TW202315726A - Component abnormality monitoring method, electronic equipment, and storage medium - Google Patents

Abstract

The present application provides a component abnormality monitoring method, electronic equipment, and a storage medium. The component abnormality monitoring method includes: acquiring data to be tested of a component; extracting characteristic data from the data to be tested; performing a principal component analysis on the characteristic data to obtain statistics; monitoring whether the component is abnormal according to the statistics and a preset standard value interval. By utilizing this application, the accuracy and efficiency of component abnormality monitoring can be improved.

Description

Abnormality monitoring method of components, electronic equipment and storage medium

The invention relates to the field of data analysis, in particular to an abnormality monitoring method for components, electronic equipment and a storage medium.

At present, due to the invisible running state of the mechanical arm in the production process, when the mechanical arm fails or is about to fail, the relevant personnel cannot find the failure in time, resulting in untimely maintenance of the failure, which seriously affects production efficiency and Production quality.

In view of the above, it is necessary to provide a component abnormality monitoring method, electronic equipment and storage medium, which can improve the accuracy and efficiency of component abnormality monitoring, thereby improving production efficiency.

The present application provides a method for abnormal monitoring of components, the method comprising: obtaining the data to be tested of the components; extracting characteristic data from the data to be tested; performing principal component analysis on the characteristic data to obtain statistics; The statistic and the preset standard value interval monitor whether there is any abnormality in the component.

In a possible implementation manner, the acquiring the data to be tested of the component includes: acquiring the sensor data of the component through a sensor; acquiring the controller data of the component through a controller; Sensor data and the controller data are used as the data to be tested.

In a possible implementation manner, the extracting feature data from the data to be tested includes: extracting vibration data and position error data from the sensor data; extracting current data from the controller data; The vibration data, the position error data and the current data are used as the characteristic data.

In a possible implementation manner, the performing principal component analysis on the feature data to obtain statistics includes: extracting multiple first principal components of the vibration data through a principal component analysis algorithm; The algorithm extracts a plurality of second principal components of the position error data; extracts a plurality of third principal components of the current data through the principal component analysis algorithm; according to the plurality of first principal components, the plurality of The second principal component and the plurality of third principal components are used to calculate the statistics.

In a possible implementation manner, the calculating the statistics according to the multiple first principal components, the multiple second principal components, and the multiple third principal components includes: according to the multiple first principal components A principal component, the plurality of second principal components and the plurality of third principal components are calculated to obtain T2 statistical values; according to the plurality of first principal components, the plurality of second principal components and the plurality of The third principal component is calculated to obtain the SPE statistical value; the T2 statistical value and the SPE statistical value are used as the statistical quantities.

In a possible implementation manner, the monitoring whether there is an abnormality in the component according to the statistical quantity and a preset standard value interval includes: determining the first T2 statistical value and the preset first standard value interval. Monitoring results; determining a second monitoring result according to the SPE statistical value and a preset second standard value interval; monitoring whether the components are abnormal according to the first monitoring result and the second monitoring result.

In a possible implementation manner, the determining the first monitoring result according to the T2 statistical value and the preset first standard value interval includes: judging whether the T2 statistical value is within the preset first standard value interval. value interval; when the T2 statistical value is within the preset first standard value interval, it is determined that the first monitoring result is normal; when the T2 statistical value is not within the preset first standard value interval When it is within the value interval, it is determined that the first monitoring result is abnormal.

In a possible implementation manner, the determining whether the component is abnormal according to the first monitoring result and the second monitoring result includes: when each of the first monitoring result and the second monitoring result When all the monitoring results are normal, it is determined that there is no abnormality in the component; when at least one of the first monitoring result and the second monitoring result is abnormal, it is determined that the component is abnormal.

The present application also provides an electronic device, the electronic device includes a processor and a storage, and the processor is used to realize the abnormality monitoring method of components when executing a computer program stored in the storage.

The present application also provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the above-mentioned abnormality monitoring method for components is implemented.

