A method for constructing a digital twin of ship manufacturing welding assisted by computer

Abstract

The present application relates to the technical field of parameter prediction for welding processes, and specifically to a computer-aided method for constructing a digital twin for shipbuilding welding, the method comprising: real-time acquisition of the temperature of the welding pool and the welding current of the welding gun head, real-time acquisition of vibration data of the welding equipment during welding, and stress at the joints of the welded hull ribs; analysis of the rate of change of the temperature of the welding pool at each moment and the stability of the welding current to determine the thermal stability index at each moment during ship welding; analysis of the correlation between the thermal temperature index and the vibration data and the stress in the time domain and in the frequency domain in the time series to determine the mechanical coupling degree at each moment during ship welding; combining the mechanical coupling degree of the time series with the welding current, and using a time series prediction model to predict the welding current within a preset time period after the current moment. The present application improves the prediction robustness of welding current in complex scenarios.

Description

Technical Field

[0001] The present application relates to the technical field of parameter prediction of welding processes, and in particular to a computer-aided method for constructing a digital twin of shipbuilding welding. Background Art

[0002] The Digital Twin of shipbuilding welding and assembly involves creating a virtual model of the welding and assembly process through digital means, enabling real-time monitoring, simulation, optimization, and management. This digital twin is based on the physical world of shipbuilding welding and assembly. Using sensors, cloud computing, and other technologies, it captures and analyzes data in real time, dynamically updates the virtual model, and achieves comprehensive digital simulation and management of the entire welding and assembly process.

[0003] Although existing shipbuilding welding technology has introduced digital means, the coupled modeling of multiple physical fields (heat, force, and vibration) is highly complex. Traditional simulation methods rely on simplified assumptions and cannot accurately describe the nonlinear interactions of multiple physical fields, resulting in deviations in the prediction of thermal stress distribution in shipbuilding welding and inaccurate dynamic behavior of the molten pool. In the event of sudden vibrations or nonlinear fluctuations in the thermal properties of the material, traditional welding current prediction methods cannot distinguish between normal fluctuations and abnormal disturbances, resulting in insufficient robustness in the prediction of welding current under sudden interference and inaccurate control of the molten pool heat input. Summary of the Invention

[0004] In order to solve the above technical problems, the present application provides a computer-aided method for constructing a digital twin of shipbuilding and welding to solve the existing problems.

[0005] The computer-aided digital twin construction method for shipbuilding and welding in this application adopts the following technical solutions:

[0006] One embodiment of the present application provides a computer-aided method for constructing a digital twin of shipbuilding welding, the method comprising the following steps:

[0007] Real-time data collection of the temperature of the welding pool and the welding current of the welding gun head, as well as the vibration data of the welding equipment during the welding process and the stress of the welded hull rib joints;

[0008] The welding currents at each moment and all previous moments are combined into a current sequence at each moment, a process capability index and a process capability offset index of the current sequence are obtained using a statistical process control algorithm, a gradient modulus of the temperature of the welding pool at each moment is calculated, and a thermal stability index at each moment during ship assembly welding is determined based on the process capability index, the process capability offset index, and the gradient modulus; wherein the thermal stability index is positively correlated with the process capability index and the process capability offset index, and negatively correlated with the gradient modulus;

[0009] The thermal stability index, vibration data and stress at each moment and all previous moments are respectively formed into a thermal stability sequence, a vibration sequence and a stress sequence;

[0010] Grey correlation analysis is used to obtain the grey correlation between the thermal stability sequence and the vibration sequence at each moment, which is recorded as the first correlation. Correspondingly, the grey correlation between the thermal stability sequence and the stress sequence at each moment is obtained, which is recorded as the second correlation.

[0011] Perform continuous wavelet transform on the thermodynamic stability sequence and vibration sequence at each moment to obtain the wavelet coherence between the thermodynamic stability sequence and the vibration sequence, which is recorded as the first coherence. Correspondingly, obtain the wavelet correlation between the thermodynamic stability sequence and the stress sequence, which is recorded as the second coherence.

[0012] fusing the first correlation degree, the second correlation degree, the first coherence, and the second coherence to obtain a mechanical coupling degree at each moment during ship assembly and welding;

[0013] The mechanical coupling degree and the welding current of the time series are combined and a time series prediction model is used to predict the welding current within a preset time period after the current moment.

[0014] In one embodiment, the thermal stability index is determined as follows:

[0015] The product of the process capability index and the process capability deviation index is calculated, and the sum of the gradient modulus and a preset value greater than 0 is calculated. The thermodynamic stability index is the ratio of the product to the sum.

