Computer-assisted shipbuilding welding digital twin construction method

Abstract

The invention relates to the technical field of parameter prediction of a welding process, in particular to a computer-aided shipbuilding welding digital twin construction method, which comprises the following steps of: acquiring the temperature of a welding pool and the welding current of a welding gun head in real time, acquiring the vibration data of welding equipment in the welding process in real time, and calculating the temperature of the welding pool and the welding current of the welding gun head; stress at the joints of the hull ribs is welded; the change rate of the temperature of the welding pool at each moment and the stability degree of the welding current are analyzed, and the thermodynamic stability index at each moment during ship assembling and welding is determined; the correlation between the thermal temperature index and the vibration data and the correlation between the thermal temperature index and the stress in the time domain and the correlation between the thermal temperature index and the stress in the frequency domain in the time sequence are analyzed, and the mechanical coupling degree of the ship at all moments during assembling and welding is determined; and in combination with the mechanical coupling degree of the time sequence and the welding current, the time sequence prediction model is utilized to predict the welding current within a preset time period after the current moment. According to the method, the prediction robustness of the welding current in a complex scene is improved.

Description

Technical Field

[0001] This application relates to the technical field of parameter prediction in welding processes, and specifically relates to a method for constructing a digital twin of ship manufacturing welding under computer assistance. Background Art

[0002] The construction of a digital twin for ship manufacturing welding refers to constructing a virtual model of the welding link in the ship manufacturing process through digital means to achieve functions such as real-time monitoring, simulation, optimization, and management. It is based on the physical-world ship manufacturing welding process, and through technical means such as sensors and cloud computing, data is acquired in real time and analyzed, and the virtual model is dynamically updated to achieve a comprehensive digital simulation and management of the entire ship welding process.

[0003] Although existing ship manufacturing welding technologies have introduced digital means, the complexity of coupled modeling of multiple physical fields (heat, force, vibration) is high. Traditional simulation methods rely on simplified assumptions and are difficult to accurately describe the non-linear interaction of multiple physical fields, resulting in prediction deviations in the thermal stress distribution of ship manufacturing welding and inaccuracies in the dynamic behavior of the molten pool. When sudden vibrations or non-linear fluctuations in the thermal physical properties of materials occur, traditional welding current prediction methods cannot distinguish normal fluctuations from abnormal disturbances, resulting in insufficient prediction robustness of welding current under sudden disturbances and inaccurate control of the heat input to the molten pool. Summary of the Invention

[0004] To solve the above technical problems, this application provides a method for constructing a digital twin of ship manufacturing welding under computer assistance to solve existing problems.

[0005] The method for constructing a digital twin of ship manufacturing welding under computer assistance in this application adopts the following technical solutions: An embodiment of this application provides a method for constructing a digital twin of ship manufacturing welding under computer assistance, and this method includes the following steps: Collect the temperature of the welding molten pool and the welding current at the head of the welding torch in real time, collect the vibration data of the welding equipment during the welding process, and the stress at the connection of the ship's hull ribs in real time; Form the current sequence at each moment from the welding currents at each moment and all previous moments, use the statistical process control algorithm to obtain the process capability index and the process capability offset index of the current sequence, calculate the gradient modulus value of the temperature of the welding molten pool at each moment, and determine the thermal-mechanical stability index at each moment during ship welding based on the process capability index, the process capability offset index, and the gradient modulus value; wherein, the thermal-mechanical stability index is positively correlated with both the process capability index and the process capability offset index, and negatively correlated with the gradient modulus value; Form a thermal stability sequence, a vibration sequence, and a stress sequence with the thermal stability indices, vibration data, and stresses at each moment and all previous moments respectively; Use grey relational analysis to obtain the grey relational degree between the thermal stability sequence and the vibration sequence at each moment, denoted as the first relational degree. Correspondingly, obtain the grey relational degree between the thermal stability sequence and the stress sequence at each moment, denoted as the second relational degree; Perform continuous wavelet transform on the thermal stability sequence and the vibration sequence at each moment to obtain the wavelet coherence between the thermal stability sequence and the vibration sequence, denoted as the first coherence. Correspondingly, obtain the wavelet correlation between the thermal stability sequence and the stress sequence, denoted as the second coherence; Fuse the first relational degree, the second relational degree, the first coherence, and the second coherence to obtain the mechanical coupling degree at each moment during ship welding and assembly; Combine the mechanical coupling degree in time series with the welding current, and use a time series prediction model to predict the welding current within a preset time period after the current moment.