The component abnormality monitoring method and related equipment disclosed in this application extract the main data affecting the component by extracting the characteristic data from the component to be tested after obtaining the test data of the component. The principal component analysis algorithm performs principal component analysis on the characteristic data to obtain statistics, and can reduce the dimension of the characteristic data to obtain statistics with lower dimensions. Finally, according to the statistics and the preset standard value interval Monitor whether the components are abnormal. Since the statistics are a small amount of data with low dimensions, the abnormal monitoring of components based on statistics reduces the complexity of data calculation, and the reduction of data complexity helps to improve the abnormality. Analysis efficiency. Fast and effective abnormal monitoring of components, so as to detect faulty components in a timely manner and eliminate abnormal components, thereby assisting in improving the production quality of products.

In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

Please refer to FIG. 1 , which is a schematic diagram of an electronic device according to an embodiment of the present application. Referring to FIG. 1 , the electronic device 1 includes, but is not limited to, a storage 11 and at least one processor 12. The above-mentioned components may be connected through a bus bar or directly.

The electronic device 1 may be a computer, a mobile phone, a tablet computer, a personal digital assistant (Personal Digital Assistant, PDA) and other devices installed with application programs. Those skilled in the art can understand that the schematic diagram 1 is only an example of the electronic device 1, and does not constitute a limitation to the electronic device 1, and may include more or less components than those shown in the figure, or combine certain components, or be different For example, the electronic device 1 may also include input and output devices, network access devices, bus bars (for example, 13 shown in FIG. 1 ), and the like.

As shown in FIG. 2 , it is a flow chart of a preferred embodiment of the abnormality monitoring method for components of the present application. The abnormality monitoring method of components is applied in the electronic equipment 1 . According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted. In this embodiment, the abnormality monitoring method of the components includes:

S21. Obtain the data to be tested of the components.

In an embodiment of the present application, the component may be a robot arm (Universal Robots, UR). The UR robot arm is mainly used in the production workshop, and can be used for assembly, painting, screwing, labeling, injection molding and welding. The UR robotic arm has the characteristics of simple program design, flexible deployment, quick installation and high safety. The obtaining the data to be tested of the components may include: obtaining the sensor data of the UR mechanical arm through the sensor; obtaining the controller data of the UR mechanical arm through the controller; combining the sensor data and The data of the controller is used as the data to be tested.

During specific implementation,

(1) In view of the characteristics of high hardness of the UR robot arm and the difficulty of slotting, the ultrasonic sensor is installed on the shaft joint motor and the clamp mechanism of the UR robot arm by pasting. Real-time acquisition of sensor data of the UR robotic arm through the ultrasonic sensor, for example, the movement speed of the UR robotic arm, the angle of the UR robotic arm, and the distance between the UR robotic arm and the target point . The ultrasonic sensor sends the sensor data to the data acquisition card, and the data acquisition card divides the sensor data, and through data segmentation, irregular data and redundant data can be removed to obtain Useful information. Furthermore, the data acquisition card sends the divided sensor data to the electronic device. It should be noted that the UR robotic arm is composed of multiple single axes, so the data of each single axis can be collected separately, and the following embodiments can be the data processing and analysis for each single axis.

(2) Obtain the controller information of the UR robotic arm through the controller that comes with the UR robotic arm, wherein the controller refers to changing the wiring of the main circuit or control circuit and changing the resistance value in the circuit according to a predetermined sequence To control the starting, speed regulation, braking and reverse of the motor, the controller data includes various current data, such as resistance value and current direction. The controller sends the controller data to a data acquisition card, and the data acquisition card divides the controller data. Furthermore, the data acquisition card sends the divided controller data to the electronic device.

In one embodiment of the present application, compared with traditional strain sensors, the ultrasonic sensor has the advantages of small size, fast response, wide measurement frequency range, high linearity, and no need for external power supply. By collecting the sensor data and the controller data, the accuracy and extensiveness of the data are improved, and subsequent data analysis can be made more accurate.

S22. Extract feature data from the data to be tested.

In practical applications, the sensor data and the controller data often contain a large number of redundant data types. Therefore, in order to improve the efficiency and accuracy of subsequent data analysis, it is necessary to extract Representative data.

