A fault anomaly monitoring method and system for a drive device

Abstract

The present invention relates to the field of electrical fault detection technology, and specifically to a fault anomaly monitoring method and system for a drive device. The method obtains the current current signal and current vibration signal of each key part of the drive device; based on the current data in the current current signal, the degree of abnormality is obtained to divide the current current signal into local current areas; based on the distribution of vibration data in the local current vibration signal corresponding to the local current area, the degree of vibration influence is obtained; based on the current current distortion degree, vibration influence degree and abnormality degree of the key part, the signal decomposition strength of the local current area is obtained, and then the optimal decomposition interval scale of the local current area in the LMD decomposition algorithm is obtained. The present invention obtains the optimal decomposition interval scale, and then accurately decomposes the current current signal, removes the influence of interference factors on the current current signal, and is conducive to accurately monitoring the fault anomalies of each key part of the drive device.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical fault detection, and in particular to a fault anomaly monitoring method and system for a drive device. Background Art

[0002] A drive device generally refers to a device or system used to provide power or motion control. It can be a device of various types and sizes that is used to drive mechanical parts, systems or other equipment to perform specific movements or operations. Common types of drive devices include electric drive devices, hydraulic drive devices, pneumatic drive devices, mechanical drive devices and other drive devices. In order to ensure the safe and stable operation of the drive device, the current signals of each key part of the drive device during operation are obtained in real time. By analyzing the current signals of each key part in real time, the faults and abnormalities of each key part of the drive device can be discovered in time and repaired in time.

[0003] In actual situations, the current signal obtained may be interfered by other external factors such as electromagnetics and vibrations, resulting in distortion of the current signal waveform. In order to remove the interference of other external factors such as electromagnetics and vibrations in the current signal, the existing method uses the local mean decomposition (LMD) algorithm to decompose the current signals of each key part of the drive device, decompose the real current signal and the interference signal, and then analyze the decomposed real current signal to determine the fault anomaly of each key part of the drive device. However, in actual situations, the signal distribution in different areas of the current signal is different. Directly decomposing the current signal through the decomposition interval scale in the traditional local mean decomposition (LMD) algorithm will result in the inability to accurately decompose the interference signal and the real current signal, and thus the inability to accurately monitor the fault anomaly of each key part of the drive device based on the real current signal. Summary of the invention

[0004] In order to solve the technical problem that the current signal is directly decomposed by the decomposition interval scale in the traditional local mean decomposition (LMD) algorithm, which will lead to the inability to accurately decompose the interference signal and the real current signal, and then the inability to accurately monitor the fault abnormality of each key part of the drive device according to the real current signal, the purpose of the present invention is to provide a fault abnormality monitoring method and system for the drive device, and the technical scheme adopted is as follows:

[0005] In a first aspect, an embodiment of the present invention provides a method for monitoring faults and abnormalities of a drive device, the method comprising the following steps:

[0006] Obtain the current current signal and current vibration signal of each key part of the current operation of the drive device;

[0007] Based on the distribution of each current data in the current current signal and the surrounding current data, the abnormality degree of each current data is obtained; based on the abnormality degree, all current current signals are divided into local current areas;

[0008] Based on the distribution of vibration data in the local current vibration signal corresponding to each local current area, the vibration influence degree of each local current area is obtained;

[0009] Based on the current current distortion degree of each key part, the vibration influence degree and the abnormality degree in each local current area, obtaining the signal decomposition intensity of each local current area of ​​each key part;

[0010] The optimal decomposition interval scale of each local current region in the LMD decomposition algorithm is obtained based on the signal decomposition strength.

[0011] Furthermore, the method for obtaining the abnormality degree is:

[0012] Constructing a first preset window of each current data in all current current signals;

[0013] For any current data in all current current signals, obtaining the information entropy of the current data in a first preset window of the current data as a first abnormal reference value of the current data;

[0014] Obtaining a mean value of all current data in a first preset window of the current data as a first characteristic value of the current data;

[0015] using a first characteristic value difference between the current data and the previous adjacent current data as a second abnormal reference value of the current data;

[0016] taking the difference between the maximum current data and the minimum current data in the first preset window of the current data as the current difference;

[0017] taking the difference between the time points corresponding to the maximum current data and the minimum current data in the first preset window of the current data as the time difference;

[0018] The ratio of the current difference to the time difference is used as a third abnormal reference value of the current data;

[0019] The abnormality degree of the current data is acquired according to the first abnormality reference value, the second abnormality reference value and the third abnormality reference value of the current data.

[0020] Furthermore, the method for obtaining the local current area is:

[0021] For any current current signal, obtaining a difference in abnormality between any two adjacent current data in the current current signal as a first difference;

[0022] When the first difference is greater than or equal to a preset first difference threshold, division is performed between two corresponding adjacent current data, and each local current signal segment after the current current signal is divided is used as a local current region.

[0023] Furthermore, the method for acquiring the local current vibration signal corresponding to each local current area is:

[0024] For any local current region, the time period corresponding to the local current region is used as a reference time period;

[0025] The current vibration signal of the key part corresponding to the local current area within the reference time period is used as the local current vibration signal corresponding to the local current area.

[0026] Furthermore, the method for obtaining the vibration impact degree is:

[0027] For any local current region, the local current vibration signal corresponding to the local current region is taken as the local vibration region;

[0028] For any maximum value point in the local vibration area, a second preset window of the maximum value point is constructed, and all the maximum value points in the second preset window of the maximum value point are used as reference points;

[0029] The probability of the amplitude corresponding to each reference point appearing in the current vibration signal in the local vibration area is used as the occurrence probability value of each reference point;

[0030] Obtain the product of the occurrence probability values ​​of all reference points as the reference analysis value;

[0031] Obtain the slope difference between the adjacent points on the left and right of the maximum point as the oscillation intensity of the maximum point;

[0032] According to the reference analysis value and the oscillation intensity, the vibration reference degree of the maximum value point is obtained; wherein the reference analysis value and the vibration reference degree are negatively correlated, and the oscillation intensity and the vibration reference degree are positively correlated;

[0033] The average value of the vibration reference degrees of all the maximum value points in the local vibration area is obtained as the vibration influence degree of the local current area.