[0006] In one embodiment, the determination of the thermal stability index is as follows: Calculate the product of the process capability index and the process capability offset index, calculate the sum of the gradient modulus value and a preset value greater than 0, and the thermal stability index is the ratio of the product to the sum.

[0007] In one embodiment, the current sequence is arranged in chronological order.

[0008] In one embodiment, the determination of the mechanical coupling degree includes: Calculate the mean of the first relational degree and the second relational degree, denoted as the first mean. Calculate the mean of the first coherence and the second coherence, denoted as the second mean. The mechanical coupling degree is positively correlated with both the first mean and the second mean.

[0009] In one embodiment, the mechanical coupling degree is the product of the first mean and the second mean.

[0010] In one embodiment, the prediction of the welding current within a preset time period after the current moment includes: Form a mechanical coupling sequence with the mechanical coupling degrees at the current moment and all previous moments. Use the current moment's current sequence as the input of the time series prediction model, and combine the mechanical coupling sequence to obtain the prediction result of the welding current after the current moment.

[0011] In one embodiment, the mechanical coupling sequence serves as an exogenous variable of the time series prediction model.

[0012] In one embodiment, the time series prediction model is an autoregressive integrated moving average model.

[0013] The present application has at least the following beneficial effects: The present application collects the temperature of the welding molten pool and the welding current at the head of the welding torch in real time, collects the vibration data of the welding equipment during the welding process, and the stress at the connection of the hull ribs in real time; analyzes the change rate of the temperature of the welding molten pool at each moment and the stability of the welding current, and determines the thermal stability index at each moment during ship welding; the thermal stability index improves the refined perception ability of the welding thermal dynamic process. The real-time monitoring of the temperature change rate can capture the instantaneous abnormality of the molten pool heat conduction, while the quantitative evaluation of the welding current stability overcomes the limitation of the traditional method that only relies on the current threshold judgment, enhancing the stability of the thermal balance from the energy input dimension. The combination of the two helps to synchronously optimize the heat source control and the solidification behavior of the molten pool, reducing weld cracks or deformations caused by thermal stress concentration; respectively analyzes the correlation of the thermal temperature index with the vibration data and the stress in the time domain and the frequency domain in time series, and determines the mechanical coupling degree at each moment during ship welding; the calculation of the mechanical coupling degree enhances the real-time detection ability of the mechanical disturbance during the welding process. The time domain correlation analysis can identify the direct impact of the vibration and stress mutations on the thermal state, and the frequency domain correlation reveals the potential threat of the periodic mechanical load to the welding quality. The mechanical coupling degree describes the dynamic coupling strength between the thermal stability and the mechanical environment during the ship manufacturing and welding process, improving the accuracy of the thermal stability detection during the welding process; combines the mechanical coupling degree with the welding current in time series, and uses the time series prediction model to predict the welding current within a preset time period after the current moment. The mechanical coupling degree, as an exogenous variable of the time series prediction model, provides additional environmental information for the time series prediction model, enabling it to distinguish normal fluctuations from abnormal disturbances. When the mechanical coupling degree drops suddenly, the time series prediction model can combine the current mechanical coupling state to predict the possible penetration fluctuation caused by vibration in the molten pool, making up for the limitation of single physical quantity prediction, significantly enhancing the prediction robustness of the welding current in complex scenarios, and finally realizing more accurate and real-time prediction of the welding current trend, reducing the penetration width deviation and energy fluctuation, and improving the welding quality of ship manufacturing. Description of the Drawings

[0014] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0015] Figure 1The flowchart of the steps of a method for constructing a digital twin for ship manufacturing welding assisted by a computer provided by this application; Figure 2 It is the flowchart for welding current prediction. Detailed implementation manners

[0016] In order to further elaborate on the technical means and effects adopted by this application to achieve the intended invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details a method for constructing a digital twin for ship manufacturing welding assisted by a computer proposed according to this application, including its specific implementation manners, structures, features and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0017] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs.

