zero-mean normalization of the feature matrix helps eliminate bias between data, improves the stability and generalization ability of the model, simplifies the training process, and avoids problems such as data overflow or underflow.

[0061] S304: Multiply the zero-mean eigenma matrix on the right by a full-rank matrix to obtain the target matrix:

[0062] Y = X0·P

[0063] Where Y represents the target matrix and P represents the full-rank matrix.

[0064] It should be noted that the feature matrix is ​​right-multiplied by a full-rank matrix, that is, the 15 features are linearly combined, resulting in a Y (m×r) dimension, where r < n. For the dimensionality-reduced matrix Y, in order to accurately reflect the information of the original matrix X...

[0065] S305: Calculate the variance of each column in the target matrix:

[0066]

[0067] Among them, Var(b i ) represents the variance of the i-th column in the target matrix, b i Let () represent the column vector of the i-th column in the target matrix. T This represents the transpose of a matrix. ji Let r represent the element in the j-th row and i-th column, and r represent the number of columns in the target matrix.

[0068] Variance describes the degree of dispersion, and divergence can be used to measure the amount of information loss. Therefore, we should try to maximize the variance of the data after dimensionality reduction in order to minimize information loss.

[0069] S306: Calculate the covariance of any two columns in the target matrix:

[0070]

[0071] Among them, Cov(b i ,b j ) represents the covariance between the i-th and j-th columns in the target matrix, b j This represents the column vector of the j-th column in the target matrix.

[0072] Covariance describes the correlation between two variables. If the covariance between two variables is 0, then the two variables are linearly independent. Linear independence can avoid redundancy in information expressed across multiple columns.

[0073] S307: Construct a covariance matrix based on the variance of each column in the target matrix and the covariance of any two columns in the target matrix:

[0074]

[0075] S308: Perform similarity diagonalization on the covariance matrix to determine the orthogonal matrix:

[0076]

[0077] Where Q represents an orthogonal matrix [Q1, Q2, ..., Q] composed of eigenvectors. n ], λ i Let Q represent the i-th time-domain eigenvalue. i Let λ represent the i-th eigenvector. i With Q i One-to-one correspondence.

[0078] S309: Sort the time-domain eigenvalues ​​of the orthogonal matrix in descending order.

[0079] In this invention, by sorting the eigenvalues ​​of orthogonal matrices in descending order, the principal components that contribute most to the data variance can be identified. This helps determine which principal components contain the most important information.

[0080] S310: Principal component time-domain feature values ​​whose cumulative variance contribution rate is greater than the preset contribution rate.

[0081] In this invention, principal components with higher variance contributions are selected and retained based on a preset variance contribution rate. This reduces data dimensionality while preserving as much of the main information in the original data as possible, minimizing information loss.

[0082] S311: Construct the principal component matrix based on the eigenvectors corresponding to the time-domain eigenvalues ​​of the principal components.

[0083] S312: Dimensionality reduction of the feature matrix using the principal component matrix:

[0084] Y t =X·P t

[0085] Among them, Y t Let P represent the feature matrix after dimensionality reduction. t This represents the principal component matrix.

[0086] In this invention, dimensionality reduction helps remove redundant information and noise from the feature matrix, resulting in cleaner data and a more robust model. Simultaneously, dimensionality reduction preserves principal components that significantly contribute to the data variance, making the data easier to interpret and understand. This facilitates a deeper understanding of the data's characteristics and structure during subsequent analysis and modeling.

[0087] In summary, subsequent steps such as similarity diagonalization of the covariance matrix and principal component analysis can help identify key features, reduce data dimensionality, decrease redundant information, and improve the interpretability and computational efficiency of the model.

[0088] S4: Construct an internal leakage diagnostic model based on the principal component time-domain eigenvalues ​​of the rodless chamber pressure signal and the rod chamber pressure signal.

[0089] In one possible implementation, S4 specifically refers to:

[0090] Using the principal component time-domain eigenvalues ​​of the rodless chamber pressure signal and the rod chamber pressure signal as independent variables, an internal leakage diagnostic model is constructed:

[0091]

[0092] Among them, y k α represents the health status of the hydraulic cylinder determined based on the pressure signal acquired in the kth sampling. i The diagnostic coefficient, x, represents the time-domain eigenvalue of the i-th principal component of the rod chamber pressure signal. i (k) represents the time-domain feature value of the i-th principal component extracted from the pressure signal acquired in the k-th time, β j z represents the diagnostic coefficient of the time-domain eigenvalue of the j-th principal component of the rodless chamber pressure signal. j (k) represents the time-domain feature value of the j-th principal component extracted from the pressure signal acquired in the k-th time, where α = [α1, α2, ..., αk]. n ] T and β=[β1,β2,...,β n ] T The parameters of the model are: d(k) represents the system noise at the k-th acquisition, C represents the internal leakage threshold, and s represents the internal leakage indicator function. k This represents the internal leakage fault diagnosis result determined based on the pressure signal collected in the kth iteration, and I represents the indicative function.

