An intelligent cutting device and cutting method for a titanium alloy structural component

Abstract

The present invention discloses an intelligent cutting device and a cutting method for titanium alloy structural parts, including: analyzing the temperature gradient change rate based on the temperature distribution data and determining the key areas prone to oxidation reaction in combination with geometric features to obtain the target monitoring area data; obtaining the reflection spectrum information of the cutting area and the comparison spectrum information of the adjacent uncut area according to the target monitoring area data to obtain the spectral feature data; performing spatio-temporal collaborative analysis on the spectral feature data, extracting the spectral feature change value and combining it with the diffusion rate of the oxidation reaction to obtain the oxidation state prediction data; adjusting the cutting power in regions according to the oxidation state prediction data and dynamically compensating the flow field parameters of the shielding gas to perform the cutting of the titanium alloy structural parts. The technical solution of the present invention realizes the dynamic prediction and precise control of the oxidation reaction through spectral monitoring and spatio-temporal collaborative analysis, solves the problem of unstable laser energy coupling caused by surface oxidation reaction, and ensures the cutting quality.

Description

Technical Field

[0001] The present invention relates to the technical field of precision machining of titanium alloy structural parts, and particularly to an intelligent cutting device and a cutting method for titanium alloy structural parts. Background Art

[0002] Due to their excellent specific strength, corrosion resistance, biocompatibility and other characteristics, titanium alloy structural parts are widely used in high-end manufacturing fields such as aerospace, military equipment and medical devices. Such structural parts often need to meet complex shape and size requirements in actual applications, so precise cutting processing is required. In some fields, titanium alloy structural parts not only require high dimensional accuracy, but also need to ensure the quality of the cutting surface to ensure their reliability and service life in harsh working environments.

[0003] Currently, high-energy laser cutting has become the main method for processing titanium alloy structural parts due to its high processing efficiency and good cut quality. However, in the actual cutting process, due to the low thermal conductivity and high chemical activity of titanium alloy, it is easy to rapidly accumulate heat in local areas during processing, and trigger a violent oxidation reaction, resulting in the rapid formation of an oxide film on the workpiece surface. The formation of this oxide film not only changes the optical properties of the material surface, but also causes dynamic fluctuations in the energy coupling efficiency between the laser and the workpiece during the laser cutting process. In traditional cutting methods, the processing technology usually relies on preset fixed parameters, such as laser power, cutting speed, focal length, etc. These parameters are often the average values obtained through a large number of experiments in an idealized or laboratory environment, and do not fully consider the dynamic characteristics of local temperature changes, environmental interference and the oxidation reaction of titanium alloy itself during the actual processing process. At the same time, the traditional process mainly adopts an open-loop control mode, lacking real-time feedback and adjustment means, so it is difficult to cope with the problem of unstable energy transmission caused by the change of the oxide film between the laser and the workpiece surface, and finally leads to hidden problems such as uneven cutting edges, depth deviation and micro-defects. Summary of the Invention

[0004] The main object of the present invention is to solve the technical problem of unstable laser energy coupling caused by the dynamic reflectivity change caused by the surface oxidation reaction in the existing high-energy laser cutting technology of titanium alloy structural parts.

[0005] The first aspect of the present invention provides an intelligent cutting method for titanium alloy structural parts, and the intelligent cutting method for titanium alloy structural parts includes:

[0006] Analyze the change rate of the temperature gradient according to the temperature distribution data on the surface of the titanium alloy structural part, and determine the key areas prone to oxidation reaction in combination with the geometric characteristics of the titanium alloy structural part to obtain the target monitoring area data;

[0007] Based on the data of the target monitoring area, obtain the reflection spectrum information of the cutting area of the titanium alloy structural part and the comparison spectrum information of the adjacent uncut area to obtain spectral characteristic data;

[0008] Perform spatio-temporal collaborative analysis on the spectral characteristic data, extract the spectral intensity change value, peak shape change value and peak position drift value, and combine the spatial diffusion rate and time evolution data of the oxidation reaction to obtain oxidation state prediction data;

[0009] According to the oxidation state prediction data, adjust the cutting power in different regions and dynamically compensate the flow field parameters of the shielding gas to perform the cutting of the titanium alloy structural part.

[0010] Optionally, the process of obtaining the temperature distribution data on the surface of the titanium alloy structural part includes:

[0011] According to the cutting trajectory of the titanium alloy structural part, divide the cutting path into straight segments, corner segments and curve segments, and determine the heat accumulation characteristics of different types of segments according to the thermal conductivity parameters of the titanium alloy to obtain heat accumulation characteristic marking data;

[0012] According to the heat accumulation characteristic marking data, establish an initial heat conduction prediction band along the cutting trajectory, and the width and shape of the initial heat conduction prediction band are adapted to the heat accumulation characteristics of different cutting segments to obtain prediction band contour data;

[0013] Based on the prediction band contour data, set up an array of temperature monitoring points, perform real-time temperature acquisition on the array of temperature monitoring points, and calculate the heat diffusion direction and rate according to the temperature change trend to obtain heat conduction characteristic data;

[0014] According to the heat conduction characteristic data, perform dynamic spatial clustering on temperature abnormal points, and adjust the boundaries of the clustering regions in combination with the heat diffusion direction and rate to generate the temperature distribution data on the surface of the titanium alloy structural part.

[0015] Optionally, the process of analyzing the change rate of the temperature gradient based on the temperature distribution data on the surface of the titanium alloy structural part and determining the key areas prone to oxidation reaction in combination with the geometric characteristics of the titanium alloy structural part to obtain the target monitoring area data includes:

[0016] Perform gradient scanning on the temperature distribution data on the surface of the titanium alloy structural part, calculate the change rate of the temperature gradient, and perform heat zoning on the surface of the titanium alloy structural part according to the change rate to obtain heat distribution characteristic data;

[0017] Perform geometric feature analysis on the surface contour of the titanium alloy structural part, identify the corner transition area, groove convergence area and thickness mutation area, and combine the heat distribution characteristic data to determine the heat accumulation risk of each characteristic area to obtain area risk characteristic data;

[0018] According to the regional risk characteristic data, combine the thermal conductivity parameters of titanium alloy to calculate the heat transfer rate between different characteristic regions, and analyze the heat interaction relationship between adjacent regions to obtain heat transfer chain data;

[0019] Based on the heat transfer chain data, combine the oxidation activity parameters of titanium alloy to calculate the oxidation reaction probability of each region, and analyze the chain propagation law of the oxidation reaction to obtain the target monitoring region data.

