KR102550108B1 - Welding defects detecting method using artificial intelligence model in cloud platform - Google Patents

Abstract

According to an embodiment of the present disclosure, a welding defect detection method using a cloud platform is disclosed. Specifically, according to the present disclosure, a computing device learns a welding defect detection model based on initial learning data, generates an auto-labeling tool based on the learned welding defect detection model in the cloud platform, and generates additional images. Upload data to a cloud platform, perform labeling on the additional image data by utilizing the auto labeling tool on the cloud platform, and additionally learn a welding defect detection model based on the labeled additional image data on the cloud platform. and updates the auto labeling tool based on the additionally learned welding defect detection model in the cloud platform.

Description

Welding defect detection method using artificial intelligence model in cloud platform {WELDING DEFECTS DETECTING METHOD USING ARTIFICIAL INTELLIGENCE MODEL IN CLOUD PLATFORM}

The present invention relates to a welding defect detection method using an artificial intelligence model in a cloud platform. It is about how to deploy the model to perform welding defect detection.

Welding between metals relies only on the experience of a skilled welding worker, and since a difference occurs between the capabilities of welding workers, it is difficult to secure stable welding quality. Conventionally, destructive tests such as tensile tests and separation tests have been mainly performed as a method of detecting successful welding and managing welding quality, and a method of measuring the resistance value of bonded electrodes has been used as a non-destructive test. . However, these methods have a problem in that it is difficult to determine in real time whether a welding defect has occurred.

On the other hand, artificial intelligence models are widely used in various fields of industry, such as defective product detection and anomaly detection. AI models trained through deep learning can perform tasks at a higher speed than human workers, and are more sensitive to errors not detected by human workers.

This artificial intelligence model can also be used for the purpose of detecting defects in product welding, but it is difficult to build an effective artificial intelligence model with limited computing resources in a local environment, and users who are not familiar with artificial intelligence model development There is a problem with poor accessibility.

Therefore, there is a demand in the art for a method of effectively detecting welding defects through an artificial intelligence model.

Korean Patent Publication No. 2022-0126248 discloses a welding quality inspection device and a welding quality inspection method.

The present disclosure has been made in response to the above background technology, learning a welding defect detection model on a cloud platform, generating an auto-labeling tool based on the welding defect detection model, and distributing the welding defect detection model to detect welding defects. intended to perform.

On the other hand, the technical problem to be achieved by the present disclosure is not limited to the above-mentioned technical problem, and may include various technical problems within a range apparent to those skilled in the art from the contents to be described below.

According to an embodiment of the present disclosure for realizing the above object, a method for detecting welding defects using a cloud platform by a computing device is disclosed. The method may include learning a welding defect detection model based on initial learning data; generating an auto labeling tool on the cloud platform based on the learned welding defect detection model; Uploading additional image data to a cloud platform; Labeling the additional image data using the auto-labeling tool in the cloud platform; In the cloud platform, additionally learning a welding defect detection model based on the labeled additional image data, and in the cloud platform, updating the auto labeling tool based on the additionally learned welding defect detection model. can include

In one embodiment, the welding defect detection model may be an artificial neural network model that detects welding defects from an image of a welding bead surface.

In one embodiment, the step of learning the welding defect detection model based on the initial training data is: identifying the type of the initial learning data or the task of the welding defect detection model in the cloud platform. step; Based on the identified type or the identified task, identifying an artificial neural network model to be trained among one or more artificial neural network models existing in the cloud platform, and determining the identified artificial neural network model as a welding defect detection model; and The method may include training the welding defect detection model in the cloud platform.

In one embodiment, based on the identified type or the identified task, an artificial neural network model to be trained is identified among one or more artificial neural network models existing in the cloud platform, and the identified artificial neural network model is used as a welding defect detection model. The determining step may include: identifying a plurality of different artificial neural network models on the cloud platform based on the identified type or the identified task; The method may include ensembling the plurality of different artificial neural network models and determining the ensemble model as the welding defect detection model.

In one embodiment, the additional training of a welding defect detection model based on the labeled additional image data in the cloud platform includes: including the labeled additional image data in a training data set in the cloud platform; and and performing additional learning of the welding defect detection model based on the learning data set.

In one embodiment, the updating of the auto labeling tool based on the additionally learned welding defect detection model may include: generating an updated auto labeling tool based on the additionally learned welding defect detection model; The method may include performing performance evaluation on the updated auto labeling tool and updating the auto labeling tool based on the performance evaluation.

In one embodiment, the method may further include deploying the additionally learned welding defect detection model and detecting whether or not there is a welding defect based on the distributed welding defect detection model.

In one embodiment, the welding defect detection model includes a prediction module and a defect detection module, and the step of detecting whether there is a welding defect based on the distributed welding defect detection model includes: using the prediction module, welding Predicting a next frame of an image based on an image obtained by photographing a bead surface; and detecting a defect of the weld bead surface based on a weld bead surface image by utilizing the defect detection module.

In one embodiment, the detecting whether there is a welding defect based on the distributed welding defect detection model includes: collecting welding defect detection information of the product; and generating a welding defect detection database in the cloud platform based on the welding defect detection information.

According to an embodiment of the present disclosure for realizing the above object, a computer program for performing operations for detecting welding defects using a cloud platform is disclosed. The operations may include: learning a welding defect detection model based on initial learning data; generating an auto labeling tool on the cloud platform based on the learned welding defect detection model; Uploading additional image data to a cloud platform; labeling the additional image data by using the auto-labeling tool in the cloud platform; In the cloud platform, an operation of additionally learning a welding defect detection model based on the labeled additional image data and an operation of updating the auto labeling tool based on the additionally trained welding defect detection model.

According to an embodiment of the present disclosure for realizing the above object, a computing device for detecting welding defects using a cloud platform is disclosed. The computing device includes at least one processor and a memory, and the at least one processor includes: training a welding defect detection model based on initial learning data; In the cloud platform, an auto-labeling tool is created based on the learned welding defect detection model, additional image data is uploaded to the cloud platform, and the auto-labeling tool is used in the cloud platform to generate the additional image data. Perform labeling on the cloud platform, additionally learn a welding defect detection model based on the labeled additional image data, and update the auto labeling tool based on the additionally learned welding defect detection model. there is.

