Welding robot working condition identification method

Abstract

The embodiment of the invention provides a welding robot working condition recognition method and device, computer equipment and a storage medium. The method comprises the steps that operation state data of the welding robot in the operation process are obtained; wherein the running state data comprises a plurality of state data samples arranged according to a time sequence; based on the operation state data, a working condition recognition threshold value of the welding robot and process recognition data corresponding to the multiple state data samples are obtained; wherein the working condition identification threshold value is used for limiting the normal change range of the operation state data, and the process identification data is used for reflecting the change trend of the operation state data in the time range of a state data sample corresponding to the process identification data; and according to the relation between the process identification data and the working condition identification threshold value, the working condition in the operation process of the welding robot is identified. The working condition of the welding robot is identified by judging whether data changes of the welding robot in different time periods exceed a normal range or not.

Description

Technical Field

[0001] The present application relates to the field of intelligent industrial robots, and specifically to a welding robot working condition identification method, device, computer equipment and storage medium. Background Art

[0002] With the continuous advancement of automation, networking, digitization, and intelligentization in automotive welding production lines, welding robots are playing an increasingly important role in automotive manufacturing. Over extended periods of operation, welding robots inevitably experience component aging and performance degradation. These issues can lead to unstable welding quality, reduced welding efficiency, and even production accidents. To address these issues, it is necessary to identify the operating conditions of welding robots during operation and implement appropriate countermeasures based on the specific conditions.

[0003] In existing technology, the identification of welding robot working conditions mainly relies on manual experience. When the operating time of the welding robot reducer reaches a certain empirical value, the reducer is replaced. However, relying solely on manual experience cannot accurately identify the working conditions of the welding robot during operation. Summary of the Invention

[0004] In view of this, multiple embodiments of the present application are dedicated to providing a welding robot working condition identification method, which can improve the accuracy of welding robot working condition identification to a certain extent.

[0005] In a first aspect, an embodiment of the present application provides a method for identifying a working condition of a welding robot, comprising:

[0006] Acquire the operating status data of the welding robot during operation; wherein the operating status data includes multiple status data samples arranged in chronological order; based on the operating status data, derive the working condition recognition threshold of the welding robot and the process recognition data corresponding to the multiple status data samples; wherein the working condition recognition threshold is used to limit the normal variation range of the operating status data, and the process recognition data is used to reflect the variation trend of the operating status data within the time range of the status data samples corresponding to the process recognition data; according to the relationship between the process recognition data and the working condition recognition threshold, identify the working condition of the welding robot during operation.

[0007] Optionally, the state data sample includes multiple sample points arranged in chronological order, and the number of sample points in the state data sample is the same; wherein, any two state data samples adjacent in chronological order include multiple common sample points, and the number of common sample points is the same.

[0008] Optionally, the welding robot working condition includes a stable working condition and an unstable working condition. Among all the sample points included in the operating status data, some sample points corresponding to the unstable working condition precede some sample points corresponding to the stable working condition in chronological order.

[0009] Optionally, each of the sample points includes variable values ​​of multiple state variables, and each of the multiple state variables corresponds to multiple variable features. The method of obtaining the working condition recognition threshold of the welding robot and the process identification data corresponding to the multiple state data samples based on the operating state data includes: extracting the variable features corresponding to the state variables of the sample points in the state data samples based on the variable values ​​of the state variables corresponding to the sample points in the state data samples to obtain a variable feature space; the variable feature space includes multiple variable feature samples, and the variable feature samples form a corresponding relationship with the state data samples.

[0010] Optionally, the process identification data includes normal identification data and abnormal identification data. The working condition identification threshold of the welding robot and the process identification data corresponding to the multiple status data samples are obtained based on the operating status data. It also includes: performing conversion calculations on the variable feature space to obtain normal identification data and abnormal identification data of the status data samples corresponding to the multiple variable feature samples in the variable feature space.

[0011] Optionally, the working condition identification threshold includes a normal identification threshold and an abnormal identification threshold. The working condition identification threshold of the welding robot and the process identification data corresponding to the multiple status data samples are obtained based on the operating status data. It also includes: performing statistical calculations on the normal identification data and abnormal identification data corresponding to the multiple status data samples in the operating status data to obtain the normal identification threshold and abnormal identification threshold of the welding robot.

[0012] Optionally, the working condition of the welding robot during operation is identified based on the relationship between the process identification data and the working condition identification threshold, including: if the normal identification data corresponding to the state data sample is less than the normal identification threshold, and the abnormal identification threshold corresponding to the state data sample is less than the abnormal identification threshold, the working condition of the welding robot operating within the time range of the state data sample is identified as a stable working condition.

