Robotic arm detection method, device, electronic device and storage medium

Abstract

The present application provides a method, apparatus, electronic device, and storage medium for detecting a robotic arm. The method comprises: determining a vibration signal to be detected from a vibration signal of the robotic arm; determining an energy entropy ratio of the vibration signal to be detected; and determining whether the robotic arm is abnormal based on the energy entropy ratio of the vibration signal to be detected. Determining whether the robotic arm is abnormal based on the energy entropy ratio of the vibration signal to be detected can accurately distinguish between a normal robotic arm and an abnormal robotic arm.

Description

Technical Field

[0001] The present application relates to the field of robotic arm industry, and more specifically, to a robotic arm detection method, device, electronic equipment, and storage medium. Background Art

[0002] The robotic arm is a typical example of an industrial robot. Its structure is similar to that of a human arm, typically consisting of an open chain of connecting rods connected in series. This is called a manipulator. The manipulator's transmission system is responsible for transmitting power to its various joints. Its operating status is directly related to the quality of its intended tasks. Therefore, monitoring and managing the vibration quality of the manipulator's transmission system is an essential component of the manipulator's production process.

[0003] Therefore, how to judge whether the robotic arm is normal is an urgent problem to be solved. Summary of the Invention

[0004] The purpose of this application is to address the deficiencies in the above-mentioned prior art and provide a method, device, electronic device and storage medium for detecting the constant speed working condition of a robotic arm based on energy-entropy ratio, so as to improve the accuracy of distinguishing normal robotic arms from abnormal robotic arms.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of the present application are as follows:

[0006] In a first aspect, an embodiment of the present application provides a robotic arm detection method, the method comprising:

[0007] Determining a vibration signal to be detected in the vibration signal of the robotic arm, wherein the vibration signal to be detected is a vibration signal corresponding to a preset speed range;

[0008] determining an energy entropy ratio of the vibration signal to be detected;

[0009] Whether the robotic arm is abnormal is determined according to the energy entropy ratio of the vibration signal to be detected.

[0010] Optionally, determining the energy entropy ratio of the vibration signal to be detected includes:

[0011] Performing spectrum transformation on the vibration signal to be detected to obtain a spectrum sequence of the vibration signal to be detected;

[0012] Calculating the permutation entropy of the spectrum of the vibration signal to be detected according to the spectrum sequence of the vibration signal to be detected to obtain the spectrum permutation entropy of the vibration signal to be detected;

[0013] The energy entropy ratio of the vibration signal to be detected is determined according to the spectral arrangement entropy.

[0014] Optionally, calculating the permutation entropy of the spectrum of the vibration signal to be detected according to the spectrum sequence of the vibration signal to be detected to obtain the spectrum permutation entropy of the vibration signal to be detected includes:

[0015] Performing phase space reconstruction on the frequency spectrum sequence of the vibration signal to be detected to obtain a reconstructed frequency spectrum of the vibration signal to be detected;

[0016] sorting the reconstructed frequency spectrum of the vibration signal to be detected to obtain a reconstructed sequence;

[0017] The permutation entropy of the frequency spectrum of the vibration signal to be detected is calculated according to the reconstructed sequence to obtain the permutation entropy of the spectrum of the vibration signal to be detected.

[0018] Optionally, calculating the permutation entropy of the frequency spectrum of the vibration signal to be detected according to the reconstructed sequence includes:

[0019] Calculating the probability of each sequence in the reconstructed sequence appearing in all sequences, and calculating the first permutation entropy of the frequency spectrum of the vibration signal to be detected based on the probability of each sequence;

[0020] Normalization is performed on the first permutation entropy to obtain the spectral permutation entropy of the vibration signal to be detected.

[0021] Optionally, determining the energy entropy ratio of the vibration signal to be detected according to the spectral arrangement entropy includes:

[0022] Calculating the root mean square of the vibration signal to be detected;

[0023] The energy entropy ratio is calculated based on the root mean square of the vibration signal to be detected and the spectral permutation entropy.

[0024] Optionally, the step of determining a vibration signal to be detected in the vibration signal of the robotic arm, wherein the vibration signal to be detected is a vibration signal corresponding to a preset speed range, includes:

[0025] Preprocessing the vibration signal of the robotic arm;

[0026] A uniform vibration signal is extracted from the preprocessed vibration signal of the robotic arm.

