CN117381105A

CN117381105A - Robot welding current control method and device, electronic equipment and storage medium

Info

Publication number: CN117381105A
Application number: CN202311685912.2A
Authority: CN
Inventors: 陈晓波
Original assignee: Binzel Guangzhou Welding Technology Co ltd
Current assignee: Binzel Guangzhou Welding Technology Co ltd
Priority date: 2023-12-11
Filing date: 2023-12-11
Publication date: 2024-01-12
Anticipated expiration: 2043-12-11
Also published as: CN117381105B

Abstract

The invention discloses a method, a device, electronic equipment and a storage medium for controlling welding current of a robot, which comprise the following steps: the method comprises the steps of controlling a first camera to collect a first image, controlling a second camera to collect a video, controlling an infrared camera to collect a second image, determining real-time temperature of an electric arc from the second image, determining molten pool depth from the first image, determining molten drop volume and molten drop frequency from the video, determining temperature weight, depth weight, volume weight and frequency weight based on preset process parameters, calculating a current regulation proportion according to the real-time temperature, the molten pool depth, the molten drop volume, the molten drop frequency, the temperature weight, the depth weight, the volume weight and the frequency weight, and controlling welding current of a welding robot according to the current regulation proportion, so that accuracy of the calculated current regulation proportion is improved through data combination weights of multiple dimensions of the real-time temperature, the molten pool depth, the molten drop volume and the molten drop frequency, the welding current can be accurately controlled, and the welding quality is improved.

Description

Robot welding current control method and device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of welding robots, and in particular, to a method and apparatus for controlling welding current of a robot, an electronic device, and a storage medium.

Background

With the development of welding robot technology, welding robots are widely applied to welding of welding seams in the industrial field, and in the welding process, welding current directly influences welding quality and is important to welding current control.

At present, a sensor is arranged on a welding machine to detect the real-time temperature of an electric arc or a molten pool during welding, for example, the real-time temperature of the electric arc or the molten pool is detected in real time through a thermocouple, an infrared camera and the like, the current regulation proportion is determined after the real-time temperature is compared with the reference temperature, so that the welding current is controlled through the current regulation proportion, however, the temperature of the electric arc or the molten pool is easily influenced by the environmental temperature, the accuracy of the current regulation proportion determined through the real-time temperature is low, the welding current of the welding robot cannot be accurately controlled, the welding current is excessively large or excessively small, the state of the molten pool, molten drops and the electric arc during welding cannot be regulated to an ideal state, and the welding quality is difficult to ensure.

Disclosure of Invention

The invention provides a method, a device, electronic equipment and a storage medium for controlling welding current of a robot, which are used for solving the problems that the accuracy of determining the current regulation proportion by detecting the real-time temperature of an electric arc or a molten pool is low and the welding quality is difficult to ensure.

In a first aspect, the present invention provides a welding current control method for a robot, where the welding robot is provided with a welding gun, a first camera, a second camera and an infrared camera, the first camera is located at a side of the welding gun facing a welding direction, and the second camera is located at a side of the welding gun facing away from the welding direction, and the method includes:

when a welding robot welds a welding seam, a first camera is controlled to acquire a first image of the welding seam opposite to the welding gun, and a second camera is controlled to acquire a video of an area between the welding gun and the welding seam;

controlling the infrared camera to acquire a second image of an arc area formed by the welding gun, and determining the real-time temperature of the arc from the second image;

determining a bath depth from the first image;

determining the volume and the frequency of the molten drops from the video;

determining a temperature weight, a depth weight, a volume weight and a frequency weight based on preset process parameters;

calculating a current regulation proportion according to the real-time temperature, the molten pool depth, the molten drop volume, the molten drop frequency, the temperature weight, the depth weight, the volume weight and the frequency weight;

And controlling the welding current of the welding robot according to the current regulation proportion.

In a second aspect, the present invention provides a welding current control device for a robot, where the welding robot is provided with a welding gun, a first camera, a second camera and an infrared camera, the first camera is located at a side of the welding gun facing a welding direction, the second camera is located at a side of the welding gun facing away from the welding direction, and the welding current control device includes:

the image and video acquisition module is used for controlling the first camera to acquire a first image of a welding line opposite to the welding gun and controlling the second camera to acquire a video of an area between the welding gun and the welding line when the welding robot welds the welding line;

the infrared temperature measurement module is used for controlling the infrared camera to acquire a second image of an arc area formed by the welding gun, and determining the real-time temperature of the arc from the second image;

the molten pool depth determining module is used for determining the molten pool depth from the first image;

the droplet volume and frequency determining module is used for determining droplet volume and droplet frequency from the video;

the weight determining module is used for determining temperature weight, depth weight, volume weight and frequency weight based on preset process parameters;

The current regulation proportion calculation module is used for calculating a current regulation proportion according to the real-time temperature, the molten pool depth, the molten drop volume, the molten drop frequency, the temperature weight, the depth weight, the volume weight and the frequency weight;

and the current control module is used for controlling the welding current of the welding robot according to the current regulation proportion.

In a third aspect, the present invention provides an electronic device, including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the robot welding current control method of any one of the first aspects of the invention.

In a fourth aspect, the present invention provides a computer readable storage medium storing computer instructions for causing a processor to implement the method for controlling welding current of a robot according to any one of the first aspects of the present invention when executed.

