Laser near-net forming working distance monitoring method and system based on data fusion

Abstract

The invention discloses a laser near-net forming working distance monitoring method and system based on data fusion, and the method comprises the steps: obtaining an acoustic emission signal and a molten pool temperature signal, and carrying out the data preprocessing and vector fusion processing, and obtaining a fusion signal feature vector of laser near-net forming; performing data training on the Gaussian naive Bayesian regression model through the fusion signal feature vector of laser near-net shaping to obtain a trained Gaussian naive Bayesian regression model; and performing laser near-net forming working distance monitoring on the acoustic emission signal and the molten pool temperature signal based on the trained Gaussian naive Bayes regression model to obtain a laser near-net forming working distance value. By using the laser near-net forming working distance monitoring method, the precision of laser near-net forming working distance monitoring can be improved by adopting a feature level signal fusion method without being affected by shielding. The laser near-net forming working distance monitoring method and system based on data fusion can be widely applied to the technical field of intelligent man-machine interaction.

Description

Technical Field

[0001] The present invention relates to the field of intelligent artificial interaction technology, and in particular to a laser near-net-shape working distance monitoring method and system based on data fusion. Background Art

[0002] Laser near-net forming is a type of additive manufacturing technology. The laser creates a molten pool in the area to be added, and continuously delivers metal powder or filamentary materials, depositing layer by layer to form high-performance three-dimensional parts. During the manufacturing process, due to the accumulation of thermal stress, the surface of the part to be added is prone to defects such as warping or collapse. If the working path of the robot arm remains unchanged, the actual working distance and theoretical distance between the optical head and the part to be added will deviate, affecting the quality of the additive and material utilization rate. In severe cases, there may even be interference between the working path of the robot arm and the part to be added, causing damage to the equipment and the parts. Therefore, in the process of laser near-net forming, real-time monitoring of the working distance between the optical head and the part to be added and timely adjustment of the moving path of the robot arm are of great significance to improving the product quality and production safety of laser near-net forming.

[0003] The existing combination of multiple rangefinder digital cameras can accurately measure the working distance between the optical head and the part to be added, but this measurement method has certain requirements on lighting conditions and is easily affected by occlusion. In summary, the technical problems existing in the relevant technology need to be improved. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a laser near-net-shape working distance monitoring method and system based on data fusion, which can improve the accuracy of laser near-net-shape working distance monitoring by adopting a feature-level signal fusion method without being affected by occlusion.

[0005] The first technical solution adopted by the present invention is: a laser near-net-shape working distance monitoring method based on data fusion, comprising the following steps:

[0006] Acquire the acoustic emission signal and the molten pool temperature signal during the laser near-net forming process;

[0007] The acoustic emission signal and the molten pool temperature signal are subjected to data preprocessing and vector fusion processing to obtain the fusion signal feature vector of laser near-net forming;

[0008] The Gaussian Naive Bayesian regression model is trained with data through the fusion signal feature vector of the laser near-net-shaped process to obtain the trained Gaussian Naive Bayesian regression model;

[0009] Based on the trained Gaussian naive Bayesian regression model, the laser near-net forming working distance is monitored by the acoustic emission signal and the molten pool temperature signal, and the laser near-net forming working distance value is obtained.

[0010] Further, the step of obtaining the acoustic emission signal during the laser near-net forming process and the molten pool temperature signal during the laser near-net forming process specifically includes:

[0011] The acoustic emission probe is placed at the bottom of the substrate to be added, and an ultrasonic coupling agent is applied between the acoustic emission probe and the bottom of the substrate to be added, and the acoustic emission signal in the laser near-net forming process is obtained according to a preset sampling rate;

[0012] The two-color pyrometer is coaxially arranged with the laser path of the molten pool, and a trigger start signal is set to obtain the molten pool temperature signal during the laser near-net forming process.

