Acoustic monitoring signal processing method in melting process of laser powder bed and related device

Abstract

The invention discloses a laser powder bed melting process acoustic monitoring signal processing method and a related device. The method comprises the following steps: performing high-frequency physical information data enhancement on an airborne acoustic emission signal through a pre-emphasis filter; performing discrete Fourier transform on the airborne acoustic emission signal after the high-frequency physical information data enhancement to obtain a frequency spectrum sequence signal of the airborne acoustic emission signal; extracting a key low-frequency sequence signal and a key high-frequency sequence signal from the frequency spectrum sequence signal, and reconstructing the key low-frequency sequence signal and the key high-frequency sequence signal according to an original frequency spectrum sequence sequence to obtain a one-dimensional key frequency spectrum sequence signal; converting the one-dimensional key frequency spectrum sequence signal into a two-dimensional key frequency spectrum sequence gray mapping image through an improved gray mapping method; and performing gray mapping feature contrast enhancement on the two-dimensional key frequency spectrum sequence gray mapping image to obtain a key frequency spectrum sequence gray enhancement mapping image. According to the method, physical and reasonable laser powder bed melting acoustic signal defect information expression can be richer and clearer, so that the credibility of defect information expression and the accuracy of defect feature description are improved, and the accuracy of defect acoustic monitoring in the laser powder bed melting process is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of metal additive manufacturing, and specifically relates to a method and related device for processing acoustic monitoring signals during a laser powder bed melting process. Background Art

[0002] Laser powder bed fusion (LPBF) additive manufacturing (AM) process, also known as selective laser melting (SLM), uses a high-power laser beam to selectively melt metal powder materials and accumulate them layer by layer to build metal components designed by computer models. In the past few years, this process has provided a creative example for the design and production of complex precision metal parts. Due to its unique advantages in manufacturing flexibility, material saving, development cycle, complex structure forming and organizational performance, this technology has gained wide attention and application in aerospace, military defense, automotive industry, biomedicine and other industries. Despite the significant advantages of this technology, it still faces severe challenges in terms of quality consistency and process repeatability. The rapid melting and solidification process in the intense interaction between laser and powder in this process will produce extremely complex molten pool dynamics. Unsuitable process parameters will make the fluidity of the molten pool unstable, eventually leading to the formation of defects. In particular, this process is prone to unpredictable porosity defects, which seriously limits its application scope and hinders its wider industrial application. On-site process real-time monitoring is a promising solution and the key to ensure the success of additive manufacturing. Therefore, on-site monitoring of the process is necessary.

[0003] Acoustic monitoring technology has been proven to be a feasible solution and has attracted widespread attention due to its high sensitivity, low cost and excellent equipment compatibility. This technology can not only monitor the dynamics of the molten pool and its volume dynamics in real time during the laser powder bed melting process, but also obtain information about complex physical processes such as melting, solidification, crack propagation and pore generation. It has been widely used in quality monitoring of laser welding processes. At present, the research on acoustic monitoring methods in the field of laser additive manufacturing is limited. Since the laser additive process is a layer-by-layer cumulative forming process of complex geometric shapes that is far more complex than the welding process, the process and defect acoustic signals involved are more complex, and related research is more challenging. The mechanism of acoustic signal generation in the laser powder bed melting process is very complex. Extracting features that reflect target properties from the signal through signal processing methods is the most important part of LPBF process monitoring based on acoustic monitoring technology. Reliable feature extraction through effective acoustic signal processing is the key to establishing the correlation between airborne acoustic emission and laser powder bed melting defects and the prerequisite for accurate monitoring of laser powder bed melting defects. At present, there are still the following problems in acoustic monitoring of the LPBF process: on the one hand, the LPBF acoustic monitoring scenario is very complex, and it is difficult to directly obtain high-quality defect characteristics through the original acoustic signal to achieve reliable defect differentiation; on the other hand, the traditional time-frequency analysis method cannot take into account the information characteristics and the LPBF process-defect-signal correlation mechanism, and it is difficult to achieve an interpretable and accurate expression of the defect feature information. Summary of the invention

[0004] In response to the problems existing in the prior art, the present invention provides a method and related devices for processing acoustic monitoring signals of a laser powder bed melting process, which can make the physically reasonable expression of defect information of laser powder bed melting acoustic signals richer and clearer, thereby improving the credibility of defect information expression and the accuracy of defect feature description, and contributing to the accuracy of defect acoustic monitoring of the laser powder bed melting process.

