Additive manufacturing forming monitoring method, device and system

Abstract

The invention provides an additive manufacturing forming monitoring method, device and system, and the method comprises the steps: receiving multi-source synchronous monitoring data in an additive manufacturing process, the multi-source synchronous monitoring data at least comprise acoustic signals, temperature field data, morphology data of a molten pool and plasma spectral signals generated in the additive manufacturing process; performing fusion analysis on the multi-source synchronous monitoring data according to the timestamps, and extracting key features representing forming quality; and evaluating the quality of the formed part according to the key features to obtain an evaluation result. By means of the scheme, the comprehensive monitoring capacity of the additive manufacturing process can be improved.

Description

Technical Field

[0001] The present invention relates to the field of additive manufacturing monitoring technology, and in particular to an additive manufacturing forming monitoring method, device and system. Background Art

[0002] The additive manufacturing (AM) forming process generates signals such as infrared radiation, visible light, ultraviolet light, sound, ultrasound and plasma. The dynamic changes of these signals have been shown to be closely related to the final forming defects and quality. In recent years, many studies have collected various signals during the deposition process through infrared thermal imagers, complementary metal oxide semiconductor (CMOS) cameras, acoustic emission sensors, spectrometers, etc., and used artificial intelligence methods such as machine learning and deep learning to achieve defect detection and quality evaluation of AM formed parts. However, in the existing monitoring schemes, it is difficult for sensor data information to comprehensively and accurately describe the dynamic forming characteristics of the metal additive process, and it is difficult to conduct real-time monitoring of the process, which limits the accuracy of defect detection and quality evaluation. Summary of the invention

[0003] The present invention provides an additive manufacturing forming monitoring method, device and system to enhance the comprehensive monitoring capability of the additive manufacturing process.

[0004] To this end, the present invention provides the following technical solutions:

[0005] In one aspect, the present invention provides an additive manufacturing forming monitoring method, the method comprising:

[0006] Receiving multi-source synchronous monitoring data during the additive manufacturing process, the multi-source synchronous monitoring data having a timestamp, the multi-source synchronous monitoring data comprising at least: acoustic signals, temperature field data, morphology data of the molten pool, and plasma spectrum signals generated during the additive manufacturing process;

[0007] Performing fusion analysis on the multi-source synchronous monitoring data according to the timestamp to extract key features characterizing the forming quality;

[0008] The quality of the formed part is evaluated according to the key features to obtain an evaluation result.

[0009] Optionally, the method further comprises: caching the multi-source synchronously collected data at the same time and converting the data into a set file format and saving the format into a storage module.

[0010] Optionally, the method further comprises:

[0011] The acoustic signal is collected by using an acoustic signal collection device; the acoustic signal collection device includes: a contact acoustic emission collection module and / or a non-contact sound collection module;

[0012] The temperature field information is collected by using a thermal signal collection device; the thermal signal collection device comprises: a near-infrared thermal imager;

[0013] The molten pool morphology is collected by using an optical imaging device; the optical imaging device comprises a CMOS camera;

[0014] The plasma spectrum signal is collected by using a plasma collection device; the plasma collection device includes: a multi-channel spectrometer.

[0015] Optionally, the key features include any one or more of the following: frequency response of an acoustic signal, characteristic peaks of a spectral signal, temperature gradients of thermal imaging data, and texture and morphological features of a topographic image.

[0016] Optionally, the method further includes: outputting feedback information according to the evaluation result.

[0017] On the other hand, the present invention also provides an additive manufacturing forming monitoring device, the device comprising:

[0018] A data acquisition module, used for receiving multi-source synchronous monitoring data in the additive manufacturing process, wherein the multi-source synchronous monitoring data carries a timestamp and includes at least: acoustic signals, temperature field data, morphology data of the molten pool, and plasma spectrum signals generated in the additive manufacturing process;

[0019] A data analysis module, used to perform fusion analysis on the multi-source synchronous monitoring data according to the timestamp, and extract key features characterizing the forming quality;

[0020] The quality evaluation module is used to evaluate the quality of the formed part according to the key features.

