Metal additive manufacturing online detection method and system

Abstract

The invention provides a metal additive manufacturing online detection method and system, and the method comprises the steps: S1, inputting part drawing information, setting process parameters required by a machine, and carrying out additive manufacturing; s2, collecting a laser ultrasonic signal in the additive manufacturing process, and converting the laser ultrasonic signal into an electric signal; and S3, the electric signals are classified, and the actual situation of additive manufacturing is judged according to the classification result. The machine learning method can be used for fully and reasonably processing the electric signals converted from the laser ultrasonic signals in the forming process, and online detection of additive manufacturing is achieved; the additive manufacturing efficiency and the forming quality can be further improved, the metal additive manufacturing cost can be effectively reduced, and a technical foundation is laid for wide application of metal additive manufacturing.

Description

Technical Field

[0001] The present invention relates to the field of additive manufacturing, and in particular, to an online detection method and system for metal additive manufacturing, and in particular to an online detection method and system for processing conversion signals in additive manufacturing using a machine learning method. Background Art

[0002] Metal additive manufacturing is one of the most cutting-edge and promising additive manufacturing technologies, and is an important development direction of advanced manufacturing technology. Metal additive manufacturing technology uses high-energy beams (laser beams / electron beams / arcs, etc.) as heat sources to melt powder or wire materials to achieve layer-by-layer stacking and forming of metal components. At present, the application fields are becoming more and more extensive. From aerospace, automobiles, energy, to civilian consumer goods, cultural and creative products, construction and other industries, metal additive manufacturing production and manufacturing solutions have been applied. It can be expected that various types of more efficient and lower-cost additive manufacturing processes and methods will be proposed in the future to promote the continuous development and application of metal additive manufacturing technology. Further optimizing additive manufacturing technology and improving the quality of formed workpieces are of great significance to the development of my country's industry and manufacturing industry.

[0003] In a Chinese patent document with publication number CN107952957B, an additive manufacturing system is disclosed, the additive manufacturing system includes an additive manufacturing module, the additive manufacturing module has two lateral supports and an additive manufacturing forming cavity located between the two lateral supports, the two lateral supports extend in parallel and are separated by a predetermined distance, the additive manufacturing system also includes an additive manufacturing device and a longitudinal support straddling the two lateral supports, the longitudinal support can move relative to the two lateral supports along the direction in which the two lateral supports extend, the additive manufacturing device is connected to the longitudinal support through a guiding device and can move together with the longitudinal support, wherein the additive manufacturing system can include a plurality of the additive manufacturing modules, and two adjacent additive manufacturing modules are joined together by a splicing connection device. However, the patent document mainly controls the volume of the forming cavity flexibly according to the size of the part to be formed, which can greatly shorten the exhaust time of the forming cavity, reduce the consumption of inert protective gas, and ultimately reduce resource waste; while the present invention is to achieve online detection of additive manufacturing, which helps to further improve the efficiency and forming quality of additive manufacturing, and is essentially different from the method and technology adopted in the patent document. Summary of the invention

[0004] In view of the defects in the prior art, an object of the present invention is to provide an online detection method and system for metal additive manufacturing.

[0005] A metal additive manufacturing online detection method provided by the present invention comprises:

[0006] Step S1: Input part drawing information, set the process parameters required by the machine, and perform additive manufacturing;

[0007] Step S2: collecting laser ultrasonic signals during the additive manufacturing process and converting them into electrical signals;

[0008] Step S3: classify the electrical signals and determine the actual situation of additive manufacturing according to the classification results.

[0009] Preferably, step S2 includes using a laser diffractometer to collect laser ultrasonic signals, transmitting the laser ultrasonic signals to a photodetector and converting them into electrical signals.

[0010] Preferably, step S3 includes the following sub-steps:

[0011] Step S3.1: using a machine learning device with a signal acquisition card to receive electrical signals, and classifying the electrical signals into strong signals, weak signals, and normal signals;

[0012] Step S3.2: The differentiated electrical signal is converted into electronic information through an analog-to-digital converter and transmitted to the control panel of the printing device for data processing.

[0013] Preferably, the strong signal indicates that the temperature of the forming surface exceeds a preset value, resulting in heat input exceeding a preset range; the weak signal indicates that the powder is not completely melted due to uneven surface energy input; and the normal signal indicates that the forming meets preset conditions.

[0014] Preferably, the step S3 also includes a machine learning device dividing the electrical signal into a red zone, a green zone and a yellow zone, and the red zone corresponds to a strong signal, the green zone corresponds to a weak signal, and the yellow zone corresponds to a normal signal.

[0015] A metal additive manufacturing online detection system provided by the present invention comprises:

[0016] Module M1: Input part drawing information, set the process parameters required by the machine, and perform additive manufacturing;

[0017] Module M2: Collects laser ultrasonic signals during the additive manufacturing process and converts them into electrical signals;

[0018] Module M3: Classify the electrical signals and determine the actual situation of additive manufacturing based on the classification results.