[0020] Optionally, perform geometric feature analysis on the surface profile of the titanium alloy structural part, identify the corner transition region, groove convergence region and thickness mutation region, and combine the heat distribution characteristic data to determine the heat accumulation risk of each characteristic region to obtain regional risk characteristic data, including:

[0021] Perform curvature analysis on the surface profile of the titanium alloy structural part, calculate the curvature values of each point on the surface, and identify geometric feature mutation points according to the change rate of the curvature values to obtain feature point distribution data;

[0022] According to the feature point distribution data, perform connectivity analysis on adjacent feature points, divide the corner transition region, groove convergence region and thickness mutation region, and calculate the area and depth parameters of each region to obtain feature region parameter data;

[0023] Perform cross-mapping of the feature region parameter data and the heat distribution characteristic data, calculate the heat density values in each feature region, and analyze the heat flow trend in the feature region to obtain heat accumulation mode data;

[0024] According to the heat accumulation mode data, combine the specific heat capacity parameters of titanium alloy to calculate the heat storage capacity and heat diffusion coefficient of each characteristic region to obtain regional risk characteristic data.

[0025] Optionally, the performing cross-mapping of the feature region parameter data and the heat distribution characteristic data, calculating the heat density values in each feature region, and analyzing the heat flow trend in the feature region to obtain heat accumulation mode data includes:

[0026] Calculate the weight of the area and depth parameters in the feature region parameter data to generate a regional shape coefficient, and correct each regional shape coefficient according to the thermal conductivity characteristics of titanium alloy to obtain regional characteristic weight data;

[0027] According to the regional characteristic weight data, divide the heat distribution characteristic data into regions, and calculate the heat density gradient and heat flow direction in each region to obtain heat flow distribution data;

[0028] Perform time series analysis on the heat flux distribution data, calculate the change rate of the heat density in each region, and analyze the residence time of heat in the region in combination with the thermal diffusion coefficient of the titanium alloy to obtain heat residence characteristic data;

[0029] According to the heat residence characteristic data, analyze the heat accumulation rate and diffusion mode in each region, and calculate the heat accumulation risk index in combination with the critical oxidation temperature of the titanium alloy to obtain heat accumulation mode data.

[0030] Optionally, according to the target monitoring area data, obtain the reflection spectrum information of the cutting area of the titanium alloy structural part and the comparison spectrum information of the adjacent uncut area to obtain spectral characteristic data, including:

[0031] Perform regional stratification processing on the target monitoring area data, divide the surface of the titanium alloy structural part into a core cutting area, an edge transition area, and a reference comparison area, and determine the acquisition frequency band of each area according to the spectral characteristic band of the titanium alloy to obtain spectral acquisition area data;

[0032] According to the spectral acquisition area data, perform multi-band spectral scanning on each area, identify the characteristic spectral peaks of the titanium alloy oxidation reaction, and calculate the spectral reflection intensity of different acquisition frequency bands to obtain multi-band spectral data;

[0033] Perform spatial distribution analysis on the multi-band spectral data, calculate the spectral intensity gradient between adjacent acquisition points, and analyze the spatial migration law of the characteristic spectral peaks to obtain spectral distribution characteristic data;

[0034] According to the spectral distribution characteristic data, perform comparative analysis on the spectral characteristics of the cutting area and the adjacent uncut area, calculate the spectral difference coefficient, and calculate the oxidation degree index in combination with the oxidation spectral characteristics of the titanium alloy to obtain spectral characteristic data.

[0035] Optionally, according to the spectral acquisition area data, perform multi-band spectral scanning on each area, identify the characteristic spectral peaks of the titanium alloy oxidation reaction, and calculate the spectral reflection intensity of different acquisition frequency bands to obtain multi-band spectral data, including:

[0036] Perform multi-band scanning on each area in the spectral acquisition area data, set the scanning band group based on the oxidation reaction characteristics of the titanium alloy, and classify and collect the spectral information of different bands to obtain band spectral data;

[0037] Perform characteristic peak identification on the band spectral data, calculate the peak position and peak intensity of the titanium alloy oxidation reaction in different bands, and analyze the evolution characteristics of the spectral peaks according to the growth law of the oxide film to obtain spectral peak characteristic data;

[0038] Based on the spectral peak characteristic data, calculate the spectral reflection intensity of different acquisition frequency bands, and perform intensity correction in combination with the energy coupling characteristics of the titanium alloy oxide film to obtain multi-band spectral data.

[0039] Optionally, perform spatio-temporal collaborative analysis on the spectral characteristic data, extract the spectral intensity change value, peak shape change value, and peak position drift value, and combine the spatial diffusion rate and time evolution data of the oxidation reaction to obtain oxidation state prediction data, including:

[0040] Perform time-segmented processing on the spectral characteristic data, calculate the characteristic change values of each time period according to the change rates of spectral intensity, peak shape, and peak position, and analyze the change trend in combination with the oxidation kinetic parameters of the titanium alloy to obtain time-sequence characteristic data;

[0041] Perform spatial mapping analysis on the time-sequence characteristic data, calculate the spectral characteristic difference values between adjacent regions, and determine the propagation direction and rate of the oxidation reaction according to the oxidation diffusion characteristics of the titanium alloy to obtain spatial propagation data;

[0042] According to the spatial propagation data, perform spatio-temporal coupling analysis on the diffusion process of the oxidation reaction, calculate the oxidation reaction activity index of different regions, and analyze the reaction chain effect in combination with the critical oxidation temperature of the titanium alloy to obtain oxidation state prediction data.