According to the invention, a first image is acquired through the first camera positioned at one side of the welding gun facing the welding direction, a video is acquired through the second camera positioned at one side of the welding gun facing away from the welding direction, the real-time temperature of an electric arc is determined through the second image acquired through the infrared camera, the molten pool depth is determined from the first image, the molten drop volume and the molten drop frequency are determined from the video, the temperature weight, the depth weight, the volume weight and the frequency weight are determined based on preset technological parameters, the current regulation proportion is calculated through the real-time temperature, the molten pool depth, the molten drop volume, the molten drop frequency, the temperature weight, the depth weight, the volume weight and the frequency weight, so that the welding current is controlled, the current regulation proportion is calculated through the data combination weight of the real-time temperature, the molten pool depth, the molten drop volume and the molten drop frequency in multiple dimensions, the problem that the accuracy of the current regulation proportion is low due to the influence of the environmental temperature is solved, the calculated accuracy of the current regulation proportion can be improved, the welding current can be accurately controlled, the welding quality can be adjusted to an ideal state, and the welding quality is improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of a method for controlling welding current of a robot according to an embodiment of the present invention;

FIG. 2 is a schematic illustration of a welding robot welding a weld;

fig. 3 is a flowchart of a method for controlling welding current of a robot according to a second embodiment of the present invention;

FIG. 4 is a schematic view of bath depth;

fig. 5 is a schematic structural diagram of a welding current control device for a robot according to a third embodiment of the present invention;

fig. 6 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

Example 1

Fig. 1 is a flowchart of a method for controlling welding current of a robot according to an embodiment of the present invention, where the method may be performed by a welding current control device of a robot, and the welding current control device of the robot may be implemented in hardware and/or software, and the welding current control device of the robot may be configured in an electronic device. As shown in fig. 1, the welding current control method of the robot includes:

s101, when a welding robot welds a welding line, controlling a first camera to acquire a first image of the welding line opposite to a welding gun, and controlling a second camera to acquire a video of an area between the welding gun and the welding line.

The robot in this embodiment may be a welding robot for realizing fusion welding by current, for example, may be an arc welding robot, as shown in fig. 2, where the welding robot includes a welding gun 1, a first camera 2, a second camera 3, and an infrared camera (not shown), and the working principle of the welding robot is that a welding wire 4 is disposed in the welding gun 1, after the welding gun 1, the welding wire 4 and a welding seam 5 in a workpiece form a welding loop, an arc is generated between the welding wire 4 and the welding seam 5, the welding wire 4 is melted by the high temperature of the arc to form a molten drop 6, and the molten drop 6 is dropped into the welding seam 5 to realize welding of the welding seam 5.

The first camera 2 and the second camera 3 may be cameras provided with optical filters to filter arc light generated by an arc through the optical filters, the first camera 2 is disposed on one side of the welding gun 1 facing the welding direction F, the second camera 3 is disposed on one side of the welding gun 1 facing away from the welding direction F, and the first camera 2 and the second camera 3 may be disposed directly above the welding seam, for example, centers of the welding gun 1, the first camera 2, the second camera 3 and the welding seam 5 are on the same plane, as shown in fig. 2, and centers of the welding gun 1, the first camera 2, the second camera 3 and the welding seam 5 are on the same plane in the vertical direction.

As can be seen from fig. 2, the first camera 2 can capture an image of the area of the weld 5 where it is not welded and where it is welded, and the second camera 3 can capture a video of the area between the weld 5 and the gun 1 including the welded weld, the welding wire 4, and the droplet 6.

In one embodiment, the first camera 2 may be controlled to acquire the first image at a preset period, and the second camera 3 may be controlled to acquire the video at a preset frame rate.

S102, controlling the infrared camera to acquire a second image of an arc area formed by the welding gun, and determining the real-time temperature of the arc from the second image.

The infrared camera of this embodiment may include a temperature detection module, after the infrared camera is controlled to collect the second image of the arc area, the real-time temperature of the arc is determined from the second image by the temperature detection module, and the method of collecting the infrared image to identify the temperature by the infrared camera in the prior art may be referred to, which will not be described in detail herein.

S103, determining the depth of a molten pool from the first image.

The depth of the molten pool may be a depth of a molten pool formed after the molten droplet is dropped onto the weld, and in welding, the larger the welding current is, the deeper the molten pool depth is, in one embodiment, after the gray scale of the first image is processed to obtain a gray scale image, an edge detection operator such as Roberts, sobelisk, prewitt, laplace, or a Canny edge detector is used to perform edge detection on the gray scale image to obtain an edge of the molten pool, and the molten pool depth is calculated through the edge of the molten pool.

In another embodiment, the gray level map may also be input into the molten pool detection model to obtain a minimum external detection frame of the molten pool, and the depth of the molten pool is calculated through the length or width of the minimum external detection frame.

S104, determining the droplet volume and the droplet frequency from the video.

The droplet volume may be the maximum volume during droplet formation and the droplet frequency may be the number of droplets formed per unit time, with the larger the welding current, the smaller the droplet volume and the larger the droplet frequency.

In one embodiment, a video may be input into a preset droplet detection tracking model to obtain a droplet volume of each droplet, the number of droplets detected from the video is counted, the ratio of the number to the length is calculated after the length of the video is determined to obtain a droplet frequency, the sum of the droplet volumes is calculated, and the ratio of the sum to the number is calculated to obtain the droplet volume.

S105, determining temperature weight, depth weight, volume weight and frequency weight based on preset process parameters.

