Method and apparatus for quality detection of laser additive manufacturing

Abstract

The application provides a laser additive manufacturing quality detection method and device, the method comprising: acquiring an electrical signal corresponding to an optical signal in a first time period of a laser additive manufacturing process, the first time period being a time period of processing a target slice layer of a target part in the laser additive manufacturing process; in a case where an electrical signal amplitude corresponding to a first division region in the target slice layer is determined to be in a first threshold range corresponding to the first division region, if, among a plurality of first sub-regions contained in the first division region, a first target sub-region corresponding to a first ratio is not in a preset ratio range, the first target sub-region is determined as an abnormal region. In this way, the accuracy of laser additive manufacturing quality detection can be improved.

Description

Technical Field

[0001] The present application relates to the field of additive manufacturing technology, and in particular to a laser additive manufacturing quality detection method and device. Background Art

[0002] Currently, laser additive manufacturing quality inspection primarily involves monitoring key variables during the additive manufacturing process, thereby enabling real-time inspection of the additive process. As described in Chinese patent application number CN202311764353.4, the additive manufacturing quality inspection method includes: obtaining electrical signals corresponding to optical signals during a first period of time during the laser additive manufacturing process; constructing at least two trajectory amplitude maps based on at least two electrical signals corresponding to at least two optical signals by an industrial control computer; partitioning the at least two trajectory amplitude maps to obtain multiple image block sets; and determining whether the region corresponding to each image block in each image block set in the target slice layer contains defects based on the electrical signal amplitudes of the image blocks in each image block set. This method facilitates the detection of abnormal regions in the slice layer of a part during additive manufacturing. The method primarily involves calculating the ratio between the eigenvalue corresponding to a subregion within the partitioned region of the current slice layer and the eigenvalue corresponding to the partitioned region. For example, the inspection result for each second image block in each image block set is determined based on the electrical signal amplitude of each second image block in the image block set and the electrical signal corresponding to the first image block set to which the second image block belongs. When the calculated ratio is within a reasonable range, the currently selected area is considered normal. When the calculated ratio is within an unreasonable range, the currently selected area is considered abnormal. The above detection method can be called adaptive algorithm detection.

[0003] However, when most of the area in the current divided area is in abnormal printing and only a small part is in normal printing, the signal at the abnormal printing position will pull the eigenvalue corresponding to the current divided area off, so that when calculating the ratio between the eigenvalue of the subsequent sub-area and the eigenvalue of the current divided area, the ratio between the eigenvalue of the sub-area at the normal printing position and the eigenvalue of the current divided area will not be within a reasonable range, while the ratio between the eigenvalue of the sub-area at the abnormal printing position and the eigenvalue of the current divided area will be within a reasonable range. At this time, the "reverse selection" phenomenon will occur when detecting based on the adaptive algorithm. That is, the normal sub-area inside the current divided area is judged as abnormal, and the abnormal sub-area is judged as normal. Therefore, how to avoid the "reverse selection" phenomenon when detecting based on the adaptive algorithm is a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0004] The present application provides a laser additive manufacturing quality inspection method and device, which first uses a baseline value algorithm to make a judgment to achieve comprehensive quality inspection of the first divided area in the target slice layer, and then performs quality inspection of the local area based on an adaptive algorithm if the comprehensive quality inspection passes, thereby avoiding the "reverse selection" phenomenon that occurs when inspecting based on the adaptive algorithm.

[0005] In a first aspect, the present application provides a laser additive manufacturing quality inspection method, the method comprising:

[0006] Acquire an electrical signal corresponding to an optical signal in a first time period during the laser additive manufacturing process, where the first time period is a time period during which a target slice layer of a target part is processed during the laser additive manufacturing process;

[0007] When it is determined that the electrical signal amplitude corresponding to the first divided area in the target slice layer is within the first threshold range corresponding to the first divided area, if, among the multiple first sub-areas included in the first divided area, a first ratio corresponding to the first target sub-area is not within the preset ratio range, the first target sub-area is determined as an abnormal area;

[0008] The first ratio corresponding to the first target sub-region is the ratio between the electrical signal amplitude corresponding to the first target sub-region and the electrical signal amplitude corresponding to the target region of the first shape in the first divided region, and the first shape is the shape corresponding to the first target sub-region.

[0009] It can be seen that in the embodiment of the present application, by obtaining the optical signal in the laser additive manufacturing process and converting it into an electrical signal, a judgment is first made through the reference value algorithm to realize the comprehensive quality detection of the first divided area in the target slice layer, and then the quality detection of the local area is performed based on the adaptive algorithm when the comprehensive quality detection passes. In this way, the phenomenon of "reverse selection" based on the adaptive algorithm detection can be avoided when most of the area in the first divided area in the target slice layer is abnormally printed, thereby improving the accuracy of laser additive manufacturing quality detection.

[0010] In a feasible example, before determining the first target sub-region as an abnormal region, the method further includes:

[0011] determining a plurality of detection points in the first divided area;

[0012] For each detection point among the plurality of detection points, determining a first area of ​​a first shape with a first position of the detection point as a center;

[0013] The detection point is controlled to move in the first divided area, and a second area of ​​the first shape is determined with a second position of the detection point after the movement as the center. The multiple first sub-areas include multiple first areas and multiple second areas.

[0014] In the present application, the detection points are dispersed in the first division area by moving, and the first area and the second area of the first shape are respectively set with the initial position and the position after moving of the detection points as the center. Thus, the adaptive algorithm detection is performed according to the first area and the second area, which can avoid that the defect in the first division area is just between the multiple first sub-areas when the first division area is divided into fixed sub-areas, so that the defect is difficult to be effectively detected, and the accuracy of the laser additive manufacturing quality detection is improved.

[0015] In a feasible example, the first shape includes at least one of the following: a square, a circle, a horizontal rectangle, and a vertical rectangle.

[0016] In the present application, by introducing multiple first shapes, different first shapes can adapt to different types and directions of defects, improving the universality and adaptability of the detection method. The combination of multiple shapes ensures comprehensive coverage of the entire first division area, reduces the risk of missing potential defects, and thus can achieve the technical effects of improving the accuracy and reliability of the laser additive manufacturing quality detection.

[0017] In a feasible example, before controlling the detection point to move in the first division area, the method further includes:

[0018] constructing a trajectory amplitude graph corresponding to the first division area based on the multiple trajectory amplitude lines, the contour of the trajectory amplitude graph being the same as the contour of the first division area, the multiple trajectory amplitude lines corresponding to the machining trajectory when machining the first division area of the target slice layer, the amplitude represented by the trajectory amplitude line being the amplitude of the electrical signal in the process of machining the first division area of the target slice layer;

[0019] controlling the detection point to move in the first division area, including:

[0020] determining a first direction between adjacent pixel points in the trajectory amplitude graph in which the amplitude gradient of the detection point is the largest;

[0021] determining a first distance according to the size of the amplitude gradient of the detection point in the first direction in the trajectory amplitude graph, the larger the amplitude gradient in the first direction, the smaller the first distance;

[0022] controlling the detection point to move in the first division area based on the first direction and the first distance.

[0023] In the present application, by the intelligent moving strategy based on the amplitude gradient, the detection point can focus more accurately on the potential defect area, improving the accuracy and efficiency of the detection, while avoiding missing important information, significantly improving the reliability and efficiency of the quality detection in the laser additive manufacturing process.

