Surgical robot fault analysis method, device and equipment and storage medium

By obtaining the motor speed data of the surgical robot and calculating the fault statistics, the problem of low accuracy caused by single data in the surgical robot fault analysis is solved, and the accuracy of fault analysis is improved.

CN119014985AActive Publication Date: 2024-11-26HARBIN SIZHERUI INTELLIGENT MEDICAL EQUIP CO LTD +1
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411138235.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-26
Estimated Expiration
2044-08-19

AI Technical Summary

Technical Problem

The reference data in surgical robot fault analysis is single, resulting in low accuracy of fault analysis.

Method used

By obtaining the motor speed data of the surgical robot, the target load matrix is ​​determined, and the first fault statistics and the second fault statistics are calculated based on the matrix to determine the fault analysis results.

Benefits of technology

It enriches the reference data for fault analysis, improves the accuracy of fault analysis, and can more accurately judge the fault condition of the surgical robot.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119014985A_ABST
    Figure CN119014985A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a surgical robot fault analysis method, device and equipment and a storage medium, and the method comprises the steps: obtaining the motor rotating speed data of a target surgical robot; determining a target load matrix corresponding to the motor rotating speed data, and determining a first fault statistic and a second fault statistic according to the target load matrix; and determining a target fault analysis result of the target surgical robot according to the first fault statistics and the second fault statistics. According to the technical scheme provided by the embodiment of the invention, the problems of relatively single fault analysis reference data and relatively low fault analysis accuracy of the surgical robot in the prior art are solved, fault analysis can be carried out based on the motor rotating speed data of the surgical robot, the fault analysis reference data are enriched, and the fault analysis accuracy is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of robot control technology, and in particular, to a surgical robot fault analysis method, device, equipment and storage medium. Background Art

[0002] In the field of surgical robot control, encoders play a key role. Surgical robots need to be able to perform various tasks, such as moving and grasping objects. However, due to many factors such as long-term workload, version iteration or system update, surgical robots may have many hidden faults. Therefore, it is necessary to evaluate the operating status of the equipment through the detection of physical phenomena or technical parameters to determine whether the equipment has failed. If a fault occurs, an alarm is triggered to further diagnose the cause and location of the fault, locate the fault, and predict potential faults that have not yet occurred.

[0003] Currently, robot faults are usually analyzed based on the data from the encoders in the surgical robot. The reference data for fault analysis is relatively simple, and there is a problem of low accuracy in fault analysis. Summary of the invention

[0004] The embodiments of the present invention provide a surgical robot fault analysis method, device, equipment and storage medium, which can perform fault analysis based on the motor speed data of the surgical robot, enrich the fault analysis reference data, and improve the accuracy of fault analysis.

[0005] In a first aspect, an embodiment of the present invention provides a method for analyzing a surgical robot failure, the method comprising:

[0006] Acquire motor speed data of the target surgical robot;

[0007] Determine a target load matrix corresponding to the motor speed data, and determine a first fault statistic and a second fault statistic according to the target load matrix;

[0008] A target fault analysis result of the target surgical robot is determined according to the first fault statistic and the second fault statistic.

[0009] In a second aspect, an embodiment of the present invention provides a surgical robot fault analysis device, the device comprising:

[0010] A motor speed data acquisition module, used to acquire the motor speed data of the target surgical robot;

[0011] A fault statistic determination module, used to determine a target load matrix corresponding to the motor speed data, and determine a first fault statistic and a second fault statistic according to the target load matrix;

[0012] A fault analysis module is used to determine a target fault analysis result of the target surgical robot according to the first fault statistic and the second fault statistic.

[0013] In a third aspect, an embodiment of the present invention provides a computer device, the computer device comprising:

[0014] one or more processors;

[0015] A memory for storing one or more programs;

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the surgical robot fault analysis method described in any embodiment.

[0017] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the surgical robot fault analysis method described in any embodiment.

[0018] The technical solution provided by the embodiment of the present invention obtains the motor speed data of the target surgical robot; determines the target load matrix corresponding to the motor speed data, and determines the first fault statistic and the second fault statistic according to the target load matrix; and determines the target fault analysis result of the target surgical robot according to the first fault statistic and the second fault statistic. The technical solution of the embodiment of the present invention solves the problem that the reference data for fault analysis of surgical robots is relatively single and the fault analysis accuracy is low in the prior art. Fault analysis can be performed based on the motor speed data of the surgical robot, enriching the fault analysis reference data and improving the fault analysis accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flow chart of a surgical robot fault analysis method provided by an embodiment of the present invention;

[0020] Figure 2 This is a flow chart of another method for analyzing a surgical robot failure provided by an embodiment of the present invention;

[0021] Figure 3 is a flow chart of a method for determining a target coefficient threshold provided by an embodiment of the present invention;

[0022] Figure 4 It is a workflow diagram for performing fault analysis of a surgical robot provided by an embodiment of the present invention;

[0023] Figure 5 It is a structural schematic diagram of a surgical robot fault analysis device provided by an embodiment of the present invention;

[0024] Figure 6 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Figure 1 It is a flow chart of a surgical robot fault analysis method provided by an embodiment of the present invention. The embodiment of the present invention can be applied to the scenario of analyzing whether a surgical robot has a fault. The method can be executed by a surgical robot fault analysis device, which can be implemented by software and / or hardware.

