Methods, apparatus, media, and program product for performing weld data analysis

Abstract

The purpose of the present application is to provide a method, device, medium and program product for welding data analysis, the method comprising: determining a welding data analysis task, wherein the welding data analysis task comprises a short circuit transition analysis or a data filtering analysis; determining analysis parameter information matched with the welding data analysis task according to the welding data analysis task and welding data; and determining analysis result information corresponding to the welding data analysis task based on the analysis parameter information and the welding data. According to the present application, after determining the welding data analysis task selected by the user, the optimal analysis parameter used in the welding data analysis task can be automatically calculated, thereby avoiding the cumbersome process of manual parameter adjustment, improving the analysis efficiency and analysis result accuracy, reducing the analysis threshold of the user for welding data analysis, and optimizing the user experience.

Description

Technical Field

[0001] This application relates to the field of welding analysis, and more particularly to a technique for performing welding data analysis. Background Technology

[0002] Welding is a crucial process in modern industrial production. The quality of welding directly impacts the overall performance of the welded product, such as ductility and strength. With the rapid development of IoT technology, more and more companies are connecting their workshop welding equipment to the Internet of Things (IoT) to collect key quality IoT data during the welding process, such as current, voltage, and gas flow. To assist process engineers in effectively extracting value from this data, a welding quality intelligent analysis system needs to be built to perform multi-dimensional analysis of various welding data, such as short-circuit transition analysis and data filtering, to obtain a quantitative evaluation of the welding process stability and quality. Typically, when performing short-circuit transition analysis or data filtering, users need to manually set appropriate analysis parameters before analysis and then determine whether the results match expectations after analysis, such as whether the short-circuit transition interval segmentation is reasonable and whether data filtering achieves the desired deburring effect. If they do not match expectations, the analysis parameters need to be modified, and the calculation recursively. The entire analysis process requires users to repeatedly adjust the analysis parameters, which is time-consuming and labor-intensive, and also requires users to have a deep understanding of the welding data used for analysis, as well as the corresponding welding process knowledge and analysis algorithms. Summary of the Invention

[0003] One object of this application is to provide a method, apparatus, medium, and procedure for performing welding data analysis.

[0004] According to one aspect of this application, a method for performing welding data analysis is provided, the method comprising:

[0005] Define the welding data analysis task, wherein the welding data analysis task includes short-circuit transition analysis or data filtering analysis;

[0006] Based on the welding data analysis task and the welding data, determine the analysis parameter information that matches the welding data analysis task;

[0007] Based on the analysis parameter information and the welding data, the analysis result information corresponding to the welding data analysis task is determined.

[0008] According to one aspect of this application, a computer device for performing welding data analysis is provided, including 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 any of the methods described above.

[0009] According to one aspect of this application, a computer-readable storage medium is provided having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the steps of any of the methods described above.

[0010] According to one aspect of this application, a computer program product is provided, comprising a computer program, characterized in that, when executed by a processor, the computer program implements the steps of any of the methods described above.

[0011] According to one aspect of this application, an apparatus for performing welding data analysis is provided, the apparatus comprising:

[0012] A module is used to determine the welding data analysis task, which includes short-circuit transition analysis or data filtering analysis.

[0013] The first and second modules are used to determine the analysis parameter information that matches the welding data analysis task based on the welding data analysis task and the welding data.

[0014] The first and third modules are used to determine the analysis result information corresponding to the welding data analysis task based on the analysis parameter information and the welding data.

[0015] Compared with existing technologies, this application determines the welding data analysis task, which includes short-circuit transition analysis or data filtering analysis; based on the welding data analysis task and welding data, it determines the analysis parameter information matching the welding data analysis task; and based on the analysis parameter information and the welding data, it determines the analysis result information corresponding to the welding data analysis task. After determining the welding data analysis task selected by the user, this solution can automatically calculate the optimal analysis parameters used in that task, thereby avoiding the tedious process of manual parameter tuning, improving analysis efficiency and accuracy, lowering the analysis threshold for users, and optimizing the user experience. Attached Figure Description

[0016] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0017] Figure 1 A flowchart illustrating a method for performing welding data analysis according to an embodiment of this application is shown.

