Industrial design cloud platform system based on artificial intelligence

Abstract

The present invention relates to the field of data processing technology, and in particular to an artificial intelligence-based industrial design cloud platform system, comprising: an acquisition module for acquiring vibration monitoring data and operating parameters of a target part of a target device within a monitoring period; a decomposition module for performing independent component decomposition on the vibration monitoring data to obtain multiple vibration components and signal component sequences; a determination module for determining the average abnormality of the vibration monitoring data based on the amplitude of the data points of the signal component sequence of each vibration component and the signal component sequence; a determination module for determining the vibration deviation of the vibration monitoring data of the target part based on the operating parameters; the determination module is further used to determine the processing requirement of the vibration monitoring data based on the average abnormality and the vibration deviation; and a processing module for smoothing the vibration monitoring data based on the processing requirement to remove noise interference in the vibration monitoring data. This improves the accuracy and credibility of the monitoring data.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an industrial design cloud platform system based on artificial intelligence. Background Art

[0002] Industrial design cloud platforms combine the powerful capabilities of the cloud with the complex demands of industry, aiming to support the management and optimization of industrial products from conception to production. These platforms typically include key features such as integrated design tools, collaboration and communication, big data and analytics, and security and reliability.

[0003] In some scenarios, AI-based industrial design cloud platform systems often need to integrate monitoring data from multiple different data sources, including sensors, production equipment, and product testing. However, the quality of the monitoring data collected in real time from various data sources varies. Some monitoring data has high quality, while others have low quality. Low-quality monitoring data may be due to significant noise interference or abnormal data caused by the equipment itself. Actual abnormal data caused by the equipment itself can be retained to facilitate subsequent monitoring and prevention. Abnormal data caused by significant noise interference can result in low accuracy and reliability of the monitoring data, which is not conducive to the management and optimization of the entire process of industrial products from conception to production. Summary of the Invention

[0004] In order to solve the technical problem of low accuracy and credibility of monitoring data, the purpose of the present invention is to provide an industrial design cloud platform system based on artificial intelligence. The technical solutions adopted are as follows:

[0005] The embodiment of the present application provides an industrial design cloud platform system based on artificial intelligence, including: an acquisition module for acquiring vibration monitoring data of a target part of a target device within a monitoring period and operating parameters of the target part of the target device during operation; a decomposition module for performing independent component decomposition on the vibration monitoring data to obtain multiple vibration components and a signal component sequence corresponding to each vibration component; a determination module for determining the average abnormality of the vibration monitoring data based on the amplitude of the data point of the signal component sequence of each vibration component and the signal component sequence, the average abnormality indicating the authenticity of the vibration monitoring data, and the average abnormality is inversely proportional to the authenticity; a determination module for determining the vibration of the target part according to the operating parameters The vibration deviation of the monitoring data indicates the possibility that the abnormal data points in the vibration monitoring data are caused by the target device, and the vibration deviation is proportional to the possibility that the abnormal data points in the vibration monitoring data are caused by the target device; the determination module is also used to determine the processing requirement of the vibration monitoring data based on the average abnormality and the vibration deviation, the processing requirement indicates the possibility that the abnormal data points in the vibration monitoring data are caused by noise interference, and the processing requirement is proportional to the possibility that the abnormal data points in the vibration monitoring data are caused by noise interference; the processing module is used to smooth the vibration monitoring data based on the processing requirement to remove noise interference in the vibration monitoring data.

[0006] Optionally, the determination module is also used to: determine the number of types of data points in the signal component sequence of the vibration component and the total number of data points of all data points, wherein data points with equal values ​​are of the same type; determine the local complexity of the vibration component among all vibration components based on the distribution probability value, the number of types and the total number of data points of each type of data points in the signal component sequence of the vibration component, the local complexity indicates the periodicity of the vibration component, and the local complexity is inversely proportional to the periodicity of the vibration component; determine the vibration abnormality of each data point in the signal component sequence of the vibration component based on the local complexity and the amplitude of the data point in the signal component sequence, the vibration abnormality indicates the possibility of the data point being abnormal, and the vibration abnormality is directly proportional to the possibility of the data point being abnormal; determine the average abnormality of the vibration monitoring data based on the vibration abnormality of each data point of each vibration component.

[0007] Optionally, the determination module is also used to: determine the absolute value of the difference between the distribution probability values ​​of any two types of data points in the signal component sequence of the vibration component to obtain m groups of absolute values ​​of the difference; superimpose the absolute values ​​of the m groups of differences and compare them with m to obtain a first ratio, the first ratio indicating the number of similar data points existing in the vibration monitoring data, the first ratio is inversely proportional to the number of similar data points existing in the vibration monitoring data, and m is an integer greater than 0; determine the second ratio between the number of types of the signal component sequence of the vibration component and the total number of data points; determine the product of the first ratio and the second ratio as the local complexity.

[0008] Optionally, the determination module is also used to: determine the average amplitude of the amplitudes of all data points in the signal component sequence of the vibration component, and the first difference between the maximum amplitude and the minimum amplitude of the data points in the signal component sequence; determine the absolute value of the second difference between the amplitude of the data point and the average amplitude, and the absolute value of the third difference between the amplitude of the data point and the first difference; determine a third ratio of the absolute value of the second difference to the absolute value of the third difference; perform a function operation on the local complexity using a hyperbolic tangent function to obtain an operation result; determine the product of the third ratio and the operation result, and use the product of the third ratio and the operation result as the vibration abnormality of the data point in the signal component sequence.

