Intelligent welding platform data acquisition method and system based on Internet of Things

Abstract

The invention relates to the technical field of welding data processing, in particular to an intelligent welding platform data acquisition method and system based on the Internet of Things. The method comprises the steps of performing curve fitting on an observation range of a current data point, and obtaining a real index of the current data point through a fitting error of the current data point and fitting errors of other current data points except the current data point in the observation range; the authenticity of the current data point is obtained through the Pearson's correlation coefficient between the observation range of the current data point and the observation range of the corresponding voltage data point and the real index of the current data point; in the HANTS algorithm, the corrected difference value is obtained through the product of the authenticity of the current data point and the difference value of the current data point before and after denoising, data denoising is achieved based on the corrected difference value, and the accuracy of welding data collection is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of welding data processing, and in particular to a data acquisition method and system for an intelligent welding platform based on the Internet of Things. Background Art

[0002] The intelligent welding platform is an important part of intelligent manufacturing in the industrial era. It integrates a number of cutting-edge technologies, can quickly switch between different welding tasks, meet the production needs of small batches and multiple varieties, and improve welding quality and production efficiency. By installing various sensors on the welding machine to obtain various parameters during the welding process, remote monitoring and management of the welding process can be achieved.

[0003] In the prior art, research on the application of welding data tends to evaluate the welding effect. For example, a patent application document with publication number CN115186423A discloses a method for evaluating the welding capacity of a narrow lap resistance welding machine. The method collects strip steel and welding process parameters; calculates the height of the weld nugget and the total heat required for welding; calculates the total resistance at the weld, the effective heat generated at the weld, and the target function value; determines whether the target function value meets the conditions, if not, the evaluation result is that it does not meet the welding requirements. If so, the inner and outer stresses of the resistance welding machine frame beams and columns are calculated, and then it is determined whether the inner and outer stresses meet the conditions. If so, the evaluation result is that it meets the welding requirements, otherwise, the welding parameters exceed the capacity of the resistance welding machine.

[0004] The above-mentioned prior art can improve production efficiency by analyzing welding process parameters to evaluate welding effects. However, there may be interference from noise data in the process of collecting welding data and transmitting data through the Internet of Things, which has low accuracy, resulting in poor accuracy of the welding evaluation effect obtained based on this.

[0005] Based on this, how to effectively improve the accuracy of welding data collection is an urgent problem to be solved by technical personnel in this field. Summary of the invention

[0006] In order to solve the technical problem of how to effectively improve the accuracy of welding data collection, the present invention provides a data collection method and system for an intelligent welding platform based on the Internet of Things.

[0007] In the first aspect, the present invention provides a data collection method for an intelligent welding platform based on the Internet of Things, which adopts the following technical solutions: The data collection method of the intelligent welding platform based on the Internet of Things includes the following steps: The observation range of the current data point and the voltage data point in the preset welding process in the current data time series sequence and the voltage data time series sequence is performed; the observation range of the current data point is curve fitted to obtain the ratio of the fitting error of the current data point to the mean of the fitting errors of other current data points in the observation range except the current data point, and the negative number of the ratio is used as the exponent of the exponential function with e as the base to obtain the true index of the current data point; the product of the Pearson correlation coefficient between the observation range of the current data point and the observation range of the corresponding voltage data point and the true index of the current data point is obtained, and the negative number of the product is used as the exponent of the exponential function with e as the base to obtain the authenticity of the current data point; in the HANTS algorithm, the authenticity of the current data point is obtained by multiplying the difference before and after denoising the current data point to obtain the corrected difference, and data denoising is implemented based on the corrected difference.

[0008] The present invention takes into account the possibility of noise interference during the current data collection process, and therefore uses the HANTS algorithm to denoise the current data points that are prominent in the current data time series sequence, which can effectively reduce the impact of noise data on subsequent data processing. In this process, the present invention takes into account that the normal changing current data points are similar to the noise data, and directly screens the noise data based on the prominence of the current data points, which may identify the normal changing current data as noise data. Based on this, the present invention further verifies the authenticity of the current data points by obtaining the correlation between the current data and the voltage data, so that the noise data in the current data time series sequence can be accurately identified, effectively improving the accuracy of welding data collection.