[0024] In a feasible example, the control of the detection point to move in the first division region includes:

[0025] The control of the detection point to move in the first division region multiple times until the position of the detection point after the movement is the first position; and / or the control of the detection point to move in the first division region multiple times until the union set of the multiple first sub-regions covers the first division region.

[0026] In the present application, by controlling each detection point to move multiple times until each detection point moves to the initial position, the multiple detections of the same region, the verification of the previous detection results, and the reduction of the possibility of misjudgment can be achieved by returning the detection point to the initial position. And by controlling each detection point to move multiple times to ensure that the union set of the multiple first regions and the multiple second regions covers the first division region, the reliability of the laser additive manufacturing quality detection can be improved.

[0027] In a feasible example, the determination of the first target sub-region as an abnormal region includes: if the first target sub-region is multiple, and there is an intersection between the multiple first target sub-regions, then the region obtained by merging the multiple first target sub-regions is determined as an abnormal region.

[0028] In the present application, if there is also an intersection between the multiple first target sub-regions determined from the multiple first regions and the multiple second regions, then the region obtained by merging the multiple first target sub-regions can be determined as an abnormal region. In this way, not only can the repetition between multiple abnormal regions be avoided, but also a single larger region with defects can be directly determined.

[0029] In a feasible example, the optical signal includes at least one of the following: an optical signal of a laser in a laser additive manufacturing process, and a laser reflection signal, an infrared light signal, and a visible light signal.

[0030] In the present application, by detecting multiple optical signals, the accuracy of the detection can be improved.

[0031] In a second aspect, the present application provides a laser additive manufacturing quality detection device, which comprises:

[0032] The acquisition unit is configured to acquire an electrical signal corresponding to an optical signal in a first time period of a laser additive manufacturing process, the first time period being a time period of processing a target slice layer of a target part in the laser additive manufacturing process.

[0033] The processing unit is configured to, in a case where the amplitude value of the electrical signal corresponding to the first division region in the target slice layer is determined to be within a first threshold range of the first division region, if there is a first target sub-region in the multiple first sub-regions included in the first division region, and a first ratio corresponding to the first target sub-region is not within a preset ratio range, then the first target sub-region is determined as an abnormal region.

[0034] The first ratio corresponding to the first target sub-region is the ratio between the electrical signal amplitude corresponding to the first target sub-region and the electrical signal amplitude corresponding to the target region of the first shape in the first divided region, and the first shape is the shape corresponding to the first target sub-region.

[0035] In a feasible example, the processing unit is further configured to:

[0036] determining a plurality of detection points in the first divided area;

[0037] For each detection point among the plurality of detection points, determining a first area of ​​a first shape with a first position of the detection point as a center;

[0038] The detection point is controlled to move in the first divided area, and a second area of ​​the first shape is determined with a second position of the detection point after the movement as the center. The multiple first sub-areas include multiple first areas and multiple second areas.

[0039] In a feasible example, the first shape includes at least one of the following: a square, a circle, a horizontal rectangle, and a vertical rectangle.

[0040] In a feasible example, the processing unit is further configured to:

[0041] constructing a trajectory amplitude map corresponding to the first divided area based on the plurality of trajectory amplitude lines, wherein the contour of the trajectory amplitude map is the same as the contour of the first divided area, the plurality of trajectory amplitude lines correspond to processing trajectories when processing the first divided area of ​​the target slice layer, and the amplitudes represented by the trajectory amplitude lines are the amplitudes of the electrical signals during the process of processing the first divided area of ​​the target slice layer;

[0042] In terms of controlling the detection point to move in the first divided area, the processing unit is specifically configured to:

[0043] Determine the first direction in which the amplitude gradient between adjacent pixels of the detection point is the largest in the trajectory amplitude map;

[0044] Determine the first distance according to the magnitude of the amplitude gradient of the detection point in the first direction in the trajectory amplitude map, wherein the larger the amplitude gradient in the first direction, the smaller the first distance;

[0045] The detection point is controlled to move in the first divided area based on the first direction and the first distance.

[0046] In a feasible example, in terms of controlling the detection point to move within the first divided area, the processing unit is specifically configured to:

[0047] The control point is controlled to move in the first divided region for multiple times until the position of the control point after the movement is the first position; and / or the control point is controlled to move in the first divided region for multiple times until the union set of the multiple first sub-regions covers the first divided region.

[0048] In one possible example, in terms of determining the first target sub-region as the abnormal region, the processing unit is specifically configured to:

[0049] If the first target sub-region is multiple, and there is an intersection between the multiple first target sub-regions, a region obtained by merging the multiple first target sub-regions is determined as the abnormal region.

[0050] In one possible example, the processing unit is further configured to:

[0051] If the electric signal amplitude corresponding to the first divided region in the target slice layer is not within the first threshold range corresponding to the first divided region, and if there is a second target sub-region in the multiple second sub-regions included in the first divided region, the electric signal amplitude corresponding to the second target sub-region is not within the second threshold range corresponding to the second target sub-region, the second target sub-region is determined as the abnormal region.

[0052] In one possible example, the optical signal includes an output signal of a laser in a laser additive manufacturing process, and a laser reflection signal, an infrared light signal, and a visible light signal.

[0053] In a third aspect, the present application provides an electronic device, which includes a processor, a memory, and a communication interface, the processor, the memory, and the communication interface are connected to each other and complete communication work with each other, the memory stores executable program codes, the communication interface is used for wireless communication, and the processor is used to call the executable program codes stored in the memory and execute part or all of the steps described in any method of the first aspect.

[0054] In a fourth aspect, the present application provides a computer readable storage medium, which stores electronic data, and the electronic data is used to execute the electronic data to realize part or all of the steps described in the first aspect of the present application when executed by a processor.

[0055] In a fifth aspect, the present application provides a computer program product, which includes a computer program operable to cause a computer to execute part or all of the steps described in the first aspect of the present application. The computer program product can be a software installation package. BRIEF DESCRIPTION OF DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0057] Figure 1 A schematic structural diagram of a laser additive manufacturing quality inspection system provided in an embodiment of the present application;

[0058] Figure 2 A schematic flow chart of a laser additive manufacturing quality inspection method provided in an embodiment of the present application;

[0059] Figure 3 A schematic flow chart of another laser additive manufacturing quality inspection method provided in an embodiment of the present application;

[0060] Figure 4 A schematic diagram of a structure of multiple detection points provided in an embodiment of the present application;

[0061] Figure 5 A schematic structural diagram of a first shape provided in an embodiment of the present application;

[0062] Figure 6 A schematic flow chart of another laser additive manufacturing quality inspection method provided in an embodiment of the present application;

[0063] Figure 7 This is a block diagram of the functional units of a laser additive manufacturing quality inspection device provided in an embodiment of the present application;

[0064] Figure 8 A block diagram of the functional units of another laser additive manufacturing quality inspection device provided in an embodiment of the present application;

[0065] Figure 9 This is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0066] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention 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 scope of protection of this application.

[0067] The terms "first," "second," and so on, in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps is not limited to the listed steps but may optionally include steps not listed, or may optionally include other steps inherent to the process, method, product, or apparatus.