[0027] Optionally, determining the vibration signal to be detected in the vibration signal of the robotic arm includes:

[0028] A signal segment corresponding to the vibration signal is selected according to the preset rotation speed segment of the robotic arm as the vibration signal to be detected.

[0029] In a second aspect, an embodiment of the present application further provides a robotic arm detection device, the device comprising:

[0030] a determination module, configured to determine a vibration signal to be detected in the vibration signal of the robotic arm, wherein the vibration signal to be detected is a vibration signal corresponding to a preset speed range;

[0031] A determination module, configured to determine the energy entropy ratio of the vibration signal to be detected;

[0032] A determination module is used to determine whether the robotic arm is abnormal based on the energy entropy ratio of the vibration signal to be detected.

[0033] Optionally, the determining module is specifically configured to:

[0034] Performing spectrum transformation on the vibration signal to be detected to obtain a spectrum sequence of the vibration signal to be detected;

[0035] Calculating the permutation entropy of the spectrum of the vibration signal to be detected according to the spectrum sequence of the vibration signal to be detected to obtain the spectrum permutation entropy of the vibration signal to be detected;

[0036] The energy entropy ratio of the vibration signal to be detected is determined according to the spectral arrangement entropy.

[0037] Optionally, the determining module is specifically configured to:

[0038] Performing phase space reconstruction on the frequency spectrum sequence of the vibration signal to be detected to obtain a reconstructed frequency spectrum of the vibration signal to be detected;

[0039] sorting the reconstructed frequency spectrum of the vibration signal to be detected to obtain a reconstructed sequence;

[0040] The permutation entropy of the frequency spectrum of the vibration signal to be detected is calculated according to the reconstructed sequence to obtain the permutation entropy of the spectrum of the vibration signal to be detected.

[0041] Optionally, the determining module is specifically configured to:

[0042] Calculating the probability of each sequence in the reconstructed sequence appearing in all sequences, and calculating the first permutation entropy of the frequency spectrum of the vibration signal to be detected based on the probability of each sequence;

[0043] Normalization is performed on the first permutation entropy to obtain the spectral permutation entropy of the vibration signal to be detected.

[0044] Optionally, the determining module is specifically configured to:

[0045] Calculating the root mean square of the vibration signal to be detected;

[0046] The energy entropy ratio is calculated based on the root mean square of the vibration signal to be detected and the spectral permutation entropy.

[0047] Optionally, the determining module is specifically configured to:

[0048] Preprocessing the vibration signal of the robotic arm;

[0049] A uniform vibration signal is extracted from the preprocessed vibration signal of the robotic arm.

[0050] Optionally, the determining module is specifically configured to:

[0051] According to the preset speed segment, a uniform vibration signal corresponding to the preset speed segment is selected from the uniform vibration signals as the vibration signal to be detected.

[0052] In a third aspect, an embodiment of the present application further provides an electronic device comprising: a processor, a storage medium and a bus, wherein the storage medium stores program instructions executable by the processor. When the application is running, the processor communicates with the storage medium through the bus, and the processor executes the program instructions to perform the steps of the robotic arm detection method described in the first aspect above.

[0053] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program is read and executes the steps of the robotic arm detection method described in the first aspect above.

[0054] The beneficial effects of this application are:

[0055] The present application provides a method, device, electronic device, and storage medium for detecting a robotic arm. The method comprises determining a vibration signal to be detected in the vibration signal of the robotic arm; determining the energy entropy ratio of the vibration signal to be detected; and determining whether the robotic arm is abnormal based on the energy entropy ratio of the vibration signal to be detected. Whether the robotic arm is abnormal is determined by the energy entropy ratio of the vibration signal to be detected. The energy entropy ratio of the vibration signal of a normal robotic arm is highly stable and has small fluctuations, while the energy entropy ratio of the vibration signal of an abnormal robotic arm is less stable and has large fluctuations. The energy entropy ratio of the vibration signal of a normal robotic arm is significantly smaller than the energy entropy ratio of the vibration signal of an abnormal robotic arm, and there is a clear dividing line between the two. Therefore, a normal robotic arm and an abnormal robotic arm can be clearly and accurately distinguished. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0057] Figure 1 A schematic diagram of an exemplary scenario provided in an embodiment of the present application;