[0013] Further, the step of performing data preprocessing and vector fusion processing on the acoustic emission signal and the molten pool temperature signal to obtain the fusion signal feature vector of laser near-net forming specifically includes:

[0014] Performing bandpass filtering on the acoustic emission signal to obtain a filtered acoustic emission signal;

[0015] The filtered acoustic emission signal and the molten pool temperature signal are respectively subjected to signal window processing to obtain a segmented acoustic emission signal and a segmented molten pool temperature signal;

[0016] The segmented acoustic emission signal and the segmented molten pool temperature signal are respectively calculated in time domain and frequency domain to obtain the acoustic signal feature vector and the molten pool temperature signal feature vector;

[0017] The acoustic signal feature vector and the molten pool temperature signal feature vector are vector-fused and normalized to obtain the fused signal feature vector of laser near-net forming.

[0018] Furthermore, the expressions for performing signal window processing on the filtered acoustic emission signal and the molten pool temperature signal are specifically as follows:

[0019]

[0020] In the above formula, hanning(·) represents the hanning window function, M represents the length of the window, and n represents the input signal data.

[0021] Furthermore, the time domain characteristics and frequency domain characteristics specifically include mean, peak, absolute mean, root mean square, absolute standard deviation, envelope standard deviation, kurtosis, skewness, average power, spectral kurtosis, spectral skewness and spectral center of gravity.

[0022] Furthermore, the step of performing data training on the Gaussian Naive Bayesian regression model by using the fusion signal feature vector of the laser near-net shaping to obtain the trained Gaussian Naive Bayesian regression model specifically includes:

[0023] Assigning data labels to the fusion signal feature vector of the laser near-net shaping to obtain a fusion signal feature vector with a label, wherein the data label represents a working distance value between the optical head and the part to be added;

[0024] Construct a Gaussian Naive Bayes regression model;

[0025] The fused signal feature vector with labels is input into the Gaussian Naive Bayes regression model for category prediction to obtain the predicted working distance value;

[0026] Determine a distance deviation value according to the predicted working distance value and the working distance value between the optical head and the part to be added;

[0027] Based on the distance deviation value, the model performance is evaluated by the root mean square error and the coefficient of determination, and the trained Gaussian naive Bayes regression model is output.

[0028] Furthermore, the expression of the Gaussian Naive Bayes regression model is specifically as follows:

[0029]

[0030] In the above formula, y pred represents the regression prediction value, P(y i |X) indicates that the feature vector X belongs to category y i The probability of y i Represents the category label, n represents the input signal data, and i represents the i-th category label.

[0031] The second technical solution adopted by the present invention is: a laser near-net-shape working distance monitoring system based on data fusion, comprising:

[0032] The first module is used to obtain the acoustic emission signal and the molten pool temperature signal in the laser near-net forming process;

[0033] The second module is used to perform data preprocessing and vector fusion processing on the acoustic emission signal and the molten pool temperature signal to obtain the fusion signal feature vector of laser near-net forming;

[0034] The third module is used to perform data training on the Gaussian Naive Bayesian regression model through the fusion signal feature vector of the laser near-net forming to obtain the trained Gaussian Naive Bayesian regression model;

[0035] The fourth module is used to monitor the laser near-net forming working distance based on the trained Gaussian naive Bayes regression model for the acoustic emission signal and the molten pool temperature signal to obtain the laser near-net forming working distance value.