[0034] Furthermore, the method for obtaining the current current distortion degree is:

[0035] Obtain the current signals of each key part of the driving device during each operation in the historical time period as historical current signals;

[0036] Obtain the absolute value of the Pearson correlation coefficient of the historical current signals of the same operation between any two key parts as a reference correlation value;

[0037] The average of all reference correlation values ​​between any two key parts in the historical time period is used as the current impact value of the corresponding two key parts;

[0038] For any key part, obtain the average of the current influence values ​​of the key part and each other key part as the overall influence degree value of the key part;

[0039] Obtaining the degree of abnormality of the current current of the key part according to the difference between the mean value of all current data in the current current signal of the key part and the mean value of all current data in each of its historical current signals;

[0040] The current current distortion degree of the key part is obtained according to the overall influence degree value of the key part and the current current abnormality degree; wherein the overall influence degree value and the current current abnormality degree are both positively correlated with the current current distortion degree.

[0041] Furthermore, the method for obtaining the signal decomposition strength is:

[0042] For any local current region of any key part, the signal complexity of the local current region of the key part is obtained according to the vibration influence degree of the local current region and the current current distortion degree of the key part; wherein the vibration influence degree and the current current distortion degree are both positively correlated with the signal complexity;

[0043] Obtaining a mean value of the abnormality levels of all current data in the local current region as a reference abnormality level of the local current region;

[0044] According to the signal complexity and the reference abnormality, the signal decomposition strength of the local current area of ​​the key part is obtained; wherein the signal complexity and the reference abnormality are both positively correlated with the signal decomposition strength.

[0045] Furthermore, the method for obtaining the optimal decomposition interval scale is:

[0046] For any local current region, the result of negative correlation of the signal decomposition intensity of the local current region is used as the adjustment weight of the local current region;

[0047] The initial decomposition interval scale of the local current region in the LMD decomposition algorithm is adjusted by adjusting the weight, so as to obtain the optimal decomposition interval scale of the local current region in the LMD decomposition algorithm.

[0048] Furthermore, the fault anomaly monitoring method for a drive device further includes:

[0049] According to the optimal decomposition interval scale of each local current region of each current current signal in the LMD decomposition algorithm, each current current signal is decomposed by the LMD decomposition algorithm to obtain the component signal of each current current signal;

[0050] The component signals of each segment of the current current signal are sorted in descending order according to the stability, so as to obtain a component signal sequence of each segment of the current current signal;

[0051] Reconstructing the first preset number of component signals in each component signal sequence respectively to obtain the reconstructed current signal of each current current signal as the real current signal of the corresponding key part;

[0052] The result of normalizing the current data of each segment of the real current signal at the current moment is used as the fault reference value of the corresponding key part;

[0053] When the fault reference value is greater than or equal to the preset abnormal current data threshold, the corresponding key part has a fault abnormality at the current moment.

[0054] In the second aspect, another embodiment of the present invention provides a fault and abnormality monitoring system for a drive device, the system comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of any one of the above methods are implemented.

[0055] The present invention has the following beneficial effects:

[0056] Based on the distribution of each current data in the current current signal and the surrounding current data, the abnormality degree of each current data is obtained, which accurately reflects the abnormality degree of each current data, which is conducive to accurate regional division of the current current signal, and then all the current current signals are divided into local current areas based on the abnormality degree, which is conducive to the subsequent accurate analysis of the degree of external interference factors of the current signal in different areas of the current current signal, and improves the accuracy of the local mean decomposition algorithm in decomposing the current current signal; in order to obtain the interference degree of the current signal in each local current area, based on the distribution of vibration data in the local current vibration signal corresponding to each local current area, the vibration influence degree of each local current area is obtained, which accurately reflects the vibration interference degree of the current signal in each local current area; at the same time, the current current distortion degree of each key part is obtained. , accurately reflecting the degree to which the current signal in each local current area is interfered by other uncertain factors; then, based on the current current distortion degree of each key part, the vibration influence degree and the abnormality degree in each local current area, the signal decomposition strength of each local current area of ​​each key part is obtained, accurately reflecting the intensity of the current signal in each local current area that needs to be decomposed; then, based on the signal decomposition strength, the optimal decomposition interval scale of each local current area in the LMD decomposition algorithm is accurately obtained, and the current current signal of each key part is accurately decomposed, so that the interference signal and the real current signal are accurately decomposed, and then the real current signal of each key part is analyzed, and the fault abnormality of each key part is accurately analyzed, and the fault abnormal part in the drive device is timely determined, which is conducive to the staff to carry out maintenance in time and ensure the stable and safe operation of the drive device. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 A schematic flow chart of a method for monitoring a fault anomaly of a drive device provided by an embodiment of the present invention;

[0059] Figure 2 A flow chart of a method for obtaining an abnormality degree provided by an embodiment of the present invention;

[0060] Figure 3 A flow chart of a method for obtaining signal decomposition strength provided by an embodiment of the present invention;

[0061] Figure 4 A flow chart of a method for obtaining the degree of distortion of current provided by an embodiment of the present invention;

[0062] Figure 5 A structural diagram of a fault anomaly monitoring system for a drive device provided by an embodiment of the present invention;

[0063] Figure 6 A schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a method and system for monitoring fault anomalies of a drive device according to the present invention, its specific implementation, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0065] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0066] The specific scheme of a fault and abnormality monitoring method and system for a drive device provided by the present invention is described in detail below with reference to the accompanying drawings.

[0067] Embodiment 1:

[0068] The specific scenario of this embodiment is: in order to timely discover the abnormal fault parts in the drive device, this embodiment obtains and analyzes the current signals of each key part of the drive device in real time. Considering that the current signal will be interfered by other external factors such as electromagnetic and vibration, the existing method uses the local mean decomposition (LMD) algorithm to decompose the current signal of each key part during the current operation, obtain a series of signal components with clear physical meanings, and then remove the interference signal components, extract the signal components representing the true current signal from them for reconstruction, and obtain the true current signal of each key part during the current operation, and then accurately analyze the abnormal fault situation of each key part at the current moment, and perform maintenance in time. In actual situations, the signal complexity in different areas of the current signal of each key part during the current operation is different. If the current signal of each key part during the current operation is directly decomposed by the decomposition interval scale in the traditional local mean decomposition (LMD) algorithm, the interference signal and the true current signal cannot be accurately decomposed. Therefore, this embodiment first obtains the abnormality of each current data in the current current signal based on the distribution of each current data in the current current signal and the surrounding current data; then divides the current current signal of each key part into local current areas according to the abnormality; then analyzes each local current area to determine the degree of interference of the current signal in each local current area by other uncertain factors, and then accurately obtains the signal decomposition strength of each local current area of ​​each key part; finally, based on the signal decomposition strength, adaptively obtains the optimal decomposition interval scale of each local current area in the LMD decomposition algorithm, and then accurately decomposes the current current signal of each key part through the local mean decomposition (LMD) algorithm and the optimal decomposition interval scale, so that the fault abnormality of each key part of the drive device can be accurately monitored subsequently. Among them, the local mean decomposition (Local Mean Decomposition, LMD) algorithm and the method of obtaining the decomposition interval scale through the local mean decomposition (LMD) algorithm are both well-known technologies and will not be described in detail.

