Laser equipment fault intelligent diagnosis system and method based on Internet of Things

Abstract

The invention discloses an intelligent laser equipment fault diagnosis system and method based on the Internet of Things, and relates to the technical field of laser equipment fault diagnosis, and the system comprises a laser cutting monitoring module, an infrared image analysis module and a cutting path adjustment module. The laser cutting monitoring module obtains infrared image data of a laser cutting area in real time and conducts temperature distribution marking on all pixel points. The infrared image analysis module is used for positioning an actual laser cutting point in the infrared image through sliding window temperature integration, predicting the actual laser cutting point in the infrared image collected at the future moment, and analyzing a temperature transfer deviation coefficient and a radiation heat accumulation coefficient of laser cutting in the infrared image; and the cutting path adjusting module is used for adjusting and judging a laser cutting path in the real-time infrared image, and correcting a moving speed vector of a laser head according to a temperature transfer deviation coefficient and a radiation heat accumulation coefficient of laser cutting.

Description

Technical Field

[0001] The present invention relates to the technical field of laser equipment fault diagnosis, and in particular to an intelligent laser equipment fault diagnosis system and method based on the Internet of Things. Background Art

[0002] As various industries have higher requirements for equipment and workpiece processing accuracy, high-precision laser cutting has become a more mainstream technical means in the field of workpiece processing. The diagnosis and correction of laser cutting path deviation is particularly important in high-precision processing operations. During actual laser cutting processing, due to the difference in local thermal conductivity of inhomogeneous materials, the heating and melting efficiency on both sides of the laser radiation point is inconsistent, causing the preset laser radiation point to deviate from the actual laser cutting center position. In the traditional laser path deviation diagnosis method, there is a lack of real-time tracking and analysis of the local thermal conductivity of inhomogeneous materials, and real-time correction of the laser cutting path, resulting in redundant loss of processing materials and reduced processing efficiency during laser cutting.

[0003] Therefore, there is a need for an intelligent diagnosis system and method for laser equipment faults based on the Internet of Things to solve the above-mentioned technical defects. Summary of the invention

[0004] The purpose of the present invention is to provide a laser equipment fault intelligent diagnosis system and method based on the Internet of Things to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solutions: An intelligent diagnosis method for laser equipment faults based on the Internet of Things comprises the following steps: Step S100: performing real-time monitoring when the laser equipment performs a laser cutting task, obtaining infrared image data of the laser cutting area in real time through an infrared thermal imaging device, and marking the temperature distribution of each pixel in the infrared image data; Step S200: performing sliding window integration along the direction parallel to the preset cutting path in the infrared image, calculating the temperature integral of each pixel in the infrared image, and then screening and locating the actual laser cutting point in the infrared image, and calculating the temperature transfer deviation coefficient of the laser cutting in the infrared image according to the sliding window width; Step S300: setting a laser cutting temperature calibration value, measuring the maximum spacing of pixels at the actual laser cutting point in the infrared image perpendicular to the preset laser cutting path, where the temperature value is greater than or equal to the laser cutting temperature calibration value, and calculating the radiation heat accumulation coefficient of the laser cutting; Step S400: annotating the actual laser cutting points in the historical multi-frame infrared image data, constructing a laser cutting data set and training a laser cutting prediction neural network model to predict the actual laser cutting point positions in future frames of infrared image data; Step S500: real-time monitoring of the actual laser cutting point during laser cutting, and control and adjustment of the laser cutting path according to the temperature transfer deviation coefficient and the radiation heat accumulation coefficient of the laser cutting in the infrared image.

[0006] In the above technical solution, step S100 includes the following contents: Use infrared thermal imaging equipment to monitor laser cutting materials in real time, obtain infrared image data of the laser cutting area, suppress noise and remove outliers in the real-time infrared image data, and mark the temperature distribution; For any pixel point P, the temperature distribution is marked as: P[x_P, y_P, T_P]; where x_P is the horizontal arrangement number of the pixel point P in the infrared image data, y_P is the vertical arrangement number of the pixel point P in the infrared image data, and T_P is the temperature displayed by the pixel point P in the infrared image data.

[0007] In the above technical solution, step S200 includes the following analysis steps: Step S201: setting the sliding window width w and length l, and performing sliding window integration along the direction parallel to the preset cutting path in the infrared image with the pixel spacing as the sliding step length; Step S202: Calculate the sliding window integral result corresponding to each pixel point in the infrared image, and select the pixel point corresponding to the maximum value of the calculation result as the actual laser cutting point of the current infrared image; If there are multiple pixels with the same sliding window integral calculation results, the two-dimensional spatial clustering center of all pixels with the same calculation results is used as the actual laser cutting point of the current infrared image data; Step S203: Obtain the temperature data of the actual laser cutting point at intervals of l pixels on both sides of the preset cutting path direction, and calculate the temperature transfer deviation coefficient k_grad of the laser cutting in the infrared image according to the formula: k_grad=(|△T_left|-|△T_right|) / (|△T_left|+|△T_right|); Among them, △T_left is the temperature difference between the pixel point with an interval of l on the left side of the actual laser cutting point perpendicular to the preset cutting path direction and the actual laser cutting point, and △T_right is the temperature difference between the pixel point with an interval of l on the right side of the actual laser cutting point perpendicular to the preset cutting path direction and the actual laser cutting point; By calculating the difference ratio of temperature distribution of processed materials during laser cutting and analyzing the offset between the actual slit center and the cutting point caused by the difference in local thermal conductivity of the material at the laser cutting point, the rationality and scientificity of laser cutting path adjustment are improved.