[0036] The beneficial effects of the method and system of the present invention are as follows: by acquiring the acoustic emission signal and the molten pool temperature signal in the laser near-net forming process, the present invention is not affected by occlusion compared with the working distance monitoring based on paraxial vision, and can support the working distance detection of application scenarios such as inner wall repair, and then perform data preprocessing and vector fusion processing on the acoustic emission signal and the molten pool temperature signal to obtain the fusion signal feature vector of the laser near-net forming, and perform data training on the Gaussian naive Bayes regression model through the fusion signal feature vector of the laser near-net forming to obtain the trained Gaussian naive Bayes regression model, and through the Gaussian naive Bayes regression model, the working distance in the laser near-net forming process can be monitored in real time, and further adopting the feature-level signal fusion method, the signal stability is better than that of a single signal, and finally based on the trained Gaussian naive Bayes regression model, the acoustic emission signal and the molten pool temperature signal are used to monitor the laser near-net forming working distance to obtain the laser near-net forming working distance value, thereby improving the accuracy of the laser near-net forming working distance monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flow chart of the steps of the laser near-net-shape working distance monitoring method based on data fusion of the present invention;

[0038] Figure 2 It is a structural block diagram of the laser near-net-shape working distance monitoring system based on data fusion of the present invention;

[0039] Figure 3 It is a schematic diagram of laser near-net-shape working distance monitoring provided by a specific embodiment of the present invention;

[0040] Figure 4 It is a schematic diagram of a device for obtaining acoustic emission signals and molten pool temperature signals provided in a specific embodiment of the present invention. DETAILED DESCRIPTION

[0041] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The step numbers in the following embodiments are only provided for the convenience of explanation and description, and the order between the steps is not limited in any way. The execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0042] Reference Figure 1 The present invention provides a laser near-net-shape working distance monitoring method based on data fusion, the method comprising the following steps:

[0043] S100, acquiring an acoustic emission signal and a molten pool temperature signal during a laser near-net forming process;

[0044] Specifically, an acoustic emission probe is placed at the bottom of the substrate to be added, and an ultrasonic coupling agent is applied between the acoustic emission probe and the bottom of the substrate to be added, and an acoustic emission signal in the laser near-net forming process is obtained according to a preset sampling rate;

[0045] In this embodiment, if Figure 4 As shown in the figure, the acoustic emission equipment is used to collect the acoustic emission signals of several groups of laser near-net shaping single-channel experiments at different working distances, and the actual working distance of the experiment is recorded. The working distance of the single-channel experiment is designed to be between 12mm and 24mm. The acoustic emission probe is clamped on the bottom of the substrate to be added with a pre-tightening clamp, and an appropriate amount of ultrasonic coupling agent is applied to the contact surface. The sampling rate is set to sample_rate_AE, where sample_rate_AE is greater than twice the highest frequency in the frequency response range of the acoustic emission equipment. According to the Nyquist sampling theorem, during the conversion of analog / digital signals, when the sampling frequency sample_rate_AE is greater than twice the highest frequency fmax in the signal (sample_rate_AE>=2fmax), the digital signal after sampling completely retains the information in the original signal, that is, the sampling rate of the data acquisition card needs to be set. According to the sampling theorem, the sampling rate of the data acquisition card needs to be greater than twice the maximum value of the frequency response range of the acoustic emission probe. In industrial applications, 2.5 times is usually used to ensure the reliability of the signal. Specifically, the acoustic emission signal of the laser near-net shaping process is measured using an acoustic emission device, and the sampling rate is set to 1Mps.

[0046] The two-color pyrometer is coaxially arranged with the laser path of the molten pool, and a trigger start signal is set to obtain the molten pool temperature signal during the laser near-net forming process.

[0047] In this embodiment, a colorimetric pyrometer device is used to collect the molten pool temperature signal of the laser near-net forming process. The two-color pyrometer and the aforementioned acoustic emission device use the same trigger signal to start data collection, and the sampling rate is the same as the aforementioned acoustic emission device, both of which are 1Mps. The acoustic emission sensor contact-connected to the part to be added and the coaxially installed two-color pyrometer have no requirements for lighting conditions and are not affected by obstructions. They are suitable for industrial application scenarios with obstructions such as inner wall repair. The two-color pyrometer is coaxially arranged with the laser route of the molten pool, indicating that the signal path of the pyrometer, that is, the route from the molten pool to the pyrometer, coincides with the laser action route.