[0009] According to the data acquisition method for an intelligent welding platform based on the Internet of Things provided by the present invention, the observation range of the current data points and the voltage data points in the preset welding process in the current data time series sequence and the voltage data time series sequence, also includes: collecting the current data and the voltage data in the welding process, and obtaining the current data time series sequence and the voltage data time series sequence after preprocessing.

[0010] The present invention takes into account that the originally collected current simulation data is not conducive to subsequent data processing, and therefore adjusts the original current data through preprocessing to facilitate subsequent data processing.

[0011] According to the data acquisition method of the intelligent welding platform based on the Internet of Things provided by the present invention, the observation range acquisition method of the current data point and the voltage data point includes: presetting the length of the observation range , taking the current data point or voltage data point as the center, obtain equal amounts on both sides current data points or voltage data points to obtain the corresponding observation range.

[0012] The present invention takes into account that normal data changes relatively slowly over a period of time, while noise data points are more prominent. Therefore, by acquiring other current data points equally on both sides of the current data point to construct an observation range, the degree of data mutation of the current data point in the local range can be accurately obtained based on this.

[0013] According to the data acquisition method for an intelligent welding platform based on the Internet of Things provided by the present invention, the curve fitting of the observation range of the current data points includes: performing least squares fitting with the time series number of each current data point in the observation range as the horizontal coordinate and the current value corresponding to the current data point as the vertical coordinate to obtain the fitting value of each current data point in the observation range.

[0014] According to the data acquisition method of the intelligent welding platform based on the Internet of Things provided by the present invention, the method for obtaining the difference between the current data points before and after denoising includes: decomposing the current data time series sequence into multiple harmonic components, removing the high-frequency noise, and then recombining to obtain the target current data time series sequence; determining the difference between the current data points in the current data time series sequence and the target current data time series sequence.

[0015] The present invention denoises outstanding current data points in the current data time series sequence through the HANTS algorithm, which can better retain the details of the current data itself while denoising the data, and interpolate the missing data while denoising, effectively ensuring the integrity of the current data.

[0016] According to the data acquisition method for an intelligent welding platform based on the Internet of Things provided by the present invention, data denoising is achieved based on the corrected difference, including: presetting a noise threshold; and removing current data points whose corrected difference is greater than the noise threshold as noise points to achieve data denoising.

[0017] According to the data acquisition method of the intelligent welding platform based on the Internet of Things provided by the present invention, the data denoising is implemented, and then the following further comprises: abnormal monitoring of the current data time series sequence during the welding process.

[0018] The present invention takes into account that the current data generated during the welding process can reflect the state of welding. If the current data is abnormal, it means that there may be an abnormality in the welding process. Therefore, the present invention also reduces safety hazards by monitoring the abnormality of the current data time series during the welding process.

[0019] In the second aspect, the present invention provides an intelligent welding platform data acquisition system based on the Internet of Things, which adopts the following technical solutions: The data acquisition system of an intelligent welding platform based on the Internet of Things includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the data acquisition method of the intelligent welding platform based on the Internet of Things is implemented.

[0020] By adopting the above technical solution, the above-mentioned data acquisition method of the intelligent welding platform based on the Internet of Things is generated into a computer program and stored in the memory to be loaded and executed by the processor, so that a terminal device is made according to the memory and the processor for easy use.

[0021] The present invention has the following technical effects: Based on the above technical solution, the present invention uses the HANTS algorithm to denoise the current data points with outstanding performance in the current data time series sequence during the data acquisition process of the intelligent welding platform, which can effectively reduce the impact of noise data on subsequent data processing. In this process, the present invention further verifies the authenticity of the current data points by obtaining the correlation between the current data and the voltage data, so that the noise data in the current data time series sequence can be accurately identified, and the impact of the current data that is similar to the noise data on the denoising effect is reduced, which effectively improves the accuracy of welding data acquisition. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0023] Figure 1 A schematic flow chart of a data collection method for an intelligent welding platform based on the Internet of Things provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0025] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0026] It should be noted that the intelligent welding platform is an important part of intelligent manufacturing in the industrial era. It can quickly switch between different welding tasks, meet the production needs of small batches and multiple varieties, and improve welding quality and production efficiency. By installing various sensors on the welding machine to obtain various parameters during the welding process, remote monitoring and management of the welding process can be achieved.