[0013] Optionally, the identifying of the working condition of the welding robot during operation based on the relationship between the process identification data and the working condition identification threshold also includes: if the normal identification data corresponding to the state data sample is greater than or equal to the normal identification threshold, or the abnormal identification threshold corresponding to the state data sample is greater than or equal to the abnormal identification threshold, the working condition of the welding robot operating within the time range of the state data sample is identified as an unstable working condition.

[0014] In the second aspect, an embodiment of the present application also provides a welding robot working condition identification device, including: an acquisition module for acquiring operating status data of the welding robot during operation; wherein the operating status data includes multiple status data samples arranged in chronological order; an analysis module for deriving the working condition identification threshold of the welding robot and the process identification data corresponding to the multiple status data samples based on the operating status data; wherein the working condition identification threshold is used to limit the normal variation range of the operating status data, and the process identification data is used to reflect the variation trend of the operating status data within the time range of the status data samples corresponding to the process identification data; an identification module for identifying the working condition of the welding robot during operation based on the relationship between the process identification data and the working condition identification threshold.

[0015] In a third aspect, an embodiment of the present application further provides an electronic device, comprising a memory and a processor, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor to implement the welding robot working condition identification method as described above.

[0016] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one computer program, and when the at least one computer program is executed by a processor, it can implement the aforementioned welding robot working condition identification method.

[0017] In multiple embodiments provided in the present application, by obtaining the operating status data of the welding robot during operation, process identification data reflecting the changing trend of the operating status data within different time ranges during the operation of the welding robot is obtained based on the operating status data, as well as a working condition identification threshold for limiting the normal changing range of the operating status data, and according to the relationship between the process identification data and the working condition identification threshold within different time ranges during the operation of the welding robot, the working condition of the welding robot within the corresponding time range is identified. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flowchart of a welding robot working condition identification method provided in one embodiment of the present application.

[0019] Figure 2 A schematic diagram of a module of a welding robot working condition identification device provided in one embodiment of the present application.

[0020] Figure 3 A schematic diagram of an electronic device provided in accordance with one embodiment of the present application. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0022] See also Figure 1 . An embodiment of the present application provides a method for identifying the working condition of a welding robot. The CNC machine tool control method can be applied to a welding robot working condition identification device. The welding robot working condition identification device can be an electronic device with certain computing capabilities. The electronic device can have a controller and a memory, etc. Of course, in some embodiments, the welding robot working condition identification device can also refer to a program module running in an electronic device. The welding robot working condition identification method can include the following steps.

[0023] Step S110: Acquire the operation status data of the welding robot during operation; wherein the operation status data includes a plurality of status data samples arranged in chronological order.

[0024] Step S120: Based on the operating status data, the working condition identification threshold of the welding robot and the process identification data corresponding to the multiple status data samples are obtained; wherein, the working condition identification threshold is used to limit the normal variation range of the operating status data, and the process identification data is used to reflect the variation trend of the operating status data within the time range of the status data samples corresponding to the process identification data.

[0025] Step S130: Identifying the working condition of the welding robot during operation according to the relationship between the process identification data and the working condition identification threshold.

[0026] In this embodiment, the welding robot may be a device used to perform welding processing on a workpiece or mold to be processed in an automobile welding production line, such as a six-axis welding robot. When performing welding processing on a workpiece or mold to be processed, the welding robot can usually perform welding according to a beat rule. Specifically, for example, the welding robot can start welding at the beginning of a single beat and stop welding at the end of the single beat. When the welding robot performs welding processing according to the beat rule, a large amount of beat data can be generated. For example, for a six-axis welding robot, the beat data may include the unique code of the six-axis welding robot, the unique code of the vehicle model corresponding to the automobile workpiece welded by the six-axis welding robot, and the motor current, motor temperature, torque and other data of different axes of the six-axis welding robot corresponding to different moments of multiple beats.