[0093] The noise d(k) follows a normal distribution.

[0094] It should be noted that y k Y is the output variable, representing the health status of the hydraulic cylinder; C is the threshold for determining whether there is internal leakage, when y kWhen C is less than or equal to y, no internal leakage occurs in the hydraulic cylinder; when y... k When the value is greater than C, internal leakage occurs in the hydraulic cylinder; s k It is the internal leakage characteristic function, s k =1 indicates that the hydraulic cylinder is working normally (no internal leakage has occurred), s k =0 indicates that the hydraulic cylinder has an internal leakage fault.

[0095] In this invention, the principal component time-domain eigenvalues ​​are used as input variables to construct the model, which can comprehensively consider the characteristics of the pressure signal, thereby improving the diagnostic accuracy of internal leakage faults. Simultaneously, by analyzing the principal component time-domain eigenvalues ​​of the pressure signal, the characteristics of internal leakage faults in hydraulic cylinders can be captured more sensitively, improving the sensitivity of fault detection.

[0096] Furthermore, constructing an internal leakage diagnostic model can achieve automated fault detection and diagnosis, improve diagnostic accuracy and fault detection sensitivity, reduce maintenance costs and the risk of production accidents, and is of great significance to the safety and stability of hydraulic systems.

[0097] S5: Parameter estimation of the internal leakage diagnostic model is performed using a binary value identification algorithm.

[0098] The Two-Set Identification Algorithm is a method for system identification and parameter estimation. It is commonly used for modeling and identifying dynamic systems, particularly in the fields of control systems and signal processing.

[0099] In one possible implementation, S5 specifically includes:

[0100] S501: Order w k =y(k)-C, rewrite the internal leakage diagnostic model:

[0101]

[0102] S502: Let η = [α] T ,β T [C] T , φ k =[x T (k),z T (k),-1] T The internal leakage diagnostic model was rewritten:

[0103]

[0104] S503: Using principal component analysis, extract the time-domain eigenvalues ​​of the rod-side cavity and the rodless cavity, as well as the corresponding hydraulic cylinder state, from the existing pressure signal.

[0105] {x(k):k=1,2,...,N}

[0106] {z(k):k = 1, 2, ..., N}

[0107] {s k :k=1,2,...,N}

[0108] Where x(k) represents the time-domain feature value extracted from the rod chamber pressure signal acquired in the kth acquisition, z(k) represents the time-domain feature value extracted from the rodless chamber pressure signal acquired in the kth acquisition, and N represents the hydraulic cylinder state and the number of sets of extracted hydraulic chamber time-domain feature values;

[0109] In this invention, principal component analysis reduces the dimensionality of the original data, retaining only the most important features, thus reducing data processing complexity and improving data analysis efficiency. Simultaneously, by extracting the time-domain feature values ​​of the rod-side and rodless cylinders and combining them with the hydraulic cylinder's state information, a more accurate monitoring model can be established, enabling precise monitoring and evaluation of the hydraulic cylinder's state. This helps in the timely detection of potential problems and the implementation of corresponding measures.

[0110] In summary, by using principal component analysis to extract the time-domain features of the rod-side cavity and the rodless cavity, as well as the corresponding hydraulic cylinder state, from the existing pressure signal, multiple features can be comprehensively considered, reducing data dimensionality, improving model interpretability, facilitating pattern recognition, and enhancing the monitoring accuracy of the hydraulic cylinder state.

[0111] S504: Based on the time-domain characteristic values ​​of the rod-side chamber and the rodless chamber of the existing pressure signal, the system parameters are obtained using the rewritten internal leakage diagnostic model:

[0112] {φ k :k=1,2,...,N}

[0113] Where, φ k Indicates system parameters.

[0114] S505: Using a binary value identification algorithm, based on the hydraulic cylinder state and system parameter φ corresponding to the pressure time-domain characteristic values ​​of the existing pressure signal. k The estimated sequence of system parameters η is obtained as follows:

[0115]

[0116] in, Let Ψ() represent the probability density function of the standard normal distribution, and let σ represent the cumulative distribution function. 2 Variance representing system noise express, Let represent the estimated value of the parameters generated in the t-th iteration. This represents the estimated value of the parameters generated in the (t+1)th iteration. T This indicates the transpose operation.

[0117] In this invention, by being able to handle the uncertainty and randomness of system parameters, the requirements for input and output data are relatively low, and relatively accurate parameter estimation results can be obtained.