[0016] In one embodiment, the current sequences are arranged in a time sequence.

[0017] In one embodiment, determining the degree of mechanical coupling includes:

[0018] The mean of the first correlation degree and the second correlation degree is calculated and recorded as a first mean. The mean of the first coherence and the second coherence is calculated and recorded as a second mean. The mechanical coupling degree is positively correlated with both the first mean and the second mean.

[0019] In one embodiment, the mechanical coupling degree is the product of the first mean value and the second mean value.

[0020] In one embodiment, the predicting of the welding current within a preset time period after the current moment includes:

[0021] The mechanical coupling degrees at the current moment and all previous moments are combined into a mechanical coupling sequence, and the current sequence at the current moment is used as the input of the time series prediction model. Combined with the mechanical coupling sequence, the prediction result of the welding current after the current moment is obtained.

[0022] In one embodiment, the mechanical coupling sequence serves as an exogenous variable in a time series prediction model.

[0023] In one embodiment, the time series prediction model is an autoregressive integrated moving average model.

[0024] This application has at least the following beneficial effects:

[0025] The present application collects the temperature of the welding pool and the welding current of the welding gun head in real time, collects the vibration data of the welding equipment during the welding process, and the stress at the connection of the welded hull ribs in real time; analyzes the temperature change rate of the welding pool at each moment and the stability of the welding current to determine the thermal stability index at each moment during the ship assembly and welding; the thermal stability index improves the refined perception ability of the welding thermal dynamic process, and the real-time monitoring of the temperature change rate can capture the instantaneous abnormality of the heat conduction of the molten pool, while the quantitative evaluation of the stability of the welding current overcomes the limitation of the traditional method that only relies on the current threshold judgment, and enhances the stability of the thermal balance from the energy input dimension. The combination of the two helps to simultaneously optimize the heat source control and the solidification behavior of the molten pool, and reduce weld cracks or deformation caused by thermal stress concentration; respectively analyze the correlation between the thermal temperature index and the vibration data, the stress in the time domain, and the correlation in the frequency domain in the time series to determine the mechanical coupling degree at each moment during the ship assembly and welding; the calculation of the mechanical coupling degree enhances the real-time detection of mechanical disturbances in the welding process The time domain correlation analysis can identify the direct impact of vibration and stress mutation on the thermal state, and the frequency domain correlation reveals the potential threat of periodic mechanical loads to welding quality. The mechanical coupling degree describes the dynamic coupling strength between the thermal stability and mechanical environment of the shipbuilding welding process, which improves the accuracy of the thermal stability detection of the welding process. Combining the mechanical coupling degree and the welding current of the time series, the time series prediction model is used 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 fluctuation of the penetration depth of the molten pool caused by vibration, which makes up for the limitations of the prediction of a single physical quantity, significantly improves the prediction robustness of the welding current in complex scenarios, and ultimately achieves more accurate and real-time prediction of the welding current trend, reduces the weld width deviation and energy fluctuation, and improves the welding quality of shipbuilding. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0027] Figure 1 This is a flowchart of the steps of a computer-aided method for constructing a digital twin of shipbuilding and welding provided in this application;

[0028] Figure 2 This is the welding current prediction flow chart. DETAILED DESCRIPTION

[0029] To further illustrate the technical means and effectiveness of this application to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effectiveness of a computer-aided method for constructing a digital twin for shipbuilding assembly and welding, as proposed in this application. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0030] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0031] The following describes in detail a specific scheme of a computer-aided method for constructing a digital twin for shipbuilding and welding provided by this application with reference to the accompanying drawings.

[0032] An embodiment of the present application provides a computer-aided method for constructing a digital twin of shipbuilding and welding. Specifically, the following computer-aided method for constructing a digital twin of shipbuilding and welding is provided. Figure 1 , the method comprises the following steps:

[0033] Step S001 , real-time collection of the temperature of the welding pool and the welding current of the welding gun head, real-time collection of the vibration data of the welding equipment during the welding process, and the stress at the connection of the welded hull ribs.

[0034] A digital twin is a virtual model of a physical entity created through digital technology. It reflects the state, behavior, and performance of the physical entity in real time and enables simulation, prediction, and optimization. A digital twin serves as a bridge between the physical and digital worlds, acquiring data from the physical entity through sensors and data acquisition devices to monitor, analyze, and control the actual physical system. In the welding process of shipbuilding, the application of digital twins can significantly improve production efficiency, reduce errors, and optimize quality management. For example, sensors collect temperature and stress data in the welding area and feed this data into the digital twin, enabling real-time monitoring of welding quality. Alternatively, by integrating sensors with predictive models, the digital twin can analyze the status of welding equipment, detect potential failures in advance, and ensure the continued stable operation of the ship welding process.