In this embodiment, the preset process parameters may be process parameters when the welding robot welds the weld seam under ideal conditions according to a reference current theoretically designed, and the process parameters may include a reference temperature, a reference volume, a reference frequency, and a reference depth, where the reference temperature is a temperature of the arc under ideal conditions, the reference volume and the reference frequency are a volume and a frequency of the droplet under ideal conditions, and the reference depth is a depth of the molten pool under ideal conditions.

After determining the real-time temperature, bath depth, droplet volume, and droplet frequency, the deviation rates of the real-time temperature, bath depth, droplet volume, and droplet frequency from the corresponding reference values may be calculated, and each weight may be determined from the deviation rates, where the weights are positively correlated to the deviation rates, and in one embodiment, the normalized deviation rates may be used as the weights after normalizing each deviation rate.

S106, calculating the current regulation proportion according to the real-time temperature, the molten pool depth, the molten drop volume, the molten drop frequency, the temperature weight, the depth weight, the volume weight and the frequency weight.

In one embodiment, the current adjustment ratio corresponding to the real-time temperature, the bath depth, the droplet volume and the droplet frequency may be determined first, the current adjustment ratio may be a percentage of a reference current with respect to a theoretical design, specifically, a temperature and current adjustment ratio comparison table may be preset, the current adjustment ratio corresponding to the real-time temperature is determined in the temperature and current adjustment ratio comparison table, or a temperature and current adjustment curve may be preset, the current adjustment ratio corresponding to the real-time temperature is determined in the current adjustment curve, and the current adjustment ratio may be calculated by substituting the real-time temperature into a preset function with the temperature as an independent variable and the current adjustment ratio as a dependent variable.

After determining the current regulation proportion corresponding to the real-time temperature, the molten pool depth, the molten drop volume and the molten drop frequency, calculating the weighted sum of the current regulation proportion by adopting the temperature weight, the depth weight, the volume weight and the frequency weight to be used as the final current regulation proportion.

And S107, controlling the welding current of the welding robot according to the current regulation proportion.

After the current adjustment ratio is determined, the product of the current adjustment ratio and the reference current can be calculated as a current adjustment amount, the sum of the reference current and the current adjustment amount is calculated to obtain a target welding current, and the current welding current of the welding robot is adjusted to the target welding current.

According to the embodiment of the invention, the first image is acquired through the first camera positioned at one side of the welding gun facing the welding direction, the video is acquired through the second camera positioned at one side of the welding gun facing away from the welding direction, the real-time temperature of the electric arc is determined through the second image acquired through the infrared camera, the molten pool depth is determined from the first image, the molten drop volume and the molten drop frequency are determined from the video, the temperature weight, the depth weight, the volume weight and the frequency weight are determined based on preset technological parameters, the current regulation proportion is calculated through the real-time temperature, the molten pool depth, the molten drop volume, the molten drop frequency, the temperature weight, the depth weight and the frequency weight, so that the welding current is controlled, the current regulation proportion is calculated through the data combination weight of the real-time temperature, the molten pool depth, the molten drop volume and the molten drop frequency, the current regulation proportion accuracy is low due to the influence of the environmental temperature, the accuracy of the calculated current regulation proportion can be improved through the data combination weight of the real-time temperature, the molten pool depth, the molten drop volume and the molten drop frequency, the molten drop frequency multiple dimensions, the accuracy of the calculated current regulation proportion can be controlled accurately, the welding current can be adjusted to an ideal state, the welding quality is improved, and the welding quality is improved.

Example two

Fig. 3 is a flowchart of a method for controlling welding current of a robot according to a second embodiment of the present invention, where the method for controlling welding current of a robot according to the first embodiment of the present invention is optimized on the basis of the first embodiment, as shown in fig. 3, and includes:

s301, when the welding robot welds the welding seams, controlling the first camera to acquire a first image of the welding seams opposite to the welding guns, and controlling the second camera to acquire videos of the areas between the welding guns and the welding seams.

As shown in fig. 2, when the welding robot welds a weld, the first camera 2 is controlled to acquire a first image of the region of the weld facing the welding gun 1 according to a preset period, and the second camera 3 is controlled to acquire video of a molten pool and a molten drop included in the region between the welding gun 1 and the weld 5 according to a preset frame rate.

S302, controlling an infrared camera to acquire a second image of an arc area formed by the welding gun, and determining the real-time temperature of the arc from the second image.

S303, determining a minimum external detection frame of the molten pool from the first images aiming at each first image.

In one embodiment, gray scale processing can be performed on the first image to obtain a gray scale image, an edge detection algorithm is adopted to perform edge detection on the gray scale image to obtain a molten pool edge, a first minimum external rectangle is generated based on the molten pool edge, the gray scale image is input into a preset molten pool detection model to obtain a second minimum external rectangle and confidence coefficient, if the confidence coefficient is larger than or equal to a preset threshold value, the second minimum external rectangle is determined to be a minimum external detection frame of the molten pool, and if the confidence coefficient is smaller than the preset threshold value, a union is obtained on the first minimum external rectangle and the second minimum external rectangle, and the minimum external rectangle of the union is taken as the minimum external detection frame of the molten pool.

The edge detection algorithm may include at least one of Roberts, sobelisk, prewitt, laplace, and the like, the puddle detection model may be CNN (convolutional neural network, convolutional Neural Networks), RNN (recurrent neural network ), GCN (graph convolution network, graph Convolutional Networks), and the like, and in practical application, an image including and labeled a detection frame of the puddle may be used as a training image to train the puddle detection model, and a specific training method may refer to a training method of various neural networks in the prior art, which is not described in detail herein.