[0118] S506: Iteratively calculate the estimated sequence of system parameters η. When the termination condition is met, stop the iteration and output the current estimated values ​​of system parameters.

[0119] S507: Based on the estimated system parameters, obtain the internal leakage diagnostic model after parameter estimation:

[0120]

[0121] in, This represents an estimate of η. This represents t that satisfies the preset conditions.

[0122] Optionally, the termination condition is:

[0123]

[0124] Where ∈ represents a constant.

[0125] In this invention, through iterative calculation and model updating, the binary value identification algorithm can continuously optimize the parameter estimation sequence until the termination condition is met, thereby obtaining a more accurate system parameter estimate, providing a reliable basis for subsequent internal leakage diagnosis.

[0126] Furthermore, parameter estimation using the binary value identification algorithm can handle the uncertainty and randomness of the system, reduce data requirements, obtain accurate parameter estimation results, improve system performance, and has advantages such as flexibility and adjustability, which helps to improve the accuracy and reliability of the internal leakage diagnosis model.

[0127] S6: Based on the internal leakage diagnostic model after parameter estimation, diagnose the internal leakage fault of the hydraulic cylinder.

[0128] It should be noted that, based on the internal leakage diagnostic model after parameter estimation, it is possible to determine whether internal leakage has occurred based on the new measurement signals. Signals are acquired to obtain the (N+1)th pressure signal sequence; feature extraction and principal component analysis are performed on the (N+1)th pressure signal sequence to calculate... As a result, if If no leakage occurs, then no internal leakage has occurred; otherwise, internal leakage has occurred.

[0129] After completing the above steps, the actual state of the hydraulic cylinder is confirmed, thus obtaining a new set of data. At this point, N is updated to N+1, and a new estimate of η is recalculated. This process of continuously accumulating new data and updating the estimate of η is repeated.

[0130] In this invention, by continuously updating the parameter estimate η, the internal leakage diagnostic model can be continuously optimized based on new data, making it more consistent with the actual situation and improving the accuracy and reliability of the diagnosis.

[0131] Furthermore, by continuously accumulating new data and updating parameter estimates, data-driven decision-making can be achieved, allowing for timely adjustments to diagnostic models and maintenance strategies to ensure the normal operation of hydraulic cylinders and improve the reliability and stability of the equipment.

[0132] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0133] In this invention, pressure signals from the rodless chamber and the rod chamber are acquired, and time-domain feature values ​​of the pressure signals are extracted respectively. These time-domain feature values ​​provide a direct representation of the equipment's operational status. Principal component analysis (PCA) is used to reduce the dimensionality of the time-domain feature values, selecting principal components. PCA identifies the main directions of change in the data, retaining the most important information while removing redundant information, thus improving the accuracy of internal leakage fault identification. A binary value identification algorithm is used to estimate the parameters of the internal leakage diagnostic model. This algorithm continuously optimizes the parameter estimation sequence until a termination condition is met, resulting in more accurate system parameter estimates. Based on the internal leakage diagnostic model with the estimated parameters, internal leakage faults in the hydraulic cylinder are diagnosed, improving the accuracy of internal leakage fault identification and avoiding the need for the hydraulic cylinder to stop normal operation during diagnosis, thereby enhancing the real-time performance of internal leakage fault detection.

[0134] Reference manual attached Figure 3 The diagram shows a structural schematic of an internal leakage fault diagnosis device for a hydraulic cylinder provided in an embodiment of the present invention.

[0135] This invention provides a hydraulic cylinder internal leakage fault diagnosis device 20, comprising:

[0136] Acquisition module 201 is used to acquire rodless chamber pressure signals and rod chamber pressure signals;

[0137] Extraction module 202 is used to extract the time-domain feature values ​​of the rodless cavity pressure signal and the rod cavity pressure signal, respectively;

[0138] The selection module 203 is used to perform dimensionality reduction on the time-domain feature values ​​through principal component analysis to select the time-domain feature values ​​of the principal components.

[0139] Module 204 is used to construct an internal leakage diagnostic model based on the principal component time-domain characteristic values ​​of the rodless chamber pressure signal and the rod chamber pressure signal;

[0140] The estimation module 205 is used to estimate the parameters of the internal leakage diagnostic model using a binary value identification algorithm;

[0141] The diagnostic module 206 is used to diagnose internal leakage faults in hydraulic cylinders based on the internal leakage diagnostic model after parameter estimation.

[0142] In one possible implementation, the selection module is specifically used for:

[0143] The extracted time-domain feature values ​​are stored as an m×n dimensional feature matrix:

[0144]

[0145] Where X represents the characteristic matrix, a mn Let n represent the nth feature of the mth sample, where m represents the total number of samples and n represents the total number of time-domain feature values.