[0058] Figure 2 A schematic diagram of a flow chart of a robotic arm detection method provided in an embodiment of the present application;

[0059] Figure 3 A schematic flow chart of a method for determining an energy-entropy ratio according to an embodiment of the present application;

[0060] Figure 4 A schematic flow chart of a method for determining spectral permutation entropy provided in an embodiment of the present application;

[0061] Figure 5 A schematic flow chart of another method for determining spectral permutation entropy provided in an embodiment of the present application;

[0062] Figure 6 A flow chart of another method for determining the energy-entropy ratio provided in an embodiment of the present application;

[0063] Figure 7 A schematic diagram of the actual verification results provided by the embodiment of the present application;

[0064] Figure 8 Another schematic diagram of actual verification results provided by an embodiment of the present application;

[0065] Figure 9 A schematic diagram of a device for a robotic arm detection method provided in an embodiment of the present application;

[0066] Figure 10 This is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of illustration and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts can be implemented out of sequence, and steps without logical context can be reversed or implemented simultaneously. In addition, those skilled in the art, under the guidance of the contents of this application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0068] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0069] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0070] Figure 1 An exemplary scenario diagram provided in an embodiment of the present application is as follows: Figure 1 As shown, the method is applied to a scenario where the motion state of a robotic arm is detected to determine whether it is normal. This scenario involves a robotic arm being detected and an electronic device. The electronic device can be, for example, a terminal device with computing and display capabilities, such as a desktop computer or laptop computer, or a server. The electronic device is in communication with the robotic arm.

[0071] Among them, when the robotic arm rotates, the electronic device can obtain the vibration signal of the robotic arm. The electronic device detects the received vibration signal using the method of the embodiment of the present application to obtain a detection result, and determines whether the robotic arm is normal or abnormal in this motion state based on the detection result.

[0072] Figure 2 This is a flow chart of a method for detecting a robotic arm provided in an embodiment of the present application, wherein the execution subject of the method is the aforementioned electronic device. Figure 2 As shown, the method includes:

[0073] S101: Determine a vibration signal to be detected in a vibration signal of a robotic arm.

[0074] Among them, the vibration signal of the robotic arm may refer to the vibration signal when the robotic arm is in a rotational motion state. When the motion state of the robotic arm changes, the changed motion state may be manifested in the vibration signal. By detecting the vibration signal to be detected, the quality state of the robotic arm may be detected, and the quality state may include a normal state and an abnormal state.

[0075] Optionally, the robotic arm can have multiple speeds during the rotational movement, different speeds correspond to different speed segments, and different speed segments correspond to different vibration signals. The vibration signal to be detected is the vibration signal corresponding to the preset speed segment. That is to say, a speed segment is specified from multiple different speed segments, and the vibration signal corresponding to the speed segment is selected as the vibration signal to be detected to detect the motion quality state of the robotic arm in the speed segment.

[0076] S102: Determine the energy entropy ratio of the vibration signal to be detected.

[0077] Optionally, the energy entropy ratio of the vibration signal to be detected is determined based on the energy and spectral permutation entropy of the vibration signal to be detected, wherein the spectral permutation entropy can reflect the complexity and stability of the spectrum signal. When the spectral permutation entropy is relatively high, it indicates that the complexity of the spectrum signal is high. When the spectral permutation entropy is low, it indicates that the complexity of the spectrum signal is low and the distribution is orderly. The spectral permutation entropy distribution of the vibration signal of the normal mechanical arm is relatively stable, and the spectral permutation entropy of the vibration signal of the abnormal mechanical arm is smaller than the spectral permutation entropy of the vibration signal of the normal mechanical arm. However, the difference between the spectral permutation entropy of the vibration signal of the normal mechanical arm and the spectral permutation entropy of the vibration signal of the abnormal mechanical arm is small. At the same time, the spectral permutation entropy only considers the frequency domain characteristics of the vibration signal. Therefore, the time domain energy of the vibration signal to be detected is combined with the spectral permutation entropy to form the energy entropy ratio of the vibration signal to be detected. The energy entropy ratio of the vibration signal of the normal mechanical arm has high stability and small fluctuation. The energy entropy ratio of the vibration signal of the abnormal mechanical arm has low stability and large fluctuation. Moreover, the energy entropy ratio of the vibration signal of the normal mechanical arm is smaller than the energy entropy ratio of the vibration signal of the abnormal mechanical arm.

