Electric arc additive lamination parameter real-time regulation and control system and method based on reverse modeling

Abstract

The invention discloses an electric arc additive lamination parameter real-time regulation and control system and method based on reverse modeling, and the method comprises the steps: obtaining data in an additive process through a data obtaining unit, carrying out the comparison with a theoretical model, obtaining defect data in an additive, carrying out the analysis, recognizing the defect type and severity, and carrying out the real-time regulation and control of the parameters. And in combination with information such as molten pool parameters, temperature field parameters, melt channel defects and component forming deviation, follow-up electric arc additive lamination parameters are corrected through parameter self-adaptive adjustment, and real-time automatic regulation and control of the lamination parameters in the electric arc additive process are achieved. The method has good generalization ability, is suitable for large complex components, and improves the stability of the electric arc additive process, reduces the defects of the electric arc additive component and improves the performance and quality of the electric arc additive component by automatically regulating and controlling parameters in the electric arc additive process in real time.

Description

Technical Field

[0001] The present invention belongs to the field of arc additive manufacturing, and in particular relates to a system and method for real-time control of arc additive layer deposition parameters based on inverse modeling. Background Art

[0002] As a key structural component of a ship, the tail shaft bracket bears complex loads, and its manufacturing quality is directly related to the safety and reliability of the ship. Currently, the tail shaft bracket is mainly manufactured through casting, which has problems such as low material utilization, long production cycles, and difficulty in manufacturing large and complex structures.

[0003] Wire arc additive manufacturing (WAAM) offers a new approach for the manufacture of ship stern shaft brackets, with its advantages of high material utilization, rapid prototyping, and the ability to manufacture large, complex structures. However, the WAAM process for manufacturing large, complex components is subject to complex path planning, high heat input, and relatively low forming accuracy. These factors can easily lead to excessive defects, coarse microstructures, and large shape errors in the finished parts, compromising the mechanical properties and forming accuracy of the stern shaft brackets. Therefore, a method and system for real-time control of WAAM buildup parameters is urgently needed to improve the quality and performance of WAAM stern shaft brackets. Summary of the Invention

[0004] In response to the above problems, the purpose of the present invention is to provide a real-time control system and method for arc additive lamination parameters based on inverse modeling, which greatly improves the forming quality and precision of arc additive without reducing the efficiency of arc additive, accumulates learning materials during the processing, and realizes real-time control of lamination parameters in the arc additive manufacturing process.

[0005] The specific technical solutions for achieving the purpose of the present invention are as follows:

[0006] A real-time control system for arc additive layer deposition parameters based on inverse modeling, comprising a control unit, a data acquisition unit, a motion execution unit, and an additive unit;

[0007] The material adding unit performs arc material adding action under the drive of the motion execution unit, and the data acquisition unit is arranged on or around the material adding unit to acquire various data in the arc material adding;

[0008] The control unit obtains data on the arc additive task and the additive process, and performs real-time regulation of arc additive layer parameters based on the data.

[0009] Furthermore, the data acquisition unit includes a thermal imager, a line laser sensor, a 3D vision scanner and a molten pool camera;

[0010] The 3D visual scanner covers the periphery of the component to be added material, and is used to obtain three-dimensional visual data of the component;

[0011] The thermal imager is fixedly connected to the additive unit and moves with the additive unit to obtain real-time temperature field data of the molten pool and the deposited layer;

[0012] The line laser sensor is fixedly connected to the additive unit and moves with the additive unit to obtain the topography data of the deposited layer;

[0013] The molten pool camera is fixedly connected to the additive unit and moves with the additive unit to obtain real-time morphology data of the molten pool.

[0014] Furthermore, the control unit includes a model parsing module, a parameter setting module, a slicing and additive strategy planning module, a reverse modeling module, an analysis module, and a parameter adaptive adjustment module;

[0015] The model parsing module performs parsing based on the imported component theoretical model to extract geometric structure information of points, edges and faces of the component model;

[0016] The parameter setting module is used to perform initial settings of various parameters in the arc additive task;

[0017] The slicing and additive strategy planning module performs slicing, path planning, process parameter matching, and actuator program generation based on the information of the analyzed component theoretical model;

[0018] The reverse modeling module is based on the three-dimensional point cloud information obtained by the line laser sensor and the 3D visual scanner, and is spliced into a complete three-dimensional model of the component. The discrete point cloud data is converted into a continuous three-dimensional surface model through interpolation and fitting algorithms to complete the reverse modeling of the component and obtain the actual model of the component.