[0068] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0069] At present, the quality inspection of laser additive manufacturing is mainly based on adaptive detection algorithm. The principle of adaptive algorithm is as follows:

[0070]

[0071] in, Representative constituency characteristics, Represents regional features, where feature refers to statistical characteristics such as mean and standard deviation. For the currently selected area, if the ratio calculated based on the above formula is within a reasonable range, the currently selected area is considered normal. If the calculated ratio is within an unreasonable range, the currently selected area is considered abnormal. However, if the majority of the area in the current slice layer is abnormally printed, while only a small area is normally printed, the signal at the abnormal printing location will shift the corresponding eigenvalue of the current slice layer. As a result, when calculating the ratio between the eigenvalue of the subsequent selected area and the eigenvalue of the current slice layer, the ratio between the eigenvalue of the selected area at the normal printing location and the eigenvalue of the current slice layer will not be within a reasonable range, while the ratio between the eigenvalue of the selected area at the abnormal printing location and the eigenvalue of the current slice layer will be within a reasonable range. In this case, the adaptive algorithm will experience a "reverse selection" phenomenon, where the normal area within the current slice layer is judged to be abnormal, while the abnormal area is judged to be normal.

[0072] Based on this, an embodiment of the present application provides a laser additive manufacturing quality detection method, which first obtains the electrical signal corresponding to the optical signal of the target slice layer during the laser additive manufacturing process, and then performs a reference value detection. That is, when it is determined that the layer electrical signal amplitude corresponding to the target slice layer is not within the first threshold range, the abnormal area can be directly determined based on the electrical signal amplitude of the area in the target slice layer. When it is determined that the layer electrical signal amplitude corresponding to the optical signal is within the first threshold range, the abnormal area in the target slice layer is determined by an adaptive algorithm. This can avoid the "reverse selection" phenomenon and improve the accuracy of laser additive manufacturing quality detection.

[0073] Below through Figure 1 The system architecture of this application is described as follows:

[0074] See also Figure 1 , Figure 1 This is a schematic diagram of a laser additive manufacturing quality inspection system provided in an embodiment of the present application. Figure 1 As shown, the system includes a laser 1, a field lens 2, a scanning galvanometer 3, a beam splitter 4, a sensor module 5, a signal processor 6, and an industrial control computer 7, wherein the sensor module 5 is coaxially installed in the scanning galvanometer system of the laser additive manufacturing equipment, the sensor module 5 is connected to the signal processor 6 through a signal line, the signal processor 6 is connected to the industrial control computer 7 through a signal line, and the signal processor 6 is connected to the control system 8 of the laser additive manufacturing equipment through a signal line.

[0075] In this embodiment, the laser light generated by the laser 1 is first transmitted to the sensor module of the laser light signal of the sensor module 5 through the beam splitter 4. At the same time, the laser light generated by the laser 1 is also incident into the molding cavity 9 by the scanning galvanometer 3 and the field lens 2. The light radiation generated during the laser additive manufacturing process is transmitted to the sensor module 5 through the field lens 2, the scanning galvanometer 3 and the beam splitter 4. The sensor module 5 can realize photoelectric conversion and can convert light radiation signals of multiple wavelengths into electrical signals, including visible light (400-700nm), laser reflection (1060-1070nm), laser light (1060-1070nm). ) and infrared light (>1200nm); the electrical signal is transmitted to the signal processor 6 via the signal line, and the signal processor 6 performs relevant processing on the electrical signal, including signal amplification and filtering. After the signal processing, it is transmitted to the industrial control computer 7 via the signal line, and the industrial control computer 7 extracts and processes the corresponding characteristic values ​​of the signal, and compares it with the preset upper and lower thresholds and upper and lower ratio thresholds, so as to judge the processing quality of each slice layer in the additive manufacturing process. The industrial control computer 7 transmits the corresponding processing information to the control system 8 of the laser additive manufacturing equipment through the signal line and the signal processor 6, so as to adjust and optimize the process parameters of the additive manufacturing.

[0076] Optionally, the sensor module 5 comprises at least one of a laser light emission signal sensor, a laser light reflection signal sensor, a visible light signal sensor, and an infrared light signal sensor.

[0077] The laser wavelength generated by the laser 1 is 1070-1070nm, and the sensor module 5 can realize photoelectric conversion, specifically through a silicon photoelectric sensor; the sensor module 5 can perform photoelectric conversion on light of multiple wavelengths, including visible light (400-700nm), laser reflection (915nm, 1070nm, etc.), and infrared light (>1200nm); the signal processor 6 processes the electrical signal, including signal amplification and filtering, so that the signal amplitude is larger and the signal noise is reduced; the industrial computer 7 can further filter the signal, and then determine whether the slice layer of the part has an abnormal area according to the collected electrical signal, and if there is an abnormal area, the position information of the abnormal area is obtained; the position information or other information of the abnormal area is transmitted to the control system 8 of the laser additive manufacturing equipment through the signal line and the signal processor 6, so that the control system controls the laser 1 or the laser processing head or other components in the laser welding system to reprocess the abnormal area.

[0078] In the application of laser processing, the infrared radiation signal corresponds to an infrared radiation signal with a wavelength in the range of 1250nm to 1700nm. The visible light radiation signal corresponds to a visible light radiation signal in the range of 400nm to 700nm. The laser processing reflection signal corresponds to the processing laser reflection signal during actual laser processing, such as processing laser wavelengths of 915nm, 1064nm, 1070nm, etc. The wavelength of the processing laser is related to the wavelength of the actual laser used. In some use environments, the suitable range of the infrared radiation signal can be extended outside the range of 1250nm to 1700nm. In some use environments, the visible light radiation signal can be extended outside the range of 400nm to 700nm.

[0079] In this application, the industrial computer 7 obtains the electrical signal corresponding to the optical signal of the target slice layer of the target part during the laser additive manufacturing process from the signal processor 6, and then performs reference value detection. That is, in the case where the electrical signal amplitude corresponding to the first divided region in the target slice layer is within the first threshold range, the adaptive algorithm is used to determine the abnormal sub-region in the first divided region. In this way, the phenomenon of "reverse selection" can be avoided, and the accuracy of laser additive manufacturing quality detection is improved.

[0080] Based on this, the embodiment of the present application provides a laser additive manufacturing quality detection method, which will be described in detail below with reference to the accompanying drawings.

[0081] Embodiment one, the framework of the laser additive manufacturing quality detection method in the embodiment of the present application will be described below.

[0082] See also Figure 2 , Figure 2 This is a flow chart of a laser additive manufacturing quality inspection method provided in an embodiment of the present application, which is applied to the above-mentioned industrial control computer, such as Figure 2 As shown, the method includes the following steps:

[0083] Step S201 : obtaining an electrical signal corresponding to an optical signal in a first time period during a laser additive manufacturing process.

[0084] In the laser additive manufacturing process, a slice layer refers to a series of thin horizontal layers formed by dividing a 3D digital model along the vertical direction (usually the Z-axis). Each layer is a 2D contour representing the cross-sectional shape of the part at that height. During processing, the laser melts or sinters the material (such as metal powder) layer by layer according to the contour information of each layer, ultimately accumulating it into a 3D solid. As you can see, the electrical signal is obtained by photoelectric conversion of the optical signal by the aforementioned sensor module, reflecting the intensity changes of the optical signal.

[0085] Optionally, the optical signal includes at least one of the following: an output light signal of a laser during laser additive manufacturing, as well as a laser reflection signal, an infrared light signal, and a visible light signal.

