Electric arc fuse wire additive material pore defect detection method based on multiple sensing signals

Abstract

An electric arc fuse wire additive material pore defect detection method based on multiple sensing signals comprises the steps that an online monitoring platform is built firstly, and the online monitoring platform comprises an electric arc fuse wire mechanical arm, a high-speed CCD camera, a current and voltage acquisition module and a spectrum acquisition module; secondly, high-speed CCD image information, current and voltage signals and spectral signals are collected in real time in the electric arc fuse wire additive manufacturing process, size and position information of pore defects is obtained by conducting CT scanning on a printed piece, and a pore defect feature set is analyzed and constructed; the pore defects are divided into non-pore defects, small pore defects and medium-large pore defects, high-speed CCD images, current and voltage signals and spectral signals collected at corresponding moments are subjected to correspondence, and a pore defect feature data set is extracted; and finally, directional optimization of the arc fuse wire additive manufacturing process is carried out according to the pore defect feature data set. According to the invention, nondestructive and rapid detection of pore defects in arc fuse additive manufacturing is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of arc fuse additive manufacturing, and in particular to a method for detecting pore defects in arc fuse additive manufacturing based on multiple sensor signals. Background Art

[0002] Arc fuse additive manufacturing technology is widely used in aerospace, automobile manufacturing and other fields due to its high efficiency and flexibility. The physical mechanism of the interaction between arc and material in the additive manufacturing process is extremely complex. This complexity may cause defects such as cracks, holes, inclusions, etc. inside and outside the parts, which will seriously affect the performance and service life of the parts. Therefore, in order to ensure the reliability of additive manufacturing technology and the high quality of parts, it is particularly important to implement online monitoring and defect detection.

[0003] Online monitoring technology can monitor the manufacturing process in real time, detect and warn potential defects in a timely manner, thereby ensuring the quality and performance of the parts. Through the application of this technology, early identification and timely intervention of defects can be achieved in the manufacturing process, greatly improving the reliability and safety of products, which is crucial to improving the development level of high-end equipment manufacturing and high-precision and cutting-edge technology.

[0004] The patent application named "Metal Surface Defect Detection Method and System Based on Improved YOLOX" (publication number: CN117635521A) receives metal defect detection samples with annotations, pre-processes the annotated metal defect detection samples, and obtains a metal defect data set. However, similar methods of using data sets for training require manual annotation, and there are problems such as a large amount of labeled data. Summary of the invention

[0005] In order to overcome the shortcomings of the above-mentioned prior art, the purpose of the present invention is to provide a method for detecting pore defects in arc fuse additive manufacturing based on multi-sensor signals. In the process of arc fuse additive manufacturing, high-speed CCD image information, current and voltage signals, and spectral signals are collected, and the size and position information of the pore defects are obtained by CT scanning the printed part, and the feature data set corresponding to the defect is obtained from the signal. The pore defects in arc fuse additive manufacturing are detected by machine learning, so as to realize real-time non-destructive and rapid detection of pore defects in arc fuse additive manufacturing.

[0006] In order to achieve the above object, the present invention is implemented by the following technical solutions:

[0007] A method for detecting porosity defects in arc fuse additives based on multiple sensor signals comprises the following steps:

[0008] The first step is to build an online monitoring platform, which includes an arc fuse robot arm, a high-speed CCD camera, a current and voltage acquisition module, and a spectrum acquisition module;

[0009] In the second step, the arc fuse additive process collects high-speed CCD image information, current and voltage signals, and spectral signals in real time. The size and position information of the pore defects are obtained by CT scanning the printed parts, and the pore defect feature set is analyzed and constructed; the pore defects are divided into: no pore defects, small pore defects, medium and large pore defects, and the high-speed CCD images, current and voltage signals, and spectral signals collected at the corresponding time are matched to extract the pore defect feature data set;

[0010] In the third step, the directional optimization of the arc fuse additive process is carried out based on the porosity defect feature dataset.

[0011] The second step is specifically as follows: first obtain high-speed CCD images, current and voltage signals, and spectral signals during the arc fuse additive manufacturing process, and at the same time build a pore defect data set of the printed parts to associate the signal features with the pore defects; pre-build a standard defect recognition module, and use the sample defect features to concentrate the pore defect samples to update the model parameters of the standard defect recognition module.

[0012] Construct a porosity defect dataset of the printed part. Specifically, collect data during the arc fuse additive process, perform industrial CT scanning on the printed part after printing, and obtain the location of the porosity defect center and the porosity defect size information.