[0005] In order to solve the above technical problems, the present invention is implemented by the following technical solutions:

[0006] According to a first aspect of the present invention, a method for processing acoustic monitoring signals of a laser powder bed melting process is provided, comprising:

[0007] Acquire the airborne acoustic emission signals generated during the laser powder bed fusion additive manufacturing process;

[0008] Performing high-frequency physical information data enhancement on the airborne acoustic emission signal through a pre-emphasis filter;

[0009] Performing discrete Fourier transformation on the airborne acoustic emission signal after the high-frequency physical information data enhancement to obtain a frequency spectrum sequence signal of the airborne acoustic emission signal;

[0010] Extracting a key low-frequency sequence signal and a key high-frequency sequence signal from the spectrum sequence signal, and reconstructing the key low-frequency sequence signal and the key high-frequency sequence signal according to the original spectrum sequence order to obtain a one-dimensional key spectrum sequence signal;

[0011] Converting the one-dimensional key spectrum sequence signal into a two-dimensional key spectrum sequence grayscale mapping image by an improved grayscale mapping method;

[0012] The two-dimensional key spectrum sequence grayscale mapping image is subjected to grayscale mapping feature contrast enhancement to obtain a key spectrum sequence grayscale enhanced mapping image.

[0013] In a possible implementation manner of the first aspect, extracting the key low-frequency sequence signal and the key high-frequency sequence signal from the spectrum sequence signal is specifically:

[0014]

[0015] The key low-frequency sequence signal and the key high-frequency sequence signal are reconstructed according to the original spectrum sequence order to obtain a one-dimensional key spectrum sequence signal, specifically:

[0016]

[0017] In the formula, k start and k end are the starting frequencies f of the key low-frequency sequence signal or the key high-frequency sequence signal respectively start and the stop frequency f end The corresponding sequence value; L is the key low-frequency sequence signal; H is the key high-frequency sequence signal; f s is the sampling frequency; Z[n] is the one-dimensional key spectrum sequence signal with a time window length of n; Q is the data length of the key low-frequency sequence signal; M is the data length of the key high-frequency sequence signal.

[0018] In a possible implementation manner of the first aspect, converting the one-dimensional key spectrum sequence signal into a two-dimensional key spectrum sequence grayscale mapping image by using an improved grayscale mapping method includes:

[0019] The one-dimensional key spectrum sequence signal is sequentially filled with the rows of the conversion grayscale matrix through the sliding window R and the spectrum sequence scale factor δ, and the matrix size is ensured to be R×R by the zero-filling technology, and the pixel value is always kept in 0-255 by standardization, specifically:

[0020]

[0021] Where P(x, y) is the pixel value of the grayscale mapping image coordinate (x, y) of the two-dimensional key spectrum sequence; round{·} is the rounding function.

[0022] In a possible implementation manner of the first aspect, the pre-emphasis filter is a first-order digital high-pass filter, specifically:

[0023] H[n]=X[n]-αX[n-1]

[0024] Where X[n] is the airborne acoustic emission signal with a time window length of n; α is the pre-emphasis coefficient; H[n] is the airborne acoustic emission signal after the high-frequency physical information data is enhanced with a time window length of n.

[0025] In a possible implementation manner of the first aspect, performing a discrete Fourier transform on the airborne acoustic emission signal after the high-frequency physical information data is enhanced is specifically:

[0026]

[0027] Wherein, k is the sequence value of the spectrum sequence signal X[k] of the airborne acoustic emission signal after the high-frequency physical information data is enhanced; H[n] is the airborne acoustic emission signal after the high-frequency physical information data is enhanced with a time window length of n; N is the length of H[n].

[0028] In a possible implementation manner of the first aspect, the frequency range corresponding to the key low-frequency sequence signal is 5 kHz to 20 kHz, and the frequency range corresponding to the key high-frequency sequence signal is 35 kHz to 50 kHz.