[0086] Based on this, the electrical signal corresponding to the optical signal may include one or more of a first electrical signal corresponding to the outgoing optical signal, a second electrical signal corresponding to the laser reflection signal, a third electrical signal corresponding to the visible light signal, and a fourth electrical signal corresponding to the infrared light signal.

[0087] During the laser additive manufacturing process, the keyhole metal vapor generated radiates visible light, the molten pool radiates infrared light, and the laser reflected light not absorbed by the powder and the laser output light signal are collected by the sensor module and photoelectrically converted into electrical signals, including: obtaining a corresponding first voltage value through the laser output light signal sensor, obtaining a corresponding second voltage value through the visible light signal sensor, obtaining a corresponding third voltage value through the laser reflection signal sensor, and obtaining a corresponding fourth voltage value through the infrared light signal sensor, and performing gain adjustment on the first voltage value, the second voltage value, the third voltage value, and the fourth voltage value, respectively, to obtain an adjusted output electrical signal. During the process of machining the target slicing layer of the target part, the first electrical signal corresponding to the output light signal, the second electrical signal corresponding to the laser reflection signal, the third electrical signal corresponding to the visible light signal, and the fourth electrical signal corresponding to the infrared light signal can be obtained in the above manner.

[0088] In step S202, in a case where the electric signal amplitude corresponding to the first division region in the target slice layer is determined to be in the first threshold range corresponding to the first division region, if, among the plurality of first sub-regions contained in the first division region, there is a first target sub-region corresponding to a first ratio that is not in a preset ratio range, the first target sub-region is determined as an abnormal region.

[0089] The first ratio corresponding to the first target sub-region is a ratio between the electric signal amplitude corresponding to the first target sub-region and the electric signal amplitude corresponding to a target region of a first shape in the first division region, and is used to evaluate the relative signal strength of the region. The first shape is the shape corresponding to the first target sub-region. The target region can refer to the largest region of the first shape in the first division region. The preset ratio range is a reasonable range that is preset and can be determined according to an empirical value.

[0090] It can be understood that the electric signal includes an electric signal amplitude, a frequency, a phase, and the like. The electric signal amplitude corresponding to a single region described in the present application can be determined according to the electric signal in the single region. The electric signal amplitude corresponding to a single region also includes an electric signal amplitude corresponding to an emitted light signal, an electric signal amplitude corresponding to a laser reflection signal, an electric signal amplitude corresponding to a visible light signal, and an electric signal amplitude corresponding to an infrared light signal.

[0091] Meanwhile, the electric signal amplitude of the single region can be an average electric signal amplitude in the single region or a weighted sum of the electric signal amplitudes of all points in the single region. It should be understood that, in the process of one layer of additive manufacturing, the photosensor collects the electric signal amplitude corresponding to the light signal of the additive manufacturing point at a certain frequency, and for each layer, a plurality of electric signal amplitudes corresponding to the additive manufacturing points are collected.

[0092] In step S203, in a case where the electric signal amplitude corresponding to the first division region in the target slice layer is determined to be not in the first threshold range corresponding to the first division region, if, among the plurality of second sub-regions contained in the first division region, there is a second target sub-region corresponding to an electric signal amplitude that is not in a second threshold range corresponding to the second target sub-region, the second target sub-region is determined as an abnormal region.

[0093] Optionally, the upper limit and the lower limit of the first threshold range are respectively the maximum value and the minimum value of the electric signal amplitude corresponding to the first division region in the process of forming a defect-free slice layer under the same processing parameters, and the upper limit and the lower limit of the second threshold range are respectively the maximum value and the minimum value of the electric signal amplitude corresponding to the second sub-region in the process of forming a defect-free slice layer under the same processing parameters.

[0094] Optionally, the first threshold range and the second threshold range can be the same.

[0095] In addition, the first threshold range can also be divided into a first threshold range corresponding to the light emission signal, a first threshold range corresponding to the laser reflection signal, a first threshold range corresponding to the visible light signal, and a first threshold range corresponding to the infrared light signal. The second threshold range is the same.

[0096] In this step, it is determined that the electrical signal amplitude corresponding to the first divided region is not in the first threshold range, including at least one of the following: the electrical signal amplitude corresponding to the light emission signal in the first divided region is not in the first threshold range corresponding to the light emission signal, the electrical signal amplitude corresponding to the laser reflection signal in the first divided region is not in the first threshold range corresponding to the laser reflection signal, the electrical signal amplitude corresponding to the visible light signal in the first divided region is not in the first threshold range corresponding to the visible light signal, and the electrical signal amplitude corresponding to the infrared light signal in the first divided region is not in the first threshold range corresponding to the infrared light signal.

[0097] Similarly, in this step, the electrical signal amplitude corresponding to the second sub-region is not in the second threshold range corresponding to the second sub-region, including at least one of the following: the electrical signal amplitude of the light emission signal corresponding to the second sub-region is not in the second threshold range corresponding to the light emission signal corresponding to the second sub-region, the electrical signal amplitude of the laser reflection signal corresponding to the second sub-region is not in the second threshold range corresponding to the laser reflection signal corresponding to the second sub-region, the electrical signal amplitude of the visible light signal corresponding to the second sub-region is not in the second threshold range corresponding to the visible light signal corresponding to the second sub-region, and the electrical signal amplitude of the infrared light signal corresponding to the second sub-region is not in the second threshold range corresponding to the infrared light signal corresponding to the second sub-region.

[0098] It can be seen that the laser additive manufacturing quality detection method provided in this embodiment, by acquiring the light signal in the laser additive manufacturing process and converting it into an electrical signal, first judges by the reference value algorithm, realizes comprehensive quality detection of the target slice layer, and in the case of passing the comprehensive quality detection, again based on the adaptive algorithm, the quality detection of the local region, solves the limitation of the adaptive algorithm, avoids the reverse selection phenomenon, and improves the accuracy of the laser additive manufacturing quality detection.

[0099] In the second embodiment, the laser additive manufacturing quality detection method will be described in detail in the following.

[0100] Please refer to Figure 3 , Figure 3 The flowchart of another laser additive manufacturing quality detection method provided in this embodiment is shown in the figure. This method is applied to the industrial computer described above. As shown in Figure 3 , the method comprises the following steps:

[0101] Step S301, acquiring the electrical signal corresponding to the light signal in the first period of the laser additive manufacturing process.

[0102] Step S302, in the case where the electric signal amplitude corresponding to the first division region in the target slice layer is determined to be in the first threshold range corresponding to the first division region, a plurality of detection points in the first division region are determined.

[0103] The detection points can be self-defined small units, which can be generated by computer program simulation or constructed by actual sensors, probes and other devices. For example, the detection points can include virtual computing units or physical probes. First, the plurality of detection points are dispersed in the target slice layer. For example, the plurality of detection points can be uniformly distributed on the target slice layer to ensure that the initial spacing between the detection points is reasonable to cover the entire slice layer. The number of the plurality of detection points can be determined according to the size of the target slice layer and the size of the third region and the fourth region defined subsequently. For example, the number of the plurality of detection points can be determined according to the ratio between the size of the third region and the size of the target slice layer, and / or the ratio between the size of the fourth region and the size of the target slice layer.

[0104] Step S303, for each detection point in the plurality of detection points, a first region of a first shape is determined with the first position of the detection point as the center.

