Dynamic parameter adjustment 2-micron laser welding system based on complex high-molecular polymer

Abstract

The invention discloses a dynamic parameter adjustment 2-micron laser welding system based on complex high-molecular polymers, and belongs to the technical field of high-molecular material processing and laser manufacturing. The problems that the depth of a molten pool is difficult to control, the welding uniformity is poor and the bonding strength is insufficient due to the fact that the material characteristics of an existing 2-micron laser welding technology are diversified, the dynamic change of thermal behaviors in the welding process is remarkable and a welding mode with fixed parameters is difficult to adapt in real time are solved. The melting state and the interface behavior of a material in the welding process are monitored in real time, and laser output parameters are dynamically adjusted according to the monitoring result. According to the method, the limitation of a traditional fixed parameter mode is broken through, welding process parameters can be flexibly optimized according to changes of material characteristics and machining states, and therefore the welding process is accurately controlled.

Description

Technical Field

[0001] The present invention belongs to the technical field of polymer material processing and laser manufacturing, and specifically relates to a 2um laser welding system based on dynamic parameter adjustment of complex polymers. Background Art

[0002] Due to its excellent properties such as light weight, high strength, corrosion resistance and insulation performance, polymers have been widely used in high-end manufacturing fields such as aerospace, medical devices and electronic packaging. However, the complex molecular structure and thermophysical properties of such materials have brought many challenges in the processing process, significantly limiting their utilization rate. Specifically, the molecular chain length of polymers is relatively long, and they are often accompanied by highly cross-linked or branched structures, which makes their thermal conductivity efficiency low and their melting behavior uneven. In addition, these materials usually have a high coefficient of thermal expansion and are prone to thermal deformation or warping during welding, which affects the welding quality and part performance. At the same time, since these materials are prone to decomposition or degradation under the action of heat, their welding window is narrow, and the precise control of welding process parameters is required to be high. These characteristics make polymer materials have great potential in practical applications, but their utilization rate is low due to the difficulty of processing.

[0003] To solve the above problems, laser welding technology has become one of the important methods for polymer material processing with its advantages of non-contact, high precision and strong controllability. In particular, the application of lasers with a wavelength of 2μm in polymer welding shows unique potential. Compared with traditional 1μm band lasers, 2μm lasers can significantly improve the light energy absorption rate of polymer materials. This is because this band is closer to the characteristic absorption spectrum of polymer materials, thereby effectively enhancing the utilization efficiency of laser energy by materials. This feature enables 2μm lasers to show higher thermal efficiency and processing adaptability in the melting and welding of polymers. However, although 2μm lasers have potential advantages in welding applications, the limitations of their traditional fixed parameter mode still exist. For complex polymers, due to the diversity of their material properties and the significant dynamic changes in thermal behavior during welding, the fixed parameter welding mode is difficult to adapt in real time, resulting in problems such as difficult control of molten pool depth, poor welding uniformity and insufficient bonding strength. This technical bottleneck restricts the promotion and application of 2μm laser welding technology in actual production. Summary of the invention

[0004] In order to solve the problems of existing 2μm laser welding technology, such as difficulty in controlling the molten pool depth, poor welding uniformity and insufficient bonding strength due to the diversity of material properties and significant dynamic changes in thermal behavior during welding, the present invention provides a 2um laser welding system based on dynamic parameter adjustment of complex polymers.

[0005] The system includes a welding operation unit, a sensor unit and a host computer, wherein the host computer includes a dynamic imaging detection unit and an intelligent feedback control unit; the welding operation unit performs a high molecular polymer welding operation, and during the welding process, the dynamic imaging detection unit detects the surface morphology characteristics of the molten pool in real time through the sensor unit, and feeds back the surface morphology characteristics of the molten pool to the intelligent feedback control unit, and the intelligent feedback control unit adjusts the welding parameters in the welding operation unit according to the surface morphology characteristics of the molten pool.

[0006] Furthermore, the sensor unit includes a visual sensor, which is used to take high-resolution photos of the welding process through a high-speed camera and capture the dynamic changes of the surface morphology of the molten pool in real time. Furthermore, the welding operation unit includes a 2um fiber laser, an optical isolation lens group and a dynamic focusing lens group. During welding, the 2um fiber laser is started to generate a high-energy 2um laser, which is isolated and processed by the optical isolation lens group in the optical path, and the light beam is focused and transmitted by the dynamic focusing lens group.