[0009] Optionally, the determination module is also used to: determine the feed rate of the target part during the monitoring period from the operating parameters; determine the error between the operating parameters and the vibration monitoring data; determine the parameter change complexity of the operating parameters based on the error and the feed rate, the parameter change complexity indicates the possibility that the abnormal data points in the vibration monitoring data are caused by the operating parameters of the target part, and the parameter change complexity is proportional to the possibility that the abnormal data points in the vibration monitoring data are caused by the operating parameters of the target part; determine the load on the target part during the monitoring period and the displacement of the target part under the load; determine the rigidity of the target part based on the load and displacement, the rigidity is inversely proportional to the probability of an abnormality in the data point in the vibration monitoring data; use the hyperbolic tangent function to perform a function operation on the product of the rigidity and the parameter change complexity to obtain the vibration deviation.

[0010] Optionally, the determination module is also used to: fit the operating parameters of the target part according to the monitoring time of the vibration monitoring data to obtain a fitting curve; determine the mean square error between the fitting curve and the vibration monitoring curve of the vibration monitoring data as the error; determine the degree of fluctuation of the feed rate of the target part within the monitoring time; and determine the parameter change complexity of the operating parameters based on the mean square error and the degree of fluctuation.

[0011] Optionally, the determination module is further used to: determine the ratio of the fluctuation degree to the mean square error as the parameter change complexity.

[0012] Optionally, the load includes radial load and axial load, and the displacement includes axial displacement and radial displacement. The acquisition module is further configured to: obtain the radial load and axial load of the target portion during the monitoring period, and the axial displacement of the target portion in the axial direction and the radial displacement of the target portion in the radial direction; the determination module is further configured to: determine the ratio of the fluctuation degree to the mean square error as the parameter variation complexity; determine a fourth ratio between the axial load and the axial displacement, and a fifth ratio between the radial load and the radial displacement; and determine the product of the fourth ratio and the fifth ratio as the stiffness of the target portion.

[0013] Optionally, the determination module is further used to: determine the sum of the square of the average abnormality and the square of the reciprocal of the vibration deviation; perform a square root operation on the sum to obtain an operation result, and use the operation result as the processing requirement.

[0014] The processing module is further used to: use the processing requirement as the standard deviation obeyed by the filter kernel of the Gaussian filter to obtain a target Gaussian filter; and use the target Gaussian filter to smooth the vibration monitoring data.

[0015] The present invention has the following beneficial effects: an acquisition module acquires vibration monitoring data of a target part of a target device within a monitoring period and operating parameters of the target part of the target device during operation, a decomposition module then performs independent component decomposition on the vibration monitoring data to obtain a plurality of vibration components and corresponding signal component sequences, a determination module then determines the average abnormality of the vibration monitoring data according to the amplitude of the data points of the signal component sequences of each vibration component and the signal component sequence, and determines the vibration deviation of the vibration monitoring data of the target part according to the operating parameters, the vibration deviation can reflect whether the abnormal data points in the vibration monitoring data are caused by the device, thereby predicting possible failures of the target device during the production process, thereby timely processing and improving production efficiency. Finally, the determination module determines the processing requirement of the vibration monitoring data according to the average abnormality and the vibration deviation, the processing requirement can reflect whether the abnormal data points in the vibration monitoring data are caused by noise interference, so that the processing module can perform smoothing processing on the vibration monitoring data based on the processing requirement to remove noise interference in the vibration monitoring data, thereby improving the accuracy and credibility of the monitoring data, and facilitating the whole process management and optimization of industrial products from concept to production. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. 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 any creative work.

[0017] Figure 1 A schematic diagram of the module composition of an artificial intelligence-based industrial design cloud platform system provided by one embodiment of the present invention;

[0018] Figure 2 A schematic diagram of a curve showing a fitting curve and intensity values ​​of vibration monitoring data provided by an embodiment of the present invention;

[0019] Figure 3A schematic diagram of radial load and axial load acting on a main shaft provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0020] To further illustrate the technical means and effects employed by the present invention to achieve the intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effects of an artificial intelligence-based industrial design cloud platform system proposed by the present invention. In the following description, different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0021] 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.

[0022] The following describes in detail an artificial intelligence-based industrial design cloud platform system provided by the present invention in conjunction with the accompanying drawings.

[0023] See also Figure 1 , which shows a schematic diagram of the module composition of an artificial intelligence-based industrial design cloud platform system provided by an embodiment of the present invention. The artificial intelligence-based industrial design cloud platform system 100 includes: an acquisition module 101, a decomposition module 102, a determination module 103 and a processing module 104.

[0024] The acquisition module 101 is configured to acquire vibration monitoring data of a target portion of a target device within a monitoring period and operating parameters of the target portion of the target device during operation.

[0025] Specifically, the target device can be production line equipment, industrial robots, and the like, such as a CNC machine tool. The target location can be a key location of the target device, and the vibration monitoring data can be collected by installing a vibration sensor at the target location. For example, key locations of a CNC machine tool can be the spindle, spindle box, worktable, guide rails, and the like. Vibration sensors can be installed at these key locations to collect vibration data at each location. The acquisition module 101 uses a wireless or wired network, such as Ethernet or Wireless Fidelity (WIFI), to acquire the vibration monitoring data collected by the vibration sensor. The monitoring duration can be set according to actual needs and is not limited in this embodiment of the present application.

[0026] Vibration monitoring data includes but is not limited to acceleration, velocity, displacement, phase and other data. The vibration monitoring data of the target equipment can reflect the operating status and health of the equipment. By monitoring vibration data in real time, it is possible to identify abnormal vibration patterns of the target equipment, predict possible mechanical failures or component wear, and perform maintenance and repairs in a timely manner to avoid production interruptions and additional costs caused by sudden equipment shutdowns. In the vibration monitoring data of the target equipment, since the vibration monitoring data may contain some deviations from the normal vibration pattern, this may be caused by parameter settings during the operation of the target equipment or the equipment itself, or it may be caused by the presence of more interference in the vibration monitoring data. Therefore, it is necessary to conduct a detailed analysis of the causes of the abnormalities in the vibration monitoring data.