[0078] S103. Determine whether the robotic arm is abnormal based on the energy entropy ratio of the vibration signal to be detected.

[0079] Optionally, the energy entropy ratio can be a specific numerical value. By judging this numerical value, a normal robotic arm and an abnormal robotic arm can be distinguished. For example, the energy entropy ratio calculated from the vibration signal to be detected of a normal robotic arm is relatively low, and the energy entropy ratio calculated from the vibration signal to be detected of an abnormal robotic arm is relatively high. There is a clear dividing line between the two. Therefore, based on the energy entropy ratio of the vibration signal to be detected, it can be determined whether the robotic arm is normal or abnormal.

[0080] Optionally, a preset rule can be used to determine the threshold value of the abnormal situation of the robotic arm. If the energy entropy ratio of the vibration signal to be detected exceeds the threshold value of the preset rule, the robotic arm corresponding to the vibration signal to be detected is abnormal. Specifically, the 3sigma criterion can be used as the preset rule, and the corresponding formula is formula (1).

[0081] threshold=μ normal +3σ normal Formula (1)

[0082] Among them, threshold is the threshold value corresponding to the 3sigma criterion, μ normal is the mean value of the energy entropy ratio of the normal vibration signal, σ normal is the standard deviation of the energy entropy ratio of normal vibration signals.

[0083] This embodiment determines the vibration signal to be detected in the vibration signal of the robotic arm; determines the energy entropy ratio of the vibration signal to be detected; and determines whether the robotic arm is abnormal based on the energy entropy ratio of the vibration signal to be detected. Whether the robotic arm is abnormal is determined by the energy entropy ratio of the vibration signal to be detected. The energy entropy ratio of the vibration signal of a normal robotic arm is highly stable and has small fluctuations, while the energy entropy ratio of the vibration signal of an abnormal robotic arm is less stable and has large fluctuations. The energy entropy ratio of the vibration signal of a normal robotic arm is significantly smaller than the energy entropy ratio of the vibration signal of an abnormal robotic arm, and there is a clear dividing line between the two. Therefore, a normal robotic arm can be clearly and accurately distinguished from an abnormal robotic arm.

[0084] Figure 3 A flow chart of a method for determining the energy entropy ratio provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the above step S102 of determining the energy entropy ratio of the vibration signal to be detected may include:

[0085] S201 , performing spectrum transformation on the vibration signal to be detected to obtain a spectrum sequence of the vibration signal to be detected.

[0086] Optionally, the vibration signal to be detected is a time domain signal, and a spectrum transformation is performed on the vibration signal to be detected, for example, by using a fast Fourier transform, to obtain a spectrum sequence of the vibration signal to be detected. Specifically, the spectrum transformation can be performed according to formula (2).

[0087]

[0088] Among them, x[i] is the vibration signal to be detected, N is the length of the vibration signal to be detected, F s (n) is the spectrum sequence of the vibration signal to be detected after spectrum transformation.

[0089] S202 . Calculate the permutation entropy of the spectrum of the vibration signal to be detected according to the spectrum sequence of the vibration signal to be detected, and obtain the spectrum permutation entropy of the vibration signal to be detected.

[0090] Among them, Permutation Entropy (PE) is an average entropy parameter that measures the complexity of a one-dimensional time series. It is a method to reflect the complexity of a one-dimensional time series.

[0091] Optionally, the permutation entropy of the spectrum of the vibration signal to be detected is calculated according to the spectrum sequence of the vibration signal to be detected and a calculation method of the permutation entropy.

[0092] S203 : Determine the energy entropy ratio of the vibration signal to be detected according to the spectral permutation entropy.

[0093] Optionally, the spectrum permutation entropy calculated in S202 may be used to calculate a corresponding energy entropy ratio according to a preset condition, where the preset condition may be other signal parameters of the vibration signal to be detected.