[0007] Furthermore, the optical isolation lens group includes two wedge-shaped prisms, namely a first wedge-shaped prism and a second wedge-shaped prism. The function of the optical isolation lens group is to ensure that no return light is generated after the 2um laser passes through.

[0008] Furthermore, the dynamic focusing lens group includes two focusing lenses, namely a first focusing lens and a second focusing lens. The function of the dynamic focusing lens group is to compensate for the focusing and divergence of the laser beam. The focal length of each focusing lens is different. When the laser beam passes through the dynamic focusing lens group, the spot is adjusted, so that the energy density on the polymer is different, the spot size is different, and the welding surface is dynamically adjusted.

[0009] Furthermore, the dynamic imaging detection unit is built on the basis of the FPN feature pyramid network. The dynamic imaging detection unit includes three layers, namely, a low layer, a middle layer and a high layer, and the outputs of the three layers are coupled to obtain the final output of the dynamic imaging detection unit; The low layers include convolutional layers, activation layers, pooling layers, batch normalization layers, residual block layers, and transposed convolutional layers in sequence; the middle layers include convolutional layers, activation layers, pooling layers, and feature fusion layers in sequence; the high layers include convolutional layers, nonlinear activation layers, maximum pooling layers, residual block layers, full convolutional layers, and feature fusion layers in sequence; A residual connection is made between the pooling layer and the feature fusion layer of the middle layer, and the residual connection is also connected to the residual block layer in the lower layer to achieve continuous jumping; the transposed convolution layer of the lower layer is connected to the feature fusion layer of the middle layer through the upsampling layer, and the output of the lower layer is input to the feature fusion layer of the middle layer; the feature fusion layer of the middle layer is connected to the feature fusion layer of the high layer through the upsampling layer, and the upsampling layer is also connected to the residual block layer of the high layer to achieve continuous jumping.

[0010] Furthermore, before the features are input to the higher layers, they are first extracted through a large kernel convolution operation.

[0011] Furthermore, the intelligent feedback control unit uses an MPC control module, a PPO reinforcement learning module, and an LSTM long short-term memory neural network module to form a three-layer coupling architecture; The MPC control module calculates and processes the observation data of the current state and predicts it, and optimizes the welding parameters in the rolling time domain to predict the welding parameters for the next welding work; The PPO reinforcement learning module uses the future state prediction and current state real-time feedback provided by the MPC control module to adjust the control strategy to ensure that the intelligent feedback control unit can output the optimal welding parameters under uncertain conditions; The LSTM long short-term memory neural network module provides a prediction estimate of the future state based on the stored historical state, helping the MPC control module to predict the future state more accurately; The output of the intelligent feedback control unit is: ;in, for The optimal welding parameter output at the moment; For MPC control module Welding parameter output at each moment; Strengthen learning module for PPO The welding parameter output at the moment, where Learned for the PPO reinforcement learning module The optimal control strategy at each moment, for The current state at the moment; LSTM long short time series memory neural network module Hidden state output at the moment; , and are the weighted coefficients of the three-layer coupling architecture.

[0012] The beneficial effects of the system of the present invention are: The introduction of dynamic parameter adjustment technology has opened up a new path for 2μm laser welding of polymers. By real-time monitoring of the melting state and interface behavior of the material during the welding process, the laser output parameters (including power, frequency, spot size, etc.) are dynamically adjusted according to the monitoring results. This method breaks through the limitations of the traditional fixed parameter mode and can flexibly optimize the welding process parameters according to changes in material properties and processing status, thereby achieving precise control of the welding process. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a structural diagram of a welding operation unit in an embodiment of the present invention; Figure 2 This is a working diagram of a 2um laser welding system based on dynamic parameter adjustment of complex high molecular polymers in an embodiment of the present invention; Figure 3 1 is a pyramid structure diagram of a dynamic imaging detection unit in an embodiment of the present invention; Figure 4 is a structural diagram of a dynamic imaging detection unit in an embodiment of the present invention; Figure 5 Schematic diagram of the intelligent feedback control unit in an embodiment of the present invention. DETAILED DESCRIPTION

[0014] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the protection scope of the present invention.