The present disclosure may provide a welding defect detection method using a cloud platform. For example, the present disclosure learns a welding defect detection model based on initial learning data, creates an auto-labeling tool based on the learned welding defect detection model in the cloud platform, and generates additional image data. Upload to a cloud platform, perform labeling on the additional image data using the auto labeling tool on the cloud platform, and additionally learn a welding defect detection model based on the labeled additional image data on the cloud platform. and update the auto labeling tool on the cloud platform based on the additionally learned welding defect detection model.

1 is a block diagram of a computing device for performing welding defect detection using a cloud platform according to an embodiment of the present disclosure.
2 is a schematic diagram showing a network function according to an embodiment of the present disclosure.
3 is a flowchart illustrating a process for performing welding defect detection using a cloud platform according to an embodiment of the present disclosure.
4 is a conceptual diagram illustrating the structure of a cloud platform according to an embodiment of the present disclosure.
5 is a conceptual diagram showing the structure of a prediction module according to an embodiment of the present disclosure.
6 is a conceptual diagram illustrating the structure of a failure detection module according to an embodiment of the present disclosure.
7 is a simplified and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

The present disclosure discloses a method of performing welding defect detection by learning a welding defect detection model on a cloud platform, generating an auto labeling tool based on the welding defect detection model, and distributing the welding defect detection model.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the present disclosure. However, it is apparent that these embodiments may be practiced without these specific details.

The terms “component,” “module,” “system,” and the like, as used herein, refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or an execution of software. For example, a component may be, but is not limited to, a procedure, processor, object, thread of execution, program, and/or computer running on a processor. For example, both an application running on a computing device and a computing device may be components. One or more components may reside within a processor and/or thread of execution. A component can be localized within a single computer. A component may be distributed between two or more computers. Also, these components can execute from various computer readable media having various data structures stored thereon. Components may be connected, for example, via signals with one or more packets of data (e.g., data and/or signals from one component interacting with another component in a local system, distributed system) to other systems and over a network such as the Internet. data being transmitted) may communicate via local and/or remote processes.

In addition, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or”. That is, unless otherwise specified or clear from the context, “X employs A or B” is intended to mean one of the natural inclusive substitutions. That is, X uses A; X uses B; Or, if X uses both A and B, "X uses either A or B" may apply to either of these cases. Also, the term "and/or" as used herein should be understood to refer to and include all possible combinations of one or more of the listed related items.

Also, the terms "comprises" and/or "comprising" should be understood to mean that the features and/or components are present. However, it should be understood that the terms "comprises" and/or "comprising" do not exclude the presence or addition of one or more other features, elements, and/or groups thereof. Also, unless otherwise specified or where the context clearly indicates that a singular form is indicated, the singular in this specification and claims should generally be construed to mean "one or more".

In addition, the term “at least one of A or B” should be interpreted as meaning “when only A is included”, “when only B is included”, and “when A and B are combined”.

Those skilled in the art will further understand that the various illustrative logical blocks, components, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be implemented using electronic hardware, computer software, or combinations of both. It should be recognized that it can be implemented as To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented in hardware or as software depends on the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application. However, such implementation decisions should not be interpreted as causing a departure from the scope of this disclosure.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art of this disclosure. The general principles defined herein may be applied to other embodiments without departing from the scope of this disclosure. Thus, the present disclosure is not limited to the embodiments presented herein. This disclosure is to be interpreted in the widest light consistent with the principles and novel features presented herein.

In the present disclosure, a 'welding defect detection model' may refer to an artificial neural network model that detects welding defects from an image of a welding bead surface.

Also, in the present disclosure, a prediction module may refer to an artificial neural network model that predicts the next frame of an image from an image of a weld bead surface.

In addition, in the present disclosure, a defect detection module may refer to an artificial neural network model that detects welding defects from an image of a weld bead surface.

1 is a block diagram of a computing device for performing welding defect detection using a cloud platform according to an embodiment of the present disclosure.

The configuration of the computing device 100 shown in FIG. 1 is only a simplified example. In one embodiment of the present disclosure, the computing device 100 may include other components for performing a computing environment of the computing device 100, and only some of the disclosed components may constitute the computing device 100.

The computing device 100 may include a processor 110 , a memory 130 , and a network unit 150 .

The processor 110 may include one or more cores, and includes a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. unit), data analysis, and processors for deep learning. The processor 110 may read a computer program stored in the memory 130 and process data for machine learning according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor 110 may perform an operation for learning a neural network. The processor 110 is used for neural network learning, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating neural network weights using backpropagation. calculations can be performed.

At least one of the CPU, GPGPU, and TPU of the processor 110 may process learning of the network function. For example, the CPU and GPGPU can process learning of network functions and data classification using network functions. In addition, in an embodiment of the present disclosure, the learning of a network function and data classification using a network function may be processed by using processors of a plurality of computing devices together. In addition, a computer program executed in a computing device according to an embodiment of the present disclosure may be a CPU, GPGPU or TPU executable program.

According to an embodiment of the present disclosure, the processor 110 may obtain input data. The input data may be data stored in the memory 130 of the computing device 100 or data transmitted through the network 150 . In the present disclosure, input data may be image data obtained by photographing a surface of a welding bead. However, in the present disclosure, the path for obtaining input data and the type of input data are not limited to the above examples.

According to an embodiment of the present disclosure, the processor 110 may train a welding defect detection model based on initial learning data. A detailed method of learning a welding defect detection model based on initial learning data will be described later with reference to FIG. 3 .

According to an embodiment of the present disclosure, the processor 110 may generate an auto-labeling tool on the cloud platform based on an initially learned welding defect detection model.

According to an embodiment of the present disclosure, the processor 110 may perform a labeling operation on additional image data by utilizing an auto-labeling tool in a cloud platform. A detailed description of the labeling operation using the auto labeling tool will be described later with reference to FIG. 3 .

According to an embodiment of the present disclosure, the processor 110 may perform additional learning of a welding defect detection model on the cloud platform based on labeled additional image data. A detailed description of performing additional learning of a welding defect detection model based on the labeled additional image data will be described later with reference to FIG. 3 .