[0043] Optionally, according to the oxidation state prediction data, perform regional adjustment on the cutting power and perform dynamic compensation on the flow field parameters of the shielding gas to perform the cutting of the titanium alloy structural part, including:

[0044] Perform regional mapping on the oxidation state prediction data and the cutting path of the titanium alloy structural part, determine the energy coupling efficiency threshold and critical oxidation temperature of each region, and calculate the attenuation coefficient of the laser energy by the oxide layer thickness to obtain energy compensation parameters;

[0045] Based on the energy compensation parameters, calculate the cutting power correction values of the corner transition section, straight section, and curve section respectively, and calculate the power adjustment step according to the oxidation activity of the titanium alloy at different temperatures to obtain cutting parameter data;

[0046] Analyze the cutting parameter data, calculate the flow field deformation of the shielding gas in the high-temperature area, determine the pressure distribution characteristics of the gas flow disturbance area, and adjust the gas flow direction and flow rate according to the temperature field distribution of the cutting area to perform the cutting of the titanium alloy structural part.

[0047] The second aspect of the present invention provides an intelligent cutting device for a titanium alloy structural part, and the intelligent cutting device for the titanium alloy structural part includes:

[0048] A thermal field prediction module, which is used to analyze the change rate of the temperature gradient according to the temperature distribution data on the surface of the titanium alloy structural part, and determine the key areas prone to oxidation reaction in combination with the geometric characteristics of the titanium alloy structural part, so as to obtain the data of the target monitoring area;

[0049] A spectral acquisition module, which is used to obtain the reflection spectral information of the cutting area of the titanium alloy structural part and the comparison spectral information of the adjacent uncut area according to the data of the target monitoring area, so as to obtain spectral characteristic data;

[0050] An oxidation analysis module, which is used to perform spatio-temporal collaborative analysis on the spectral characteristic data, extract the spectral intensity change value, peak shape change value and peak position drift value, and combine the spatial diffusion rate and time evolution data of the oxidation reaction to obtain oxidation state prediction data;

[0051] A parameter regulation module, which is used to adjust the cutting power in regions according to the oxidation state prediction data, and dynamically compensate the flow field parameters of the protective gas, so as to perform the cutting of the titanium alloy structural part.

[0052] The technical solution provided by the embodiment of the present application preliminarily scans and analyzes the workpiece according to the temperature distribution data and geometric characteristics of the workpiece surface, and identifies the key areas prone to oxidation reaction. In this process, the temperature data of each point on the workpiece surface is obtained through thermal imaging technology, and the change rate of the temperature gradient is calculated. Combining the shape information of the workpiece (such as corners, grooves and thickness mutation areas), the areas with local heat accumulation are determined. Due to the low thermal conductivity of titanium alloy, the local temperature rise is more obvious, and the high chemical activity easily promotes the occurrence of oxidation reaction. Therefore, through this pre-screening step, the areas with higher oxidation risk can be locked before cutting, providing a clear target for subsequent real-time monitoring.

[0053] Next, in the determined key monitoring area, the reflection spectral data of the cutting area and the adjacent uncut area are collected through multi-band spectral acquisition technology. The key here is the comparative analysis. By collecting two groups of data simultaneously, the change in reflectivity caused by the formation of the oxide film can be captured more accurately. Since the formation of the oxide film will change the optical properties of the material surface, and these changes are different between different regions, the comparative acquisition not only helps to exclude environmental interference, but also highlights the subtle changes in spectral characteristics caused by oxidation. This step provides a direct and accurate physical signal for the subsequent dynamic monitoring of the oxidation state.

[0054] Next, spatiotemporal collaborative analysis is performed on the collected spectral feature data. In this process, the system not only focuses on the change in spectral intensity, but also statistically analyzes and analyzes multi-dimensional features such as spectral peak shape and peak position drift. At the same time, combining time series data and spatial diffusion information, the evolution trend of the oxidation reaction in the key area is modeled to predict the growth direction, diffusion rate and possible chain reaction of the oxide film. The key here is to quantify and track the dynamic change process so that the fluctuations in the oxidation state during the cutting process can be reflected in real time and form a set of index data for subsequent regulation. Through this detailed spatiotemporal data analysis, the system can identify the omen of the intensification of the oxidation reaction in advance, providing a timely basis for laser energy adjustment.

[0055] Finally, according to the predicted oxidation state data, the laser cutting parameters and the protective gas flow field are adjusted adaptively in a regional and dynamic manner. In specific operations, the system will adjust the output power of the laser according to the oxidation risk in different regions, and at the same time refine the management of the cutting path; in the regions with higher oxidation risk, the energy input will be appropriately reduced, and by changing the flow rate and flow direction of the protective gas, a locally stronger gas barrier will be formed to inhibit the rapid development of the oxidation reaction. The adjustment here is hierarchical: macroscopically, the overall cutting parameters are adjusted, mesoscopically, different settings are made according to the regional characteristics, and microscopically, fine energy compensation and air flow control are carried out. This linkage adjustment method ensures that the transmission of laser energy is more stable during the entire cutting process. Even if the reflectivity fluctuates due to the surface oxidation reaction, the energy coupling consistency can be maintained through real-time compensation.

[0056] Overall, this application fundamentally solves the problem of dynamic reflectivity change caused by the surface oxidation reaction of titanium alloy by identifying the key oxidation risk areas in advance, then using real-time and regional spectral monitoring to capture the surface oxidation dynamics, and finally through hierarchical regulation of laser power and gas flow parameters. Specifically, the comprehensive analysis of temperature data and geometric features enables the precise locking of the oxidation occurrence position; the real-time collection and comparison of spectral data clearly present the reflectivity change during the oxidation process; the spatiotemporal collaborative analysis converts these changes into predictable data indicators; and the final adaptive regulation can timely adjust the cutting process parameters according to the actual situation, so that the energy coupling between the laser and the workpiece surface remains stable, thus ensuring the cutting quality and accuracy. Through these four closely connected steps, the problem of unstable energy coupling caused by the surface oxidation reaction during the high-energy laser cutting of titanium alloy can be effectively solved. Description of the Drawings

[0057] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on the structures shown in these drawings.

[0058] Figure 1 It is a schematic diagram of an embodiment of the intelligent cutting method for titanium alloy structural parts in an embodiment of the present invention;

[0059] Figure 2 It is a schematic diagram of an embodiment of the intelligent cutting device for titanium alloy structural parts in an embodiment of the present invention;

[0060] Figure 3 It is a schematic diagram of an embodiment of the intelligent cutting equipment for titanium alloy structural parts in an embodiment of the present invention.