[0021] Optionally, the device further comprises: a big data cache module and a storage module;

[0022] The data acquisition module uses one thread to cache the multi-source synchronously collected data in the big data cache module, and uses another thread to convert the data in the big data cache module into a set file format and save it to the storage module.

[0023] Optionally, the device further comprises: a feedback module, configured to output feedback information according to the evaluation result.

[0024] On the other hand, the present invention further provides an additive manufacturing forming monitoring system for monitoring an additive manufacturing process of an additive manufacturing device, wherein the additive manufacturing device comprises: a laser, a printing platform, a mechanical arm, and a cladding head arranged on the mechanical arm; the system comprises: a data acquisition device, and the additive manufacturing forming monitoring device;

[0025] The data acquisition device is used to collect multiple different types of monitoring data during the additive manufacturing process and send the collected monitoring data to the additive manufacturing forming monitoring device;

[0026] The material forming monitoring device is used to receive multi-source synchronous monitoring data and evaluate the quality of the formed part according to the multi-source synchronous monitoring data.

[0027] Optionally, the data acquisition device includes:

[0028] An acoustic signal collecting device, used for collecting acoustic signals;

[0029] A temperature signal acquisition device, used for acquiring temperature field data;

[0030] An image acquisition device, used for acquiring topographic data of the molten pool;

[0031] The plasma collection device is used to collect the plasma spectrum signal generated in the additive manufacturing process.

[0032] Optionally, the acoustic signal collection device includes: a contact acoustic emission collection module and / or a non-contact sound collection module;

[0033] The contact acoustic emission acquisition module is installed on the printing platform and is used to collect elastic wave high-frequency signals;

[0034] The non-contact sound collection module is arranged around the printing platform and is used for collecting low-frequency acoustic signals of the molten pool.

[0035] Optionally, the temperature signal acquisition device includes: a near-infrared thermal imager, which is arranged near the cladding head and connected to the end of the robotic arm through an adaptive clamp, and is used to collect temperature field data of the molten pool and the surrounding area.

[0036] Optionally, the image acquisition device includes: a CMOS camera, which is fixed above the cladding head through a coaxial optical system and is used to collect morphological data of the molten pool during the additive manufacturing process.

[0037] Optionally, the plasma collection device includes: a fiber optic collimator is arranged near the cladding head and connected to the end of the robot arm through an adaptive clamp, and the collimator is connected to a multi-channel spectrometer through an optical fiber to collect plasma spectrum signals generated during the additive manufacturing process.

[0038] Optionally, different acquisition devices are configured to trigger operation synchronously and add time stamps to the acquired data.

[0039] On the other hand, the present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the additive manufacturing forming monitoring method are executed.

[0040] The additive manufacturing forming monitoring method, device and system provided by the present invention simultaneously monitor the additive manufacturing process in multiple ways, and realize all-round monitoring of the additive manufacturing forming mechanism through data collection in multiple different ways such as sound, light, heat and plasma, and obtain multi-source synchronous monitoring data with timestamps. By performing online fusion analysis on the multi-source synchronous monitoring data, the correlation and complementarity between these data are fully explored and utilized, and the key features that characterize the forming quality are extracted; and the quality of the formed parts is evaluated based on the key features.

[0041] Furthermore, in view of the fact that the signals generated in the additive manufacturing process are diverse and complex, the multi-source synchronously collected data is cached simultaneously through a multi-threaded manner and converted into a set file format and saved in the storage module. Through the multi-threaded design, real-time storage and online processing of high-frequency and large-scale data are achieved, thereby realizing online monitoring and feedback control of component forming defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 It is a flow chart of the additive manufacturing forming monitoring method provided by the present invention;

[0044] Figure 2 It is a structural schematic diagram of the additive manufacturing forming monitoring device provided by the present invention;

[0045] Figure 3 It is another structural schematic diagram of the additive manufacturing forming monitoring device provided by the present invention;

[0046] Figure 4 It is a structural schematic diagram of the additive manufacturing forming monitoring system of the present invention;

[0047] Figure 5It is a schematic diagram of a specific structure of a data acquisition device in the additive manufacturing forming monitoring system of the present invention and its interface with the additive manufacturing forming monitoring device.