According to an embodiment of the present disclosure, the processor 110 may update the auto labeling tool based on the additionally trained welding defect detection model in the cloud platform. In this case, the update method may be a method of replacing an existing auto labeling tool with an additionally learned welding defect detection model. In this case, since the welding defect detection model additionally learned based on the additional image data performs labeling as a new auto labeling tool, better performance than the auto labeling tool before the update can be expected. The processor 110 may improve the performance of the auto labeling tool and the welding defect detection model by repeatedly performing the above-described process in a cloud environment.

The processor 110 stores welding defect detection models for each version, including the initial welding defect detection model and the additionally trained welding defect detection model, in the cloud platform, and updates the auto labeling tool by referring to the welding defect detection models for each version. Weld defect detection models can be deployed. For example, the processor 110 may execute performance evaluation for each version of the welding defect detection model learned in the cloud platform. After that, the processor can distribute the model of the measured version with the highest performance among each version to the equipment in the local environment.

In an embodiment, a processor in a local environment may perform welding defect detection on a weld bead surface by utilizing a distributed welding defect detection model. Also, in the process of detecting welding defects, the processor in the local environment may collect welding defect detection details and create a welding defect detection database in the cloud platform based on the welding defect detection details. At this time, the welding defect detection details may include information such as whether or not a welding defect is included, a ratio of a bead surface including a welding defect, and the accuracy of a welding defect detection model.

By repeating the process of the present disclosure, it is possible to continuously learn a welding defect detection model in a cloud environment and continuously distribute a welding defect detection model with high performance to increase the accuracy of welding defect detection in a local environment.

According to an embodiment of the present disclosure, the memory 130 is a flash memory type, a hard disk type, a multimedia card micro type, or a card type memory (eg, SD or XD memory, etc.), RAM (Random Access Memory, RAM), SRAM (Static Random Access Memory), ROM (Read-Only Memory, ROM), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory) -Only Memory), a magnetic memory, a magnetic disk, and an optical disk may include at least one type of storage medium. The computing device 100 may operate in relation to a web storage that performs a storage function of the memory 130 on the Internet. The above description of the memory is only an example, and the present disclosure is not limited thereto.

The network unit 150 according to an embodiment of the present disclosure includes a Public Switched Telephone Network (PSTN), x Digital Subscriber Line (xDSL), Rate Adaptive DSL (RADSL), Multi Rate DSL (MDSL), and VDSL ( Various wired communication systems such as Very High Speed DSL), Universal Asymmetric DSL (UADSL), High Bit Rate DSL (HDSL), and Local Area Network (LAN) may be used.

In addition, the network unit 150 presented in this specification includes Code Division Multi Access (CDMA), Time Division Multi Access (TDMA), Frequency Division Multi Access (FDMA), Orthogonal Frequency Division Multi Access (OFDMA), SC-FDMA ( Single Carrier-FDMA) and other systems.

In the present disclosure, the network unit 150 may use any type of wired or wireless communication system.

The techniques described herein may be used in the networks mentioned above as well as other networks.

2 is a schematic diagram showing a network function according to an embodiment of the present disclosure.

Throughout this specification, the terms computational model, neural network, network function, and neural network may be used interchangeably. A neural network may consist of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network includes one or more nodes. Nodes (or neurons) constituting neural networks may be interconnected by one or more links.

In a neural network, one or more nodes connected through a link may form a relative relationship of an input node and an output node. The concept of an input node and an output node is relative, and any node in an output node relationship with one node may have an input node relationship with another node, and vice versa. As described above, an input node to output node relationship may be created around a link. More than one output node can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of data of the output node may be determined based on data input to the input node. Here, a link interconnecting an input node and an output node may have a weight. The weight may be variable, and may be changed by a user or an algorithm in order to perform a function desired by the neural network. For example, when one or more input nodes are interconnected by respective links to one output node, the output node is set to a link corresponding to values input to input nodes connected to the output node and respective input nodes. An output node value may be determined based on the weight.

As described above, in the neural network, one or more nodes are interconnected through one or more links to form an input node and output node relationship in the neural network. Characteristics of the neural network may be determined according to the number of nodes and links in the neural network, an association between the nodes and links, and a weight value assigned to each link. For example, when there are two neural networks having the same number of nodes and links and different weight values of the links, the two neural networks may be recognized as different from each other.

A neural network may be composed of a set of one or more nodes. A subset of nodes constituting a neural network may constitute a layer. Some of the nodes constituting the neural network may form one layer based on distances from the first input node. For example, a set of nodes having a distance of n from the first input node may constitute n layers. The distance from the first input node may be defined by the minimum number of links that must be passed through to reach the corresponding node from the first input node. However, the definition of such a layer is arbitrary for explanation, and the order of a layer in a neural network may be defined in a method different from the above. For example, a layer of nodes may be defined by a distance from a final output node.

An initial input node may refer to one or more nodes to which data is directly input without going through a link in relation to other nodes among nodes in the neural network. Alternatively, in a relationship between nodes based on a link in a neural network, it may mean nodes that do not have other input nodes connected by a link. Similarly, the final output node may refer to one or more nodes that do not have an output node in relation to other nodes among nodes in the neural network. Also, the hidden node may refer to nodes constituting the neural network other than the first input node and the last output node.

In the neural network according to an embodiment of the present disclosure, the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes decreases and then increases again as the number of nodes progresses from the input layer to the hidden layer. can In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes of the input layer may be less than the number of nodes of the output layer and the number of nodes decreases as the number of nodes increases from the input layer to the hidden layer. there is. In addition, the neural network according to another embodiment of the present disclosure is a neural network in which the number of nodes in the input layer may be greater than the number of nodes in the output layer, and the number of nodes increases as the number of nodes increases from the input layer to the hidden layer. can A neural network according to another embodiment of the present disclosure may be a neural network in the form of a combination of the aforementioned neural networks.

A deep neural network (DNN) may refer to a neural network including a plurality of hidden layers in addition to an input layer and an output layer. Deep neural networks can reveal latent structures in data. In other words, it can identify the latent structure of a photo, text, video, sound, or music (e.g., what objects are in the photo, what the content and emotion of the text are, what the content and emotion of the audio are, etc.). . Deep neural networks include convolutional neural networks (CNNs), recurrent neural networks (RNNs), auto encoders, generative adversarial networks (GANs), and restricted boltzmann machines (RBMs). machine), a deep belief network (DBN), a Q network, a U network, a Siamese network, a Generative Adversarial Network (GAN), and the like. The description of the deep neural network described above is only an example, and the present disclosure is not limited thereto.