[0027] The welding robot's operating condition can be used to describe whether the welding robot's operating status is normal during operation. In some embodiments, for example, the welding robot's operating condition can be divided into a stable operating condition and an unstable operating condition. The stable operating condition of the welding robot can be used to describe the welding robot in a normal operating state, while the unstable operating condition of the welding robot can be used to describe the welding robot in an abnormal operating state. The welding robot's reducer plays an important role in the operation of the welding robot. For example, the welding robot's reducer can adjust the speed of the welding robot's motor, thereby controlling the welding speed of the welding robot to meet the actual needs of different working scenarios. After a certain period of operation, the welding robot's reducer may experience problems such as component aging and performance degradation, which in turn affects the overall performance of the welding robot. Therefore, the welding robot's reducer generally needs to be replaced and maintained after a certain period of operation. When the welding robot's reducer is replaced and maintained, maintenance data for the welding robot's reducer can be generated. For example, for a six-axis welding robot, each of the six axes of the six-axis welding robot includes a reducer, and the reducer maintenance data may include the reducer unique code corresponding to the reducer of each axis of the six-axis welding robot, the axis number, the time before replacement and maintenance, the time after replacement and maintenance, and other data.

[0028] As the level of intelligence in automobile welding production lines becomes higher and higher, a large amount of beat data and reducer maintenance data of welding robots have been collected and stored. For example, the beat data of the welding robot during operation can be collected through various intelligent sensors, and the reducer maintenance data of the welding robot can be collected through the maintenance log of the welding robot and stored in the industrial Internet of Things big data platform. The welding robot working condition identification device can obtain the beat data generated by a welding robot when welding workpieces of different models of cars and the reducer maintenance data of the welding robot from the industrial Internet of Things big data platform. In some embodiments, for example, for a six-axis welding robot, the welding robot working condition identification device can obtain the beat data generated by welding workpieces of different models of cars for a period of time before and after the replacement and maintenance of any one of the reducers of the six axes of the six-axis welding robot based on the reducer maintenance data of the six axes of the six-axis welding robot. Specifically, for example, the time for replacement and maintenance of one of the reducers of the six-axis welding robot is January 28, 2025. The period before replacement and maintenance can be 20 days before the corresponding time of 8:00 a.m. on January 28, 2025, and the period after replacement and maintenance can be 10 days after the corresponding time of 8:00 a.m. on January 29, 2025.

[0029] The welding robot operating condition identification device can mark the tact data for a period of time before any of the reducers on the six axes of the six-axis welding robot are replaced and maintained as an unstable operating condition, and mark the tact data for a period of time after any of the reducers on the six axes of the six-axis welding robot are replaced and maintained as a stable operating condition. The welding robot operating condition identification device can sort the tact data for the period of time before the replacement and maintenance and the tact data for the period of time after the replacement and maintenance in chronological order, and then extract the tact data of the welding robot welding different types of automotive workpieces based on the vehicle model unique codes of different vehicle models contained in the tact data. The tact data of each different vehicle model in the tact data of the welding robot welding different types of automotive workpieces are also sorted in chronological order to obtain the operating status data of the welding robot when welding different types of automotive workpieces. In some embodiments, for a six-axis welding robot, the operating status data may include the welding robot unique code, the vehicle model unique code, a timestamp, whether the tact start time, a working condition mark, and the motor current, motor temperature, and torque of each axis of the six-axis welding robot.

[0030] After obtaining the operating status data of a welding robot welding a workpiece of a certain vehicle model, the welding robot operating condition identification device can divide the operating status data into multiple status data samples in chronological order. The status data samples can be used to describe the operating status of the welding robot within the time period corresponding to the status data samples. Based on the multiple status data samples, the welding robot operating condition identification device can derive process identification data corresponding to each status data sample. The process identification data can be used to reflect the changing trend of the operating status data within the time range of the status data sample corresponding to the process identification data. Based on the process identification data corresponding to the multiple status data samples, the welding robot operating condition identification device can derive a working condition identification threshold for the welding robot through statistical calculation. The working condition identification threshold can be used to define the normal variation range of the operating status data. Finally, the welding robot operating condition identification device can identify the operating condition of the welding robot within the time range of the status data sample by comparing the process identification data corresponding to each status data sample with the working condition identification threshold.

[0031] In multiple embodiments provided in the present application, by obtaining the operating status data of the welding robot during operation, process identification data reflecting the changing trend of the operating status data within different time ranges during the operation of the welding robot is obtained based on the operating status data, as well as a working condition identification threshold for limiting the normal changing range of the operating status data, and according to the relationship between the process identification data and the working condition identification threshold within different time ranges during the operation of the welding robot, the working condition of the welding robot within the corresponding time range is identified.

[0032] In some embodiments, the state data sample includes multiple sample points arranged in chronological order, and the number of sample points in the state data sample is the same; wherein, any two state data samples adjacent in chronological order include multiple common sample points, and the number of the common sample points is the same.