[0018] The following specifically describes the specific solution of a method for constructing a digital twin for ship manufacturing welding assisted by a computer provided by this application in combination with the accompanying drawings.

[0019] A method for constructing a digital twin for ship manufacturing welding assisted by a computer provided by an embodiment of this application. Specifically, a method for constructing a digital twin for ship manufacturing welding assisted by a computer is provided as follows. Please refer to Figure 1 , and this method includes the following steps: Step S001: Real-time collect the temperature of the welding molten pool, the welding current at the head of the welding torch, the vibration data of the welding equipment during the welding process, and the stress at the connection of the ship's hull ribs.

[0020] A digital twin refers to a virtual model of a physical entity established through digital technology. It can reflect the state, behavior and performance of the physical entity in real time and can perform operations such as simulation, prediction and optimization. A digital twin is a bridge between the physical and digital worlds, obtaining data of the physical entity through sensors and data acquisition devices, so as to monitor, analyze and control the actual physical system. During the welding process of ship manufacturing, the application of digital twins can greatly improve production efficiency, reduce errors and optimize quality management. For example, using sensors to collect data such as temperature and stress in the welding area and feeding them back into the digital twin to monitor the welding quality in real time. Or through the integration of sensors and prediction models, the digital twin can analyze the state of the welding equipment, detect potential faults in advance, and ensure the continuous and stable operation of the ship welding process.

[0021] Based on the above analysis, in the process of shipbuilding and assembly welding using a welding robot, this embodiment uses a non-contact infrared temperature sensor to collect the temperature of the welding pool at each moment in real time, and integrates a high-precision Hall current sensor in the welding gun head of the welding robot to collect the welding current at each moment in real time; strain gauge sensors are installed at the rib connections of the hull sections to collect local stresses at each moment in the welding process. In addition, a vibration sensor is installed at the supporting structure of the welding robot to collect vibration data of the welding equipment, that is, the welding robot, at each moment in the welding process.

[0022] In this embodiment, all types of data collected above are collected synchronously, and the collection frequency is 100 Hz. The implementer can set it according to the actual situation, and this embodiment does not limit it here.

[0023] Step S002, analyzing the change rate of the temperature of the welding pool at each moment and the stability of the welding current, and determining the thermal stability index at each moment during the ship assembly welding.

[0024] Due to the complexity of ship welding technology and the coupling characteristics of multiple physical fields, welding quality defects are easily caused by uneven thermal distribution and energy input fluctuations during welding. Specifically, the heat conduction process of the welding molten pool is affected by the combined effects of current fluctuations, nonlinear changes in material thermal physical parameters, and external environmental interference, which will cause abnormal temperature gradient distribution in the molten pool, leading to thermal stress concentration and uneven metal phase change in the weld area, which will induce welding deformation, microcracks and even macro-structural instability. At the same time, random fluctuations in welding current will destroy the stability of energy input, resulting in inconsistent penetration depth, deviation in penetration width or porosity defects, which will directly affect the mechanical properties and fatigue life of the weld.

[0025] In order to analyze the uniformity characteristics of the heat distribution of the molten pool, this embodiment first calculates the rate of change of the temperature of the welding molten pool at each moment, specifically, calculates the gradient of the temperature of the welding molten pool at each moment.

[0026] It should be noted that, in another embodiment, the difference between the temperature of the welding pool at each moment and the temperature of the welding pool at the previous moment can be calculated to measure the rate of change of the temperature of the welding pool at each moment, that is, the implementer can choose other existing methods to calculate the rate of change of temperature, and this embodiment does not limit it.

[0027] Then, in order to analyze the input stability of the welding energy, in this embodiment, the welding currents at each moment and all moments before it are arranged in chronological order to form the current sequence at each moment. The welding current at each moment is used as the input of the Statistical Process Control (SPC) algorithm to obtain the process capability index Cp of the welding current and the process capability offset index Cpk of the welding current. The process capability index Cp determines the potential stability of the welding energy input by comparing the actual fluctuation of the welding current with the design tolerance. The process capability offset index Cpk takes into account the mean shift on the basis of the process capability index Cp to comprehensively evaluate the actual stability of the welding energy input. In this embodiment, the design tolerance of the welding current, that is, the upper specification limit and the lower specification limit of the welding current, where the upper specification limit is the rated current of the welding current + 10A, and the lower specification limit is the rated current of the welding current - 10A.