[0015] Embodiment 1, The present embodiment provides a 2um laser welding system based on dynamic parameter adjustment of complex high molecular polymers, the system includes a welding operation unit, a sensor unit and a host computer, the host computer includes a dynamic imaging detection unit and an intelligent feedback control unit; the welding operation unit performs high molecular polymer welding operations, and during the welding process, the dynamic imaging detection unit detects the surface morphology characteristics of the molten pool in real time through the sensor unit, and feeds back the surface morphology characteristics of the molten pool to the intelligent feedback control unit, and the intelligent feedback control unit adjusts the welding parameters in the welding operation unit according to the surface morphology characteristics of the molten pool.

[0016] The sensor unit includes a visual sensor, which is used to take high-resolution photos of the welding process through a high-speed camera and capture the dynamic changes of the surface morphology of the molten pool in real time. The welding operation unit is as follows Figure 1As shown, it includes a 2um fiber laser 1, an optical isolation lens group 2 and a dynamic focusing lens group 3. During welding, the 2um fiber laser 1 is started to generate a high-energy 2um laser, which is isolated and processed by the optical isolation lens group 2 in the optical path, and the light beam is focused and transmitted by the dynamic focusing lens group 3.

[0017] Compared with the traditional 1μm wavelength laser, the 2μm laser has a higher matching with the absorption spectrum of polymer materials, which greatly improves the laser absorption efficiency of the material, thereby reducing energy waste and improving welding efficiency. The 2um fiber laser outputs the laser beam through the optical fiber. The light beam transmitted in the optical fiber has a lower transmission loss, and the laser output is stable, which is suitable for long-term and high-efficiency welding operations.

[0018] The optical isolation lens group 2 includes two wedge-shaped prisms, namely a first wedge-shaped prism M1 and a second wedge-shaped prism M2. The function of the optical isolation lens group 2 is to ensure that no return light is generated after the 2um laser passes through.

[0019] The dynamic focusing lens group 3 includes two focusing lenses, namely a first focusing lens M3 and a second focusing lens M4. The function of the dynamic focusing lens group 3 is to compensate for the focusing and divergence of the laser beam. The focal length of each focusing lens is different. When the laser beam passes through the dynamic focusing lens group 3, the spot is adjusted, so that the energy density on the polymer is different, the spot size is different, and the welding surface is dynamically adjusted.

[0020] The laser beam is transmitted to the dynamic focusing lens group 3 after passing through the optical isolation lens group 2. The dynamic focusing lens group 3 focuses the parallel laser beam to the welding area to form a laser focus with high energy density. The control of the beam focus point is very important. By adjusting the focal length and angle of the focusing lens, it is ensured that the laser beam can be focused to the required welding depth and welding surface during the welding process. The precision control of this step can effectively avoid welding defects caused by inaccurate focus during the welding process, such as local overheating or uneven fusion.

[0021] The working flow diagram of the system of the present invention is as follows: Figure 2 As shown, when the system of the present invention starts working, it first detects whether the laser focusing state and energy output are normal. If not, the system is restarted or the dynamic focusing lens group 3 is checked. If normal, the visual sensor is started to collect data in real time, and it is determined whether the data is normal. If the data is abnormal, the visual sensor is checked. If normal, the sensor data is fed back to the host computer, which includes a dynamic imaging detection unit and an intelligent feedback control unit. The dynamic imaging detection unit detects the surface morphology characteristics of the molten pool in real time through the sensor unit, and feeds back the surface morphology characteristics of the molten pool to the intelligent feedback control unit. The intelligent feedback control unit dynamically adjusts the welding parameters in the welding operation unit according to the surface morphology characteristics of the molten pool.

[0022] Furthermore, as an extension of the solution of this embodiment, the sensor unit may also include a temperature sensor and an infrared sensor, and the temperature sensor can monitor the change of the molten pool temperature in real time. If the molten pool temperature is detected to be too high, the control system will automatically reduce the power output of the laser to prevent thermal damage or crack formation caused by overheating. When the molten pool temperature is too low or the energy in the welding area is insufficient, the system will automatically increase the laser power to ensure the smooth progress of the welding process.

[0023] Embodiment 2, This embodiment further limits the embodiment 1 and further introduces the dynamic imaging detection unit. Figure 3 As shown, the dynamic imaging detection unit is built based on the FPN feature pyramid network, and the dynamic imaging detection unit includes three layers, namely, a low layer, a middle layer and a high layer.

