Additive manufacturing deposition layer repair method by varying real-time cladding volume

Abstract

Based on the change of real-time cladding volume additive manufacturing deposition layer repair method, it mainly solves the existing deposition layer surface uneven, high requirement of metal transition stability when the deposition of the wall, and the deposition layer shape irregular problem. The technical scheme is that the visual positioning is used to complete the welding machine self-starting identification of the accumulated wall layer additive manufacturing process, deposition layer position pre-marking and real-time position acquisition, and the binocular vision sensing system is used to collect the data of the side edge profile of the deposition layer and feed back to the image processing system. According to the original setting deposition layer parameters and the received position parameters, the area of the deposition layer required to be filled is calculated, and then the wire cladding volume required to fill the deposition layer is calculated, the process parameters are inversely solved according to the wire cladding volume, and then the process parameters are fed back to the main control system. The main control system changes the wire feeding speed and the welding gun moving speed to change the cladding volume, so as to achieve the effect of filling the deposition layer.

Description

Technical Field

[0001] This invention specifically relates to a repair method for additive manufacturing deposited layers based on changing the real-time cladding amount, which belongs to the field of additive manufacturing. Background Technology

[0002] In arc additive manufacturing, unstable metal transitions and heat accumulation effects can lead to uneven surfaces on the deposited layer, reducing product precision. To ensure the quality of the deposited layer, defects need to be repaired. However, during repair, the surface unevenness of the deposited layer needs to be monitored in real time, making it difficult to control the quality of the repair.

[0003] Currently, the commonly used welding repair techniques for repairing metal parts mainly include automatic submerged arc welding, gas shielded welding, plasma arc welding, and laser cladding. Electric arc welding is simple, flexible, and requires minimal equipment, making it suitable for various welding repair applications, but its production efficiency is low. Automatic submerged arc welding is a stable process with low operational skill requirements and high productivity, but it is only suitable for large-volume repairs of long deposition layers and thick, large parts. Gas shielded welding does not require welding rods or flux, and there is no need to clean the welded surface after repair; it has high productivity and low repair costs, but its application is greatly limited. Spray painting has a wide range of applications on part materials, but the operation is difficult. Due to the high thermal conductivity of the material, the contact temperature drops rapidly upon impact with the part surface, preventing proper fusion. Essentially, most deposition repair methods have some degree of inaccuracy.

[0004] Whether in welding repair or arc additive manufacturing, there is a need for a technology that can repair defects in the deposited layer in real time. This invention proposes a repair method for additive manufacturing deposited layers based on changing the real-time cladding amount to improve the efficiency and quality of deposited layer repair. Summary of the Invention

[0005] The purpose of this invention is to provide a method for filling defects that occur during the welding deposition process. It designs a method to fill the defects in the deposition layer by calculating the amount of cladding to be repaired and then resolving the required repair process parameters. By using a binocular vision sensing system, the location and trajectory of the defects can be found more accurately, thereby effectively solving the problem of over-welding and under-welding caused by low accuracy.

[0006] The objective of this invention is achieved through the following technical solutions: such as Figure 1As shown, the device includes a binocular vision sensing system, an image processing system, an adjustable wire feeder, a welding torch, and a main control system. Its operation is as follows: During the deposition process, the binocular vision sensing system, composed of two industrial high-speed cameras (a and b), monitors and captures images in real time, transmitting the data to the image processing system. The image processing system extracts parameters, processes the data, and compares it with the original data before feeding it back to the main control system. During the deposition repair process, the main control system further utilizes the data fed back from the image processing system and sends target commands to the machine. The machine then adjusts the cladding amount by changing the wire feed speed and the welding torch movement speed, thereby achieving the effect of filling the deposition layer.

[0007] The overall process of the method is divided into a deposition process and a deposition repair process. During the deposition process, a binocular vision sensing system observes in real time as each layer is deposited. The image processing system analyzes and calculates the data for each deposition layer corresponding to each time period t, and stores it. After each layer deposition process is completed, the deposition repair process begins. During the deposition repair process, the main control system calls the processed data for each deposition layer from the deposition process and then controls an automatic welding machine to repair the deposition layer. Simultaneously, the main control system also controls industrial high-speed cameras a and b to continuously observe the layer. The observation results are used by the image processing system to determine whether a secondary repair is needed for this layer. Furthermore, when the deposition repair process is about to end and the next layer deposition process is about to begin, the image processing system performs mean filtering on each set of previously collected data, obtains the optimal data, stores it for engineers to reference and improve, and releases excess data to save memory space.