In an embodiment of the present application, the representative data include: vibration data, position error data and current data. The extracting characteristic data from the data to be tested includes: extracting the vibration data and the position error data from the sensor data; extracting the current data from the controller data; data, the position error data and the current data are used as the characteristic data.

During specific implementation, three types of sample data are obtained, and the three types of sample data are respectively vibration data samples, position error data samples and current data samples. sequentially extracting first data from the sensor data, calculating a plurality of first distances between the first data and each of the vibration data samples and each of the position error data samples multiple second distances, take a first average value for the multiple first distances, use the first data whose first average value is less than the preset first average value threshold as the vibration data, and take the first average value for the multiple second distances A second average value is taken for the distance, and the first data whose second average value is smaller than a preset second average threshold value is used as the position error data until all the first data in the sensor data are extracted. Next, sequentially extract second data from the controller data, calculate multiple third distances between the second data and each data in the current data sample, and average the multiple third distances , taking the third data whose average value is smaller than the preset third average threshold value as the current data, until all the third data in the controller data are extracted.

By extracting the characteristic data in the data to be tested, the main data affecting the UR robotic arm are extracted, which can improve the efficiency and accuracy of subsequent data analysis.

S23. Perform principal component analysis on the feature data to obtain statistics.

In one embodiment of the present application, the calculation of the statistics of the characteristic data through a principal component analysis algorithm includes: extracting a plurality of first principal components of the vibration data through a principal component analysis algorithm; The algorithm extracts a plurality of second principal components of the position error data; extracts a plurality of third principal components of the current data through a principal component analysis algorithm; according to the plurality of first principal components, the plurality of first principal components, Two principal components and the plurality of third principal components compute the statistic.

The calculating the statistics according to the multiple first principal components, the multiple second principal components and the multiple third principal components includes: according to the multiple first principal components, the multiple The second principal component and the plurality of third principal components are calculated to obtain T2 statistical values; according to the plurality of first principal components, the plurality of second principal components and the plurality of third principal components are calculated to obtain SPE statistics value; the T2 statistical value and the SPE statistical value are used as the statistical quantities.

During specific implementation, standardization processing is performed on the vibration data to obtain the first normalization data. performing dimensionality reduction on the first standardized data through the principal component analysis (PCA) algorithm to obtain several first principal components, and calculate the first covariance matrix of the first standardized data, and then calculate The first eigenvalue and the first eigenvector of the first covariance matrix, obtaining the contribution rate of each of the first eigenvalues, and using the first principal component whose contribution rate is greater than the preset first threshold as the multiple first principal components. Standardize the position error data to obtain second normalized data. Using the PCA algorithm to reduce the dimension of the second standardized data to obtain a number of second principal components, calculate the second covariance matrix of the second standardized data, and then calculate the second covariance matrix of the second covariance matrix Two eigenvalues and second eigenvectors, obtaining the contribution rate of each of the second eigenvalues, and using the second principal components whose contribution rates are greater than a preset second threshold as the plurality of first principal components. Standardize the current data to obtain third normalized data. Using the PCA algorithm to reduce the dimension of the third standardized data to obtain a number of third principal components, calculate the third covariance matrix of the third normalized data, and then calculate the third covariance matrix of the third covariance matrix Three eigenvalues and a third eigenvector, obtaining the contribution rate of each of the third eigenvalues, and using the third principal components whose contribution rates are greater than a preset third threshold as the plurality of third principal components. Furthermore, the plurality of first principal components, the plurality of second principal components and the plurality of third principal components may be input into the PCA algorithm model, and the T2 statistical value and the SPE statistical value may be output.

By using the principal component analysis algorithm to reduce a large amount of data into a small amount of data, the complexity of the data is reduced, and the efficiency of abnormal data analysis can be improved.

S24. Monitor whether the components are abnormal according to the statistics and a preset standard value interval.

When the UR robotic arm is normal, the load will be in the range of 5 kg to 9 kg, that is, when the UR mechanical arm is normal, the statistic will be in a standard value range. The standard value interval can be obtained by collecting data on a normal weight-bearing interval.