[0024] like Figure 4 The structure diagram of the dynamic imaging detection unit is shown in FIG. The dynamic imaging detection unit is built on the basis of the FPN feature pyramid network. The dynamic imaging detection unit includes three layers, namely, the low layer, the middle layer and the high layer. The outputs of the low layer, the middle layer and the high layer are respectively , and And the outputs of the three layers are coupled to obtain the final output of the dynamic imaging detection unit; The low layers include convolutional layers, activation layers, pooling layers, batch normalization layers, residual block layers, and transposed convolutional layers in sequence; the middle layers include convolutional layers, activation layers, pooling layers, and feature fusion layers in sequence; the high layers include convolutional layers, nonlinear activation layers, maximum pooling layers, residual block layers, full convolutional layers, and feature fusion layers in sequence; A residual connection is made between the pooling layer and the feature fusion layer of the middle layer, and the residual connection is also connected to the residual block layer in the lower layer to achieve continuous jumping; the transposed convolution layer of the lower layer is connected to the feature fusion layer of the middle layer through the upsampling layer, and the output of the lower layer is input to the feature fusion layer of the middle layer; the feature fusion layer of the middle layer is connected to the feature fusion layer of the high layer through the upsampling layer, and the upsampling layer is also connected to the residual block layer of the high layer to achieve continuous jumping.

[0025] Before the features are input to the higher layers, they are first extracted through a large kernel convolution operation.

[0026] In the low-level convolutional layer, feature extraction is first performed through a feature extraction module, and then detail scanning is performed through a convolution operation to extract visual features. The feature extraction module uses multiple layers of convolution to extract more abstract local detail patterns.

[0027] Combining upsampling and continuous skip connections, the feature fusion in multi-scale object detection tasks is effectively optimized. The network extracts preliminary features through convolutional layers, and the low-level feature maps contain detailed information, such as edges and textures, which are suitable for small object detection. After being processed by nonlinear activation functions and pooling layers, the spatial resolution of the low-level feature maps is reduced, which enhances the sensitivity to local changes. The middle layer abstracts local pattern features, such as object parts and textures, through deeper convolutional layers. Residual blocks and skip connections ensure that low-level features can be directly transmitted to the middle layer, avoiding information loss and promoting information flow between the low and middle layers. High-level features mainly extract global pattern information, such as the overall structure of objects. In order to fuse with low-level features, upsampling technology is used to increase the spatial resolution of high-level feature maps and align them with low-level feature maps to ensure effective fusion of multi-scale features. Skip connections establish direct connections between low and high layers to help the network combine global information and local details. Through this structure, important detail information can be retained when detecting multi-scale objects, while improving the recognition ability of complex scenes and small objects to enhance information fusion at different scales.

[0028] like Figure 3 As shown, Features extracted for the lower layers, i.e. the initial layers of the dynamic imaging detection unit network structure, can capture small defects and surface textures. The middle-level features correspond to the middle-level outputs of the dynamic imaging detection unit network, which mainly extract local patterns, that is, capture pattern changes and local geometric forms of objects in local areas. It is the high-level feature, i.e. the high-level output of the dynamic imaging detection unit network. It mainly monitors the overall morphology, the overall layout of the welding process, and the global output. In order to adjust the dimensions on different layers to match them, the above function is modified, and the convolution dimension reduction (Conv1×1) is introduced to unify the number of channels to match the algorithm. The adaptive weight and attention mechanism are added to correct it. The output of the fused network is expressed as: ;in , and is the adaptive weight, calculated by the attention mechanism (SA): ; Among them, the adaptive weight function and Respectively represent the current number of calculation layers, and Respectively represent Layer and The feature information extracted by the layer, Indicates The layer feature attention value indicates the importance of the layer feature, and the adaptive weight of each layer is calculated , thereby dynamically adjusting the importance of each layer of features when multiple layers of features are fused.

[0029] By optimizing the multi-layer network of the dynamic imaging detection unit through correction functions, the feature weights of each layer can be adaptively adjusted according to the characteristic distribution of defects, avoiding the loss of molten pool feedback information, improving accuracy, and providing powerful data for the dynamic parameter adjustment system.