[0029] In a possible implementation manner of the first aspect, performing grayscale mapping feature contrast enhancement on the two-dimensional key spectrum sequence grayscale mapping image includes:

[0030] The Gamma algorithm is used to perform grayscale mapping feature contrast enhancement on the grayscale mapping image of the two-dimensional key spectrum sequence, specifically:

[0031]

[0032] In the formula, I in is the pixel value of the grayscale mapping image of the two-dimensional key spectrum sequence; I out It is the grayscale pixel value of the grayscale enhanced mapping image of the key spectrum sequence after Gamma grayscale mapping; γ is the Gamma correction coefficient.

[0033] According to a second aspect of the present invention, there is provided a laser powder bed melting process acoustic monitoring signal processing device, comprising:

[0034] An acquisition module, used for acquiring air-borne acoustic emission signals generated during the laser powder bed fusion additive manufacturing process;

[0035] A high-frequency enhancement module, used for performing high-frequency physical information data enhancement on the airborne acoustic emission signal through a pre-emphasis filter;

[0036] A transformation module, used for performing a discrete Fourier transformation on the airborne acoustic emission signal after the high-frequency physical information data is enhanced to obtain a frequency spectrum sequence signal of the airborne acoustic emission signal;

[0037] A reconstruction module, used for extracting a key low-frequency sequence signal and a key high-frequency sequence signal from the spectrum sequence signal, and reconstructing the key low-frequency sequence signal and the key high-frequency sequence signal according to the original spectrum sequence order to obtain a one-dimensional key spectrum sequence signal;

[0038] A conversion module, used for converting the one-dimensional key spectrum sequence signal into a two-dimensional key spectrum sequence grayscale mapping image by an improved grayscale mapping method;

[0039] The contrast enhancement module is used to perform grayscale mapping feature contrast enhancement on the two-dimensional key spectrum sequence grayscale mapping image to obtain a key spectrum sequence grayscale enhanced mapping image.

[0040] According to a third aspect of the present invention, there is provided a device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of a method for processing acoustic monitoring signals of a laser powder bed melting process when executing the computer program.

[0041] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of a method for processing acoustic monitoring signals of a laser powder bed melting process.

[0042] Compared with the prior art, the present invention has at least the following beneficial effects:

[0043] The present invention provides a method for processing acoustic monitoring signals of a laser powder bed melting process. The method combines acoustic information features with the LPBF process-defect-signal correlation mechanism to perform high-frequency physical information data enhancement and one-dimensional key spectrum sequence signal reconstruction. On the one hand, the high-frequency physical information data enhancement avoids the loss of key high-frequency information strongly correlated with LPBF acoustic signal defects and the influence of noise; on the other hand, the physical mechanism-driven one-dimensional key spectrum sequence signal reconstruction realizes the data simplicity of the spectrum sequence of air-borne acoustic emission signals, while reducing information redundancy and enhancing the credible representation of defect-related information, which is conducive to the interpretability and accurate expression of defect features. At the same time, the present invention adopts an improved grayscale enhancement mapping strategy to convert the one-dimensional key spectrum sequence signal into a two-dimensional key spectrum sequence grayscale enhancement mapping image with efficient execution, rich physical reasonable defect information expression and key defect strong correlation feature mapping. Not only does it realize the prominent feedback of valuable associated defect information between adjacent pixels in the horizontal and vertical directions through grayscale images on the basis of intuitive expression of physically reasonable defect features, but it also realizes the contrast enhancement of grayscale mapping features, which is conducive to improving the accuracy of acoustic monitoring.

[0044] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the specific implementation modes of the present invention, the drawings required for use in the description of the specific implementation modes will be briefly introduced below. Obviously, the drawings described below are some implementation modes of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 This is a flow chart of a method for processing acoustic monitoring signals during laser powder bed melting according to an embodiment of the present invention;

[0047] Figure 2 The air-borne acoustic emission signal and its spectrum diagram of the laser powder bed melting process collected by the air-borne acoustic emission sensor in the embodiment of the present invention;

[0048] Figure 3 A schematic diagram of a process of reconstructing a key spectrum sequence signal in an embodiment of the present invention;

[0049] Figure 4 Schematic diagram of conversion of grayscale image of key spectrum sequence in an embodiment of the present invention;

[0050] Figure 5 It is a grayscale enhanced mapping image of the key spectrum sequence of different defect signals in the embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 the present invention.