[0018] Figure 2 This illustration shows a segmentation diagram of a welding voltage curve according to an embodiment of this application;

[0019] Figure 3 This diagram illustrates an abnormal short circuit according to one embodiment of the present application.

[0020] Figure 4 This illustrates a Fourier spectrum according to one embodiment of the present application;

[0021] Figure 5 This diagram illustrates a structural diagram of an apparatus for performing welding data analysis according to an embodiment of this application.

[0022] Figure 6 Exemplary systems that can be used to implement the various embodiments described in this application are shown.

[0023] The same or similar reference numerals in the accompanying drawings represent the same or similar parts. Detailed Implementation

[0024] The present application will now be described in further detail with reference to the accompanying drawings.

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

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

[0027] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using 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 technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0028] The devices referred to in this application include, but are not limited to, user equipment, network equipment, or devices composed of user equipment and network equipment integrated through a network. The user equipment includes, but is not limited to, any mobile electronic product capable of human-computer interaction (e.g., via a touchpad), such as smartphones and tablets. These mobile electronic products can use any operating system, such as Android or iOS. The network equipment includes an electronic device capable of automatically performing numerical calculations and information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), and embedded devices. The network equipment includes, but is not limited to, computers, network hosts, single network servers, multiple network server clusters, or clouds composed of multiple servers. Here, a cloud consists of a large number of computers or network servers based on cloud computing, where cloud computing is a type of distributed computing, consisting of a virtual supercomputer composed of a group of loosely coupled computer clusters. The network includes, but is not limited to, the Internet, wide area network, metropolitan area network, local area network, VPN network, wireless ad hoc network, etc. Preferably, the device can also be a program running on the user equipment, network device, or a device formed by integrating user equipment and network device, network device, touch terminal, or network device and touch terminal through a network.

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

[0030] In the description of this application, "multiple" means two or more, unless otherwise expressly and specifically defined.

[0031] Figure 1A flowchart illustrating a method for performing welding data analysis according to an embodiment of this application is shown. The method includes steps S11, S12, and S13. In step S11, device 1 determines a welding data analysis task, wherein the welding data analysis task includes short-circuit transition analysis or data filtering analysis. In step S12, device 1 determines analysis parameter information matching the welding data analysis task based on the welding data analysis task and the welding data. In step S13, device 1 determines analysis result information corresponding to the welding data analysis task based on the analysis parameter information and the welding data.

[0032] In step S11, device 1 determines a welding data analysis task, which includes short-circuit transition analysis or data filtering analysis. In some embodiments, device 1 includes, but is not limited to, user equipment or network equipment capable of performing welding data analysis. In some embodiments, device 1 can determine the corresponding welding data analysis task based on the user's selection.

[0033] In step S12, device 1 determines analysis parameter information matching the welding data analysis task based on the welding data analysis task and the welding data. In some embodiments, the welding data can be directly imported by the user or obtained by device 1 from a corresponding welding database or an IoT gateway at the welding production site. In some embodiments, device 1 can determine an analysis algorithm matching the welding data analysis task based on the welding data analysis task, and then combine it with the welding data to determine the corresponding analysis parameter information. For example, if the welding data analysis task includes short-circuit transition analysis, device 1 can use a genetic algorithm combined with the welding data to determine the corresponding optimal short-circuit voltage threshold, or it can use an unsupervised anomaly detection algorithm to obtain the optimal short-circuit time threshold. Alternatively, if the welding data analysis task includes data filtering analysis, device 1 can also use Fourier transform to determine the corresponding cutoff frequency information.

[0034] In step S13, device 1 determines the analysis result information corresponding to the welding data analysis task based on the analysis parameter information and the welding data. In some embodiments, the analysis result information includes, but is not limited to, the short-circuit interval or abnormal short-circuit data corresponding to the welding data, and the welding data after filtering.