[0027] Arc welding is one of the commonly used welding methods in industrial production. It uses the heat generated by arc discharge to melt the electrode and the workpiece together and form a weld after condensation, thereby obtaining a strong joint. However, there may be interference from noise data in the process of collecting welding data and transmitting data through the Internet of Things, resulting in low accuracy of the collected welding data.

[0028] Based on this, the embodiment of the present invention discloses a data collection method for an intelligent welding platform based on the Internet of Things, which can effectively improve the accuracy of the collected welding data by performing data denoising on the collected welding data. Figure 1 As shown, Figure 1 A flow chart of a data collection method for an intelligent welding platform based on the Internet of Things provided in an embodiment of the present invention, the method specifically includes the following steps.

[0029] S1: Preset the observation range of the current data point in the current data time series sequence during the welding process.

[0030] For example, in an embodiment of the present invention, the observation range of the current data point in the welding process is preset in the current data time series sequence, which also includes: collecting the current data in the welding process and obtaining the current data time series sequence after preprocessing.

[0031] The preprocessing may be data format conversion, etc., which may be specifically configured according to actual needs, and the embodiment of the present invention does not impose too many limitations thereon.

[0032] Specifically, the current data is collected by setting a collection frequency for the current sensor, taking the current value obtained by each collection as a current data point, and arranging the current data points according to the collection time sequence to obtain a current data time series sequence.

[0033] Among them, the acquisition frequency table can be set to 10Hz, which can be set according to actual needs.

[0034] It should be noted that the Harmonic Analysis of Time Series (HANTS) algorithm is an algorithm used for time series analysis and interpolation. By comparing the original time series with the fitted time series, the algorithm regards the points that obviously deviate from the fitting curve as noise points, and uses the known harmonic components to estimate the missing data points, thereby achieving data denoising while ensuring the integrity and continuity of the data and retaining the detailed information of the original data. Therefore, the HANTS algorithm can be used to accurately denoise the current data time series.

[0035] However, the current data usually changes with the change of the parameters of the object to be welded. Therefore, if the noise data points in the current data time series are obtained directly based on the difference between the original current data time series and the fitted current data time series, the normally changing current data points may be identified as noise data, affecting the accuracy of denoising.

[0036] Based on this, an embodiment of the present invention obtains the degree of damage to the data performance of the current data point in the local range by obtaining the possibility that it is noise data. The more prominent the current data point is, the higher the possibility that it is noise data is. The difference between the original current data time series sequence and the fitted current data time series sequence is corrected through the possibility that the current data point is noise data.

[0037] For example, in an embodiment of the present invention, the method for obtaining the observation range of current data points specifically includes the following two possible implementation methods: In a possible implementation, the length of the observation range can be preset , taking the current data point as the center, obtain equal amounts on both sides current data points to obtain the corresponding observation range.

[0038] Among them, the length of the observation range can be preset to 21, and can be set according to actual needs.

[0039] It is understandable that for some current data points, the number of data points on one side may be insufficient to construct the observation range. For such current data points, the remaining number of current data points can be supplemented on the other side.

[0040] In this way, the embodiment of the present invention can better analyze the data changes on both sides of the current data point by acquiring the current data on the left and right sides of the current data point as the observation range of the current data point, thereby accurately obtaining the data mutation situation relative to the observation range.

[0041] In another possible implementation, the length of the observation range can be preset , taking the current data point as the end of its observation range, obtain current data points to obtain the corresponding observation range.

[0042] In this way, by acquiring historical data as the observation range of the current current data point, the embodiment of the present invention can better reflect the regular change rules and trends of the current data, based on which the prominence of the current current data point compared with the surrounding historical data can be accurately obtained.

[0043] After obtaining the observation range of the current data point based on any of the above possible implementations, the possibility that the current data point is noise data can be obtained based on the prominence of the current data point compared to the observation range, that is, continue to perform the following steps.