[0028] It should be understood that the calculation of the SPC algorithm, the process capability index CP, and the process capability offset index Cpk are all well-known existing technologies, and the specific process will not be elaborated in detail in this embodiment.

[0029] It should be noted that the implementer can choose other existing feasible methods to measure the change stability of the current sequence data, such as standard deviation, coefficient of variation, etc., which are not limited in this embodiment.

[0030] Based on the above analysis, this embodiment calculates the thermal stability index at each moment during ship welding and assembly. The specific calculation method is as follows: ; where A is the thermal stability index at each moment during ship welding and assembly, Cp is the process capability index of the welding current, is the process capability offset index of the welding current, is the modulus of the temperature gradient of the welding pool at each moment, is a preset value greater than 0 to avoid the denominator being 0. In this embodiment, , which can be set by the implementer according to the actual situation and is not limited in this embodiment.

[0031] It should be understood that the process capability index Cp is the core index in statistical process control. The larger its value, the smaller the actual fluctuation of the welding current is far less than the design tolerance, indicating that the potential stability of the welding energy input is higher; the larger the process capability offset index Cpk, the closer the mean value of the welding current is to the rated current, and the smaller the fluctuation, the higher the actual stability of the welding energy input; quantifies the temperature change rate of the welding pool. The larger its value, the more uneven the temperature distribution is, the steeper the temperature gradient in the welding pool is, and the more likely it is to cause local stress concentration and welding defects.

[0032] The thermal stability index A is a multi-dimensional coupling index used to quantify the dynamic balance relationship between the stability of energy input and the uniformity of thermal distribution during the welding process. The larger the thermal stability index, the more stable the welding process is, indicating better thermal coupling.

[0033] Step S003: Analyze the correlations of the thermal temperature index with the vibration data and the stress in the time domain and frequency domain respectively, and determine the mechanical coupling degree at each moment during ship welding and assembly.

[0034] Since the ship welding process involves the dynamic coupling of multiple physical fields such as heat, force, and vibration, traditional single-dimensional monitoring indicators are difficult to comprehensively evaluate the welding quality risk. In a complex welding environment, although the thermal stability index can reflect the equilibrium state of energy input and the temperature field, the thermodynamic behavior of the welding pool will have a non-linear interaction with the mechanical stress field and external vibration interference: on the one hand, the non-uniform thermal expansion in the weld area will induce local stress concentration. When the stress accumulation exceeds the material yield limit, it will lead to weld deformation and even the initiation of micro-cracks; on the other hand, the mechanical vibration of the welding robot is transmitted to the welding torch through the welding robot, which may change the dynamic balance of the molten pool and exacerbate the fluctuations in weld penetration and the deviation of weld width.

[0035] Therefore, to reflect the dynamic coupling between multiple physical fields during the ship welding process, in this embodiment, the thermal stability indexes at each moment and all previous moments are arranged in chronological order to form the thermal stability sequence at each moment, the stresses at each moment and all previous moments are arranged in chronological order to form the stress sequence at each moment, and the vibration data at each moment and all previous moments are arranged in chronological order to form the vibration sequence at each moment.

[0036] For each moment, in this embodiment, the thermal stability sequence is used as the reference sequence, and the stress sequence and the vibration sequence are used as the comparison sequences respectively. First, the grey relational analysis is used to obtain the grey relational degree between the thermal stability sequence and the vibration sequence at each moment, denoted as the first relational degree. Correspondingly, the grey relational analysis is used to obtain the grey relational degree between the thermal stability sequence and the stress sequence at each moment, denoted as the second relational degree. Among them, the grey relational analysis can reflect the correlation between the two sequences in the time domain, and the grey relational analysis is a well-known existing technology, and the specific process will not be elaborated. Implementers can choose other existing feasible algorithms to reflect the correlation between the two sequences, such as Pearson correlation coefficient, cosine similarity, etc. This embodiment does not limit this here.