[0035] For example, if the welding data analysis task includes short-circuit transition analysis, the analysis parameter information includes the optimal short-circuit voltage threshold and the optimal short-circuit time threshold. (Reference) Figure 2 The welding voltage curve segmentation diagram shown indicates that device 1 can determine the corresponding welding voltage-time curve based on the welding data, and then, according to the optimal short-circuit voltage threshold (e.g., ... Figure 2The 13V section is divided into segments, where the voltage range above the optimal short-circuit voltage threshold is the arcing stage, and the range below the optimal short-circuit voltage threshold is the short-circuit stage. Device 1 can also analyze the welding data obtained from the segmentation of the short-circuit stages, and, in conjunction with the optimal short-circuit time threshold, determine the corresponding abnormal short-circuit data, for example, by referring to... Figure 3 The diagram shows an abnormal short circuit. The abnormal short circuit data includes, but is not limited to, welding data information of abnormal short circuits (e.g., short circuit time is not within the range corresponding to the optimal short circuit time threshold, short circuit time is too long or too short) in the short circuit stage, or information on the proportion of abnormal short circuits in the short circuit stage.

[0036] For example, if the welding data analysis task includes data filtering analysis, and the analysis parameter information includes cutoff frequency information, which includes a low cutoff frequency and a high cutoff frequency, the device 1 can retain the frequency components in the welding data that are between the low and high cutoff frequencies, and remove other frequency components, thereby obtaining filtered welding data.

[0037] In some embodiments, the welding data analysis task includes short-circuit transition analysis, and the analysis parameter information includes an optimal short-circuit voltage threshold and an optimal short-circuit time threshold. Step S12 includes: device 1 determining the optimal short-circuit voltage threshold using a genetic algorithm based on the welding data; determining the short-circuit interval data corresponding to the welding data based on the optimal short-circuit voltage threshold; and determining the optimal short-circuit time threshold based on the short-circuit interval data. In some embodiments, the voltage value of the welding data corresponding to the short-circuit interval data is less than the optimal short-circuit voltage threshold. In some embodiments, if the welding data analysis task includes short-circuit transition analysis, device 1 can first determine an analysis algorithm matching the short-circuit transition analysis, the analysis algorithm including but not limited to genetic algorithms and unsupervised anomaly detection algorithms. Then, based on the determined analysis algorithm and the welding data, corresponding analysis parameter information is determined, the analysis parameter information including the optimal short-circuit voltage threshold and the optimal short-circuit time threshold. Thus, device 1 can judge abnormal short circuits based on the determined optimal short-circuit voltage threshold and the optimal short-circuit time threshold.

[0038] In some embodiments, determining the optimal short-circuit voltage threshold using a genetic algorithm based on welding data includes: the device 1 constructing a fitness function for the genetic algorithm based on the welding data; determining a corresponding population based on a preset short-circuit voltage threshold search interval; updating and iterating the population based on the fitness function until the iteration condition is met; and determining the optimal short-circuit voltage threshold based on the updated population.

[0039] In some embodiments, device 1 constructs a fitness function with a short-circuit voltage threshold as the independent variable. For example, based on the short-circuit voltage threshold σ, the standard deviation S of welding data with voltage values ​​greater than the short-circuit voltage threshold σ is determined. up The standard deviation S of welding data in which the voltage value is greater than the short-circuit voltage threshold σ. down According to the standard deviation S up With S down Device 1 can construct the corresponding fitness function. For example, the fitness function F fit =S up +S down = f(σ). In some embodiments, device 1 can determine the corresponding population based on a preset short-circuit voltage threshold search interval and a preset population size. The short-circuit voltage threshold search interval is the range of possible values ​​for the independent variable σ of the fitness function, and the population size is the number of possible values ​​for the independent variable σ. For example, if device 1 determines that the short-circuit voltage threshold search interval is [3, 20] and the population size is 100, then 100 random numbers are selected from the interval [3, 20] as the population. In some embodiments, device 1 updates and iterates the population based on the fitness function using the genetic operators corresponding to the genetic algorithm and parameters such as crossover probability and mutation probability corresponding to the genetic operators until the iteration conditions are met. The genetic operators include, but are not limited to, selection operators, crossover operators, and mutation operators. The selection operators include, but are not limited to, stochastic tournament, optimal retention selection, and expected value selection. The crossover operators include, but are not limited to, one-point crossover, two-point crossover, multi-point crossover, and arithmetic crossover. The mutation operators include, but are not limited to, simple mutation, boundary mutation, and Gaussian approximation mutation. The iteration conditions include, but are not limited to, reaching an iteration threshold. In some embodiments, the device 1 obtains the fitness value corresponding to each individual in the iterated population (i.e., the value corresponding to the short-circuit voltage threshold σ) based on the fitness function; based on the fitness value corresponding to each individual in the iterated population (i.e., the value corresponding to the short-circuit voltage threshold σ), the individual with the highest fitness value is taken as the optimal short-circuit voltage threshold.