[0048] Reference numerals:

[0049] 11. Adaptive fixture;

[0050] 21. Contact acoustic emission collection module, 24. Non-contact sound collection module;

[0051] 30. Temperature signal acquisition device;

[0052] 40. Image acquisition device, 42. Coaxial optical system;

[0053] 50. Plasma collection device;

[0054] 61. Laser, 62. Robotic arm, 63. Cladding head, 64. Material feeding device,

[0055] 65. PLC, 66. Shielding gas device, 67. Printing platform, 70. Molten pool. DETAILED DESCRIPTION

[0056] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0057] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. 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 should fall within the scope of protection of the present invention.

[0058] In view of the problem that the existing additive manufacturing forming monitoring process is limited in signal collection and cannot meet the complete and comprehensive requirements of the process, which in turn affects the accuracy of defect detection and quality evaluation, an embodiment of the present invention provides an additive manufacturing forming monitoring method and system, which obtains multi-source synchronous monitoring data with timestamps through all-round synchronous monitoring of sound, light, heat and plasma in the additive manufacturing process, and fully explores and utilizes the correlation and complementarity between these data through online fusion analysis of the multi-source synchronous monitoring data, extracts key features that characterize the forming quality, and evaluates the quality of the formed parts based on the key features.

[0059] like Figure 1 FIG. 1 is a flow chart of the additive manufacturing forming monitoring method provided by the present invention, comprising the following steps:

[0060] Step 101, receiving multi-source synchronous monitoring data during the additive manufacturing process, wherein the multi-source synchronous monitoring data carries a timestamp and includes at least: acoustic signals, temperature field data, morphology data of the molten pool, and plasma spectrum signals generated during the additive manufacturing process.

[0061] Different types of monitoring data can be collected by corresponding sensors, such as:

[0062] The sound information is collected by using an acoustic signal collection device; the acoustic signal collection device may include, for example: a contact acoustic emission collection module and / or a non-contact sound collection module; wherein the contact acoustic emission collection module may be installed on the printing platform to collect elastic wave high-frequency signals; the non-contact sound collection module may be arranged around the printing platform to collect molten pool low-frequency acoustic signals;

[0063] The temperature field information is collected by using a thermal signal collection device; the thermal signal collection device may include, for example: a near-infrared thermal imager;

[0064] The molten pool morphology is collected by using an optical imaging device; the optical imaging device may include a CMOS camera, for example;

[0065] A plasma collection device is used to collect plasma spectrum signals generated during the additive manufacturing process; the plasma collection device may include, for example: a fiber collimating lens, a one-to-eight optical fiber, and an eight-channel spectrometer.

[0066] Each sensor starts synchronously, and each adds a time stamp to the collected data and transmits it to the data processing center for analysis.

[0067] Furthermore, considering the large frequency and scale of data collection, different threads can be used to cache the multi-source synchronously collected data and convert it into a set file format and save it in the storage module, which can effectively ensure the storage and processing efficiency of the data.

[0068] Step 102: performing fusion analysis on the multi-source synchronous monitoring data according to the timestamp to extract key features characterizing the forming quality.

[0069] Specifically, the multi-source synchronous monitoring data can be read from the storage module, and the data from different sensors can be fused and analyzed according to the timestamps in the data. For example, the synchronous data from different sources can be fused and analyzed at the data level, feature level, and decision level.

[0070] In the additive manufacturing process, high-precision clock and data synchronization technology can be integrated to ensure that the collected multi-source synchronous monitoring data have a unified timestamp.

[0071] Furthermore, an adaptive filter can be used to remove environmental noise and interference signals in real time, and to pre-process the data online to ensure that the acquired signal has a high signal-to-noise ratio and consistency.

[0072] In some embodiments, the key features may include, but are not limited to, any one or more of the following: frequency response of an acoustic signal, characteristic peaks of a spectral signal, temperature gradients of thermal imaging data, and texture and morphological features of a topographic image.

[0073] Step 103, evaluating the quality of the formed part according to the key features to obtain an evaluation result.