[0013] The signal features are associated with the pore defects, specifically: the arc area, current and voltage signal base value and peak value, and spectral characteristic line information in the high-speed CCD image are extracted and corresponded with the defect information, and the characteristic value weights are set in segments to improve the online monitoring effect and accuracy; high-speed CCD is used to record the video, frame-by-frame image processing is performed, the grayscale threshold is set, the number of pixels in the arc part is calculated to reflect the size of the arc area, and the position of the arc fuse gun tip at that moment is determined and corresponded to the defect position, and also to the current and voltage values ​​at that moment.

[0014] Construct the relationship between arc area and current and voltage, the relationship function is as follows:

[0015]

[0016] Among them, S is the arc area, k is the relationship coefficient, η is the thermal efficiency, U i is the instantaneous voltage, I i is the instantaneous current, v is the welding speed;

[0017] At the same time, high-speed CCD, current, voltage, and spectral signals are collected and associated with the pore defects of the printed parts. Based on the different sizes of the pore defects, they are disassembled into multi-sensor information corresponding to no pore defects, small pore defects, and medium and large pore defects.

[0018] The third step is specifically as follows: training a machine learning model based on the obtained pore defect feature data set, and predicting the formation of pores online; and feeding back the predicted pore position and size to the arc fuse welding gun control interface to adjust the wire feeding speed and welding speed.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] (A) Since the present invention adopts an online monitoring method and uses the spectrum, current and voltage, and high-speed CCD image monitored during the arc fuse additive manufacturing process, it is non-destructive and fast compared to traditional detection methods.

[0021] (B) Since the present invention adopts multiple sensing methods such as spectrum, current voltage, and high-speed CCD image, it reduces the disadvantages of signal instability caused by using a single signal source, and has the advantages of multiple signal sources, more reliable analysis results, and high credibility; at the same time, it uses machine learning methods, and there is no need to manually label a large number of data sets for training.

[0022] (C) Since the present invention adopts the method of online monitoring and closed-loop control, the process parameters can be adjusted through real-time monitoring results to achieve the advantage of reducing the formation of pore defects.

[0023] In summary, the present invention collects high-speed CCD image information, current and voltage signals, and spectral signals in the arc fuse additive manufacturing process, obtains feature data sets from the signals, and detects porosity defects in the arc fuse additive manufacturing through machine learning, thereby realizing non-destructive and rapid detection of porosity defects in the arc fuse additive manufacturing. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 The figure is a flow chart of a method according to an embodiment of the present invention.

[0025] Figure 2 This is the high-speed CCD image processing process of the embodiment of the present invention.

[0026] Figure 3 The figures are comparison diagrams of pore changes before and after optimization of the embodiments of the present invention; wherein (a) is the pore diagram before optimization of the embodiments; and (b) is the pore diagram after optimization of the embodiments. DETAILED DESCRIPTION

[0027] The present invention is described in detail below in conjunction with embodiments and drawings.

[0028] Reference Figure 1 , a method for detecting porosity defects in arc fuse additives based on multi-sensor signals, comprising the following steps:

[0029] The first step is to build an online monitoring platform, which includes an arc fuse robot arm, a high-speed CCD camera, a current and voltage acquisition module, and a spectrum acquisition module;

[0030] In the second step, the arc fuse additive process collects high-speed CCD image information, current and voltage signals, and spectral signals in real time. The size and position information of the pore defects are obtained by CT scanning the printed parts, and the pore defect feature set is analyzed and constructed; the pore defects are divided into: no pore defects, small pore defects, medium and large pore defects, and the high-speed CCD images, current and voltage signals, and spectral signals collected at the corresponding time are matched to extract the pore defect feature data set;

[0031] In this embodiment, a high-speed CCD image, current and voltage signal, and spectral signal are first obtained during the additive manufacturing process of the arc fuse, and a pore defect data set of the printed part is constructed, and the signal features are associated with the pore defects; a standard defect recognition module is pre-constructed, and the pore defect samples in the sample defect feature set are used to adjust and update the model parameters of the standard defect recognition module;

[0032] The specific steps of constructing the pore defect dataset of the printed part are as follows: collecting data during the arc fuse additive process, performing industrial CT scanning on the printed part after printing, and obtaining the location of the pore defect center and the pore defect size information;

[0033] The signal features are associated with the pore defects as follows: the arc area, current and voltage signal base value and peak value, and spectral characteristic line information in the high-speed CCD image are extracted, corresponding to the defect information, and the characteristic value weight is set in sections to improve the online monitoring effect and accuracy; the video is recorded with a high-speed CCD, and frame-by-frame image processing is performed, the grayscale threshold is set, and the number of pixels in the arc part is calculated to reflect the size of the arc area, and the position of the arc fuse gun head at that moment is determined, corresponding to the defect position, and corresponding to the current and voltage value at that moment;

[0034] Construct the relationship between arc area and current and voltage, the relationship function is as follows:

[0035]

[0036] Among them, S is the arc area, k is the relationship coefficient, η is the thermal efficiency, U i is the instantaneous voltage, I i is the instantaneous current, v is the welding speed;

[0037] At the same time, high-speed CCD, current voltage, and spectral signals are collected and correlated with the pore defects of the printed parts. Based on the different sizes of pore defects, they are disassembled into multi-sensor information corresponding to no pore defects, small pore defects, and medium and large pore defects;

[0038] In the third step, the directional optimization of the arc fuse additive process is carried out based on the porosity defect feature dataset.