[0146] Calculate the mean of the dataset in each column of the feature matrix;

[0147] The feature matrix is ​​zero-mean normalized based on the mean of each column of the dataset.

[0148]

[0149] Where X0 represents the feature matrix after zero-mean normalization, u n The nth column represents the mean of the dataset; multiplying the zero-mean eigenma matrix on the right by a full-rank matrix yields the target matrix:

[0150] Y = X0·P

[0151] Where Y represents the target matrix and P represents a full-rank matrix;

[0152] Calculate the variance of each column in the target matrix:

[0153]

[0154] Among them, Var(b i ) represents the variance of the i-th column in the target matrix, b i Let () represent the column vector of the i-th column in the target matrix. T b represents the transpose of a matrix; ji Let r represent the element in the j-th row and i-th column, and r represent the number of columns in the target matrix;

[0155] Calculate the covariance of any two columns in the target matrix:

[0156]

[0157] Among them, Cov(b i ,b j ) represents the covariance between the i-th and j-th columns in the target matrix, b j Represents the column vector of the j-th column in the target matrix;

[0158] Construct the covariance matrix based on the variance of each column in the target matrix and the covariance of any two columns in the target matrix:

[0159]

[0160] By performing similarity diagonalization on the covariance matrix, an orthogonal matrix is ​​determined:

[0161]

[0162] Where Q represents an orthogonal matrix [Q1, Q2, ..., Q] composed of eigenvectors. n ], λ i Let Q represent the i-th time-domain eigenvalue. i Let λ represent the i-th eigenvector. i With Q i One-to-one correspondence;

[0163] Sort the time-domain eigenvalues ​​of the orthogonal matrix in descending order;

[0164] The principal component time-domain feature values ​​whose cumulative variance contribution rate is greater than the preset contribution rate are retained.

[0165] Construct the principal component matrix based on the eigenvectors corresponding to the temporal eigenvalues ​​of the principal components;

[0166] The dimensionality of the feature matrix is ​​reduced using the principal component matrix:

[0167] Y t =X·P t

[0168] Among them, Y t Let P represent the feature matrix after dimensionality reduction. t This represents the principal component matrix.

[0169] In one possible implementation, the building module is specifically used for:

[0170] Using the principal component time-domain eigenvalues ​​of the rodless chamber pressure signal and the rod chamber pressure signal as independent variables, an internal leakage diagnostic model is constructed:

[0171]

[0172]

[0173] Among them, y k α represents the health status of the hydraulic cylinder determined based on the pressure signal acquired in the kth sampling. i The diagnostic coefficient, x, represents the time-domain eigenvalue of the i-th principal component of the rod chamber pressure signal. i (k) represents the time-domain feature value of the i-th principal component extracted from the pressure signal acquired in the k-th time, β j z represents the diagnostic coefficient of the time-domain eigenvalue of the j-th principal component of the rodless chamber pressure signal. j (k) represents the time-domain feature value of the j-th principal component extracted from the pressure signal acquired in the k-th time, where α = [α1, α2, ..., αk]. n ] T and β=[β1,β2,...,β n ] T The parameters of the model are: d(k) represents the system noise at the k-th acquisition, C represents the internal leakage threshold, and s represents the internal leakage indicator function. k This represents the internal leakage fault diagnosis result determined based on the pressure signal collected in the kth iteration, and I represents the indicative function.

[0174] In one possible implementation, the estimation module is specifically used for:

[0175] Let w k =y(k)-C, rewrite the internal leakage diagnostic model:

[0176]

[0177] Let η = [α] T ,β T [C] T , φ k =[x T (k),z T (k),-1] T The internal leakage diagnostic model was rewritten:

[0178]

[0179] Principal component analysis was used to extract the time-domain eigenvalues ​​of the rod cavity and the rodless cavity, as well as the corresponding hydraulic cylinder states, from the existing pressure signal.

[0180] {x(k):k=1,2,...,N}

[0181] {z(k):k = 1, 2, ..., N}

[0182] {s k :k=1,2,...,N}

[0183] Where x(k) represents the time-domain feature value extracted from the rod chamber pressure signal acquired in the kth acquisition, z(k) represents the time-domain feature value extracted from the rodless chamber pressure signal acquired in the kth acquisition, and N represents the hydraulic cylinder state and the number of sets of extracted hydraulic chamber time-domain feature values;

[0184] Based on the time-domain characteristic values ​​of the rod-side cavity and the rodless cavity of the existing pressure signal, the system parameters are obtained using the rewritten internal leakage diagnostic model:

[0185] {φ k :k=1,2,...,N}

[0186] Where, φ k Indicates system parameters;

[0187] Using a binary value identification algorithm, based on the hydraulic cylinder state and system parameter φ corresponding to the pressure time-domain characteristic values ​​of the existing pressure signal... k The estimated sequence of system parameters η is obtained as follows:

[0188]

[0189] in, Let Ψ() represent the probability density function of the standard normal distribution, and let σ represent the cumulative distribution function. 2 Variance representing system noise express, Let represent the estimated value of the parameters generated in the t-th iteration. This represents the estimated value of the parameters generated in the (t+1)th iteration. T Indicates the transpose operation;

[0190] The system iteratively calculates the estimated sequence of system parameters η. When the termination condition is met, the iteration stops and the current estimated values ​​of system parameters are output.