In one embodiment of the present disclosure, the network function may include an autoencoder. An autoencoder may be a type of artificial neural network for outputting output data similar to input data. An auto-encoder may include at least one hidden layer, and an odd number of hidden layers may be disposed between input and output layers. The number of nodes of each layer may be reduced from the number of nodes of the input layer to an intermediate layer called the bottleneck layer (encoding), and then expanded symmetrically with the reduction from the bottleneck layer to the output layer (symmetrical to the input layer). Autoencoders can perform non-linear dimensionality reduction. The number of input layers and output layers may correspond to dimensions after preprocessing of input data. In the auto-encoder structure, the number of hidden layer nodes included in the encoder may decrease as the distance from the input layer increases. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) is too small, a sufficient amount of information may not be conveyed, so more than a certain number (e.g., more than half of the input layer, etc.) ) may be maintained.

The neural network may be trained using at least one of supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Learning of the neural network may be a process of applying knowledge for the neural network to perform a specific operation to the neural network.

A neural network can be trained in a way that minimizes output errors. In the learning of the neural network, the learning data is repeatedly input into the neural network, the output of the neural network for the training data and the error of the target are calculated, and the error of the neural network is transferred from the output layer of the neural network to the input layer in the direction of reducing the error. It is a process of updating the weight of each node of the neural network by backpropagating in the same direction. In the case of teacher learning, the learning data in which the correct answer is labeled is used for each learning data (ie, the labeled learning data), and in the case of comparative teacher learning, the correct answer may not be labeled in each learning data. That is, for example, learning data in the case of teacher learning about data classification may be data in which each learning data is labeled with a category. Labeled training data is input to a neural network, and an error may be calculated by comparing an output (category) of the neural network and a label of the training data. As another example, in the case of comparative history learning for data classification, an error may be calculated by comparing input learning data with a neural network output. The calculated error is back-propagated in a reverse direction (ie, from the output layer to the input layer) in the neural network, and the connection weight of each node of each layer of the neural network may be updated according to the back-propagation. The amount of change in the connection weight of each updated node may be determined according to a learning rate. The neural network's computation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently according to the number of iterations of the learning cycle of the neural network. For example, a high learning rate may be used in the early stage of neural network training to increase efficiency by allowing the neural network to quickly obtain a certain level of performance, and a low learning rate may be used in the late stage to increase accuracy.

In neural network learning, generally, training data can be a subset of real data (ie, data to be processed using the trained neural network), and therefore, errors for training data are reduced, but errors for real data are reduced. There may be incremental learning cycles. Overfitting is a phenomenon in which errors for actual data increase due to excessive learning on training data. For example, a phenomenon in which a neural network that has learned a cat by showing a yellow cat does not recognize that it is a cat when it sees a cat other than yellow may be a type of overfitting. Overfitting can act as a cause of increasing the error of machine learning algorithms. Various optimization methods can be used to prevent such overfitting. To prevent overfitting, methods such as increasing the training data, regularization, inactivating some nodes in the network during learning, and using a batch normalization layer should be applied. can

3 is a flowchart illustrating a process for performing welding defect detection using a cloud platform according to an embodiment of the present disclosure.

According to FIG. 3, the process of performing welding defect detection using the cloud platform of the present disclosure is to learn a welding defect detection model based on initial learning data (S310), and to use the learned welding defect detection model in the cloud platform. Creating an auto-labeling tool as a basis (S320), uploading additional image data to the cloud platform (S330), and learning a welding defect detection model based on the labeled additional image data in the cloud platform. (S330), performing labeling on additional image data using an auto-labeling tool on the cloud platform (S340), additionally learning a welding defect detection model based on the labeled additional image data on the cloud platform ( S350) and updating the auto labeling tool based on the additionally learned welding defect detection model in the cloud platform (S360).

In step S310, the processor 110 may acquire initial learning data. In this case, the initial learning data may be image data obtained by photographing a welding bead surface labeled with defects in welding. After that, the processor uploads the initial training data to the cloud platform, so that it can be used to learn the welding defect detection model. By initial learning, the welding defect detection model can detect whether the image of the weld bead surface contains defects.

The processor 110 may perform welding defect detection among one or more artificial neural network models existing in the cloud platform based on the type of initial input data identified among the artificial neural network models existing in the cloud platform or the task of the welding defect detection model. Artificial neural network models can be identified.

For example, the processor 110 may identify an artificial neural network model in an initial state that has not been trained and determine it as a welding defect detection model.

Unlike this, the processor 110 may identify an artificial neural network model associated with an identified type or task among one or more artificial neural network models existing in the cloud platform and determine it as a welding defect detection model. In the cloud platform of the present disclosure, a plurality of artificial neural network models already trained by the current user or other users to perform other tasks may exist. The processor 110 may identify a model suitable for processing input data or a model suitable for performing a current task among these models.

For example, when the input data is 'image of a weld bead surface' and the task is 'detection of welding defects', the processor 110 performs the same task as 'detection of welding defects' among various neural network models already existing on the cloud platform. can identify a model that performs Then, the processor 110 may determine the corresponding artificial neural network model as a welding defect detection model.

In addition, when a plurality of artificial neural network models exist in the cloud platform that are determined to be suitable for performing the task identified by the processor 110, the processor 110 performs an artificial neural network ensemble of outputs of the plurality of corresponding artificial neural network models. can be configured. Then, the processor 110 may determine the ensemble artificial neural network model as a welding defect detection model.

However, in the present disclosure, a method for identifying an artificial neural network model to be trained among artificial neural network models existing in a cloud platform is not limited to the above example, and various criteria for generating a suitable welding defect detection model may be used.

As described above, the welding defect detection model determined by the processor 110 may be learned based on the initial learning data.

In step S320, the processor 110 may generate an auto labeling tool based on the learned welding defect detection model in the cloud platform. Since the welding defect detection model is a model learned to detect whether a product image includes a defect, it can be used as a model that labels whether a product image includes a defect, that is, an auto-labeling tool.

In step S330, the processor 110 may upload additional image data to the cloud platform. In this case, the additional image data may be an image of the product, and may be used as training data of a welding defect detection model after labeling.