[0074] For example, in a non-limiting embodiment, quality evaluations of different dimensions can be performed for data from different sources in the same time period based on the timestamps in the multi-source data, such as: using acoustic emission and thermal imaging data to detect internal defects in the material, such as cracks, delamination, and pores; evaluating the geometric accuracy, roughness, surface oxide layer, etc. of the surface through CMOS camera and spectral data analysis; evaluating the stability of equipment operation and the consistency of process parameters based on non-contact microphone and acoustic emission data; using spectral data to monitor the composition changes of materials during processing to ensure the consistency and quality of the materials. Then, these different dimensional quality evaluations are combined to obtain the final forming quality evaluation results of laser directed energy deposition.

[0075] For example, in another non-limiting embodiment, the multimodal fusion network in deep learning (such as a joint convolutional neural network and an attention mechanism) can be used to fuse these key features in a high-dimensional space to generate a comprehensive quality characterization vector.

[0076] The multimodal fusion network can be trained by collecting various monitoring data in the additive manufacturing process. By training the neural network model, the quality characterization vector generated by the fusion of multimodal data is associated with the forming quality in the actual process (such as material density, internal defects, surface finish, etc.), thereby improving the accuracy and reliability of data fusion and achieving accurate evaluation of the quality of additively manufactured parts.

[0077] The specific training process of the multimodal fusion network is similar to the existing corresponding network training process, which will not be repeated here.

[0078] Using this multimodal fusion network, defects that may occur in the additive manufacturing process can be accurately identified, such as overheating of the melt pool, incomplete melting of the material, inconsistent morphology, and other problems.

[0079] By utilizing the additive manufacturing forming monitoring method provided by the present invention, the complementarity between the modal data can be utilized to automatically identify and enhance the information useful for the quality assessment of the formed parts, thereby improving the accuracy and reliability of data fusion.

[0080] Furthermore, in some embodiments, corresponding control measures can be taken for different types of defects, that is, feedback information is output according to the evaluation results, so that the additive manufacturing equipment can adjust the working parameters in time according to the feedback signal. For example, the working parameters of each device or component of the additive manufacturing platform, such as laser power, robot arm movement speed, material feed rate, etc., are adjusted in real time to eliminate forming defects and ensure forming quality.

[0081] Accordingly, an embodiment of the present invention further provides an additive manufacturing forming monitoring device, such as Figure 2 Shown is a structural schematic diagram of the device.

[0082] The additive manufacturing forming monitoring device 200 includes the following modules:

[0083] A data acquisition module 201 is used to receive multi-source synchronous monitoring data in the additive manufacturing process, wherein the multi-source synchronous monitoring data carries a timestamp and includes at least: acoustic signals, temperature field data, morphology data of the molten pool, and plasma spectrum signals generated in the additive manufacturing process;

[0084] A data analysis module 202, configured to perform fusion analysis on the multi-source synchronous monitoring data according to the timestamps, and extract key features characterizing the forming quality;

[0085] The quality evaluation module 203 is used to evaluate the quality of the formed part according to the key features.

[0086] like Figure 3 As shown, in another embodiment, the additive manufacturing forming monitoring device 200 may further include: a big data cache module 204 and a storage module 205.

[0087] In this embodiment, the data acquisition module 201 uses one thread to cache the multi-source synchronously collected data in the big data cache module 204, and uses another thread to convert the data in the big data cache module 204 into a set file format and save it to the storage module 205.

[0088] The data acquisition module 201 uses different threads to work, which not only improves the data storage and processing efficiency, but also the design of the big data cache module 204 effectively avoids the problem of data loss caused by the inconsistency of data acquisition and file storage speed.

[0089] In other embodiments, the additive manufacturing forming monitoring device 200 may further include: a feedback module (not shown), which is used to output feedback information based on the evaluation results, so that the additive manufacturing equipment can adjust the working parameters in time according to the feedback signal, such as laser power, feed speed and other working parameters, to eliminate forming defects and ensure forming quality.

[0090] Correspondingly, an embodiment of the present invention further provides an additive manufacturing forming monitoring system for monitoring the additive manufacturing process of an additive manufacturing device.