[0044] S2: Perform curve fitting on the observation range of the current data point, obtain the ratio of the fitting error of the current data point to the mean of the fitting errors of other current data points in the observation range except the current data point, and use the negative of the ratio as the exponent of the exponential function with e as the base to obtain the true index of the current data point.

[0045] It should be noted that the destructiveness of the current data point to the data change in its observation range can be characterized by the fitting error when the curve is fitted to the observation range. The larger the fitting error, the more destructive the current data point is to the data change in its observation range, and the greater the degree of mutation.

[0046] By way of example, in an embodiment of the present invention, curve fitting is performed on the observation range of the current data points, including: performing least squares fitting with the time series number of each current data point in the observation range as the horizontal coordinate and the current value corresponding to the current data point as the vertical coordinate to obtain the fitting value of each current data point in the observation range.

[0047] For example, to determine the true index of the current data point, please refer to the following relationship: ; In the formula, represents the true indicator of the ith current data point, represents the number of current data points in the observation range of the i-th current data point, represents the current value of the i-th current data point, represents the fitted value of the i-th current data point, represents the current value of the jth current data point in the observation range of the i-th current data point, represents the fitted value of the jth current data point in the observation range of the i-th current data point except the i-th current data point itself, Represents an exponential function with base e.

[0048] In the above formula, It represents the fitting error of the i-th current data point. The larger the value is, the more prominent the current value of the i-th current data point is relative to the entire observation range. The possibility that the current data point is the real data generated by the current data itself is lower, and the corresponding real index is also lower.

[0049] It represents the mean fitting error of other current data points except the current data point in the observation range of the i-th current data point. The larger the mean fitting error is, the larger the fitting error of other current data points is. The lower the destructive credibility of the fitting error of the i-th current data point is, the lower the true index of the corresponding i-th current data point is.

[0050] After obtaining the true index of each current data point based on the above formula, continue to perform the following steps.

[0051] S3: Obtain the observation range of the voltage data point corresponding to the current data point in the voltage data time series sequence, and correct the true index of the current data point by the correlation between the observation range of the current data point and the observation range of the corresponding voltage data point to obtain the authenticity of the current data point.

[0052] The method for obtaining the observation range of the voltage data point is similar to the method for obtaining the observation range of the current data point, and the embodiment of the present invention will not be described in detail here.

[0053] It should be noted that the current data usually changes with the parameters of the object to be welded or the welding speed and other factors. If the noise data is obtained directly based on the real index of the current data point obtained in the above steps, the normal changing current data point may be identified as noise data, reducing the real index. In the arc welding process, the increase in welding current will lead to an increase in the resistance heat of the arc, thereby increasing the arc temperature and the arc diameter. In order to maintain the stability of the arc and a good molten pool shape, the welding voltage will increase to adapt to such changes. There is a good positive correlation between the voltage data and the current data.

[0054] Based on this, the embodiment of the present invention can correct the true index of the current data point obtained in the above steps by obtaining the correlation between the voltage data and the current data, so as to accurately obtain the authenticity of the current data point.

[0055] For example, in an embodiment of the present invention, obtaining the observation range of the voltage data point corresponding to the current data point in the voltage data time series sequence also includes: collecting the voltage data during the welding process, and obtaining the voltage data time series sequence after preprocessing.

[0056] The preprocessing method may be specifically set according to actual needs, and the embodiment of the present invention does not impose too many limitations on this.

[0057] Specifically, the voltage data is collected by setting the collection frequency for the voltage sensor, taking the voltage value collected each time as a voltage data point, and arranging the voltage data points according to the collection time sequence to obtain a voltage data time series sequence. The voltage data points in the obtained voltage data time series sequence correspond to the current data points in the current data time series sequence one by one, that is, at the same collection time, a voltage value and a current value can be collected at the same time.

[0058] By way of example, in an embodiment of the present invention, the authenticity of the current data point is obtained by correcting the true indicator of the current data point through the degree of correlation between the observation range of the current data point and the observation range of the corresponding voltage data point, including: obtaining the product of the Pearson correlation coefficient between the observation range of the current data point and the observation range of the corresponding voltage data point and the true indicator of the current data point, and using the negative of the product as the exponent of an exponential function with base e to obtain the authenticity of the current data point.