[0027] The operating parameters of the target part of the target device during operation include, but are not limited to, data such as rotation speed, power, feed rate, spindle ratio, temperature, humidity, load, and displacement under load. In the industrial design cloud platform system based on artificial intelligence, the vibration of the target device is monitored in real time, and in the process of processing the vibration monitoring data, "abnormal" phenomena that are different from normal vibration patterns may also be "abnormal" behaviors caused by parameter changes or equipment operation time during the operation of the equipment. Such abnormal behavior is inevitable, that is, the allowable error in the operation process, so as to better distinguish the actual noise interference situation. Therefore, the operating parameters of the target device can be used to distinguish whether the abnormality in the vibration monitoring data is caused by the equipment itself or by the existence of interference noise.

[0028] The decomposition module 102 is used to perform independent component decomposition on the vibration monitoring data to obtain multiple vibration components and a signal component sequence corresponding to each vibration component.

[0029] Specifically, the decomposition module 102 can use a decomposition algorithm to decompose the vibration monitoring data. The decomposition algorithm has certain decomposition rules in the process of decomposing signal data. That is, due to the presence of different types of vibration components in the vibration monitoring data, it will be decomposed into different vibration components, such as fundamental frequency components, harmonic components, subharmonic components, natural frequencies, etc. The signal component sequence corresponding to each vibration component includes multiple data points.

[0030] The determination module 103 is used to determine the average abnormality of the vibration monitoring data according to the amplitude of the data points of the signal component sequence of each vibration component and the signal component sequence. The average abnormality indicates the authenticity of the vibration monitoring data and is inversely proportional to the authenticity.

[0031] Furthermore, the authenticity indicates the number of abnormal data points in the vibration monitoring data, and the authenticity is inversely proportional to the number of abnormal data points in the vibration monitoring data.

[0032] Specifically, there are multiple data points in the signal component sequence, each corresponding to a specific amplitude (value). Data points with equal amplitudes are considered to be one type of data point. For example, in a signal component sequence of vibration monitoring data, data points with a value of 5 are considered to be one type of data point, and data points with a value of 2 are considered to be another type of data point. The local complexity of the signal component sequence of each vibration component can be calculated, and then the vibration anomaly of each data point in each vibration component can be determined based on the local complexity. Finally, the average anomaly of the vibration monitoring data can be determined based on the local complexity and the vibration anomaly.

[0033] Among them, the process of determining the local complexity by the determination module 103 is as follows: determining the number of types of data points and the total number of data points of all data points in the signal component sequence of the vibration component, wherein data points with equal values ​​are of the same type; determining the local complexity of the vibration component among all vibration components based on the distribution probability value, number of types and total number of data points of each type of data points in the signal component sequence of the vibration component, the local complexity indicates the periodicity of the vibration component, and the local complexity is inversely proportional to the periodicity of the vibration component.

[0034] Specifically, the amplitude of the data points in the signal component sequence may have multiple different values, and the number of types of data points can be determined from the number of different values. For example, if there are multiple data points with values ​​of 1, 2, 4, and 6 in the signal component sequence, the number of types of data points is 4. The total number of data points is the number of all data points in the signal component sequence. The greater the local complexity, the worse the periodicity of the vibration component, and there are fewer equal data points among all the data points in the signal component sequence of the vibration component, indicating that the local complexity of the data points of the vibration component among all vibration components is higher. This local complexity provides data support for the subsequent evaluation of anomalies in the monitoring data. The distribution probability value refers to the probability of the data of the signal component sequence of the vibration component in a certain interval or specific value. The content related to the distribution probability value in the prior art also falls within the scope to be protected by the embodiments of the present application. They can be referenced with each other, and the embodiments of the present application will not be repeated here.

[0035] When the determination module 103 determines the local complexity, the process is as follows: determining the absolute value of the difference between the distribution probability values ​​of any two types of data points in the signal component sequence of the vibration component to obtain m groups of absolute values ​​of the difference; superimposing the absolute values ​​of the m groups of differences and comparing them with m to obtain a first ratio, the first ratio indicating the number of similar data points existing in the vibration monitoring data, m being an integer greater than 0, and the first ratio being inversely proportional to the number of similar data points existing in the vibration monitoring data; determining a second ratio between the number of types of the signal component sequence of the vibration component and the total number of data points; and determining the product of the first ratio and the second ratio as the local complexity.

[0036] Specifically, local complexity can be expressed as follows:

[0037]

[0038] Where, represents the local complexity, It represents the distribution probability value of the i-th type of data point in the signal component sequence of the vibration component of the vibration monitoring data of the target equipment (data points with equal values ​​are recorded as one type of data point); It represents the distribution probability value of the j-th data point in the signal component sequence of the vibration component of the vibration monitoring data of the target equipment; there is a set of difference values ​​between the distribution probability values ​​of any two types of data points, and there are m sets of difference values ​​in total; g represents the number of types of data points in the signal component sequence in the vibration monitoring data; G represents the total number of data points of all data points.