[0191] Based on the estimated system parameters, the internal leakage diagnostic model after parameter estimation is obtained:

[0192]

[0193] in, This represents an estimate of η. This represents t that satisfies the preset conditions.

[0194] The hydraulic cylinder internal leakage fault diagnosis device 20 provided by the present invention can realize the above-mentioned hydraulic cylinder internal leakage fault diagnosis method and achieve the same or similar technical effects. To avoid repetition, the present invention will not elaborate further.

[0195] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0196] In this invention, pressure signals from the rodless chamber and the rod chamber are acquired, and time-domain feature values ​​of the pressure signals are extracted respectively. These time-domain feature values ​​provide a direct representation of the equipment's operational status. Principal component analysis (PCA) is used to reduce the dimensionality of the time-domain feature values, selecting principal components. PCA identifies the main directions of change in the data, retaining the most important information while removing redundant information, thus improving the accuracy of internal leakage fault identification. A binary value identification algorithm is used to estimate the parameters of the internal leakage diagnostic model. This algorithm continuously optimizes the parameter estimation sequence until a termination condition is met, resulting in more accurate system parameter estimates. Based on the internal leakage diagnostic model with the estimated parameters, internal leakage faults in the hydraulic cylinder are diagnosed, improving the accuracy of internal leakage fault identification and avoiding the need for the hydraulic cylinder to stop normal operation during diagnosis, thereby enhancing the real-time performance of internal leakage fault detection.

[0197] Reference manual attached Figure 4 The diagram shows a structural schematic of an internal leakage fault diagnosis system for a hydraulic cylinder provided by the present invention.

[0198] The present invention also provides a hydraulic cylinder internal leakage fault diagnosis system 30, applied to the above-mentioned hydraulic cylinder internal leakage fault diagnosis method, comprising:

[0199] Processor 301.

[0200] The memory 302 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 301, they implement the internal leakage fault diagnosis method for the hydraulic cylinder as described in the method embodiment.

[0201] The hydraulic cylinder internal leakage fault diagnosis system 30 provided by the present invention can perform the above-mentioned hydraulic cylinder internal leakage fault diagnosis method and achieve the same or similar technical effects. To avoid repetition, the present invention will not elaborate further.

[0202] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0203] In this invention, by acquiring pressure signals from the rodless chamber and the rod chamber, time-domain feature values ​​of the pressure signals are extracted respectively. Principal component analysis is used to reduce the dimensionality of the time-domain feature values, and principal component time-domain feature values ​​are selected. Based on the principal component time-domain feature values ​​of the pressure signals from the rodless chamber and the rod chamber, an internal leakage diagnostic model is constructed. A binary value identification algorithm is used to estimate the parameters of the internal leakage diagnostic model. Based on the internal leakage diagnostic model with the estimated parameters, the internal leakage fault of the hydraulic cylinder is diagnosed, which improves the accuracy of internal leakage fault identification, avoids the need for the hydraulic cylinder to stop normal operation during diagnosis, and improves the real-time performance of internal leakage fault detection.

[0204] It should be understood that the processor in the embodiments of the present invention can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0205] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0206] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0207] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0208] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0209] It should be understood that, in various embodiments of the present invention, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0210] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0211] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0212] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0213] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0214] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0215] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0216] This invention provides a computer-readable storage medium storing a computer program thereon, characterized in that, when executed by a processor, the program implements the method for diagnosing internal leakage faults in a hydraulic cylinder as described in the method embodiment.

[0217] The present invention provides a computer-readable storage medium that can implement the steps and effects of the hydraulic cylinder internal leakage fault diagnosis method of the above method embodiments. To avoid repetition, the present invention will not repeat them.