[0091] Additive manufacturing, also known as 3D printing, is a rapid prototyping technology that uses a computer three-dimensional design model as a blueprint. Through software separation and discrete and CNC prototyping systems, metal powders, ceramic powders, plastics, cell tissues, etc. are stacked and bonded layer by layer using laser beams, hot melt nozzles, etc., and finally superimposed to form a physical product. Therefore, 3D printing can be simply understood as multi-layer two-dimensional printing. 3D printing generally uses special materials, based on a coordinate system, and according to three-dimensional drawings, it is sprayed or sintered layer by layer into three-dimensional space, thereby manufacturing highly complex products that are difficult to manufacture with traditional processes.

[0092] Combine the following Figure 4 The structure of the additive manufacturing equipment shown in the figure illustrates in detail the structure of the additive manufacturing forming monitoring system of the present invention.

[0093] Reference Figure 4 The additive manufacturing equipment mainly includes: a laser 61, a printing platform 67, a robot arm 62, and a cladding head 63 arranged on the robot arm 62, and also includes a material feeding device 64 and a PLC (programmable logic controller) 65.

[0094] The shielding gas device 66 is used to spray shielding gas around the molten pool through a pipeline at the cladding head 63 to protect the molten pool from oxidation.

[0095] Among them, the material feeding device 64 is used to provide the raw materials required in the manufacturing process; PLC65 is used to control the working state of the entire additive manufacturing platform and realize signal transmission with the multi-source data fusion monitoring device 200.

[0096] The additive manufacturing forming monitoring system provided in the embodiment of the present invention comprises: a data acquisition device, and the additive manufacturing forming monitoring device 200 in the above embodiments. Among them:

[0097] The data acquisition device is used to collect various types of monitoring data during the additive manufacturing process, and send the collected monitoring data to the additive manufacturing forming monitoring device 200;

[0098] The material manufacturing forming monitoring device 200 is used to receive multi-source synchronous monitoring data and evaluate the quality of the formed part according to the multi-source synchronous monitoring data.

[0099] like Figure 4 As shown, the data acquisition device may include multiple different types of acquisition devices. For example, in some embodiments, it may specifically include:

[0100] (1) An acoustic signal acquisition device, used to acquire the acoustic signal; for example, it may include: a contact acoustic emission acquisition module 21 and / or a non-contact sound acquisition module 24. The contact acoustic emission acquisition module 21 is arranged on the printing platform 67 to acquire elastic wave high-frequency signals; the non-contact sound acquisition module 24 is arranged around the printing platform 67 to acquire molten pool low-frequency acoustic signals to assist in acoustic analysis of the acoustic wave signals acquired by the contact acoustic emission acquisition module 21.

[0101] The contact acoustic emission acquisition module 21 may include an acoustic emission probe and a high-frequency acquisition card, wherein the acoustic emission probe may be disposed on the printing platform 67 and fixed by an adaptive bracket.

[0102] The non-contact sound collection module 24 may include a non-contact microphone and a low-frequency collection card.

[0103] (2) A temperature signal acquisition device 30, for acquiring the temperature field data; for example, a near-infrared thermal imager may be used, which is disposed near the cladding head 63 and connected to the end of the robotic arm 62 via an adaptive fixture 11, for acquiring the temperature field data of the molten pool and the surrounding area.

[0104] (3) An image acquisition device 40, used to acquire the morphological data of the molten pool; for example, a CMOS camera can be used, which is fixed above the cladding head 63 through a coaxial optical system 42 to acquire the morphological data of the molten pool during the additive manufacturing process.

[0105] (4) A plasma collection device 50, used to collect plasma spectrum signals generated during the additive manufacturing process; for example, the plasma collection device 50 may include an optical fiber collimator and a multi-channel spectrometer. The optical fiber collimator is arranged near the cladding head 63 and connected to the end of the mechanical arm 62 through an adaptive fixture 11, and the optical fiber collimator is connected to the multi-channel spectrometer through an optical fiber. The multi-channel spectrometer collects plasma spectrum signals generated during the additive manufacturing process.