[0069] The present invention proposes a fault anomaly monitoring method for a drive device, please refer to Figure 1 , which shows a schematic flow chart of a fault anomaly monitoring method for a drive device provided by an embodiment of the present invention, the method comprising the following steps:

[0070] Step S1: obtaining the current current signal and the current vibration signal of each key part of the driving device during the current operation.

[0071] Specifically, in this embodiment, a current sensor and a vibration sensor are installed at each key part of the drive device, such as the bearing and the base, to obtain the current signal and vibration signal of each key part of the drive device in real time each time it runs, that is, each key part of the drive device under each operation corresponds to a current signal and a vibration signal. In actual situations, the duration of each operation of the drive device is not fixed, so the length of the current signal and the length of the vibration signal of each key part of the drive device under different operations are different. By analyzing the current signal of each key part of the drive device, the fault abnormal part in the drive device is determined. Among them, the role of obtaining the vibration signal is to more accurately analyze the situation where the current signal is disturbed by the mechanical vibration of the key part, which is conducive to a more accurate analysis of the current signal. It should be noted that the current signal and the vibration signal of each key part of the drive device are collected simultaneously each time the drive device runs, that is, the current data and vibration data of each key part are collected simultaneously at a certain moment during the operation of the drive device. In this embodiment, the time interval between two adjacent data collection moments is set to 1 second. The implementer can set the time interval between two adjacent data collection moments according to the actual situation, which is not limited here. Among them, the current signal of each key part of the driving device during each operation is composed of the current data at each moment, and the vibration signal is composed of the vibration data at each moment.

[0072] In order to promptly discover faults and anomalies in the drive device, this embodiment obtains the current current signal and current vibration signal of each key part of the current operation of the drive device. At the same time, in order to subsequently accurately analyze the degree of interference of external factors that may affect the current current signal, the current signals of each key part of each operation of the drive device in the historical time period are obtained, all of which are used as historical current signals. In this embodiment, the historical time period is set to 1 month, and the last operation of the drive device in the historical time period and the current operation of the drive device are two adjacent operations. The implementer can set the size of the historical time period according to actual conditions, and it is not limited here. Among them, the drive device must have operated in the historical time period. It should be noted that the real-time moment of the current operation of the drive device is the current moment and the drive device at the current moment must be in operation.

[0073] Step S2: based on the distribution of each current data in the current current signal and the surrounding current data, obtain the abnormality degree of each current data; and divide all current current signals into local current areas based on the abnormality degree.

[0074] Normally, the drive device will generate a certain amount of heat due to the electrothermal effect during operation. When a critical part of the drive device fails abnormally, for example, when the bearing of the drive device is damaged, the temperature of the bearing will rise sharply, thereby affecting the characteristics of the electrical components at the bearing, causing the current signal at the bearing to become disordered, and the current signal will surge or drop sharply. It is known that the abnormal current signal caused by the abnormal failure of the critical part is a continuous process. In order to accurately divide the normal current signal area and the abnormal current signal area in all current current signals, so as to analyze the signals in different areas of the current current signal more accurately later, this embodiment analyzes the distribution of each current data in the current current signal of each critical part and the current data around it. When the difference between a certain current data and the current data around it is greater, that is, the distribution is more unstable, it means that the current data is more likely to be abnormal. Therefore, this embodiment obtains the degree of abnormality of each current data based on the distribution of each current data in the current current signal and the current data around it. When the difference in abnormality between two adjacent current data is greater, it means that the corresponding two adjacent current data are less likely to be current signals with the same signal characteristics, and then all current current signals are divided into various local current areas based on the abnormality degree, which is essentially to distinguish the normal current signal area from the abnormal current signal area in each segment of the current current signal.

[0075] Preferably, in some possible implementations of this embodiment, the method for obtaining the abnormality degree can be found in Figure 2 , which shows a flow chart of a method for obtaining an abnormality degree provided by an embodiment of the present invention, the method comprising the following steps:

[0076] Step S201: Obtain a first abnormal reference value.

[0077] In order to determine the surrounding current data of each current data, this embodiment constructs the first preset window of each current data in all current current signals. Among them, the method for obtaining the first preset window of each current data is: for any current data in all current current signals, with the current data as the end point, a window with a length of 10 is constructed as the first preset window of the current data, wherein one current data represents a unit length "1" of the window. The implementer can set the length of the first preset window according to the actual situation, which is not limited here. It should be noted that for the boundary current data in each current current signal, when the number of a certain boundary current data and the current data before it is not enough to constitute a first preset window, the boundary current data and the current data before it are still defaulted to a first preset window. It is known that there is no other current data before the first current data in each current current signal, so this embodiment does not analyze the first current data in each current current signal. So far, the first preset window of each current data in the current current signal is obtained, that is, the surrounding current data of each current data is determined.

[0078] For any current data in the current current signal, the more chaotic the distribution of the current data in the first preset window of the current data is, the more unstable the distribution of the current data and the current data around it is, and the greater the possibility that the current data is abnormal; this embodiment obtains the information entropy of the current data in the first preset window of the current data to reflect the degree of chaos of the current data in the first preset window of the current data. The greater the information entropy, the greater the possibility that the current data is abnormal. For ease of description, this embodiment uses the information entropy of the current data in the first preset window of the current data as the first abnormal reference value of the current data. Among them, the method for obtaining information entropy is a well-known technology and will not be repeated.

[0079] At this point, the first abnormal reference value of each current data is acquired.

[0080] Step S202: Obtain a second abnormal reference value.