[0037] In addition, to further reflect the phase synchronization of the thermal stability sequence with the vibration sequence and the thermal stability sequence with the stress sequence in the time-frequency domain, in this embodiment, continuous wavelet transform is performed on the thermal stability sequence, the vibration sequence, and the stress sequence to obtain the energy distribution in the time-frequency domain, and the wavelet coherence between the thermal stability sequence and the vibration sequence is calculated, denoted as the first coherence, and the wavelet correlation between the thermal stability sequence and the stress sequence is calculated, denoted as the second coherence. Among them, the calculation of continuous wavelet transform and wavelet coherence are both well-known existing technologies, and the specific process will not be elaborated.

[0038] Furthermore, the first correlation degree, the second correlation degree, the first coherence, and the second coherence are fused to obtain the mechanical coupling degree at each moment during ship welding, that is, the mechanical coupling degree is the fusion result of the first correlation degree, the second correlation degree, the first coherence, and the second coherence. Fusion means combining multiple variables, and specifically, it can be calculated by means such as addition, multiplication, addition-multiplication mixture, and averaging. This embodiment does not limit this; In this embodiment, the calculation method of the mechanical coupling degree at each moment during ship welding is specifically as follows: calculate the average value of the first correlation degree and the second correlation degree, denoted as the first average value, calculate the average value of the first coherence and the second coherence, denoted as the second average value, and the mechanical coupling degree is the product of the first average value and the second average value.

[0039] It should be understood that the first average value quantifies the correlation of the change trends between the thermal stability sequence and the vibration sequence, and the thermal stability sequence and the stress sequence. The larger the first average value, the higher the correlation between the change of the thermal stability index and the changes of stress and vibration; the second average value measures the phase synchronization of the thermal stability sequence with the vibration sequence and the thermal stability sequence with the stress sequence in the frequency domain. The larger the second average value, the more synchronous the fluctuations of the thermal stability index with the fluctuations of stress and vibration at specific frequencies and times.

[0040] The mechanical coupling degree describes the dynamic coupling strength between the thermal stability and the mechanical environment during ship manufacturing and welding. The higher the mechanical coupling degree, the more coordinated the thermal stability is with mechanical stress and vibration, the welding process is in a dynamic equilibrium state, the temperature gradient of the molten pool is uniform, the energy input is stable, and defects are not easily generated.

[0041] Step S004, combining the mechanical coupling degree with the welding current in time series, and using a time series prediction model to predict the welding current within a preset time period after the current moment.

[0042] The mechanical coupling degrees at the current moment and all previous moments are combined into a mechanical coupling sequence in chronological order. The current moment's current sequence is used as the input of the time series prediction model, and the current moment's mechanical coupling sequence is used as the exogenous variable of the time series model to predict the welding current within a preset time period after the current moment, obtaining the welding current prediction result. Among them, in this embodiment, the preset time period is 3 seconds, and the implementer can determine the length of the preset time period according to the actual situation, which is not limited in this embodiment. The flowchart of welding current prediction is as shown in Figure 2 shown.

[0043] Among them, the time series prediction model in this embodiment is the autoregressive integrated moving average (ARIMA) model. The autoregressive integrated moving average model is a well-known existing technology, and the specific process will not be elaborated. The implementer can choose other existing feasible time series prediction models by himself / herself, which is not limited in this embodiment.

[0044] Since in the shipbuilding welding process, the welding process involves the non-linear interaction of multiple physical fields such as thermodynamics, mechanical stress, and external vibration, the traditional prediction model cannot adapt to the dynamic changes in real time. Therefore, in this embodiment, the mechanically calculated coupling degree in real time is used as the exogenous variable of the ARIMA model. By providing additional environmental information through the exogenous variable, the prediction model can identify sudden disturbances faster, thereby optimizing the real-time performance of the prediction. An increase in the mechanical coupling degree indicates that the welding process is in a stable state with a high degree of coordination between the thermal and mechanical environments. At this time, external disturbances, that is, vibrations and stress mutations, decrease. On the contrary, a decrease in the mechanical coupling degree reflects an increase in mechanical vibration or thermal stress concentration, resulting in coupling imbalance and the input of thermal energy entering an unstable state. The mechanical coupling degree, as the exogenous variable of the time series prediction model, provides additional environmental information for the time series prediction model, enabling it to distinguish normal fluctuations from abnormal disturbances. For example, when the mechanical coupling degree suddenly drops, the time series prediction model can combine the current mechanical coupling state to predict the possible penetration fluctuations caused by vibration in the molten pool, making up for the limitations of single physical quantity prediction, significantly improving the prediction robustness of welding current in complex scenarios, and ultimately achieving more accurate and real-time prediction of the welding current trend, reducing the bead width deviation and energy fluctuation, and improving the welding quality of shipbuilding.