[0033] In this embodiment, the sample points in each state data sample in the operating state data are arranged in chronological order, and each sample point in the multiple sample points may include the operating state data of the welding robot at the time corresponding to the sample point. Specifically, for example, for a six-axis welding robot, one of the multiple sample points may include a welding robot unique code, a vehicle model unique code, a timestamp, whether it is the beat start time, a working condition mark, 1-axis motor current, 2-axis motor current, 3-axis motor current, 4-axis motor current, 5-axis motor current, 6-axis motor current, 1-axis motor temperature, 2-axis motor temperature, 3-axis motor temperature, 4-axis motor temperature, 5-axis motor temperature, 6-axis motor temperature, 1-axis torque, 2-axis torque, 3-axis torque, 4-axis torque, 5-axis torque, 6-axis torque. Any two state data samples adjacent in the chronological order may include multiple shared sample points, and the number of shared sample points is the same. In some embodiments, for example, the number of sample points in each status data sample in the operating status data may be 1000, and for any two status data samples that are adjacent in time sequence in the operating status data, the number of common sample points may be 999.

[0034] When the welding robot operating condition identification device divides the operating status data into multiple status data samples, the device sets the number of sample points in each status data sample to be the same, thereby better capturing the changing trends of the data in each status data sample. Furthermore, when the welding robot operating condition identification device divides the operating status data into multiple status data samples, the device sets the number of sample points shared by any two chronologically adjacent status data samples to be the same. This allows the device to continuously update the sample points in the status data samples in a real-time data environment, thereby capturing the latest changes in the operating status data.

[0035] This embodiment can better capture the change trend of data in each status data sample by setting the number of sample points in each status data sample to be the same when the operating status data is divided into multiple status data samples.

[0036] In some embodiments, the welding robot working condition includes a stable working condition and an unstable working condition. Among all the sample points included in the operating status data, some sample points corresponding to the unstable working condition precede some sample points corresponding to the stable working condition in chronological order.

[0037] In this embodiment, all the sample points included in the operating status data include sample points corresponding to the operating status data for a period of time before and after the replacement and maintenance of the welding robot reducer. The earlier sample points in the time sequence may be sample points for a period of time before the replacement and maintenance of the welding robot reducer, and the remaining sample points may be sample points for a period of time after the replacement and maintenance of the welding robot reducer. By marking the working condition corresponding to the operating status data before replacement and maintenance as an unstable working condition, and marking the working condition corresponding to the operating status data after replacement and maintenance as a stable working condition, the welding robot working condition identification device can make the operating status data more consistent with the working condition change law of the welding robot during actual operation, thereby improving the accuracy of identifying the welding robot working condition.

[0038] This embodiment marks the operating status data of the welding robot reducer before and after replacement and maintenance, making the operating status data more consistent with the operating condition change law of the welding robot during actual operation, thereby improving the accuracy of the welding robot's working condition identification.

[0039] In some embodiments, each of the sample points includes variable values ​​of multiple state variables, each of the multiple state variables corresponds to multiple variable features, and the working condition recognition threshold of the welding robot and the process identification data corresponding to the multiple state data samples are obtained based on the operating state data, including: based on the variable values ​​of the state variables corresponding to the sample points in the state data samples, the variable features corresponding to the state variables of the sample points in the state data samples are extracted to obtain a variable feature space; the variable feature space includes multiple variable feature samples, and the variable feature samples form a corresponding relationship with the state data samples.

[0040] In this embodiment, the state variables can be used to describe the operating state of the welding robot at the time corresponding to the sample point where the state variables are located. In some embodiments, for example, for a six-axis welding robot, the state variables may include 1-axis motor current, 2-axis motor current, 3-axis motor current, 4-axis motor current, 5-axis motor current, 6-axis motor current, 1-axis motor temperature, 2-axis motor temperature, 3-axis motor temperature, 4-axis motor temperature, 5-axis motor temperature, 6-axis motor temperature, 1-axis torque, 2-axis torque, 3-axis torque, 4-axis torque, 5-axis torque, and 6-axis torque, for a total of 18 different state variables. Specifically, for the six-axis welding robot, each sample point may include the variable values ​​of the above multiple state variables at the time corresponding to each sample point. Each of the multiple state variables corresponds to multiple variable characteristics. Specifically, for example, the multiple variable characteristics may include time domain characteristics for describing the time domain characteristics of the state variable, such as mean value, standard deviation, minimum value, first quartile, second quartile, third quartile, maximum value, skewness, kurtosis, range, waveform factor, peak factor, pulse factor, and margin factor, a total of 14 different time domain characteristics, and frequency domain characteristics for describing the frequency domain characteristics of the state variable, such as center of gravity frequency, average frequency, frequency standard deviation, and root mean square standard deviation, a total of 4 different frequency domain characteristics.