[0061] The realization of the objectives, functional features and advantages of the present invention will be further described in conjunction with the embodiments and with reference to the drawings. Specific embodiments

[0062] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0063] It should be noted that if there are directional indications (such as up, down, left, right, front, back...) involved in the embodiments of the present invention, the directional indications are only used to explain the relative position relationship and movement conditions between components in a specific posture (as shown in the drawings). If the specific posture changes, the directional indications will also change accordingly.

[0064] In addition, the descriptions involving "first", "second", etc. in the present invention are for descriptive purposes only, and should not be construed as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, "and / or" throughout the text includes three scenarios. Taking A and / or B as an example, it includes the technical solution of A, the technical solution of B, and the technical solution that both A and B are satisfied at the same time. In addition, the technical solutions between various embodiments can be combined with each other, which must be based on the fact that those skilled in the art can implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0065] An embodiment of the present application provides an intelligent cutting method for a titanium alloy structural part. Figure 1 It is a flowchart of an intelligent cutting method for a titanium alloy structural part provided by an embodiment of the present application. In this embodiment, the method includes:

[0066] Please refer to Figure 1 , analyze the change rate of the temperature gradient based on the temperature distribution data on the surface of the titanium alloy structural part, and combine the geometric characteristics of the titanium alloy structural part to determine the key areas prone to oxidation reaction, so as to obtain the data of the target monitoring area;

[0067] In an embodiment of the present invention, the process of obtaining the temperature distribution data on the surface of the titanium alloy structural part includes:

[0068] According to the cutting trajectory of the titanium alloy structural part, divide the cutting path into straight segments, corner segments and curve segments, and determine the heat accumulation characteristics of different types of segments according to the thermal conductivity parameters of the titanium alloy, so as to obtain the heat accumulation characteristic marking data;

[0069] According to the heat accumulation characteristic marking data, establish an initial heat conduction prediction band along the cutting trajectory, and the width and shape of the initial heat conduction prediction band are adapted to the heat accumulation characteristics of different cutting segments, so as to obtain the prediction band contour data;

[0070] Based on the prediction band contour data, set up an array of temperature monitoring points, perform real-time temperature acquisition on the array of temperature monitoring points, and calculate the heat diffusion direction and rate according to the temperature change trend, so as to obtain the heat conduction characteristic data;

[0071] According to the heat conduction characteristic data, perform dynamic spatial clustering on the temperature abnormal points, and combine the heat diffusion direction and rate to adjust the boundary of the clustering area, so as to generate the temperature distribution data on the surface of the titanium alloy structural part.

[0072] The following is a specific description of the steps involved in the above embodiments: First, according to the cutting trajectory of the titanium alloy structural part, the cutting path is divided in detail, and the path is divided into straight segments, corner segments, and curved segments. This process is achieved by digitizing the workpiece CAD data or high-precision scanned images, using conventional design software to automatically identify the straight and curved parts, and judging the corner areas according to the geometric shape. Subsequently, combined with the known thermal conductivity parameters of titanium alloy, the heat accumulation characteristics of different types of segments are quantitatively analyzed. The straight segment is expected to have low heat accumulation due to its stable direction and uniform heat flow distribution; while the corner segment and the curved segment have high heat accumulation because of the sharp direction changes, and the local heat is difficult to spread quickly. This step uses standard digital image processing techniques and mathematical models to analyze the cutting trajectory and generate the heat accumulation characteristic marking data for each segment; in some alternative solutions, manual marking or simplified models can be used for preliminary judgment. This step realizes an accurate quantitative description of the heat behavior in each area of the cutting path, provides data support for the subsequent delineation of the heat conduction area, and clarifies the risk distribution of heat accumulation.

[0073] In the second step, according to the heat accumulation characteristic marking data obtained above, an initial heat conduction prediction band is established along the cutting trajectory. The specific method is to use computer simulation methods to determine the width and shape of the prediction band according to the heat accumulation characteristics of each cutting segment: the prediction band corresponding to the straight segment is narrower, while the corner segment and the curved segment require wider or asymmetrically distributed prediction bands to adapt to the local heat conduction characteristics. A common finite element analysis software is used to simulate the heat conduction situation in the cutting area, combining the thermal conductivity coefficient of titanium alloy with the geometric data to generate a set of prediction band contour data, which details the heat conduction influence range of each area. As an alternative, an analytical heat conduction model can also be used for rough estimation. The prediction band contour data obtained in this step provides an accurate spatial reference for the arrangement of temperature monitoring points, ensuring that the key monitoring areas cover the actual range of heat flow diffusion.

[0074] In the third step, based on the prediction band contour data obtained in the second step, a temperature monitoring point array is set up, and real-time temperature acquisition is carried out on this array. The specific method is to arrange conventional thermocouples or standard infrared temperature sensors in the prediction band according to certain rules, or a high-resolution infrared thermal imager can also be used to continuously scan the specified area. The sensors output temperature data in real time through the data acquisition system, and use digital signal processing technology to calculate the temperature change trend. Further, according to the temperature gradient and time series, the numerical differential method is used to solve the heat diffusion direction and diffusion rate, forming detailed heat conduction characteristic data. Alternative solutions include using fixed sampling points and regional average temperature values for simplified analysis. This step realizes the real-time monitoring of the dynamic changes of the workpiece surface temperature, provides accurate data basis for reflecting the heat conduction characteristics, and ensures that the temperature acquisition coverage area is consistent with the prediction band.

[0075] In the fourth step, based on the heat conduction characteristic data obtained in the third step, dynamic spatial clustering is performed on the temperature anomaly points. Using a density-based spatial clustering algorithm, the acquisition points in the temperature data that are higher than the set threshold are aggregated into one or more regions, and then, in combination with the previously calculated heat diffusion direction and rate, the boundaries of each clustering region are automatically adjusted to more accurately reflect the actual heat diffusion situation. During the implementation process, the common algorithm generates the adjusted contour of the temperature anomaly region by processing the sensor coordinates and temperature values; image segmentation technology can be selected to process the infrared thermal image to obtain a similar effect. The temperature distribution data on the surface of the titanium alloy structural part generated in this step accurately depicts the local heat accumulation and diffusion, providing an accurate thermal state map for subsequent process control. Through this method, the temperature anomaly region is accurately located and its boundary is optimized, ensuring that the heat conduction characteristics are fully reflected in space, thereby providing a basis for energy compensation during the laser cutting process.