[0218] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0219] In this invention, pressure signals from the rodless chamber and the rod chamber are acquired, and time-domain feature values ​​of the pressure signals are extracted respectively. These time-domain feature values ​​provide a direct representation of the equipment's operational status. Principal component analysis (PCA) is used to reduce the dimensionality of the time-domain feature values, selecting principal components. PCA identifies the main directions of change in the data, retaining the most important information while removing redundant information, thus improving the accuracy of internal leakage fault identification. A binary value identification algorithm is used to estimate the parameters of the internal leakage diagnostic model. This algorithm continuously optimizes the parameter estimation sequence until a termination condition is met, resulting in more accurate system parameter estimates. Based on the internal leakage diagnostic model with the estimated parameters, internal leakage faults in the hydraulic cylinder are diagnosed, improving the accuracy of internal leakage fault identification and avoiding the need for the hydraulic cylinder to stop normal operation during diagnosis, thereby enhancing the real-time performance of internal leakage fault detection.

[0220] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0221] The following points need to be explained:

[0222] (1) The accompanying drawings of the embodiments of the present invention only involve the structures involved in the embodiments of the present invention. Other structures can refer to the general design.

[0223] (2) For clarity, the thickness of layers or regions is enlarged or reduced in the drawings used to describe embodiments of the present invention; that is, these drawings are not drawn to actual scale. It is understood that when an element such as a layer, film, region, or substrate is referred to as being “above” or “below” another element, the element may be “directly” located “above” or “below” the other element, or there may be intermediate elements.

[0224] (3) Where there is no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0225] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for diagnosing internal leakage faults in a hydraulic cylinder, characterized in that, The hydraulic cylinder comprises a cylinder barrel, a cylinder head, a piston, and a piston rod. The piston divides the cylinder barrel into two chambers: a rod chamber containing the piston rod and a rodless chamber without the piston rod. The method includes: S1: Acquire pressure signals from the rodless chamber and the rod chamber; S2: Extract the time-domain feature values ​​of the rodless cavity pressure signal and the rod cavity pressure signal respectively; S3: The time-domain eigenvalues ​​are reduced in dimensionality using principal component analysis to select the principal component time-domain eigenvalues. S4: Construct an internal leakage diagnostic model based on the principal component time-domain characteristic values ​​of the rodless cavity pressure signal and the rod cavity pressure signal; S5: Parameter estimation of the internal leakage diagnostic model is performed using a binary value identification algorithm; S6: Based on the internal leakage diagnostic model after parameter estimation, diagnose the internal leakage fault of the hydraulic cylinder.

2. The method for diagnosing internal leakage faults in a hydraulic cylinder according to claim 1, characterized in that, The time-domain feature values ​​specifically include: Maximum value, minimum value, average value, peak value, root square magnitude, standard deviation, root mean square, mean square deviation, variance, skewness, kurtosis, peak factor, impulse factor, margin factor and / or waveform factor.

3. The method for diagnosing internal leakage faults in a hydraulic cylinder according to claim 1, characterized in that, S3 specifically includes: S301: Store the extracted time-domain feature values ​​as... 3D feature matrix: ； in, X Represents the characteristic matrix, a mn Indicates the first m The first sample n One characteristic, m Represents the total number of samples. n This represents the total number of time-domain eigenvalues; S302: Calculate the mean of the dataset in each column of the feature matrix; S303: Perform zero-mean normalization on the feature matrix based on the mean of each column of the dataset: ； in, X 0 indicates the feature matrix after zero-mean normalization. u n Indicates the first n The mean of the column dataset; S304: Multiply the zero-mean eigenma matrix on the right by a full-rank matrix to obtain the target matrix: ； in, Y Represents the target matrix. P Represents a full-rank matrix; S305: Calculate the variance of each column in the target matrix: ； in, Represents the nth element in the target matrix i The variance of the column, b i Represents the nth element in the target matrix i The column vector of the column, ( ) T Represents the transpose of a matrix; b ji Indicates the first j Line number i Column elements, r Indicates the number of columns in the target matrix; S306: Calculate the covariance of any two columns in the target matrix: ； in, Represents the nth element in the target matrix i Column and number j The covariance of the column, b j Represents the nth element in the target matrix j The column vector of a column; S307: Construct a covariance matrix based on the variance of each column in the target matrix and the covariance of any two columns in the target matrix: ； S308: Perform similarity diagonalization on the covariance matrix to determine the orthogonal matrix: ； in, Q Represents an orthogonal matrix composed of eigenvectors , λ i Indicates the first i Each time-domain feature value, Q i Indicates the first i 1 eigenvector λ i and Q i One-to-one correspondence; S309: Sort the time-domain eigenvalues ​​of the orthogonal matrix in descending order; S310: Principal component time-domain feature values ​​whose cumulative variance contribution rate is greater than the preset contribution rate are retained; S311: Construct the principal component matrix based on the eigenvectors corresponding to the temporal eigenvalues ​​of the principal components; S312: Dimensionality reduction of the feature matrix is ​​performed using the principal component matrix: ； in, Y t This represents the feature matrix after dimensionality reduction. P t This represents the principal component matrix.