[0030] Embodiment 3, This embodiment further limits the embodiment 1 and further introduces the intelligent feedback control unit. Figure 5 As shown, the intelligent feedback control unit uses an MPC control module, a PPO reinforcement learning module, and an LSTM long short-term memory neural network module to form a three-layer coupling architecture; The MPC control module calculates and processes the observation data of the current state and predicts it, and optimizes the welding parameters in the rolling time domain to predict the welding parameters for the next welding work; The PPO reinforcement learning module uses the future state prediction and current state real-time feedback provided by the MPC control module to adjust the control strategy to ensure that the intelligent feedback control unit can output the optimal welding parameters under uncertain conditions; The LSTM long short-term memory neural network module provides a prediction estimate of the future state based on the stored historical state, helping the MPC control module to predict the future state more accurately; The output of the intelligent feedback control unit is: ;in, for The optimal welding parameter output at the moment; For MPC control module Welding parameter output at each moment; Strengthen learning module for PPO The welding parameter output at the moment, where Learned for the PPO reinforcement learning module The optimal control strategy at each moment, for The current state at the moment; LSTM long short time series memory neural network module Hidden state output at the moment; , and are the weighted coefficients of the three-layer coupling architecture respectively.

[0031] Compared with the traditional PID fuzzy control which has the characteristics of lack of memory ability, this embodiment proposes a three-layer intelligent control architecture enhanced system with predictive, adaptable and long-term memory capabilities, which can achieve optimal control of welding parameters in the field of laser welding. The proposed three-layer architecture coupling module can effectively realize intelligent decision-making and precise control of dynamic systems.

[0032] First, as a model-based control strategy, MPC uses the dynamic model of the system to perform rolling time domain optimization by observing the current state and predicting the future state to calculate the optimal control input in the future. The core advantage of MPC is that it can handle constraints and dynamically adjust the control input in each control cycle to ensure that the system always maintains optimal performance in a changing environment. At the same time, PPO, as a reinforcement learning algorithm, mainly relies on interaction with the environment to continuously optimize the control strategy. PPO gradually improves control decisions and maximizes cumulative rewards by updating the policy network based on the current state and reward signal. In this framework, PPO uses the state prediction and real-time feedback provided by MPC to adjust the control strategy to ensure that the controller can make the best choice in an uncertain environment. LSTM is mainly responsible for modeling time series data in this framework, capturing the long-term dependency of system states through time storage and call. LSTM stores historical state information through its memory cell (Cell State) and selectively retains or updates important time information through the gate control machine. The core role of LSTM is to provide a prediction estimate of the future state of the system based on historical data. It helps MPC to more accurately predict future state changes, thereby improving control accuracy.

[0033] like Figure 5 As shown, firstly, the modified nonlinear MPC is introduced by feedback image data from the dynamic imaging monitoring unit. By optimizing the control sequence of the next N steps, the reinforcement learning compensation factor and LSTM memory error are increased. The correction here aims to more accurately control the degree of reinforcement intelligence and avoid calculation errors under small feedback signals. The optimized formula is as follows: ; in It represents the output of the modified MPC control module, taking the temperature parameter in the welding parameter as an example: Indicates that at time step The system temperature at the time, The set temperature indicates that the system reaches the target temperature. It describes the degree of deviation of the system from the set target and optimizes the control input to minimize the deviation. Indicates that at time step The final control input at time t is obtained by weighted fusion of the output control signal in the coupling equation. Represents the time step The final control input at the moment, Reflects the smoothness of the control input. Indicates that at time step The constraint error at time, Its function is to measure the constraint error. By minimizing this item, it ensures that the system meets all constraints during the optimization control process, avoids violations of system limitations, and improves the stability and performance of the overall system. and It is a weight parameter used to adjust the importance of different items in the objective function, control the smoothness of the input, find a balance between the deviation between the system state and the target and the constraints, and output smoothly.

[0034] At the same time, the PPO and bidirectional LSTM structures learn and optimize parameters such as laser power and scanning speed in real time to adapt to complex working conditions, and simultaneously store the time series of the welding process to improve the stability and continuity of welding parameter adjustment.

Claims

1. A 2um laser welding system based on dynamic parameter adjustment of complex polymers, characterized in that: The system includes a welding operation unit, a sensor unit and a host computer, wherein the host computer includes a dynamic imaging detection unit and an intelligent feedback control unit; the welding operation unit performs a high molecular polymer welding operation, and during the welding process, the dynamic imaging detection unit detects the surface morphology characteristics of the molten pool in real time through the sensor unit, and feeds back the surface morphology characteristics of the molten pool to the intelligent feedback control unit, and the intelligent feedback control unit adjusts the welding parameters in the welding operation unit according to the surface morphology characteristics of the molten pool.