[0040] It should be understood by those skilled in the art that the above-mentioned genetic operators are merely examples, and other existing or future genetic operators that are applicable to this application should also be included within the scope of protection of this application, and are hereby incorporated by reference.

[0041] In some embodiments, updating and iterating the population based on the fitness function until the iteration condition is met includes: device 1 determining the fitness value corresponding to each individual in the population based on the fitness function; and updating and iterating the population according to the fitness value until the iteration condition is met. For example, device 1 determines the fitness value corresponding to each individual σ in the population based on the fitness function, and then, based on the fitness value, uses a selection operator to select individuals with higher fitness values ​​for crossover and mutation to perform population update and iteration. The above steps can be repeated until the iteration condition is met.

[0042] In some embodiments, determining the short-circuit interval data corresponding to the welding data based on the optimal short-circuit voltage threshold includes: device 1 determining multiple short-circuit transition intervals corresponding to the welding data based on the optimal short-circuit voltage threshold; determining short-circuit interval data according to the multiple short-circuit transition intervals, wherein the short-circuit interval data includes short-circuit data information corresponding to each of the multiple short-circuit transition intervals, and the short-circuit data information includes the average voltage and short-circuit time corresponding to the short-circuit transition interval. In some embodiments, device 1 can divide consecutive welding data with voltage values ​​lower than the optimal short-circuit voltage threshold into a short-circuit transition interval according to the optimal short-circuit voltage threshold. Device 1 can determine the average voltage and short-circuit time corresponding to the short-circuit transition interval based on the voltage value and time corresponding to the welding data contained in each short-circuit transition interval.

[0043] In some embodiments, determining the optimal short-circuit time threshold based on the short-circuit interval data includes: device 1 using an unsupervised anomaly detection algorithm to determine classification information corresponding to the short-circuit interval data, wherein the classification information includes normal data information or abnormal data information; determining a short-circuit time series based on the short-circuit interval data, wherein the short-circuit time series includes multiple short-circuit time elements; determining the proportion information of normal data information corresponding to each of the multiple short-circuit time elements; and determining the optimal short-circuit time threshold based on the proportion information.

[0044] In some embodiments, the unsupervised anomaly detection algorithm includes, but is not limited to, the Isolation Forest (iForest), Local Outlier Factor (LOF), and K-Nearest Neighbors (KNN). The short-circuit interval data includes short-circuit data information corresponding to each of multiple short-circuit transition intervals. The short-circuit data information includes the average voltage and short-circuit time corresponding to that short-circuit transition interval. The device 1 can classify each short-circuit data information into normal data information or abnormal data information according to the unsupervised anomaly detection algorithm. Taking the Isolation Forest algorithm as an example, the device 1 can obtain a preset number of samples from the short-circuit interval data and train multiple decision tree models based on these samples. For each short-circuit data information, it traverses each decision tree model, calculating the average path length corresponding to the short-circuit data information based on its path length in each decision tree model. Then, the classification corresponding to the short-circuit data information is determined based on the average path length. For example, based on the average path length, an outlier corresponding to the short-circuit data information is determined. If the outlier is higher than an anomaly threshold, the short-circuit data information is considered abnormal; otherwise, it is considered normal data. Wherein, the outlier s = 2 -d / c d is the average path length corresponding to the short-circuit data information, and c is a constant related to the number of samples.

[0045] In this document, those skilled in the art should understand that the above-described unsupervised anomaly detection algorithm is merely an example. Other existing or future unsupervised anomaly detection algorithms that are applicable to this application should also be included within the scope of protection of this application, and are hereby incorporated by reference.