As shown in fig. 4, a first minimum bounding rectangle a of the molten pool can be determined in a first image through an edge detection algorithm, a second minimum bounding rectangle B of the molten pool and a confidence coefficient can be determined through a molten pool detection model, the confidence coefficient represents the probability that the second minimum bounding rectangle B predicted by the molten pool detection model is the minimum bounding detection frame of the molten pool, the higher the confidence coefficient is, the more accurate the second minimum bounding rectangle B is, when the confidence coefficient is greater than or equal to a preset threshold (such as greater than or equal to 0.95), the second minimum bounding rectangle B can be determined as the minimum bounding detection frame of the molten pool, and when the confidence coefficient is less than the preset threshold, the union of the first minimum bounding rectangle a and the second minimum bounding rectangle B can be taken, and the minimum bounding rectangle C of the union is taken as the minimum bounding detection frame of the molten pool.

According to the method, the device and the system, the minimum external detection frame of the molten pool is determined through the edge detection and the molten pool detection model, whether the detection frame predicted by the molten pool detection module is used as a standard or not is determined through the confidence, and when the confidence is smaller than a preset threshold, the minimum external detection frame of the molten pool is determined through the edge detection and the molten pool detection model together, so that the problem that the minimum external detection frame is inaccurate when the edge detection or the molten pool detection model is independently adopted can be avoided, and the accuracy of the minimum external detection frame is improved.

S304, calculating the pixel distance of the minimum external detection frame in the depth direction of the molten pool in the continuous N first images, and calculating the average value of the N pixel distances to obtain the average pixel distance.

After determining the minimum external detection frame of the molten pool in the image through each first image, the maximum pixel distance of the minimum external detection frame in the depth direction of the molten pool, such as the maximum pixel number of the minimum external detection frame in the depth direction of the molten pool or the pixel coordinates of two pixel points of the maximum distance of the minimum external detection frame in the depth direction of the molten pool, is calculated, the distance between the pixel coordinates of the two pixels is calculated to be the pixel distance, and the average value of the pixel distances determined by the continuous N first images is further calculated to be the average pixel distance.

S305, converting the average pixel distance into the distance under the coordinate system of the first camera by adopting the calibration parameters of the first camera to serve as the depth of the molten pool.

The average pixel distance is the distance under the image coordinate system of the first image, and calibration parameters such as the focal length of the first camera, CCD parameters, the relative position between the first camera and the welding gun and the like can be adopted to convert the average pixel distance into the distance under the coordinate system of the first camera, so as to obtain the depth d of the molten pool.

According to the embodiment, the average pixel distance is obtained by calculating the average value of the pixel distances determined by the continuous first images, and the average pixel distance is converted into the molten pool depth, so that the average value filtering processing of the molten pool depth is realized, the problem that the molten pool depth is inaccurate due to the fact that a single first image is adopted to determine the molten pool depth is avoided, and the accuracy of the molten pool depth is further improved.

S306, determining the droplet volume and the droplet frequency from the video.

In one embodiment, a droplet detection tracking model may be trained in advance, when the droplet detection tracking model is trained, a training video segment may be acquired first, a first droplet volume may be marked for a video image in each video segment, and a first droplet frequency may be marked for an entire video segment, after the video segment is input into the droplet detection tracking model, a second droplet volume of a droplet in each frame of the video image and a second droplet frequency of the entire video segment may be predicted, and a loss rate may be calculated by the first droplet volume, the first droplet frequency, the second droplet volume, and the second droplet frequency, and when the loss rate is greater than a preset threshold, model parameters of the droplet detection tracking model may be updated, and a step of inputting the video segment into the droplet detection tracking model may be returned until the droplet detection tracking model is determined to complete training when the loss rate is less than the preset threshold.

In one embodiment, the loss rate may be calculated by a cross entropy loss function, and in another embodiment, the loss rate may be calculated by the following formula:

；

the method comprises the steps that n is the number of video images of detected droplets in a video segment, vi1 and Vi2 are respectively the first droplet volume and the predicted second droplet volume of an ith frame of video image annotation, fre1 and Fre2 are respectively the first droplet frequency and the second droplet frequency, gamma is a punishment coefficient, M is a threshold frequency, M can be a preset constant, an exemplary video segment serving as a training sample can be a video segment with uniform standard duration, a sufficient number of droplets in an ideal video segment should be marked, namely the standard droplet number, a threshold frequency M can be set according to the standard frequency, for example, the threshold frequency M can be 0.5 times and 0.4 times of the standard frequency, and the like, for example, the length of the video segment which can be processed by a droplet detection tracking model is 15 seconds, at least 8 droplets are required to be used for marking in the video segment, the video segment can be trained, the performance of the droplet detection tracking model can be better, the droplet loss is calculated through the video segment, and if the number of the video segment is more than the standard droplet number, namely the punishment loss is larger than the threshold frequency, namely the loss is larger than the threshold frequency, and the loss is more than the threshold frequency is required to be reduced, namely the loss is larger than the main loss, namely the loss is more than the loss is larger than the loss.

Through the loss function, the capacity of detecting the volume and the frequency of the molten drops can be learned from the molten drop volume loss and the molten drop frequency loss constraint molten drop detection tracking model, and a punishment coefficient is set so as to punish the lost volume of the molten drops when the frequency of the molten drops in the video segment is too small and the quantity of the molten drops marked in the video segment is too small, so that the problem that the total loss rate is inaccurate when the quantity of the molten drops marked in the video segment is too small is avoided, and the accuracy of the loss rate is improved.