In step S340, the processor 110 may label additional image data by using an auto-labeling tool in the cloud platform.

For example, when the input data is 'image of a welding bead surface' and the task is 'detection of welding defects', the auto labeling tool detects whether each input image has a welding defect and performs labeling on each image data. can do.

In step S350, the processor 110 may perform additional learning of a welding defect detection model on the cloud platform based on the labeled additional image data.

In addition, in the additional learning of the welding defect detection model, the additional image data itself labeled by the auto labeling tool in step S340 can be used as a training data set, and in step S340 to the training data set previously existing in the cloud platform. Additional labeled image data can be added to form a new training data set.

In step S360, the processor 110 may update the auto labeling tool based on the additionally learned welding defect detection model in the cloud platform.

For example, the update may be performed by replacing an auto labeling tool stored in a specific server of the cloud platform with an additionally trained welding defect detection model.

As another example, the processor 110 generates an ensemble model of the additionally learned welding defect detection model and the output of an existing version of the auto labeling tool, and then ensembles the existing auto labeling tool. The model can be updated.

The welding defect detection model can perform the same task as the auto labeling tool, and corresponds to a model additionally learned by input data labeled by the auto labeling tool, that is, new training data.

Accordingly, when the auto labeling tool is updated based on the additionally learned welding defect detection model, the performance of the auto labeling tool may be higher than before and additional input data may be better labeled.

However, the method of updating the auto labeling tool based on the welding defect detection model learned in the present disclosure is not limited to the replacement method and the ensemble method exemplified above.

After updating the auto labeling tool based on the welding defect detection model, the processor 110 may grow the auto labeling tool by repeating the same process.

For example, when another image data is input to the local environment, the processor 110 detects whether the image data includes a defect using a welding defect detection model, and then transfers at least some of the added image data to the cloud. can be uploaded to the environment. Thereafter, the updated auto labeling tool may label new image data, and may go through a process of retraining a welding defect detection model with the labeled additional image data. Therefore, the welding defect detection model and the auto labeling tool can be continuously updated and grown by repeating the above process.

In the process of updating the auto-labeling tool based on the learned welding defect detection model, the processor 110 determines the learned welding defect detection model as a new version of the existing auto-labeling tool, and transfers each version to the cloud platform. can be saved Each version of the auto-labeling tool, some of which may be used to update the model in the future, or to perform tasks requested by other users or to process other kinds of input data.

For example, the processor 110 may identify a welding defect detection model of the latest version existing in the cloud platform, and determine the identified welding defect detection model of the latest version as an auto labeling tool. In addition, the processor 110 identifies a previous version of the welding defect detection model existing in the cloud platform (when it is analyzed that the recently added training data has caused a negative learning result such as overfitting, based on the performance evaluation) and the identified welding defect detection model of the previous version can be determined by the auto labeling tool.

As in the present disclosure, by continuously updating the welding defect detection model and the auto labeling tool in the cloud platform, it is possible to easily generate a necessary welding defect detection model locally regardless of limited resources in a local computing environment.

4 is a conceptual diagram illustrating the structure of a cloud platform according to an embodiment of the present disclosure.

When the input data 410 is input to the local device 420 , the local device 420 may upload the input data to the cloud platform 430 . Thereafter, the processor 110 of the cloud platform may identify a type of input data or a task of a welding defect detection model based on analyzing the input data 410 .

The processor 110 may generate labeled input data 433 by using the auto labeling tool 432 .

Thereafter, the processor 110 may include the labeled input data 433 in training data to additionally train the welding defect detection model 434 . A detailed method of additionally learning the welding defect detection model has been described above with reference to FIG. 3 .

The processor 110 may evaluate the performance of the welding defect detection model through the performance evaluation unit 435 . At this time, the processor may not update the auto labeling tool if the welding defect detection model does not meet the performance evaluation standard. In contrast, when the learned welding defect detection model satisfies the performance evaluation criteria, the processor 110 creates a new auto-labeling tool 432 based on the welding defect detection model 434, and updates the existing auto-labeling tool. can do.

By continuously inputting new input data 410 into the local equipment 420 and repeating the above process, the welding defect detection model is continuously learned with new learning data to improve performance, and as a result, the welding defect detection model is based on The performance of the updated auto labeling tool can also be improved.

When performance of the continuously learned welding defect detection model satisfies a predetermined criterion, the processor 110 may distribute the welding defect detection model to the local equipment 420 . Since the welding defect detection model is sufficiently trained in the cloud environment, the welding defect detection model can properly perform tasks with respect to new input data.

In the present disclosure, the process of continuously learning the auto labeling tool and the welding defect detection model is all performed on the cloud platform, so it is possible to obtain an artificial neural network model that can achieve the purpose without being limited by computing resources in the local environment, and Artificial neural networks existing on the platform are recycled, which has the effect of reducing the cost required for initial learning.

Hereinafter, an exemplary structure of the welding defect detection model of the present disclosure is disclosed. In one embodiment of the present disclosure, the welding defect detection model may include a prediction module and a defect detection module.

5 is a conceptual diagram showing the structure of a prediction module according to an embodiment of the present disclosure.

The structure of the prediction module shown in FIG. 5 is exemplary, and artificial neural network models of other structures may be used to achieve the same purpose.

In one embodiment of the present disclosure, the processor 110 may generate a prediction value 520 for a next frame of an image of a bead surface captured based on an image 510 of a weld bead surface by utilizing a prediction module. there is. Specifically, the processor 110 may extract feature values from each frame of the image 510 in which the welding bead surface is photographed by utilizing a feature extraction network such as a convolutional neural network included in the prediction module. Thereafter, the processor 110 generates a feature vector set of the image from the feature values using the prediction module, and uses a bidirectional long-short term memory (BiLSTM) and a fully connected layer ), it is possible to generate a predicted value 520 for the next frame of the image in which the bead surface is photographed.

6 is a conceptual diagram illustrating the structure of a failure detection module according to an embodiment of the present disclosure.

The structure of the defect detection module shown in FIG. 6 is exemplary, and artificial neural network models with other structures may be used to achieve the same purpose.

In one embodiment of the present disclosure, the processor 110 may detect welding defects from the image 610 of the weld bead surface by utilizing the defect detection module. Specifically, the processor 110 extracts a feature vector from the image of the weld bead surface using a convolutional neural network included in the defect detection module and passes it through a fully connected layer to detect the weld bead. The noodle image 610 may be classified as 'normal (OK)' or 'poor (NG)'.