[0027] like Figure 1 As shown, the surgical robot fault analysis method includes the following steps:

[0028] S110, obtaining motor speed data of the target surgical robot.

[0029] The target surgical robot may be a surgical robot that needs to be analyzed for faults. The motor speed data may be the speed data of the motor in the target surgical robot. Optionally, a corresponding motor speed detection device may be provided in the target surgical robot to detect the motor speed of the target surgical robot, and to obtain the transfer data detected by the motor speed detection device, thereby obtaining the motor speed data.

[0030] S120, determining a target load matrix corresponding to the motor speed data, and determining a first fault statistic and a second fault statistic according to the target load matrix.

[0031] The target load matrix may be a residual load matrix corresponding to the oblique variance matrix. Exemplarily, the covariance matrix may be determined according to the motor speed data, and then the target load matrix may be determined based on the eigenvalues ​​and eigenvectors corresponding to the covariance matrix.

[0032] Furthermore, the first fault statistic and the second fault statistic can be reference data for analyzing the fault information of the target surgical robot. Specifically, the target load matrix can be substituted into the two formulas for obtaining the fault statistics, thereby obtaining the first fault statistic and the second fault statistic. Exemplarily, the squared prediction error statistic (SPE statistic) can be used as the first fault statistic, and T 2The statistic is used as the second fault statistic. Among them, the SPE statistic can monitor the state of multiple variables at the same time, indicating the degree of deviation of the real-time measurement sample value from the principal component model; T 2 The statistic indicates the degree to which the real-time measurement sample values ​​deviate from the principal component model in terms of change trend and amplitude.

[0033] S130. Determine a target fault analysis result of the target surgical robot according to the first fault statistic and the second fault statistic.

[0034] Among them, the target fault analysis result can be a fault analysis result of the target surgical robot determined based on the motor speed. Specifically, the target fault analysis result can be determined based on the values ​​of the first fault statistic and the second fault statistic. For example, when the first fault statistic is greater than the corresponding control threshold, it can be determined that the target fault analysis result is that there is a machine fault in the target surgical robot. This indicates that the correlation structure between the variables in the normal working state of the target surgical robot is destroyed, that is, a more serious fault has occurred. If only the second fault statistic exceeds the corresponding control threshold, it can be determined that the target fault analysis result is a disturbance alarm result, indicating that it may be caused by a disturbance under normal system operation, and there is no obvious fault.

[0035] The technical solution provided by the embodiment of the present invention obtains the motor speed data of the target surgical robot; determines the target load matrix corresponding to the motor speed data, and determines the first fault statistic and the second fault statistic according to the target load matrix; and determines the target fault analysis result of the target surgical robot according to the first fault statistic and the second fault statistic. The technical solution of the embodiment of the present invention solves the problem that the reference data for fault analysis of surgical robots is relatively single and the fault analysis accuracy is low in the prior art. Fault analysis can be performed based on the motor speed data of the surgical robot, enriching the fault analysis reference data and improving the fault analysis accuracy.

[0036] Figure 2 It is another flow chart of a surgical robot fault analysis method provided by an embodiment of the present invention. The embodiment of the present invention can be applied to the scenario of analyzing whether a surgical robot has a fault. Based on the above embodiment, this embodiment further explains how to determine the target load matrix corresponding to the motor speed data. The device can be implemented by software and / or hardware and integrated into a computer device with application development function.

[0037] like Figure 2 As shown, the surgical robot fault analysis method includes the following steps:

[0038] S210: Acquire motor speed data of the target surgical robot.

[0039] The target surgical robot may be a surgical robot that needs to be analyzed for faults. The motor speed data may be the speed data of the motor in the target surgical robot. Optionally, a corresponding motor speed detection device may be provided in the target surgical robot to detect the motor speed of the target surgical robot, and to obtain the transfer data detected by the motor speed detection device, thereby obtaining the motor speed data.

[0040] Optionally, after obtaining the motor speed data of the target surgical robot, the motor speed data can be decomposed based on a preset decomposition function to obtain multiple layers of initial wavelet coefficients; the initial wavelet coefficients can be adjusted based on a target coefficient threshold to obtain target wavelet coefficients; for each layer of the target wavelet coefficients, the low-frequency component, high-frequency component, low-pass filter conjugate value and high-pass filter conjugate value of the target wavelet coefficients are determined; based on the low-frequency component, high-frequency component, low-pass filter conjugate value and high-pass filter conjugate value of the multiple layers of the target wavelet coefficients, the filtered motor speed data is obtained, and then the operation of determining the target load matrix of the filtered motor speed data is performed.