[0008] In the above technical solution, step S300 includes the following analysis steps: Step S301: setting a laser cutting temperature calibration value T_cal, and performing pixel point traversal along a preset laser cutting path direction at an actual laser cutting point; Step S302: Filter all pixels whose temperature values ​​are greater than or equal to T_cal, and measure the pixel spacing l_spac between the farthest pixels; Step S303: Calculate the radiation heat accumulation coefficient k_heat of laser cutting according to the l_spac measurement result and the formula k_heat=k_ad×(l_spac-l_slit) / l_slit; Among them, k_ad is the heat accumulation adjustment coefficient, the value range is: (0,1), l_slit is the reference slit width of laser cutting; By limiting the laser cutting temperature calibration value, the actual transmission range of the thermal radiation effect during laser cutting is calculated, and then the laser energy consumption efficiency and material processing effect during the laser cutting process are analyzed to ensure that the processing effect is met while minimizing the laser's additional radiation energy loss.

[0009] In the above technical solution, step S400 includes the following analysis steps: Step S401: Acquire historical multiple frames of infrared image data of the laser cutting area, and perform attribute marking on the actual laser cutting points that are screened and located; For any frame of infrared image data i, the attribute of the actual laser cutting point P_i in the image is annotated as: P_i[loc_(i-1),loc_i,v_P,F_laser]; In the actual laser cutting point attribute annotation result, loc_(i-1) is the position of the actual laser cutting point P_(i-1) in the infrared image data of the previous frame of infrared image data i, loc_i is the position of the actual laser cutting point P_i in the infrared image data i, v_P is the travel vector from the actual laser cutting point P_(i-1) to the actual laser cutting point P_i, and F_laser is the laser radiation parameter set; wherein, the actual laser cutting point position includes the horizontal arrangement number and the vertical arrangement number of the actual laser cutting point in the infrared image data; The distance between the actual laser cutting point in the infrared image and the preset cutting path is expressed as a signed number; when the value is negative, it means that the actual laser cutting point in the infrared image is on the left side of the preset cutting path, and when the value is positive, it means that the actual laser cutting point in the infrared image is on the right side of the preset cutting path; Step S402: construct a laser cutting data set and train a laser cutting prediction neural network model; the laser cutting prediction neural network model inputs the actual laser cutting point attribute annotation results in the current frame infrared image, and outputs the predicted orientation of the actual laser cutting point in the next frame infrared image.

[0010] In the above technical solution, step S500 includes the following contents: Real-time monitoring of the actual laser cutting point during laser cutting, using the laser cutting prediction neural network model to predict the actual laser cutting point position of future infrared image frames, and performing laser cutting path deviation fault diagnosis; The laser path deviation threshold and the radiation heat accumulation coefficient threshold are set, and the path deviation fault diagnosis paradigm is constructed as follows: (1) The distance between the predicted orientation of the actual laser cutting point and the preset laser cutting path is less than the laser path deviation threshold; (2) The radiation heat accumulation coefficient of the laser cutting at any time point is less than the radiation heat accumulation coefficient threshold; When any of the above paradigms is not satisfied, it is determined that the current laser cutting path needs to be adjusted. For the laser cutting path at any moment, the adjustment strategy is as follows: v_l_fix=(1+k_heat)×v_l_ini; v_t_fix=k_grad×dev_P / T0; Wherein, v_l_fix is ​​the correction value of the laser head moving speed parallel to the preset laser cutting path, k_heat is the radiation heat accumulation coefficient of laser cutting in the infrared image, v_l_ini is the initial value of the laser head moving speed parallel to the preset laser cutting path, v_t_fix is ​​the correction value of the laser head moving speed perpendicular to the preset laser cutting path, k_grad is the temperature transfer deviation coefficient of laser cutting in the infrared image, dev_P is the distance between the actual laser cutting point and the preset cutting path in the infrared image, and T0 is the infrared image acquisition period; Taking the preset laser cutting path direction as the reference direction, the laser head moving speed correction values ​​parallel and perpendicular to the reference direction are added by vector as the laser head moving speed vector correction result at the current moment; The path deviation is decomposed into parallel speed correction and vertical fine-tuning to avoid oscillation caused by single parameter adjustment. At the same time, the laser cutting path is adaptively adjusted according to the temperature transfer deviation coefficient and radiation heat accumulation coefficient of laser cutting, which further improves the energy utilization efficiency of the processing process and the workpiece processing effect.