[0048] S200, performing data preprocessing and vector fusion processing on the acoustic emission signal and the molten pool temperature signal to obtain a fusion signal feature vector of laser near-net forming;

[0049] S210, performing bandpass filtering on the acoustic emission signal to obtain a filtered acoustic emission signal;

[0050] In this embodiment, the acoustic emission signal is band-pass filtered to improve the signal-to-noise ratio, and the pass frequency range of the band-pass filter is P1 to P2, where P1 is the lowest frequency 35kHz in the frequency response range of the acoustic emission device, and P2 is the highest frequency 400kHz in the frequency response range of the acoustic emission device.

[0051] S220, performing signal windowing processing on the filtered acoustic emission signal and the molten pool temperature signal respectively to obtain a segmented acoustic emission signal and a segmented molten pool temperature signal;

[0052] In this embodiment, the filtered acoustic emission signal is divided into acoustic signal windows with consistent time intervals, and the molten pool temperature signal is divided into molten pool temperature signal windows with consistent time intervals, wherein the length of the divided window is M, the overlap rate is 0.5, and the window function uses the Hanning window, and the specific function is as follows:

[0053]

[0054] In the above formula, hanning(·) represents the hanning window function, M represents the length of the window, and n represents the input signal data.

[0055] In addition, it should be noted that the actual time corresponding to the length of the molten pool temperature signal window must be the same as the time corresponding to the length of an acoustic emission signal window.

[0056] More specifically, when a material or component is deformed or cracked during the stress process, the strain energy is released in the form of elastic waves, which is called acoustic emission. Using acoustic emission equipment to monitor the changes in elastic waves on the surface of the part to be added can reflect the collision between the powder and the surface to be added and the fluctuation of the molten pool; the colorimetric pyrometer can obtain the precise temperature of the heated object based on the ratio of the radiation intensity at two wavelengths in the radiation emitted by the heated object. Using a colorimetric pyrometer to monitor the coaxial molten pool can accurately reflect the highest temperature of the molten pool. When the working distance between the optical head and the part to be added changes, the powder flow distribution and the molten pool energy density change accordingly. The acoustic emission equipment and the pyrometer equipment are used to receive the acoustic emission signal and the molten pool temperature signal of the laser near-net forming process, and the working distance can be monitored in real time. Since the original signals of the acoustic emission equipment and the pyrometer only present their respective physical information in the form of time series, the working distance cannot be directly identified. The time domain and frequency domain feature statistics of the windowed signal can reduce the amount of data to be processed and retain most of the effective information. The Gaussian Naive Bayes regression model can perform statistical regression on the signal according to the signal characteristics to realize the working distance monitoring of the laser near-net forming process. Compared with the working distance monitoring based on paraxial vision, the acoustic emission equipment and the pyrometer equipment are not affected by occlusion, and can support the working distance detection of application scenarios such as inner wall repair, and the fused signal is more reliable than a single signal.

[0057] S230, respectively calculating the time domain characteristics and the frequency domain characteristics of the segmented acoustic emission signal and the segmented molten pool temperature signal to obtain an acoustic signal feature vector and a molten pool temperature signal feature vector;

[0058] In this embodiment, 12 time domain features and frequency domain features are calculated in each acoustic signal window to obtain an acoustic signal feature vector with a dimension of 1*12, and 12 time domain features and frequency domain features are calculated in each molten pool temperature signal window to obtain a molten pool temperature signal feature vector with a dimension of 1*12.

[0059] 12 time domain and frequency domain features, including mean, peak, absolute mean, root mean square (RMS), absolute standard deviation, envelope standard deviation, kurtosis, skewness, average power, spectrum kurtosis, spectrum skewness and spectrum center of gravity. The calculation formulas and their physical meanings of each feature are shown in Table 1, where x i is the i-th sample value in the data window, N is the length of the data window, is the absolute mean, e i =|h(x i )|,h(x i ) is the signal envelope after Hilbert transform, is the mean of the envelope, s is the standard deviation, and f k is the frequency, S(f k ) is the intensity of the spectrum, S is the mean of the spectrum, δs is the standard deviation of the spectrum.