[0041] Among them, the preset decomposition function can be a function for decomposing the motor speed data. By decomposing the motor speed data based on the preset decomposition function, multiple layers of initial wavelet coefficients can be obtained. The initial wavelet coefficients can be the original wavelet coefficients that have not been filtered. The target coefficient threshold can be a reference threshold for filtering the initial wavelet coefficients. Among them, the wavelet coefficients of the real signal are large, while the wavelet coefficients of the noise signal are small, so the smaller initial wavelet coefficients can be filtered based on the target coefficient threshold, that is, the noise data in the motor speed data is filtered. Among them, the target coefficient threshold can be adaptively adjusted according to the initial wavelet coefficients, that is, the target coefficient threshold can be adaptively adjusted according to the motor speed data. By matching the motor speed data with an adaptive target coefficient threshold, the data filtering effect can be enhanced.

[0042] Furthermore, the target wavelet coefficients may be initial wavelet coefficients after filtering. Specifically, the initial wavelet coefficients may be adjusted based on the target coefficient threshold, and the adjusted and unadjusted wavelet coefficients may be used as target wavelet coefficients. Furthermore, the low-frequency component, high-frequency component, low-pass filter conjugate value, and high-pass filter conjugate value of the target wavelet coefficients may be determined for each layer of the target wavelet coefficients; the filtered motor speed data may be obtained based on the low-frequency component, high-frequency component, low-pass filter conjugate value, and high-pass filter conjugate value of the target wavelet coefficients of the multiple layers, and then the operation of determining the target load matrix of the filtered motor speed data may be performed.

[0043] Exemplarily, the formulas for determining the low-frequency component, high-frequency component, low-pass filter conjugate value, and high-pass filter conjugate value of the target wavelet coefficient are as follows:

[0044]

[0045]

[0046] In the formula, j represents the number of layers, k represents the number of levels, j, k∈Z, c j+1,k ,d j+1,k are the wavelet transform coefficients after the (j+1)th layer processing The low-frequency and high-frequency components of are respectively the conjugate value of the low-pass filter and the conjugate value of the high-pass filter. Further, the motor speed data can be reconstructed based on the low-frequency component, high-frequency component, low-pass filter conjugate value and high-pass filter conjugate value of the target wavelet coefficient to obtain the filtered motor speed data. Exemplarily, the reconstructed formula is as follows:

[0047]

[0048] Optionally, the initial wavelet coefficients are adjusted based on the target coefficient threshold, including: when the initial wavelet coefficients are smaller than the target coefficient threshold, the initial wavelet coefficients are set to zero.

[0049] Optionally, determining the target coefficient threshold includes: determining a reference classification threshold based on the initial wavelet coefficients, and classifying the initial wavelet coefficients based on the reference classification threshold to obtain a first coefficient set and a second coefficient set; determining the between-class variance and the overall variance of the wavelet coefficients in the first coefficient set and the second coefficient set; determining the reference coefficient threshold based on the between-class variance and the overall variance, and when the current reference coefficient threshold is less than the previous reference coefficient threshold corresponding to the current reference coefficient threshold, using the current reference coefficient threshold as the target coefficient threshold.

[0050] Among them, the reference classification threshold can be a reference threshold for classifying the initial wavelet coefficients. Specifically, the reference classification threshold can be set manually or determined according to the extreme values ​​in the initial wavelet coefficients. For example, the average of the maximum and minimum values ​​in the initial wavelet coefficients can be taken as the reference classification threshold. The first coefficient set and the second coefficient set can be two sets obtained after classifying the initial wavelet coefficients. Exemplarily, the first coefficient set can be constructed based on the initial wavelet coefficients less than the reference classification threshold, and the second coefficient set can be constructed based on the initial wavelet coefficients greater than or equal to the reference classification threshold. Further, the inter-class variance can be the variance of the wavelet coefficients between different coefficient sets. The overall variance can be the sum of the inter-class variance and the intra-class variance. Among them, the intra-class variance can be the variance of the wavelet coefficients within the same coefficient set. Specifically, the variance A1 of the wavelet coefficients within the first coefficient set and the variance A2 of the wavelet coefficients within the second coefficient set can be determined, and finally A2 and A1 are weighted summed to obtain the intra-class variance.

[0051] Further, the ratio of the between-class variance and the overall variance can be calculated, and the obtained ratio can be used as the reference coefficient threshold. The current reference coefficient threshold can be the reference coefficient threshold determined at the current number of iterations. Correspondingly, the previous reference coefficient threshold can be the reference coefficient threshold determined at the previous number of iterations corresponding to the current number of iterations. Further, the current reference coefficient threshold can be compared with the previous reference coefficient threshold, and when the current reference coefficient threshold is less than the corresponding previous reference coefficient threshold, the current reference coefficient threshold is used as the target coefficient threshold. When the current reference coefficient threshold is not greater than the corresponding previous reference coefficient threshold, the iteration step can be restarted from the step of determining the reference classification threshold.