[0011] For the correction value of the laser head moving speed perpendicular to the reference direction, if the value is positive, the laser head moving speed direction is perpendicular to the reference direction to the right, if the value is negative, the laser head moving speed direction is perpendicular to the reference direction to the left; For the laser head moving speed vector correction result, if the vector modulus value is less than or equal to the maximum moving speed of the laser head, the laser head moving speed vector correction result is used as the laser head moving speed vector at the current moment, and the laser cutting path adjustment strategy decision is re-made at the next infrared image acquisition time point; if the vector modulus value is greater than the maximum moving speed of the laser head, the laser head moving speed vector correction result is proportionally reduced until the vector modulus value is equal to the maximum moving speed of the laser head, and the laser cutting path adjustment strategy decision is re-made at the next infrared image acquisition time point.

[0012] An intelligent diagnosis system for laser equipment faults based on the Internet of Things using an intelligent diagnosis method for laser equipment faults based on the Internet of Things in the above technical solution, the system comprising: a laser cutting monitoring module, an infrared image analysis module, and a cutting path adjustment module; The laser cutting monitoring module acquires infrared image data of the laser cutting area in real time, and marks the temperature distribution of each pixel point; the infrared image analysis module locates the actual laser cutting point in the infrared image through the sliding window temperature integral, and predicts the actual laser cutting point in the infrared image collected at the future moment, and is also used to analyze the temperature transfer deviation coefficient and the radiation heat accumulation coefficient of the laser cutting in the infrared image; the cutting path adjustment module adjusts and judges the laser cutting path in the real-time infrared image, and corrects the laser head moving speed vector according to the temperature transfer deviation coefficient and the radiation heat accumulation coefficient of the laser cutting.

[0013] In the above technical solution, the laser cutting monitoring module includes: an infrared data monitoring unit and a temperature distribution marking unit; The infrared data monitoring unit acquires infrared image data of the laser cutting area in real time through an infrared thermal imaging device; and the temperature distribution marking unit marks the temperature distribution of each pixel in the infrared image.

[0014] In the above technical solution, the infrared image analysis module includes: an actual laser cutting point positioning unit, a temperature transfer deviation analysis unit, a radiation heat accumulation analysis unit, and an actual laser cutting point prediction unit; The actual laser cutting point positioning unit locates the actual laser cutting point in the infrared image through sliding window temperature integration; the temperature transfer deviation analysis unit is used to analyze the temperature transfer deviation coefficient of laser cutting in the infrared image; the radiation heat accumulation analysis unit is used to analyze the radiation heat accumulation coefficient of laser cutting in the infrared image; the actual laser cutting point prediction unit predicts the actual laser cutting point orientation in the infrared image collected at a future time based on the actual laser cutting point data in the historical infrared data.

[0015] In the above technical solution, the cutting path adjustment module includes: a cutting path adjustment judgment unit and a laser head moving speed correction unit; The cutting path adjustment and judgment unit adjusts and judges the laser cutting path in the real-time infrared image; the laser head moving speed correction unit corrects the laser head moving speed vector according to the temperature transfer deviation coefficient and the radiation heat accumulation coefficient of the laser cutting.

[0016] Compared with the prior art, the present invention has the following beneficial effects: In the present invention, the material temperature data in the laser cutting process is obtained by real-time infrared image monitoring, which can effectively avoid the increase in the misjudgment rate of image features caused by smoke interference and material reflection in the visual solution, and can also diagnose and correct the deviation of the laser cutting path in a more real-time manner; In the present invention, abnormal infrared isolated points caused by material residues are eliminated through image outlier processing and noise suppression, the center point of the laser cutting seam is located, and the deviation between the laser radiation point and the center of the molten pool caused by the difference in local thermal conductivity of non-homogeneous materials is fully considered. Compared with the acoustic vibration solution, the accuracy and intuitiveness of the actual laser cutting point identification and positioning are significantly improved.

[0017] In the present invention, by real-time analysis of the temperature transfer deviation coefficient and radiation heat accumulation coefficient of laser cutting in infrared image data, compared with a purely data-driven black box model, the interpretability of laser cutting path deviation diagnosis and correction is ensured, while the system's adaptability to complex working conditions is also improved, significantly improving the utilization of processing materials and laser energy consumption during laser cutting. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of an intelligent diagnosis method for laser equipment faults based on the Internet of Things of the present invention; Figure 2 This is an organizational structure diagram of an intelligent diagnosis system for laser equipment faults based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Example: See Figure 1-Figure 2 , the present invention provides the following technical solutions: like Figure 1 As shown, the present invention provides a laser equipment fault intelligent diagnosis method based on the Internet of Things, comprising the following steps: Step S100: performing real-time monitoring when the laser equipment performs a laser cutting task, obtaining infrared image data of the laser cutting area in real time through an infrared thermal imaging device, and marking the temperature distribution of each pixel in the infrared image data; Step S200: performing sliding window integration along the direction parallel to the preset cutting path in the infrared image, calculating the temperature integral of each pixel in the infrared image, and then screening and locating the actual laser cutting point in the infrared image, and calculating the temperature transfer deviation coefficient of the laser cutting in the infrared image according to the sliding window width; Step S300: setting a laser cutting temperature calibration value, measuring the maximum spacing of pixels at the actual laser cutting point in the infrared image perpendicular to the preset laser cutting path, where the temperature value is greater than or equal to the laser cutting temperature calibration value, and calculating the radiation heat accumulation coefficient of the laser cutting; Step S400: annotating the actual laser cutting points in the historical multi-frame infrared image data, constructing a laser cutting data set and training a laser cutting prediction neural network model to predict the actual laser cutting point positions in future frames of infrared image data; Step S500: real-time monitoring of the actual laser cutting point during laser cutting, and control and adjustment of the laser cutting path according to the temperature transfer deviation coefficient and the radiation heat accumulation coefficient of the laser cutting in the infrared image.