[0052] like Figure 1 As shown, an embodiment of the present invention provides a method for processing acoustic monitoring signals of a laser powder bed melting process, which specifically includes the following steps:

[0053] S1. Acquire the airborne acoustic emission signal generated during the laser powder bed fusion additive manufacturing process.

[0054] Specifically, an acoustic sensor array is installed near the laser powder bed fusion additive manufacturing equipment to capture and record the air-borne acoustic emission signals generated during the entire additive manufacturing process. The air-borne acoustic emission signals contain rich information on the melt pool dynamics and potential defect generation.

[0055] Exemplarily, the air-transmitted acoustic emission signal generated during the laser powder bed fusion additive manufacturing process is collected by an AM4I air-coupled acoustic emission sensor produced by PAC Corporation of the United States.

[0056] S2. Perform high-frequency physical information data enhancement on the airborne acoustic emission signal through a pre-emphasis filter.

[0057] That is to say, the collected airborne acoustic emission signal is input into the pre-emphasis filter, and the purpose of the pre-emphasis filter is to enhance the high-frequency part of the airborne acoustic emission signal to highlight the high-frequency physical information that may be relatively weak in the original signal but is important for defect identification.

[0058] In one embodiment, the pre-emphasis filter is implemented by a first-order digital high-pass filter, and its transfer function is specifically in the form of:

[0059] H[n]=X[n]-αX[n-1]

[0060] Where X[n] is the airborne acoustic emission signal with a time window length of n; α is the pre-emphasis coefficient, and the value of α is 0.98; H[n] is the airborne acoustic emission signal after the high-frequency physical information data is enhanced with a time window length of n.

[0061] S3. Performing discrete Fourier transformation on the airborne acoustic emission signal after the high-frequency physical information data is enhanced to obtain a frequency spectrum sequence signal of the airborne acoustic emission signal.

[0062] That is to say, the airborne acoustic emission signal after pre-emphasis processing is subjected to discrete Fourier transform, which is converted from the time domain to the frequency domain to obtain a spectrum sequence signal.

[0063] Specifically, the calculation formula of discrete Fourier transform is:

[0064]

[0065] Wherein, k is the sequence value of the spectrum sequence signal X[k] of the airborne acoustic emission signal after the high-frequency physical information data is enhanced; N is the length of H[n].

[0066] S4. Extracting a key low-frequency sequence signal and a key high-frequency sequence signal from the spectrum sequence signal, and reconstructing the key low-frequency sequence signal and the key high-frequency sequence signal according to the original spectrum sequence order to obtain a one-dimensional key spectrum sequence signal.

[0067] In this embodiment, the frequency range corresponding to the key low-frequency sequence signal is 5 kHz to 20 kHz, and the frequency range corresponding to the key high-frequency sequence signal is 35 kHz to 50 kHz.

[0068] Specifically, in the obtained spectrum sequence signals, by analyzing the signal frequency characteristics, the key low-frequency and high-frequency sequence signals that are highly correlated with the stability of the molten pool and the generation of defects are identified. Subsequently, these key low-frequency and high-frequency sequence signals are reconstructed according to the order of the original spectrum sequence to form a one-dimensional key spectrum sequence signal, accurately identifying the spectrum components that are important for defect identification.

[0069] In one embodiment, a key low-frequency sequence signal and a key high-frequency sequence signal are extracted from the spectrum sequence signal as follows:

[0070]

[0071]

[0072]

[0073] In the formula, k start and k end are the starting frequencies f of the key low-frequency sequence signal or the key high-frequency sequence signal respectively start and the stop frequency f end The corresponding sequence value; L is the key low-frequency sequence signal; H is the key high-frequency sequence signal; f s is the sampling frequency.

[0074] In one embodiment, the key low-frequency sequence signal and the key high-frequency sequence signal are reconstructed according to the original spectrum sequence order to obtain a one-dimensional key spectrum sequence signal, specifically:

[0075]

[0076] Wherein, Z[n] is a one-dimensional key spectrum sequence signal with a time window length of n; Q is the data length of the key low-frequency sequence signal; and M is the data length of the key high-frequency sequence signal.

[0077] S5. Convert the one-dimensional key spectrum sequence signal into a two-dimensional key spectrum sequence grayscale mapping image by an improved grayscale mapping method. The two-dimensional key spectrum sequence grayscale mapping image not only retains the important information in the original signal, but also displays the spectrum characteristics of the signal in an intuitive way, which is beneficial to subsequent defect recognition and monitoring.