[0076] In an embodiment of the present invention, analyzing the change rate of the temperature gradient based on the temperature distribution data on the surface of the titanium alloy structural part, and combining the geometric characteristics of the titanium alloy structural part to determine the key regions prone to oxidation reaction, to obtain the target monitoring region data, includes:

[0077] Performing a gradient scan on the temperature distribution data on the surface of the titanium alloy structural part, calculating the change rate of the temperature gradient, and partitioning the surface of the titanium alloy structural part according to the change rate to obtain heat distribution characteristic data;

[0078] Performing geometric feature analysis on the surface contour of the titanium alloy structural part, identifying the corner transition region, the groove convergence region, and the thickness mutation region, and combining the heat distribution characteristic data to determine the heat accumulation risk of each characteristic region to obtain region risk characteristic data;

[0079] According to the region risk characteristic data, combining the thermal conductivity parameter of titanium alloy to calculate the heat transfer rate between different characteristic regions, and analyzing the heat interaction relationship between adjacent regions to obtain heat transfer chain data;

[0080] Based on the heat transfer chain data, combining the oxidation activity parameter of titanium alloy, calculating the oxidation reaction probability of each region, and analyzing the chain propagation law of the oxidation reaction to obtain the target monitoring region data.

[0081] The following is a specific description of the steps involved in the above embodiments: First step, perform a gradient scan on the temperature distribution data on the surface of the titanium alloy structural part. First, use an infrared thermal imager or a thermocouple array to collect the temperature data of each point on the titanium alloy surface, and discretize the temperature distribution image through image processing software to form a digital matrix. Subsequently, use the numerical differentiation method to calculate the gradient of the temperature matrix to obtain the numerical data of the temperature change rate at each position; for example, use the two-dimensional difference formula to calculate the gradient value of each pixel point, where each parameter in the formula represents the change amount of temperature in the horizontal and vertical directions respectively. The calculated gradient change rate data will be divided into heat zones according to the set threshold, that is, the surface is divided into high, medium, and low heat accumulation zones according to the magnitude of the temperature gradient value; an alternative is to use an algorithm based on edge detection for gradient scanning. This step obtains detailed heat distribution characteristic data by quantitatively describing the local heat flow change, providing a numerical basis for the subsequent risk assessment of the area.

[0082] Second step, perform geometric feature analysis on the surface contour of the titanium alloy structural part. Use common edge detection and curvature analysis algorithms to extract the contour of the digital image of the titanium alloy surface, so as to identify the corner transition zone, the groove convergence zone, and the thickness mutation zone; for example, by calculating the curvature value of each point on the surface, when the curvature value exceeds the preset threshold, mark this position as a geometric mutation point. Combine the extracted geometric features with the heat distribution characteristic data obtained in the first step, and quantitatively evaluate the heat accumulation risk of each characteristic area according to the heat density distribution in each area; an alternative is to use morphological filtering processing for area recognition. The area risk characteristic data generated in this step clearly indicates the strength of heat accumulation in each geometric feature area on the workpiece surface, reflecting the risk differences in heat accumulation in different areas, and providing a basis for area division for subsequent heat transfer analysis.

[0083] Step 3: According to the regional risk characteristic data, combine the thermal conductivity parameters of titanium alloy to calculate the heat transfer rate between different characteristic regions. Using the classical heat conduction law, calculate the heat flux density between regions. The calculation formula for the heat flux density q is: q = -k·(ΔT / Δx), where q represents the local heat flux density (unit: W / m²), k represents the thermal conductivity of titanium alloy (unit: W / (m·K)), ΔT is the temperature difference between adjacent regions (unit: K), and Δx is the distance between two regions (unit: m). Using the temperature difference value and spatial distance within each region in the regional risk characteristic data, obtain the heat transfer rate between regions. Further, analyze the heat interaction relationship between adjacent regions, model the heat transfer process through numerical simulation or finite element analysis software, and generate heat transfer chain data describing the heat flow transfer path and its intensity; an alternative is to use a model based on statistical distribution to estimate the heat transfer rate. This step realizes a quantitative description of the heat transfer dynamics between regions of the workpiece, provides detailed data for identifying heat flow interactions, and ensures that the heat transfer chain data truly reflects the actual heat flow evolution.

[0084] Step 4: Based on the heat transfer chain data, combine the oxidation activity parameters of titanium alloy to calculate the oxidation reaction probability of each region, and analyze the chain propagation law of the oxidation reaction. According to the kinetic theory of oxidation reaction, a mathematical model similar to the Arrhenius equation can be used to calculate the local oxidation reaction probability P, and its formula is:

[0085] ;

[0086] where P is the oxidation reaction probability, A is the pre-exponential factor (the unit is related to the reaction rate), is the activation energy of the oxidation reaction (unit: J / mol), R is the gas constant (about 8.314 J / (mol·K)), and T is the absolute temperature within the region (unit: K). Combining the heat transfer chain data obtained in Step 3, analyze the influence of temperature changes and heat flux distribution in each region on the oxidation reaction, establish an oxidation reaction propagation model between regions, and thus obtain the data of the target monitoring region. By comprehensively considering heat transfer and temperature factors, this model quantitatively calculates the oxidation risk of each region in the actual laser cutting environment; alternative solutions include data-driven prediction models, but using the kinetic formula can more directly reflect the oxidation activity of the material.

[0087] In an embodiment of the present invention, geometric feature analysis is performed on the surface profile of the titanium alloy structural member to identify the corner transition region, groove convergence region, and thickness mutation region, and in combination with the heat distribution characteristic data, determine the heat accumulation risk of each characteristic region to obtain regional risk characteristic data, including:

[0088] Perform curvature analysis on the surface profile of the titanium alloy structural part, calculate the curvature values of each point on the surface, identify geometric feature mutation points based on the change rate of the curvature values, and obtain feature point distribution data;

[0089] According to the feature point distribution data, perform connectivity analysis on adjacent feature points, divide the corner transition area, groove convergence area, and thickness mutation area, and calculate the area and depth parameters of each area to obtain feature area parameter data;

[0090] Perform cross-mapping on the feature area parameter data and the heat distribution feature data, calculate the heat density value in each feature area, and analyze the heat flow trend in the feature area to obtain heat accumulation pattern data;

[0091] According to the heat accumulation pattern data, combined with the specific heat capacity parameter of titanium alloy, calculate the heat storage capacity and heat diffusion coefficient of each feature area to obtain regional risk feature data.