[0039] The average value of the difference between the distribution probability values ​​of various data points in the signal component sequence representing the vibration component of the vibration monitoring data. The smaller the average value, the more similar data points there are in the vibration component of the vibration monitoring data, which means that the data corresponding to the vibration component of the vibration monitoring data of the target device has a strong periodic feature; The smaller the ratio is, the more it means that the number of data point types is less than the total number of data points, which means that there must be more data points with equal values ​​among the G data points. The local complexity of the data of the vibration component of the vibration monitoring data of the target device among all vibration components is as follows: the greater the local complexity, the worse the periodicity of the vibration component of the vibration monitoring data of the target device is, and there are fewer equal data points among all data points of the vibration component of the vibration monitoring data of the target device, indicating that the local complexity of the vibration component of the vibration monitoring data of the target device is high. The local complexity provides data support for the subsequent evaluation of anomalies in the monitoring data.

[0040] The process of determining the vibration abnormality by the determination module 103 is as follows: the vibration abnormality of each data point in the signal component sequence of the vibration component is determined based on the local complexity and the amplitude of the data point in the signal component sequence. The vibration abnormality indicates the possibility of abnormality of the data point, and the vibration abnormality is proportional to the possibility of abnormality of the data point.

[0041] Specifically, during the independent component analysis of vibration monitoring data, under normal circumstances, the data points in the signal component sequence of a single vibration component should not exhibit any local abnormal behavior. That is, the average level of data points in this vibration component should be relatively stable. If there are relatively "prominent" data points in the signal component sequence of the vibration component, they can be considered to be relatively abnormal data points. This prominent data point can be identified by the vibration anomaly degree. The greater the vibration anomaly degree of the data point, the greater the possibility that the data point is abnormal.

[0042] More specifically, the determination module 103 determines the vibration abnormality in a more specific process as follows: determining the average amplitude of the amplitudes of all data points in the signal component sequence of the vibration component, and a first difference between the maximum amplitude and the minimum amplitude of the data points in the signal component sequence; determining the absolute value of the second difference between the amplitude of the data point and the average amplitude, and the absolute value of the third difference between the amplitude of the data point and the first difference; determining a third ratio of the absolute value of the second difference to the absolute value of the third difference; performing a function operation on the local complexity using a hyperbolic tangent function to obtain an operation result; determining the product of the third ratio and the operation result, and using the product of the third ratio and the operation result as the vibration abnormality of the data point in the signal component sequence.

[0043] The vibration abnormality can be calculated using the following formula:

[0044]

[0045] Where, Indicates the degree of vibration abnormality. represents the local complexity of the u-th vibration component, represents the amplitude of the e-th data point in the vibration component of the vibration monitoring data of the target device; Represents the average amplitude of the amplitudes of all data points in the signal component sequence; The first difference (range) between the maximum and minimum amplitudes of the data points in the signal component sequence represented by , represents the hyperbolic tangent function.

[0046] in, It represents the initial vibration abnormality of a single data point. The larger the ratio, the greater the difference between the data point and the average level of the vibration component of the vibration monitoring data of the target equipment. The closer the difference is to the first difference, the more obvious the "abnormal" behavior of the data point in the distribution is. The “initial vibration abnormality” of a single data point is adjusted as the overall weight of the vibration component; The larger the product of , the greater the vibration abnormality of the data point. This value mainly provides data support for the subsequent screening of abnormal data points.

[0047] Furthermore, in order to avoid If the vibration abnormality cannot be calculated due to the value of 0, the absolute value of the third difference can be multiplied by the constant After adding, compare with the absolute value of the second difference. A value other than 0 may be taken according to actual conditions, and the present embodiment is not limited thereto. That is, the calculation formula for the vibration abnormality degree may also adopt the following formula according to actual conditions:

[0048]

[0049] Where, Indicates the degree of vibration abnormality. represents the local complexity of the u-th vibration component, represents the amplitude of the e-th data point in the vibration component of the vibration monitoring data of the target device; Represents the average amplitude of the amplitudes of all data points in the signal component sequence; The first difference (range) between the maximum and minimum amplitudes of the data points in the signal component sequence represented by , represents the hyperbolic tangent function, is a constant, and the value of k is as small as possible. As an embodiment of the present invention, for example, the value of k can be set to 0.1.

[0050] in, It represents the initial vibration abnormality of a single data point. The larger the ratio, the greater the difference between the data point and the average level of the vibration component of the vibration monitoring data of the target equipment. The closer the difference is to the first difference, the more obvious the "abnormal" behavior of the data point in the distribution is. The “initial vibration abnormality” of a single data point is adjusted as the overall weight of the vibration component; The larger the product of , the greater the vibration abnormality of the data point. This value mainly provides data support for the subsequent screening of abnormal data points.

[0051] The vibration anomaly degree of a single data point in a single vibration component is obtained through the above method. The vibration anomaly degrees of all data points in this vibration component are then sorted in ascending order. The difference between two adjacent vibration anomaly degrees is then obtained. All differences are traversed to find the first node with the largest difference. The sorted sequence is then divided into two parts. The data point to the right of the maximum difference is considered to have the largest vibration anomaly degree. Alternatively, the vibration anomaly degree corresponding to the maximum value is directly selected as the data point with the largest vibration anomaly degree. Based on the anomaly degrees of these data points, the abnormal components of the vibration monitoring data in the artificial intelligence-based industrial design cloud platform system can be evaluated.

[0052] Finally, the process of determining the average abnormality by the determination module 103 is as follows: determining the average abnormality of the vibration monitoring data according to the vibration abnormality of each data point of each vibration component.

[0053] Specifically, AI-based industrial design cloud platform systems typically integrate vibration monitoring data from various devices and environments, and effectively process the collected vibration monitoring data. However, the degree of interference in the vibration monitoring data can overwhelm the ability to express real data, thereby reducing the authenticity of the system's vibration monitoring data. The average abnormality can indicate the authenticity of the vibration monitoring data and can be calculated using the following formula:

[0054]

[0055] In the above formula, It represents the average abnormality. Assuming that the vibration components of the vibration monitoring data of a single target device have E data points screened out, It represents the vibration abnormality degree of the e-th abnormal data point in the signal component sequence of the u-th vibration component of the vibration monitoring data, and the vibration monitoring data has a total of R vibration components.