[0046] In some embodiments, device 1 sorts the short-circuit times corresponding to each short-circuit data information in ascending order to obtain a short-circuit time sequence. If multiple short-circuit data information pieces correspond to the same short-circuit time, it is recorded only once in the short-circuit time sequence. For example, if there are short-circuit times of 1ms, 1ms, 4ms, 3ms, 4ms, 4ms, and 3ms, the determined short-circuit time sequence is {1ms, 3ms, 4ms}. Device 1 determines the proportion of short-circuit data information that belongs to normal data information among the one or more short-circuit data information pieces corresponding to each short-circuit time element in the short-circuit time sequence. Device 1 determines the optimal short-circuit time threshold based on this proportion information corresponding to each short-circuit time element.

[0047] In some embodiments, determining the optimal short-circuit time threshold based on the ratio information includes: device 1 determining a corresponding ratio sequence based on the ratio information; determining a target subsequence in the ratio sequence; and determining the optimal short-circuit time threshold based on the target subsequence. In some embodiments, device 1 determines the corresponding ratio sequence based on the short-circuit time sequence and the ratio information, wherein the ratio information elements in the ratio sequence correspond to the short-circuit time elements in the short-circuit time sequence. For example, for the short-circuit time sequence {t i}, i = 1, 2, ..., n, and each t i The corresponding proportion of normal data information r i Determine the corresponding proportional sequence {r} i Let i = 1, 2, ..., n. In some embodiments, the target subsequence is the longest continuous subsequence in which all proportional information elements contained in the subsequence are greater than the corresponding proportional threshold. In some embodiments, device 1 determines the short-circuit time threshold corresponding to the target subsequence based on the short-circuit time elements corresponding to the proportional information elements contained in the target subsequence. For example, if the target subsequence is determined to be [r2, r5], then the corresponding short-circuit time threshold is [t2, t5]. Short-circuit times within the short-circuit time threshold range are considered normal short-circuit transition times, while short-circuit times outside the range are considered abnormal short-circuit transition times.

[0048] In some embodiments, determining the target subsequence in the ratio sequence includes: device 1 determining one or more continuous subsequences in the ratio sequence, wherein the ratio element corresponding to each of the one or more continuous subsequences is greater than a preset ratio threshold; and determining the target subsequence from the one or more continuous subsequences. For example, device 1 determines one or more continuous subsequences from the ratio sequence, wherein multiple ratio information elements contained in each of the one or more continuous subsequences are all greater than the corresponding ratio threshold, and these ratio information elements are continuous in the ratio sequence. Device 1 determines the corresponding target subsequence from the multiple continuous subsequences, wherein the target subsequence corresponds to the longest sequence length.

[0049] In some embodiments, the welding data analysis task includes data filtering analysis; step S12 includes: device 1 using Fast Fourier Transform to determine the frequency sequence and corresponding amplitude sequence of the welding data, and plotting a corresponding spectrum based on the frequency sequence and corresponding amplitude sequence; determining one or more frequency windows in the spectrum that meet the amplitude conditions; and determining analysis parameter information matching the data filtering analysis based on the one or more frequency windows, wherein the analysis parameter information includes cutoff frequency information. For example, if the welding data analysis task includes data filtering analysis, device 1 performs Fast Fourier Transform (FFT) on the welding data to determine the corresponding frequency sequence {f j} and the corresponding amplitude sequence {a j}, j = 1, 2, ..., n. Device 1 is based on the frequency sequence {f j} and the corresponding amplitude sequence {a j}Draw as Figure 4 The spectrum shown contains data points with coordinates (f j a j Let j = 1, 2, ..., n. Device 1 can use a sliding window method to determine one or more frequency windows, wherein the amplitude information corresponding to each frequency window satisfies a corresponding amplitude condition, and the amplitude information corresponding to the frequency window is the sum of the amplitudes of the data points contained in the frequency window. Then, based on the one or more frequency windows, the corresponding cutoff frequency information is determined.

[0050] In some embodiments, determining analysis parameter information matching the data filtering analysis based on the one or more frequency windows, wherein the analysis parameter information includes cutoff frequency information, includes: device 1 determining a target frequency window from the one or more frequency windows based on the window width of each frequency window in the one or more frequency windows; and determining corresponding cutoff frequency information based on the target frequency window. In some embodiments, device 1 needs to determine the frequency window with the largest average amplitude, i.e., the highest energy density of the corresponding frequency component, from the one or more frequency windows as the target frequency window. The smaller the window width of a frequency window in the one or more frequency windows, the larger its corresponding average amplitude. Therefore, device 1 can determine the window width of each frequency window, and then directly determine the corresponding target frequency window based on the window width of each frequency window. The window width of the target frequency window is smaller than the window width of other frequency windows. In some embodiments, the cutoff frequency information includes a high cutoff frequency and a low cutoff frequency. Device 1 can use the upper bound of the target frequency window as the high cutoff frequency for filtering and its lower bound as the low cutoff frequency.