[0106] It should be noted that different acquisition devices are configured to trigger work synchronously and add time stamps to the acquired data.

[0107] Figure 5A specific structure of the data acquisition device in an embodiment of the present invention and an interface method with the additive manufacturing forming monitoring device are shown.

[0108] Also refer to Figure 4 and Figure 5 The acoustic emission probe in the data acquisition device is set on the printing platform 67, for example, on the back or side of the printing platform 67, to collect the high-frequency vibration signal of the printing platform 67 during the additive manufacturing process, and transmit it to the USB1 interface of the additive manufacturing monitoring device 200 through a high-frequency acquisition card.

[0109] The non-contact microphone in the data acquisition device is fixed to the side axis of the cladding head 63 through a designed adaptive fixture to collect low-frequency sound signals around the printing platform 63 in the molten pool 70 during the additive manufacturing process, and transmits them to the USB2 interface of the additive manufacturing monitoring device 200 through a low-frequency acquisition card.

[0110] The near-infrared thermal imager is fixed to the side axis of the cladding head 63 through a designed adaptive fixture to collect temperature field data of the molten pool and the surrounding area, and transmits the collected temperature field data to the additive manufacturing forming monitoring device 200 through a Gigabit Ethernet interface.

[0111] The optical fiber collimating lens is fixed to the bypass of the cladding head 63 through an adaptive fixture to collect the plasma spectrum signal generated during the additive manufacturing process, and transmit it to the USB3 interface of the additive manufacturing forming monitoring device 200 through a one-to-eight optical fiber and an eight-channel spectrometer.

[0112] The CMOS camera is fixed above the cladding head 63 through a coaxial optical system to collect morphological data of the molten pool during the additive manufacturing process, and transmits the collected morphological data to another Gigabit Ethernet interface of the additive manufacturing forming monitoring device 200.

[0113] In the additive manufacturing forming monitoring system provided by the embodiment of the present invention, the additive manufacturing forming monitoring device can be a computer, and the computer can be designed in layers, which are divided into: a human-computer interaction interface, a compatibility layer, and a bottom layer from top to bottom.

[0114] The human-computer interaction interface mainly completes functions such as parameter interface display, data collection operation, real-time data visualization, and multi-language.

[0115] The compatibility layer is responsible for connecting to the sensor interface and completing functions such as sensor configuration data sending, start and stop control, data conversion, and big data buffering.

[0116] The bottom layer receives data from each sensor and processes files on disk. It adopts a multi-process design to ensure the real-time storage performance of large-scale data and fully utilizes the multi-core high concurrency performance of the computer.

[0117] In the system of the present invention, each data acquisition module exists as a separate process, which is isolated from each other and does not interfere with each other. In addition, the computer also receives and converts data at the same time under the human-computer interaction interface, realizing high concurrency and high performance of data acquisition. A separate service is provided for each sensor, which mainly completes the configuration of sensor parameters, sensor start and stop control, sensor data acquisition logic, data conversion and data storage.

[0118] By utilizing the additive manufacturing forming monitoring method, device and system provided in the embodiments of the present invention, it is possible to achieve comprehensive and synchronous monitoring and perception of sound-heat-light-plasma and other phenomena in the additive manufacturing process. In addition, by using a data-driven method, different sensor signals are fused and analyzed, key features characterizing the forming quality are extracted, and accurate and high-quality evaluation of the quality of the formed parts is achieved.

[0119] Furthermore, the evaluation results can be used to guide subsequent process control and improve process quality.

[0120] For example, the material manufacturing and forming monitoring device 200 detects abnormalities in the manufacturing process, such as overheating of the molten pool, incomplete melting of the material, inconsistent morphology, etc., and feeds back the abnormal information to the Figure 4 PLC61 in the system. PLC61 adjusts the working parameters of the additive manufacturing platform in real time according to the feedback information, such as laser power, robot arm movement speed, material feed rate, etc., to eliminate forming defects and ensure forming quality.