[0052] For example, Figure 3 is a flow chart of a method for determining a target coefficient threshold provided by an embodiment of the present invention. Figure 3 As shown, the method for determining the target coefficient threshold includes the following steps:

[0053] (1) Suppose the wavelet coefficients that need threshold processing among the coefficients after wavelet transformation are W j,k ;

[0054] (2) Determine the initial parameter r m and λ j,m The initial value of m is 1, r m The initial value of is set to infinite, λ j,m is defined as:

[0055] λ j,m =(w j,k,min +w j,k,max ) / 2, where w j,k,min is the minimum wavelet transform coefficient, w j,k,max is the largest wavelet transform coefficient, and each wavelet transform coefficient w is calculated at the same time j,k The probability of occurrence p j,k .

[0056]

[0057] Among them, n j,k is the wavelet coefficient W j,k The number of occurrences, N is the total number of wavelet coefficients.

[0058] (3) According to λ j,m , the wavelet transform coefficients are divided into two parts, namely H1 = {w j,k ,|w j,k |<λ j,m} and H2={w,|w j,k |≥λ j,m}, and calculate the occurrence probabilities ζ1 and ζ2 of the two parts, as well as the means ε1 and ε2. The mean is defined as:

[0059]

[0060]

[0061] Among them, h1 and h2 are the number of times the two parts of the wavelet H1 and H2 appear after decomposition, and N is the total number of wavelet coefficients.

[0062]

[0063]

[0064] Calculate the variance of the two-part sum, that is:

[0065]

[0066]

[0067] (4) Calculate the intra-class variance, inter-class variance, and overall variance, that is,

[0068]

[0069]

[0070]

[0071] (5) m = m + 1, calculate the ratio of the between-class variance to the overall variance According to the calculated mean, the new threshold λ is obtained again j,m =(ε1+ε2) / 2.

[0072] (6) If r m <r m-1 Then the iteration ends and jumps to step (7), and the threshold λ at this time j,m is the optimal threshold; otherwise, return to step (3) for iterative calculation;

[0073] (7) Bringing the obtained optimal threshold into the adaptive threshold wavelet denoising function, and using the optimal threshold to process the wavelet transform coefficients;

[0074]

[0075] Where λ is the adaptive threshold λ obtained after processing from step (1) to step (6) j,m , j is the decomposition scale, a is any positive constant, w j,k are the wavelet transform coefficients, are the processed wavelet transform coefficients.

[0076] S220 . Determine a covariance matrix according to the motor speed data, and determine an eigenvalue matrix and an eigenvector matrix corresponding to the covariance matrix.

[0077] The oblique variance matrix may be a covariance matrix corresponding to the motor speed data. Further, the eigenvalues ​​and eigenvectors corresponding to the oblique variance matrix may be determined, thereby obtaining an eigenvalue matrix and an eigenvector matrix.

[0078] S230, determining average eigenvalues ​​and variance cumulative sum percentages according to the eigenvalue matrix and the eigenvector matrix, and determining a target load matrix according to the average eigenvalues ​​and variance cumulative sum percentages.

[0079] Among them, the average value of all eigenvalues ​​in the eigenvalue matrix can be determined, and the obtained average value is used as the average eigenvalue. The formula for determining the cumulative sum percentage of variance (CPV) is as follows:

[0080]

[0081] Among them, λ i is the eigenvalue, and m is the number of variables in the motor speed data.

[0082] Further, when the variance cumulative sum percentage is greater than a preset threshold, the number of principal components can be determined, and the target load matrix can be determined based on the number of principal components. The target load matrix can be the residual load matrix corresponding to the oblique variance matrix. Specifically, the target load matrix P is determined e The formula is as follows:

[0083] P e =R m×(m-k)

[0084] S240. Determine a first fault statistic and a second fault statistic according to the target load matrix.

[0085] The first fault statistic and the second fault statistic may be reference data for analyzing the fault information of the target surgical robot. For example, the squared prediction error statistic (SPE statistic) may be used as the first fault statistic, and T 2 The statistic is used as the second fault statistic. Among them, the SPE statistic can monitor the state of multiple variables at the same time, indicating the degree of deviation of the real-time measurement sample value from the principal component model; T 2The statistic indicates the degree to which the real-time measurement sample value deviates from the principal component model in terms of change trend and amplitude. Specifically, the formula for determining the first fault statistic and the second fault statistic is as follows:

[0086]

[0087] Among them, the data set X∈R of the motor speed data n×m , is the data after X is standardized, is the model value of the matrix X, I is the identity matrix, is the target load matrix.

[0088]

[0089] Among them, t i is the principal component score matrix The i-th pivot score in , Λ∈R kxk is a diagonal matrix consisting of the eigenvalues ​​corresponding to the first k principal elements, is the target load matrix, is the sampled data X∈R n×m Standardizing Data The i-th row of .

[0090] S250. Determine a target fault analysis result of the target surgical robot according to the first fault statistic and the second fault statistic.