[0021] The step S100 includes the following contents: Use infrared thermal imaging equipment to monitor laser cutting materials in real time, obtain infrared image data of the laser cutting area, suppress noise and remove outliers in the real-time infrared image data, and mark the temperature distribution; For any pixel point P, the temperature distribution is marked as: P[x_P, y_P, T_P]; where x_P is the horizontal arrangement number of the pixel point P in the infrared image data, y_P is the vertical arrangement number of the pixel point P in the infrared image data, and T_P is the temperature displayed by the pixel point P in the infrared image data; In the specific implementation, a high-dynamic and high-frame-rate infrared thermal imager is selected to perform real-time monitoring above the side of the laser cutting head. At the same time, a filter is used to suppress the strong light interference directly irradiated by the plasma. After the filter is installed, the image of the infrared thermal imager is recalibrated due to the filter pair, and a pixel temperature-true temperature mapping table is constructed. The image overexposure in the plasma flash area is further repaired through local image repair, and the temperature distribution of the repaired image is annotated according to the pixel temperature-true temperature mapping table.

[0022] The step S200 includes the following analysis steps: Step S201: setting the sliding window width w and length l, and performing sliding window integration along the direction parallel to the preset cutting path in the infrared image with the pixel spacing as the sliding step length; Step S202: Calculate the sliding window integral result corresponding to each pixel point in the infrared image, and select the pixel point corresponding to the maximum value of the calculation result as the actual laser cutting point of the current infrared image; If there are multiple pixels with the same sliding window integral calculation results, the two-dimensional spatial clustering center of all pixels with the same calculation results is used as the actual laser cutting point of the current infrared image data; Step S203: Obtain the temperature data of the actual laser cutting point at intervals of l pixels on both sides of the preset cutting path direction, and calculate the temperature transfer deviation coefficient k_grad of the laser cutting in the infrared image according to the formula: k_grad=(|△T_left|-|△T_right|) / (|△T_left|+|△T_right|); Among them, △T_left is the temperature difference between the pixel point with an interval of l on the left side of the actual laser cutting point perpendicular to the preset cutting path direction and the actual laser cutting point, and △T_right is the temperature difference between the pixel point with an interval of l on the right side of the actual laser cutting point perpendicular to the preset cutting path direction and the actual laser cutting point; In specific implementation, due to the possible local uniformity differences in the internal structure of the material to be processed, the heat transfer efficiency of different areas near different laser radiation points is also inconsistent during laser cutting. It is inevitable that some areas in the preset laser cutting path have melted and fallen off, while some areas have not yet melted, resulting in the deviation between the final slit and the preset cutting path. Furthermore, in order to refine the evaluation of the heat transfer characteristics of each area during laser cutting, infrared images are used to compare and analyze the thermal radiation efficiency on both sides of the laser radiation point of the material to be processed, and then the center position of the final slit is determined, and this is used to evaluate whether the laser cutting path has lateral deviation; Furthermore, the sliding window l=w=3px is set, corresponding to the actual distance of 0.3mm, and the sliding step is 1px, corresponding to the actual distance of 0.1mm; when performing sliding window integration, in order to simplify the calculation, the left and right areas of the preset cutting path are divided into 3cm wide areas as sliding areas; Assume that the sliding window of the pixel point p1 with an interval of 3px on the left side of the actual laser cutting point located contains the pixel point temperature values ​​(unit: Celsius) of [230, 250, 220; 1400, 1550, 1450; 1350, 1480, 1520], and the sliding window of the pixel point p2 with an interval of 3px on the right side contains the pixel point temperature values ​​of [1480, 1520, 160; 1550, 1450, 170; 250, 220, 175]. The calculated temperature integral value of the pixel point p1 is 10400, and the temperature integral value of p2 is 7065. Assuming that the actual temperature value of the laser cutting point is 1600, the temperature transfer deviation coefficient of laser cutting k_grad=(|1600-1550|-|1600-1450|) / (|1600-1550|+|1600-1450|)=-0.5.