[0056] in, This represents the average abnormality of all vibration components in the target device's vibration monitoring data. A higher average abnormality indicates a higher number of abnormal data points and a higher degree of abnormality, reflecting the lower the authenticity of the vibration monitoring data. Subsequent verification and correction of abnormalities in the vibration monitoring data will be required from the target device itself.

[0057] The determination module 103 is configured to determine the vibration deviation of the vibration monitoring data of the target part according to the operating parameters.

[0058] The vibration deviation indicates the possibility that the abnormal data point of the vibration monitoring data is caused by the target device, and the vibration deviation is proportional to the possibility that the abnormal data point of the vibration monitoring data is caused by the target device.

[0059] Specifically, in an AI-based industrial design cloud platform system, vibration monitoring data from a target device is monitored. During the processing of the vibration monitoring data, "abnormal" phenomena that differ from the normal vibration pattern of the target device may also be caused by changes in operating parameters or the operating time of the device during operation. This abnormal behavior is caused by the device itself and is inevitable, that is, the allowable error during operation. Another situation is that there are interference components in the vibration monitoring data, which affects the evaluation of the target device. The operating parameters are used to determine the true cause of the abnormal data points in the vibration monitoring data. If it is caused by interference noise, the interference components are purified to more accurately screen out the interference components. Therefore, the vibration deviation of the target part of the target device can be determined by the operating parameters, so as to determine the true cause of the abnormal data points in the vibration monitoring data, so as to carry out targeted processing and improve the accuracy and effectiveness of the vibration monitoring data.

[0060] The process of determining the vibration deviation by the determination module 103 is as follows: first, determining the parameter variation complexity of the operating parameters, secondly determining the rigidity of the target part of the target device, and finally determining the vibration deviation according to the rigidity and the parameter variation complexity.

[0061] First, the process of determining the parameter change complexity by the determination module 103 is as follows: determining the feed rate of the target part within the monitoring time from the operating parameters; determining the error between the operating parameters and the vibration monitoring data; determining the parameter change complexity of the operating parameters based on the error and the feed rate, the parameter change complexity indicating the possibility that the abnormal data points in the vibration monitoring data are caused by the operating parameters of the target part, and the parameter change complexity is proportional to the possibility that the abnormal data points in the vibration monitoring data are caused by the operating parameters of the target part.

[0062] Specifically, the embodiment of the present application is described by taking the target device as a CNC machine tool as an example. The target part can be the spindle of the CNC machine tool, and the operating parameters can be the feed rate and the speed of the spindle. The error between the operating parameters and the vibration monitoring data can be the mean square error. The complexity of parameter changes indicates the possibility that the cause of the abnormal data points in the vibration monitoring data is caused by the change of the operating parameters of the target part. The greater the complexity of parameter changes, the more it indicates that the abnormal cause of the abnormal data points in the vibration monitoring data is mainly caused by the change of the operating parameters, and is not caused by external noise interference during the data acquisition process. In this way, the real cause of the abnormal data points in the vibration monitoring data can be distinguished, so that targeted processing can be carried out, thereby improving data processing efficiency and ensuring the reliability of vibration monitoring data.

[0063] When determining the error, the determination module 103 fits the operating parameters of the target part according to the monitoring time of the vibration monitoring data to obtain a fitting curve; and determines the mean square error between the fitting curve and the vibration monitoring curve of the vibration monitoring data as the error. Figure 2 As shown, the determination module 103 performs least square fitting on the spindle speed according to the monitoring time of the vibration monitoring data to obtain a speed curve; performs least square fitting on the vibration monitoring data of the spindle to obtain a vibration curve; normalizes the vertical coordinates of the speed curve and the vibration monitoring curve respectively to ensure the comparability of the two types of monitoring data in one coordinate system, and then keeps the horizontal coordinate at the time point unchanged, thereby obtaining a new coordinate system, in which the horizontal coordinate represents time, and the vertical coordinate represents the normalized data of the speed data and the normalized data of the vibration monitoring data, which can be understood as the intensity value of the speed and vibration monitoring data, and the obtained value is as follows. Figure 2 The curve shown, Figure 2 middle, is the fitting curve of the normalized value of the main shaft speed, that is, p is the fitting curve of the strength value of the speed, is the curve of the normalized value of the vibration monitoring data, that is, q is the fitting curve of the intensity value of the vibration monitoring data; Figure 2 The horizontal axis is time, and the vertical axis is the intensity value of the speed data and vibration monitoring data, where the vertical axis value range is 0-1. Then determine the mean square error of the fitting curve and the vibration monitoring curve as the error between the speed of the main shaft and the vibration monitoring curve. It should be noted that Figure 2 The vertical axis in is the normalized value, which ranges from 0 to 1 and has no unit; Figure 2 The unit of the horizontal axis is seconds (s). Mapping the vibration monitoring data and speed data to a coordinate system is to determine whether there is a changing response relationship between the two dimensions of data. Because the mean square error needs to be calculated, it is necessary to ensure that the subtracted data are in the same dimension. Therefore, the two data are normalized and fitted to the same coordinate system.

[0064] When determining the parameter variation complexity, the determination module 103 determines the degree of fluctuation of the feed rate of the target part during the monitoring period; and determines the parameter variation complexity of the operating parameter based on the mean square error and the degree of fluctuation. Specifically, the determination module 103 determines the parameter variation complexity as the ratio of the degree of fluctuation to the mean square error.