[0091] Optionally, the position feedback data of the encoder in the target surgical robot can also be obtained, and the reference motor speed data can be determined based on the position feedback data; the reference fault analysis result can be determined based on the reference motor speed data, and the robot fault analysis result can be determined based on the target fault analysis result and the reference fault analysis result.

[0092] Among them, the position feedback data may be the spatial position data of the target surgical robot. Among them, the position feedback data may include the absolute position and relative position of the target surgical robot. Specifically, the position feedback data may be obtained from the encoder in the target surgical robot. Further, the reference motor speed data may be the motor speed data determined based on the position feedback data. Optionally, a forward difference operation may be performed on the position feedback data to obtain the reference motor speed data. The reference fault analysis result may be a fault analysis result determined based on the reference motor speed data. Optionally, a first fault statistic and a second fault statistic corresponding to the reference motor speed data may also be determined, and then a reference fault analysis result may be determined based on the first fault statistic and the second fault statistic corresponding to the reference motor speed data. The robot fault analysis result may be a fault analysis result of the target surgical robot determined from multiple angles. Optionally, the target fault analysis result and the reference fault analysis result may be combined to obtain the robot fault analysis result.

[0093] For illustrative purposes, in order to better understand the technical solution provided by the present invention, specific embodiments are introduced below. Figure 4 FIG. 1 is a flowchart of a surgical robot fault analysis process provided by an embodiment of the present invention. Figure 4 As shown in the figure, the workflow of surgical robot fault analysis includes the following steps: on the one hand, the target speed signal data output by the motor of the surgical robot is obtained, and on the other hand, the encoder position feedback signal data is forward-differentiated to obtain the reference speed signal data, and then the target speed signal data and the reference speed signal data are subjected to the same denoising, and the statistics are calculated and the steps of fault analysis are determined according to the statistics, and the corresponding fault source is determined in the case of a fault. The following introduces the three aspects of signal denoising, determination of the target load matrix, and fault analysis.

[0094] (1) The speed signal is denoised using wavelet denoising with adaptive threshold (i.e. improved).

[0095] Wavelet transform is a time-frequency analysis method that can analyze the local characteristics of the signal. It has a higher frequency resolution in the low-frequency part and a higher time resolution in the high-frequency part. It can adapt to the needs of time-frequency signal analysis and process the details of the signal more carefully. The meaning of wavelet transform is to take a function called wavelet basis as a displacement b, and then make an inner product with the signal to be analyzed f(t) at different scales, that is,

[0096]

[0097] In the formula, φ a,b (t) is the wavelet basis function; a and b are the scale information factor and translation parameter factor respectively; L2 (R) represents the square integrable space. Generally, the discretization formulas of scale parameter a and translation parameter b are expressed as Therefore, the discrete wavelet function can be expressed as:

[0098]

[0099] The reconstruction formula is:

[0100]

[0101] In the formula, C is a constant that has nothing to do with the signal. It can be seen that j,k (t) is the convolution of the signal x(t) and the wavelet function.

[0102] The present invention uses the Mallat algorithm to perform convolution operations on wavelet coefficients and filter banks, thereby realizing rapid pyramidal multi-resolution decomposition of signals, which greatly reduces the complexity of traditional wavelet transform algorithms. The decomposition formula is:

[0103]

[0104]

[0105] In the formula, c j+1,k ,d j+1,k are the wavelet transform coefficients after the (j+1)th layer processing The low-frequency component (low-frequency component) and high-frequency component (detail component) of the image; are the conjugate values ​​of the low-pass and high-pass filters respectively.

[0106] In general, useful signals are expressed as low-frequency parts or relatively stable signals, while noise signals are expressed as high-frequency signals, so only high-frequency coefficients need to be processed. Because the wavelet coefficients obtained by wavelet transform contain important time-frequency information, the wavelet coefficients of the real signal are large, while the wavelet coefficients of the noise coefficients are small. Therefore, a threshold is set for the high-frequency coefficients, and the wavelet coefficients less than the threshold are set to zero. The signal after wavelet reconstruction can eliminate noise. The reconstruction formula is as follows:

[0107]

[0108] According to the above formula, the original signal can be restored. It can be seen from the process of wavelet denoising that the denoising result depends on the effect of the threshold processing step. In view of the shortcomings of traditional wavelet denoising at signal singular points, the present invention proposes an adaptive threshold processing method to process the encoder output signal.

[0109] The adaptive threshold processing flow is as described in the above step S210.

[0110] (II) Establishing the principal component statistical model

[0111] The present invention uses sample data of variables within a normal variation range to establish a principal component statistical model, which is a prerequisite for performing principal component analysis on the entire process variables.

[0112] Usually, the motor speed data set X∈R under normal equipment conditions n×m , n is the number of samples, and m is the number of variables. In order to remove the influence of data scale, X is first standardized to obtain

[0113]

[0114] Where V = [v1, v2, ..., v m ] is the mean of X, s=[s1,s2,…,s m ] is the standard deviation of X.