[0035] 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 on 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 stress at each moment in the welding process. In addition, a vibration sensor is installed on 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.

[0036] 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 impose any restrictions here.

[0037] Step S002: Analyze the change rate of the temperature of the welding pool at each moment and the stability of the welding current to determine the thermal stability index at each moment during the ship assembly welding.

[0038] Due to the complexity of ship welding processes and their multi-physics coupling, welding quality defects are easily caused by uneven thermal distribution and fluctuating energy input. Specifically, the heat conduction process in the weld pool is affected by current fluctuations, nonlinear changes in the material's thermophysical properties, and external environmental interference. This can cause abnormal temperature gradient distribution in the weld pool, leading to concentrated thermal stress and uneven metal phase transformation in the weld area, which in turn can induce weld deformation, microcracks, and even macrostructural instability. At the same time, random fluctuations in welding current can undermine the stability of energy input, resulting in inconsistent penetration depth, deviations in weld width, or porosity defects, directly affecting the mechanical properties and fatigue life of the weld.

[0039] 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.

[0040] 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 for calculating the rate of change of temperature, and this embodiment does not limit this.

[0041] To analyze the stability of welding energy input, this embodiment chronologically combines the welding current at each moment and all previous moments into a current sequence. This current sequence is then used as input for a statistical process control (SPC) algorithm to obtain the process capability index (Cp) and the process capability shift index (Cpk). The process capability index (Cp) compares the actual fluctuations in welding current with the design tolerance to determine the potential stability of welding energy input. The process capability shift index (Cpk) integrates the process capability index (Cp) with mean shift considerations to comprehensively assess the actual stability of welding energy input. In this embodiment, the design tolerance for welding current is defined as the upper and lower specification limits (ULLs), where the UL is the rated current +10A and the LL is the rated current -10A.

[0042] It should be understood that the SPC algorithm and the calculation of the process capability index CP and the process capability shift index Cpk are all existing well-known technologies, and the specific process will not be described in detail in this embodiment.

[0043] It should be noted that the implementer may choose other feasible existing methods for measuring the stability of current series data changes, such as standard deviation, coefficient of variation, etc., and this embodiment does not limit this.

[0044] Based on the above analysis, this embodiment calculates the thermal stability index at each moment during ship welding. The specific calculation method is:

[0045] Where A is the thermal stability index at each moment during ship welding, Cp is the process capability index of welding current, is the process capability deviation index of welding current, is the module of the temperature gradient of the welding pool at each moment, To preset a value greater than 0 to avoid the denominator being 0, in this embodiment The implementer can set it according to the actual situation, and this embodiment does not limit it here.

[0046] It should be understood that the process capability index Cp is a core indicator in statistical process control. The larger its value, the smaller the actual fluctuation of the welding current is, indicating that the potential stability of the welding energy input is higher. The larger the process capability deviation index Cpk is, the closer the mean welding current is to the rated current, the smaller the fluctuation is, and the higher the actual stability of the welding energy input is. The temperature change rate of the welding pool is quantified. The larger the value, the more uneven the temperature distribution is. The welding pool has a steep temperature gradient, which is more likely to cause local stress concentration and welding defects.

[0047] The thermal stability index A is a multi-dimensional coupling indicator used to quantify the dynamic balance 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 and the better the thermal coupling is.

[0048] Step S003 , analyzing the correlation between the thermal temperature index and the vibration data, the stress in the time domain, and the frequency domain, respectively, to determine the mechanical coupling degree at each moment during the ship assembly and welding.

[0049] Since the ship welding process involves the dynamic coupling of multiple physical fields of heat, force and vibration, traditional single-dimensional monitoring indicators are difficult to comprehensively assess welding quality risks. In a complex welding environment, although the thermal stability index can reflect the equilibrium state of energy input and temperature field, the thermodynamic behavior of the welding molten pool will produce nonlinear interactions with the mechanical stress field and external vibration interference: on the one hand, the non-uniform thermal expansion of the weld area will induce local stress concentration. When the stress accumulation exceeds the yield limit of the material, it will cause weld deformation and even microcracks to initiate; on the other hand, the mechanical vibration of the welding robot is transmitted to the welding gun through the welding robot, which may change the dynamic balance of the molten pool and aggravate the fluctuation of the weld depth and the deviation of the weld width.