[0094] Figure 4 A flow chart of a method for determining spectral permutation entropy provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the above step S202 calculates the permutation entropy of the spectrum of the vibration signal to be detected based on the spectrum sequence of the vibration signal to be detected to obtain the spectrum permutation entropy of the vibration signal to be detected, which may include:

[0095] S301 : reconstructing a frequency spectrum sequence of a vibration signal to be detected in phase space to obtain a reconstructed frequency spectrum of the vibration signal to be detected.

[0096] Specifically, the phase space vector of the corresponding dimension is constructed by different delay times of the one-dimensional time series to obtain the spectrum matrix of the vibration signal to be detected. The spectrum matrix is ​​as follows:

[0097]

[0098] Where m is the embedding dimension, τ is the time delay, K = N-(m-1)τ, N is the signal length, and each X′(i) corresponds to a corresponding reconstructed component, with a total of K components.

[0099] S302 : Sort the reconstructed frequency spectrum of the vibration signal to be detected to obtain a reconstructed sequence.

[0100] Optionally, the data in the above spectrum matrix is ​​sorted in ascending order, as shown in formula (3).

[0101] F s [i+(j1-1)τ]≤F s [i+(j2-1)τ]≤…≤F s [i+(j m -1)τ] Formula (3)

[0102] Thus, for each reconstructed sequence, each row corresponds to a labeled sequence number.

[0103] S′(l)=(j1,j2,…,j m )

[0104] Wherein, S′(l) is the reconstructed label sequence of each row, l=1, 2,…, k, and k≤m.

[0105] S303 : Calculate the permutation entropy of the frequency spectrum of the vibration signal to be detected according to the reconstructed sequence to obtain the permutation entropy of the frequency spectrum of the vibration signal to be detected.

[0106] Optionally, the sequence reconstructed in step S302 can be used to calculate the permutation entropy of the frequency spectrum of the vibration signal to be detected according to a preset formula to obtain the permutation entropy of the spectrum of the vibration signal to be detected.

[0107] In this embodiment, by calculating the permutation entropy of the spectrum of the signal to be detected, the result of the spectrum calculation based on the signal can be made more accurate.

[0108] Figure 5 A flow chart of another method for determining spectral permutation entropy provided in an embodiment of the present application is shown as follows: Figure 5 As shown, the above step S303 calculates the permutation entropy of the frequency spectrum of the vibration signal to be detected according to the reconstructed sequence, which may include:

[0109] S401 : Calculate the probability of each reconstructed sequence appearing in all sequences, and calculate the first permutation entropy of the frequency spectrum of the vibration signal to be detected based on the probability of each sequence.

[0110] Optionally, the probability of each reconstructed sequence is calculated based on its probability of appearing in all sequences. The probability of each sequence S′(1), S′(2), ..., S′(k) appearing is recorded as P1, P2, ..., P k , and ∑P=1, that is, the sum of the probabilities of each sequence is 1. For example, there are 4 rows of sequences in total, the probability of sequence S′(1) is 0.2, the probability of sequence S′(2) is 0.3, the probability of sequence S′(3) is 0.1, and the probability of sequence S′(2) is 0.4.

[0111] The first permutation entropy of the frequency spectrum of the vibration signal to be detected is calculated according to the probability of each sequence and formula (IV).

[0112]

[0113] Among them, H P is the first permutation entropy of the spectrum of the vibration signal to be detected, P j is the probability of each sequence of the reconstructed sequence appearing in all sequences.

[0114] S402 : Normalize the first permutation entropy to obtain the spectrum permutation entropy of the vibration signal to be detected.

[0115] Optionally, for the convenience of calculation, the first permutation entropy calculated in step S401 is processed using a normalization method, such as formula (5).

[0116]

[0117] Among them, H SP is the spectral permutation entropy of the vibration signal to be detected, H P is the first permutation entropy of the spectrum of the vibration signal to be detected, and m is the embedding dimension.

[0118] Figure 6 A flow chart of another method for determining the energy entropy ratio provided in an embodiment of the present application is shown as follows: Figure 6 As shown, determining the energy entropy ratio of the vibration signal to be detected according to the spectral arrangement entropy in the above step S203 may include:

[0119] S501: Determine the root mean square of the vibration signal to be detected.