[0065] Specifically, the parameter change complexity can be calculated by the following formula:

[0066]

[0067] Where, Indicates the complexity of parameter changes, It represents the mean square error between the fitting curve of the spindle speed of the target equipment (such as CNC machine tools) in the cloud platform system and the vibration monitoring data curve of the spindle; Indicates the degree of fluctuation of the spindle feed rate within the monitoring period.

[0068] in, It indicates the complexity of parameter changes of the monitored target device during the data monitoring period of the cloud platform system. The larger the product, the higher the responsiveness of the spindle speed change to the vibration monitoring data and the greater the fluctuation of the feed rate. This indicates that the reason for the "abnormal" vibration of the target device during the monitoring process may be due to the change of the spindle feed rate or the change of the spindle speed, and is not caused by external interference during the data acquisition process.

[0069] Secondly, the process of determining the rigidity by the determination module 103 is as follows: determining the load on the target part during the monitoring period and the displacement of the target part under the load; determining the rigidity of the target part based on the load and displacement, and the rigidity is inversely proportional to the probability of an abnormality in the data point in the vibration monitoring data.

[0070] Specifically, in an AI-based industrial design cloud platform system, during vibration monitoring of CNC machine tools, abnormalities in the spindle's vibration monitoring data may be due to the spindle's axial and radial rigidity during machining. If the spindle deforms during operation or is affected by external factors, resulting in insufficient rigidity, the vibration pattern will deviate from its normal state, increasing the probability of abnormal data points in the vibration monitoring data. Therefore, the probability of abnormal data points in the vibration monitoring data can be determined by rigidity. The greater the rigidity, the lower the probability of abnormal data points in the vibration monitoring data due to rigidity, while the higher the probability of abnormal data points in the vibration monitoring data due to external interference noise. The lower the rigidity, the higher the probability of abnormal data points in the vibration monitoring data due to rigidity, while the lower the probability of abnormal data points in the vibration monitoring data due to external interference noise. The loads on the spindle during the monitoring period include radial loads and axial loads, and the displacements of the spindle under the action of the loads include axial displacements and radial displacements.

[0071] First, electromagnetic induction sensors are installed at the radial position and axial position of the main shaft to detect the radial displacement and axial displacement generated when the main shaft is subjected to radial force, such as Figure 3 As shown, the forces (loads) applied to the main shaft at the axial and radial positions can be directly measured using force sensors to obtain the axial load and radial load.

[0072] When the determination module 103 determines the load on the target part during the monitoring period and the displacement of the target part under the load, the acquisition module 101 is first required to obtain the radial load and axial load of the target part during the monitoring period, as well as the axial displacement of the target part in the axial direction and the radial displacement of the target part in the radial direction. Specifically, the acquisition module 101 can obtain the radial load, axial load, axial displacement, and radial displacement from the electromagnetic induction sensor and the force sensor. The determination module 103 then determines the fourth ratio between the axial load and the axial displacement, and the fifth ratio between the radial load and the radial displacement; the product of the fourth ratio and the fifth ratio is determined to be the rigidity of the target part.

[0073] Specifically, the determination module 103 may determine the rigidity using the following formula:

[0074]

[0075] Where, Indicates rigidity, Indicates the axial load of the spindle during the vibration monitoring period, Indicates the radial load of the spindle during the vibration monitoring period; Indicates the axial displacement of the spindle measured in the axial direction, Indicates the radial displacement of the spindle measured in the radial direction.

[0076] in, This value represents the rigidity (axial and radial rigidity) of the spindle of the target device in the cloud platform system. A larger product indicates stronger rigidity. Stronger rigidity means less deformation of the spindle when subjected to force, which helps maintain machining accuracy and reduce vibration. Deformation of the spindle during operation or insufficient rigidity due to external influences can more easily cause abnormal vibration behavior, leading to abnormal data points in the vibration monitoring data.

[0077] The process of the final determination module 103 determining the vibration deviation is specifically as follows: a hyperbolic tangent function is used to perform a function operation on the product of the rigidity and the parameter variation complexity to obtain the vibration deviation.

[0078] Specifically, the vibration deviation can be calculated using the following formula:

[0079]

[0080] Where, Indicates the vibration deviation, Indicates the rigidity of the target device in the cloud platform system; Indicates the complexity of parameter changes of target devices during the data monitoring period of the cloud platform system. represents the hyperbolic tangent function.

[0081] in, This product represents the vibration deviation of the main shaft vibration of the target device in the cloud platform system. A larger product indicates a greater vibration deviation of the vibration monitoring data in the cloud platform system. This means that the abnormal data points in the vibration monitoring data are more likely to be caused by equipment abnormalities, indicating that there may be less external noise interference (i.e., noise intensity) in the vibration monitoring data. A smaller product indicates a smaller vibration deviation of the vibration monitoring data in the cloud platform system. This means that the abnormal data points in the vibration monitoring data are more likely to be caused by external noise interference, indicating that there may be more external interference in the vibration monitoring data. This is used to adjust and purify anomalies in the vibration monitoring data.

[0082] The determination module 103 is further configured to determine the processing requirement of the vibration monitoring data according to the average abnormality and the vibration deviation.

[0083] The processing requirement indicates the possibility that the abnormal data point in the vibration monitoring data is caused by noise interference, and the processing requirement is proportional to the possibility that the abnormal data point in the vibration monitoring data is caused by noise interference.