4. The method for diagnosing internal leakage faults in a hydraulic cylinder according to claim 1, characterized in that, Specifically, S4 is: Using the principal component time-domain eigenvalues ​​of the rodless chamber pressure signal and the rod chamber pressure signal as independent variables, an internal leakage diagnostic model is constructed: ； ； in, y k Indicates according to the first k The health status of the hydraulic cylinder is determined by the pressure signal collected in the second test. α i The first part representing the rod chamber pressure signal i Diagnostic coefficients of the temporal eigenvalues ​​of the principal components x i ( k ) indicates according to the k The pressure signal collected the first time was extracted. i Temporal eigenvalues ​​of principal components β j The first line representing the rodless chamber pressure signal j Diagnostic coefficients of the temporal eigenvalues ​​of the principal components z j ( k ) indicates according to the k The pressure signal collected the first time was extracted. j Temporal eigenvalues ​​of principal components and Represents the parameters of the model. d ( k ) indicates the first k System noise during the first data acquisition C Indicates the internal leakage threshold. s This represents the internal leakage characteristic function. s k Indicates according to the first k The internal leakage fault diagnosis result determined by the pressure signal collected in the second test. I Represents the characteristic function.

5. The method for diagnosing internal leakage faults in a hydraulic cylinder according to claim 1, characterized in that, S5 specifically includes: S501: Order The internal leakage diagnostic model is rewritten as follows: ； ； S502: Set , The internal leakage diagnostic model is rewritten as follows: ； ； S503: Using the principal component analysis method, extract the time-domain characteristic values ​​of the rod cavity, the time-domain characteristic values ​​of the rodless cavity, and the corresponding hydraulic cylinder state of the existing pressure signal: ； ； ； in, x ( k ) indicates the first k The time-domain feature values ​​extracted from the rod chamber pressure signal acquired in the second acquisition. z ( k ) indicates the first k The time-domain feature values ​​extracted from the rodless cavity pressure signal acquired in the second acquisition. N This represents the hydraulic cylinder state and the number of sets of time-domain feature values ​​extracted from the two hydraulic chambers; S504: Based on the time-domain characteristic values ​​of the rod-side chamber and the rodless chamber of the existing pressure signal, the system parameters are obtained using the rewritten internal leakage diagnostic model: ； in, Φ k Indicates system parameters; S505: Using a binary value identification algorithm, based on the hydraulic cylinder state and system parameters corresponding to the pressure time-domain characteristic values ​​of the existing pressure signal. Φ k Obtain system parameters η Estimated sequence: ； in, The probability density function representing the standard normal distribution function. Ψ ( ) represents the cumulative distribution function. σ 2 Variance representing system noise k express, Indicates the first t The estimated values ​​of the parameters generated by the iteration. Indicates the first t The estimated value of the parameters generated by +1 iteration, ( ) T Indicates the transpose operation; S506: Iterative Calculation of System Parameters η The estimated sequence is obtained, and when the termination condition is met, the iteration stops and the current estimated values ​​of the system parameters are output. S507: Based on the estimated system parameters, obtain the internal leakage diagnostic model after parameter estimation: ； ； in, express η The estimated value, Indicates that the preset conditions are met. t .

6. The method for diagnosing internal leakage faults in a hydraulic cylinder according to claim 5, characterized in that, The termination condition is: ； in, Represents a constant.

7. A device for diagnosing internal leakage faults in a hydraulic cylinder, the device being used to implement the method for diagnosing internal leakage faults in a hydraulic cylinder as described in any one of claims 1-6, characterized in that, The device includes: The acquisition module is used to acquire pressure signals from the rodless chamber and the rod chamber. An extraction module is used to extract the time-domain feature values ​​of the rodless cavity pressure signal and the rod cavity pressure signal, respectively. The selection module is used to perform dimensionality reduction processing on the time-domain feature values ​​using principal component analysis to select the principal component time-domain feature values. A construction module is used to construct an internal leakage diagnostic model based on the principal component time-domain feature values ​​of the rodless cavity pressure signal and the rod cavity pressure signal; The estimation module is used to estimate the parameters of the internal leakage diagnostic model using a binary value identification algorithm; The diagnostic module is used to diagnose the internal leakage fault of the hydraulic cylinder based on the internal leakage diagnostic model after parameter estimation.