[0078] Specifically, the improved grayscale mapping method is to fill the rows of the conversion grayscale matrix with the one-dimensional key spectrum sequence signal through the sliding window R and the spectrum sequence scale factor δ, and ensure that the matrix size is R×R by zero filling technology, and perform standardization so that its pixel value is always kept in 0-255. Its mathematical expression is as follows:

[0079]

[0080] Where P(x, y) is the pixel value of the grayscale mapping image coordinate (x, y) of the two-dimensional key spectrum sequence; round{·} is the rounding function.

[0081] More specifically, the size of the sliding window is defined as R, and the window will slide on the one-dimensional key spectrum sequence signal. Each time it slides, the signal value in the window will be selected to fill the grayscale matrix. At the same time, a spectrum sequence scale factor δ is defined, which is used to adjust the scale relationship when mapping from the one-dimensional key spectrum sequence signal to the two-dimensional key spectrum sequence grayscale mapping image to ensure that the signal information is reasonably displayed on the image. The one-dimensional key spectrum sequence signal is traversed by the sliding window, and the signal values ​​in the window are filled into the corresponding rows of the grayscale matrix in turn each time. If the length of the one-dimensional key spectrum sequence signal is not enough to completely fill the entire grayscale matrix, the zero padding technique (i.e., adding zero values ​​at the end of the grayscale matrix) is used to ensure that the size of the grayscale matrix reaches the preset R×R size.

[0082] Since the amplitude range of the one-dimensional key spectrum sequence signal may exceed the pixel value range of 0-255, the grayscale matrix is ​​normalized. The purpose of the normalization process is to map each pixel value in the grayscale matrix to the range of 0-255 for subsequent image display and processing.

[0083] S6. Perform grayscale mapping feature contrast enhancement on the two-dimensional key spectrum sequence grayscale mapping image to obtain a key spectrum sequence grayscale enhanced mapping image.

[0084] That is, the obtained two-dimensional key spectrum sequence grayscale mapping image is subjected to grayscale mapping feature contrast enhancement processing to enhance the key feature information in the image.

[0085] Preferably, the grayscale mapping feature contrast enhancement is performed on the grayscale mapping image of the two-dimensional key spectrum sequence using a Gamma algorithm, specifically:

[0086]

[0087] In the formula, I in is the pixel value of the grayscale mapping image of the two-dimensional key spectrum sequence; I out It is the grayscale pixel value of the grayscale enhanced mapping image of the key spectrum sequence after Gamma grayscale mapping; γ is the Gamma correction coefficient, which determines the degree of nonlinearity of the mapping.

[0088] Example:

[0089] In this embodiment, an airborne acoustic emission sensor is used to collect the airborne acoustic emission signal generated during the laser powder bed melting experiment. The experiment uses 316L stainless steel powder as the original metal powder material for printing, and sets 8 groups of pore defect simulation parts with different porosities. The defect simulation part has a specification of 10mm×10mm×10mm. In the experiment, the data acquisition frequency of the airborne acoustic emission sensor is set to 100kHz, and the airborne acoustic emission sensor is installed in a position suitable for acoustic signal acquisition.

[0090] In this embodiment, according to step S1 of the present invention, an AM4I air-coupled acoustic emission sensor produced by PAC Corporation of the United States is used to collect air-transmitted acoustic emission signals generated during the laser powder bed melting additive manufacturing process. The time domain waveform and spectrum of the collected air-transmitted acoustic emission signals are shown in FIG. Figure 2 As shown. Figure 2 It can be found that the spectrum information of the defect signal is mainly distributed in the key low frequency band of 5-20kHz and the key high frequency band of 35-50kHz. The special key high frequency band information can effectively feedback the dynamic changes of the defect.

[0091] According to the above step S2, the air-borne acoustic emission signal of the laser powder bed melting process collected by the sensor with a window length n of 4096 is subjected to high-frequency physical information data enhancement through a pre-emphasis filter with a pre-emphasis coefficient α=0.98, and the air-borne acoustic emission signal sample after high-frequency physical information data enhancement is obtained. High-frequency physical information data enhancement can effectively avoid the loss of information of the high-frequency components of the signal with high attenuation characteristics during the air propagation process, and reduce the adverse effects of low-frequency noise on defect monitoring.