[0051] In some embodiments, the method further includes: step S14 (not shown), whereby device 1 determines corresponding total amplitude information based on the amplitude sequence; and determines the amplitude condition based on the total amplitude information. For example, device 1 performs amplitude summation based on the amplitude sequence to determine the corresponding total amplitude information S. a Based on the total amplitude information S a The corresponding amplitude conditions are determined. These amplitude conditions include the amplitude information corresponding to the frequency window and the total amplitude information S. a Matching, for example, the amplitude information corresponding to the frequency window = kS a k is a constant taking values ​​in the range (0, 1). The value of this constant k is matched to the data filtering analysis task; the more aggressive the data filtering process, the smaller this value becomes; when k is 1, no filtering process is performed. (See reference...) Figure 4 The spectrum shown shows that if k = 0.5, then device 1 can determine multiple frequency windows that satisfy the amplitude conditions, for example, Figure 4 Three corresponding amplitude values ​​of 0.5S were selected from the winning bids. a Frequency window.

[0052] In some embodiments, the welding data analysis task may further include UI phase diagram analysis, probability density analysis, feature analysis, or envelope backtracking, etc. Device 1 can determine the analysis algorithm matching each welding data analysis task based on these tasks. Then, combining the welding data, it automatically calculates the optimal analysis parameters used in the welding data analysis task. Based on the optimal analysis parameter information, it determines the analysis result information corresponding to the welding data analysis task. This avoids the tedious process of manual parameter tuning by the user when performing various welding data analyses, improving analysis efficiency and the accuracy of analysis results. Here, the analysis methods for welding data analysis tasks such as UI phase diagram analysis, probability density analysis, feature analysis, or envelope backtracking are the same as or similar to those in steps S11-S13, and therefore will not be repeated here, but are included by reference.

[0053] Figure 5 This diagram illustrates a structural diagram of a welding data analysis device according to an embodiment of this application. The device 1 includes a first module 11, a second module 12, and a third module 13. The first module 11 determines a welding data analysis task, wherein the welding data analysis task includes short-circuit transition analysis or data filtering analysis. The second module 12 determines analysis parameter information matching the welding data analysis task based on the welding data analysis task and the welding data. The third module 13 determines the analysis result information corresponding to the welding data analysis task based on the analysis parameter information and the welding data. Figure 5The specific implementation methods corresponding to the first module 11, the second module 12 and the third module 13 shown are the same as or similar to the specific embodiments of the aforementioned steps S11, S12 and S13, and therefore will not be repeated here. They are included here by reference.

[0054] In some embodiments, the device 1 further includes a quad module 14 (not shown). The quad module 14 determines the corresponding total amplitude information based on the amplitude sequence; and determines the amplitude condition based on the total amplitude information. Here, the specific implementation of the quad module 14 is the same as or similar to the specific implementation of the aforementioned step S14, and therefore will not be repeated here, but is included by reference.

[0055] Figure 6 Exemplary systems that can be used to implement the various embodiments described in this application are shown; such as Figure 6 As shown in some embodiments, system 300 can function as any of the devices described in each of the embodiments. In some embodiments, system 300 may include one or more computer-readable media having instructions (e.g., system memory or NVM / storage device 320) and one or more processors (e.g., one or more processors 305) coupled to the one or more computer-readable media and configured to execute the instructions to implement the module and thus perform the actions described in this application.

[0056] In one embodiment, the system control module 310 may include any suitable interface controller to provide any suitable interface to at least one of the processors 305 and / or any suitable device or component communicating with the system control module 310.

[0057] 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.

[0058] System memory 315 can be used, for example, to load and store data and / or instructions for system 300. In one embodiment, system memory 315 may include any suitable volatile memory, such as suitable DRAM. In some embodiments, system memory 315 may include double data rate type quad synchronous dynamic random access memory (DDR4 SDRAM).