[0105] The plurality of detection points in the first division region are first determined, and then a first region of a first shape and size can be defined for each detection point with the detection point as the center, and the electric signal characteristic value in each first region is recorded, so that the local region where the problem may exist can be preliminarily screened out by defining the first region, thereby providing a technical effect of providing a basis for further refined detection.

[0106] Step S304, the position of the detection point is moved in the first division region, and a second region of the first shape is determined with the second position of the detection point after the position movement as the center.

[0107] The plurality of first sub-regions include the plurality of first regions and the plurality of second regions. The position movement of the detection point can be according to a certain rule in the first division region, or can be random movement. After each detection point moves to the corresponding position, a second region of the first shape is determined with each detection point as the center, and the electric signal characteristic value in each second region is recorded.

[0108] For example, please refer to Figure 4 , Figure 4 A structure diagram of a plurality of detection points provided by an embodiment of the present application is shown in Figure 4 The plurality of detection points 402 are dispersed on the first division region 401, and the plurality of detection points 402 move in the first division region 401 according to respective corresponding directions.

[0109] In the present application, by determining a plurality of detection points in the first division region and also moving, a first region and a second region of a first shape are respectively set with the initial position and the position after moving of the detection points as the center, so that the adaptive algorithm detection is performed according to the first region and the second region, which can avoid that when fixed sub-region division is performed on the inside of the first division region, the defect in the first division region is just between a plurality of first sub-regions, so that the defect is difficult to be effectively detected, thereby improving the accuracy of laser additive manufacturing quality detection.

[0110] Optionally, the first shape includes at least one of a square, a circle, a horizontal rectangle, and a vertical rectangle.

[0111] It can be understood that the first shape can also be other polygons in addition to the aforementioned square, circle, horizontal rectangle, and vertical rectangle, such as a rhombus. The first shape can be a specific pattern used to define the geometric contour of the detection region, and different types of geometric shapes can be set to adapt to different detection requirements.

[0112] The square is a geometric shape with four equal sides and four right angles, which is suitable for relatively uniform defect detection. A square region with a fixed side length can be obtained by centering on the detection point, and the square region can cover a relatively regular detection region, which is suitable for preliminary screening or large-scale scanning.

[0113] The circle is a geometric shape in which the distance from all points to the center is equal, which is suitable for scenarios requiring symmetry detection, especially when the defect can be circular or approximately circular. A circular region with a fixed radius can be obtained by centering on the detection point, and the circular region can more naturally capture radial changes.

[0114] The horizontal rectangle is a rectangle with a length-width ratio greater than 1 and a long side along the horizontal direction, which is suitable for detecting defects extending along the horizontal direction, such as interlayer cracks or horizontally expanding pores. A rectangular region with a long side along the horizontal direction can be obtained by centering on the detection point, and the rectangular region can more effectively capture signal changes along the horizontal direction.

[0115] The vertical rectangle is a rectangle with a length-width ratio greater than 1 and a long side along the vertical direction, which is suitable for detecting defects extending along the vertical direction, such as columnar pores or vertical cracks. A rectangular region with a long side along the vertical direction can be obtained by centering on the detection point, and the rectangular region can more effectively capture signal changes along the vertical direction.

[0116] For example, refer to Figure 5 , Figure 5 A structural diagram of a first shape provided by an embodiment of the present application is shown in FIG. 1.Figure 5 The first shape includes a square, a circle, a horizontal rectangle, and a vertical rectangle, respectively.

[0117] In addition, the first region or the second region set by the application at each detection point before and after each movement can be set according to a single first shape in the plurality of first shapes, or can be set according to the plurality of first shapes. For example, at a single position, a circular region is first set, and after calculating the amplitude of the electrical signal in the circular region, a square region is set, and after calculating the amplitude of the electrical signal in the square region, a horizontal rectangular region is set, and so on. In this way, the region set by the detection point at a single position can cover a larger range.

[0118] It can be seen that by introducing a plurality of first shapes, different first shapes can adapt to different types and directions of defects, improving the universality and adaptability of the detection method, and the combination of a plurality of shapes ensures comprehensive coverage of the entire first divided region, reducing the risk of missing potential defects, thereby achieving the technical effects of improving the accuracy and reliability of laser additive manufacturing quality detection.

[0119] Optionally, before controlling the detection point to move in the first divided region, the method further comprises: constructing a track amplitude graph corresponding to the first divided region based on a plurality of track amplitude lines, the contour of the track amplitude graph being the same as the contour of the first divided region, the plurality of track amplitude lines corresponding to the machining tracks when machining the first divided region of the target slice layer, the amplitude represented by the track amplitude line being the amplitude of the electrical signal during machining the first divided region of the target slice layer;

[0120] Controlling the detection point to move in the first divided region comprises: determining a first direction between adjacent pixel points in the track amplitude graph in which the detection point has the maximum amplitude gradient; determining a first distance according to the size of the amplitude gradient of the first direction of the detection point in the track amplitude graph, the larger the amplitude gradient of the first direction, the smaller the first distance; and controlling the detection point to move in the first divided region based on the first direction and the first distance.

[0121] The track amplitude line can be a line representing the change of the electrical signal amplitude on each machining track during the machining process. It can be obtained by recording the electrical signal amplitude on each machining track during the machining process. For example, the track amplitude line can include the change curve of the electrical signal such as laser power and molten pool temperature.

[0122] The trajectory amplitude map can be a two-dimensional image obtained by mapping a plurality of trajectory amplitude lines into an image, the contour of which is the same as that of the first divided region, reflecting the electrical signal distribution of the entire first divided region. It can be obtained by mapping these electrical signal amplitudes according to the corresponding processing trajectory positions onto a two-dimensional plane to form a plurality of trajectory amplitude lines, and integrating all the trajectory amplitude lines into a complete trajectory amplitude map, ensuring that its contour is consistent with the contour of the target slice layer. Illustratively, the trajectory amplitude map can be used to intuitively reflect the electrical signal distribution of the entire first divided region. It can be understood that the trajectory amplitude map corresponding to the target slice layer can be directly constructed.

[0123] In addition, the amplitude gradient refers to the rate of change of the electrical signal amplitude between adjacent pixel points. It can be obtained by calculating the amplitude difference between adjacent pixel points. Illustratively, the amplitude gradient can be used to indicate the degree of signal change in the region, and the region where defects may exist often has a larger amplitude gradient.

[0124] The first direction corresponding to each detection point can be the direction with the largest amplitude gradient in the preset region corresponding to the current position of the detection point. Determining the first direction based on the direction with the largest amplitude gradient can ensure that the detection point focuses on the potential defect region.

[0125] The first distance corresponding to each detection point can be determined according to the size of the amplitude gradient corresponding to the first direction. The larger the amplitude gradient, the smaller the first distance; the smaller the amplitude gradient, the larger the first distance, so as to ensure that the detection point can search for potential defects in detail or improve the search efficiency.

[0126] The technical operation of controlling the position movement of the detection point in the first divided region can be realized through the following sub-steps:

[0127] 1. Initialization: Set the initial position and state of the detection point. 2. Iterative movement: According to the calculated first direction and first distance, the position of the detection point is updated one by one. 3. Stop condition: When the detection point reaches the predetermined stop condition (such as the number of movements reaches the upper limit), stop moving. 4. Redetermine the region: After each stop of the detection point, a second region of the first shape is redefined with the final position of each detection point as the center.