[0092] According to the above step S3, the airborne acoustic emission signal samples after the high-frequency physical information data enhancement with a data length of 4096 are subjected to discrete Fourier transform to obtain a frequency spectrum sequence signal of the airborne acoustic emission sample signal.

[0093] According to the above step S4, Figure 3 As shown in the figure, the key low-frequency sequence signal L with a frequency range of 5kHz to 20kHz and the key high-frequency sequence signal H with a frequency range of 35kHz to 50kHz are extracted from the spectrum sequence signal of the airborne acoustic emission sample signal, and reconstructed in the order of the spectrum sequence to obtain a one-dimensional key spectrum sequence signal Z. The constructed key spectrum sequence signal not only effectively retains the internal data characteristics of the airborne acoustic emission signal in the LPBF process and its original spectrum information structure, but also realizes the data simplification of the spectrum sequence of the airborne acoustic emission signal based on the physically reasonable LPBF acoustic signal defect information expression characteristics, and realizes the interpretable expression of the defect-related information while reducing the information redundancy.

[0094] According to the above step S5, Figure 4 As shown in the figure, the one-dimensional key spectrum sequence signal is sequentially filled with the rows of the conversion grayscale matrix under the control of the sliding window R=224 and the spectrum sequence scale factor δ=4. The size of the grayscale matrix is ​​ensured to be 224×224 by zero filling technology, and the grayscale pixel value is always kept at 0-255 by standardized calculation processing, and finally a two-dimensional key spectrum sequence grayscale mapping image is obtained. This operation realizes the associated representation of the key spectrum sequence in different gradient directions, which is conducive to a more comprehensive description of the complex changes in the characteristics of different defect signals. On the one hand, the fixed frequency scale in the horizontal gradient direction can effectively feedback the local dynamic change characteristics of the key spectrum sequence within the detail frequency range. On the other hand, the spectrum in the vertical gradient direction realizes the dimensional span from low frequency to high frequency, which can effectively feedback the key frequency component characteristics most relevant to the molten pool sound, and through the image representation method of data reuse, the defect feature expression loss caused by signal distortion or insufficient feature information is alleviated to the greatest extent.

[0095] According to the above step S6, the two-dimensional key spectrum sequence grayscale mapping image is subjected to grayscale mapping feature contrast enhancement through the Gamma algorithm to obtain a key spectrum sequence grayscale enhanced mapping image, wherein the Gamma correction coefficient γ is 0.6. The nonlinear brightness adjustment method provided by the Gamma algorithm can optimize the visual features of the grayscale image as a carrier of defect information, which helps to improve the recognition accuracy of the defect monitoring deep learning model. Figure 5 The grayscale enhanced mapping images of the key spectrum sequences of different defect signals are displayed. It can be found that the grayscale enhanced mapping images of the key spectrum sequences provide a clear and detailed characterization of the information aggregation characteristics of the key frequency bands that are strongly correlated with the defects, and realize the expression of the local dynamic differences of the key spectrum sequence information related to the defects.

[0096] In this embodiment, based on the grayscale enhanced mapping images of the key spectrum sequence of different defect signals, a data set is constructed, which includes a training set of 70% of the grayscale enhanced mapping images of the key spectrum sequence and a test set of 30% of the grayscale enhanced mapping images of the key spectrum sequence. AlexNet and MS-CNN models are selected as defect monitoring deep learning models, and the training set containing 70% of the grayscale enhanced mapping images of the key spectrum sequence is used for the training of the defect monitoring deep learning model, and the test set containing 30% of the grayscale enhanced mapping images of the key spectrum sequence is used for the verification of the defect monitoring deep learning model, so as to obtain the final defect monitoring deep learning model.

[0097] As shown in Table 1, the defect recognition accuracy results of different defect monitoring deep learning models used in this embodiment are shown. It can be seen that the recognition accuracy of 8 types of defects using AlexNet and MS-CNN models is above 97%, and the single sample response time of the model is less than 1ms, which has a better defect monitoring effect.