[0092] The following is a specific description of the steps involved in the above embodiments: The first step is to use digital image processing technology to collect and perform curvature analysis on the profile of the workpiece surface. First, obtain a high-resolution image of the surface of the titanium alloy structural part through an industrial camera or a laser scanner, and use image processing software to extract the edge of the workpiece surface to form digital contour data. Then, use the discrete differential method or the local polynomial fitting technique to calculate the curvature values of each point on the contour, and determine the geometric feature mutation points according to the change rate of the curvature values of adjacent sampling points. Record the spatial coordinates of the mutation points, which forms the feature point distribution data. This method ensures the accurate capture of the geometric change information on the workpiece surface and provides a detailed geometric basis for subsequent area division.

[0093] The second step is to perform connectivity analysis on adjacent feature points according to the feature point distribution data obtained in the first step to divide different geometric feature areas. Use the connected component analysis algorithm (such as the findContours method based on OpenCV) to group adjacent feature points in the image, and then identify the corner transition area, groove convergence area, and thickness mutation area. In each divided area, obtain the area of the area by using the polygon area calculation formula (such as calculating the area of continuous boundary points) after extracting the area boundary, and at the same time use a laser rangefinder or a 3D scanner to obtain the local thickness data in the area to obtain the depth parameter. The generated feature area parameter data contains the area and depth information of each area, and such quantitative description can accurately reflect the geometric features of each area on the workpiece surface.

[0094] In the third step, cross-map the characteristic region parameter data obtained in the second step with the heat distribution characteristic data, and then calculate the heat density values within each characteristic region and analyze the heat flow trend. First, align the temperature distribution with the coordinate system of the workpiece surface based on the temperature data collected by the infrared thermal imager or thermocouple array. Statistically analyze the temperature monitoring points within each characteristic region, calculate the average temperature or cumulative temperature value within the region, and then divide by the region area to obtain the heat density value. Combining the time-series temperature data, describe the flow direction and rate of heat within the region through vector field analysis methods, and then construct the heat accumulation pattern data. This method realizes the precise matching of geometric regions and local heat data, and truly reflects the heat distribution and dynamic changes within each region.

[0095] In the fourth step, based on the heat accumulation pattern data obtained in the third step, combined with the thermal physical properties parameters of titanium alloy, quantitatively calculate the heat storage capacity and heat diffusion coefficient of each characteristic region, so as to form the regional risk characteristic data. First, obtain the area and thickness data of each characteristic region through digital image processing and three-dimensional scanning, and record them respectively as (region area, unit: m²) and (region thickness, unit: m). Using the known density of titanium alloy material (unit: kg / m³), calculate the mass of each region, and the formula is:

[0096] ;

[0097] where represents the mass of the characteristic region (unit: kg).

[0098] Next, based on the temperature change range (unit: K) within the region and the specific heat capacity (unit: J / (kg·K)) of titanium alloy, the formula for calculating the heat storage capacity is:

[0099] ;

[0100] This formula quantitatively describes the heat stored in each region. At the same time, according to the thermal conductivity (unit: W / (m·K)) of titanium alloy, use the relationship of heat diffusion:

[0101] ;

[0102] Calculate the heat diffusion coefficient , reflecting the rate of heat diffusion within the region. By comprehensively evaluating the heat density, heat storage capacity, and diffusion coefficient of each region, the generated regional risk characteristic data can accurately describe the heat accumulation and diffusion risks in each characteristic region during the laser cutting process, thereby providing a quantitative basis for the precise regulation of process parameters.

[0103] In one embodiment of the present invention, the cross-mapping of the characteristic region parameter data and the heat distribution characteristic data, calculating the heat density values within each characteristic region, and analyzing the heat flow trend within the characteristic region to obtain the heat accumulation pattern data includes:

[0104] Calculating the weights of the region area and depth parameters in the characteristic region parameter data to generate a region shape coefficient, and correcting each region shape coefficient according to the thermal conductivity characteristics of titanium alloy to obtain region characteristic weight data;

[0105] According to the region characteristic weight data, dividing the heat distribution characteristic data into regions, and calculating the heat density gradient and heat flow direction within each region to obtain the heat flow distribution data;

[0106] Performing a time series analysis on the heat flow distribution data, calculating the change rate of the heat density in each region, and analyzing the residence time of heat in the region in combination with the thermal diffusion coefficient of titanium alloy to obtain the heat residence characteristic data;

[0107] According to the heat residence characteristic data, analyzing the heat accumulation rate and diffusion mode of each region, and calculating the heat accumulation risk index in combination with the critical oxidation temperature of titanium alloy to obtain the heat accumulation pattern data.

[0108] The following is a specific description of the steps involved in the above embodiment: First step, using the region area and depth parameters in the characteristic region parameter data for weight calculation. First, extract the area data (denoted as , unit: square meter) and region depth data (denoted as , unit: meter) of each characteristic region from the three-dimensional scan data through digital image processing methods. Adopting a calculation method based on the ratio of area to depth, generate a region shape coefficient, and the calculation method is to normalize and and combine them into a dimensionless coefficient, which quantitatively describes the geometric shape of the region. Subsequently, according to the thermal conductivity characteristics of titanium alloy, correct the region shape coefficient. Here, a conventional material heat conduction model is used, and the known thermal conductivity of titanium alloy (denoted as , with the unit of W / (m·K)) as a correction factor to adjust the shape factor to reflect the ease of heat conduction in the region, thereby generating regional characteristic weight data. While ensuring the accurate quantification of the regional geometric characteristics of the data, this method incorporates the thermal physical property parameters of the material and can better predict local heat conduction behavior. As an alternative, other normalization methods can be used, but the method combined with thermal conductivity correction has a more explicit physical meaning.