[0115] matrix Can be decomposed into:

[0116]

[0117] Among them, t i ∈R n is the principal component score vector, p i ∈R m is the load vector, and

[0118]

[0119] Where, T = [t1, t2, ..., t m ] is the score matrix, P = [p1, p2, ..., p m ] is the load matrix.

[0120] All score vectors and load vectors are orthogonal, that is, for any i≠j, In addition, the length of each load vector is 1, that is, when i=j, So we can get the following formula:

[0121]

[0122] Explain that each score vector is actually a data matrix The projection in the direction of the load vector corresponding to this score vector. Vector t i The length of the data matrix In p i The greater its length, In p iThe greater the coverage or range of variation in the direction. If the score vectors are sorted by their length:

[0123] ||t1||>||t2||>…>||t m ||

[0124] Then the load vector p1 will represent the data The direction of the greatest change, p2 is perpendicular to p1 and represents the data The second largest direction of change, p m Representative data The direction with the smallest change, matrix can be rewritten as:

[0125]

[0126] definition:

[0127]

[0128]

[0129] In the formula, k is the number of principal components, is a matrix The model value of is the pivot score matrix and is the target load matrix and E is the residual matrix, T e ∈R n×(m-k) is the residual score matrix, P e =R m×(m-k) is the residual loading matrix (also known as the target loading matrix).

[0130] but It can be expressed as:

[0131]

[0132] Pair Matrix Conducting principal component analysis is actually equivalent to The covariance matrix of is used for vector analysis. The loading vector of is actually the eigenvector of its covariance moment.

[0133] The covariance of is:

[0134]

[0135] Among them, λ i is the eigenvalue of Σ, and λ1≥λ2≥…≥λ m ≥0,p1,p2,…,pm is the eigenvector corresponding to these eigenvalues. Cumulative variance and percentage CPV are usually used to determine the number of principal components, which can be expressed as:

[0136]

[0137] Generally, when the CPV of the current number of principal components k is ≥ 85%, it can be considered that the feature information of the current number of principal components k is able to describe the performance of the entire process, that is, the number of principal components is k.

[0138] (III) Fault diagnosis based on principal component analysis

[0139] Once the number of principal components is determined and the principal component model is established, the principal component model can be used to obtain the statistics of the real-time collected data samples for testing, and the fault can be detected based on whether the value of the statistic exceeds the control threshold. Commonly used statistics include SPE squared prediction error statistics and Hotelling's T 2 Statistics.

[0140] The SPE statistic can monitor the state of multiple variables at the same time. It represents the degree of deviation of the real-time measured sample value from the principal component model and is defined as follows:

[0141]

[0142] in, is the data after X is standardized, is the model value of the matrix X, I is the identity matrix, is the target load matrix.

[0143] T 2 The statistic indicates the degree to which the real-time measurement sample value deviates from the principal component model in terms of change trend and amplitude, and is defined as:

[0144]

[0145] Among them, t i is the principal component score matrix The i-th pivot score in , Λ∈R kxk is a diagonal matrix consisting of the eigenvalues ​​corresponding to the first k principal elements, is the target load matrix, is the sampled data X∈R n×m Standardizing Data The i-th row of .

[0146] It is generally believed that if the SPE statistic exceeds its control threshold, it indicates that the correlation structure between variables under normal working conditions is destroyed, that is, a fault has occurred; 2The statistic exceeds its control threshold, indicating that it may be caused by disturbances in the normal operation of the system without obvious faults.

[0147] The motor speed signal obtained by principal component model analysis and the encoder position feedback signal are forward-differentiated and the SPE statistics and T are calculated respectively. 2 Statistics are generated and graphs are drawn to monitor the system operation status. The graphs obtained from the two types of signals are compared by control thresholds to draw conclusions on whether the encoder is faulty.

[0148] The technical solution provided by the embodiment of the present invention obtains the motor speed data of the target surgical robot; determines the covariance matrix according to the motor speed data, and determines the eigenvalue matrix and eigenvector matrix corresponding to the covariance matrix; determines the average eigenvalue and the cumulative percentage of variance according to the eigenvalue matrix and the eigenvector matrix, and determines the target load matrix according to the average eigenvalue and the cumulative percentage of variance; determines the first fault statistic and the second fault statistic according to the target load matrix; determines the target fault analysis result of the target surgical robot according to the first fault statistic and the second fault statistic. The technical solution of the embodiment of the present invention solves the problem that the reference data for fault analysis of the surgical robot is relatively single and the fault analysis accuracy is low in the prior art. It can perform fault analysis based on the motor speed data of the surgical robot, enrich the fault analysis reference data, and improve the fault analysis accuracy.

[0149] Figure 5 It is a structural schematic diagram of a surgical robot fault analysis device provided in an embodiment of the present invention. The embodiment of the present invention can be applied to the scenario of analyzing whether a surgical robot has a fault. The device can be implemented by software and / or hardware and integrated into a computer device with application development capabilities.