[0098] Table 1 Defect recognition accuracy results of different defect monitoring deep learning models

[0099]

[0100] It can be seen that after being processed by the acoustic monitoring signal processing method of the laser powder bed melting process proposed in the present invention, the acoustic signal of the laser powder bed melting process can be efficiently applied to the reliable distinction of pore defects in the laser powder bed melting process with complex working conditions, and the interpretable and accurate expression of the defect characteristic information of the acoustic signal of the laser powder bed melting process is achieved. In combination with the deep learning model, high-accuracy in-situ acoustic monitoring of defects in the laser powder bed melting additive manufacturing process is completed, which has good engineering applicability.

[0101] In another embodiment of the present invention, a laser powder bed melting process acoustic monitoring signal processing device is provided, which specifically includes the following modules:

[0102] The acquisition module is used to acquire the air-transmitted acoustic emission signal generated during the laser powder bed fusion additive manufacturing process.

[0103] The high-frequency enhancement module is used to enhance the high-frequency physical information data of the air-borne acoustic emission signal through a pre-emphasis filter.

[0104] The transformation module is used to perform discrete Fourier transformation on the airborne acoustic emission signal after the high-frequency physical information data is enhanced to obtain a frequency spectrum sequence signal of the airborne acoustic emission signal.

[0105] The reconstruction module is used to extract the key low-frequency sequence signal and the key high-frequency sequence signal from the spectrum sequence signal, and reconstruct the key low-frequency sequence signal and the key high-frequency sequence signal according to the original spectrum sequence order to obtain a one-dimensional key spectrum sequence signal.

[0106] The conversion module is used to convert the one-dimensional key spectrum sequence signal into a two-dimensional key spectrum sequence grayscale mapping image by using an improved grayscale mapping method.

[0107] The contrast enhancement module is used to perform grayscale mapping feature contrast enhancement on the two-dimensional key spectrum sequence grayscale mapping image to obtain a key spectrum sequence grayscale enhanced mapping image.

[0108] All relevant contents of each step involved in the aforementioned embodiment of a method for processing acoustic monitoring signals of a laser powder bed melting process can be referred to the functional description of the functional module corresponding to a device for processing acoustic monitoring signals of a laser powder bed melting process in the embodiment of the present invention, and will not be repeated here. The division of modules in the embodiment of the present invention is schematic and is only a logical functional division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present invention may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules.

[0109] In another embodiment of the present invention, a computer device is provided, the computer device including a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of a method for processing acoustic monitoring signals of a laser powder bed melting process.

[0110] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It can be understood that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the above-mentioned embodiment in a method for processing acoustic monitoring signals of a laser powder bed melting process.

[0111] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0112] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0113] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0114] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0115] In the present invention, the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the described specific features, structures, materials or characteristics may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0116] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for processing acoustic monitoring signals during laser powder bed melting, characterized in that: include: Acquire the airborne acoustic emission signals generated during the laser powder bed fusion additive manufacturing process; Performing high-frequency physical information data enhancement on the airborne acoustic emission signal through a pre-emphasis filter; Performing discrete Fourier transformation on the airborne acoustic emission signal after the high-frequency physical information data enhancement to obtain a frequency spectrum sequence signal of the airborne acoustic emission signal; Extracting a key low-frequency sequence signal and a key high-frequency sequence signal from the spectrum sequence signal, and reconstructing the key low-frequency sequence signal and the key high-frequency sequence signal according to the original spectrum sequence order to obtain a one-dimensional key spectrum sequence signal; Converting the one-dimensional key spectrum sequence signal into a two-dimensional key spectrum sequence grayscale mapping image by an improved grayscale mapping method; The two-dimensional key spectrum sequence grayscale mapping image is subjected to grayscale mapping feature contrast enhancement to obtain a key spectrum sequence grayscale enhanced mapping image.

2. The method for processing acoustic monitoring signals of a laser powder bed melting process according to claim 1, characterized in that: The extracting of the key low-frequency sequence signal and the key high-frequency sequence signal from the spectrum sequence signal is specifically: The key low-frequency sequence signal and the key high-frequency sequence signal are reconstructed according to the original spectrum sequence order to obtain a one-dimensional key spectrum sequence signal, specifically: In the formula, k start and k end are the starting frequencies f of the key low-frequency sequence signal or the key high-frequency sequence signal respectively start and the stop frequency f end The corresponding sequence value; L is the key low-frequency sequence signal; H is the key high-frequency sequence signal; f s is the sampling frequency; Z[n] is the one-dimensional key spectrum sequence signal with a time window length of n; Q is the data length of the key low-frequency sequence signal; M is the data length of the key high-frequency sequence signal.