[0060] Table 1 Calculation formula data table of each feature

[0061]

[0062]

[0063] S240, performing vector fusion and normalization processing on the acoustic signal feature vector and the molten pool temperature signal feature vector to obtain a fusion signal feature vector of laser near-net forming.

[0064] In this embodiment, the acoustic signal feature vector corresponding to the same period of time is merged with the molten pool temperature signal feature vector in the feature dimension direction to obtain a feature vector of the fused signal, and normalization is performed for each type of feature in the feature matrix composed of the fused feature vector to obtain a normalized fused signal feature vector.

[0065] The normalized expression is as follows:

[0066]

[0067] In the above formula, max represents the maximum value of a feature in the data set, min represents the minimum value of a feature in the data set, x represents a feature value, and x' represents the normalized feature value.

[0068] S300, performing data training on a Gaussian naive Bayesian regression model through a fusion signal feature vector of laser near-net forming to obtain a trained Gaussian naive Bayesian regression model;

[0069] Specifically, a data label is assigned to the fusion signal feature vector of laser near-net forming to obtain a fusion signal feature vector with a label, wherein the data label represents the working distance value between the optical head and the part to be added; a Gaussian naive Bayes regression model is constructed; the fusion signal feature vector with the label is input into the Gaussian naive Bayes regression model for category prediction to obtain a predicted working distance value; a distance deviation value is determined according to the predicted working distance value and the working distance value between the optical head and the part to be added; based on the distance deviation value, the model performance is evaluated by the root mean square error and the determination coefficient, and the trained Gaussian naive Bayes regression model is output.

[0070] In this embodiment, it should be noted that the Gaussian Naive Bayesian regression model is an improved model based on the Gaussian Naive Bayesian classification model. The model calculates the probability that the feature vector belongs to each category based on a given feature vector, and outputs the sum of the product of the probability of each category and the category label as the regression value. The formula is as follows:

[0071]

[0072] In the above formula, y pred represents the regression prediction value, P(y i |X) indicates that the feature vector X belongs to category y i The probability of y i Represents the category label, n represents the input signal data, and i represents the i-th category label.

[0073] The core idea of ​​the Gaussian Naive Bayes regression model is to assume that the conditional probability of each feature follows a Gaussian distribution (normal distribution). In the regression scenario, the model calculates the probability that the feature vector belongs to each category, and outputs the sum of the product of the probability of each category and the category label as the regression value. It has the following advantages:

[0074] 1) High computational efficiency: Due to the conditional independence assumption, the computational complexity of the model is low and suitable for large-scale data sets.

[0075] 2) Applicable to small sample data: Gaussian naive Bayes regression can still perform well with small samples because it uses prior probabilities and simple probability distribution assumptions.

[0076] 3) Good robustness: The model is not very sensitive to noise and missing values ​​in the input data.

[0077] Furthermore, the model performance can be evaluated by the root mean square error (RMSE) and the coefficient of determination (R-squared, R2): RMSE is used to measure the deviation between the sample prediction value and the true value. The smaller the RMSE value, the higher the prediction accuracy of the model; conversely, the larger the RMSE value, the worse the prediction accuracy. 2 It is used to evaluate the goodness of fit of the regression model, R 2 The closer the value is to 1, the better the model fit is; the closer it is to 0, the worse the fit is. The specific evaluation index calculation method is as follows:

[0078]

[0079] In the above formula, RMSE represents the root mean square error function, R 2 represents the coefficient of determination, N represents the number of prediction samples, y i Represents the true value of the i-th sample, y' i represents the predicted value of the i-th sample, and y represents the average of the true values ​​of all samples.