[0109] In the second step, the heat distribution characteristic data is divided into regions according to the regional characteristic weight data, and the heat density gradient and heat flow direction within each region are calculated. The overall heat distribution map is divided into several sub-regions according to the regional characteristic weight data by using a spatial segmentation algorithm, and each sub-region corresponds to a region with relatively uniform geometric characteristics. Subsequently, by performing discrete gradient calculations on the temperature field data within each sub-region, the heat density gradient is obtained, which is a quantitative description of the temperature change per unit distance; at the same time, the vector field analysis method is used to statistically analyze the gradient direction of the temperature field to determine the main heat flow direction within the region. This step uses common image segmentation and gradient calculation algorithms to convert continuous temperature data into spatial data reflecting heat flow characteristics, effectively revealing the dynamic distribution of local heat transfer. As an alternative, the optical flow method can be selected, but gradient analysis and vector field statistics are more intuitive in terms of numerical accuracy.

[0110] In the third step, time series analysis is performed on the heat flow distribution data to calculate the change rate of the heat density in each region, and the residence time of heat in the region is analyzed in combination with the thermal diffusivity of titanium alloy. The temperature data within each sub-region is collected in real time using a thermal sensor or an infrared thermal imager, and numerical differentiation calculations are performed on the time series data to obtain the heat density change rate, which is the change amplitude of the heat density per unit time. At the same time, the obtained change rate is combined with the thermal diffusivity of titanium alloy (denoted as , with the unit of m² / s, calculated according to the formula , where is the density, is the specific heat capacity) to evaluate the residence time of heat in space within each region using heat conduction theory. This analysis method can quantitatively describe the evolution of heat in the region over time and provide dynamic data support for subsequent risk assessment. Alternative methods include using numerical simulation means, but direct time series analysis can more timely reflect the thermal dynamics in the actual processing environment.

[0111] In the fourth step, based on the heat residence characteristic data, the heat accumulation rate and diffusion mode of each region are analyzed, and the heat accumulation risk index is calculated in combination with the critical oxidation temperature of titanium alloy. For each sub-region, the heat accumulation rate is calculated according to the aforementioned time series analysis results, and the diffusion pattern of heat in space is described in combination with the heat diffusion mode within the region. Using the critical oxidation temperature of titanium alloy (denoted as ), for reference, compare the actual temperature peak with and calculate the heat accumulation risk index by setting a weighted formula. This index quantitatively describes the risk degree of heat exceeding the safety threshold in the region. The generated heat accumulation pattern data can reflect the possibility of oxidation reactions caused by heat accumulation in each characteristic region during the laser cutting process, thereby providing a quantitative risk basis for the real-time regulation of the cutting process. An alternative can be a risk prediction model based on machine learning, but the weighted calculation method combined with the critical oxidation temperature is more physically based in theory.

[0112] Please continue to refer to Figure 1 and obtain the reflected spectral information of the cutting area of the titanium alloy structural part and the comparative spectral information of the adjacent uncut area according to the data of the target monitoring area to obtain spectral characteristic data;

[0113] In an embodiment of the present invention, the obtaining the reflected spectral information of the cutting area of the titanium alloy structural part and the comparative spectral information of the adjacent uncut area according to the data of the target monitoring area to obtain spectral characteristic data includes:

[0114] Perform regional stratification processing on the data of the target monitoring area, divide the surface of the titanium alloy structural part into a core cutting area, an edge transition area, and a reference comparison area, and determine the acquisition frequency bands of each area according to the spectral characteristic bands of the titanium alloy to obtain spectral acquisition area data;

[0115] According to the spectral acquisition area data, perform multi-band spectral scanning on each area, identify the characteristic spectral peaks of the oxidation reaction of the titanium alloy, and calculate the spectral reflection intensity of different acquisition frequency bands to obtain multi-band spectral data;

[0116] Perform spatial distribution analysis on the multi-band spectral data, calculate the spectral intensity gradient between adjacent acquisition points, and analyze the spatial migration law of the characteristic spectral peaks to obtain spectral distribution characteristic data;

[0117] According to the spectral distribution characteristic data, perform comparative analysis on the spectral characteristics of the cutting area and the adjacent uncut area, calculate the spectral difference coefficient, and calculate the oxidation degree index in combination with the oxidation spectral characteristics of the titanium alloy to obtain spectral characteristic data.

[0118] The following is a specific description of the steps involved in the above embodiments: In the first step, based on the data of the target monitoring area, regional hierarchical processing is adopted to divide the surface of the titanium alloy structural part into a core cutting area, an edge transition area, and a reference comparison area. The specific method is to divide the surface of the workpiece into three hierarchical areas according to the temperature distribution and cutting requirements by using infrared thermal imaging data or digital image processing results. Among them, the core cutting area is the key area for laser cutting, the edge transition area is the area where the temperature and oxidation reaction change relatively gently, and the reference comparison area is the area not affected by cutting. Common image segmentation algorithms (such as threshold segmentation, region growing algorithm) are used to process the digital image, and combined with the region information predefined in the workpiece design drawing, accurate division is achieved. Subsequently, according to the characteristic spectral bands shown by titanium alloy during the oxidation process, the frequency bands to be collected in each area are determined. For example, a narrower band is used in the core area to cover high oxidation-sensitive signals, while a wider band is used in the reference area for comparison. This step obtains accurate spectral acquisition area data through regional stratification and acquisition frequency band setting, providing clear spatial and frequency information for subsequent multi-band scanning; an alternative is to use manual assistance to divide the area, but the automatic stratification method has data processing consistency and efficiency.

[0119] In the second step, based on the spectral acquisition area data obtained in the first step, multi-band spectral scanning is performed on each area. A conventional programmable fiber optic spectrometer is used to scan each preset area separately to collect multi-band spectral data including ultraviolet, visible, and near-infrared. The instrument records the reflection spectra in each band according to the set acquisition frequency band, and the data output is the spectral reflection intensity of different acquisition frequency bands. The algorithm built into the system uses feature peak recognition technology to detect the typical peaks that appear in the titanium alloy during the oxidation reaction, such as the abnormal reflectivity at a specific wavelength caused by the formation of the oxide film. This method can accurately capture different spectral information through multi-band scanning, realizing quantitative recording of the spectral characteristics of the oxidation reaction in the area; an alternative is single-band acquisition, but multi-band scanning can more comprehensively reflect the dynamic changes of the oxidation reaction.