[0120] Optionally, the root mean square indicates the root mean square of the energy corresponding to the time domain signal of the vibration signal to be detected. Specifically, the root mean square of the energy of the vibration signal to be detected can be calculated according to formula (6).

[0121]

[0122] Wherein, x[i] is the time domain energy of the vibration signal to be detected, and N is the length of the vibration signal to be detected.

[0123] S502: Calculate the energy entropy ratio according to the root mean square of the vibration signal to be detected and the spectrum permutation entropy.

[0124] Optionally, the energy entropy ratio of the vibration signal to be detected is calculated according to the ratio of the energy root mean square of the time domain of the vibration signal to be detected to the spectral permutation entropy, specifically, as shown in formula (VII).

[0125]

[0126] Where, EER is the energy entropy ratio of the vibration signal to be detected, RMS is the root mean square energy of the vibration signal to be detected, and H SP is the spectrum permutation entropy of the vibration signal to be detected.

[0127] Optionally, before determining the vibration signal to be detected in the vibration signal of the robot arm in step S101, the following steps may be included:

[0128] Optionally, the vibration signal of the robotic arm is preprocessed.

[0129] Among them, the vibration signal can be a vibration signal corresponding to multiple speed segments. The vibration signal of each speed segment is preprocessed, for example, it can be processed using a de-averaging method, that is, the energy of the vibration signal of each speed segment is subtracted from the energy mean of the speed signal segment.

[0130] Optionally, a uniform vibration signal is extracted from the preprocessed vibration signal of the robotic arm.

[0131] Among them, the vibration signal corresponding to each speed segment has acceleration and deceleration time from the initial point to the end point, so it is necessary to extract the uniform motion signal segment in the vibration signal corresponding to each speed segment to detect the quality of the robotic arm. Specifically, the first and last time of the signal segment with a preset duration can be subtracted from the vibration signal corresponding to each speed segment, and the signal segment corresponding to the remaining time is the uniform motion signal segment.

[0132] Exemplarily, the preset duration may be 0.4 seconds.

[0133] Optionally, determining a vibration signal to be detected in the vibration signal of the robotic arm may include:

[0134] Optionally, each speed segment includes signal segments going back and forth between the two ends in the vibration signal, for example, from endpoint A to endpoint B, and from endpoint B back to endpoint A. In the embodiment of the present application, the motion signal segment from endpoint A to endpoint B is selected to analyze the motion vibration signal of the speed segment.

[0135] Optionally, a uniform vibration signal corresponding to a preset speed segment is selected from the uniform vibration signal according to a preset speed segment as the vibration signal to be detected. Specifically, a corresponding speed segment can be searched in each speed segment according to a speed specified by an input. For example, a signal segment in which the vibration signal is located can be selected according to the motor speed of the robotic arm, such as formula (8).

[0136]

[0137] Among them, seg is the speed segment where the vibration signal is located, and n is the motor speed.

[0138] Figure 7 The actual verification result diagram provided by the embodiment of this application is as follows: Figure 7 As shown in the figure, the energy entropy ratios of multiple normal robotic arms and multiple abnormal robotic arms obtained by the above method in each speed signal segment when the motor speed is 2000 rpm, 2500 rpm, and 3000 rpm, wherein the serial number (a) represents the motor speed of 2000 rpm, the serial number (b) represents the motor speed of 2500 rpm, and the serial number (c) represents the motor speed of 3000 rpm. The circular marks in each figure are the energy entropy ratios of different groups of data, that is, the energy entropy ratios of the vibration signals of different robotic arms. The black dotted line is the threshold value calculated based on the first 4 groups of normal robotic arms, and the left and right sides of the black dotted line represent the normal robotic arm and the abnormal robotic arm respectively.

[0139] from Figure 7As can be seen in the figure, as the speed increases, the energy entropy ratio of both the normal and abnormal robotic arms gradually increases. Therefore, the threshold value also increases with the increase in speed. At speeds of 2000 rpm, 2500 rpm, and 3000 rpm, it can be seen that there is a clear dividing line between the energy entropy ratio of the normal robotic arm and the energy entropy ratio of the abnormal robotic arm. Therefore, the robotic arm detection method proposed in the embodiment of the present application can accurately distinguish between normal and abnormal robotic arms, verifying the effectiveness of the method.