[0019] The analysis module analyzes and calculates the temperature field and molten pool morphology information obtained by the thermal imager and the molten pool camera based on the actual model of the component, obtains the defects of the deposited layer and the overall forming deviation value, and evaluates the overall forming quality and defects according to the forming deviation threshold and defect standard set in the parameter setting module to determine whether the subsequent arc additive deposition parameters need to be corrected;

[0020] The parameter adaptive adjustment module adjusts subsequent arc additive layer deposition parameters through an adaptive iterative learning control algorithm based on multimodal data of defect information, forming deviation information, molten pool image, temperature field information and deposition layer profile, thereby eliminating defects in the arc additive manufacturing process and realizing real-time automatic control of the deposition parameters in the arc additive manufacturing process.

[0021] Furthermore, after importing the component theoretical model, the model parsing module repairs the imported model, processes possible topological errors and non-manifold geometry, and ensures the integrity and accuracy of the model.

[0022] Furthermore, the slicing and additive strategy planning module first inputs a preset slice layer thickness before slicing;

[0023] According to the different parts of the component model, the actual cladding situation, the shape of the envelope and the ratio of the envelope to the filling part, the model is sliced layer by layer and the thickness of each slice is corrected to dynamically adjust the layer thickness;

[0024] A composite filling method combining contour offset path and Zigzag internal filling path is used to determine the path trajectory of each layer;

[0025] Then, the ant colony algorithm is used to search for the optimal combination of path planning sequence and arc starting and extinguishing points to minimize the total empty stroke length of the filling path and complete the overall path planning.

[0026] Finally, the corresponding arc additive layer parameters are matched according to the results of each layer's path planning to determine the actuator's motion path planning and process planning.

[0027] Furthermore, the parameter adaptive adjustment module first extracts characteristic parameters based on multimodal data of defect information, forming deviation information, molten pool image, temperature field information and deposited layer profile, and performs data fusion on these parameters;

[0028] Build a support vector machine classification model and train it to classify and identify defects in the arc additive process;

[0029] According to the defect diagnosis results, the adaptive iterative learning control algorithm is used to adjust the subsequent arc additive layer parameters to eliminate defects in the arc additive manufacturing process and realize real-time automatic control of the layer parameters in the arc additive manufacturing process.

[0030] The present invention also provides a method for real-time control of arc additive deposition parameters based on inverse modeling, comprising the following steps:

[0031] Step 1: Import the theoretical model of the component to be added;

[0032] Step 2: Set component forming deviation threshold, defect standards and various parameters;

[0033] Step 3: Slice the component model in layers, use a composite path planning algorithm to complete path planning, match the arc additive layer parameters, and determine the actuator's motion planning and path planning;

[0034] Step 4: Use a 3D visual scanner and a line laser sensor to obtain the real-time forming morphology and current layer-by-layer morphology of the component, process the 3D point cloud, complete the 3D point cloud splicing, and perform reverse modeling on the printed parts of the component;

[0035] Step 5: Analyze the defects of the current layer buildup, identify the defect type and severity, and determine whether the defects can be eliminated through subsequent parameter adjustments. If so, correct the subsequent arc additive buildup parameters; if not, call subtractive equipment to deal with the defects;

[0036] Step 6: Compare and analyze the actual model of the printed part of the component with the theoretical model, calculate the overall forming deviation value, and determine whether it exceeds the set threshold;

[0037] Step 7: If the threshold is exceeded, the subsequent arc additive deposition parameters are corrected through an adaptive iterative learning control algorithm based on the multimodal data of defect information, forming deviation information, molten pool image, temperature field information and deposited layer profile, thereby realizing real-time automatic control of the arc additive process deposition parameters.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The solution of the present invention uses reverse modeling based on various sensor data to establish a real-time model of the printed part, and then compares and analyzes it with the theoretical model. Based on the analysis results, an adaptive iterative learning control algorithm is further used to achieve real-time adjustment of the arc additive process layer parameters, thereby improving the forming accuracy of the arc additive component.

[0040] The solution of the present invention can analyze and discover defects in real time during the arc additive manufacturing process and provide corresponding solutions, including parameter optimization and adjustment, to eliminate defects in a timely manner and improve the quality of arc additive components.

