Method, equipment, medium and program product for constructing welding quality detection model

Abstract

The purpose of the present application is to provide a method, device, medium and program product for constructing a welding quality detection model, the method comprising: obtaining welding process data within a target time period in welding production through a target sensor; determining a plurality of welding sample data based on the welding process data, and determining a feature vector corresponding to each welding sample data in the plurality of welding sample data; determining a welding defect rate in the welding production within the target time period; and obtaining a welding quality detection model and a path length threshold corresponding to the welding quality detection model by training using an isolation forest algorithm based on the feature vector corresponding to each welding sample data in the plurality of welding sample data and the welding defect rate. This eliminates the need to label and measure the sample data, saves labor costs in model construction, avoids the reduction in model accuracy due to manual labeling errors, and facilitates project implementation.

Description

Technical Field

[0001] The present application relates to the field of welding technology, and in particular to a technology for constructing a welding quality detection model. Background Art

[0002] In recent years, intelligent online welding quality detection has become a key research area for universities and institutions. For example, variations in arc energy can cause defects, and arc sound is generated by the periodic changes in the welding arc energy. Speech recognition algorithms are used to identify arc sound characteristics and determine welding quality. Using weld pool images and image processing methods, methods are proposed to determine the weld pool contour and characteristic parameters. Alternatively, a fusion algorithm can be used to comprehensively determine weld quality based on spectral, voltage, acoustic, and visual information. However, in actual industrial environments, these solutions are difficult to implement due to factors such as interference sources on the welding site and the cost of welding quality testing. Summary of the Invention

[0003] One purpose of this application is to provide a method, device, medium and program product for constructing a welding quality detection model.

[0004] According to one aspect of the present application, a method for constructing a welding quality detection model is provided, the method comprising:

[0005] Acquire welding process data within a target time period during welding production through target sensors;

[0006] Determine a plurality of welding sample data according to the welding process data, and determine a feature vector corresponding to each welding sample data in the plurality of welding sample data;

[0007] determining a welding defect rate in the welding production within the target time period;

[0008] According to the characteristic vector corresponding to each welding sample data in the multiple welding sample data and the welding defect rate, the isolation forest algorithm is used to train to obtain a welding quality detection model and a path length threshold corresponding to the welding quality detection model.

[0009] According to one aspect of the present application, a computer device for constructing a welding quality detection model is provided, comprising a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0010] According to one aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the steps of any of the methods described above are implemented.

[0011] According to one aspect of the present application, a computer program product is provided, comprising a computer program, wherein the computer program implements the steps of any of the above methods when executed by a processor.

[0012] According to one aspect of the present application, there is provided a device for constructing a welding quality detection model, the device comprising:

[0013] A module is used to obtain welding process data within a target time period in welding production through a target sensor;

[0014] Module one and module two, configured to determine a plurality of welding sample data according to the welding process data, and determine a feature vector corresponding to each welding sample data in the plurality of welding sample data;

[0015] A third module is used to determine the welding defect rate in the welding production within the target time period;

[0016] A fourth module is used to obtain a welding quality detection model and a path length threshold corresponding to the welding quality detection model by using an isolation forest algorithm to train according to the characteristic vector corresponding to each welding sample data in the multiple welding sample data and the welding defect rate.

[0017] Compared with the prior art, the present application obtains welding process data within a target time period in welding production through a target sensor; determines multiple welding sample data based on the welding process data, and determines the characteristic vector corresponding to each welding sample data in the multiple welding sample data; determines the welding defect rate in the welding production within the target time period; and uses the isolation forest algorithm to train a welding quality detection model and a path length threshold corresponding to the welding quality detection model based on the characteristic vector corresponding to each welding sample data in the multiple welding sample data and the welding defect rate. It is unnecessary to label and measure the sample data, which saves labor costs in model construction and avoids the reduction in model accuracy due to manual labeling errors, thereby facilitating project implementation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Other features, objects and advantages of the present application will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0019] Figure 1 A flow chart of a method for constructing a welding quality detection model according to one embodiment of the present application is shown;

[0020] Figure 2 A branch schematic diagram according to an embodiment of the present application is shown;

[0021] Figure 3 A structural diagram of a device for constructing a welding quality detection model according to an embodiment of the present application is shown;

[0022] Figure 4 An exemplary system is shown that can be used to implement the various embodiments described in this application.