[0041] A welding robot operating condition identification device obtains operating state data of a welding robot welding a certain vehicle model workpiece and, after chronologically dividing the operating state data into multiple state data samples, can extract variable features corresponding to the state variables at the sample points in the state data samples based on the variable values ​​of the state variables corresponding to the sample points in the state data samples, thereby obtaining a variable feature space. In some embodiments, for example, for a six-axis welding robot, the state variables at the sample points may include 18 different state variables, each of which may include 18 different variable features. Therefore, the variable features corresponding to the state variables at the sample points in the state data samples may include 324 different variable features, such as the average value of the motor current on axis 1, the average frequency of the motor temperature on axis 2, etc. Specifically, for example, the number of sample points in the state data sample may be 1000, and the average value of the motor current on axis 1 of the state data sample may be the average value of the motor current on axis 1 at each of the 1000 sample points in the state data sample.

[0042] The variable feature space may include multiple variable feature samples. Specifically, for multiple state data samples in the operating state data, each state data sample in the multiple state data samples may include multiple variable features corresponding to the state variables of the sample points in the state data samples, and the multiple variable features may constitute a variable feature sample in the variable feature space. In some embodiments, for example, for a six-axis welding robot, a variable feature sample in the variable feature space may be composed of multiple variable features corresponding to the state variables of the sample points in the state data samples corresponding to the variable feature samples, and the variable feature sample may include 324 different variable features corresponding to the state data samples. The variable feature space is a high-dimensional space. In the variable feature space, the size of the eigenvalues ​​of different variable features can reflect the importance of the variable features. The welding robot working condition recognition device can select more important variable features through subsequent transformation calculations, such as eigendecomposition, and the most valuable variable features can be retained by selecting the eigenvectors corresponding to the largest eigenvalues.

[0043] This embodiment obtains a variable feature space by extracting the variable features corresponding to the state variables of the sample points in the state data sample. It can reflect the importance of the variable features through the size of the feature values ​​of different variable features, and provides necessary conditions for subsequent conversion calculations of the variable feature space.

[0044] In some embodiments, the process identification data includes normal identification data and abnormal identification data. The process identification data corresponding to the working condition identification threshold of the welding robot and the multiple state data samples are obtained based on the operating state data. It also includes: performing conversion calculations on the variable feature space to obtain normal identification data and abnormal identification data of the state data samples corresponding to the multiple variable feature samples in the variable feature space.

[0045] In this embodiment, after the welding robot working condition recognition device obtains the variable feature space, it can perform a conversion calculation on the variable feature space to obtain normal recognition data and abnormal recognition data of the state data samples corresponding to multiple variable feature samples in the variable feature space. Specifically, the welding robot working condition recognition device can use a conversion function to convert the variable feature space. For example, the conversion function can be a Gaussian radial basis function K. For any two variable feature samples x and y in the variable feature space, the calculation of the function matrix of the Gaussian radial basis function K is based on the formula:

[0046]

[0047] Wherein, σ is the parameter of the Gaussian radial basis function, and ‖x―y‖ is the Euclidean distance between the variable feature samples x and y. Then, the welding robot working condition recognition device can perform centralization processing on the Gaussian radial basis function matrix to obtain the matrix K after centralization processing. c , the matrix K c The calculation is based on the formula:

[0048] K c =K-I l K-KI l +I l KI l

[0049] Among them, I l is an l×l matrix, I l All elements in Wherein l is the number of variable features included in the variable feature sample. In some embodiments, for example, for the aforementioned six-axis welding robot, l can be 324.

[0050] Then, the welding robot working condition identification device can identify the matrix K c Perform eigendecomposition and obtain eigenvectors α1, α2, …, α l and the corresponding eigenvalues ​​λ1, λ2, …, λ l , where λ1≥λ2≥…≥λ l The welding robot working condition identification device can be used to identify the cumulative variance contribution rate. The first pe eigenvectors are retained, where pe≤l, and the principal component te of the variable feature space is obtained. The principal component te of the variable feature space can be calculated based on the formula:

[0051] te=ZT·α

[0052] Where ZT is the matrix obtained after the variable feature space is standardized, α is the matrix composed of the first pe eigenvectors α=[α1,α2,…,α pe ],te=[te1,te2…,te pe ].