[0023] The step S300 includes the following analysis steps: Step S301: setting a laser cutting temperature calibration value T_cal, and performing pixel point traversal along a preset laser cutting path direction at an actual laser cutting point; Step S302: Filter all pixels whose temperature values ​​are greater than or equal to T_cal, and measure the pixel spacing l_spac between the farthest pixels; Step S303: Calculate the radiation heat accumulation coefficient k_heat of laser cutting according to the l_spac measurement result and the formula k_heat=k_ad×(l_spac-l_slit) / l_slit; Among them, k_ad is the heat accumulation adjustment coefficient, the value range is: (0,1), l_slit is the reference slit width of laser cutting; In specific implementation, the internal structure and physical and chemical properties of the material to be processed in the area near the laser radiation point may change with the laser thermal radiation. Due to the inconsistency of the local heat transfer efficiency of the material, the same thermal radiation intensity affects the material range and orientation in different areas differently, resulting in uneven ranges of materials affected near the laser cutting seam, affecting the application of the final processed product. Furthermore, in order to measure the interference of laser cutting thermal radiation on the material, the area with higher thermal radiation near the actual laser cutting seam is divided through infrared images to intuitively reflect the area that is greatly affected by thermal radiation during the laser cutting process. Then, according to the regional range division results in the infrared images at different time points, the actual influence range of the laser radiation point in different areas of the material to be processed is quantified; Furthermore, assuming that the temperature values ​​of 9 pixel points on the left and right sides of the current actual laser cutting point (unit: degrees Celsius) are from left to right: 1100, 1250, 1400, 1550, 1600, 1600, 1500, 1400, 1300; the laser cutting temperature calibration value is set to 1300, and the measurement shows that l_spac = 6px (0.6mm). Assuming that the laser cutting reference slit width l_slit = 0.4mm, the heat accumulation adjustment coefficient k_ad = 0.5, the radiation heat accumulation coefficient k_heat of laser cutting is calculated to be 0.25.

[0024] The step S400 includes the following analysis steps: Step S401: Acquire historical multiple frames of infrared image data of the laser cutting area, and perform attribute marking on the actual laser cutting points that are screened and located; For any frame of infrared image data i, the attribute of the actual laser cutting point P_i in the image is annotated as: P_i[loc_(i-1),loc_i,v_P,F_laser]; In the actual laser cutting point attribute annotation result, loc_(i-1) is the position of the actual laser cutting point P_(i-1) in the infrared image data of the previous frame of infrared image data i, loc_i is the position of the actual laser cutting point P_i in the infrared image data i, v_P is the travel vector from the actual laser cutting point P_(i-1) to the actual laser cutting point P_i, and F_laser is the laser radiation parameter set; wherein, the actual laser cutting point position includes the horizontal arrangement number and the vertical arrangement number of the actual laser cutting point in the infrared image data; The distance between the actual laser cutting point in the infrared image and the preset cutting path is expressed as a signed number; when the value is negative, it means that the actual laser cutting point in the infrared image is on the left side of the preset cutting path, and when the value is positive, it means that the actual laser cutting point in the infrared image is on the right side of the preset cutting path; Step S402: construct a laser cutting data set and train a laser cutting prediction neural network model; the laser cutting prediction neural network model inputs the actual laser cutting point attribute annotation results in the current frame infrared image, and outputs the predicted orientation of the actual laser cutting point in the next frame infrared image.

[0025] The step S500 includes the following contents: Real-time monitoring of the actual laser cutting point during laser cutting, using the laser cutting prediction neural network model to predict the actual laser cutting point position of future infrared image frames, and performing laser cutting path deviation fault diagnosis; The laser path deviation threshold and the radiation heat accumulation coefficient threshold are set, and the path deviation fault diagnosis paradigm is constructed as follows: (1) The distance between the predicted orientation of the actual laser cutting point and the preset laser cutting path is less than the laser path deviation threshold; (2) The radiation heat accumulation coefficient of the laser cutting at any time point is less than the radiation heat accumulation coefficient threshold; In specific implementation, when the cutting line deviates greatly from the preset cutting path, the cutting edge line needs to be processed again due to accuracy requirements during subsequent processing, which will cause secondary processing losses. At the same time, if the laser cutting causes the material around the cutting line to generate strong heat radiation, it will cause damage to the internal structure of the material and excessive use of laser energy. Therefore, it is necessary to judge the path deviation and heat radiation accumulation during laser cutting processing; When any of the above paradigms is not satisfied, it is determined that the current laser cutting path needs to be adjusted. For the laser cutting path at any moment, the adjustment strategy is as follows: v_l_fix=(1+k_heat)×v_l_ini; v_t_fix=k_grad×dev_P / T0; Wherein, v_l_fix is ​​the correction value of the laser head moving speed parallel to the preset laser cutting path, k_heat is the radiation heat accumulation coefficient of laser cutting in the infrared image, v_l_ini is the initial value of the laser head moving speed parallel to the preset laser cutting path, v_t_fix is ​​the correction value of the laser head moving speed perpendicular to the preset laser cutting path, k_grad is the temperature transfer deviation coefficient of laser cutting in the infrared image, dev_P is the distance between the actual laser cutting point and the preset cutting path in the infrared image, and T0 is the infrared image acquisition period; In the specific implementation, when the laser cutting seam deviates greatly from the preset laser cutting path, it is necessary to perform negative feedback adjustment on the lateral movement of the laser head to ensure that the laser cutting seam is as close to the preset laser cutting path as possible. At the same time, when the thermal radiation generated by the laser radiation point in the local area of ​​the material to be processed is strong, it is necessary to appropriately increase the longitudinal movement speed of the laser head to suppress the further influence of the laser cutting thermal radiation on the processed material near the laser cutting point, so as to ensure the local quality consistency of the final processed product.