[0039] This embodiment performs machine learning model training based on the obtained pore defect feature data set, and simultaneously predicts the formation of pores online; based on the predicted pore position and size, feedback is given to the arc fuse welding gun control interface to adjust the wire feeding speed and welding speed.

[0040] Reference Figure 2 , Figure 2 The high-speed CCD image processing process of this embodiment is as follows: the video captured by the high-speed CCD is processed frame by frame, and then the initial image is processed in grayscale, and the number of pixels in the arc area is extracted to reflect the size of the arc area; at the same time, since the substrate will reflect the arc during the arc fuse additive process, it will interfere with the extraction of pixels, so it is necessary to perform regional selection on the obtained grayscale image to eliminate this part of the influence, that is, Figure 2 The final image result is shown.

[0041] Reference Figure 3 , Figure 3 The figure is a comparison diagram of the porosity changes before and after the optimization of this embodiment; wherein (a) is the porosity diagram before the optimization of the embodiment, and (b) is the porosity diagram after the optimization of the embodiment; it can be seen that before the optimization of the embodiment, the arc fuse additive has obvious porosity defects. After the optimization of the embodiment, the wire feeding speed and the welding speed are changed to achieve the purpose of changing the heat input. In the additive manufacturing process, the porosity defects usually increase with the increase of heat input. By reducing the heat input at the position where the porosity is detected to have a tendency to appear, the porosity is effectively reduced.

Claims

1. A method for detecting pore defects in arc fuse additives based on multi-sensor signals, characterized in that: The following steps are involved: The first step is to build an online monitoring platform, which includes an arc fuse robot arm, a high-speed CCD camera, a current and voltage acquisition module, and a spectrum acquisition module; In the second step, the arc fuse additive process collects high-speed CCD image information, current and voltage signals, and spectral signals in real time. The size and position information of the pore defects are obtained by CT scanning the printed parts, and the pore defect feature set is analyzed and constructed; the pore defects are divided into: no pore defects, small pore defects, medium and large pore defects, and the high-speed CCD images, current and voltage signals, and spectral signals collected at the corresponding time are matched to extract the pore defect feature data set; In the third step, the directional optimization of the arc fuse additive process is carried out based on the porosity defect feature dataset.

2. The method according to claim 1, characterized in that The second step is specifically as follows: firstly, obtaining a high-speed CCD image, current and voltage signals, and spectral signals during the arc fuse additive manufacturing process, and at the same time constructing a pore defect data set of the printed part, and establishing a correlation between the signal features and the pore defects; A standard defect recognition module is pre-built, and the pore defect samples in the sample defect feature set are used to update the model parameters of the standard defect recognition module.

3. The method according to claim 2, characterized in that The specific steps for constructing the pore defect dataset of the printed part are as follows: data is collected during the arc fuse additive process, and an industrial CT scan is performed on the printed part after printing is completed to obtain the location of the pore defect center and the pore defect size information.

4. The method according to claim 2, characterized in that: The signal characteristics are associated with the pore defects as follows: the arc area, the base value and peak value of the current and voltage signals, and the spectral characteristic line information in the high-speed CCD image are extracted, corresponding to the defect information, and the characteristic value weights are set in sections to improve the online monitoring effect and accuracy; High-speed CCD is used to record video, perform frame-by-frame image processing, set the grayscale threshold, calculate the number of pixels in the arc part to reflect the size of the arc area, and determine the position of the arc fuse gun tip at that moment, correspond to the defect position, and correspond to the current and voltage values ​​at that moment.

5. The method according to claim 4, characterized in that Construct the relationship between arc area and current and voltage, the relationship function is as follows: Among them, S is the arc area, k is the relationship coefficient, η is the thermal efficiency, U i is the instantaneous voltage, I i is the instantaneous current, v is the welding speed; At the same time, high-speed CCD, current, voltage, and spectral signals are collected and associated with the pore defects of the printed parts. Based on the different sizes of the pore defects, they are disassembled into multi-sensor information corresponding to no pore defects, small pore defects, and medium and large pore defects.

6. The method according to claim 1, characterized in that The third step is specifically as follows: training a machine learning model based on the obtained pore defect feature data set, and predicting the formation of pores online; and feeding back the predicted pore position and size to the arc fuse welding gun control interface to adjust the wire feeding speed and welding speed.

Images