[0059] For example, to determine the authenticity of the current data point, please refer to the following relationship: ; In the formula, represents the authenticity of the i-th current data point, represents the true indicator of the ith current data point, represents the Pearson correlation coefficient between the observation range of the ith current data point and the observation range of the corresponding voltage data point, Represents an exponential function with base e.

[0060] In the above formula, the larger the Pearson correlation coefficient between the observation range of the current data point and the observation range of the corresponding voltage data point, the greater the correlation between the observation range of the current data point and the observation range of the corresponding voltage data point, the greater the possibility that the current value of the current data point is a normal change, and the higher the authenticity of the current data point.

[0061] After the correlation between each current data point and the corresponding voltage data point is obtained based on the above steps to correct the authenticity index of the current data point, the difference can be corrected based on the authenticity of each current data point, that is, continue to perform the following steps.

[0062] S4: In the HANTS algorithm, the corrected difference is obtained by multiplying the authenticity of the current data point and the difference before and after denoising the current data point, and data denoising is implemented based on the corrected difference.

[0063] It should be noted that the HANTS algorithm compares the difference between the original time series and the fitted time series, and obtains the noise points that obviously deviate from the fitting curve through the difference. However, this processing method will identify the normally changing current data as noise data. Therefore, the embodiment of the present invention obtains the authenticity of each current data point based on the above steps. The higher the authenticity, the higher the possibility that the current value of the current data point is caused by normal changes.

[0064] Based on this, the embodiment of the present invention corrects the difference by the authenticity of each current data point, which can effectively improve the accuracy of noise data recognition.

[0065] By way of example, in an embodiment of the present invention, a method for obtaining the difference between current data points before and after denoising includes: decomposing a current data time series sequence into multiple harmonic components, removing high-frequency noise, and then recombining to obtain a target current data time series sequence; and determining the difference between the data of the current data point between the current data time series sequence and the target current data time series sequence.

[0066] Among them, the current data time series can be decomposed into multiple harmonic components through Fourier transform.

[0067] It can be understood that at the same acquisition time, the current data point has a corresponding current value in both the current data time series sequence and the target current data time series sequence, and the difference between the current values ​​is determined.

[0068] For example, in an embodiment of the present invention, data denoising is implemented based on the corrected difference, including: presetting a noise threshold; and removing current data points whose corrected difference is greater than the noise threshold as noise points to implement data denoising.

[0069] The noise threshold may be set to 0.2. The noise threshold may be set according to actual needs, and the embodiment of the present invention does not impose too many limitations on this.

[0070] Specifically, after data denoising is achieved, the low-frequency harmonic components that reflect the main characteristics of the target current data time series can also be identified and selected, and the low-frequency harmonic components are processed by the least squares method to obtain a harmonic model. The harmonic model can be used to capture the periodic changes and main trends in the target current data time series to obtain the current prediction value; the position of the noise point is obtained, and the position of the noise point is interpolated by the current prediction value. Repeat the data denoising and interpolation steps until the difference of all current data points in the current data time series is no greater than the noise threshold.

[0071] After the current data time series sequence is denoised based on the above steps, the current data time series sequence can also be monitored for abnormalities to reduce safety hazards.

[0072] For example, in an embodiment of the present invention, data denoising is implemented, and then the method further includes: performing abnormal monitoring on the timing sequence of current data during the welding process.

[0073] The specific steps of performing abnormal monitoring on the current data time series can be implemented by the existing technology, and will not be described in detail in the embodiment of the present invention.

[0074] It can be seen that in the embodiment of the present invention, when realizing data collection of the intelligent welding platform based on the Internet of Things, the observation range of the current data point and the voltage data point in the welding process in the current data time series sequence and the voltage data time series sequence can be preset; the observation range of the current data point is curve fitted to obtain the ratio of the fitting error of the current data point to the mean of the fitting errors of other current data points in the observation range except the current data point, and the negative of the ratio is used as the exponent of the exponential function with e as the base to obtain the true index of the current data point; the product of the Pearson correlation coefficient between the observation range of the current data point and the observation range of the corresponding voltage data point and the true index of the current data point is obtained, and the negative of the product is used as the exponent of the exponential function with e as the base to obtain the authenticity of the current data point; in the HANTS algorithm, the authenticity of the current data point is obtained by multiplying the difference before and after denoising the current data point to obtain the corrected difference, and data denoising is implemented based on the corrected difference.