After training the droplet detection tracking model, a video can be input into a preset droplet detection tracking model to obtain the droplet volume of each droplet, the number of droplets detected from the video is counted, the ratio of the number to the length is calculated after the length of the video is determined to obtain the droplet frequency, the sum of the droplet volumes is calculated, and the ratio of the sum to the number is calculated to obtain the droplet volume.

S307, respectively calculating a first absolute value of a difference value between the real-time temperature and the reference temperature, a second absolute value of a difference value between the molten pool depth and the reference depth, a third absolute value of a difference value between the molten drop volume and the reference volume, and a fourth absolute value of a difference value between the molten drop frequency and the reference frequency.

Specifically, assuming that the real-time temperature is T, the reference temperature is Tref, the bath depth is D, the reference depth is Dref, the droplet volume is V, the reference volume is Vref, the droplet frequency is F, the reference frequency is Fref, the first absolute value Abs 1= |t-tref| can be calculated, the second absolute value Abs 2= |d-dref| can be calculated, the third absolute value Abs 3= |v-vref| can be calculated, and the fourth absolute value Abs 4= |f-fref| can be calculated.

S308, calculating the ratio of the first absolute value to the reference temperature, the ratio of the second absolute value to the reference depth, the ratio of the third absolute value to the reference volume and the ratio of the fourth absolute value to the reference frequency respectively to obtain the temperature deviation rate, the molten pool depth deviation rate, the droplet volume deviation rate and the droplet frequency deviation rate.

I.e. temperature deviation dev_t=abs 1/Tref, melt pool depth deviation dev_d=abs 2/Dref, droplet volume deviation dev_v=abs 3/Vref, droplet frequency deviation dev_f=abs 4/Fref.

S309, determining a temperature weight, a depth weight, a volume weight and a frequency weight based on the temperature deviation rate, the molten pool depth deviation rate, the droplet volume deviation rate and the droplet frequency deviation rate, wherein the temperature weight is positively correlated with the temperature deviation rate, the depth weight is positively correlated with the molten pool depth deviation rate, the volume weight is positively correlated with the droplet volume deviation rate, and the frequency weight is positively correlated with the droplet frequency deviation rate.

In one embodiment, the temperature weight w_t=dev_t/(1+dev_t), the depth weight w_d=dev_d/(1+dev_d), the volume weight w_v=dev_v/(1+dev_v), and the frequency weight w_f=dev_f/(1+dev_f).

In another embodiment, the temperature weight w_t=dev_t, the depth weight w_d=dev_d, the volume weight w_v=dev_v, and the frequency weight w_f=dev_f may be used to achieve positive correlation between each weight and the deviation rate.

In this embodiment, the temperature weight, the depth weight, the volume weight and the frequency weight are positively correlated with the corresponding deviation rates, the larger the corresponding deviation rate is, the larger the weight is, the larger the influence of the current regulation proportion determined by the parameters corresponding to the weight in the total current regulation proportion is, so that after the welding current is regulated by the current regulation proportion, the parameter with the large deviation rate is regulated to the reference value as much as possible, and the welding quality is improved.

S310, determining current regulation proportions of the real-time temperature, the molten pool depth, the molten drop volume and the molten drop frequency in a preset temperature and current regulation proportion comparison table, a molten pool depth and current regulation proportion comparison table, a molten drop volume and current regulation proportion comparison table and a molten drop frequency and current regulation proportion comparison table respectively to obtain a first current regulation proportion, a second current regulation proportion, a third current regulation proportion and a fourth current regulation proportion.

The embodiment can preset a temperature and current regulation proportion comparison table, a molten pool depth and current regulation proportion comparison table, a droplet volume and current regulation proportion comparison table and a droplet frequency and current regulation proportion comparison table, and can determine the current regulation proportion corresponding to the real-time temperature, the molten pool depth, the droplet volume and the droplet frequency through table lookup, and each current regulation proportion can be more than 0, equal to 0 and less than 0.

S311, acquiring an environment real-time temperature, calculating an absolute value of a difference value between the environment real-time temperature and a preset environment standard temperature, and calculating a ratio of the absolute value to the environment standard temperature to be used as a temperature punishment coefficient.

The embodiment can also obtain the real-time environmental temperature of the scene where the welding is performed, calculate the absolute value of the difference between the real-time environmental temperature and the standard environmental temperature, and calculate the ratio of the absolute value to the standard environmental temperature as a temperature penalty coefficient, wherein the standard environmental temperature can be an ideal environmental temperature required by welding according to a reference current designed theoretically, the temperature penalty coefficient is used for measuring the reliability of the current controlled by temperature, the larger the temperature penalty coefficient is, the larger the difference between the real-time environmental temperature and the standard environmental temperature is, the larger the influence of the environment temperature is, the less reliable the control current is determined by adopting temperature, and the influence of the current adjustment proportion determined by the real-time temperature on the total current adjustment proportion should be reduced.

S312, calculating a first difference value between the droplet volume deviation rate and the droplet frequency deviation rate, and calculating a second difference value between the value 1 and the first difference value as a droplet penalty coefficient.