By combining the prediction module and the defect detection module, the welding defect detection model of the present disclosure can predict a next frame from an image of a weld bead surface and detect welding defects from the predicted frame. Therefore, the welding defect detection model can detect defects in real time by predicting the progress of welding without detecting defects ex post by analyzing a given image after welding is completed. As a result, it is possible to detect welding defects more efficiently through the configuration of the welding defect detection model of the present disclosure.

Meanwhile, a computer readable medium storing a data structure according to an embodiment of the present disclosure is disclosed.

Data structure can refer to the organization, management, and storage of data that enables efficient access and modification of data. Data structure may refer to the organization of data to solve a specific problem (eg, data retrieval, data storage, data modification in the shortest time). A data structure may be defined as a physical or logical relationship between data elements designed to support a specific data processing function. A logical relationship between data elements may include a connection relationship between user-defined data elements. A physical relationship between data elements may include an actual relationship between data elements physically stored in a computer-readable storage medium (eg, a persistent storage device). The data structure may specifically include a set of data, a relationship between data, and a function or command applicable to the data. Through an effectively designed data structure, a computing device can perform calculations while using minimal resources of the computing device. Specifically, the computing device can increase the efficiency of operation, reading, insertion, deletion, comparison, exchange, and search through an effectively designed data structure.

The data structure can be divided into a linear data structure and a non-linear data structure according to the shape of the data structure. A linear data structure may be a structure in which only one data is connected after one data. Linear data structures may include lists, stacks, queues, and decks. A list may refer to a series of data sets in which order exists internally. The list may include a linked list. A linked list may be a data structure in which data are connected in such a way that each data is connected in a single line with a pointer. In a linked list, a pointer can contain information about connection to the next or previous data. A linked list can be expressed as a singly linked list, a doubly linked list, or a circular linked list depending on the form. A stack can be a data enumeration structure that allows limited access to data. A stack can be a linear data structure in which data can be processed (eg, inserted or deleted) at only one end of the data structure. The data stored in the stack may be a LIFO-Last in First Out (Last in First Out) data structure. A queue is a data listing structure that allows limited access to data, and unlike a stack, it can be a data structure (FIFO-First in First Out) in which data stored later comes out later. A deck can be a data structure that can handle data from either end of the data structure.

The nonlinear data structure may be a structure in which a plurality of data are connected after one data. The non-linear data structure may include a graph data structure. A graph data structure can be defined as a vertex and an edge, and an edge can include a line connecting two different vertices. A graph data structure may include a tree data structure. The tree data structure may be a data structure in which one path connects two different vertices among a plurality of vertices included in the tree. That is, it may be a data structure that does not form a loop in a graph data structure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. Hereinafter, a neural network is unified and described. The data structure may include a neural network. And the data structure including the neural network may be stored in a computer readable medium. The data structure including the neural network may also include preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation function associated with each node or layer of the neural network, and neural network It may include a loss function for learning of . A data structure including a neural network may include any of the components described above. That is, the data structure including the neural network includes preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation function associated with each node or layer of the neural network, and neural network. It may be configured to include all or any combination thereof, such as a loss function for learning of . In addition to the foregoing configurations, the data structure comprising the neural network may include any other information that determines the characteristics of the neural network. In addition, the data structure may include all types of data used or generated in the computational process of the neural network, but is not limited to the above. A computer readable medium may include a computer readable recording medium and/or a computer readable transmission medium. A neural network may consist of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network includes one or more nodes.

The data structure may include data input to the neural network. A data structure including data input to the neural network may be stored in a computer readable medium. Data input to the neural network may include training data input during a neural network learning process and/or input data input to a neural network that has been trained. Data input to the neural network may include pre-processed data and/or data subject to pre-processing. Pre-processing may include a data processing process for inputting data to a neural network. Accordingly, the data structure may include data subject to pre-processing and data generated by pre-processing. The foregoing data structure is only an example, and the present disclosure is not limited thereto.

The data structure may include the weights of the neural network. (In this specification, weights and parameters may be used in the same meaning.) Also, a data structure including weights of a neural network may be stored in a computer readable medium. A neural network may include a plurality of weights. The weight may be variable, and may be changed by a user or an algorithm in order to perform a function desired by the neural network. For example, when one or more input nodes are interconnected by respective links to one output node, the output node is set to a link corresponding to values input to input nodes connected to the output node and respective input nodes. A data value output from an output node may be determined based on the weight. The foregoing data structure is only an example, and the present disclosure is not limited thereto.

As a non-limiting example, the weights may include weights that are varied during neural network training and/or weights for which neural network training has been completed. The variable weight in the neural network learning process may include a weight at the time the learning cycle starts and/or a variable weight during the learning cycle. The weights for which neural network learning has been completed may include weights for which learning cycles have been completed. Accordingly, the data structure including the weights of the neural network may include a data structure including weights that are variable during the neural network learning process and/or weights for which neural network learning is completed. Therefore, it is assumed that the above-described weights and/or combinations of weights are included in the data structure including the weights of the neural network. The foregoing data structure is only an example, and the present disclosure is not limited thereto.

The data structure including the weights of the neural network may be stored in a computer readable storage medium (eg, a memory or a hard disk) after going through a serialization process. Serialization can be the process of converting a data structure into a form that can be stored on the same or another computing device and later reconstructed and used. A computing device may serialize data structures to transmit and receive data over a network. The data structure including the weights of the serialized neural network may be reconstructed on the same computing device or another computing device through deserialization. The data structure including the weights of the neural network is not limited to serialization. Furthermore, the data structure including the weights of the neural network is a data structure for increasing the efficiency of operation while minimizing the resource of the computing device (for example, B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree). The foregoing is only an example, and the present disclosure is not limited thereto.

The data structure may include hyper-parameters of the neural network. Also, the data structure including the hyperparameters of the neural network may be stored in a computer readable medium. A hyperparameter may be a variable variable by a user. Hyperparameters include, for example, learning rate, cost function, number of learning cycle iterations, weight initialization (eg, setting the range of weight values to be targeted for weight initialization), hidden unit number (eg, the number of hidden layers and the number of nodes in the hidden layer). The foregoing data structure is only an example, and the present disclosure is not limited thereto.