[0081] In order to more accurately analyze the abnormal situation of each current data, the mean value of all current data in the first preset window of each current data is further obtained as the first characteristic value of each current data; when the difference between a certain current data and the first characteristic value of its previous adjacent current data is greater, it means that the current data is more unstable and the possibility that the current data is abnormal is greater. Therefore, this embodiment obtains the absolute value of the difference between the first characteristic value of each current data and its previous adjacent current data as the second abnormal reference value of the corresponding current data. The larger the second abnormal reference value, the greater the possibility that the corresponding current data is abnormal. It should be noted that this embodiment analyzes the difference in the first characteristic value between each current data and its previous adjacent current data, because it takes into account that the current data is acquired in real time from front to back in time sequence.

[0082] At this point, the second abnormal reference value of each current data is acquired.

[0083] Step S203: Obtain a third abnormal reference value.

[0084] It is known that abnormal faults in key parts will cause the generated current signal to surge or drop sharply. Therefore, in order to more accurately analyze the abnormal situation of each current data, the difference between the maximum current data and the minimum current data in the first preset window of a certain current data is obtained as the current difference; the absolute value of the difference between the maximum current data and the minimum current data in the first preset window of the current data is obtained as the time difference; the ratio of the current difference to the time difference is used as the third abnormal reference value of the current data; the larger the third abnormal reference value, the more obvious the surge or drop phenomenon is, and the greater the degree of abnormality of the current data.

[0085] At this point, the third abnormal reference value of each current data is acquired.

[0086] Step S204: Obtain the abnormality degree.

[0087] It is known that the larger the first abnormal reference value, the larger the second abnormal reference value and the larger the third abnormal reference value, the greater the possibility that the corresponding current data is abnormal. Therefore, this embodiment obtains the abnormality degree of each current data according to the first abnormal reference value, the second abnormal reference value and the third abnormal reference value of each current data.

[0088] In order to accurately indicate the abnormality of each current data, this embodiment specifically quantifies the abnormality of each current data into an abnormality value. The larger the abnormality value, the more abnormal the corresponding current data. The calculation formula of the abnormality value is: ; In the formula, is the abnormality value of the kth current data; is the first abnormal reference value of the kth current data; is the first eigenvalue of the kth current data; is the first eigenvalue of the k-1th current data; is the second abnormal reference value of the k-th current data; is the maximum current data in the first preset window of the kth current data; is the minimum current data in the first preset window of the kth current data; is the current difference; The time corresponding to the maximum current data in the first preset window of the kth current data; is the time corresponding to the minimum current data in the first preset window of the kth current data; For time difference; is the third abnormal reference value of the k-th current data; is an absolute value function; norm is a normalization function. In other embodiments, the abnormality degree value of each current data may be obtained by multiplying the first abnormality reference value, the second abnormality reference value and the third abnormality reference value of each current data, which is not limited here.

[0089] At this point, the abnormality level value of each current data is acquired.

[0090] In actual situations, there are obvious differences between normal current data and abnormal current data in the current current signals of various key parts. In order to divide the normal area and abnormal area in the current current signals of various key parts, it is beneficial to accurately decompose the current current signal through the local mean decomposition algorithm later. Therefore, this embodiment divides all current current signals into various local current areas based on the degree of abnormality.

[0091] Preferably, in some possible implementations of this embodiment, the method for obtaining the local current area is: for any current current signal, obtain the absolute value of the difference in the abnormality degree value between any two adjacent current data in the current current signal as the first difference; when the first difference is larger, it means that the signal characteristics of the corresponding two adjacent current data are more different, and the corresponding two adjacent current data should be divided more. Therefore, this embodiment sets the preset first difference threshold to 0.5, and the implementer can set the size of the preset first difference threshold according to actual conditions, which is not limited here. When the first difference is greater than or equal to the preset first difference threshold, the division is performed between the corresponding two adjacent current data, and each local current signal segment after the current current signal is divided is used as a local current area.

[0092] At this point, each current signal is divided into local current regions.

[0093] Step S3: based on the distribution of vibration data in the local current vibration signal corresponding to each local current area, the vibration influence degree of each local current area is obtained.

[0094] Specifically, during the operation of the drive device, various key parts will generate mechanical vibrations to varying degrees, and a strong oscillation frequency will cause the circuit connection of the key parts of the drive device to loosen, thereby interfering with the signal line, causing the current signal of the key parts of the drive device to have different degrees of signal waveform distortion. In actual situations, the mechanical vibrations generated by the key parts are not fixed. In order to determine whether the current signal in each local current area in the current current signal is affected by the mechanical vibration, this embodiment obtains the degree of vibration influence of each local current area based on the distribution of vibration data in the local current vibration signal corresponding to each local current area, wherein the greater the degree of vibration influence, the greater the degree of mechanical vibration interference to the current signal in the corresponding local current area.

[0095] In one implementation of the present embodiment, a method for acquiring the local current vibration signal corresponding to each local current area is as follows: for any local current area, the time period corresponding to the local current area is used as a reference time period; and the current vibration signal of the key part corresponding to the local current area within the reference time period is used as the local current vibration signal corresponding to the local current area.

[0096] Preferably, in some possible implementations of this embodiment, the method for obtaining the vibration impact degree is as follows:

[0097] For any local current region, the local current vibration signal corresponding to the local current region is taken as the local vibration region. During the operation of the drive device, when a strong oscillation occurs in a key part, the vibration signal corresponding to the key part will continue to have an abnormally large vibration amplitude. Therefore, in order to analyze the vibration degree of the local vibration region and then determine the degree to which the current signal in the local current region is disturbed by the vibration, this embodiment constructs a second preset window of the maximum point for any maximum point in the local vibration region, and uses the maximum points in the second preset window of the maximum point as reference points. When there are more reference points and the more abnormal the amplitude of the reference points is, it means that the vibration degree corresponding to the maximum point is greater, which indirectly means that the greater the vibration degree of the local vibration region is, the greater the degree to which the current signal in the local current region is disturbed by the vibration.