[0023] The same or similar reference numerals in the drawings represent the same or similar components. DETAILED DESCRIPTION

[0024] The present application is described in further detail below with reference to the accompanying drawings.

[0025] In a typical configuration of the present application, the terminal, the device of the service network and the trusted party all include one or more processors (eg, a central processing unit (CPU)), an input / output interface, a network interface and a memory.

[0026] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory. Memory is an example of a computer-readable medium.

[0027] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PCM), programmable random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0028] The devices referred to in this application include but are not limited to user devices, network devices, or devices formed by integrating user devices and network devices through a network. The user devices include but are not limited to any mobile electronic product that can interact with a user (for example, through a touchpad), such as a smartphone, a tablet computer, etc. The mobile electronic product can use any operating system, such as the Android operating system, the iOS operating system, etc. Among them, the network device includes an electronic device that can automatically perform numerical calculations and information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc. The network device includes but is not limited to a computer, a network host, a single network server, a set of multiple network servers, or a cloud composed of multiple servers; here, the cloud is composed of a large number of computers or network servers based on cloud computing, wherein cloud computing is a type of distributed computing, a virtual supercomputer composed of a group of loosely coupled computers. The network includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a VPN network, a wireless self-organizing network (Ad Hoc network), etc. Preferably, the device may also be a program running on the user device, the network device, or a device formed by integrating the user device and the network device, the network device and the touch terminal, or the network device and the touch terminal via a network.

[0029] Of course, those skilled in the art should understand that the above-mentioned devices are only examples, and other existing or future devices that are applicable to this application should also be included in the scope of protection of this application and are included here by reference.

[0030] In the description of the present application, “plurality” means two or more, unless otherwise clearly defined.

[0031] Figure 1A flow chart of a method for constructing a welding quality detection model according to one embodiment of the present application is shown, the method comprising steps S11, S12, S13, and S14. In step S11, device 1 obtains welding process data within a target time period in welding production through a target sensor; in step S12, device 1 determines a plurality of welding sample data based on the welding process data, and determines a feature vector corresponding to each welding sample data in the plurality of welding sample data; in step S13, device 1 determines a welding defect rate in the welding production within the target time period; in step S14, device 1 uses an isolation forest algorithm to train a welding quality detection model and a path length threshold corresponding to the welding quality detection model based on the feature vector corresponding to each welding sample data in the plurality of welding sample data and the welding defect rate.

[0032] In step S11, device 1 uses a target sensor to obtain welding process data within a target time period during welding production. In some embodiments, device 1 is a device used to train a welding quality detection model. In some embodiments, the target sensor includes, but is not limited to, a current sensor and a voltage sensor deployed in a welding machine. For example, the ring of a Hall effect current sensor is connected to the cable at the current output end of the welding machine, and the current passing through the circuit is measured using the Hall effect; a voltage sensor is connected in parallel with the welding machine power supply, and the main circuit voltage is measured using the principle that the voltage of the parallel circuit is equal to the main circuit voltage. In some embodiments, the target sensor simulates the detected data into a 0-5V weak current signal and transmits it to the IoT gateway. The IoT gateway decodes the weak current signal, determines the corresponding voltage or current data as welding process data, and sends the welding process data to device 1 as training data for constructing a welding quality detection model.

[0033] In some embodiments, the method further includes: step S15 (not shown), in which device 1 determines the target time period based on the longest operating cycle of the welding machine spare part in the welding production. In some embodiments, there is a certain correlation between welding quality and the life cycle of the welding machine spare part. To ensure the accuracy of the constructed welding quality detection model, device 1 can determine a corresponding target time period based on the longest operating cycle of the welding machine spare part and obtain welding process data within the target time period, wherein the target time period covers at least one of the longest operating cycles. For example, if the longest operating cycle corresponding to the welding machine spare part is 4 days, data can be collected for three cycles according to the longest operating cycle, that is, 12 days.

[0034] In step S12, the device 1 determines multiple welding sample data based on the welding process data and determines a feature vector corresponding to each welding sample data in the multiple welding sample data. In some embodiments, the welding process data is time-series stream data. To avoid excessive data volume corresponding to each data sample, the device 1 can segment the welding process data based on a preset time period to obtain multiple welding sample data. The device 1 then calculates each welding sample data in the multiple welding sample data to determine a feature vector corresponding to the welding sample data. The feature vector includes time domain, frequency domain, or time-frequency domain features corresponding to the welding sample data, such as the mean, standard deviation, range, skewness, kurtosis, dominant frequency, Fourier coefficient, etc. of the welding sample data.