[0008] The method for repairing the deposited layer employs a controlled variable approach, which has two methods: one is the wire feeding speed v. s With the cladding fill function V remaining constant, T (x) Calculate the location to be repaired x i Required welding torch moving speed v h Secondly, the moving speed v of the welding torch. h With the cladding fill function V remaining constant, T (x) Calculate the location to be repaired x i Required wire feeding speed v s .

[0009] The binocular vision sensing system consists of two industrial high-speed cameras, a and b, which operate simultaneously with the deposition process. During deposition, the high-speed cameras a and b capture real-time cross-sectional images of the deposition layer from the left and right sides, respectively, and feed them back to the image processing system. The image processing system first compares and fits the left and right cross-sections of the deposition layer fed back by the binocular sensing system to determine whether repair is needed. If repair is needed, the system processes and analyzes the data; otherwise, it releases the image data from the memory.

[0010] The image processing system analyzes and processes the real-time data fed back by the binocular vision sensing system before transmitting the processed data to the main control system. During operation, the system first compares the real-time image data from the binocular vision sensing system with the desired image data. If the comparison error is large, the system further processes the real-time data. If the error is negligible, the system proceeds to compare data from the next time period. Next, the system extracts feature values ​​from the sedimentation layer contour image from the binocular vision sensing system and obtains the side contour function F(x) through fitting and comparison. Then, based on the side contour function F(x), layer height h, and layer width d, it calculates the original area S, the current area S1, and the area to be filled S. i Further determine the location x of the sedimentary layer to be repaired. i The required cladding volume function V R (x i Meanwhile, the optimal wire feeding speed v obtained after multiple experiments will be determined. s and the moving speed v of the welding torch h Volume function V of required cladding amount R (x i The cladding fill function V is obtained by combining these steps. T (x). Finally, the image processing system feeds back the processed data to the main control system for further processing. During each data processing iteration, the image processing system simultaneously optimizes and adjusts the side contour function F(x), continuously optimizing until the optimal state is reached. When depositing the next layer to the repair location, the cladding fill function V is used... T (x) Adjust the wire feeding speed v s and the moving speed v of the welding torch h This is used to control the amount of cladding at the location to be repaired, thereby filling the surface of the deposited layer and making the surface of the previous deposited layer smooth again.

[0011] The main control system primarily receives data processed and analyzed by the image processing system to write instructions and control the welding machine. When receiving data from the image processing system, fuzzy PID control is used to control the automatic welding machine. Fuzzy PID control is an intelligent control algorithm that mimics human fuzzy reasoning and decision-making processes. Simultaneously, the main control system monitors the working status of industrial high-speed cameras a and b. During the deposition repair process, the main control system continuously monitors the machine, repairing while observing. The observation results are judged by the image processing system. If no non-negligible defects are found, the next layer of deposition is performed. If non-negligible defects remain after one layer of repair, a feedback process is initiated. This monitoring method not only significantly reduces the error in deposition repair but also saves time and improves repair efficiency.

[0012] The feedback process, namely the secondary repair performed after the first layer of deposition repair, ensures the accuracy of the process. In this process, the main control system first sends a specific signal to the image processing system. The image processing system then transmits the location to be repaired a second time and the required cladding amount to the main control system, which then controls the repair process.

[0013] The automatic welding machine includes a welding torch and an adjustable wire feeder. When the automatic welding machine receives a time command, it controls the duration of dwell time on each segment of the deposition layer without changing other conditions. When it receives a command to change the wire feeding method, the welding machine will change the amount of cladding required while keeping other parameters constant by changing the wire feeding method, angle, etc., to perform the repair.