[0140] Figure 8 Another practical verification result diagram provided in the embodiment of the present application is as follows: Figure 8 As shown, the embodiment of the present application compares the verification results of detecting the robotic arm by using the energy entropy ratio feature of the vibration signal to be detected with the root mean square feature and spectral permutation entropy feature of the vibration signal used in the prior art.

[0141] In order to quantify the differences between the three features mentioned above in measuring the vibration signals of normal and abnormal manipulators, the change rates of the features extracted from the vibration signals of abnormal manipulators compared with the features extracted from the vibration signals of normal manipulators are calculated at different speeds. Figure 8 It can be seen that among the three characteristics, the rate of change of the spectral permutation entropy is the smallest, the root mean square is smaller, and the rate of change of the energy entropy ratio is the largest. Moreover, at the three rotational speeds, the energy entropy ratio is the indicator with the largest change. Therefore, compared with the root mean square and spectral permutation entropy, the energy entropy ratio can clearly distinguish between normal robotic arms and abnormal robotic arms, further verifying the advantages of the robotic arm detection method provided in the embodiment of the present application.

[0142] Figure 9 A schematic diagram of a device for a robotic arm detection method provided in an embodiment of the present application is shown in FIG. Figure 9 As shown, the device includes:

[0143] A determination module 601 is configured to determine a vibration signal to be detected in a vibration signal of the robotic arm, wherein the vibration signal to be detected is a vibration signal corresponding to a preset speed range;

[0144] A determination module 601 is configured to determine the energy entropy ratio of the vibration signal to be detected;

[0145] A determination module is used to determine whether the robotic arm is abnormal based on the energy entropy ratio of the vibration signal to be detected.

[0146] Optionally, the determining module 601 is specifically configured to:

[0147] Performing spectrum transformation on the vibration signal to be detected to obtain a spectrum sequence of the vibration signal to be detected;

[0148] Calculating the permutation entropy of the spectrum of the vibration signal to be detected according to the spectrum sequence of the vibration signal to be detected to obtain the spectrum permutation entropy of the vibration signal to be detected;

[0149] The energy entropy ratio of the vibration signal to be detected is determined according to the spectral arrangement entropy.

[0150] Optionally, the determining module 601 is specifically configured to:

[0151] Performing phase space reconstruction on the frequency spectrum sequence of the vibration signal to be detected to obtain a reconstructed frequency spectrum of the vibration signal to be detected;

[0152] sorting the reconstructed frequency spectrum of the vibration signal to be detected to obtain a reconstructed sequence;

[0153] The permutation entropy of the frequency spectrum of the vibration signal to be detected is calculated according to the reconstructed sequence to obtain the permutation entropy of the spectrum of the vibration signal to be detected.

[0154] Optionally, the determining module 601 is specifically configured to:

[0155] Calculating the probability of each sequence in the reconstructed sequence appearing in all sequences, and calculating the first permutation entropy of the frequency spectrum of the vibration signal to be detected based on the probability of each sequence;

[0156] Normalization is performed on the first permutation entropy to obtain the spectral permutation entropy of the vibration signal to be detected.

[0157] Optionally, the determining module 601 is specifically configured to:

[0158] Calculating the root mean square of the vibration signal to be detected;

[0159] The energy entropy ratio is calculated based on the root mean square of the vibration signal to be detected and the spectral permutation entropy.

[0160] Optionally, the determining module 601 is specifically configured to:

[0161] Preprocessing the vibration signal of the robotic arm;

[0162] A uniform vibration signal is extracted from the preprocessed vibration signal of the robotic arm.

[0163] Optionally, the determining module 601 is specifically configured to:

[0164] According to the preset speed segment, a uniform vibration signal corresponding to the preset speed segment is selected from the uniform vibration signals as the vibration signal to be detected.

[0165] Figure 10 This is a structural block diagram of an electronic device 700 provided in an embodiment of the present application, such as Figure 10As shown, the electronic device may include: a processor 701 and a memory 702.

[0166] Optionally, a bus 703 may be further included, wherein the memory 702 is used to store machine-readable instructions (for example, Figure 7 When the electronic device 700 is running, the processor 701 communicates with the memory 702 via the bus 703, and when the machine-readable instructions are executed by the processor 701, the method steps in the above method embodiment are executed.