[0128] In this application, through the intelligent movement strategy based on the amplitude gradient, the detection point can focus more accurately on the potential defect region, improving the accuracy and efficiency of detection, while avoiding missing important information, significantly improving the reliability and efficiency of quality detection in the laser additive manufacturing process.

[0129] Step S305, if the first ratio corresponding to the first target sub-region does not fall within the preset ratio range, the first target sub-region is determined as an abnormal region.

[0130] Optionally, the first target sub-region is determined as an abnormal region, including: if the first target sub-region is multiple and there is an intersection between the multiple first target sub-regions, a region obtained by merging the multiple first target sub-regions is determined as an abnormal region.

[0131] Wherein, since the aforementioned multiple detection points are moving in the first division region, there may be an intersection between the multiple first regions and the multiple second regions determined before and after the movement. If there is also an intersection between the multiple first target sub-regions determined from the multiple first regions and the multiple second regions at this time, a region obtained by merging the multiple first target sub-regions can be determined as an abnormal region. In this way, not only can the repetition between multiple abnormal regions be avoided, but also a single larger region with defects can be directly determined.

[0132] Step S306, if the electrical signal amplitude corresponding to the first division region in the target slice layer does not fall within the first threshold range corresponding to the first division region, if the electrical signal amplitude corresponding to the second target sub-region does not fall within the second threshold range corresponding to the second target sub-region, the second target sub-region is determined as an abnormal region.

[0133] Embodiment three, the movement of each detection point can be multiple times, and the laser additive manufacturing quality detection method is described below based on this.

[0134] Please refer to Figure 6 , Figure 6 Another flowchart of a laser additive manufacturing quality detection method provided by the embodiment of the application is provided, and the method is applied to the industrial computer. As shown in Figure 6 , the method includes the following steps:

[0135] Step S601, acquiring an electrical signal corresponding to an optical signal in a first time period of a laser additive manufacturing process.

[0136] Step S602, determining multiple detection points in the first division region in the target slice layer if the electrical signal amplitude corresponding to the first division region falls within the first threshold range corresponding to the first division region.

[0137] Step S603, for each detection point in the multiple detection points, a first region of a first shape is determined with the first position of the detection point as the center.

[0138] Step S604a, control the detection points to move in the first divided region for multiple times until the position of the detection points after moving is the first position, and determine a second region of the first shape with the second position of the detection points after moving as the center after the detection points stop moving each time.

[0139] In which, firstly, record the initial position (first position) of each detection point, determine the moving direction and moving distance of each detection point according to the amplitude gradient in the trajectory amplitude graph, and move for the first time. After each movement, update the position of the detection point, and continue to calculate the amplitude gradient according to the new position to determine the moving direction and moving distance of the next step. After each movement, check whether the detection point has returned to its initial position. If not, continue to move; if yes, stop moving. This process ensures that the detection point can return to the original position for repeated detection or verification after completing the detection within a certain range.

[0140] As can be seen, by controlling each detection point to move for multiple times until each detection point moves to the initial position, the detection point is allowed to return to the initial position to detect the same region multiple times, verify the previous detection results, and reduce the possibility of misjudgment.

[0141] Step S604b, control the detection points to move in the first divided region for multiple times until the union of the multiple first sub-regions covers the first divided region, and determine a second region of the first shape with the second position of the detection points after moving as the center after the detection points stop moving each time.

[0142] In which, record the first region corresponding to the current position before each detection point moves, and then control each detection point to move for multiple times. At this time, the moving direction and moving distance of each detection point can also be determined according to the amplitude gradient in the trajectory amplitude graph, and the second region corresponding to the second position of each detection point after single position movement can be recorded after single movement. At the same time, after each movement, it is also necessary to check whether the union of the multiple first regions and the multiple second regions of all detection points has completely covered the first divided region. If not, continue to move; if yes, stop moving to ensure that there is no missing defect region. In addition, if each detection point moves randomly, the moving direction and moving distance of each detection point can also be dynamically adjusted according to the situation of the uncovered region during the movement of each detection point to ensure efficient coverage, avoid unnecessary repeated movement, and improve detection efficiency.

[0143] As can be seen, by controlling the detection points to move in the first divided region for multiple times, ensuring that the union of the multiple first regions and the multiple second regions covers the first divided region, the reliability of the laser additive manufacturing quality detection can be improved.

[0144] For example, the update formula of the detection point coordinates is as follows:

[0145]

[0146] In the above formula, ( , ) represents the i-th moving coordinate of the m-th detection point among multiple detection points, Indicates the i+1th moving coordinate of the mth detection point among multiple detection points, Represents the distance each detection point moves, Represents the maximum magnitude and direction of the gradient in the x direction of the pixel where the detection point is located. Represents the maximum magnitude and direction of the gradient in the y direction of the pixel where the detection point is located.

[0147] It can be understood that either step S604a or step S604b can be performed.

[0148] Step S605: If, among the multiple first sub-regions included in the first divided region, there is a first target sub-region whose first ratio is not within the preset ratio range, the first target sub-region is determined as an abnormal region.

[0149] In step S606, when it is determined that the electrical signal amplitude corresponding to the first divided area in the target slice layer is not within the first threshold range corresponding to the first divided area, if, among the multiple second sub-areas contained in the first divided area, there is a second target sub-area whose electrical signal amplitude corresponding to the second target sub-area is not within the second threshold range corresponding to the second target sub-area, then the second target sub-area is determined as an abnormal area.

[0150] It can be seen that in the embodiment of the present application, by obtaining the optical signal in the laser additive manufacturing process and converting it into an electrical signal, the benchmark value algorithm is first used to make a judgment to achieve a comprehensive quality inspection of the target slice layer, and then the quality inspection of the local area is performed based on the adaptive algorithm when the comprehensive quality inspection passes. In this way, the situation where most of the area in the target slice layer is abnormally printed can be avoided, and the "reverse selection" phenomenon based on the adaptive algorithm detection can be avoided, thereby improving the accuracy of laser additive manufacturing quality inspection.

[0151] In accordance with the above-mentioned embodiment, please refer to Figure 7 , Figure 7 This is a functional unit block diagram of a laser additive manufacturing quality inspection device provided in an embodiment of the present application. The laser additive manufacturing quality inspection device is the above-mentioned industrial control computer or a part of the industrial control computer. Figure 7 As shown, the laser additive manufacturing quality detection device 70 includes:

[0152] An acquisition unit 701 is configured to acquire an electrical signal corresponding to an optical signal during a first period of time in a laser additive manufacturing process, where the first period of time is a period of time during which a target slice layer of a target part is processed during the laser additive manufacturing process;

[0153] The processing unit 702 is configured to, when determining that the electrical signal amplitude corresponding to the first divided region in the target slice layer is within the first threshold range corresponding to the first divided region, determine the first target subregion as an abnormal region if, among the multiple first subregions included in the first divided region, a first ratio corresponding to the first target subregion is not within the preset ratio range;

[0154] The first ratio corresponding to the first target sub-region is the ratio between the electrical signal amplitude corresponding to the first target sub-region and the electrical signal amplitude corresponding to the target region of the first shape in the first divided region, and the first shape is the shape corresponding to the first target sub-region.

[0155] In a feasible embodiment, the processing unit 702 is further configured to:

[0156] determining a plurality of detection points in the first divided area;

[0157] For each detection point among the plurality of detection points, determining a first area of ​​a first shape with a first position of the detection point as a center;

[0158] The detection point is controlled to move in the first divided area, and a second area of ​​the first shape is determined with a second position of the detection point after the movement as the center. The multiple first sub-areas include multiple first areas and multiple second areas.