[0084] Specifically, in an AI-based industrial design cloud platform system, a large amount of vibration monitoring data needs to be integrated and processed to achieve effective monitoring and management of the cloud platform system. The processing of vibration monitoring data requires effectively removing the interference components in the vibration monitoring data and retaining the real abnormal data caused by the equipment itself in the vibration monitoring data to facilitate subsequent monitoring and prevention. Therefore, the processing demand degree can be used to determine whether the cause of data anomalies in the vibration monitoring data is caused by noise interference. The greater the processing demand degree, the greater the possibility that the abnormal cause of the abnormal data point in the vibration monitoring data is due to noise interference. The smaller the processing demand degree, the less likely the abnormal cause of the abnormal data point in the vibration monitoring data is due to noise interference.

[0085] The process of determining the processing requirement by the determination module 103 is as follows: determining the sum of the square of the average abnormality and the square of the reciprocal of the vibration deviation; performing a square root operation on the sum to obtain a calculation result, and using the calculation result as the processing requirement.

[0086] Furthermore, the calculation formula for processing demand is as follows:

[0087]

[0088] Where, represents the processing demand, W represents the average abnormality of the vibration monitoring data in the cloud platform system, and T represents the vibration deviation of the main shaft vibration of the target equipment in the cloud platform system.

[0089] in, It represents the Euclidean norm of the average abnormality of the vibration monitoring data in the cloud platform system and the vibration deviation of the main shaft vibration of the target device in the cloud platform system. The purpose of the Euclidean norm is to output a comprehensive indicator between the abnormality in the vibration monitoring data and the operating status of the target device. The larger the value of the Euclidean norm, the greater the possibility that the cause of the abnormal data in the vibration monitoring data is external noise interference, that is, there may be a large degree of noise interference in the vibration monitoring data, that is, the higher the processing demand of the vibration monitoring data in the cloud platform system, the more necessary it is to denoise and purify the vibration monitoring data.

[0090] The processing module 104 is configured to perform smoothing processing on the vibration monitoring data based on the processing requirement to remove noise interference in the vibration monitoring data.

[0091] Specifically, after obtaining the processing demand degree, the processing module 104 can perform targeted denoising on the vibration monitoring data according to the value of the processing demand degree. For example, when the processing demand degree is greater than a threshold value, the processing module 104 can determine that the noise interference in the vibration monitoring data needs to be removed. When the processing demand degree is not greater than the threshold value, it indicates that the abnormal data points in the vibration monitoring data are caused by the device itself and need to be retained. The threshold value can be determined according to actual conditions and is not limited in this embodiment of the present application.

[0092] Alternatively, the processing module 104 uses the processing requirement as the standard deviation obeyed by the filter kernel of the Gaussian filter to obtain a target Gaussian filter; and uses the target Gaussian filter to perform smoothing processing on the vibration monitoring data.

[0093] Specifically, the processing requirement of the vibration monitoring data collected in the cloud platform system is calculated as the noise intensity value contained in the vibration monitoring data center. This processing requirement is then used as the standard deviation of the filter kernel of a Gaussian filter. This filter, with the adjusted standard deviation (target Gaussian filter), is then used to smooth the vibration monitoring data collected in the cloud platform system, removing noise interference and generating high-quality monitoring data. Using this noise-free vibration monitoring data can effectively improve industrial safety and production efficiency, leading to more efficient production operations and product design optimization.

[0094] It is worth noting that in the above embodiment, the target device is a CNC machine tool, the target part is a spindle, and the operating parameters are the operating parameters of the spindle. According to actual conditions, the embodiment of the present application can also be applied to any type of target device and the target part corresponding to the target device. The embodiment of the present application does not impose any limitations on the target device and the target part.

[0095] The present invention has the following beneficial effects: an acquisition module acquires vibration monitoring data of a target part of a target device within a monitoring period and operating parameters of the target part of the target device during operation, a decomposition module then performs independent component decomposition on the vibration monitoring data to obtain multiple vibration components and corresponding signal component sequences, a determination module then determines the average abnormality of the vibration monitoring data based on the amplitude of the data points of the signal component sequence of each vibration component and the signal component sequence, and determines the vibration deviation of the vibration monitoring data of the target part based on the operating parameters, the vibration deviation can reflect whether the abnormal data points in the vibration monitoring data are caused by the device, thereby predicting possible failures of the target device during the production process, thereby timely processing and improving production efficiency. Finally, the determination module determines the processing requirement of the vibration monitoring data based on the average abnormality and vibration deviation, the processing requirement can reflect whether the abnormal data points in the vibration monitoring data are caused by noise interference, so that the processing module can smooth the vibration monitoring data based on the processing requirement to remove the noise interference in the vibration monitoring data, thereby improving the accuracy and credibility of the monitoring data, and facilitating the whole process management and optimization of industrial products from concept to production.

[0096] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. An industrial design cloud platform system based on artificial intelligence, characterized by: The artificial intelligence-based industrial design cloud platform system includes: an acquisition module, configured to acquire vibration monitoring data of a target portion of a target device within a monitoring period and operating parameters of the target portion of the target device during operation; a decomposition module, configured to perform independent component decomposition on the vibration monitoring data to obtain a plurality of vibration components and a signal component sequence corresponding to each of the vibration components; a determination module, configured to determine an average abnormality of the vibration monitoring data based on the amplitude of the data point of the signal component sequence of each vibration component and the signal component sequence, wherein the average abnormality indicates the authenticity of the vibration monitoring data and is inversely proportional to the authenticity; The determining module is configured to determine a vibration deviation of the vibration monitoring data of the target part based on the operating parameter, wherein the vibration deviation indicates a possibility that an abnormal data point in the vibration monitoring data is caused by the target device, and the vibration deviation is proportional to the possibility that the abnormal data point in the vibration monitoring data is caused by the target device; The determining module is further configured to determine a processing requirement of the vibration monitoring data based on the average abnormality and the vibration deviation, wherein the processing requirement indicates a probability that an abnormal data point in the vibration monitoring data is caused by noise interference, and the processing requirement is proportional to the probability that the abnormal data point in the vibration monitoring data is caused by noise interference; A processing module is used to perform smoothing processing on the vibration monitoring data based on the processing requirement to remove noise interference in the vibration monitoring data.