[0167] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method steps in the above-mentioned embodiment of the robot arm detection method are executed.

[0168] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0169] In addition, the functional units in the various embodiments of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0170] The above is only a specific implementation method of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the protection scope of the present application.

Claims

1. A robotic arm detection method, characterized in that: The method comprises: Determining a vibration signal to be detected in the vibration signal of the robotic arm, wherein the vibration signal to be detected is a vibration signal corresponding to a preset speed range; determining an energy entropy ratio of the vibration signal to be detected; determining whether the robotic arm is abnormal according to the energy entropy ratio of the vibration signal to be detected; Determining the energy entropy ratio of the vibration signal to be detected includes: Performing spectrum transformation on the vibration signal to be detected to obtain a spectrum sequence of the vibration signal to be detected; Calculating the permutation entropy of the spectrum of the vibration signal to be detected according to the spectrum sequence of the vibration signal to be detected to obtain the spectrum permutation entropy of the vibration signal to be detected; The energy entropy ratio of the vibration signal to be detected is determined according to the spectral arrangement entropy.

2. The robotic arm detection method according to claim 1, characterized in that: Calculating the permutation entropy of the spectrum of the vibration signal to be detected according to the spectrum sequence of the vibration signal to be detected to obtain the spectrum permutation entropy of the vibration signal to be detected includes: Performing phase space reconstruction on the frequency spectrum sequence of the vibration signal to be detected to obtain a reconstructed frequency spectrum of the vibration signal to be detected; sorting the reconstructed frequency spectrum of the vibration signal to be detected to obtain a reconstructed sequence; The permutation entropy of the frequency spectrum of the vibration signal to be detected is calculated according to the reconstructed sequence to obtain the permutation entropy of the spectrum of the vibration signal to be detected.

3. The robotic arm detection method according to claim 2, wherein: The step of calculating the permutation entropy of the frequency spectrum of the vibration signal to be detected according to the reconstructed sequence includes: Calculating the probability of each sequence in the reconstructed sequence appearing in all sequences, and calculating the first permutation entropy of the frequency spectrum of the vibration signal to be detected based on the probability of each sequence; Normalization is performed on the first permutation entropy to obtain the spectral permutation entropy of the vibration signal to be detected.

4. The robot arm detection method according to claim 1, characterized in that: Determining the energy entropy ratio of the vibration signal to be detected according to the spectral arrangement entropy includes: Calculating the root mean square of the vibration signal to be detected; The energy entropy ratio is calculated based on the root mean square of the vibration signal to be detected and the spectral permutation entropy.

5. The robotic arm detection method according to any one of claims 1 to 4, characterized in that: The method of determining a vibration signal to be detected in the vibration signal of the robotic arm, wherein the vibration signal to be detected is a vibration signal corresponding to a preset speed range, includes: Preprocessing the vibration signal of the robotic arm; A uniform vibration signal is extracted from the preprocessed vibration signal of the robotic arm.

6. The robot arm detection method according to claim 5, characterized in that: The step of determining the vibration signal to be detected in the vibration signal of the robotic arm includes: According to the preset speed segment, a uniform vibration signal corresponding to the preset speed segment is selected from the uniform vibration signals as the vibration signal to be detected.

7. A robotic arm detection device, characterized in that: include: a determination module, configured to determine a vibration signal to be detected in the vibration signal of the robotic arm, wherein the vibration signal to be detected is a vibration signal corresponding to a preset speed range; A determination module, configured to determine the energy entropy ratio of the vibration signal to be detected; a determination module, configured to determine whether the robotic arm is abnormal based on the energy entropy ratio of the vibration signal to be detected; The determining module is specifically configured to: Performing spectrum transformation on the vibration signal to be detected to obtain a spectrum sequence of the vibration signal to be detected; Calculating the permutation entropy of the spectrum of the vibration signal to be detected according to the spectrum sequence of the vibration signal to be detected to obtain the spectrum permutation entropy of the vibration signal to be detected; The energy entropy ratio of the vibration signal to be detected is determined according to the spectral arrangement entropy.

8. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program executable by the processor, and when the processor executes the computer program, the steps of the robot arm detection method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the robotic arm detection method according to any one of claims 1 to 6.

Images