[0041] The present invention will be further described below with reference to specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 Schematic diagram of the system architecture for real-time control of arc additive deposition parameters based on inverse modeling in an embodiment of the present invention.

[0043] Figure 2 Schematic diagram of the flow of the method for real-time control of arc additive deposition parameters based on inverse modeling of the present invention. DETAILED DESCRIPTION

[0044] Example

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. The described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts are within the scope of protection of the present invention.

[0046] As used in this application and the claims, the words "a," "an," "an," and / or "the" are not intended to refer to the singular but may include the plural unless the context clearly indicates otherwise. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0047] Unless otherwise specifically stated, the relative arrangement of the parts and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present application. At the same time, it should be understood that, for ease of description, the sizes of the various parts shown in the drawings are not drawn according to actual proportional relationships. The techniques, methods and equipment known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the techniques, methods and equipment should be considered as part of the authorization specification. In all examples shown and discussed here, any specific values should be interpreted as being merely exemplary and not as limitations. Therefore, other examples of the exemplary embodiments may have different values. It should be noted that similar numbers and letters represent similar items in the following figures, and therefore, once an item is defined in one figure, it does not need to be further discussed in subsequent figures.

[0048] Combine Figure 1 , a real-time control system for arc additive layer deposition parameters based on inverse modeling, comprising a control unit 100, a data acquisition unit, a motion execution unit and an additive unit;

[0049] The additive unit performs arc additive action under the drive of the motion execution unit, which is the additive gun 240 in this embodiment. The data acquisition unit is disposed on or around the additive unit to acquire various data during the arc additive process.

[0050] The control unit 100 obtains data on the arc additive task and the additive process, and adjusts the arc additive layer parameters in real time according to the data.

[0051] The data acquisition unit includes a thermal imager 220, a line laser sensor 210, a 3D vision scanner (201 and 202) and a molten pool camera 230;

[0052] The 3D vision scanner covers the periphery of the component to be added material and is used to obtain three-dimensional visual data of the component. The 3D vision scanner in this embodiment includes a first 3D vision scanner 201 and a second 3D vision scanner 202, which are respectively arranged on both sides of the component, that is, the periphery of the component is within the working field of the two 3D vision scanners;

[0053] The thermal imager 220 is fixedly connected to the additive unit, i.e., the additive gun 240, and moves with the additive unit to obtain real-time temperature field data of the molten pool and the deposited layer;

[0054] The line laser sensor 210 is fixedly connected to the additive unit. In this embodiment, the line laser sensor 210 is arranged in the direction of travel of the additive gun 240 and is fixedly connected to the additive gun 240. It moves with the movement of the additive unit. The laser line is located 10 mm behind the molten pool to obtain the topography data of the deposited layer.

[0055] The molten pool camera 230 is fixedly connected to the additive unit and moves with the additive unit to obtain real-time morphology data of the molten pool.

[0056] The control unit 100 includes a model analysis module 110, a parameter setting module 120, a slicing and additive strategy planning module 130, a reverse modeling module 140, an analysis module 150 and a parameter adaptive adjustment module 160;

[0057] The model parsing module 110 performs parsing based on the imported component theoretical model to extract the geometric structure information of the points, edges and faces of the component model. In addition, after importing the component theoretical model, the model parsing module 110 repairs the imported model to process possible topological errors and non-manifold geometry to ensure the integrity and accuracy of the model.

[0058] The parameter setting module 120 is used to perform initial settings of various parameters in the arc additive task;

[0059] The slicing and additive strategy planning module 130 performs slicing, path planning, process parameter matching, and program generation for the robot actuator based on the information of the analyzed component theoretical model, including program generation for the initial additive task of the motion execution unit and the additive gun;

[0060] Specifically, before slicing, the preset slice layer thickness is first input;

[0061] According to the different parts of the component model, the actual cladding situation, the shape of the envelope and the ratio of the envelope to the filling part, the model is sliced layer by layer and the thickness of each slice is corrected to dynamically adjust the layer thickness;

[0062] A composite filling method combining contour offset path and Zigzag internal filling path is used to determine the path trajectory of each layer;

[0063] Then, the ant colony algorithm is used to search for the optimal combination of path planning sequence and arc starting and extinguishing points to minimize the total empty stroke length of the filling path and complete the overall path planning.