In an embodiment of the present application, the first normal data of the UR robotic arm with a load of 5 kg is obtained, and the first T2 standard value and the first SPE standard value of the first normal data are obtained by using the principal component analysis model. Next, obtain the second normal data of the UR robotic arm with a load of 9 kg, and use the principal component analysis model to obtain the second T2 standard value and the second SPE standard value of the second normal data. Determine the preset first standard value interval according to the first T2 standard value and the second T2 standard value, for example, the first T2 standard value is 300, and the second T2 standard value is 700, so it is determined The preset first standard value interval is (300, 700). Determine the preset second standard value interval according to the first SPE standard value and the second SPE standard value, for example, the first SPE standard value is 40, and the second SPE standard value is 90, so it is determined The preset second standard value interval is (40, 90).

In one embodiment of the present application, the determining whether there is an abnormality in the component according to the statistic and the preset standard value interval includes: determining the second T2 statistic value and the preset first standard value interval A monitoring result; determining a second monitoring result according to the SPE statistical value and a preset second standard value interval; monitoring whether the components are abnormal according to the first monitoring result and the second monitoring result.

In an embodiment of the present application, the determining the first monitoring result according to the T2 statistical value and the preset first standard value interval includes: judging whether the T2 statistical value is within the preset first standard value interval; when the T2 statistical value is within the preset first standard value interval, it is determined that the first monitoring result is normal; when the T2 statistical value is not within the preset first standard value interval , determining that the first monitoring result is abnormal.

In one embodiment of the present application, the determining the second monitoring result according to the SPE statistical value and the preset second standard value range includes: when the SPE statistical value is within the preset second standard value range When the second monitoring result is determined to be normal; when the SPE statistical value is not within the preset second standard value range, it is determined that the second monitoring result is abnormal.

In one embodiment of the present application, determining whether the component is abnormal according to the first monitoring result and the second monitoring result includes: when each of the first monitoring result and the second monitoring result When the monitoring results are all normal, it is determined that there is no abnormality in the component; when at least one of the first monitoring result and the second monitoring result is abnormal, it is determined that the component is abnormal. Specifically, when the first monitoring result is abnormal and the second monitoring result is normal, it is determined that the UR robotic arm is abnormal; when the first monitoring result is normal and the second When the second monitoring result is abnormal, it is determined that the UR robotic arm is abnormal, and when the first monitoring result is abnormal and the second monitoring result is abnormal, it is determined that the UR robotic arm is abnormal.

By monitoring the data of the UR robot arm in real time and analyzing the data, early warnings can be given to the abnormal situation of the UR robot arm, and solutions can be taken in time to reduce troubles and improve the production efficiency of the workshop. By adopting this method, the state of the UR mechanical arm can be monitored for a long time.

As an optional implementation manner, the method further includes: drawing a statistical quantity trend graph according to the statistical quantity and corresponding time points.

In an embodiment of the present application, by drawing the trend graph of the statistics, the state of the UR robot arm can be predicted, so that problems can be found in time.

Please continue to refer to FIG. 1 , in this embodiment, the storage 11 may be an internal storage of the electronic device 1 , that is, a storage built in the electronic device 1 . In other embodiments, the storage 11 may also be an external storage of the electronic device 1 , that is, a storage connected externally to the electronic device 1 .

In some embodiments, the storage 11 is used to store program codes and various data, and realize high-speed and automatic access to programs or data during the operation of the electronic device 1 .

The storage 11 may include a random access memory, and may also include a non-volatile storage, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital ( Secure Digital (SD) card, flash memory card (Flash Card), at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.

In one embodiment, the processor 12 may be a central processing unit (Central Processing Unit, CPU), and may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may be any other conventional processor and the like.

If the program codes and various data in the storage 11 are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the methods of the above-mentioned embodiments, such as the abnormality monitoring method of components, which can also be completed by instructing related hardware through computer programs, and the computer programs can be stored in a In the computer-readable storage medium, when the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be realized. Wherein, the computer program includes computer program code, and the computer program code may be in the form of original code, object code, executable document or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a flash drive, a removable hard disk, a magnetic disk, an optical disk, a computer storage, a read-only memory (ROM, Read- Only Memory), etc.