[0014] The main features of this invention are: First, a binocular vision sensing system is used to collect cross-sectional data from the left and right sides of the sedimentary layer in real time, and these data are simultaneously fitted and compared to obtain a contour image of the sedimentary layer and a predetermined trajectory for each time period. Then, the fitted image data is transmitted to an image processing system for further analysis: feature values ​​of the side contours in the image are extracted, and a side contour function F(x) is calculated and fitted from the feature values. Finally, based on the side contour function F(x), layer height h, and layer width d, the repair location x of the sedimentary layer is calculated. i Required cladding amount V R (x i When the automated welding machine deposits a layer onto the area to be repaired, it determines the cladding fill function V. T (x) Adjust the wire feeding speed v s and the moving speed v of the welding torch h This allows for the control of the cladding amount at the repair site, thereby filling the surface of the deposited layer and smoothing the surface of the previous deposited layer again. By controlling the entire process from part to whole, not only can sequential cyclical repairs be performed, but the entire system also uses feedback to adjust and monitor the repair process in real time, reducing errors.

[0015] The beneficial effects of this invention are that it provides a repair method for additive manufacturing deposited layers based on changing the real-time cladding amount, which repairs the unevenness and unavoidable defects that occur on the surface of the deposited layer during molten wire deposition, reducing the risk of collapse; at the same time, it can provide timely feedback and repair when surface unevenness problems occur, improving workpiece quality; the method provided by this invention can fill and repair at the same time, reducing the defect rate, reducing material waste, and effectively improving production efficiency. Attached Figure Description

[0016] Figure 1 Overall system flowchart

[0017] Figure 2 Schematic diagram of the sedimentary layer cross section

[0018] Figure 3 Working principle diagram of the deposition process

[0019] Figure 4 Working principle of deposition repair process

[0020] Figure 5 Schematic diagram of the metal parts repair process Detailed Implementation

[0021] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments.

[0022] See Figure 1 This is the overall system flowchart. The main devices for the repair process include industrial high-speed cameras a and b, an image processing system, a main control system, and an automatic welding machine. Industrial high-speed cameras a and b are placed on the left and right sides of the sedimentary layer, respectively, to observe the deposition process in real time and record cross-sectional data of the sedimentary layer—the cross-sectional image a recorded by camera a on the left and the cross-sectional image b recorded by camera b on the right. The image data for each time period is compared and fitted before being sent to the image processing system. The image processing system processes, optimizes, and fits the image data to obtain the side profile curve and calculates the sedimentary layer side profile function F(x) and trajectory curve. Simultaneously, the image processing system calculates the repair location x using the side profile function and existing layer height h, layer width d, and other data. i Required cladding amount V R (x i ), and then based on the wire feeding speed v s The moving speed v of the welding torch h Side profile function F(x) and required cladding amount V R (x i Obtain the cladding fill function V T (x). The image processing system sets the wire feeding speed v based on experience. s The moving speed v of the welding torch h The initial value is used to obtain the initial cladding fill function V. T (x) This is then sent to the main control system. After the main control system writes the commands, it controls the automatic welding machine to repair the deposited layer, while simultaneously changing the wire feeding speed v. s The moving speed v of the welding torch h Change the cladding fill function V T (x), thereby changing the cladding amount to achieve the effect of repairing the sedimentary layer. During the sedimentary layer repair process, in order to reduce errors, the binocular vision sensing system will also observe in real time and repeat the above steps.

[0023] See Figure 2This is a side cross-sectional view of the sedimentary layer. The height h represents the original sedimentary layer parameters. The view shows the trajectory curves of three repaired sedimentary layers and one repaired sedimentary layer. Below the trajectory curve is the existing area S1, and the light gray area above it is the area S that needs repair. i Based on the floor height h and the area S to be repaired. i The required volume of cladding is calculated, and repairs are carried out accordingly.

[0024] Example 1: Repairing additively manufactured deposited layers.