[0064] Finally, the corresponding arc additive layer parameters are matched according to the results of each layer path planning, and the action path planning and process planning of the actuator are determined.

[0065] The reverse modeling module 140 removes noise and useless data based on the three-dimensional point cloud information obtained by the line laser sensor 210 and the 3D visual scanner, and splices the point cloud data of multiple scans into a complete three-dimensional model of the component. The module then converts the discrete point cloud data into a continuous three-dimensional surface model through interpolation and fitting algorithms, thereby completing the reverse modeling of the component and obtaining the actual model of the component.

[0066] The analysis module 150 is used to identify deposited layer defects and calculate forming deviations. Based on the actual model of the component, combined with the temperature field and molten pool morphology information obtained by the thermal imager 220 and the molten pool camera 230, the analysis and calculation are performed to obtain the defects of the deposited layer and the overall forming deviation value. The overall forming quality and defects are evaluated according to the forming deviation threshold and defect standard set in the parameter setting module 120, and it is determined whether the subsequent arc additive deposition parameters need to be corrected.

[0067] The parameter adaptive adjustment module 160 is mainly used to optimize and update the subsequent arc additive layer buildup parameters. That is, based on the multimodal data of defect information, forming deviation information, molten pool image, temperature field information and deposited layer profile, the subsequent arc additive layer buildup parameters are adjusted through an adaptive iterative learning control algorithm to eliminate defects in the arc additive manufacturing process and realize real-time automatic control of the buildup parameters in the arc additive manufacturing process.

[0068] The parameter adaptive adjustment module of this solution first extracts characteristic parameters based on multimodal data of defect information, forming deviation information, melt pool image, temperature field information and deposited layer profile, and then performs data fusion on these parameters;

[0069] Build a support vector machine classification model and train it to classify and identify defects in the arc additive process;

[0070] According to the defect diagnosis results, the adaptive iterative learning control algorithm is used to adjust the subsequent arc additive layer parameters to eliminate defects in the arc additive manufacturing process and realize real-time automatic control of the layer parameters in the arc additive manufacturing process.

[0071] In addition, combined Figure 2 The present invention also provides a method for real-time control of arc additive layer deposition parameters based on inverse modeling, comprising the following steps:

[0072] Step 1: Import the theoretical model of the component to be added. Specifically in this embodiment, this is performed by the model parsing module 110. To improve the applicability of the system, the model parsing module 110 can import and parse model files in .obj, .step, .stp, and .stl formats;

[0073] Step 2: Setting component forming deviation thresholds, defect standards, and various parameters. In specific operations, this can be performed by the parameter setting module 120. The parameter setting module 120 provides a parameter interaction window on the host computer operation interface, where operators can set forming deviation thresholds and select defect standards.

[0074] Step 3: Slice the component model in layers, use a composite path planning algorithm to complete path planning, match the arc additive layer parameters, and determine the actuator's motion planning and path planning;

[0075] In this embodiment, the slicing and additive strategy planning module 130 is used to execute the process. A preset slicing layer thickness is inputted in the host computer operation interface. In this embodiment, the preset slicing layer thickness is 2 mm. After clicking the "Confirm" button in the host computer operation interface, the slicing and additive strategy planning module 130 performs stratification according to information such as different parts of the complex component model, actual cladding conditions, envelope shape, and the ratio of envelope to filling part, and dynamically adjusts the layer thickness. The composite filling method combining the built-in contour offset path and the Zigzag internal filling path in the slicing and additive strategy planning module 130 automatically determines the path trajectory of each layer. The built-in ant colony algorithm in the slicing and additive strategy planning module 130 optimizes the overall path and arc start and end points to search for the overall path with the minimum total idle stroke length. Finally, the corresponding arc additive layering parameters are automatically matched to the selected additive path to determine the motion planning and path planning of the actuator.