[0026] Furthermore, it is assumed that the laser head moves in parallel to the preset laser cutting path with an initial speed v_l_ini=5mm / s, temperature transfer deviation coefficient: k_grad=-0.5, radiation heat accumulation coefficient: k_heat=0.25, path deviation distance: dev_P=+0.2mm, infrared image acquisition cycle: T_0=0.01s, and the maximum moving speed of the laser head: v_max=20mm / s; Calculate the laser head moving speed correction value v_l_fix=6.25mm / s in the direction parallel to the preset laser cutting path, and the laser head moving speed correction value v_t_fix=-10mm / s in the direction perpendicular to the preset laser cutting path, the direction is left, and further superimpose the speed correction values ​​in the two directions with orthogonal vectors to synthesize the speed vector correction value of the laser head movement, the modulus value is about 11.79mm / s. After comparison, no scaling is required.

[0027] Taking the preset laser cutting path direction as the reference direction, the laser head moving speed correction values ​​parallel and perpendicular to the reference direction are added by vector as the laser head moving speed vector correction result at the current moment; For the correction value of the laser head moving speed perpendicular to the reference direction, if the value is positive, the laser head moving speed direction is perpendicular to the reference direction to the right, if the value is negative, the laser head moving speed direction is perpendicular to the reference direction to the left; For the laser head moving speed vector correction result, if the vector modulus value is less than or equal to the maximum moving speed of the laser head, the laser head moving speed vector correction result is used as the laser head moving speed vector at the current moment, and the laser cutting path adjustment strategy decision is re-made at the next infrared image acquisition time point; if the vector modulus value is greater than the maximum moving speed of the laser head, the laser head moving speed vector correction result is proportionally reduced until the vector modulus value is equal to the maximum moving speed of the laser head, and the laser cutting path adjustment strategy decision is re-made at the next infrared image acquisition time point.

[0028] like Figure 2 As shown, the present invention also provides a laser equipment fault intelligent diagnosis system based on the Internet of Things, the system comprising: a laser cutting monitoring module, an infrared image analysis module, and a cutting path adjustment module; The laser cutting monitoring module acquires infrared image data of the laser cutting area in real time, and marks the temperature distribution of each pixel point; the infrared image analysis module locates the actual laser cutting point in the infrared image through the sliding window temperature integral, and predicts the actual laser cutting point in the infrared image collected at the future moment, and is also used to analyze the temperature transfer deviation coefficient and the radiation heat accumulation coefficient of the laser cutting in the infrared image; the cutting path adjustment module adjusts and judges the laser cutting path in the real-time infrared image, and corrects the laser head moving speed vector according to the temperature transfer deviation coefficient and the radiation heat accumulation coefficient of the laser cutting.

[0029] The laser cutting monitoring module includes: an infrared data monitoring unit and a temperature distribution marking unit; The infrared data monitoring unit acquires infrared image data of the laser cutting area in real time through an infrared thermal imaging device; and the temperature distribution marking unit marks the temperature distribution of each pixel in the infrared image.

[0030] The infrared image analysis module includes: an actual laser cutting point positioning unit, a temperature transfer deviation analysis unit, a radiation heat accumulation analysis unit, and an actual laser cutting point prediction unit; The actual laser cutting point positioning unit locates the actual laser cutting point in the infrared image through sliding window temperature integration; the temperature transfer deviation analysis unit is used to analyze the temperature transfer deviation coefficient of laser cutting in the infrared image; the radiation heat accumulation analysis unit is used to analyze the radiation heat accumulation coefficient of laser cutting in the infrared image; the actual laser cutting point prediction unit predicts the actual laser cutting point orientation in the infrared image collected at a future time based on the actual laser cutting point data in the historical infrared data.

[0031] The cutting path adjustment module includes: a cutting path adjustment judgment unit and a laser head moving speed correction unit; The cutting path adjustment and judgment unit adjusts and judges the laser cutting path in the real-time infrared image; the laser head moving speed correction unit corrects the laser head moving speed vector according to the temperature transfer deviation coefficient and the radiation heat accumulation coefficient of the laser cutting.