[0098] Among them, the method for obtaining the second preset window is: for any maximum point in the local vibration area, take the maximum point as the starting point, and construct a window with a length of 10 as the second preset window of the maximum point. Among them, one vibration data represents the unit length "1" of a window. The implementer can set the length of the second preset window and the position of the maximum point in the second preset window according to actual conditions, which are not limited here. It should be noted that for the last maximum point in the local vibration area, when the vibration data of the maximum point and its after are insufficient to construct a second preset window, the vibration data of the maximum point and its after are still defaulted to a second preset window; if there is no vibration data after the maximum point, the maximum point will not be analyzed;

[0099] In order to analyze the situation of the reference point, this embodiment obtains the probability of the amplitude corresponding to each reference point appearing in the current vibration signal in the local vibration area as the probability of occurrence of each reference point; when the probability of occurrence is smaller, it means that the abnormal phenomenon of the amplitude of the corresponding reference point is more obvious. The product of the probability of occurrence of all reference points is obtained as the reference analysis value; it is known that the probability of occurrence is less than 1 and greater than 0. Therefore, when the reference analysis value is smaller, it means that the amplitude of the reference point is more abnormal and the number of reference points is more, which indirectly indicates that the maximum value point is in the strong vibration stage of the corresponding key part, and the vibration degree of the maximum value point is greater. In order to further consider the abnormal situation of the amplitude of the maximum value, the absolute value of the difference between the slopes of the adjacent points on the left and right of the maximum value point is obtained as the oscillation intensity of the maximum value point; the greater the oscillation intensity, the more rapid the amplitude change of the maximum value point, which indirectly indicates that the vibration degree of the maximum value point is greater. Among them, the method for obtaining the slope is a well-known technology and will not be repeated. Therefore, this embodiment obtains the vibration reference degree of the maximum value point according to the reference analysis value and the oscillation intensity; wherein the reference analysis value and the vibration reference degree are negatively correlated, and the oscillation intensity and the vibration reference degree are positively correlated;

[0100] In order to accurately represent the vibration degree of the maximum point, the present embodiment specifically quantifies the vibration reference degree into a vibration reference degree value. The larger the vibration reference degree value, the greater the vibration degree of the maximum point. The calculation formula of the vibration reference degree value is: ; In the formula, is the vibration reference value of the ith maximum point in the ath local vibration area; is the number of reference points in the second preset window of the i-th maximum point in the a-th local vibration area; For the The probability of occurrence of reference points; is the reference analysis value; e is the natural constant; is the slope of the adjacent point before the i-th maximum point in the a-th local vibration area; is the slope of the adjacent point after the ith maximum point in the ath local vibration area; is the oscillation intensity of the ith maximum point in the ath local vibration region; is an absolute value function. In other embodiments, Get or Get , which is not limited here;

[0101] At this point, the vibration reference degree value of each maximum point in the local vibration area is obtained;

[0102] In order to accurately obtain the vibration degree in the local vibration area, and then determine the degree to which the current signal in the local current area is affected by the vibration, this embodiment obtains the average of the vibration reference degree values ​​of all the maximum value points in the local vibration area as the vibration influence degree value of the local current area. The larger the vibration influence degree value, the greater the degree to which the current signal in the local current area is disturbed by the vibration;

[0103] At this point, the vibration influence degree value of each local current area is obtained.

[0104] Step S4: based on the current current distortion degree of each key part, the vibration influence degree and the abnormality degree in each local current area, the signal decomposition intensity of each local current area of ​​each key part is obtained.

[0105] Specifically, when the current current distortion degree of a key part is greater, it means that the current current signal of the key part is more interfered by external factors, which indirectly means that the current current signal of the key part is more complex. In order to accurately decompose the current current signal of the key part through the local mean decomposition algorithm, the signal decomposition strength of each local current area of ​​the key part should be greater; at the same time, when the vibration influence degree of a local current area is greater, it means that the current signal in the local current area is more disturbed by vibration, which indirectly means that the current signal in the local current area is more complex. In order to accurately decompose the current signal in the local current area through the local mean decomposition algorithm, the signal decomposition strength of the local current area should be greater; further, when the abnormality degree of the current data in a local current area is greater, it means that the local current area is more likely to have abnormalities. In order to accurately obtain the real current signal in the local current area, the signal decomposition strength of the local current area should be greater. Therefore, this embodiment obtains the signal decomposition strength of each local current area of ​​each key part based on the current current distortion degree of each key part, the vibration influence degree and the abnormality degree in each local current area. The greater the signal decomposition strength, the greater the degree to which the current signal in the corresponding local current region needs to be decomposed.

[0106] Preferably, in some possible implementations of this embodiment, the method for obtaining the signal decomposition strength is described in Figure 3 , which shows a flow chart of a method for obtaining signal decomposition strength provided by an embodiment of the present invention, the method comprising the following steps:

[0107] Step S401: Obtain the current current distortion degree.

[0108] During the operation of the drive device, electromagnetic interference is generated between the key parts, and different key parts are subjected to different degrees of electromagnetic interference, which causes different degrees of distortion of the current signal of each key part. In order to analyze the distortion of the current current signal of each key part, this embodiment first analyzes the historical current signal correlation between each key part and each other key part in the historical time period, and then determines the degree of electromagnetic interference of each key part by other key parts, and preliminarily determines the degree of electromagnetic interference of the current current signal of each key part by other key parts; then analyzes the difference between the current current signal of each key part and its historical current signal, and further determines the abnormal distortion degree of the current current signal of each key part, and finally obtains the current current distortion degree of each key part, and determines the severity of the interference of the current current signal of each key part.

[0109] Preferably, in some possible implementations of this embodiment, the method for obtaining the current current distortion degree can refer to Figure 4 , which shows a flow chart of a method for obtaining the current distortion degree provided by an embodiment of the present invention, the method comprising the following steps:

[0110] Step S401 - 1 : Obtain the overall impact value.

[0111] This embodiment first obtains the absolute value of the Pearson correlation coefficient of the historical current signal of the same operation between any two key parts as a reference correlation value; the larger the reference correlation value, the greater the correlation degree between the historical current signals of the corresponding two key parts in the same operation, which indirectly indicates that the electromagnetic mutual influence degree between the two key parts is greater; in order to more accurately obtain the electromagnetic interference degree between any two key parts, the mean of all reference correlation values ​​between any two key parts in the historical time period is obtained as the current influence value of the corresponding two key parts; the larger the current influence value, the greater the electromagnetic mutual interference degree between the two key parts. Among them, the method for obtaining the Pearson correlation coefficient is a well-known technology and will not be repeated.