8. The internal leakage fault diagnosis device for hydraulic cylinders according to claim 7, characterized in that, The selection module is specifically used for: The extracted time-domain feature values ​​are stored as 3D feature matrix: ； in, X Represents the characteristic matrix, a mn Indicates the first m The first sample n One characteristic, m Represents the total number of samples. n This represents the total number of time-domain eigenvalues; Calculate the mean of the dataset in each column of the feature matrix; The feature matrix is ​​zero-mean normalized based on the mean of each column of the dataset. ； in, X 0 indicates the feature matrix after zero-mean normalization. u n Indicates the first n The mean of the column dataset; Multiplying the zero-mean eigenma matrix on the right by a full-rank matrix yields the target matrix: ； in, Y Represents the target matrix. P Represents a full-rank matrix; Calculate the variance of each column in the target matrix: ； in, Represents the nth element in the target matrix i The variance of the column, b i Represents the nth element in the target matrix i The column vector of the column, ( ) T Represents the transpose of a matrix; b ji Indicates the first j Line number i Column elements, r Indicates the number of columns in the target matrix; Calculate the covariance of any two columns in the target matrix: ； in, Represents the nth element in the target matrix i Column and number j The covariance of the column, b j Represents the nth element in the target matrix j The column vector of a column; Construct a covariance matrix based on the variance of each column in the target matrix and the covariance of any two columns in the target matrix: ； The covariance matrix is ​​diagonalized to determine the orthogonal matrix: ； in, Q Represents an orthogonal matrix composed of eigenvectors , λ i Indicates the first i Each time-domain feature value, Q i Indicates the first i 1 eigenvector λ i and Q i One-to-one correspondence; Sort the time-domain eigenvalues ​​of the orthogonal matrix in descending order; The principal component time-domain feature values ​​whose cumulative variance contribution rate is greater than the preset contribution rate are retained. Construct the principal component matrix based on the eigenvectors corresponding to the temporal eigenvalues ​​of the principal components; The feature matrix is ​​then reduced in dimensionality using the principal component matrix: ； in, Y t This represents the feature matrix after dimensionality reduction. P t This represents the principal component matrix.

9. The internal leakage fault diagnosis device for hydraulic cylinders according to claim 7, characterized in that, The building module is specifically used for: Using the principal component time-domain eigenvalues ​​of the rodless chamber pressure signal and the rod chamber pressure signal as independent variables, an internal leakage diagnostic model is constructed: ； ； in, y k Indicates according to the first k The health status of the hydraulic cylinder is determined by the pressure signal collected in the second test. α i The first part representing the rod chamber pressure signal i Diagnostic coefficients of the temporal eigenvalues ​​of the principal components x i ( k ) indicates according to the k The pressure signal collected the first time was extracted. i Temporal eigenvalues ​​of principal components β j The first line representing the rodless chamber pressure signal j Diagnostic coefficients of the temporal eigenvalues ​​of the principal components z j ( k ) indicates according to the k The pressure signal collected the first time was extracted. j Temporal eigenvalues ​​of principal components and Represents the parameters of the model. d ( k ) indicates the first k System noise during the first data acquisition C Indicates the internal leakage threshold. s This represents the internal leakage characteristic function. s k Indicates according to the first k The internal leakage fault diagnosis result determined by the pressure signal collected in the second test. I Represents the characteristic function.

10. The internal leakage fault diagnosis device for hydraulic cylinders according to claim 7, characterized in that, The estimation module is specifically used for: make The internal leakage diagnostic model is rewritten as follows: ； ； set up , The internal leakage diagnostic model is rewritten as follows: ； ； Using the principal component analysis method, the time-domain feature values ​​of the rod cavity and the rodless cavity, as well as the corresponding hydraulic cylinder state, of the existing pressure signal are extracted: ； ； ； Among them, among them, x ( k ) indicates the first k The time-domain feature values ​​extracted from the rod chamber pressure signal acquired in the second acquisition. z ( k ) indicates the first k The time-domain feature values ​​extracted from the rodless cavity pressure signal acquired in the second acquisition. N This represents the hydraulic cylinder state and the number of sets of time-domain feature values ​​extracted from the two hydraulic chambers; Based on the time-domain characteristic values ​​of the rod-side and rodless-side chambers of the existing pressure signal, the system parameters are obtained using the rewritten internal leakage diagnostic model: ； in, Indicates system parameters; Using a binary value identification algorithm, the hydraulic cylinder state and system parameters corresponding to the pressure time-domain feature values ​​of the existing pressure signal are analyzed. Obtain system parameters η Estimated sequence: ； in, The probability density function representing the standard normal distribution function. Ψ ( ) represents the cumulative distribution function. σ 2 Variance representing system noise k express, Indicates the first t The estimated values ​​of the parameters generated by the iteration. Indicates the first t The estimated value of the parameters generated by +1 iteration, ( ) T Indicates the transpose operation; Iterative calculation of system parameters η The estimated sequence is obtained, and when the termination condition is met, the iteration stops and the current estimated values ​​of the system parameters are output. Based on the estimated system parameters, the internal leakage diagnostic model after parameter estimation is obtained: ； ； in, express η The estimated value, Indicates that the preset conditions are met. t .

Images