[0045] It should be noted that: the above sequence of embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above specific embodiments of this specification have been described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0046] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments.

[0047] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; making modifications to the technical solutions recorded in the foregoing embodiments, or making equivalent replacements to some of the technical features, does not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and should all be included within the protection scope of the present application.

Claims

1. A method for constructing a digital twin of ship manufacturing welding assisted by a computer, characterized in that The method includes the following steps: Collect the temperature of the welding molten pool and the welding current at the head of the welding torch in real time, collect the vibration data of the welding equipment during the welding process, and the stress at the connection of the hull ribs; Form the current sequence at each moment by the welding current at each moment and all the moments before it, use the statistical process control algorithm to obtain the process capability index and the process capability offset index of the current sequence, calculate the gradient modulus value of the temperature of the welding molten pool at each moment, and determine the thermal stability index at each moment during ship welding and assembly based on the process capability index, the process capability offset index and the gradient modulus value; wherein, the thermal stability index is positively correlated with both the process capability index and the process capability offset index, and negatively correlated with the gradient modulus value; Form the thermal stability sequence, the vibration sequence and the stress sequence by the thermal stability index, the vibration data and the stress at each moment and all the moments before it respectively; Use the grey relational analysis to obtain the grey relational degree between the thermal stability sequence and the vibration sequence at each moment, denoted as the first relational degree, and correspondingly, obtain the grey relational degree between the thermal stability sequence and the stress sequence at each moment, denoted as the second relational degree; Perform continuous wavelet transform on the thermal stability sequence and the vibration sequence at each moment to obtain the wavelet coherence between the thermal stability sequence and the vibration sequence, denoted as the first coherence, and correspondingly, obtain the wavelet correlation between the thermal stability sequence and the stress sequence, denoted as the second coherence; Fuse the first relational degree, the second relational degree, the first coherence and the second coherence to obtain the mechanical coupling degree at each moment during ship welding and assembly; Combine the mechanical coupling degree in time series with the welding current, and use the time series prediction model to predict the welding current within a preset time period after the current moment.

2. The method for constructing a digital twin of ship manufacturing welding assisted by a computer according to claim 1, wherein The determination of the thermal stability index is as follows: Calculate the product of the process capability index and the process capability offset index, calculate the sum value of the gradient modulus value and a preset value greater than 0, and the thermal stability index is the ratio of the product to the sum value.

3. A method for constructing a digital twin of ship manufacturing welding assisted by a computer, as claimed in claim 1, wherein The current sequence is arranged in chronological order.

4. A method for constructing a digital twin of ship manufacturing welding assisted by a computer, as claimed in claim 1, wherein The determination of the mechanical coupling degree includes: Calculate the mean value of the first relational degree and the second relational degree, denoted as the first mean value, calculate the mean value of the first coherence and the second coherence, denoted as the second mean value, and the mechanical coupling degree is positively correlated with both the first mean value and the second mean value.

5. The method for constructing a digital twin of ship manufacturing welding assisted by a computer according to claim 4, characterized in that, The mechanical coupling degree is the product of the first mean value and the second mean value.

6. The method for constructing a digital twin of ship manufacturing welding assisted by a computer according to claim 1, wherein, The prediction of the welding current within a preset time period after the current moment includes: Form the mechanical coupling sequence by the mechanical coupling degree at the current moment and all the moments before it, use the current sequence at the current moment as the input of the time series prediction model, and combine the mechanical coupling sequence to obtain the prediction result of the welding current after the current moment.

7. The method for constructing a digital twin of ship manufacturing welding assisted by a computer according to claim 6, wherein, The mechanical coupling sequence is used as an exogenous variable of the time series prediction model.

8. The method for constructing a digital twin of ship manufacturing welding assisted by a computer according to claim 6, wherein, The time series prediction model is an autoregressive integrated moving average model.

Images