[0050] Therefore, in order to reflect the dynamic coupling effect between multiple physical fields in the ship welding process, this embodiment organizes the thermal stability index of each moment and all previous moments into a thermal stability sequence at each moment in chronological order, organizes the stress of each moment and all previous moments into a stress sequence at each moment in chronological order, and organizes the vibration data of each moment and all previous moments into a vibration sequence at each moment in chronological order.

[0051] For each moment, this embodiment uses the thermal stability sequence as the reference sequence, and the stress sequence and the vibration sequence as the comparison sequences respectively. First, the gray correlation analysis is used to obtain the gray correlation between the thermal stability sequence and the vibration sequence at each moment, which is recorded as the first correlation. Correspondingly, the gray correlation analysis is used to obtain the gray correlation between the thermal stability sequence and the stress sequence at each moment, which is recorded as the second correlation. Among them, the gray correlation analysis can reflect the correlation between the two sequences in the time domain, and the gray correlation analysis is an existing well-known technology. The specific process is not described in detail. The implementer can choose other existing feasible algorithms to reflect the correlation between the two sequences, such as the Pearson correlation coefficient, cosine similarity, etc., and this embodiment does not limit it here.

[0052] Furthermore, to further reflect the phase synchronization between the thermodynamic stability sequence and the vibration sequence, and between the thermodynamic stability sequence and the stress sequence in the time-frequency domain, this embodiment performs a continuous wavelet transform on the thermodynamic stability sequence, the vibration sequence, and the stress sequence to obtain the energy distribution in the time-frequency domain. The wavelet coherence between the thermodynamic stability sequence and the vibration sequence, denoted as the primary coherence, is calculated, and the wavelet correlation between the thermodynamic stability sequence and the stress sequence, denoted as the secondary coherence, is calculated. The continuous wavelet transform and the calculation of the wavelet coherence are both well-known techniques, and the specific process is not described in detail here.

[0053] 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 the ship assembly and 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. Specifically, calculation can be performed by addition, multiplication, a combination of addition and multiplication, averaging, etc., which is not limited in this embodiment.

[0054] In this embodiment, the mechanical coupling degree at each moment during ship assembly and welding is calculated as follows: the average of the first correlation degree and the second correlation degree is calculated, recorded as the first average, and the average of the first coherence and the second coherence is calculated, recorded as the second average. The mechanical coupling degree is the product of the first average and the second average.

[0055] It should be understood that the first mean quantifies the correlation between the changing trends of the thermal stability sequence and the vibration sequence, as well as the thermal stability sequence and the stress sequence. The larger the first mean, the more highly correlated the changes in the thermal stability index are with the changes in stress and vibration. The second mean measures the phase synchronization between the thermal stability sequence and the vibration sequence, as well as the thermal stability sequence and the stress sequence in the frequency domain. The larger the second mean, the more synchronized the fluctuations in the thermal stability index are with the fluctuations in stress and vibration at specific frequencies and times.

[0056] Mechanical coupling describes the dynamic coupling strength between the thermal stability and the mechanical environment of the shipbuilding welding process. The higher the mechanical coupling, the more coordinated the thermal stability is with the mechanical stress and vibration. The welding process is in a state of dynamic equilibrium, the temperature gradient of the molten pool is uniform, the energy input is stable, and defects are less likely to occur.

[0057] Step S004 : combining the mechanical coupling degree and the welding current in the time series and using a time series prediction model to predict the welding current within a preset time period after the current moment.

[0058] The mechanical coupling degrees at the current moment and all previous moments are combined into a mechanical coupling sequence in a time series order. The current sequence at the current moment is used as the input of the time series prediction model. The mechanical coupling sequence at the current moment is used as the exogenous variable of the time series model to predict the welding current within the preset time period after the current moment to obtain the welding current prediction result. In this embodiment, the preset time period is 3 seconds. The implementer can determine the length of the preset time period according to the actual situation. This embodiment does not impose any restrictions on this. The welding current prediction flow chart is shown in the figure below. Figure 2 shown.

[0059] 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 an existing well-known technology, and the specific process is not described in detail. The implementer can choose other existing feasible time series prediction models at will, and this embodiment does not limit it here.