[0150] like Figure 5 As shown, the surgical robot fault analysis device includes: a motor speed data acquisition module 310 , a fault statistics determination module 320 and a fault analysis module 330 .

[0151] Among them, the motor speed data acquisition module 310 is used to obtain the motor speed data of the target surgical robot; the fault statistics determination module 320 is used to determine the target load matrix corresponding to the motor speed data, and determine the first fault statistic and the second fault statistic according to the target load matrix; the fault analysis module 330 is used to determine the target fault analysis result of the target surgical robot according to the first fault statistic and the second fault statistic.

[0152] The technical solution provided by the embodiment of the present invention obtains the motor speed data of the target surgical robot; determines the target load matrix corresponding to the motor speed data, and determines the first fault statistic and the second fault statistic according to the target load matrix; and determines the target fault analysis result of the target surgical robot according to the first fault statistic and the second fault statistic. The technical solution of the embodiment of the present invention solves the problem that the reference data for fault analysis of surgical robots is relatively single and the fault analysis accuracy is low in the prior art. Fault analysis can be performed based on the motor speed data of the surgical robot, enriching the fault analysis reference data and improving the fault analysis accuracy.

[0153] In an optional embodiment, the fault statistics determination module 320 includes: a load matrix determination unit, used to: determine the covariance matrix based on the motor speed data, and determine the eigenvalue matrix and eigenvector matrix corresponding to the covariance matrix; determine the average eigenvalue and the cumulative sum percentage of the variance based on the eigenvalue matrix and the eigenvector matrix, and determine the target load matrix based on the average eigenvalue and the cumulative sum percentage of the variance.

[0154] In an optional embodiment, the load matrix determination unit includes: a target load matrix determination subunit, used to: determine the target number of principal components based on the average eigenvalue and the cumulative sum of variance percentage; wherein the target number of principal components represents the number of key data in the target load matrix; determine the target load matrix based on the target number of principal components.

[0155] In an optional embodiment, the surgical robot fault analysis device also includes: a speed data filtering module, which is used to: decompose the motor speed data based on a preset decomposition function to obtain multiple layers of initial wavelet coefficients; adjust the initial wavelet coefficients based on a target coefficient threshold to obtain target wavelet coefficients; for each layer of the target wavelet coefficients, determine the low-frequency component, high-frequency component, low-pass filter conjugate value and high-pass filter conjugate value of the target wavelet coefficients; obtain the filtered motor speed data based on the low-frequency component, high-frequency component, low-pass filter conjugate value and high-pass filter conjugate value of the target wavelet coefficients of the multiple layers, and then perform the operation of determining the target load matrix of the filtered motor speed data.

[0156] In an optional embodiment, the speed data filtering module includes: a target coefficient threshold determination unit, which is used to: determine a reference classification threshold based on the initial wavelet coefficients, and classify the initial wavelet coefficients based on the reference classification threshold to obtain a first coefficient set and a second coefficient set; determine the inter-class variance and the overall variance of the wavelet coefficients in the first coefficient set and the second coefficient set; determine the reference coefficient threshold based on the inter-class variance and the overall variance, and when the current reference coefficient threshold is less than the previous reference coefficient threshold corresponding to the current reference coefficient threshold, use the current reference coefficient threshold as the target coefficient threshold.

[0157] In an optional implementation, the rotation speed data filtering module includes: a wavelet coefficient adjustment unit, configured to: set the initial wavelet coefficient to zero when the initial wavelet coefficient is less than the target coefficient threshold.

[0158] In an optional embodiment, the surgical robot fault analysis device also includes: a reference speed analysis module, which is used to: obtain position feedback data of the encoder in the target surgical robot, and determine reference motor speed data based on the position feedback data; determine a reference fault analysis result based on the reference motor speed data, and determine a robot fault analysis result based on the target fault analysis result and the reference fault analysis result.

[0159] The surgical robot fault analysis device provided in the embodiment of the present invention can execute the surgical robot fault analysis method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0160] 6 is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. 6 shows a block diagram of an exemplary computer device 12 suitable for implementing an embodiment of the present invention. The computer device 12 shown in 6 is only an example and should not bring any limitation to the functions and scope of use of the embodiment of the present invention. The computer device 12 can be any terminal device with computing capabilities and can be configured in the surgical robot fault analysis device.

[0161] As shown in FIG6 , computer device 12 is implemented as a general purpose computing device. Components of computer device 12 may include, but are not limited to, one or more processors or processing units 16, system memory 28, and bus 18 that connects various system components (including system memory 28 and processing unit 16).

[0162] The bus 18 may be one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. For example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0163] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0164] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media (not shown in FIG6 , commonly referred to as a "hard drive"). Although not shown in FIG6 , a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data media interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of various embodiments of the present invention.