[0019] Preferably, the module M2 includes using a laser diffractometer to collect laser ultrasonic signals, transmitting the laser ultrasonic signals to a photoelectric detector and converting them into electrical signals.

[0020] Preferably, the module M3 includes the following submodules:

[0021] Module M3.1: Use a machine learning device with a signal acquisition card to receive electrical signals and classify the electrical signals into strong signals, weak signals, and normal signals;

[0022] Module M3.2: Convert the differentiated electrical signal into electronic information through an analog-to-digital converter and transmit it to the control panel of the printing device for data processing.

[0023] Preferably, the strong signal indicates that the temperature of the forming surface exceeds a preset value, resulting in heat input exceeding a preset range; the weak signal indicates that the powder is not completely melted due to uneven surface energy input; and the normal signal indicates that the forming meets preset conditions.

[0024] Preferably, the module M3 also includes a machine learning device to divide the electrical signal into a red zone, a green zone and a yellow zone, and the red zone corresponds to a strong signal, the green zone corresponds to a weak signal, and the yellow zone corresponds to a normal signal.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] 1. The present invention can utilize machine learning methods to fully and reasonably process the electrical signals converted from laser ultrasonic signals during the forming process, thereby realizing online detection of additive manufacturing; it is helpful to further improve the efficiency and forming quality of additive manufacturing, effectively reduce the cost of metal additive manufacturing, and lay a technical foundation for the widespread application of metal additive manufacturing.

[0027] 2. The present invention adopts a binary online detection method, combines the conversion between laser ultrasonic signals and electrical signals to transmit the forming information in the laser additive manufacturing process, and uses a machine learning device to classify and calculate the signals. No human operation is required during the detection process, and it can be widely used in the field of additive manufacturing.

[0028] Other beneficial effects of the present invention will be explained in the specific implementation manner through the introduction of specific technical features and technical solutions. Through the introduction of these technical features and technical solutions, those skilled in the art should be able to understand the beneficial technical effects brought about by the technical features and technical solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0030] Figure 1 The figure is a flow chart of the method of the present invention.

[0031] Figure 2 It is a system structure diagram of the present invention. DETAILED DESCRIPTION

[0032] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0033] Reference Figure 1 and Figure 2 As shown, the present invention provides a metal additive manufacturing online detection method, the specific steps are as follows:

[0034] Step 1, Instrument Installation: The instruments required for the present invention include pulse laser, laser interferometer, lens No. 1, lens No. 2, photoelectric detector, machine learning device with signal acquisition card, analog-to-digital converter. Figure 2 Install and adjust the optical path and lens focus.

[0035] Step 2: Import the CAD file of the part to be formed into the program of the corresponding additive manufacturing equipment, set the process parameters required for printing (such as laser power, scanning speed, scanning spacing, powder layer thickness), and start additive manufacturing.

[0036] Step 3: The laser diffractometer collects the laser ultrasonic signal during the forming process, transmits it to the photoelectric detector, and converts the laser ultrasonic signal into an electrical signal.

[0037] Step 4: The electrical signal is received by a machine learning device with a signal acquisition card. The signal acquisition card converts the received electrical signal into a voltage amplitude through an analog-to-digital converter (ADC) and inputs it into the machine learning device. According to the voltage amplitude (i.e., the strength of the electrical signal), the machine learning device divides it into red zone (strong signal), green zone (weak signal) and yellow zone (normal signal). The training of the machine learning model includes: setting the voltage amplitude benchmark of the red zone (strong signal) to 50v, the voltage amplitude benchmark of the green zone (weak signal) to 10v, and the voltage amplitude range of the yellow zone (normal signal) to between (10-50v); importing the above set standards into the machine learning device to form a calculation model.

[0038] Step 5. The differentiated electronic signal is converted into electronic information again through an analog-to-digital converter (ADC) and transmitted to the control panel of the printing device for data processing. The data processing process includes: the control panel of the printing device records the collected real-time electronic information, and the strong signal gives the information that the temperature of the forming surface is too high, resulting in excessive heat input. The weak signal gives the information that the surface energy input is uneven, resulting in incomplete melting of the powder. The normal signal gives the information that the forming is good. Based on the information provided by the strong signal and the weak signal, there will be inevitable defects in the forming process of the printing layer. The control panel will mark the layer as a "problem layer". When the number of consecutive "problem layers" is greater than or equal to 3, the system defaults the forming parameters to unformable parameters and terminates the forming.

[0039] The present invention also provides a metal additive manufacturing online detection system, which can be implemented by executing the process steps of the metal additive manufacturing online detection method, that is, technical personnel in this field can understand the metal additive manufacturing online detection method as a preferred implementation of the metal additive manufacturing online detection system.