Under the ideal condition according to theoretical design, when the reference current is adopted for welding, the droplet volume and the droplet frequency have a one-to-one correspondence, namely, the larger the reference current is, the smaller the droplet volume is, the larger the droplet frequency is, the first difference value of the droplet volume deviation rate and the droplet frequency deviation rate can be calculated, the second difference value of the value 1 and the first difference value is calculated to serve as a droplet penalty coefficient, the droplet penalty coefficient is used for measuring the reliability of the current controlled by the droplet, if the droplet penalty coefficient is larger, the droplet volume deviation rate and the droplet frequency deviation rate are described, the determined droplet volume and the droplet frequency are poor in consistency, the current regulation proportion is determined by the droplet volume and the droplet frequency to be unreliable, and the influence of the current regulation proportion determined by the droplet volume and the droplet frequency on the total current regulation proportion is reduced.

S313, calculating the total current regulation proportion through a preset formula.

Specifically, the preset formula is as follows:

I=I1×w1×（1-λ1）+ I2×w2+ I3×w3×（1-λ2）+ I4×w4×（1-λ2）；

wherein, I1 is the first current regulation proportion determined by real-time temperature, I2 is the second current regulation proportion determined by molten pool depth, I3 is the third current regulation proportion determined by droplet volume, I4 is the fourth current regulation proportion determined by droplet frequency, w1, w2, w3, w4 are temperature weight, depth weight, volume weight and frequency weight respectively, λ1 is a temperature penalty coefficient, and λ2 is a droplet penalty coefficient.

In the above calculation formula of the current adjustment ratio, taking the depth weight w2 as an example, since the weight is positively correlated with the deviation rate, when the depth weight w2 is larger, the difference between the molten pool depth and the designed reference depth is larger, the weight of the second current adjustment ratio I2 determined by the molten pool depth in the total current adjustment ratio I is larger, that is, the welding current is mainly adjusted by the molten pool depth, and the temperature penalty coefficient λ1 and the droplet penalty coefficient λ2 are added in the formula, so that the influence of the excessively large difference between the ambient real-time temperature and the ambient standard temperature and the influence of the excessively large difference between the detected droplet volume deviation rate and the droplet frequency deviation rate are eliminated, and the accuracy of the calculated current adjustment ratio is improved.

S314, controlling the welding current of the welding robot according to the current regulation proportion.

In one embodiment, the product of the current adjustment ratio and a preset reference current may be calculated to obtain a current adjustment amount, a sum of the reference current and the current adjustment amount may be calculated to obtain a target welding current, and the welding current of the welding robot may be adjusted to the target welding current.

According to the embodiment of the invention, the first image is acquired through the first camera positioned at one side of the welding gun facing the welding direction, the video is acquired through the second camera positioned at one side of the welding gun facing away from the welding direction, the real-time temperature of the electric arc is determined through the second image acquired through the infrared camera, the molten pool depth is determined from the first image, the molten drop volume and the molten drop frequency are determined from the video, the problem that the accuracy of the current regulation proportion is low due to the influence of the environmental temperature is further solved, the temperature weight, the depth deviation rate of the molten drop and the molten drop frequency deviation rate are further calculated based on the reference value, the temperature weight, the depth weight, the volume weight and the frequency weight are determined through the corresponding deviation rate, the current regulation proportion is calculated through the real-time temperature, the molten pool depth, the molten drop volume, the molten drop frequency, the temperature weight, the depth weight and the frequency weight, so that the current regulation proportion is controlled through the real-time temperature, the depth, the molten drop volume weight and the molten pool weight, the molten pool current can be controlled, the accuracy of the welding current regulation is improved, and the welding accuracy can be controlled to the ideal welding accuracy.

Example III

Fig. 5 is a schematic structural diagram of a welding current control device for a robot according to a third embodiment of the present invention. As shown in fig. 5, the robot welding current control device includes:

the image and video acquisition module 501 is configured to control a first camera to acquire a first image of a welding seam facing the welding gun and control a second camera to acquire a video of an area between the welding gun and the welding seam when the welding robot welds the welding seam;

the infrared temperature measurement module 502 is configured to control the infrared camera to acquire a second image of an arc area formed by the welding gun, and determine a real-time temperature of the arc from the second image;

a molten pool depth determining module 503, configured to determine a molten pool depth from the first image;

a droplet volume and frequency determination module 504 for determining droplet volume and droplet frequency from the video;

the weight determining module 505 is configured to determine a temperature weight, a depth weight, a volume weight, and a frequency weight based on preset process parameters;

a current adjustment ratio calculation module 506, configured to calculate a current adjustment ratio according to the real-time temperature, the molten pool depth, the droplet volume, the droplet frequency, the temperature weight, the depth weight, the volume weight, and the frequency weight;

And the current control module 507 is used for controlling the welding current of the welding robot according to the current regulation proportion.

Optionally, the bath depth determination module 503 includes:

the minimum external detection frame determining unit is used for determining a minimum external detection frame of the molten pool from each first image;

the average value calculating unit is used for calculating the pixel distance of the minimum external detection frame in the depth direction of the molten pool in the continuous N first images, and calculating the average value of the N pixel distances to obtain an average pixel distance;

and the molten pool depth calculation unit is used for converting the average pixel distance into the distance under the coordinate system of the first camera by adopting the calibration parameters of the first camera to serve as the molten pool depth.

Optionally, the minimum external detection frame determining unit includes:

a gray level processing subunit, configured to perform gray level processing on the first image to obtain a gray level map;

the edge detection subunit is used for carrying out edge detection on the gray level image by adopting an edge detection algorithm to obtain a molten pool edge, and generating a first minimum circumscribed rectangle based on the molten pool edge;

the model prediction subunit is used for inputting the gray level diagram into a preset molten pool detection model to obtain a second minimum circumscribed rectangle and a confidence coefficient;

The first minimum external detection frame determining subunit is configured to determine the second minimum external rectangle as a minimum external detection frame of the molten pool if the confidence coefficient is greater than or equal to a preset threshold;

and if the confidence coefficient is smaller than a preset threshold value, a union set is obtained for the first minimum circumscribed rectangle and the second minimum circumscribed rectangle, and the minimum circumscribed rectangle of the union set is taken as the minimum circumscribed detection frame of the molten pool.