[0076] Step 4: Use a 3D visual scanner and a line laser sensor to obtain the real-time forming morphology and current layer-by-layer morphology of the component, process the 3D point cloud, complete the 3D point cloud splicing, and perform reverse modeling on the printed parts of the component;

[0077] Specifically, in this embodiment, the reverse modeling module 140 can be connected to the first 3D visual scanner 201 and the second 3D visual scanner 202 by means of communication interconnection, so as to obtain the three-dimensional point cloud information of the side circumference of the printed component part in real time; the reverse modeling module 140 can be connected to the line laser sensor 210 by means of communication interconnection, so as to obtain the three-dimensional point cloud information of the sedimentary layer in real time; the algorithm built into the reverse modeling module 140 automatically processes the three-dimensional point cloud information, removes noise and useless data, and splices the point cloud data of multiple scans into a complete three-dimensional model. Through interpolation and fitting algorithms, the discrete point cloud data is converted into a continuous three-dimensional surface model, thereby completing the reverse modeling of the component and obtaining the actual model of the printed component;

[0078] Step 5: Analyze the defects of the current layer buildup, identify the defect type and severity, and determine whether the defects can be eliminated through subsequent parameter adjustments. If so, correct the subsequent arc additive buildup parameters; if not, call subtractive equipment to deal with the defects;

[0079] In this embodiment, the analysis module 150 can be connected to the thermal imager 220 and the melt pool camera 230 based on a communication interconnection method to obtain temperature field information and melt pool morphology in real time. The analysis module 150 gives priority to the detection and assessment of defects. According to the defect standard set in step 2, the analysis module 150 compares the defect with the standard morphology, combines the melt pool morphology obtained by the melt pool camera 230 and the temperature field information obtained by the thermal imager 220, and performs multimodal data fusion to identify the type, location and severity of the defect. If it is judged that the severity of the defect is relatively minor, the defect information will be passed to the parameter adaptive adjustment module 160. The parameter adaptive adjustment module 160 adjusts the process parameters of the arc additive through an adaptive iterative learning control algorithm to eliminate the defect in the subsequent printing process; if it is judged that the severity of the defect is relatively serious, a defect alarm will be issued and the subtractive equipment will be called to handle the defect.

[0080] Step 6: Compare and analyze the actual model of the printed part of the component with the theoretical model, calculate the overall forming deviation value, and determine whether it exceeds the set threshold;

[0081] Step 7: If the threshold is exceeded, the subsequent arc additive deposition parameters are corrected through an adaptive iterative learning control algorithm based on the multimodal data of defect information, forming deviation information, molten pool image, temperature field information and deposited layer profile, thereby realizing real-time automatic control of the arc additive process deposition parameters.

[0082] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A real-time control system for arc additive deposition parameters based on inverse modeling, characterized in that: It includes a control unit, a data acquisition unit, a motion execution unit and an additive unit; The material adding unit performs arc material adding action under the drive of the motion execution unit, and the data acquisition unit is arranged on or around the material adding unit to acquire various data in the arc material adding; The control unit obtains data on the arc additive task and the additive process, and performs real-time regulation of arc additive layer parameters based on the data.

2. The arc additive layer parameter real-time control system based on reverse modeling according to claim 1 is characterized in that: The data acquisition unit includes a thermal imager, a line laser sensor, a 3D vision scanner and a molten pool camera; The 3D visual scanner covers the periphery of the component to be added material, and is used to obtain three-dimensional visual data of the component; The thermal imager is fixedly connected to the additive unit and moves with the additive unit to obtain real-time temperature field data of the molten pool and the deposited layer; The line laser sensor is fixedly connected to the additive unit and moves with the additive unit to obtain the topography data of the deposited layer; The molten pool camera is fixedly connected to the additive unit and moves with the additive unit to obtain real-time morphology data of the molten pool.

3. The arc additive deposition parameter real-time control system based on reverse modeling according to claim 2 is characterized in that: The control unit includes a model analysis module, a parameter setting module, a slicing and additive strategy planning module, a reverse modeling module, an analysis module and a parameter adaptive adjustment module; The model parsing module performs parsing based on the imported component theoretical model to extract geometric structure information of points, edges and faces of the component model; The parameter setting module is used to perform initial settings of various parameters in the arc additive task; The slicing and additive strategy planning module performs slicing, path planning, process parameter matching, and actuator program generation based on the information of the analyzed component theoretical model; The reverse modeling module is based on the three-dimensional point cloud information obtained by the line laser sensor and the 3D visual scanner, and is spliced into a complete three-dimensional model of the component. The discrete point cloud data is converted into a continuous three-dimensional surface model through interpolation and fitting algorithms to complete the reverse modeling of the component and obtain the actual model of the component. The analysis module analyzes and calculates the temperature field and molten pool morphology information obtained by the thermal imager and the molten pool camera based on the actual model of the component, obtains the defects of the deposited layer and the overall forming deviation value, and evaluates the overall forming quality and defects according to the forming deviation threshold and defect standard set in the parameter setting module to determine whether the subsequent arc additive deposition parameters need to be corrected; The parameter adaptive adjustment module adjusts subsequent arc additive layer deposition parameters through an adaptive iterative learning control algorithm based on multimodal data of defect information, forming deviation information, molten pool image, temperature field information and deposition layer profile, thereby eliminating defects in the arc additive manufacturing process and realizing real-time automatic control of the deposition parameters in the arc additive manufacturing process.