[0121] For another example, the material manufacturing forming monitoring device 200 detects an abnormality in the manufacturing process, such as uneven temperature field, abnormal acoustic signal, abnormal spectral signal, etc., and feeds back the abnormal information to the Figure 4 PLC61 in the machine. PLC61 adjusts the laser power, robot arm movement speed and material feed rate in real time based on feedback information to ensure the stability of the manufacturing process and the quality of the forming.

[0122] It can be seen that the system of the present invention can timely discover and correct defects in the manufacturing process, and can take corresponding control measures to adjust different types of defects, thereby ensuring the stability and forming quality of the manufacturing process. The system of the present invention can also improve the monitoring accuracy and control efficiency in the additive manufacturing process.

[0123] The additive manufacturing forming monitoring method, device and system provided by the present invention can process sensor data in real time and generate quality prediction results in real time during the deposition process. When potential quality problems are detected, the system can automatically issue an alarm and recommend adjustments to process parameters, such as laser power, scanning speed, etc., to ensure forming quality. Compared with traditional quality control methods, this solution has higher accuracy and response speed, and can significantly improve process stability and the qualified rate of finished products.

[0124] In order to further improve the intelligence of the system, an adaptive learning and quality feedback optimization mechanism is introduced. The system can continuously learn during operation, and continuously update and optimize the quality assessment model by analyzing historical data and new real-time data, so that it can adapt to different materials, process parameters and working environments. At the same time, the system also has a feedback control function, which can automatically adjust process parameters such as laser energy and scanning path according to real-time quality assessment results, thereby optimizing the stability of the forming process and product quality. This adaptive feedback mechanism enables the system to have a high degree of flexibility and autonomy, able to cope with complex and changing process requirements, and continuously improve the forming quality.

[0125] Based on the analysis of fused data, key quality indicators (KPIs) related to process parameters can be generated, which are used to guide the optimization of process parameters. Through data-driven methods, key factors affecting forming quality can be identified, and parameters such as laser power, scanning speed, and material supply rate can be automatically adjusted to optimize the forming effect. In addition, the system also has intelligent control capabilities and can dynamically adjust parameters based on real-time feedback to ensure that the process is always in the best state. Compared with traditional empirical adjustment methods, data-driven optimization strategies have higher accuracy and efficiency, and can significantly improve the controllability of the process and the consistency of formed parts.

[0126] The specific implementation of each of the above modules can refer to the description in the previous embodiment of the method of the present invention, which will not be repeated here.

[0127] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0128] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0129] In several embodiments provided by the present invention, it should be understood that the disclosed device can be implemented in other ways.

[0130] The present invention also provides a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and the computer program can be executed when it is run. Figure 1The storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc. The storage medium may also include a non-volatile memory (non-volatile) or a non-transitory memory, etc.

[0131] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless means.

[0132] The embodiments of the present invention are described in detail above. The present invention is described in detail using specific implementation methods herein. The description of the above embodiments is only used to help understand the method and system of the present invention. It is only a 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 should belong to the scope of protection of the present invention, and the content of this specification should not be understood as limiting the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for monitoring additive manufacturing, characterized in that: The method comprises: Receiving multi-source synchronous monitoring data during the additive manufacturing process, the multi-source synchronous monitoring data having a timestamp, the multi-source synchronous monitoring data comprising at least: acoustic signals, temperature field data, morphology data of the molten pool, and plasma spectrum signals generated during the additive manufacturing process; Performing fusion analysis on the multi-source synchronous monitoring data according to the timestamp to extract key features characterizing the forming quality; The quality of the formed part is evaluated according to the key features to obtain an evaluation result.

2. The additive manufacturing forming monitoring method according to claim 1, characterized in that: The method further comprises: The multi-source synchronously collected data are cached at the same time and converted into a set file format and saved in a storage module.

3. The additive manufacturing forming monitoring method according to claim 1, characterized in that: The method further comprises: The acoustic signal is collected by using an acoustic signal collection device; the acoustic signal collection device includes: a contact acoustic emission collection module and / or a non-contact sound collection module; The temperature field information is collected by using a thermal signal collection device; the thermal signal collection device comprises: a near-infrared thermal imager; The molten pool morphology is collected by using an optical imaging device; the optical imaging device comprises a CMOS camera; The plasma spectrum signal is collected by using a plasma collection device; the plasma collection device includes: a multi-channel spectrometer.