Optionally, the droplet volume and frequency determination module 504 includes:

the video input unit is used for inputting the video into a preset droplet detection tracking model to obtain the droplet volume and the droplet quantity of each droplet;

the frequency calculation unit is used for determining the duration of the video and calculating the ratio of the number to the duration to obtain the frequency of the molten drops;

and the droplet volume calculating unit is used for calculating the sum value of the droplet volumes and calculating the ratio of the sum value to the number to obtain the droplet volume.

Optionally, the preset process parameters include a reference temperature, a reference volume, a reference frequency, and a reference depth, and the weight determining module 505 includes:

an absolute value calculation unit for calculating a first absolute value of a difference between the real-time temperature and a reference temperature, a second absolute value of a difference between the bath depth and the reference depth, a third absolute value of a difference between the droplet volume and the reference volume, and a fourth absolute value of a difference between the droplet frequency and the reference frequency, respectively;

The deviation rate calculation unit is used for calculating the ratio of the first absolute value to the reference temperature, the ratio of the second absolute value to the reference depth, the ratio of the third absolute value to the reference volume and the ratio of the fourth absolute value to the reference frequency respectively to obtain a temperature deviation rate, a molten pool depth deviation rate, a molten drop volume deviation rate and a molten drop frequency deviation rate;

the weight determining unit is used for determining a temperature weight, a depth weight, a volume weight and a frequency weight based on the temperature deviation rate, the molten pool depth deviation rate, the molten drop volume deviation rate and the molten drop frequency deviation rate, wherein the temperature weight is positively correlated with the temperature deviation rate, the depth weight is positively correlated with the molten pool depth deviation rate, the volume weight is positively correlated with the molten drop volume deviation rate, and the frequency weight is positively correlated with the molten drop frequency deviation rate.

Optionally, the current adjustment ratio calculation module 506 includes:

the table look-up unit is used for respectively determining the current regulation proportion of the real-time temperature, the molten pool depth, the molten drop volume and the molten drop frequency in a preset temperature and current regulation proportion comparison table, a molten pool depth and current regulation proportion comparison table, a molten drop volume and current regulation proportion comparison table and a molten drop frequency and current regulation proportion comparison table to obtain a first current regulation proportion, a second current regulation proportion, a third current regulation proportion and a fourth current regulation proportion;

The temperature punishment coefficient calculation unit is used for obtaining the environment real-time temperature, calculating the absolute value of the difference value between the environment real-time temperature and the preset environment standard temperature, and calculating the ratio of the absolute value to the environment standard temperature to be used as a temperature punishment coefficient;

a droplet penalty coefficient calculating unit, configured to calculate a first difference between the droplet volume deviation rate and the droplet frequency deviation rate, and calculate a second difference between a value 1 and the first difference, as a droplet penalty coefficient;

the current regulation proportion calculation unit is used for calculating the current regulation proportion through a preset formula, and the preset formula is as follows:

I=I1×w1×（1-λ1）+ I2×w2+ I3×w3×（1-λ2）+ I4×w4×（1-λ2）；

Optionally, the current control module 507 includes:

the regulation amount calculating unit is used for calculating the product of the current regulation proportion and a preset reference current to obtain a current regulation amount;

A target welding current calculation unit for calculating a target welding current of a sum value of the reference current and the current adjustment amount;

and the current adjusting unit is used for adjusting the welding current of the welding robot to the target welding current.

The welding current control device for the robot provided by the embodiment of the invention can execute the welding current control method for the robot provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Example IV

Fig. 6 shows a schematic diagram of an electronic device 60 that may be used to implement an embodiment of the invention. The electronic device may be a PLC controller in the welding robot or an upper computer, a server, etc. for controlling the welding robot. As shown in fig. 6, the electronic device 60 includes at least one processor 61, and a memory, such as a Read Only Memory (ROM) 62, a Random Access Memory (RAM) 63, etc., communicatively connected to the at least one processor 61, in which the memory stores a computer program executable by the at least one processor, and the processor 61 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 62 or the computer program loaded from the storage unit 68 into the Random Access Memory (RAM) 63. In the RAM 63, various programs and data required for the operation of the electronic device 60 may also be stored. The processor 61, the ROM 62 and the RAM 63 are connected to each other via a bus 64. An input/output (I/O) interface 65 is also connected to bus 64.

Various components in the electronic device 60 are connected to the I/O interface 65, including: an input unit 66 such as a keyboard, a mouse, a first camera, a second camera, an infrared camera, etc.; an output unit 67 such as various types of displays, speakers, and the like; a storage unit 68 such as a magnetic disk, an optical disk, or the like; and a communication unit 69 such as a network card, modem, wireless communication transceiver, etc. The communication unit 69 allows the electronic device 60 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

Processor 61 can be a variety of general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of processor 61 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 61 performs the various methods and processes described above, such as the robotic welding current control method.