[0059] In one embodiment, the system control module 310 may include one or more input / output (I / O) controllers to provide interfaces to the NVM / storage device 320 and (one or more) communication interfaces 325.

[0060] For example, NVM / storage device 320 may be used to store data and / or instructions. NVM / storage device 320 may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable (one or more) non-volatile storage devices (e.g., one or more hard disk drives (HDDs), one or more optical disc drives (CDs), and / or one or more digital universal optical disc (DVD) drives).

[0061] NVM / storage device 320 may include storage resources that are physically part of a device on which system 300 is mounted, or that can be accessed by the device without necessarily being part of it. For example, NVM / storage device 320 may be accessed via a network through one or more communication interfaces 325.

[0062] One or more communication interfaces 325 may provide the system 300 with an interface to communicate over one or more networks and / or with any other suitable device. The 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.

[0063] In one embodiment, at least one of the processors 305 may be logically packaged with one or more controllers of the system control module 310 (e.g., memory controller module 330). In one embodiment, at least one of the processors 305 may be logically packaged with one or more controllers of the system control module 310 to form a system-in-package (SiP). In one embodiment, at least one of the processors 305 may be integrated with the logic of one or more controllers of the system control module 310 on the same die. In one embodiment, at least one of the processors 305 may be integrated with the logic of one or more controllers of the system control module 310 on the same die to form a system-on-a-chip (SoC).

[0064] In various embodiments, system 300 may be, but is not limited to, a server, workstation, desktop computing device, or mobile computing device (e.g., laptop computing device, handheld computing device, tablet computer, netbook, etc.). In various embodiments, system 300 may have more or fewer components and / or different architectures. 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.

[0065] In addition to the methods and devices described in the above embodiments, this application also provides a computer-readable storage medium storing computer code that, when executed, performs the method described in any of the preceding embodiments.

[0066] This application also provides a computer program product that, when executed by a computer device, performs the method described in any of the preceding claims.

[0067] This application also provides a computer device, the computer device comprising:

[0068] One or more processors;

[0069] Memory, used to store one or more computer programs;

[0070] When the one or more computer programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the method as described in any of the preceding methods.

[0071] It should be noted that this application can be implemented in software and / or a combination of software and hardware, for example, using an application-specific integrated circuit (ASIC), a general-purpose computer, or any other similar hardware device. In one embodiment, the software program of this application can be executed by a processor to implement the steps or functions described above. Similarly, the software program of this application (including related data structures) can be stored in a computer-readable recording medium, such as RAM memory, magnetic or optical drives, floppy disks, and similar devices. Furthermore, some steps or functions of this application can be implemented in hardware, for example, as circuitry that cooperates with a processor to perform the various steps or functions.

[0072] Furthermore, a portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0073] Communication media include media through 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 can include guided transmission media (such as cables and wires (e.g., optical fibers, coaxial cables, etc.)) and wireless (unguided transmission) media capable of propagating energy waves, such as sound, electromagnetic, RF, microwave, and infrared. Computer-readable instructions, data structures, program modules, or other data can be embodied as modulated data signals in, for example, wireless media (such as carrier waves or similar mechanisms embodied as part of spread spectrum technology). The term "modulated data signal" refers to a signal whose one or more characteristics are altered or set in a manner that encodes information in the signal. Modulation can be analog, digital, or a hybrid modulation technique.

[0074] By way of example and not limitation, computer-readable storage media may include volatile and non-volatile, removable and non-removable media implemented by any method or technique for storing 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 memories such as random access memory (RAM, DRAM, SRAM); and non-volatile memories 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 hereafter developed capable of storing computer-readable information / data for use by a computer system.

[0075] Herein, one embodiment of this application includes an apparatus comprising 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 apparatus is triggered to run a method and / or technical solution based on the foregoing embodiments of this application.

[0076] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within this application. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in the apparatus claims may also be implemented by a single unit or device in software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any particular order.