[0075] In this way, the embodiment of the present invention uses the HANTS algorithm to denoise the current data points that are outstanding in the current data time series, which can effectively reduce the impact of noise data on subsequent data processing. In this process, the embodiment of the present invention takes into account that the normal changing current data points are similar to the noise data. Based on this, the embodiment of the present invention further verifies the authenticity of the current data points by obtaining the correlation between the current data and the voltage data, so that the noise data in the current data time series can be accurately identified, effectively improving the accuracy of welding data acquisition.

[0076] An embodiment of the present invention also discloses an intelligent welding platform data acquisition system based on the Internet of Things, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, the intelligent welding platform data acquisition method based on the Internet of Things provided by the present invention is implemented.

[0077] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0078] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM, a dynamic random access memory DRAM, a static random access memory SRAM, an enhanced dynamic random access memory EDRAM, a high bandwidth memory HBM, a hybrid memory cube HMC, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0079] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0080] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. The data acquisition method of the intelligent welding platform based on the Internet of Things is characterized by: include: Preset the observation range of the current data point and the voltage data point in the current data time series sequence and the voltage data time series sequence during the welding process; Performing curve fitting on the observation range of the current data point, obtaining the ratio of the fitting error of the current data point to the mean of the fitting errors of other current data points in the observation range except the current data point, and using the negative of the ratio as the exponent of an exponential function with e as the base to obtain the true index of the current data point; Obtain the product of the Pearson correlation coefficient between the observation range of the current data point and the observation range of the corresponding voltage data point and the true index of the current data point, and use the negative of the product as the exponent of an exponential function with base e to obtain the authenticity of the current data point; In the HANTS algorithm, the corrected difference is obtained by multiplying the authenticity of the current data point and the difference before and after denoising the current data point, and data denoising is achieved based on the corrected difference.

2. The data acquisition method for an intelligent welding platform based on the Internet of Things according to claim 1 is characterized in that: The observation range of the current data point and the voltage data point in the preset welding process in the current data time series sequence and the voltage data time series sequence also includes: The current data and voltage data during the welding process are collected, and the current data time series sequence and the voltage data time series sequence are obtained after preprocessing.

3. The data acquisition method for an intelligent welding platform based on the Internet of Things according to claim 1 is characterized in that: The method for obtaining the observation range of the current data point and the voltage data point includes: Preset observation range length , taking the current data point or voltage data point as the center, obtain equal amounts on both sides current data points or voltage data points to obtain the corresponding observation range.

4. The data acquisition method for an intelligent welding platform based on the Internet of Things according to claim 1 is characterized in that: The curve fitting of the observation range of the current data points includes: The least squares method is used to fit the time sequence number of each current data point in the observation range as the horizontal axis and the current value corresponding to the current data point as the vertical axis to obtain the fitting value of each current data point in the observation range.

5. The data acquisition method for an intelligent welding platform based on the Internet of Things according to claim 1 is characterized in that: The method for obtaining the difference between the current data points before and after denoising includes: The current data time series sequence is decomposed into multiple harmonic components, high-frequency noise is removed, and then recombined to obtain a target current data time series sequence; and the difference between the current data points in the current data time series sequence and the target current data time series sequence is determined.

6. The data acquisition method for an intelligent welding platform based on the Internet of Things according to claim 5 is characterized in that: The method of realizing data denoising based on the corrected difference comprises: A noise threshold is preset; current data points whose corrected difference is greater than the noise threshold are removed as noise points to achieve data denoising.

7. The data acquisition method for an intelligent welding platform based on the Internet of Things according to claim 6 is characterized in that: The data denoising is implemented, and then further includes: The abnormality of the current data timing sequence during the welding process is monitored.

8. The intelligent welding platform data acquisition system based on the Internet of Things is characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the data acquisition method for the intelligent welding platform based on the Internet of Things according to any one of claims 1 to 7 is implemented.

Images