[0053] The calculation of the normal recognition data H of the state data sample can be based on the formula:

[0054] H=teΛ ―1 te T

[0055] Among them, te is the principal component of the variable feature space, Λ ―1is the diagonal inverse matrix of the eigenvalues ​​corresponding to the first pe eigenvectors. The normal recognition data can reflect the main change trend of the operating status data within the status data sample time range corresponding to the normal recognition data.

[0056] The calculation of the abnormality identification data Q of the state data sample can be based on the formula:

[0057]

[0058] The abnormality identification data may reflect other change trends of the operating status data other than the main change trend within the status data sample time range corresponding to the abnormality identification data.

[0059] This embodiment converts and calculates the variable feature space to obtain normal recognition data and abnormal recognition data of the state data samples corresponding to multiple variable feature samples in the variable feature space, and can capture the main change trends and other change trends of the welding robot's operating status within the time range of the state data samples.

[0060] In some embodiments, the working condition identification threshold includes a normal identification threshold and an abnormal identification threshold. The working condition identification threshold of the welding robot and the process identification data corresponding to the multiple status data samples are obtained based on the operating status data. It also includes: performing statistical calculations on the normal identification data and abnormal identification data corresponding to the multiple status data samples in the operating status data to obtain the normal identification threshold and abnormal identification threshold of the welding robot.

[0061] In this embodiment, after the welding robot working condition recognition device obtains the normal recognition data and abnormal recognition data of the multiple state data samples, it can perform statistical calculations on the normal recognition data and abnormal recognition data corresponding to the multiple state data samples in the operating state data to obtain the normal recognition threshold and abnormal recognition threshold of the welding robot. Specifically, the normal recognition threshold H of the welding robot L The calculation is based on the formula:

[0062]

[0063] Wherein, N is the number of status data samples in the running status data, F pe,N―pe,conf The normality recognition threshold can be used to define the normal variation range of the main variation trend in the operation status data of the welding robot within the time range corresponding to the operation status data.

[0064] The abnormality recognition threshold Q of the welding robot LThe calculation is based on the formula:

[0065]

[0066] in, where u Q and σ Q are the mean and variance of the abnormal identification data Q of all state data samples in the running state data, respectively, 2 The abnormality identification threshold can be used to define the normal variation range of the remaining variation trends in the operation status data of the welding robot, other than the main variation trend, within the time range corresponding to the operation status data.

[0067] This embodiment obtains the normal recognition threshold and abnormal recognition threshold of the welding robot by performing statistical calculations on the normal recognition data and abnormal recognition data corresponding to multiple status data samples in the operating status data. The normal recognition threshold and abnormal recognition threshold can be used to limit the normal change range of the main change trend of the operating status data and the remaining change trends, thereby identifying the working condition of the welding robot within the time range of each status data sample in the operating status data by judging whether the data change trend within the time range of each status data sample in the operating status data exceeds the normal change range.

[0068] In some embodiments, the working condition of the welding robot during operation is identified based on the relationship between the process identification data and the working condition identification threshold, including: if the normal identification data corresponding to the state data sample is less than the normal identification threshold, and the abnormal identification threshold corresponding to the state data sample is less than the abnormal identification threshold, the working condition of the welding robot operating within the time range of the state data sample is identified as a stable working condition.

[0069] In this embodiment, the welding robot working condition identification device can identify the working condition of the welding robot during operation based on the relationship between the process identification data of each state data sample in the operating state data and the working condition identification threshold of the welding robot. In some embodiments, for example, for the aforementioned six-axis welding robot, in the operating state data of the six-axis welding robot, the welding robot working condition identification device can calculate the normal identification data H=12.0308 of one state data sample, the abnormal identification data Q=1803.66 of the state data sample, and the normal identification threshold H of the six-axis welding robot. L =47.1185, the abnormality recognition threshold Q of the six-axis welding robot L=9944.91. Therefore, the welding robot operating condition identification device can conclude that the normal state identification data of the six-axis welding robot in the state data sample is less than the normal state identification threshold of the six-axis welding robot, and the abnormal state identification data of the six-axis welding robot in the state data sample is less than the abnormal state identification threshold of the six-axis welding robot. Based on the relationship between the process identification data of the six-axis welding robot in the state data sample and the operating condition identification threshold of the six-axis welding robot, the welding robot operating condition identification device can identify the operating condition of the six-axis welding robot within the time range of the state data sample as a stable operating condition.