[0025] See Figure 3 and Figure 4 This is a schematic diagram illustrating the working principle of the deposition process and the deposition layer repair process. It consists of industrial high-speed cameras a and b, an adjustable wire feeder, and an automatic welding machine. During the deposition process, industrial high-speed cameras a and b observe the deposition layer in real time from both sides. The observed data is then compared and fitted to images before being sent to the image processing and analysis system. The image processing and analysis system analyzes and calculates the required cladding amount V based on the transmitted data. R (x i ) and cladding fill function V T (x) Then, the deposition repair process begins. At this time, the main control system receives data from the image processing and analysis system and sends control commands to the automatic welding machine. By changing the wire feeding speed and the welding torch movement speed, the cladding amount is changed, thereby achieving the effect of filling the deposition layer. At the same time, industrial high-speed cameras a and b will continue to perform real-time observation to reduce the error of the deposition layer repair.

[0026] Example 2: Repair of metal parts.

[0027] See Figure 5 This describes the metal part repair process. The automatic welding machine starts repairing from the left, then proceeds to repair from the right after the first layer on the left is completed, repeating this process until the repair is finished. During the repair, a binocular vision sensing system monitors the entire process in real time. If the repaired part surface does not match expectations, the system transmits the image parameters and the fitted image trajectory curve to the image processing system for data processing. The data is then fed back to the main control system, which performs a second repair until the surface is smooth and meets the desired effect. After repair, any excess material is trimmed until the desired result is achieved. This metal part repair method primarily involves changing the wire feeding speed v. s and the moving speed v of the welding torch hThis method allows for the adjustment of the cladding amount, thereby enabling repair. Furthermore, this repair method is not only easy to implement but also saves the cost of remanufacturing a metal part. It is also applicable to different metal parts that require repair after damage.

Claims

1. An additive manufacturing deposition layer repair method based on changing the real-time cladding amount, characterized by: To repair surface irregularities in the sedimentary layer that occur during deposition, a binocular vision sensing system is used to observe the deposition process in real time. Contour images of the sedimentary layer are obtained through comparison and fitting. The acquired images are then input into an image processing system to extract feature values ​​of the side contours. A side contour function F(x) is calculated and fitted based on these feature values. Finally, the repair location x in the sedimentary layer is calculated using the side contour function F(x), layer height h, and layer width d. i Required cladding amount V R (x i When the next layer is deposited to the repair location, according to the cladding fill function V... T (x) Adjust the wire feeding speed v s and the moving speed v of the welding torch h This is used to control the amount of cladding at the location to be repaired, thereby filling the surface of the deposited layer and making the surface of the previous deposited layer smooth again.

2. The additive manufacturing deposition layer repair method based on changing the real-time cladding amount according to claim 1, characterized in that: cladding Fill function V T (x) is based on the wire feeding speed v. s The moving speed v of the welding torch h The side profile function F(x) and the required cladding amount are used to determine the cladding fill function V before repair. T (x) Solve for the wire feeding speed v at the location to be repaired. s and the moving speed v of the welding torch h The two process parameter information are transmitted to the main control system, which then controls the position x to be repaired. i The wire feeding speed v s and the moving speed v of the welding torch h To adjust the cladding amount V R (x i ).

3. The additive manufacturing deposition layer repair method based on changing the real-time cladding amount according to claim 1, characterized in that: The structure used in the repair process includes a binocular vision sensing system, an image processing system, an adjustable wire feeder, a welding torch, and a main control system. The binocular vision sensing system includes industrial high-speed cameras a and b, which acquire contour images of the sedimentary layer's sides in real time, specifically camera a capturing a cross-sectional contour image of the sedimentary layer from the left side and camera b capturing a cross-sectional contour image of the sedimentary layer from the right side. These images are then input into the image processing system, and the main control system processes them according to the cladding fill function V. T (x) is used to solve for the process parameter values, and then control them at the location to be repaired, x. i The wire feeding speed v s and the moving speed v of the welding torch h Size.

4. The additive manufacturing deposition layer repair method based on changing the real-time cladding amount according to claim 1, characterized in that: The image processing system processes the position parameters x of each trajectory image fed back by the binocular vision sensing system in real time. i Image feature values ​​are extracted and fitted to obtain a highly accurate side profile function F(x). Then, the location x to be repaired in the sediment layer is calculated based on the layer height h and the side profile function F(x). i The area S to be filled i Then according to S i x is calculated using the layer width d. i Volume function V of required cladding amount R (x i ).

Images