4. The additive manufacturing forming monitoring method according to claim 1, characterized in that: The key features include any one or more of the following: frequency response of acoustic signals, characteristic peaks of spectral signals, temperature gradients of thermal imaging data, and texture and morphological features of topographic images.

5. The additive manufacturing forming monitoring method according to any one of claims 1 to 4, characterized in that: The method further comprises: Output feedback information according to the evaluation result.

6. An additive manufacturing forming monitoring device, characterized in that: The device comprises: A data acquisition module, used for receiving multi-source synchronous monitoring data in the additive manufacturing process, wherein the multi-source synchronous monitoring data carries a timestamp and includes at least: acoustic signals, temperature field data, morphology data of the molten pool, and plasma spectrum signals generated in the additive manufacturing process; A data analysis module, used to perform fusion analysis on the multi-source synchronous monitoring data according to the timestamp, and extract key features characterizing the forming quality; The quality evaluation module is used to evaluate the quality of the formed part according to the key features.

7. The additive manufacturing forming monitoring device according to claim 6, characterized in that: The device also includes: a big data cache module and a storage module; The data acquisition module uses one thread to cache the multi-source synchronously collected data in the big data cache module, and uses another thread to convert the data in the big data cache module into a set file format and save it to the storage module.

8. The additive manufacturing forming monitoring device according to claim 6 or 7, characterized in that: The device also includes: A feedback module is used to output feedback information according to the evaluation result.

9. An additive manufacturing forming monitoring system for monitoring an additive manufacturing process of an additive manufacturing device, the additive manufacturing device comprising: A laser, a printing platform, a robotic arm, and a cladding head arranged on the robotic arm; characterized in that the system comprises: a data acquisition device, and an additive manufacturing forming monitoring device according to any one of claims 6 to 8; The data acquisition device is used to collect multiple different types of monitoring data during the additive manufacturing process and send the collected monitoring data to the additive manufacturing forming monitoring device; The material forming monitoring device is used to receive multi-source synchronous monitoring data and evaluate the quality of the formed part according to the multi-source synchronous monitoring data.

10. The additive manufacturing forming monitoring system according to claim 9, characterized in that: The data acquisition device comprises: An acoustic signal collecting device, used for collecting acoustic signals; A temperature signal acquisition device, used for acquiring temperature field data; An image acquisition device, used for acquiring topographic data of the molten pool; The plasma collection device is used to collect the plasma spectrum signal generated in the additive manufacturing process.

11. The additive manufacturing forming monitoring system according to claim 10, characterized in that: The acoustic signal collection device comprises: a contact acoustic emission collection module and / or a non-contact sound collection module; The contact acoustic emission acquisition module is installed on the printing platform and is used to collect elastic wave high-frequency signals; The non-contact sound collection module is arranged around the printing platform and is used for collecting low-frequency acoustic signals of the molten pool.

12. The additive manufacturing forming monitoring system according to claim 10, characterized in that: The temperature signal acquisition device comprises: A near-infrared thermal imager is arranged near the cladding head and connected to the end of the mechanical arm through an adaptive clamp, and is used to collect temperature field data of the molten pool and the surrounding area.

13. The additive manufacturing forming monitoring system according to claim 10, characterized in that: The image acquisition device comprises: The CMOS camera is fixed above the cladding head through a coaxial optical system and is used to collect morphological data of the molten pool during the additive manufacturing process.

14. The additive manufacturing forming monitoring system according to claim 10, characterized in that: The plasma collection device includes: an optical fiber quasi-diameter and a multi-channel spectrometer; The fiber optic collimator is arranged near the cladding head and connected to the end of the mechanical arm through an adaptive clamp. The fiber optic collimator is connected to the multi-channel spectrometer through an optical fiber.

15. The additive manufacturing forming monitoring system according to claim 10, characterized in that: Different acquisition devices are configured to trigger work synchronously and add time stamps to the acquired data.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the additive manufacturing forming monitoring method according to any one of claims 1 to 5 are executed.

Images