[0159] In a feasible embodiment, the first shape includes at least one of the following: a square, a circle, a horizontal rectangle, and a vertical rectangle.

[0160] In a feasible embodiment, the processing unit 702 is further configured to:

[0161] constructing a trajectory amplitude map corresponding to the first divided area based on the plurality of trajectory amplitude lines, wherein the contour of the trajectory amplitude map is the same as the contour of the first divided area, the plurality of trajectory amplitude lines correspond to processing trajectories when processing the first divided area of ​​the target slice layer, and the amplitudes represented by the trajectory amplitude lines are the amplitudes of the electrical signals during the process of processing the first divided area of ​​the target slice layer;

[0162] In terms of controlling the detection point to move within the first divided area, the processing unit 702 is specifically configured to:

[0163] Determine the first direction in which the amplitude gradient between adjacent pixels of the detection point is the largest in the trajectory amplitude map;

[0164] Determine the first distance according to the magnitude of the amplitude gradient of the detection point in the first direction in the trajectory amplitude map, wherein the larger the amplitude gradient in the first direction, the smaller the first distance;

[0165] The detection point is controlled to move in the first divided area based on the first direction and the first distance.

[0166] In a feasible embodiment, in terms of controlling the detection point to move within the first divided area, the processing unit 702 is specifically configured to:

[0167] The detection point is controlled to move multiple times in the first divided area until the position of the detection point after movement is the first position; and / or the detection point is controlled to move multiple times in the first divided area until the union of multiple first sub-areas covers the first divided area.

[0168] In a feasible embodiment, in determining the first target sub-region as an abnormal region, the processing unit 702 is specifically configured to:

[0169] If there are multiple first target sub-regions and there is an intersection between the multiple first target sub-regions, the region where the multiple first target sub-regions are merged is determined as the abnormal region.

[0170] In a feasible embodiment, the processing unit 702 is further configured to:

[0171] When it is determined that the electrical signal amplitude corresponding to the first divided area within the target slice layer is not within the first threshold range corresponding to the first divided area, if, among the multiple second sub-areas contained in the first divided area, there is a second target sub-area whose electrical signal amplitude corresponding to the second target sub-area is not within the second threshold range corresponding to the second target sub-area, then the second target sub-area is determined to be an abnormal area.

[0172] In a feasible embodiment, the optical signal includes an output light signal of a laser during the laser additive manufacturing process, as well as a laser reflection signal, an infrared light signal, and a visible light signal.

[0173] It can be understood that since the method embodiment and the device embodiment are different presentation forms of the same technical concept, the content of the method embodiment part in this application should be synchronously adapted to the device embodiment part and will not be repeated here.

[0174] In the case of integrated units, such as Figure 8 As shown, Figure 8 This is a block diagram of the functional units of another laser additive manufacturing quality inspection device provided in an embodiment of the present application. Figure 8In the embodiment, the laser additive manufacturing quality inspection device 70 includes: a processing module 812 and a communication module 811. The processing module 812 is used to control and manage the actions of the laser additive manufacturing quality inspection device 70, for example, the steps of the acquisition unit 701 and the processing unit 702, and / or other processes for executing the technology described herein. The communication module 811 is used to support the interaction between the laser additive manufacturing quality inspection device 70 and other devices. Figure 8 As shown, the laser additive manufacturing quality inspection device 70 may further include a storage module 813 , and the storage module 813 is used to store program codes and data of the laser additive manufacturing quality inspection device 70 .

[0175] The processing module 812 may be a processor or controller, such as a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an ASIC, an FPGA, or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication module 811 may be a transceiver, an RF circuit, or a communication interface, and the like. The storage module 813 may be a memory.

[0176] Among them, all relevant contents of each scenario involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here. The above laser additive manufacturing quality inspection device 70 can perform the above Figure 2 The laser additive manufacturing quality inspection method shown.

[0177] The above embodiments can be implemented in whole or in part via software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions according to the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. A computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

[0178] Figure 9 This is a structural block diagram of an electronic device provided in an embodiment of the present application. Figure 9 As shown, the electronic device 900 may include one or more of the following components: a processor 901, a memory 902 and a communication interface 903. The processor 901, the memory 902 and the communication interface 903 are interconnected and perform communication with each other. The memory 902 may store one or more computer programs, and the one or more computer programs may be configured to implement the methods described in the above embodiments when executed by one or more processors 901.

[0179] The processor 901 may include one or more processing cores. The processor 901 uses various interfaces and lines to connect the various parts of the entire electronic device 900, and performs various functions and processes data of the electronic device 900 by running or executing instructions, programs, code sets or instruction sets stored in the memory 902, and calling data stored in the memory 902. Optionally, the processor 901 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 901 can integrate one or more combinations of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. It is understandable that the above-mentioned modem may not be integrated into the processor 901, but may be implemented separately through a communication chip.

[0180] The memory 902 may include a random access memory (RAM) or a read-only memory (ROM). The memory 902 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 902 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc. The data storage area may also store data created by the electronic device 900 during use.

[0181] It is understandable that the electronic device 900 may include more or fewer structural elements than those in the above structural block diagram, for example, a power module, physical buttons, a WiFi (Wireless Fidelity) module, a speaker, a Bluetooth module, a sensor, etc., which are not limited here.

[0182] The electronic device 900 may be an industrial computer or a part of an industrial computer.

[0183] An embodiment of the present application provides a computer-readable storage medium, wherein program data is stored in the computer-readable storage medium. When the program data is executed by a processor, the program data is used to execute part or all of the steps of any one of the laser additive manufacturing quality inspection methods described in the above method embodiments.

[0184] The present application also provides a computer program product, including a computer program, which is operable to cause a computer to execute some or all of the steps of any of the laser additive manufacturing quality inspection methods described in the above method embodiments. The computer program product may be a software installation package.

[0185] It should be noted that for any of the aforementioned methods for detecting quality of laser additive manufacturing, for the sake of simplicity, they are all described as a series of action combinations. However, those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions involved are not necessarily required by this application.

[0186] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other variations of the disclosed embodiments by reviewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality of components or steps. The fact that certain measures are recited in different dependent claims does not mean that these measures cannot be combined to produce good results.

[0187] Those skilled in the art will appreciate that all or part of the steps in the various methods of any of the above-mentioned laser additive manufacturing quality inspection method embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0188] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of a laser additive manufacturing quality detection method and device of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, based on the idea of ​​a laser additive manufacturing quality detection method and device of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0189] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0190] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0191] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0192] It can be understood that the products, such as the terminal of the above flowchart and the computer program product, which are controlled or configured to execute the processing method of the flowchart described in the method embodiment of the laser additive manufacturing quality detection method, all belong to the scope of the related products described in the present application.

[0193] Obviously, those skilled in the art can make various modifications and variations to the laser additive manufacturing quality detection method and device provided in the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and variations.