[0035] In some embodiments, step S12 includes: the device 1 preprocesses the welding process data to determine a plurality of welding sample data, wherein each of the plurality of welding sample data includes a welding process data segment; and based on the plurality of welding sample data, determines a feature vector corresponding to each of the plurality of welding sample data. In some embodiments, the preprocessing includes but is not limited to data cleaning, data denoising, and data segmentation of the welding process data. For example, the device 1 supplements missing values ​​in the welding process data, or denoises the welding process data using high-frequency filtering. The device 1 can segment the welding process data that has been cleaned and denoised based on a preset time period to obtain a plurality of welding process data segments; and determines a plurality of welding sample data based on the plurality of welding process data segments, wherein each welding sample data includes a welding process data segment.

[0036] In step S13, device 1 determines the welding defect rate during the target time period. In some embodiments, device 1 can determine the welding defect rate during the target time period based on existing welding quality inspection methods. Device 1 can also obtain the welding defect rate during the target time period input by the user or transmitted by other devices. For example, using the welding of a water heater tank as an example, the existing water immersion and sealing inspection method for water heater tank welding production can be used to determine the tank welding defect rate during the target time period, thereby rationally utilizing existing resources and avoiding additional investment.

[0037] In step S14, the device 1 uses the isolation forest algorithm to train a welding quality detection model and a path length threshold corresponding to the welding quality detection model based on the feature vector corresponding to each welding sample data and the welding defect rate. For example, the device 1 can use the isolation forest algorithm to branch each welding sample data based on the feature vector corresponding to each welding sample data to obtain a welding quality detection model. Figure 2 The branching diagram shown in the figure randomly selects a feature from the feature vector as the starting node, performs a binary partition on the welding sample data, and repeats this binary partition operation on the left and right branches until the branch termination condition is met. The trained welding quality inspection model will retain this branching structure. The branch termination conditions include, but are not limited to, the number of welding sample data contained in the resulting child nodes being less than or equal to the sample number threshold, the welding sample data cannot be further split, or the number of partitions has reached the partition number threshold. Since defective welding sample data typically accounts for a minority of all sample data, the longer the branch path, the more similar welding sample data it contains, and the greater the probability that it is normal sample data; conversely, the longer the branch path, the greater the probability that the welding sample data is defective sample data. Therefore, the path length threshold corresponding to the welding quality inspection model can be determined based on the path length and welding defect rate of each welding sample data in the welding quality inspection model. Welding sample data with a path length less than the path length threshold is considered defective sample data, while those with a path length less than the path length threshold are considered normal sample data.

[0038] In some embodiments, step S14 includes: step S141 (not shown), in which device 1 uses an isolation forest algorithm to train a welding quality detection model based on the feature vector corresponding to each welding sample data in the plurality of welding sample data; and step S142 (not shown), in which device 1 determines a path length threshold corresponding to the welding quality detection model based on the welding quality detection model, the welding defect rate, and the feature vector corresponding to each welding sample data in the plurality of welding sample data. For example, after device 1 constructs the welding quality detection model using the isolation forest algorithm, it can determine path length information corresponding to each welding sample data in the plurality of welding sample data based on the welding quality detection model. A path length threshold is determined based on the path length information and the welding defect rate. For example, if the welding defect rate is 5%, the path length threshold is greater than 5% of the path length information and less than 95% of the path length information.

[0039] In some embodiments, step S141 includes: device 1 determining multiple welding sample sets based on the feature vector corresponding to each welding sample data in the multiple welding sample data; and using the isolation forest algorithm to train a welding quality detection model based on the multiple welding sample sets, wherein the welding quality detection model includes multiple welding quality detection tree models, each of the multiple welding quality detection tree models corresponding to a welding sample set in the multiple welding sample sets. In some embodiments, the number of welding sample sets can be determined based on the number of welding sample data or can be set by the user. Based on the number of welding sample sets, device 1 can perform multiple random sampling from the feature vectors corresponding to the multiple welding sample data to obtain feature vectors corresponding to a preset proportion or number of welding sample data to form the multiple welding sample sets. For each welding sample set in the multiple welding sample sets, device 1 can use the isolation forest algorithm to obtain a welding quality detection tree model corresponding to the welding sample set. A corresponding welding quality detection model is then determined based on the welding quality detection tree model corresponding to each welding sample set.