It can be understood that the module division described above is a logical function division, and there may be another division method in actual implementation. In addition, each functional module in each embodiment of the present application may be integrated into the same processing unit, or each module may exist separately physically, or two or more modules may be integrated into the same unit. The above-mentioned integrated modules can be implemented in the form of hardware, or in the form of hardware plus software function modules.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application without limitation. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be Make modifications or equivalent replacements without departing from the spirit and scope of the technical solutions of the present application.

1: Electronic equipment 11: Storage 12: Processor 13: busbar S21~S24: Steps

In order to more clearly illustrate the technical solutions in the embodiments of the present application or in the prior art, the accompanying drawings that need to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings in the following description are only It is an embodiment of the present application, and those skilled in the art can also obtain other drawings according to the provided drawings without creative work.

FIG. 1 is a schematic structural diagram of an electronic device according to an abnormality monitoring method for components provided by an embodiment of the present application.

Fig. 2 is a flow chart of a method for monitoring abnormalities of components provided by an embodiment of the present application.

S21~S24: Steps

Claims (10)

A component abnormality monitoring method applied to electronic equipment, wherein the method includes: Obtain the test data of components; extracting feature data from the data to be tested; Performing principal component analysis on the characteristic data to obtain statistics; Whether there is any abnormality in the components is monitored according to the statistics and the preset standard value interval. The abnormality monitoring method of components as described in claim item 1, wherein said obtaining the data to be tested of components includes: Obtaining sensor data of the component through the sensor; Obtaining the controller data of the component through the controller; The sensor data and the controller data are used as the data to be tested. The abnormality monitoring method of components as described in claim item 2, wherein said extracting characteristic data from said data to be tested includes: extracting vibration data and position error data from the sensor data; extracting current data from said controller data; The vibration data, the position error data and the current data are used as the feature data. The abnormality monitoring method for components and parts as described in claim item 3, wherein, performing principal component analysis on the characteristic data to obtain statistics includes: extracting a plurality of first principal components of the vibration data through a principal component analysis algorithm; extracting a plurality of second principal components of the position error data through the principal component analysis algorithm; extracting a plurality of third principal components of the current data through the principal component analysis algorithm; The statistic is calculated based on the plurality of first principal components, the plurality of second principal components, and the plurality of third principal components. The abnormality monitoring method of components as claimed in claim 4, wherein the calculation of the statistics is based on the plurality of first principal components, the plurality of second principal components and the plurality of third principal components include: Calculate T2 statistics according to the plurality of first principal components, the plurality of second principal components and the plurality of third principal components; SPE statistical values are calculated according to the plurality of first principal components, the plurality of second principal components, and the plurality of third principal components; The T2 statistical value and the SPE statistical value are used as the statistical quantities. The abnormality monitoring method of components as described in claim item 5, wherein the monitoring whether there is an abnormality in the components according to the statistics and the preset standard value interval includes: determining a first monitoring result according to the T2 statistical value and the preset first standard value interval; determining a second monitoring result according to the SPE statistical value and a preset second standard value interval; Monitoring whether the components are abnormal according to the first monitoring result and the second monitoring result. The abnormality monitoring method for components as described in claim 6, wherein said determining the first monitoring result according to the T2 statistical value and the preset first standard value interval includes: judging whether the T2 statistical value is within the preset first standard value interval; When the T2 statistical value is within the preset first standard value interval, it is determined that the first monitoring result is normal; When the T2 statistical value is not within the preset first standard value range, it is determined that the first monitoring result is abnormal. The abnormality monitoring method of components as claimed in item 7, wherein the determining whether the components are abnormal according to the first monitoring result and the second monitoring result includes: When each of the first monitoring result and the second monitoring result is normal, it is determined that there is no abnormality in the component; When at least one of the first monitoring result and the second monitoring result is abnormal, it is determined that the component is abnormal. An electronic device, wherein the electronic device includes a processor and a memory, and the processor is used to execute a computer program stored in the memory to realize the components described in any one of claim 1 to claim 8 Exception detection method. A computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the component device described in any one of claim 1 to claim 8 is realized abnormality monitoring method.

Images