[0040] Specifically, a metal additive manufacturing online detection system includes:

[0041] Module M1: Input part drawing information, set the process parameters required by the machine, and perform additive manufacturing;

[0042] Module M2: Collects laser ultrasonic signals during the additive manufacturing process and converts them into electrical signals;

[0043] Module M3: Classify the electrical signals and determine the actual situation of additive manufacturing based on the classification results.

[0044] The module M2 includes using a laser diffractometer to collect laser ultrasonic signals, transmitting the laser ultrasonic signals to a photoelectric detector and then converting them into electrical signals.

[0045] The module M3 includes the following submodules:

[0046] Module M3.1: Use a machine learning device with a signal acquisition card to receive electrical signals and classify the electrical signals into strong signals, weak signals, and normal signals;

[0047] Module M3.2: Convert the differentiated electrical signal into electronic information through an analog-to-digital converter and transmit it to the control panel of the printing device for data processing.

[0048] The strong signal indicates that the temperature of the forming surface exceeds the preset value, resulting in heat input exceeding the preset range; the weak signal indicates that the surface energy input is uneven, resulting in incomplete melting of the powder; and the normal signal indicates that the forming meets the preset conditions.

[0049] The module M3 also includes a machine learning device that divides the electrical signal into a red zone, a green zone and a yellow zone, and the red zone corresponds to a strong signal, the green zone corresponds to a weak signal, and the yellow zone corresponds to a normal signal.

[0050] Those skilled in the art know that, in addition to realizing the system and its various devices, modules, and units provided by the present invention in a purely computer-readable program code, it is entirely possible to realize the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a hardware component, and the devices, modules, and units included therein for realizing various functions can also be regarded as structures within the hardware component; the devices, modules, and units for realizing various functions can also be regarded as both software modules for realizing the method and structures within the hardware component.

[0051] In the description of the present application, it should be understood that the terms "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0052] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A metal additive manufacturing online detection method, characterized in that: include: Step S1: Input part drawing information, set the process parameters required by the machine, and perform additive manufacturing; Step S2: collecting laser ultrasonic signals during the additive manufacturing process and converting them into electrical signals; Step S3: classify the electrical signals and determine the actual situation of additive manufacturing according to the classification results.

2. The metal additive manufacturing online detection method according to claim 1, characterized in that: The step S2 includes collecting laser ultrasonic signals using a laser diffractometer, transmitting the laser ultrasonic signals to a photoelectric detector and converting them into electrical signals.

3. The metal additive manufacturing online detection method according to claim 1, characterized in that: The step S3 comprises the following sub-steps: Step S3.1: using a machine learning device with a signal acquisition card to receive electrical signals, and classifying the electrical signals into strong signals, weak signals, and normal signals; Step S3.2: The differentiated electrical signal is converted into electronic information through an analog-to-digital converter and transmitted to the control panel of the printing device for data processing.

4. The metal additive manufacturing online detection method according to claim 3, characterized in that: The strong signal indicates that the temperature of the forming surface exceeds the preset value, resulting in heat input exceeding the preset range; the weak signal indicates that the surface energy input is uneven, resulting in incomplete melting of the powder; and the normal signal indicates that the forming meets the preset conditions.

5. The metal additive manufacturing online detection method according to claim 3, characterized in that: The step S3 also includes the machine learning device dividing the electrical signal into a red zone, a green zone and a yellow zone, wherein the red zone corresponds to a strong signal, the green zone corresponds to a weak signal, and the yellow zone corresponds to a normal signal.

6. A metal additive manufacturing online detection system, characterized in that: include: Module M1: Input part drawing information, set the process parameters required by the machine, and perform additive manufacturing; Module M2: Collects laser ultrasonic signals during the additive manufacturing process and converts them into electrical signals; Module M3: Classify the electrical signals and determine the actual situation of additive manufacturing based on the classification results.

7. The metal additive manufacturing online detection system according to claim 6, characterized in that: The module M2 includes using a laser diffractometer to collect laser ultrasonic signals, transmitting the laser ultrasonic signals to a photoelectric detector and then converting them into electrical signals.

8. The metal additive manufacturing online detection system according to claim 6, characterized in that: The module M3 includes the following submodules: Module M3.1: Use a machine learning device with a signal acquisition card to receive electrical signals and classify the electrical signals into strong signals, weak signals, and normal signals; Module M3.2: Convert the differentiated electrical signal into electronic information through an analog-to-digital converter and transmit it to the control panel of the printing device for data processing.

9. The metal additive manufacturing online detection system according to claim 8, characterized in that: The strong signal indicates that the temperature of the forming surface exceeds the preset value, resulting in heat input exceeding the preset range; the weak signal indicates that the surface energy input is uneven, resulting in incomplete melting of the powder; and the normal signal indicates that the forming meets the preset conditions.

10. The metal additive manufacturing online detection system according to claim 8, characterized in that: The module M3 also includes a machine learning device that divides the electrical signal into a red zone, a green zone and a yellow zone, and the red zone corresponds to a strong signal, the green zone corresponds to a weak signal, and the yellow zone corresponds to a normal signal.

Images