[0040] In some embodiments, step S142 includes: device 1 determining path length information corresponding to each welding sample data item in the plurality of welding sample data items based on the welding quality detection model and the feature vector corresponding to each welding sample data item in the plurality of welding sample data items; and determining a path length threshold corresponding to the welding quality detection model based on the path length information corresponding to each welding sample data item in the plurality of welding sample data items and the welding defect rate. For example, device 1 determines path length information corresponding to each welding sample data item in the plurality of welding sample data items based on the welding quality detection model. A path length threshold is determined based on the path length information and the welding defect rate. For example, if the welding defect rate is 5%, the path length threshold is greater than 5% of the path length information items and less than 95% of the path length information items. Thus, the welding quality corresponding to the welding data can be determined based on the path length threshold. If the path length information corresponding to the welding data item is less than the path length threshold, a welding defect exists; otherwise, the welding is normal. In some embodiments, the welding quality detection model includes multiple welding quality detection tree models. Device 1 can determine sub-path length information of the welding sample data item in each welding quality detection tree model based on the feature vector corresponding to the welding sample data item. The device 1 determines the path length information corresponding to the welding sample data based on the sub-path length information. For example, the device 1 may use the average of the sub-path length information as the path length information.

[0041] In some embodiments, the method further includes: step S16 (not shown), in which the device 1 sends the welding quality detection model and the path length threshold corresponding to the welding quality detection model to the target gateway for quality detection during the welding process. For example, the device 1 can send the trained welding quality detection model and the corresponding path length threshold to the target gateway at the welding production site. The target gateway can obtain welding data through the target sensor and determine the feature vector corresponding to the welding data based on the welding data. The feature vector corresponding to the welding data is input into the welding quality detection model to determine the path length information corresponding to the welding data. If the path length information corresponding to the welding data is greater than the path length threshold, it can be determined that the quality detection result corresponding to the welding data is normal welding; otherwise, it is abnormal welding.

[0042] Figure 3 A structural diagram of a device for constructing a welding quality detection model according to an embodiment of the present application is shown, wherein the device 1 includes a first module 11, a second module 12, a third module 13, and a fourth module 14. The first module 11 obtains welding process data within a target time period in welding production through a target sensor; the first module 12 determines a plurality of welding sample data according to the welding process data, and determines a feature vector corresponding to each welding sample data in the plurality of welding sample data; the first module 13 determines the welding defect rate in the welding production within the target time period; the fourth module 14 obtains a welding quality detection model and a path length threshold corresponding to the welding quality detection model by training using an isolation forest algorithm based on the feature vector corresponding to each welding sample data in the plurality of welding sample data and the welding defect rate. Here, Figure 3 The specific implementations corresponding to the module 11, the module 12, the module 13 and the module 14 shown are the same or similar to the specific embodiments of the aforementioned steps S11, S12, S13 and S14, so they are not repeated here and are included here by reference.

[0043] In some embodiments, the 14 module 14 includes a 141 unit 141 (not shown) and a 142 unit 142 (not shown). The 141 unit 141 uses an isolation forest algorithm to train a welding quality detection model based on the feature vector corresponding to each welding sample data in the plurality of welding sample data. The 142 unit 142 determines a path length threshold corresponding to the welding quality detection model based on the welding quality detection model, the welding defect rate, and the feature vector corresponding to each welding sample data in the plurality of welding sample data. The specific implementations of the 141 unit 141 and the 142 unit 142 are the same or similar to the specific embodiments of the aforementioned steps S141 and S142, respectively, and are therefore not further described and are incorporated herein by reference.

[0044] In some embodiments, the apparatus 1 further includes a module 15 (not shown). The module 15 determines the target time period based on the longest operating cycle of the welding machine spare parts during the welding process. The specific implementation of the module 15 is the same or similar to the specific implementation of step S15 described above, and thus will not be further described. The details are incorporated herein by reference.

[0045] In some embodiments, the device 1 further includes a six-module 16 (not shown). This six-module 16 sends the welding quality detection model and the path length threshold corresponding to the welding quality detection model to the target gateway for quality detection during the welding process. The specific implementation of this six-module 16 is the same or similar to the specific implementation of step S16 described above, and is therefore not further described and is incorporated herein by reference.