In some embodiments, the robotic welding current control method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 68. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 60 via the ROM 62 and/or the communication unit 69. When the computer program is loaded into RAM 63 and executed by processor 61, one or more steps of the robot welding current control method described above may be performed. Alternatively, in other embodiments, the processor 61 may be configured to perform the robotic welding current control method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. The utility model provides a welding current control method of robot, its characterized in that welds the robot and is provided with welder, first camera, second camera and infrared camera, first camera is located welder is towards one side of welding direction, the second camera is located welder deviates from one side of welding direction includes:

determining a bath depth from the first image;

determining the volume and the frequency of the molten drops from the video;

2. The method of claim 1, wherein determining a puddle depth from the first image comprises:

determining a minimum external detection frame of a molten pool from each first image;

calculating the pixel distance of the minimum external detection frame in the depth direction of the molten pool in the continuous N first images, and calculating the average value of the N pixel distances to obtain the average pixel distance;

and converting the average pixel distance into the distance under the coordinate system of the first camera by adopting the calibration parameters of the first camera to serve as the depth of the molten pool.

3. The method of claim 1, wherein determining a minimum circumscribed detection box for a puddle from the first image comprises:

carrying out gray scale processing on the first image to obtain a gray scale image;

performing edge detection on the gray level image by adopting an edge detection algorithm to obtain a molten pool edge, and generating a first minimum circumscribed rectangle based on the molten pool edge;

inputting the gray level map into a preset molten pool detection model to obtain a second minimum circumscribed rectangle and a confidence coefficient;

if the confidence coefficient is greater than or equal to a preset threshold value, determining the second minimum circumscribed rectangle as a minimum circumscribed detection frame of a molten pool;

and if the confidence coefficient is smaller than a preset threshold value, obtaining a union of the first minimum circumscribed rectangle and the second minimum circumscribed rectangle, and taking the minimum circumscribed rectangle of the union as a minimum circumscribed detection frame of the molten pool.

4. A method according to any one of claims 1 to 3, wherein determining droplet volume and droplet frequency from the video comprises:

inputting the video into a preset droplet detection tracking model to obtain the droplet volume and the droplet quantity of each droplet;

determining the duration of the video, and calculating the ratio of the number to the duration to obtain the frequency of the molten drops;

And calculating the sum value of the droplet volumes, and calculating the ratio of the sum value to the number to obtain the droplet volumes.

5. A method according to any of claims 1-3, wherein the predetermined process parameters include a reference temperature, a reference volume, a reference frequency, a reference depth, determining a temperature weight, a depth weight, a volume weight, and a frequency weight based on the predetermined process parameters, comprising:

respectively calculating a first absolute value of a difference value between the real-time temperature and the reference temperature, a second absolute value of a difference value between the molten pool depth and the reference depth, a third absolute value of a difference value between the molten drop volume and the reference volume, and a fourth absolute value of a difference value between the molten drop frequency and the reference frequency;

respectively calculating the ratio of the first absolute value to the reference temperature, the ratio of the second absolute value to the reference depth, the ratio of the third absolute value to the reference volume and the ratio of the fourth absolute value to the reference frequency to obtain a temperature deviation rate, a molten pool depth deviation rate, a droplet volume deviation rate and a droplet frequency deviation rate;

and determining a temperature weight, a depth weight, a volume weight and a frequency weight based on the temperature deviation rate, the molten pool depth deviation rate, the droplet volume deviation rate and the droplet frequency deviation rate, wherein the temperature weight is positively correlated with the temperature deviation rate, the depth weight is positively correlated with the molten pool depth deviation rate, the volume weight is positively correlated with the droplet volume deviation rate, and the frequency weight is positively correlated with the droplet frequency deviation rate.

6. The method of claim 5, wherein calculating the current adjustment ratio based on the real-time temperature, the puddle depth, the droplet volume, the droplet frequency, the temperature weight, the depth weight, the volume weight, and the frequency weight comprises:

determining current regulation proportions of the real-time temperature, the molten pool depth, the molten drop volume and the molten drop frequency in a preset temperature and current regulation proportion comparison table, a molten pool depth and current regulation proportion comparison table, a molten drop volume and current regulation proportion comparison table and a molten drop frequency and current regulation proportion comparison table respectively to obtain a first current regulation proportion, a second current regulation proportion, a third current regulation proportion and a fourth current regulation proportion;

acquiring an environment real-time temperature, calculating an absolute value of a difference value between the environment real-time temperature and a preset environment standard temperature, and calculating a ratio of the absolute value to the environment standard temperature to be used as a temperature punishment coefficient;

calculating a first difference value between the droplet volume deviation rate and the droplet frequency deviation rate, and calculating a second difference value between a value 1 and the first difference value to serve as a droplet penalty coefficient;

calculating a current regulation proportion by a preset formula, wherein the preset formula is as follows:

I=I1×w1×（1-λ1）+ I2×w2+ I3×w3×（1-λ2）+ I4×w4×（1-λ2）；

7. The method of claim 6, wherein controlling the welding current of the welding robot in accordance with the current adjustment ratio comprises:

calculating the product of the current regulation proportion and a preset reference current to obtain a current regulation quantity;

calculating a sum of the reference current and the current adjustment value to obtain a target welding current;

and adjusting the welding current of the welding robot to the target welding current.

8. Welding current controlling means of robot, its characterized in that, welding robot are provided with welder, first camera, second camera and infrared camera, first camera is located welder is towards one side of welding direction, the second camera is located welder deviates from one side of welding direction includes:

9. An electronic device, the electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the robotic welding current control method of any one of claims 1-7.

10. A computer readable storage medium, characterized in that the computer readable storage medium stores computer instructions for causing a processor to implement the robot welding current control method of any one of claims 1-7 when executed.