7 is a simplified and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

Although the present disclosure has been described above as being generally embodied by a computing device, those skilled in the art will understand that the present disclosure may be combined with computer-executable instructions and/or other program modules that may be executed on one or more computers and/or may be implemented in hardware and software. It will be appreciated that it can be implemented as a combination.

Generally, program modules include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In addition, those skilled in the art will understand that the methods of the present disclosure can be applied to single-processor or multiprocessor computer systems, minicomputers, mainframe computers as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, and the like ( It will be appreciated that each of these may be implemented with other computer system configurations, including those that may be operative in connection with one or more associated devices.

The described embodiments of the present disclosure may also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Computers typically include a variety of computer readable media. Computer readable media can be any medium that can be accessed by a computer, including volatile and nonvolatile media, transitory and non-transitory media, removable and non-transitory media. Includes removable media. By way of example, and not limitation, computer readable media may include computer readable storage media and computer readable transmission media. Computer readable storage media are volatile and nonvolatile media, transitory and non-transitory, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. includes media Computer readable storage media may include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage device, magnetic cassette, magnetic tape, magnetic disk storage device or other magnetic storage device. device, or any other medium that can be accessed by a computer and used to store desired information.

A computer readable transmission medium typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism. Including all information delivery media. The term modulated data signal means a signal that has one or more of its characteristics set or changed so as to encode information within the signal. By way of example, and not limitation, computer readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer readable transmission media.

An exemplary environment 1100 implementing various aspects of the present disclosure is shown including a computer 1102, which includes a processing unit 1104, a system memory 1106, and a system bus 1108. do. System bus 1108 couples system components, including but not limited to system memory 1106 , to processing unit 1104 . Processing unit 1104 may be any of a variety of commercially available processors. Dual processor and other multiprocessor architectures may also be used as the processing unit 1104.

System bus 1108 may be any of several types of bus structures that may additionally be interconnected to a memory bus, a peripheral bus, and a local bus using any of a variety of commercial bus architectures. System memory 1106 includes read only memory (ROM) 1110 and random access memory (RAM) 1112 . A basic input/output system (BIOS) is stored in non-volatile memory 1110, such as ROM, EPROM, or EEPROM, and is a basic set of information that helps transfer information between components within computer 1102, such as during startup. contains routines. RAM 1112 may also include high-speed RAM, such as static RAM, for caching data.

The computer 1102 may also include an internal hard disk drive (HDD) 1114 (eg, EIDE, SATA) - the internal hard disk drive 1114 may also be configured for external use within a suitable chassis (not shown). Yes—a magnetic floppy disk drive (FDD) 1116 (e.g., for reading from or writing to a removable diskette 1118), and an optical disk drive 1120 (e.g., a CD-ROM) for reading disc 1122 or reading from or writing to other high capacity optical media such as DVDs). The hard disk drive 1114, magnetic disk drive 1116, and optical disk drive 1120 are connected to the system bus 1108 by a hard disk drive interface 1124, magnetic disk drive interface 1126, and optical drive interface 1128, respectively. ) can be connected to The interface 1124 for external drive implementation includes at least one or both of USB (Universal Serial Bus) and IEEE 1394 interface technologies.

These drives and their associated computer readable media provide non-volatile storage of data, data structures, computer executable instructions, and the like. In the case of computer 1102, drives and media correspond to storing any data in a suitable digital format. Although the description of computer readable media above refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art can use zip drives, magnetic cassettes, flash memory cards, cartridges, etc. It will be appreciated that other tangible media readable by the computer, such as the like, may also be used in the exemplary operating environment and any such media may include computer executable instructions for performing the methods of the present disclosure.

A number of program modules may be stored on the drive and RAM 1112, including an operating system 1130, one or more application programs 1132, other program modules 1134, and program data 1136. All or portions of the operating system, applications, modules and/or data may also be cached in RAM 1112. It will be appreciated that the present disclosure may be implemented in a variety of commercially available operating systems or combinations of operating systems.

A user may enter commands and information into the computer 1102 through one or more wired/wireless input devices, such as a keyboard 1138 and a pointing device such as a mouse 1140. Other input devices (not shown) may include a microphone, IR remote control, joystick, game pad, stylus pen, touch screen, and the like. Although these and other input devices are often connected to the processing unit 1104 through an input device interface 1142 that is connected to the system bus 1108, a parallel port, IEEE 1394 serial port, game port, USB port, IR interface, may be connected by other interfaces such as the like.

A monitor 1144 or other type of display device is also connected to the system bus 1108 through an interface such as a video adapter 1146. In addition to the monitor 1144, computers typically include other peripheral output devices (not shown) such as speakers, printers, and the like.

Computer 1102 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 1148 via wired and/or wireless communications. Remote computer(s) 1148 may be a workstation, computing device computer, router, personal computer, handheld computer, microprocessor-based entertainment device, peer device, or other common network node, and generally includes It includes many or all of the components described for, but for simplicity, only memory storage device 1150 is shown. The logical connections shown include wired/wireless connections to a local area network (LAN) 1152 and/or a larger network, such as a wide area network (WAN) 1154 . Such LAN and WAN networking environments are common in offices and corporations and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to worldwide computer networks, such as the Internet.

When used in a LAN networking environment, computer 1102 connects to local network 1152 through wired and/or wireless communication network interfaces or adapters 1156. Adapter 1156 may facilitate wired or wireless communications to LAN 1152, which also includes a wireless access point installed therein to communicate with wireless adapter 1156. When used in a WAN networking environment, computer 1102 may include a modem 1158, be connected to a communicating computing device on WAN 1154, or establish communications over WAN 1154, such as over the Internet. have other means. A modem 1158, which may be internal or external and a wired or wireless device, is connected to the system bus 1108 through a serial port interface 1142. In a networked environment, program modules described for computer 1102, or portions thereof, may be stored on remote memory/storage device 1150. It will be appreciated that the network connections shown are exemplary and other means of establishing a communication link between computers may be used.

Computer 1102 is any wireless device or entity that is deployed and operating in wireless communication, eg, printers, scanners, desktop and/or portable computers, portable data assistants (PDAs), communication satellites, wireless detectable tags associated with It operates to communicate with arbitrary equipment or places and telephones. This includes at least Wi-Fi and Bluetooth wireless technologies. Thus, the communication may be a predefined structure as in conventional networks or simply an ad hoc communication between at least two devices.