2. The 2um laser welding system based on complex polymer dynamic parameter adjustment according to claim 1 is characterized in that: The sensor unit includes a visual sensor, which is used to take high-resolution photos of the welding process through a high-speed camera and capture the dynamic changes of the surface morphology of the molten pool in real time.

3. The 2um laser welding system based on complex polymer dynamic parameter adjustment according to claim 2 is characterized in that: The welding operation unit comprises a 2um optical fiber laser (1), an optical isolation lens group (2) and a dynamic focusing lens group (3). During welding, the 2um optical fiber laser (1) is started to generate high-energy 2um laser light, the laser light is isolated and processed by the optical isolation lens group (2) in the optical path, and the light beam is focused and transmitted by the dynamic focusing lens group (3).

4. The 2um laser welding system based on complex polymer dynamic parameter adjustment according to claim 3 is characterized in that: The optical isolation lens group (2) comprises two wedge-shaped prisms, namely a first wedge-shaped prism (M1) and a second wedge-shaped prism (M2). The function of the optical isolation lens group (2) is to ensure that no return light is generated after the 2 um laser passes through.

5. The 2um laser welding system based on complex polymer dynamic parameter adjustment according to claim 4 is characterized in that: The dynamic focusing lens group (3) comprises two focusing lenses, namely a first focusing lens (M3) and a second focusing lens (M4). The function of the dynamic focusing lens group (3) is to compensate for the focusing and divergence of the laser beam. The focal length of each focusing lens is different. When the laser beam passes through the dynamic focusing lens group (3), the light spot is adjusted, so that the energy density on the high molecular polymer is different, the light spot size is different, and the welding surface is dynamically adjusted.

6. The 2um laser welding system based on complex polymer dynamic parameter adjustment according to claim 5 is characterized in that: The dynamic imaging detection unit is built on the basis of the FPN feature pyramid network. The dynamic imaging detection unit includes three layers, namely, a low layer, a middle layer and a high layer, and the outputs of the three layers are coupled to obtain the final output of the dynamic imaging detection unit; The low layers include convolutional layers, activation layers, pooling layers, batch normalization layers, residual block layers, and transposed convolutional layers in sequence; the middle layers include convolutional layers, activation layers, pooling layers, and feature fusion layers in sequence; the high layers include convolutional layers, nonlinear activation layers, maximum pooling layers, residual block layers, full convolutional layers, and feature fusion layers in sequence; A residual connection is made between the pooling layer and the feature fusion layer of the middle layer, and the residual connection is also connected to the residual block layer in the lower layer to achieve continuous jumping; the transposed convolution layer of the lower layer is connected to the feature fusion layer of the middle layer through the upsampling layer, and the output of the lower layer is input to the feature fusion layer of the middle layer; the feature fusion layer of the middle layer is connected to the feature fusion layer of the high layer through the upsampling layer, and the upsampling layer is also connected to the residual block layer of the high layer to achieve continuous jumping.

7. The 2um laser welding system based on complex polymer dynamic parameter adjustment according to claim 6 is characterized in that: Before the features are input to the higher layers, they are first extracted through a large kernel convolution operation.

8. The 2um laser welding system based on complex polymer dynamic parameter adjustment according to claim 7 is characterized in that: The intelligent feedback control unit uses an MPC control module, a PPO reinforcement learning module, and an LSTM long short-term memory neural network module to form a three-layer coupling architecture; The MPC control module calculates and processes the observation data of the current state and predicts it, and optimizes the welding parameters in the rolling time domain to predict the welding parameters for the next welding work; The PPO reinforcement learning module uses the future state prediction and current state real-time feedback provided by the MPC control module to adjust the control strategy to ensure that the intelligent feedback control unit can output the optimal welding parameters under uncertain conditions; The LSTM long short-term memory neural network module provides a prediction estimate of the future state based on the stored historical state, helping the MPC control module to predict the future state more accurately; The output of the intelligent feedback control unit is: ;in, for The optimal welding parameter output at the moment; For MPC control module Welding parameter output at each moment; Strengthen learning module for PPO The welding parameter output at the moment, where Learned for the PPO reinforcement learning module The optimal control strategy at each moment, for The current state at the moment; LSTM long short time series memory neural network module Hidden state output at the moment; , and are the weighted coefficients of the three-layer coupling architecture respectively.

Images