4. The arc additive deposition parameter real-time control system based on reverse modeling according to claim 3 is characterized in that: After importing the component theoretical model, the model parsing module repairs the imported model, processes possible topological errors and non-manifold geometry, and ensures the integrity and accuracy of the model.

5. The arc additive deposition parameter real-time control system based on reverse modeling according to claim 3 is characterized in that: The slicing and additive strategy planning module first inputs a preset slice layer thickness before slicing; According to the different parts of the component model, the actual cladding situation, the shape of the envelope and the ratio of the envelope to the filling part, the model is sliced layer by layer and the thickness of each slice is corrected to dynamically adjust the layer thickness; A composite filling method combining contour offset path and Zigzag internal filling path is used to determine the path trajectory of each layer; Then, the ant colony algorithm is used to search for the optimal combination of path planning sequence and arc starting and extinguishing points to minimize the total empty stroke length of the filling path and complete the overall path planning. Finally, the corresponding arc additive layer parameters are matched according to the results of each layer's path planning to determine the actuator's motion path planning and process planning.

6. The arc additive layer parameter real-time control system based on reverse modeling according to claim 3 is characterized in that: The parameter adaptive adjustment module first extracts characteristic parameters based on multimodal data of defect information, forming deviation information, molten pool image, temperature field information and deposition layer profile, and performs data fusion on these parameters; Build a support vector machine classification model and train it to classify and identify defects in the arc additive process; According to the defect diagnosis results, the adaptive iterative learning control algorithm is used to adjust the subsequent arc additive layer parameters to eliminate defects in the arc additive manufacturing process and realize real-time automatic control of the layer parameters in the arc additive manufacturing process.

7. A method for real-time control of arc additive deposition parameters based on inverse modeling, characterized in that: The following steps are involved: Step 1: Import the theoretical model of the component to be added; Step 2: Set component forming deviation threshold, defect standards and various parameters; Step 3: Slice the component model in layers, use a composite path planning algorithm to complete path planning, match the arc additive layer parameters, and determine the actuator's motion planning and path planning; Step 4: Use a 3D visual scanner and a line laser sensor to obtain the real-time forming morphology and current layer-by-layer morphology of the component, process the 3D point cloud, complete the 3D point cloud splicing, and perform reverse modeling on the printed parts of the component; Step 5: Analyze the defects of the current layer buildup, identify the defect type and severity, and determine whether the defects can be eliminated through subsequent parameter adjustments. If so, correct the subsequent arc additive buildup parameters; if not, call subtractive equipment to deal with the defects; Step 6: Compare and analyze the actual model of the printed part of the component with the theoretical model, calculate the overall forming deviation value, and determine whether it exceeds the set threshold; Step 7: If the threshold is exceeded, the subsequent arc additive deposition parameters are corrected through an adaptive iterative learning control algorithm based on the multimodal data of defect information, forming deviation information, molten pool image, temperature field information and deposited layer profile, thereby realizing real-time automatic control of the arc additive process deposition parameters.

8. The method for real-time control of arc additive deposition parameters based on reverse modeling according to claim 7, characterized in that: The action planning and path planning of the actuator determined in step 3 are specifically as follows: First, input the preset slice layer thickness. According to the different parts of the component model, the actual cladding situation, the envelope shape and the ratio of the envelope to the filling part, the model is sliced layer by layer and the thickness of each slice layer is corrected to dynamically adjust the layer thickness. A composite filling method combining contour offset path and Zigzag internal filling path is used to determine the path trajectory of each layer; Ant colony algorithm is used to search for the optimal combination of path planning sequence and arc starting and extinguishing points to minimize the total empty stroke length of the filling path and complete the overall path planning; Finally, the corresponding arc additive layer parameters are matched according to the results of each layer's path planning to determine the actuator's motion path planning and process planning.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 7 to 8 are implemented.

10. A computer storable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 7 to 8 are implemented.

Images