Claims

1. A method for analyzing welding data, wherein, The method includes: Define the welding data analysis task, wherein the welding data analysis task includes short-circuit transition analysis or data filtering analysis; Based on the welding data analysis task and the welding data, analysis parameter information matching the welding data analysis task is determined, wherein the welding data analysis task is used to determine the analysis algorithm matching the welding data analysis task, and the analysis algorithm, in combination with the welding data, is used to determine the analysis parameter information; Based on the analysis parameter information and the welding data, determine the analysis result information corresponding to the welding data analysis task; The welding data analysis task includes short-circuit transition analysis. The analysis parameters include an optimal short-circuit voltage threshold and an optimal short-circuit time threshold. The optimal short-circuit voltage threshold is used for segmentation to distinguish between the arcing stage and the short-circuit stage, and the optimal short-circuit time threshold is used to identify abnormal short-circuit data. Determining the analysis parameters matching the welding data analysis task based on the welding data includes: determining the optimal short-circuit voltage threshold using a genetic algorithm based on the welding data. The fitness function of the genetic algorithm is determined based on the standard deviation of welding data with voltage values ​​greater than the short-circuit voltage threshold and the standard deviation of welding data with voltage values ​​less than the short-circuit voltage threshold. Based on the optimal short-circuit voltage threshold, determining the short-circuit interval data corresponding to the welding data; and determining the optimal short-circuit time threshold based on the short-circuit interval data. Alternatively, The welding data analysis task includes data filtering analysis; determining the analysis parameter information matching the welding data analysis task based on the welding data includes: using Fast Fourier Transform to determine the frequency sequence and corresponding amplitude sequence of the welding data, and plotting the corresponding spectrum based on the frequency sequence and corresponding amplitude sequence; determining one or more frequency windows in the spectrum that meet the amplitude conditions, wherein the amplitude conditions include the amplitude information corresponding to the frequency window matching the total amplitude information; and determining the analysis parameter information matching the data filtering analysis based on the one or more frequency windows, wherein the analysis parameter information includes cutoff frequency information.

2. The method according to claim 1, wherein, The step of determining the optimal short-circuit voltage threshold using a genetic algorithm based on welding data includes: Based on the welding data, construct the fitness function for the genetic algorithm; The corresponding population is determined based on the preset short-circuit voltage threshold search range; Based on the fitness function, the population is updated and iterated until the iteration condition is met; The optimal short-circuit voltage threshold is determined based on the updated population.

3. The method according to claim 1, wherein, The step of determining the short-circuit interval data corresponding to the welding data based on the optimal short-circuit voltage threshold includes: Based on the optimal short-circuit voltage threshold, multiple short-circuit transition intervals corresponding to the welding data are determined; Based on the plurality of short-circuit transition intervals, short-circuit interval data is determined, wherein the short-circuit interval data includes short-circuit data information corresponding to each of the plurality of short-circuit transition intervals, and the short-circuit data information includes the average voltage and short-circuit time corresponding to the short-circuit transition interval.

4. The method according to claim 1, wherein, The step of determining the optimal short-circuit time threshold based on the short-circuit interval data includes: An unsupervised anomaly detection algorithm is used to determine the classification information corresponding to the short-circuit interval data, wherein the classification information includes normal data information or abnormal data information; Based on the short-circuit interval data, a short-circuit time series is determined, wherein the short-circuit time series includes multiple short-circuit time elements; Determine the proportion of normal data information corresponding to each of the plurality of short-circuit time elements; Based on the aforementioned ratio information, the optimal short-circuit time threshold is determined.

5. The method according to claim 4, wherein, Determining the optimal short-circuit time threshold based on the ratio information includes: Based on the ratio information, a corresponding ratio sequence is determined, wherein the ratio information elements in the ratio sequence correspond to the short-circuit time elements in the short-circuit time sequence; Determine the target subsequence in the proportional sequence; The optimal short-circuit time threshold is determined based on the target subsequence.

6. The method according to claim 1, wherein, Based on the one or more frequency windows, analysis parameter information matching the data filtering analysis is determined, wherein the analysis parameter information includes cutoff frequency information including: The target frequency window is determined from the one or more frequency windows based on the window width of each frequency window in the one or more frequency windows; The corresponding cutoff frequency information is determined based on the target frequency window.

7. A computer device for performing welding data analysis, 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 as described in any one of claims 1 to 6.

8. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method as described in any one of claims 1 to 6.

Images