[0070] For the case where the normal recognition data corresponding to the status data sample is less than the normal recognition threshold, and the abnormal recognition threshold corresponding to the status data sample is less than the abnormal recognition threshold, this embodiment identifies the working condition of the welding robot within the time range corresponding to the status data sample as a stable working condition.

[0071] In some embodiments, the identifying of the working condition of the welding robot during operation based on the relationship between the process identification data and the working condition identification threshold also includes: if the normal identification data corresponding to the state data sample is greater than or equal to the normal identification threshold, or the abnormal identification threshold corresponding to the state data sample is greater than or equal to the abnormal identification threshold, the working condition of the welding robot operating within the time range of the state data sample is identified as an unstable working condition.

[0072] In this embodiment, the welding robot working condition identification device can identify the working condition of the welding robot during operation based on the relationship between the process identification data of each state data sample in the operating state data and the working condition identification threshold of the welding robot. In some embodiments, for example, for the aforementioned six-axis welding robot, in the operating state data of the six-axis welding robot, the welding robot working condition identification device can calculate the normal identification data H=110.7965 of one state data sample, the abnormal identification data Q=537.501 of the state data sample, and the normal identification threshold H of the six-axis welding robot. L =47.1185, the abnormality recognition threshold Q of the six-axis welding robot L=9944.91. Therefore, the welding robot operating condition identification device can conclude that the normal state identification data of the six-axis welding robot in the state data sample is greater than the normal state identification threshold of the six-axis welding robot, and the abnormal state identification data of the six-axis welding robot in the state data sample is less than the abnormal state identification threshold of the six-axis welding robot. Based on the relationship between the process identification data of the six-axis welding robot in the state data sample and the operating condition identification threshold of the six-axis welding robot, the welding robot operating condition identification device can identify the operating condition of the six-axis welding robot within the time range of the state data sample as an unstable operating condition.

[0073] For the case where the normal recognition data corresponding to the status data sample is greater than or equal to the normal recognition threshold, or the abnormal recognition threshold corresponding to the status data sample is greater than or equal to the abnormal recognition threshold, this embodiment identifies the working condition of the welding robot within the time range corresponding to the status data sample as an unstable working condition.

[0074] See also Figure 2 . One embodiment of the present application also provides a welding robot working condition identification device, including: an acquisition module, used to obtain operating status data of the welding robot during operation; wherein, the operating status data includes multiple status data samples arranged in chronological order; an analysis module, used to derive the working condition identification threshold of the welding robot and process identification data corresponding to the multiple status data samples based on the operating status data; wherein, the working condition identification threshold is used to limit the normal change range of the operating status data, and the process identification data is used to reflect the change trend of the operating status data within the time range of the status data samples corresponding to the process identification data; an identification module, used to identify the working condition of the welding robot during operation according to the relationship between the process identification data and the working condition identification threshold.

[0075] In this embodiment, the specific functions and effects achieved by the welding robot working condition identification device can be explained by referring to other embodiments of the present application and will not be repeated here.

[0076] See also Figure 3 . An embodiment of the present application may provide an electronic device, comprising: a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors to enable the one or more processors to implement the aforementioned welding robot working condition identification method.

[0077] In some embodiments, the electronic device may include a processor, a storage medium, and a communication interface connected by a system bus. The storage medium may store a related computer program.

[0078] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the processor implements the aforementioned method for identifying the working condition of a welding robot.

[0079] The user information or user account information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, etc.) involved in multiple implementation methods of this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0080] It should be understood that the specific examples herein are only intended to help those skilled in the art better understand the embodiments of the present application, rather than to limit the scope of the present invention.

[0081] It can be understood that in the various implementation methods of this application, the size of the serial number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the implementation method of this application.

[0082] It can be understood that the various embodiments described in this application can be implemented individually or in combination, and the embodiments of this application are not limited to this.

[0083] Unless otherwise indicated, all technical and scientific terms used in the embodiments of the present application have the same meaning as those commonly understood by those skilled in the art in the technical field of the present application. The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit the scope of this application. The term "and / or" used in this application includes any and all combinations of one or more related listed items. The singular forms "a", "above", and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates otherwise.

[0084] It is understood that the processor in the embodiments of the present application can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above-mentioned method embodiment can be completed by hardware integrated logic circuits in the processor or software instructions. The above-mentioned processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of the present application can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above-mentioned method.