[0165] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0166] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. In addition, the computer device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown in FIG. 6, the network adapter 20 communicates with other modules of the computer device 12 via a bus 18. It should be understood that, although not shown in FIG. 6, other hardware and / or software modules may be used in conjunction with the computer device 12, including, but not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0167] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing the surgical robot fault analysis method provided in the embodiment of the present invention, the method comprising:

[0168] Acquire motor speed data of a target surgical robot; determine a target load matrix corresponding to the motor speed data, and determine a first fault statistic and a second fault statistic based on the target load matrix; determine a target fault analysis result of the target surgical robot based on the first fault statistic and the second fault statistic.

[0169] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, a surgical robot fault analysis method as provided in any embodiment of the present invention is implemented, including:

[0170] Acquire motor speed data of a target surgical robot; determine a target load matrix corresponding to the motor speed data, and determine a first fault statistic and a second fault statistic based on the target load matrix; determine a target fault analysis result of the target surgical robot based on the first fault statistic and the second fault statistic.

[0171] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0172] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0173] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0174] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or combinations thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0175] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0176] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A surgical robot fault analysis method, characterized in that: include: Acquire motor speed data of the target surgical robot; Determine a target load matrix corresponding to the motor speed data, and determine a first fault statistic and a second fault statistic according to the target load matrix; A target fault analysis result of the target surgical robot is determined according to the first fault statistic and the second fault statistic.

2. The method according to claim 1, characterized in that: The determining of the target load matrix corresponding to the motor speed data includes: Determine a covariance matrix according to the motor speed data, and determine an eigenvalue matrix and an eigenvector matrix corresponding to the covariance matrix; The average eigenvalue and the cumulative sum of variance percentage are determined according to the eigenvalue matrix and the eigenvector matrix, and the target load matrix is ​​determined according to the average eigenvalue and the cumulative sum of variance percentage.

3. The method according to claim 2, characterized in that The step of determining the target load matrix according to the average eigenvalue and the cumulative variance percentage includes: Determine the target number of principal components according to the average eigenvalue and the cumulative sum of variance percentage; wherein the target number of principal components represents the number of key data in the target load matrix; The target load matrix is ​​determined according to the target number of principal elements.

4. The method according to claim 1, characterized in that: After obtaining the motor speed data of the target surgical robot, the method further includes: Decomposing the motor speed data based on a preset decomposition function to obtain multiple layers of initial wavelet coefficients; Adjusting the initial wavelet coefficients based on a target coefficient threshold to obtain target wavelet coefficients; For each layer of target wavelet coefficients, determine the low-frequency component, high-frequency component, low-pass filter conjugate value and high-pass filter conjugate value of the target wavelet coefficients; According to the low-frequency components, high-frequency components, low-pass filter conjugate values ​​and high-pass filter conjugate values ​​of the target wavelet coefficients of the multiple layers, the filtered motor speed data is obtained, and then the operation of determining the target load matrix of the filtered motor speed data is performed.

5. The method according to claim 4, characterized in that Determining the target coefficient threshold comprises: Determining a reference classification threshold according to the initial wavelet coefficients, and classifying the initial wavelet coefficients based on the reference classification threshold to obtain a first coefficient set and a second coefficient set; Determining the between-class variance and the overall variance of the wavelet coefficients in the first coefficient set and the second coefficient set; A reference coefficient threshold is determined according to the inter-class variance and the overall variance, and when a current reference coefficient threshold is less than a previous reference coefficient threshold corresponding to the current reference coefficient threshold, the current reference coefficient threshold is used as the target coefficient threshold.

6. The method according to claim 4, characterized in that The adjusting the initial wavelet coefficients based on the target coefficient threshold comprises: When the initial wavelet coefficient is less than the target coefficient threshold, the initial wavelet coefficient is set to zero.

7. The method according to claim 1, characterized in that The method further comprises: Acquire position feedback data of an encoder in the target surgical robot, and determine reference motor speed data according to the position feedback data; A reference fault analysis result is determined according to the reference motor speed data, and a robot fault analysis result is determined according to the target fault analysis result and the reference fault analysis result.

8. A surgical robot fault analysis device, characterized in that: The device comprises: A motor speed data acquisition module, used to acquire the motor speed data of the target surgical robot; A fault statistic determination module, used to determine a target load matrix corresponding to the motor speed data, and determine a first fault statistic and a second fault statistic according to the target load matrix; A fault analysis module is used to determine a target fault analysis result of the target surgical robot according to the first fault statistic and the second fault statistic.

9. A computer device, characterized in that: The computer device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the surgical robot fault analysis method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the surgical robot fault analysis method as described in any one of claims 1-7 is implemented.

Citation Information

Patent Citations

  • On-line monitoring and diagnosis method of AC (alternating current) motor based on statistical model

    CN102033200A

  • Small-fault detection method and device based on multiple moving average

    CN103776480A

  • Data driving method of fault detection and fault separation of drone flight control system

    CN107608335A

  • Early fault diagnosis method for high-speed train electric traction system aiming at data missing

    CN118013429A

  • Method and Apparatus for Detecting and Identifying Faults in a Process

    US20140365179A1