[0060] Because the welding process in shipbuilding involves nonlinear interactions among multiple physical fields, including thermodynamics, mechanical stress, and external vibration, traditional prediction models are unable to adapt to dynamic changes in real time. Therefore, this embodiment uses the real-time calculated mechanical coupling as an exogenous variable in the ARIMA model. By providing additional environmental information through the exogenous variable, the prediction model can more quickly identify sudden interference, thereby optimizing the real-time performance of the prediction. An increase in mechanical coupling 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 interference, such as vibration and stress mutations, is reduced. Conversely, a decrease in mechanical coupling reflects an intensification of mechanical vibration or a concentration of thermal stress, leading to coupling imbalance and an unstable thermal energy input. As an exogenous variable, mechanical coupling provides additional environmental information to the time series prediction model, enabling it to distinguish normal fluctuations from abnormal disturbances. For example, when the mechanical coupling degree drops suddenly, the time series prediction model can be combined with the current mechanical coupling state to predict the possible fluctuations in the weld depth caused by vibration in the molten pool, which makes up for the limitations of the prediction of a single physical quantity and significantly improves the prediction robustness of the welding current in complex scenarios. Ultimately, it can achieve more accurate and real-time prediction of the welding current trend, reduce weld width deviation and energy fluctuation, and improve the welding quality of shipbuilding.

[0061] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0062] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0063] The above-described embodiments are only used to illustrate the technical solutions of the present application, and not to limit them. Modifications to the technical solutions described in the aforementioned embodiments, or equivalent replacements of some of the technical features therein, do 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 in the scope of protection of the present application.

Claims

1. A computer-aided method for constructing a digital twin of shipbuilding and welding, characterized in that: The method comprises the following steps: Real-time data collection of the temperature of the welding pool and the welding current of the welding gun head, as well as the vibration data of the welding equipment during the welding process and the stress of the welded hull rib joints; The welding currents at each moment and all previous moments are combined into a current sequence at each moment, a process capability index and a process capability offset index of the current sequence are obtained using a statistical process control algorithm, a gradient modulus of the temperature of the welding pool at each moment is calculated, and a thermal stability index at each moment during ship assembly welding is determined based on the process capability index, the process capability offset index, and the gradient modulus; wherein the thermal stability index is positively correlated with the process capability index and the process capability offset index, and negatively correlated with the gradient modulus; The thermal stability index, vibration data and stress at each moment and all previous moments are respectively formed into a thermal stability sequence, a vibration sequence and a stress sequence; Grey correlation analysis is used to obtain the grey correlation between the thermal stability sequence and the vibration sequence at each moment, which is recorded as the first correlation. Correspondingly, the grey correlation between the thermal stability sequence and the stress sequence at each moment is obtained, which is recorded as the second correlation. Perform continuous wavelet transform on the thermodynamic stability sequence and vibration sequence at each moment to obtain the wavelet coherence between the thermodynamic stability sequence and the vibration sequence, which is recorded as the first coherence. Correspondingly, obtain the wavelet correlation between the thermodynamic stability sequence and the stress sequence, which is recorded as the second coherence. fusing the first correlation degree, the second correlation degree, the first coherence, and the second coherence to obtain a mechanical coupling degree at each moment during ship assembly and welding; The mechanical coupling degree and the welding current of the time series are combined and a time series prediction model is used to predict the welding current within a preset time period after the current moment.

2. A computer-aided method for constructing a digital twin of shipbuilding and welding according to claim 1, characterized in that: The thermal stability index is determined as follows: The product of the process capability index and the process capability deviation index is calculated, and the sum of the gradient modulus and a preset value greater than 0 is calculated. The thermodynamic stability index is the ratio of the product to the sum.

3. The computer-aided shipbuilding welding digital twin construction method according to claim 1, characterized in that: The current sequences are arranged in a time sequence.

4. The computer-aided method for constructing a digital twin of shipbuilding and welding according to claim 1, wherein: The determination of the mechanical coupling degree includes: The mean of the first correlation degree and the second correlation degree is calculated and recorded as the first mean. The mean of the first coherence and the second coherence is calculated and recorded as the second mean. The mechanical coupling degree is positively correlated with the first mean and the second mean.

5. The computer-aided method for constructing a digital twin of shipbuilding and welding according to claim 4, characterized in that: The mechanical coupling degree is a product of the first mean value and the second mean value.

6. The computer-aided method for constructing a digital twin of shipbuilding and welding according to claim 1, wherein: The prediction of the welding current within a preset time period after the current moment includes: The mechanical coupling degrees at the current moment and all previous moments are combined into a mechanical coupling sequence, and the current sequence at the current moment is used as the input of the time series prediction model. Combined with the mechanical coupling sequence, the prediction result of the welding current after the current moment is obtained.

7. The computer-aided method for constructing a digital twin of shipbuilding and welding according to claim 6, characterized in that: The mechanical coupling series is used as an exogenous variable in the time series prediction model.

8. The computer-aided method for constructing a digital twin of shipbuilding and welding according to claim 6, characterized in that: The time series prediction model is an autoregressive integrated moving average model.

Images