[0080] S400, based on the trained Gaussian naive Bayesian regression model, the laser near-net forming working distance is monitored for the acoustic emission signal and the molten pool temperature signal to obtain the laser near-net forming working distance value.

[0081] In summary, if Figure 3 As shown, the embodiment of the present invention first uses an acoustic emission device to collect acoustic emission signals of several groups of laser near-net forming single-channel experiments at different working distances, and records the actual working distance of the experiment; band-pass filters the acoustic emission signals; divides the filtered acoustic emission signals into acoustic signal windows with consistent time intervals; calculates 12 time domain features and frequency domain features in each acoustic signal window, and obtains an acoustic signal feature vector with a dimension of 1*12; uses a colorimetric pyrometer device to collect the molten pool temperature signal of the laser near-net forming process; divides the molten pool temperature signal into molten pool temperature signal windows with consistent time intervals; calculates 12 time domain features and frequency domain features in each molten pool temperature signal window, and obtains a molten pool temperature signal feature vector with a dimension of 1*12; compares the acoustic signal feature vector corresponding to the same period of time with the molten pool temperature signal feature vector. The vectors are merged in the feature dimension direction to obtain the feature vector of the fusion signal, and each type of feature is normalized in the feature matrix composed of the fusion feature vector to obtain the normalized fusion signal feature vector; each fusion signal feature vector is labeled, and the label is the working distance value between the optical head and the part to be added; a Gaussian naive Bayes regression model is established, and regression training is performed on the data set composed of the fusion feature vector, and the trained model and parameters are saved; the acoustic emission signal of the laser near-net forming process is obtained on-site by using an acoustic emission device, and the molten pool temperature signal of the laser near-net forming process is obtained on-site by using a colorimetric pyrometer device; the acoustic emission signal and the molten pool temperature signal on-site are automatically identified by using the trained Gaussian naive Bayes regression model and parameters to obtain the working distance label of the fusion signal on-site.

[0082] Reference Figure 2 , a laser near-net-shape working distance monitoring system based on data fusion, including:

[0083] The first module 201 is used to obtain the acoustic emission signal and the molten pool temperature signal in the laser near-net forming process;

[0084] The second module 202 is used to perform data preprocessing and vector fusion processing on the acoustic emission signal and the molten pool temperature signal to obtain a fusion signal feature vector of laser near-net forming;

[0085] The third module 203 is used to perform data training on the Gaussian Naive Bayesian regression model through the fusion signal feature vector of the laser near-net shaping to obtain a trained Gaussian Naive Bayesian regression model;

[0086] The fourth module 204 is used to monitor the laser near-net forming working distance based on the trained Gaussian Naive Bayes regression model for the acoustic emission signal and the molten pool temperature signal to obtain the laser near-net forming working distance value.

[0087] The contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0088] The above is a specific description of the preferred implementation of the present invention, but the invention is not limited to the embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A laser near-net-shape working distance monitoring method based on data fusion, characterized in that: The following steps are involved: Acquire the acoustic emission signal and the molten pool temperature signal during the laser near-net forming process; The acoustic emission signal and the molten pool temperature signal are subjected to data preprocessing and vector fusion processing to obtain the fusion signal feature vector of laser near-net forming; The Gaussian Naive Bayesian regression model is trained with data through the fusion signal feature vector of the laser near-net-shaped process to obtain the trained Gaussian Naive Bayesian regression model; Based on the trained Gaussian naive Bayesian regression model, the laser near-net forming working distance is monitored by the acoustic emission signal and the molten pool temperature signal, and the laser near-net forming working distance value is obtained.