[0046] Figure 4 shows an exemplary system that can be used to implement the various embodiments described in this application;

[0047] like Figure 4 In some embodiments, the system 300 can function as any of the devices described in the various embodiments. In some embodiments, the system 300 can include one or more computer-readable media (e.g., system memory or NVM / storage device 320) having instructions and one or more processors (e.g., processor(s) 305) coupled to the one or more computer-readable media and configured to execute the instructions to implement the modules and thereby perform the actions described herein.

[0048] For one embodiment, system control module 310 may include any suitable interface controller to provide any suitable interface to at least one of processor(s) 305 and / or any suitable device or component in communication with system control module 310 .

[0049] The system control module 310 may include a memory controller module 330 to provide an interface to the system memory 315. The memory controller module 330 may be a hardware module, a software module, and / or a firmware module.

[0050] System memory 315 can be used, for example, to load and store data and / or instructions for system 300. For one embodiment, system memory 315 can include any suitable volatile memory, such as a suitable DRAM. In some embodiments, system memory 315 can include double data rate type four synchronous dynamic random access memory (DDR4 SDRAM).

[0051] For one embodiment, system control module 310 may include one or more input / output (I / O) controllers to provide interfaces to NVM / storage device 320 and communication interface(s) 325 .

[0052] For example, NVM / storage 320 may be used to store data and / or instructions. NVM / storage 320 may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable non-volatile storage device(s) (e.g., one or more hard disk drives (HDDs), one or more compact disk (CD) drives, and / or one or more digital versatile disk (DVD) drives).

[0053] NVM / storage device 320 may include storage resources that are physically part of the device on which system 300 is installed, or it may be accessible to the device without being part of the device. For example, NVM / storage device 320 may be accessed over a network via communication interface(s) 325.

[0054] Communication interface(s) 325 may provide an interface for system 300 to communicate over one or more networks and / or with any other suitable devices. System 300 may wirelessly communicate with one or more components of a wireless network in accordance with any of one or more wireless network standards and / or protocols.

[0055] For one embodiment, at least one of the processor(s) 305 may be packaged together with the logic of one or more controllers of the system control module 310 (e.g., the memory controller module 330). For one embodiment, at least one of the processor(s) 305 may be packaged together with the logic of one or more controllers of the system control module 310 to form a system-in-package (SiP). For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with the logic of one or more controllers of the system control module 310. For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with the logic of one or more controllers of the system control module 310 to form a system-on-chip (SoC).

[0056] In various embodiments, system 300 may be, but is not limited to, a server, a workstation, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet computer, a netbook, etc.). In various embodiments, system 300 may have more or fewer components and / or a different architecture. For example, in some embodiments, system 300 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including a touchscreen display), a non-volatile memory port, multiple antennas, a graphics chip, an application-specific integrated circuit (ASIC), and a speaker.

[0057] In addition to the methods and devices described in the above embodiments, the present application also provides a computer-readable storage medium, which stores computer code. When the computer code is executed, the method described in any of the above items is executed.

[0058] The present application also provides a computer program product. When the computer program product is executed by a computer device, the method described in any one of the preceding items is executed.

[0059] The present application also provides a computer device, comprising:

[0060] one or more processors;

[0061] a memory for storing one or more computer programs;

[0062] When the one or more computer programs are executed by the one or more processors, the one or more processors are caused to implement the method as described in any one of the preceding items.

[0063] It should be noted that the application can be implemented in software and / or a combination of software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the application can be executed by a processor to realize the steps or functions described above. Similarly, the software program of the application (including relevant data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the application can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0064] In addition, a part of the present application may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present application through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes but is not limited to a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0065] Communication media include media by which communication signals containing, for example, computer-readable instructions, data structures, program modules, or other data are transmitted from one system to another. Communication media may include guided transmission media such as cables and wires (e.g., fiber optic, coaxial, etc.) and wireless (unguided transmission) media capable of propagating energy waves, such as acoustic, electromagnetic, RF, microwave, and infrared. Computer-readable instructions, data structures, program modules, or other data may be embodied as, for example, a modulated data signal in a wireless medium such as a carrier wave or similar mechanism such as that embodied as part of spread spectrum technology. The term "modulated data signal" refers to a signal that has one or more of its characteristics changed or set in such a manner as to encode information in the signal. Modulation may be analog, digital, or a hybrid modulation technique.