[0032] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An intelligent diagnosis method for laser equipment faults based on the Internet of Things, characterized in that , the method comprises the following steps: Step S100: performing real-time monitoring when the laser equipment performs a laser cutting task, obtaining infrared image data of the laser cutting area in real time through an infrared thermal imaging device, and marking the temperature distribution of each pixel in the infrared image data; Step S200: performing sliding window integration along the direction parallel to the preset cutting path in the infrared image, calculating the temperature integral of each pixel in the infrared image, and then screening and locating the actual laser cutting point in the infrared image, and calculating the temperature transfer deviation coefficient of the laser cutting in the infrared image according to the sliding window width; Step S300: setting a laser cutting temperature calibration value, measuring the maximum spacing of pixels at the actual laser cutting point in the infrared image perpendicular to the preset laser cutting path, where the temperature value is greater than or equal to the laser cutting temperature calibration value, and calculating the radiation heat accumulation coefficient of the laser cutting; Step S400: annotating the actual laser cutting points in the historical multi-frame infrared image data, constructing a laser cutting data set and training a laser cutting prediction neural network model to predict the actual laser cutting point positions in future frames of infrared image data; Step S500: real-time monitoring of the actual laser cutting point during laser cutting, and control and adjustment of the laser cutting path according to the temperature transfer deviation coefficient and the radiation heat accumulation coefficient of the laser cutting in the infrared image.

2. According to the method of intelligent diagnosis of laser equipment faults based on the Internet of Things in claim 1, it is characterized in that: The step S100 includes the following contents: Use infrared thermal imaging equipment to monitor laser cutting materials in real time, obtain infrared image data of the laser cutting area, suppress noise and remove outliers in the real-time infrared image data, and mark the temperature distribution; For any pixel point P, the temperature distribution is marked as: P[x_P, y_P, T_P]; where x_P is the horizontal arrangement number of the pixel point P in the infrared image data, y_P is the vertical arrangement number of the pixel point P in the infrared image data, and T_P is the temperature displayed by the pixel point P in the infrared image data.

3. According to the method of intelligent diagnosis of laser equipment faults based on the Internet of Things in claim 1, it is characterized in that: The step S200 includes the following analysis steps: Step S201: setting the sliding window width w and length l, and performing sliding window integration along the direction parallel to the preset cutting path in the infrared image with the pixel spacing as the sliding step length; Step S202: Calculate the sliding window integral result corresponding to each pixel point in the infrared image, and select the pixel point corresponding to the maximum value of the calculation result as the actual laser cutting point of the current infrared image; If there are multiple pixels with the same sliding window integral calculation results, the two-dimensional spatial clustering center of all pixels with the same calculation results is used as the actual laser cutting point of the current infrared image data; Step S203: Obtain the temperature data of the actual laser cutting point at intervals of l pixels on both sides of the preset cutting path direction, and calculate the temperature transfer deviation coefficient k_grad of the laser cutting in the infrared image according to the formula: k_grad=(|△T_left|-|△T_right|) / (|△T_left|+|△T_right|); Among them, △T_left is the temperature difference between the pixel point with an interval of l on the left side of the actual laser cutting point perpendicular to the preset cutting path direction and the actual laser cutting point, and △T_right is the temperature difference between the pixel point with an interval of l on the right side of the actual laser cutting point perpendicular to the preset cutting path direction and the actual laser cutting point.

4. According to the method of intelligent diagnosis of laser equipment faults based on the Internet of Things in claim 1, it is characterized in that: The step S300 includes the following analysis steps: Step S301: setting a laser cutting temperature calibration value T_cal, and performing pixel point traversal along a preset laser cutting path direction at an actual laser cutting point; Step S302: Filter all pixels whose temperature values ​​are greater than or equal to T_cal, and measure the pixel spacing l_spac between the farthest pixels; Step S303: Calculate the radiation heat accumulation coefficient k_heat of laser cutting according to the l_spac measurement result and the formula k_heat=k_ad×(l_spac-l_slit) / l_slit; Among them, k_ad is the heat accumulation adjustment coefficient, the value range is: (0,1), l_slit is the reference slit width of laser cutting.

5. According to the method of intelligent diagnosis of laser equipment faults based on Internet of Things in claim 1, it is characterized in that: The step S400 includes the following analysis steps: Step S401: Acquire historical multiple frames of infrared image data of the laser cutting area, and perform attribute marking on the actual laser cutting points that are screened and located; For any frame of infrared image data i, the attribute of the actual laser cutting point P_i in the image is annotated as: P_i[loc_(i-1),loc_i,v_P,F_laser]; In the actual laser cutting point attribute annotation result, loc_(i-1) is the position of the actual laser cutting point P_(i-1) in the infrared image data of the previous frame of infrared image data i, loc_i is the position of the actual laser cutting point P_i in the infrared image data i, v_P is the travel vector from the actual laser cutting point P_(i-1) to the actual laser cutting point P_i, and F_laser is the laser radiation parameter set; wherein, the actual laser cutting point position includes the horizontal arrangement number and the vertical arrangement number of the actual laser cutting point in the infrared image data; The distance between the actual laser cutting point in the infrared image and the preset cutting path is expressed as a signed number; when the value is negative, it means that the actual laser cutting point in the infrared image is on the left side of the preset cutting path, and when the value is positive, it means that the actual laser cutting point in the infrared image is on the right side of the preset cutting path; Step S402: construct a laser cutting data set and train a laser cutting prediction neural network model; the laser cutting prediction neural network model inputs the actual laser cutting point attribute annotation results in the current frame infrared image, and outputs the predicted orientation of the actual laser cutting point in the next frame infrared image.