[0085] It will be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (programmable ROM, PROM), an erasable programmable read-only memory (erasable PROM, EPROM), an electrically erasable programmable read-only memory (EEPROM) or flash memory. The volatile memory may be a random access memory (RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0086] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0087] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, devices and units can refer to the corresponding processes in the aforementioned method implementation methods and will not be repeated here.

[0088] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0089] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of this embodiment.

[0090] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0091] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0092] The above description is merely a specific embodiment of the present application, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A welding robot working condition identification method, characterized in that: The method comprises: Acquiring operation status data of the welding robot during operation; wherein the operation status data includes a plurality of status data samples arranged in chronological order; Based on the operating status data, a working condition identification threshold of the welding robot and process identification data corresponding to the multiple status data samples are obtained; wherein the working condition identification threshold is used to limit the normal variation range of the operating status data, and the process identification data is used to reflect the variation trend of the operating status data within the time range of the status data samples corresponding to the process identification data; The working condition of the welding robot during operation is identified according to the relationship between the process identification data and the working condition identification threshold.

2. The method according to claim 1, characterized in that The state data samples include multiple sample points arranged in chronological order, and the number of sample points in the state data samples is the same; wherein, any two state data samples adjacent in chronological order include multiple common sample points, and the number of the common sample points is the same.

3. The method according to claim 2, characterized in that The welding robot working condition includes a stable working condition and an unstable working condition. Among all the sample points included in the operating status data, some sample points corresponding to the unstable working condition are earlier than some sample points corresponding to the stable working condition in chronological order.

4. The method according to claim 1, wherein Each of the sample points includes variable values ​​of multiple state variables, each of the multiple state variables corresponds to multiple variable features, and the working condition recognition threshold of the welding robot and the process recognition data corresponding to the multiple state data samples are obtained based on the operating state data, including: Based on the variable values ​​of the state variables corresponding to the sample points in the state data samples, the variable features corresponding to the state variables of the sample points in the state data samples are extracted to obtain a variable feature space; the variable feature space includes multiple variable feature samples, and the variable feature samples form a corresponding relationship with the state data samples.

5. The method according to claim 4, characterized in that The process identification data includes normal identification data and abnormal identification data. The process identification data corresponding to the working condition identification threshold of the welding robot and the plurality of state data samples are obtained based on the operating state data, and further includes: The variable feature space is converted and calculated to obtain normal recognition data and abnormal recognition data of the state data samples corresponding to the plurality of variable feature samples in the variable feature space.

6. The method according to claim 5, characterized in that The working condition recognition threshold includes a normal recognition threshold and an abnormal recognition threshold. The working condition recognition threshold of the welding robot and the process recognition data corresponding to the multiple state data samples are obtained based on the operating state data, and further includes: Statistical calculations are performed on normal recognition data and abnormal recognition data corresponding to a plurality of status data samples in the operating status data to obtain a normal recognition threshold value and an abnormal recognition threshold value of the welding robot.

7. The method according to claim 1, characterized in that The identifying the working condition of the welding robot during operation according to the relationship between the process identification data and the working condition identification threshold comprises: If the normal recognition data corresponding to the state data sample is less than the normal recognition threshold, and the abnormal recognition threshold corresponding to the state data sample is less than the abnormal recognition threshold, the working condition of the welding robot within the time range of the state data sample is identified as a stable working condition.

8. The method according to claim 7, characterized in that The identifying the working condition of the welding robot during operation according to the relationship between the process identification data and the working condition identification threshold value further includes: If the normal recognition data corresponding to the state data sample is greater than or equal to the normal recognition threshold, or the abnormal recognition threshold corresponding to the state data sample is greater than or equal to the abnormal recognition threshold, the working condition of the welding robot within the time range of the state data sample is identified as an unstable working condition.

9. A welding robot working condition identification device, characterized in that: include: An acquisition module is used to acquire operation status data of the welding robot during operation; wherein the operation status data includes a plurality of status data samples arranged in chronological order; an analysis module, configured to derive, based on the operating status data, a working condition identification threshold of the welding robot and process identification data corresponding to the plurality of status data samples; wherein the working condition identification threshold is used to limit a normal variation range of the operating status data, and the process identification data is used to reflect a variation trend of the operating status data within a time range of the status data samples corresponding to the process identification data; The identification module is used to identify the working condition of the welding robot during operation according to the relationship between the process identification data and the working condition identification threshold.

10. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor to implement the welding robot working condition identification method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores at least one computer program, and when the at least one computer program is executed by the processor, it can implement the welding robot working condition identification method according to any one of claims 1 to 8.

Images