[0112] In order to determine the electromagnetic interference of each key part to other key parts, for any key part, the average of the current influence values ​​of the key part and each other key part is obtained as the overall influence value of the key part; the larger the overall influence value, the greater the electromagnetic interference of the key part, which indirectly indicates that the current current signal of the key part is more likely to be distorted. The calculation formula of the overall influence value is: ; In the formula, is the overall impact value of the bth key part; Q is the total number of key parts; H is the number of times the drive device operates in the historical time period; is the Pearson correlation coefficient between the historical current signal of the bth key part of the hth operation of the drive device within the historical time period and the historical current signal of the qth key part; is the reference related value; is the current influence value of the bth key part and the qth key part; is the absolute value function.

[0113] At this point, the overall impact value of each key part is obtained.

[0114] Step S401 - 2: Obtain the current abnormality level.

[0115] In order to further analyze the situation where the current current signal of each key part has uncertain factors, this embodiment obtains the absolute value of the difference between the mean of all current data in the current current signal of each key part and the mean of all current data in each historical current signal, all of which are taken as the second difference; when the second difference is larger, it means that the difference between the current current signal of the corresponding key part and the historical current signal of the corresponding operation is larger, which indirectly indicates that the current current signal of the corresponding key part has a greater possibility of abnormal distortion. In order to more accurately indicate the possibility of abnormality in the current current signal of each key part, therefore, for any key part, this embodiment uses the mean of all second differences corresponding to the key part as the current current abnormality degree value of the key part. The larger the current current abnormality degree value, the greater the degree of abnormal distortion of the current current signal of the key part. Among them, the calculation formula for obtaining the current current abnormality degree value is: ; In the formula, is the current abnormality value of the bth key part; H is the number of times the drive device operates in the historical time period; is the mean value of all current data in the current current signal of the bth key part; is the mean value of all current data in the hth historical current signal of the bth key part; for the second difference; is the absolute value function.

[0116] At this point, the current abnormality level value of each key part is obtained.

[0117] Step S401 - 3 : obtaining the current current distortion degree.

[0118] It is known that the greater the overall impact value, the greater the degree of electromagnetic interference to the current current signal of the corresponding key part, which indirectly indicates that the current current signal of the corresponding key part is more likely to be distorted; the greater the current current abnormality value, the greater the possibility of abnormal distortion to the current current signal of the corresponding key part. Therefore, this embodiment obtains the current current distortion degree of each key part according to the overall impact value and the current current abnormality of each key part; wherein, the overall impact value and the current current abnormality are both positively correlated with the current current distortion degree. The greater the current current distortion degree, the greater the current current signal of the corresponding key part is affected by uncertain factors.

[0119] In order to accurately indicate the distortion degree of the current current signal at each key part, this embodiment specifically quantifies the current current distortion degree as a current current distortion degree value. The larger the current current distortion degree value, the more complex the current current signal at the corresponding key part. The calculation formula of the current current distortion degree value is: ; In the formula, is the current distortion value of the bth key part; is the overall impact value of the bth key part; is the current current abnormality value of the bth key part. In other embodiments, the current current distortion value can be obtained by adding the overall impact value and the current current abnormality value, which is not limited here.

[0120] At this point, the current distortion level value of each key part is obtained.

[0121] Step S402: Obtain signal complexity.

[0122] It is known that the greater the degree of current current distortion, the greater the degree of interference of the current current signal of the corresponding key part by uncertain factors, that is, the more information is contained in the current current signal of the corresponding key part; the greater the degree of vibration influence, the greater the degree of vibration interference of the corresponding local current area, which indirectly indicates that the current signal in the corresponding local current area is more complex. Therefore, according to the degree of current current distortion of each key part and the degree of vibration influence of each local current area of ​​the corresponding key part, the signal complexity of each local current area of ​​each key part is obtained. Among them, the degree of vibration influence and the degree of current current distortion are positively correlated with the signal complexity.

[0123] In order to accurately represent the signal complexity of each local current region of each key part, this embodiment specifically quantifies the signal complexity as a signal complexity value. The larger the signal complexity value, the more information the current signal in the corresponding local current region contains. The calculation formula of the signal complexity value is: ; In the formula, is the signal complexity value of the ath local current region of the bth key part; is the vibration influence value of the ath local current area of ​​the bth key part; is the current current distortion value of the bth key part. In other embodiments, the signal complexity value may be obtained by adding the vibration influence value to the current current distortion value, which is not limited here.

[0124] At this point, the signal complexity value of each local current area of ​​each key part is obtained.

[0125] Step S403: Obtain signal decomposition strength.

[0126] When the signal in a local current region is more complex, in order to accurately decompose the signal in the local current region, the signal decomposition strength of the local current region should be greater; when the abnormality of the current data in a local current region is greater, in order to ensure that the signal in the local current region is accurately decomposed, and then accurately analyze the abnormality of the signal in the local current region, the signal decomposition strength of the local current region should be greater. In order to determine the abnormality of the current data in each local current region, this embodiment obtains the mean of the abnormality of all current data in each local current region as the reference abnormality value of the corresponding local current region; the larger the reference abnormality value, the greater the possibility that the signal in the corresponding local current region is abnormal, and the signal decomposition strength of the corresponding local current region should be greater. Furthermore, this embodiment obtains the signal decomposition strength of each local current region of each key part according to the signal complexity and the reference abnormality; wherein the signal complexity and the reference abnormality are both positively correlated with the signal decomposition strength.

[0127] In order to accurately represent the signal decomposition strength of each local current region, this embodiment specifically quantifies the signal decomposition strength as a signal decomposition strength value. The larger the signal decomposition strength value, the more the current signal in the corresponding local current region should be decomposed by the local mean decomposition algorithm for a deeper degree of decomposition. The calculation formula of the signal decomposition strength value is: ; In the formula, is the signal decomposition intensity value of the ath local current region of the bth key part; is the signal complexity value of the ath local current region of the bth key part; is the reference abnormality value of the ath local current region of the bth key part; norm is the normalization function. In other embodiments, Get , which is not limited here.

[0128] At this point, the signal decomposition intensity value of each local current area of ​​each key part is obtained.

[0129] Step S5: obtaining the optimal decomposition interval scale of each local current region in the LMD decomposition algorithm based on the signal decomposition strength.