2. The artificial intelligence-based industrial design cloud platform system according to claim 1 is characterized in that: The determining module is further configured to: Determining the number of types of data points and the total number of data points of all data points in the signal component sequence of the vibration component, wherein data points with equal values ​​are of the same type; determining a local complexity of the vibration component among all vibration components based on distribution probability values ​​of each type of data point in the signal component sequence of the vibration component, the number of the types, and the total number of the data points, wherein the local complexity indicates the periodicity of the vibration component and is inversely proportional to the periodicity of the vibration component; determining a vibration abnormality degree of each data point in the signal component sequence of the vibration component according to the local complexity and the amplitude of the data point in the signal component sequence, wherein the vibration abnormality degree indicates a possibility that the data point is abnormal, and the vibration abnormality degree is proportional to the possibility that the data point is abnormal; The average abnormality of the vibration monitoring data is determined according to the vibration abnormality of each data point of each vibration component.

3. The artificial intelligence-based industrial design cloud platform system according to claim 2, characterized in that: The determining module is further configured to: determining the absolute value of the difference between the distribution probability values ​​of any two types of data points in the signal component sequence of the vibration component, and obtaining m groups of absolute values ​​of the difference; superimposing the absolute values ​​of the m groups of differences and comparing them with m to obtain a first ratio, wherein the first ratio indicates the number of similar data points present in the vibration monitoring data, the first ratio is inversely proportional to the number of similar data points present in the vibration monitoring data, and m is an integer greater than 0; determining a second ratio between the number of types of the signal component sequence of the vibration component and the total number of data points; A product of the first ratio and the second ratio is determined as the local complexity.

4. The artificial intelligence-based industrial design cloud platform system according to claim 2, characterized in that: The determining module is further configured to: determining an average amplitude of the amplitudes of all data points in the signal component sequence of the vibration component and a first difference between a maximum amplitude and a minimum amplitude of the data points in the signal component sequence; determining an absolute value of a second difference between the amplitude of the data point and the average amplitude, and an absolute value of a third difference between the amplitude of the data point and the first difference; determining a third ratio of the absolute value of the second difference to the absolute value of the third difference; Performing a function operation on the local complexity using a hyperbolic tangent function to obtain an operation result; The product of the third ratio and the operation result is determined, and the product of the third ratio and the operation result is used as the vibration abnormality degree of the data point in the signal component sequence.

5. The artificial intelligence-based industrial design cloud platform system according to any one of claims 1 to 4, characterized in that: The determining module is further configured to: a feed rate of the target portion determined from the operating parameters within the monitoring time period; determining an error between the operating parameter and the vibration monitoring data; determining a parameter variation complexity of the operating parameter based on the error and the feed rate, wherein the parameter variation complexity indicates a likelihood that an abnormal data point in the vibration monitoring data is caused by the operating parameter of the target part, and the parameter variation complexity is proportional to the likelihood that the abnormal data point in the vibration monitoring data is caused by the operating parameter of the target part; determining a load applied to the target portion during the monitoring period and a displacement of the target portion under the load; determining the rigidity of the target portion according to the load and the displacement, wherein the rigidity is inversely proportional to a probability of an abnormality occurring in a data point in the vibration monitoring data; A hyperbolic tangent function is used to perform a functional operation on the product of the stiffness and the parameter variation complexity to obtain the vibration deviation.

6. The artificial intelligence-based industrial design cloud platform system according to claim 5, characterized in that: The determining module is further configured to: Fitting the operating parameters of the target part according to the monitoring time of the vibration monitoring data to obtain a fitting curve; Determine a mean square error between the fitting curve and the vibration monitoring curve of the vibration monitoring data as the error; determining a degree of fluctuation of the feed rate of the target portion during the monitoring period; The parameter variation complexity of the operating parameter is determined according to the mean square error and the fluctuation degree.

7. The artificial intelligence-based industrial design cloud platform system according to claim 6, characterized in that: The determining module is further configured to: The ratio of the fluctuation degree to the mean square error is determined as the parameter variation complexity.

8. The artificial intelligence-based industrial design cloud platform system according to claim 5, characterized in that: The load includes radial load and axial load, the displacement includes axial displacement and radial displacement, and the acquisition module is further used to: Acquiring a radial load and an axial load of the target portion during the monitoring period, and an axial displacement of the target portion in the axial direction and a radial displacement of the target portion in the radial direction; The determining module is further configured to: determining a fourth ratio between the axial load and the axial displacement, and a fifth ratio between the radial load and the radial displacement; The product of the fourth ratio and the fifth ratio is determined as the stiffness of the target part.

9. The artificial intelligence-based industrial design cloud platform system according to claim 1, characterized in that: The determining module is further configured to: determining a sum of the square of the average abnormality and the square of the reciprocal of the vibration deviation; A square root operation is performed on the sum value to obtain an operation result, and the operation result is used as the processing requirement.

10. The artificial intelligence-based industrial design cloud platform system according to claim 1, characterized in that: The processing module is further configured to: The processing requirement is used as the standard deviation of the filter kernel of the Gaussian filter to obtain a target Gaussian filter; The vibration monitoring data is smoothed using the target Gaussian filter.

Images