6. According to the method of intelligent diagnosis of laser equipment fault based on Internet of Things in claim 1, it is characterized in that: The step S500 includes the following contents: Real-time monitoring of the actual laser cutting point during laser cutting, using the laser cutting prediction neural network model to predict the actual laser cutting point position of future infrared image frames, and performing laser cutting path deviation fault diagnosis; The laser path deviation threshold and the radiation heat accumulation coefficient threshold are set, and the path deviation fault diagnosis paradigm is constructed as follows: (1) The distance between the actual laser cutting point predicted position and the preset laser cutting path is less than the laser path deviation threshold; (2) The radiation heat accumulation coefficient of the laser cutting at any time point is less than the radiation heat accumulation coefficient threshold; When any of the above paradigms is not satisfied, it is determined that the current laser cutting path needs to be adjusted. For the laser cutting path at any moment, the adjustment strategy is as follows: v_l_fix=(1+k_heat)×v_l_ini; v_t_fix=k_grad×dev_P / T0; Wherein, v_l_fix is ​​the correction value of the laser head moving speed parallel to the preset laser cutting path, k_heat is the radiation heat accumulation coefficient of laser cutting in the infrared image, v_l_ini is the initial value of the laser head moving speed parallel to the preset laser cutting path, v_t_fix is ​​the correction value of the laser head moving speed perpendicular to the preset laser cutting path, k_grad is the temperature transfer deviation coefficient of laser cutting in the infrared image, dev_P is the distance between the actual laser cutting point and the preset cutting path in the infrared image, and T0 is the infrared image acquisition period; Taking the preset laser cutting path direction as the reference direction, the laser head moving speed correction values ​​parallel and perpendicular to the reference direction are added by vector as the laser head moving speed vector correction result at the current moment; For the correction value of the laser head moving speed perpendicular to the reference direction, if the value is positive, the laser head moving speed direction is perpendicular to the reference direction to the right, if the value is negative, the laser head moving speed direction is perpendicular to the reference direction to the left; For the laser head moving speed vector correction result, if the vector modulus value is less than or equal to the maximum moving speed of the laser head, the laser head moving speed vector correction result is used as the laser head moving speed vector at the current moment, and the laser cutting path adjustment strategy decision is re-made at the next infrared image acquisition time point; if the vector modulus value is greater than the maximum moving speed of the laser head, the laser head moving speed vector correction result is proportionally reduced until the vector modulus value is equal to the maximum moving speed of the laser head, and the laser cutting path adjustment strategy decision is re-made at the next infrared image acquisition time point.

7. An intelligent diagnosis system for laser equipment faults based on the Internet of Things using the intelligent diagnosis method for laser equipment faults based on the Internet of Things as claimed in any one of claims 1 to 6, characterized in that: The system includes: a laser cutting monitoring module, an infrared image analysis module, and a cutting path adjustment module; The laser cutting monitoring module acquires infrared image data of the laser cutting area in real time, and marks the temperature distribution of each pixel point; the infrared image analysis module locates the actual laser cutting point in the infrared image through the sliding window temperature integral, and predicts the actual laser cutting point in the infrared image collected at the future moment, and is also used to analyze the temperature transfer deviation coefficient and the radiation heat accumulation coefficient of the laser cutting in the infrared image; the cutting path adjustment module adjusts and judges the laser cutting path in the real-time infrared image, and corrects the laser head moving speed vector according to the temperature transfer deviation coefficient and the radiation heat accumulation coefficient of the laser cutting.

8. The intelligent diagnosis system for laser equipment faults based on the Internet of Things according to claim 7 is characterized in that: The laser cutting monitoring module includes: an infrared data monitoring unit and a temperature distribution marking unit; The infrared data monitoring unit acquires infrared image data of the laser cutting area in real time through an infrared thermal imaging device; and the temperature distribution marking unit marks the temperature distribution of each pixel in the infrared image.

9. The intelligent diagnosis system for laser equipment faults based on the Internet of Things according to claim 7 is characterized in that: The infrared image analysis module includes: an actual laser cutting point positioning unit, a temperature transfer deviation analysis unit, a radiation heat accumulation analysis unit, and an actual laser cutting point prediction unit; The actual laser cutting point positioning unit locates the actual laser cutting point in the infrared image through sliding window temperature integration; the temperature transfer deviation analysis unit is used to analyze the temperature transfer deviation coefficient of laser cutting in the infrared image; the radiation heat accumulation analysis unit is used to analyze the radiation heat accumulation coefficient of laser cutting in the infrared image; the actual laser cutting point prediction unit predicts the actual laser cutting point orientation in the infrared image collected at a future time based on the actual laser cutting point data in the historical infrared data.

10. The intelligent diagnosis system for laser equipment faults based on Internet of Things according to claim 7, characterized in that: The cutting path adjustment module includes: a cutting path adjustment judgment unit and a laser head moving speed correction unit; The cutting path adjustment and judgment unit adjusts and judges the laser cutting path in the real-time infrared image; the laser head moving speed correction unit corrects the laser head moving speed vector according to the temperature transfer deviation coefficient and the radiation heat accumulation coefficient of the laser cutting.

Images