[0130] In the traditional local mean decomposition (LMD) algorithm, this embodiment sets the sliding window of current data in each local current region to 20. The implementer can set the size of the sliding window according to the actual situation, which is not limited here. According to the local mean of the current data in the sliding window, the initial decomposition interval scale of each local current region is obtained. It is known that the current signal in each local current region is interfered by other external factors such as electromagnetic and vibration. In order to make the current signal in each local current region more accurately decomposed, therefore, this embodiment adjusts the initial decomposition interval scale of each local current region according to the signal decomposition strength of each local current region, and then accurately obtains the optimal decomposition interval scale of each local current region. Then, the current current signal of each key part is accurately decomposed by the local mean decomposition (LMD) algorithm and the optimal decomposition interval scale.

[0131] Preferably, in some possible implementations of this embodiment, the method for obtaining the optimal decomposition interval scale is: for any local current region, when the signal decomposition strength of the local current region is greater, it means that the current signal in the local current region needs a deeper degree of decomposition, and the decomposition interval scale of the local current region should be smaller; therefore, this embodiment uses the result of negative correlation of the signal decomposition strength of the local current region as the adjustment weight of the local current region; and then adjusts the initial decomposition interval scale of the local current region in the local mean decomposition (LMD) algorithm by adjusting the weight, and obtains the optimal decomposition interval scale of the local current region in the local mean decomposition (LMD) algorithm. Among them, the calculation formula for obtaining the optimal decomposition interval scale is: ; In the formula, is the optimal decomposition interval scale of the ath local current region of the bth key part in the local mean decomposition (LMD) algorithm; is the signal decomposition intensity value of the ath local current region of the bth key part; is the adjustment weight of the ath local current region of the bth key part; is the initial decomposition interval scale of the ath local current region of the bth key part in the local mean decomposition (LMD) algorithm. So far, the optimal decomposition interval scale of each local current region in the local mean decomposition (LMD) algorithm is obtained.

[0132] In order to analyze the abnormal fault conditions of each key part, each current current signal is decomposed by the local mean decomposition (LMD) algorithm according to the optimal decomposition interval scale of each local current region of each current current signal in the local mean decomposition (LMD) algorithm, and the component signal of each current current signal is accurately obtained. It is known that the component signal corresponding to the interference factor is unstable. In order to remove the influence of the interference signal, this embodiment sorts the component signal of each current current signal in order from high to low according to the stability, and obtains the component signal sequence of each current current signal; wherein, the stability of each component signal is reflected by the variance of the data in the corresponding component signal, that is, when the variance of the data in a certain component signal is smaller, the stability of the component signal is higher.

[0133] Reconstruct the first preset number of component signals in each component signal sequence separately to obtain the reconstructed current signal of each current current signal as the real current signal of the corresponding key part; in this embodiment, the preset number is set to 3, and the implementer can set the size of the preset number according to the actual situation, which is not limited here. Obtain the result of normalizing the current data of each real current signal at the current moment as the fault reference value of the corresponding key part; it is known that when a fault abnormality occurs in a key part, the larger the corresponding current data. Therefore, in this embodiment, the preset abnormal current data threshold is set to 0.5, and the implementer can set the size of the preset abnormal current data threshold according to the actual situation, which is not limited here. When the fault reference value is greater than or equal to the preset abnormal current data threshold, the corresponding key part has a fault abnormality at the current moment.

[0134] At this point, accurately obtaining the abnormal fault location of the drive device at the current moment is conducive to timely maintenance by the staff and ensures that the drive device works stably and safely.

[0135] In summary, this embodiment obtains the current current signal and current vibration signal of each key part of the drive device; based on the current data in the current current signal, the degree of abnormality is obtained to divide the current current signal into local current areas; based on the distribution of vibration data in the local current vibration signal corresponding to the local current area, the degree of vibration influence is obtained; based on the current current distortion degree, vibration influence degree and abnormality degree of the key part, the signal decomposition strength of the local current area is obtained, and then the optimal decomposition interval scale of the local current area in the LMD decomposition algorithm is obtained. The present invention obtains the optimal decomposition interval scale, and then accurately decomposes the current current signal, removes the influence of interference factors on the current current signal, and is conducive to accurately monitoring the fault anomalies of each key part of the drive device.

[0136] Embodiment 2:

[0137] The present invention also proposes a fault anomaly monitoring system for a drive device, see Figure 5 , which shows a structural diagram of a fault anomaly monitoring system for a drive device provided by an embodiment of the present invention, the system includes: an acquisition module 10, a local current area acquisition module 20, a vibration influence degree acquisition module 30, a signal decomposition intensity acquisition module 40 and an optimal decomposition interval scale acquisition module 50.

[0138] The acquisition module 10 is used to acquire the current current signal and the current vibration signal of each key part of the driving device during the current operation.

[0139] The local current region acquisition module 20 is used to acquire the abnormality degree of each current data based on the distribution of each current data in the current current signal and the surrounding current data; and divide all current current signals into local current regions based on the abnormality degree.

[0140] The vibration influence degree acquisition module 30 is used to acquire the vibration influence degree of each local current area based on the distribution of vibration data in the local current vibration signal corresponding to each local current area.

[0141] The signal decomposition strength acquisition module 40 is used to acquire the signal decomposition strength of each local current area of ​​each key part based on the current current distortion degree of each key part, the vibration influence degree and the abnormality degree in each local current area.

[0142] The optimal decomposition interval scale acquisition module 50 is used to acquire the optimal decomposition interval scale of each local current region in the LMD decomposition algorithm based on the signal decomposition strength.

[0143] It should be noted that: the system provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the above embodiment provides a fault anomaly monitoring system for a drive device and a fault anomaly monitoring method for a drive device, which belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0144] Embodiment 3:

[0145] The present invention also proposes a fault anomaly monitoring device for a drive device, the device comprising a memory and a processor, wherein the memory stores an executable program code, and the processor is used to call and execute the executable program code to execute a fault anomaly monitoring method for a drive device provided in an embodiment of the present application. The device can be a chip, a component or a module, and the chip can include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a fault anomaly monitoring method for a drive device provided in the above embodiment.

[0146] In addition, the present application embodiment also protects a computer device, see Figure 6 The computer device includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402, wherein when the processor 402 executes the computer program 403, the computer device can execute any one of the aforementioned fault and abnormality monitoring methods for a drive device.

[0147] Embodiment 4:

[0148] This embodiment also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement a fault anomaly monitoring method for a drive device provided in the above embodiment.

[0149] Embodiment 5:

[0150] This embodiment further provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement a fault and abnormality monitoring method for a drive device provided in the above embodiment.

[0151] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here.