2. The laser near-net shaping working distance monitoring method based on data fusion according to claim 1 is characterized in that: The step of obtaining the acoustic emission signal during the laser near-net forming process and the molten pool temperature signal during the laser near-net forming process specifically includes: The acoustic emission probe is placed at the bottom of the substrate to be added, and an ultrasonic coupling agent is applied between the acoustic emission probe and the bottom of the substrate to be added, and the acoustic emission signal in the laser near-net forming process is obtained according to a preset sampling rate; The two-color pyrometer is coaxially arranged with the laser path of the molten pool, and a trigger start signal is set to obtain the molten pool temperature signal during the laser near-net forming process.

3. The laser near-net shaping working distance monitoring method based on data fusion according to claim 2 is characterized in that: The step of performing data preprocessing and vector fusion processing on the acoustic emission signal and the molten pool temperature signal to obtain the fusion signal feature vector of laser near-net forming specifically includes: Performing bandpass filtering on the acoustic emission signal to obtain a filtered acoustic emission signal; The filtered acoustic emission signal and the molten pool temperature signal are respectively subjected to signal window processing to obtain a segmented acoustic emission signal and a segmented molten pool temperature signal; The segmented acoustic emission signal and the segmented molten pool temperature signal are respectively calculated in time domain and frequency domain to obtain the acoustic signal feature vector and the molten pool temperature signal feature vector; The acoustic signal feature vector and the molten pool temperature signal feature vector are vector-fused and normalized to obtain the fused signal feature vector of laser near-net forming.

4. The laser near-net shaping working distance monitoring method based on data fusion according to claim 3 is characterized in that: The expression for performing signal window processing on the filtered acoustic emission signal and the molten pool temperature signal is specifically as follows: In the above formula, hanning(·) represents the hanning window function, M represents the length of the window, and n represents the input signal data.

5. The laser near-net shaping working distance monitoring method based on data fusion according to claim 4 is characterized in that: The time domain features and frequency domain features specifically include mean, peak, absolute mean, root mean square, absolute standard deviation, envelope standard deviation, kurtosis, skewness, average power, spectrum kurtosis, spectrum skewness and spectrum center of gravity.

6. The laser near-net shaping working distance monitoring method based on data fusion according to claim 5 is characterized in that: The step of performing data training on the Gaussian Naive Bayesian regression model through the fusion signal feature vector of the laser near-net shaping to obtain the trained Gaussian Naive Bayesian regression model specifically includes: Assigning data labels to the fusion signal feature vector of the laser near-net shaping to obtain a fusion signal feature vector with a label, wherein the data label represents a working distance value between the optical head and the part to be added; Construct a Gaussian Naive Bayes regression model; The fused signal feature vector with labels is input into the Gaussian Naive Bayes regression model for category prediction to obtain the predicted working distance value; Determine a distance deviation value according to the predicted working distance value and the working distance value between the optical head and the part to be added; Based on the distance deviation value, the model performance is evaluated by the root mean square error and the coefficient of determination, and the trained Gaussian naive Bayes regression model is output.

7. The laser near-net shaping working distance monitoring method based on data fusion according to claim 6 is characterized in that: The expression of the Gaussian Naive Bayes regression model is specifically as follows: In the above formula, y pred represents the regression prediction value, P(y i |X) indicates that the feature vector X belongs to category y i The probability of y i Represents the category label, n represents the input signal data, and i represents the i-th category label.

8. Laser near-net-shape working distance monitoring system based on data fusion, characterized in that: Includes the following modules: The first module is used to obtain the acoustic emission signal and the molten pool temperature signal in the laser near-net forming process; The second module is used to perform data preprocessing and vector fusion processing on the acoustic emission signal and the molten pool temperature signal to obtain the fusion signal feature vector of laser near-net forming; The third module is used to perform data training on the Gaussian Naive Bayesian regression model through the fusion signal feature vector of the laser near-net forming to obtain the trained Gaussian Naive Bayesian regression model; The fourth module is used to monitor the laser near-net forming working distance based on the trained Gaussian naive Bayes regression model for the acoustic emission signal and the molten pool temperature signal to obtain the laser near-net forming working distance value.

Images