3. The method for processing acoustic monitoring signals of a laser powder bed melting process according to claim 2, characterized in that: The step of converting the one-dimensional key spectrum sequence signal into a two-dimensional key spectrum sequence grayscale mapping image by an improved grayscale mapping method comprises: The one-dimensional key spectrum sequence signal is sequentially filled with the rows of the conversion grayscale matrix through the sliding window R and the spectrum sequence scale factor δ, and the matrix size is ensured to be R×R by the zero-filling technology, and the pixel value is always kept in 0-255 by standardization, specifically: Where P(x, y) is the pixel value of the grayscale mapping image coordinate (x, y) of the two-dimensional key spectrum sequence; round{·} is the rounding function.

4. The method for processing acoustic monitoring signals of a laser powder bed melting process according to claim 1, characterized in that: The pre-emphasis filter is a first-order digital high-pass filter, specifically: H[n]=X[n]-αX[n-1] Where X[n] is the airborne acoustic emission signal with a time window length of n; α is the pre-emphasis coefficient; H[n] is the airborne acoustic emission signal after the high-frequency physical information data is enhanced with a time window length of n.

5. The method for processing acoustic monitoring signals of a laser powder bed melting process according to claim 1, characterized in that: The step of performing discrete Fourier transformation on the airborne acoustic emission signal after the high-frequency physical information data is enhanced is specifically as follows: Wherein, k is the sequence value of the spectrum sequence signal X[k] of the airborne acoustic emission signal after the high-frequency physical information data is enhanced; H[n] is the airborne acoustic emission signal after the high-frequency physical information data is enhanced with a time window length of n; N is the length of H[n].

6. The method for processing acoustic monitoring signals of a laser powder bed melting process according to claim 1, characterized in that: The frequency range corresponding to the key low-frequency sequence signal is 5kHz to 20kHz, and the frequency range corresponding to the key high-frequency sequence signal is 35kHz to 50kHz.

7. The method for processing acoustic monitoring signals of a laser powder bed melting process according to claim 1, characterized in that: The step of performing grayscale mapping feature contrast enhancement on the two-dimensional key spectrum sequence grayscale mapping image comprises: The Gamma algorithm is used to perform grayscale mapping feature contrast enhancement on the grayscale mapping image of the two-dimensional key spectrum sequence, specifically: In the formula, I in is the pixel value of the grayscale mapping image of the two-dimensional key spectrum sequence; I out It is the grayscale pixel value of the grayscale enhanced mapping image of the key spectrum sequence after Gamma grayscale mapping; γ is the Gamma correction coefficient.

8. A laser powder bed melting process acoustic monitoring signal processing device, characterized in that: include: An acquisition module, used for acquiring air-borne acoustic emission signals generated during the laser powder bed fusion additive manufacturing process; A high-frequency enhancement module, used for performing high-frequency physical information data enhancement on the airborne acoustic emission signal through a pre-emphasis filter; A transformation module, used for performing a discrete Fourier transformation on the airborne acoustic emission signal after the high-frequency physical information data is enhanced to obtain a frequency spectrum sequence signal of the airborne acoustic emission signal; A reconstruction module, used for extracting a key low-frequency sequence signal and a key high-frequency sequence signal from the spectrum sequence signal, and reconstructing the key low-frequency sequence signal and the key high-frequency sequence signal according to the original spectrum sequence order to obtain a one-dimensional key spectrum sequence signal; A conversion module, used for converting the one-dimensional key spectrum sequence signal into a two-dimensional key spectrum sequence grayscale mapping image by an improved grayscale mapping method; The contrast enhancement module is used to perform grayscale mapping feature contrast enhancement on the two-dimensional key spectrum sequence grayscale mapping image to obtain a key spectrum sequence grayscale enhanced mapping image.

9. A device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a method for processing acoustic monitoring signals of a laser powder bed melting process as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a method for processing acoustic monitoring signals of a laser powder bed melting process as described in any one of claims 1 to 7 are implemented.

Images