[0066] By way of example and not limitation, computer-readable storage media may include volatile and non-volatile, 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. For example, computer-readable storage media include, but are not limited to, volatile memory, such as random access memory (RAM, DRAM, SRAM); and non-volatile memory, such as flash memory, various read-only memories (ROM, PROM, EPROM, EEPROM), magnetic and ferromagnetic / ferroelectric memories (MRAM, FeRAM); and magnetic and optical storage devices (hard disks, magnetic tapes, CDs, DVDs); or other media now known or later developed that can store computer-readable information / data for use by a computer system.

[0067] Here, according to one embodiment of the present application, a device is included, which includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein, when the computer program instructions are executed by the processor, the device is triggered to run the methods and / or technical solutions based on the aforementioned multiple embodiments of the present application.

[0068] It is obvious to those skilled in the art that the present application is not limited to the details of the above-mentioned exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic characteristics of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware. Words such as first and second are used to indicate names and do not indicate any particular order.

Claims

1. A method for constructing a welding quality detection model, wherein: The method comprises: Acquire welding process data within a target time period during welding production through target sensors; Determine a plurality of welding sample data according to the welding process data, and determine a feature vector corresponding to each welding sample data in the plurality of welding sample data; determining a welding defect rate in the welding production within the target time period; According to the characteristic vector corresponding to each welding sample data in the multiple welding sample data and the welding defect rate, the isolation forest algorithm is used to train to obtain a welding quality detection model and a path length threshold corresponding to the welding quality detection model, wherein the path length threshold is determined based on the path length of each welding sample data in the welding quality detection model and the welding defect rate.

2. The method according to claim 1, wherein The method of obtaining a welding quality detection model and a path length threshold corresponding to the welding quality detection model by training using an isolation forest algorithm according to the characteristic vector corresponding to each welding sample data in the plurality of welding sample data and the welding defect rate comprises: According to the feature vector corresponding to each welding sample data in the plurality of welding sample data, an isolation forest algorithm is used to train and obtain a welding quality detection model; A path length threshold corresponding to the welding quality detection model is determined according to the welding quality detection model, the welding defect rate, and a feature vector corresponding to each welding sample data in the plurality of welding sample data.

3. The method according to claim 2, wherein: The method of obtaining a welding quality detection model by training with an isolation forest algorithm according to a feature vector corresponding to each welding sample data in the plurality of welding sample data comprises: determining a plurality of welding sample sets according to a feature vector corresponding to each welding sample data in the plurality of welding sample data; Based on the multiple welding sample sets, an isolation forest algorithm is used to train and obtain a welding quality detection model, wherein the welding quality detection model includes multiple welding quality detection tree models, and each welding quality detection tree model in the multiple welding quality detection tree models corresponds to a welding sample set in the multiple welding sample sets.

4. The method according to claim 2, wherein: Determining the path length threshold corresponding to the welding quality detection model according to the welding quality detection model, the welding defect rate, and the feature vector corresponding to each welding sample data in the plurality of welding sample data includes: determining path length information corresponding to each welding sample data in the plurality of welding sample data according to the welding quality detection model and a feature vector corresponding to each welding sample data in the plurality of welding sample data; A path length threshold corresponding to the welding quality detection model is determined according to path length information corresponding to each welding sample data in the plurality of welding sample data and the welding defect rate.

5. The method according to any one of claims 1 to 4, wherein The method further comprises: The target time period is determined according to the longest working cycle of the welding machine spare parts in the welding production.

6. The method according to any one of claims 1 to 5, wherein The step of determining a plurality of welding sample data according to the welding process data, and determining a feature vector corresponding to each welding sample data in the plurality of welding sample data comprises: Preprocessing the welding process data to determine a plurality of welding sample data, wherein each welding sample data in the plurality of welding sample data includes a welding process data segment; According to the plurality of welding sample data, a feature vector corresponding to each welding sample data in the plurality of welding sample data is determined.

7. The method according to any one of claims 1 to 6, wherein The method further comprises: The welding quality detection model and the path length threshold corresponding to the welding quality detection model are sent to a target gateway for quality detection during the welding process.

8. A computer device for constructing a welding quality detection model, comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images