[0152] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0153] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A fault anomaly monitoring method for a drive device, characterized in that: The method comprises the following steps: Obtain the current current signal and current vibration signal of each key part of the current operation of the drive device; Based on the distribution of each current data in the current current signal and the surrounding current data, the abnormality degree of each current data is obtained; based on the abnormality degree, all current current signals are divided into local current areas; Based on the distribution of vibration data in the local current vibration signal corresponding to each local current area, the vibration influence degree of each local current area is obtained; Based on the current current distortion degree of each key part, the vibration influence degree and the abnormality degree in each local current area, obtaining the signal decomposition intensity of each local current area of ​​each key part; Obtaining an optimal decomposition interval scale for each local current region in an LMD decomposition algorithm based on the signal decomposition strength; The fault anomaly monitoring method for a drive device further includes: According to the optimal decomposition interval scale of each local current region of each current current signal in the LMD decomposition algorithm, each current current signal is decomposed by the LMD decomposition algorithm to obtain the component signal of each current current signal; The component signals of each segment of the current current signal are sorted in descending order according to the stability, so as to obtain a component signal sequence of each segment of the current current signal; Reconstructing the first preset number of component signals in each component signal sequence respectively to obtain the reconstructed current signal of each current current signal as the real current signal of the corresponding key part; The result of normalizing the current data of each segment of the real current signal at the current moment is used as the fault reference value of the corresponding key part; When the fault reference value is greater than or equal to the preset abnormal current data threshold, the corresponding key part has a fault abnormality at the current moment.

2. A fault anomaly monitoring method for a drive device as claimed in claim 1, characterized in that: The method for obtaining the abnormality degree is: Constructing a first preset window of each current data in all current current signals; For any current data in all current current signals, obtaining the information entropy of the current data in a first preset window of the current data as a first abnormal reference value of the current data; Obtaining a mean value of all current data in a first preset window of the current data as a first characteristic value of the current data; using a first characteristic value difference between the current data and the previous adjacent current data as a second abnormal reference value of the current data; taking the difference between the maximum current data and the minimum current data in the first preset window of the current data as the current difference; taking the difference between the time points corresponding to the maximum current data and the minimum current data in the first preset window of the current data as the time difference; The ratio of the current difference to the time difference is used as a third abnormal reference value of the current data; The abnormality degree of the current data is acquired according to the first abnormality reference value, the second abnormality reference value and the third abnormality reference value of the current data.

3. A fault anomaly monitoring method for a drive device as claimed in claim 1, characterized in that: The method for obtaining the local current area is: For any current current signal, obtaining a difference in abnormality between any two adjacent current data in the current current signal as a first difference; When the first difference is greater than or equal to a preset first difference threshold, division is performed between two corresponding adjacent current data, and each local current signal segment after the current current signal is divided is used as a local current region.

4. A method for monitoring fault anomalies of a drive device according to claim 1, characterized in that: The method for acquiring the local current vibration signal corresponding to each local current area is: For any local current region, the time period corresponding to the local current region is used as a reference time period; The current vibration signal of the key part corresponding to the local current area within the reference time period is used as the local current vibration signal corresponding to the local current area.

5. A fault anomaly monitoring method for a drive device as claimed in claim 1, characterized in that: The method for obtaining the vibration impact degree is: For any local current region, the local current vibration signal corresponding to the local current region is taken as the local vibration region; For any maximum value point in the local vibration area, a second preset window of the maximum value point is constructed, and all the maximum value points in the second preset window of the maximum value point are used as reference points; The probability of the amplitude corresponding to each reference point appearing in the current vibration signal in the local vibration area is used as the occurrence probability value of each reference point; Obtain the product of the occurrence probability values ​​of all reference points as the reference analysis value; Obtain the slope difference between the adjacent points on the left and right of the maximum point as the oscillation intensity of the maximum point; According to the reference analysis value and the oscillation intensity, the vibration reference degree of the maximum value point is obtained; wherein the reference analysis value and the vibration reference degree are negatively correlated, and the oscillation intensity and the vibration reference degree are positively correlated; The average value of the vibration reference degrees of all the maximum value points in the local vibration area is obtained as the vibration influence degree of the local current area.

6. A method for monitoring fault anomalies of a drive device according to claim 1, characterized in that: The method for obtaining the current current distortion degree is: Obtain the current signals of each key part of the driving device during each operation in the historical time period as historical current signals; Obtain the absolute value of the Pearson correlation coefficient of the historical current signals of the same operation between any two key parts as a reference correlation value; The average of all reference correlation values ​​between any two key parts in the historical time period is used as the current impact value of the corresponding two key parts; For any key part, obtain the average of the current influence values ​​of the key part and each other key part as the overall influence degree value of the key part; Obtaining the degree of abnormality of the current current of the key part according to the difference between the mean value of all current data in the current current signal of the key part and the mean value of all current data in each of its historical current signals; The current current distortion degree of the key part is obtained according to the overall influence degree value of the key part and the current current abnormality degree; wherein the overall influence degree value and the current current abnormality degree are both positively correlated with the current current distortion degree.

7. A method for monitoring fault anomalies of a drive device according to claim 1, characterized in that: The method for obtaining the signal decomposition strength is: For any local current region of any key part, the signal complexity of the local current region of the key part is obtained according to the vibration influence degree of the local current region and the current current distortion degree of the key part; wherein the vibration influence degree and the current current distortion degree are both positively correlated with the signal complexity; Obtaining a mean value of the abnormality levels of all current data in the local current region as a reference abnormality level of the local current region; According to the signal complexity and the reference abnormality, the signal decomposition strength of the local current area of ​​the key part is obtained; wherein the signal complexity and the reference abnormality are both positively correlated with the signal decomposition strength.

8. A method for monitoring fault anomalies of a drive device according to claim 1, characterized in that: The method for obtaining the optimal decomposition interval scale is: For any local current region, the result of negative correlation of the signal decomposition intensity of the local current region is used as the adjustment weight of the local current region; The initial decomposition interval scale of the local current region in the LMD decomposition algorithm is adjusted by adjusting the weight, so as to obtain the optimal decomposition interval scale of the local current region in the LMD decomposition algorithm.

9. A fault and abnormality monitoring system for a drive device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When executing the computer program, the processor implements the steps of a fault and abnormality monitoring method for a drive device as described in any one of claims 1 to 8.

Images