Claims

1. A laser additive manufacturing quality inspection method, characterized in that: The method comprises: Acquire an electrical signal corresponding to an optical signal in a first time period during a laser additive manufacturing process, where the first time period is a time period during which a target slice layer of a target part is processed during the laser additive manufacturing process; When it is determined that the electrical signal amplitude corresponding to the first divided area in the target slice layer is within the first threshold range corresponding to the first divided area, if, among the multiple first sub-areas included in the first divided area, a first ratio corresponding to a first target sub-area is not within the preset ratio range, the first target sub-area is determined as an abnormal area; Among them, the first ratio corresponding to the first target sub-area is the ratio between the electrical signal amplitude corresponding to the first target sub-area and the electrical signal amplitude corresponding to the target area of ​​the first shape in the first divided area, the first shape is the shape corresponding to the first target sub-area, and the target area of ​​the first shape is the first divided area corresponding to the first target sub-area; the upper limit and lower limit of the first threshold range are respectively the maximum value and minimum value of the electrical signal amplitude corresponding to the first divided area in the defect-free slice layer in the process of processing the defect-free slice layer under the same processing parameters as those of processing the target part.

2. The method according to claim 1, characterized in that Before determining the first target sub-region as an abnormal region, the method further includes: determining a plurality of detection points in the first divided area; For each detection point among the plurality of detection points, determining a first area of ​​the first shape with a first position of the detection point as a center; The detection point is controlled to move in the first divided area, and a second area of ​​the first shape is determined with a second position of the detection point after the movement as the center, and the multiple first sub-areas include multiple first areas and multiple second areas.

3. The method according to claim 2, characterized in that The first shape includes at least one of the following: a square, a circle, a horizontal rectangle, and a vertical rectangle.

4. The method according to claim 2, characterized in that Before controlling the detection point to move in the first divided area, the method further includes: constructing a trajectory amplitude map corresponding to the first divided area based on the plurality of trajectory amplitude lines, wherein the contour of the trajectory amplitude map is the same as the contour of the first divided area, the plurality of trajectory amplitude lines correspond to processing trajectories when processing the first divided area of ​​the target slice layer, and the amplitudes represented by the trajectory amplitude lines are the amplitudes of the electrical signals during the process of processing the first divided area of ​​the target slice layer; The controlling the detection point to move in the first divided area includes: Determine a first direction in which the amplitude gradient between adjacent pixels of the detection point is the largest in the trajectory amplitude map; determining a first distance according to a magnitude of an amplitude gradient of the detection point in the first direction in the trajectory amplitude map, wherein a larger amplitude gradient in the first direction indicates a smaller first distance; The detection point is controlled to move in the first divided area based on the first direction and the first distance.

5. The method according to claim 2, characterized in that The controlling the detection point to move in the first divided area includes: controlling the detection point to move multiple times in the first divided area until the position of the detection point after the movement is the first position; and / or The detection point is controlled to move multiple times in the first divided area until the union of the multiple first sub-areas covers the first divided area.

6. The method according to claim 2, characterized in that Determining the first target sub-region as an abnormal region includes: If there are multiple first target sub-regions and there is an intersection between the multiple first target sub-regions, the region formed by merging the multiple first target sub-regions is determined as the abnormal region.

7. The method according to claim 1, characterized in that The method further comprises: When it is determined that the electrical signal amplitude corresponding to the first divided area within the target slice layer is not within the first threshold range corresponding to the first divided area, if, among the multiple second sub-areas contained in the first divided area, there is a second target sub-area whose electrical signal amplitude corresponding to the second target sub-area is not within the second threshold range corresponding to the second target sub-area, then the second target sub-area is determined as an abnormal area.

8. The method according to claim 1, characterized in that The optical signal includes at least one of the following: The laser output signal, laser reflection signal, infrared light signal and visible light signal of the laser in the laser additive manufacturing process.

9. A laser additive manufacturing quality detection device, characterized in that: The device comprises: An acquisition unit, configured to acquire an electrical signal corresponding to an optical signal during a first time period in a laser additive manufacturing process, wherein the first time period is a time period for processing a target slice layer of a target part during the laser additive manufacturing process; a processing unit configured to, upon determining that an electrical signal amplitude corresponding to a first divided area within the target slice layer is within a first threshold range corresponding to the first divided area, determine the first target sub-area as an abnormal area if a first ratio corresponding to a first target sub-area among a plurality of first sub-areas included in the first divided area is not within a preset ratio range; Among them, the first ratio corresponding to the first target sub-area is the ratio between the electrical signal amplitude corresponding to the first target sub-area and the electrical signal amplitude corresponding to the target area of ​​the first shape in the first divided area, the first shape is the shape corresponding to the first target sub-area, and the target area of ​​the first shape is the first divided area corresponding to the first target sub-area; the upper limit and lower limit of the first threshold range are respectively the maximum value and minimum value of the electrical signal amplitude corresponding to the first divided area in the defect-free slice layer in the process of processing the defect-free slice layer under the same processing parameters as those of processing the target part.

10. The device according to claim 9, characterized in that The processing unit is further configured to: determining a plurality of detection points in the first divided area; For each detection point among the plurality of detection points, determining a first area of ​​the first shape with a first position of the detection point as a center; The detection point is controlled to move in the first divided area, and a second area of ​​the first shape is determined with a second position of the detection point after the movement as the center, and the multiple first sub-areas include multiple first areas and multiple second areas.

11. The device according to claim 10, characterized in that The first shape includes at least one of the following: a square, a circle, a horizontal rectangle, and a vertical rectangle.

12. The device according to claim 10, characterized in that The processing unit is further configured to: constructing a trajectory amplitude map corresponding to the first divided area based on the plurality of trajectory amplitude lines, wherein the contour of the trajectory amplitude map is the same as the contour of the first divided area, the plurality of trajectory amplitude lines correspond to processing trajectories when processing the first divided area of ​​the target slice layer, and the amplitudes represented by the trajectory amplitude lines are the amplitudes of the electrical signals during the process of processing the first divided area of ​​the target slice layer; In terms of controlling the detection point to move in the first divided area, the processing unit is specifically configured to: Determine a first direction in which the amplitude gradient between adjacent pixels of the detection point is the largest in the trajectory amplitude map; determining a first distance according to a magnitude of an amplitude gradient of the detection point in the first direction in the trajectory amplitude map, wherein a larger amplitude gradient in the first direction indicates a smaller first distance; The detection point is controlled to move in the first divided area based on the first direction and the first distance.

13. The device according to claim 10, characterized in that In terms of controlling the detection point to move in the first divided area, the processing unit is specifically configured to: controlling the detection point to move multiple times in the first divided area until the position of the detection point after the movement is the first position; and / or The detection point is controlled to move multiple times in the first divided area until the union of the multiple first sub-areas covers the first divided area.

14. The device according to claim 10, characterized in that In terms of determining the first target sub-region as an abnormal region, the processing unit is specifically configured to: If there are multiple first target sub-regions and there is an intersection between the multiple first target sub-regions, the region formed by merging the multiple first target sub-regions is determined as the abnormal region.

15. The device according to claim 9, characterized in that The processing unit is further configured to: When it is determined that the electrical signal amplitude corresponding to the first divided area within the target slice layer is not within the first threshold range corresponding to the first divided area, if, among the multiple second sub-areas contained in the first divided area, there is a second target sub-area whose electrical signal amplitude corresponding to the second target sub-area is not within the second threshold range corresponding to the second target sub-area, then the second target sub-area is determined as an abnormal area.

16. The device according to claim 9, characterized in that The optical signal includes the output light signal of the laser in the laser additive manufacturing process, as well as the laser reflection signal, infrared light signal and visible light signal.

Images