Wi-Fi (Wireless Fidelity) makes it possible to connect to the Internet without wires. Wi-Fi is a wireless technology, such as a cell phone, that allows such devices, eg, computers, to transmit and receive data both indoors and outdoors, i.e. anywhere within coverage of a base station. Wi-Fi networks use a radio technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 and 5 GHz radio bands, for example, at 11 Mbps (802.11a) or 54 Mbps (802.11b) data rates, or in products that include both bands (dual band) .

Those skilled in the art will understand that information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, instructions, information, signals, bits, symbols and chips that may be referenced in the above description are voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields s or particles, or any combination thereof.

Those skilled in the art will understand that the various illustrative logical blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein are electronic hardware, (for convenience) , may be implemented by various forms of program or design code (referred to herein as software) or a combination of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and the design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

Various embodiments presented herein may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques. The term article of manufacture includes a computer program, carrier, or media accessible from any computer-readable storage device. For example, computer-readable storage media include magnetic storage devices (eg, hard disks, floppy disks, magnetic strips, etc.), optical disks (eg, CDs, DVDs, etc.), smart cards, and flash memory devices (eg, EEPROM, cards, sticks, key drives, etc.), but are not limited thereto. Additionally, various storage media presented herein include one or more devices and/or other machine-readable media for storing information.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of example approaches. Based upon design priorities, it is to be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of this disclosure. The accompanying method claims present elements of the various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art of this disclosure, and the general principles defined herein may be applied to other embodiments without departing from the scope of this disclosure. Thus, the present disclosure is not to be limited to the embodiments presented herein, but is to be interpreted in the widest scope consistent with the principles and novel features presented herein.

Claims (11)

A method performed by a computing device to detect welding defects using a cloud platform,
learning a welding defect detection model based on the initial learning data;
generating an auto labeling tool on the cloud platform based on the learned welding defect detection model;
Uploading additional image data to a cloud platform;
Labeling the additional image data using the auto-labeling tool in the cloud platform;
additionally learning a welding defect detection model based on the labeled additional image data in the cloud platform; and
updating the auto labeling tool on the cloud platform based on the additionally learned welding defect detection model;
including,
Based on the initial training data, the step of learning a welding defect detection model is:
identifying a type of the initial learning data or a task of the welding defect detection model in the cloud platform;
identifying at least some artificial neural network models among one or more artificial neural network models existing in the cloud platform, based on the identified type or the identified task;
generating a welding defect detection model based on the identified artificial neural network model; and
In the cloud platform, learning the welding defect detection model based on the initial learning data;
including,
method.
According to claim 1,
The welding defect detection model,
An artificial neural network model that detects welding defects from an image taken of a welding bead surface,
method.
delete According to claim 1,
Generating a welding defect detection model based on the identified artificial neural network model:
If the identified artificial neural network model is a plurality of different artificial neural network models, ensembling the plurality of different artificial neural network models; and
determining the ensemble model as the welding defect detection model;
including,
method.
According to claim 1,
In the cloud platform, additionally learning a welding defect detection model based on the labeled additional image data:
In the cloud platform, including the labeled additional image data in a training data set; and
performing additional learning of the welding defect detection model based on the learning data set;
including,
method.
According to claim 1,
Updating the auto labeling tool based on the additionally learned welding defect detection model includes:
generating an updated auto labeling tool based on the additionally learned welding defect detection model;
performing performance evaluation on the updated auto labeling tool; and
updating the auto labeling tool based on the performance evaluation;
including,
method.
According to claim 1,
deploying the additionally learned welding defect detection model; and
Detecting welding defects based on the distributed welding defect detection model:
Including more,
method.
According to claim 7,
The welding defect detection model,
Includes a prediction module and a defect detection module;
Based on the distributed welding defect detection model, the step of detecting whether or not there is a welding defect is:
predicting a next frame of an image based on an image of a weld bead surface by using the prediction module; and
detecting a defect of the weld bead surface based on a weld bead surface image by using the defect detection module;
including,
method.
According to claim 7,
Based on the distributed welding defect detection model, the step of detecting whether or not there is a welding defect is:
Collecting welding defect detection details; and
generating a welding defect detection database in the cloud platform based on the welding defect detection details;
Including more,
method.
A computer program stored on a computer-readable storage medium, the computer program causing at least one processor to perform operations for detecting welding defects using a cloud platform, the operations comprising:
learning a welding defect detection model based on the initial learning data;
generating an auto labeling tool on the cloud platform based on the learned welding defect detection model;
Uploading additional image data to a cloud platform;
labeling the additional image data by using the auto-labeling tool in the cloud platform;
additionally learning a welding defect detection model based on the labeled additional image data in the cloud platform; and
updating the auto labeling tool based on the additionally learned welding defect detection model;
including,
Based on the initial training data, the operation of learning a welding defect detection model is:
identifying a type of the initial learning data or a task of the welding defect detection model in the cloud platform;
identifying at least some artificial neural network models among one or more artificial neural network models existing in the cloud platform, based on the identified type or the identified task;
generating a welding defect detection model based on the identified artificial neural network model; and
learning the welding defect detection model based on the initial learning data in the cloud platform;
including,
A computer program stored on a computer readable storage medium.
As a computing device,
at least one processor; and
Memory;
including,
The at least one processor is:
learning a welding defect detection model based on the initial learning data;
In a cloud platform, based on the learned welding defect detection model, an auto labeling tool is created,
Upload additional video data to the cloud platform,
In the cloud platform, labeling of the additional image data is performed using the auto labeling tool,
In the cloud platform, additionally learning a welding defect detection model based on the labeled additional image data, and
Based on the additionally learned welding defect detection model, update the auto labeling tool,
Based on the initial training data, training a welding defect detection model is:
In the cloud platform, identifying the type of the initial learning data or the task of the welding defect detection model;
identifying at least some artificial neural network models among one or more artificial neural network models existing in the cloud platform, based on the identified type or the identified task;
generating a welding defect detection model based on the identified artificial neural network model; and
In the cloud platform, learning the welding defect detection model based on the initial learning data;
including,
computing device.

Images