[0120] In the third step, spatial distribution analysis is performed on the multi-band spectral data obtained in the second step. Digital signal processing technology is used to arrange the spectral reflection intensity data of each acquisition point according to its spatial coordinates, and calculate the spectral intensity gradient between adjacent acquisition points, that is, quantitatively describe the rate of change of the spectral signal in the local area; at the same time, analyze the position migration law of the characteristic peaks in space, and judge the direction and amplitude of the peak movement through statistical methods, so as to reflect the evolution characteristics of the local oxidation reaction in the spatial distribution. Common image processing algorithms (such as gradient operators, edge detection) are used to calculate and analyze the spatial changes of the spectral data to obtain spectral distribution characteristic data reflecting the spatial distribution of heat or oxidation effects; an alternative can be a clustering method based on local statistical features, but gradient and migration law analysis more intuitively describes the spectral change trend.

[0121] In the fourth step, based on the spectral distribution characteristic data obtained in the third step, the spectral characteristics of the cutting area and the adjacent uncut area are compared and analyzed. The specific operation is to calculate the spectral data of the cutting area and the reference comparison area point by point or by regional average value, and then determine the spectral difference coefficient through data comparison. This coefficient quantitatively reflects the amplitude of the spectral change caused by the oxidation reaction in the cutting area. Subsequently, combined with the typical spectral characteristics in the oxidation reaction of titanium alloy, the oxidation degree index is calculated based on the preset threshold and oxidation spectral characteristic parameters to quantify the formation of the oxide film in the cutting area. This comparative analysis provides objective data reflecting the surface oxidation of the material during the laser cutting process through clear spectral differences and oxidation indices, facilitating the dynamic adjustment of subsequent cutting parameters; as an alternative, data fitting or statistical test methods can be used, but direct comparison and index calculation can more intuitively reveal the degree of oxidation.

[0122] In one embodiment of the present invention, according to the spectral acquisition area data, multi-band spectral scanning is performed on each area to identify the characteristic spectral peaks of the oxidation reaction of titanium alloy, and the spectral reflection intensities of different acquisition frequency bands are calculated to obtain multi-band spectral data, including:

[0123] Perform multi-band scanning on each area in the spectral acquisition area data, set a scanning band group based on the oxidation reaction characteristics of titanium alloy, and classify and collect the spectral information of different bands to obtain band spectral data;

[0124] Perform characteristic peak identification on the band spectral data, calculate the peak positions and peak intensities of the oxidation reaction of titanium alloy in different bands, and analyze the evolution characteristics of the spectral peaks according to the growth law of the oxide film to obtain peak characteristic data;

[0125] According to the peak characteristic data, calculate the spectral reflection intensities of different acquisition frequency bands, and perform intensity correction in combination with the energy coupling characteristics of the titanium alloy oxide film to obtain multi-band spectral data.

[0126] The following is a specific description of the steps involved in the above embodiments: First step, use a conventional programmable fiber optic spectrometer to perform multi-band scanning on each region in the spectral acquisition area data. The specific method is as follows: According to the typical spectral characteristics exhibited by titanium alloy during the oxidation reaction, a scanning band group is set in advance. These bands include the ultraviolet, visible, and near-infrared regions, which can fully cover the characteristic signals that appear during the oxidation process. The instrument classifies and collects each target region according to the preset band group, records the spectral information of different bands within each region separately, and outputs the band spectral data. The digital signal processing system stores the collected data by region and band, while ensuring the spatio-temporal synchronization of each data channel. This method uses common spectral acquisition equipment and can be replaced by manually setting the scanning bands or using an automatic band adjustment algorithm. However, multi-band classification collection can more comprehensively reflect the characteristics of the oxidation reaction, ensuring that the output band spectral data can cover the information of each key band during the material oxidation process, thereby providing an accurate basis for the original spectral data.

[0127] Second step, perform characteristic peak identification on the obtained band spectral data. Using digital signal processing technology and spectral data analysis algorithms, automatically extract the peak positions and peak intensities of the reflection spectra in each band of data. The spectral analysis software built into the instrument identifies the characteristic spectral peaks that appear during the titanium alloy oxidation reaction according to the set threshold and signal-to-noise ratio criteria. Subsequently, in combination with the growth law of the oxide film, track the evolution trend of the spectral peaks in terms of time and space, record the movement of the spectral peak positions and the changes in intensity, and output the spectral peak characteristic data. This process can be achieved through common peak detection algorithms, or graphical processing or pattern recognition techniques can be used to assist in judging the data. The implementation of this step ensures the quantitative description of the key spectral characteristics during the oxidation process, enabling the spectral peak characteristic data to accurately reflect the dynamic changes in the oxidation reaction state and providing a clear basis for subsequent data correction.

[0128] In the third step, by analyzing the previously obtained spectral peak feature data, the original spectral reflection intensity of each acquisition frequency band is quantitatively calculated, and the data is intensity-corrected in combination with the energy coupling characteristics of the titanium alloy oxide film. The specific method is as follows: Under laboratory conditions, multi-band spectral measurements are carried out on standard titanium alloy samples in different oxidation states, the reflection intensity data of each band are collected, and the corresponding oxidation state parameters are recorded. Using these experimental data, a correction model is constructed through regression analysis or curve fitting methods. This model establishes a mapping relationship between the original reflection intensity of each band and the influence of the oxide film on the laser energy coupling, so as to determine the correction factor for each band. In the actual processing process, the reflection intensity in the original spectral data of each region is corrected by applying the corresponding correction factor according to its acquisition band, and the adjusted multi-band spectral data is generated. This correction process ensures that the output spectral data can truly reflect the influence of the change in the oxidation state of the titanium alloy surface on energy coupling during the laser cutting process, providing an accurate and reliable spectral basis for subsequent oxidation state analysis and process control.

[0129] Please continue to refer to Figure 1 , perform spatio-temporal collaborative analysis on the spectral feature data, extract the spectral intensity change value, peak shape change value, and peak position drift value, and combine the spatial diffusion rate and time evolution data of the oxidation reaction to obtain oxidation state prediction data;

[0130] In an embodiment of the present invention, the performing spatio-temporal collaborative analysis on the spectral feature data, extracting the spectral intensity change value, peak shape change value, and peak position drift value, and combining the spatial diffusion rate and time evolution data of the oxidation reaction to obtain oxidation state prediction data includes:

[0131] Perform time-sequence segmentation processing on the spectral feature data, calculate the characteristic change values of each time period according to the change rates of spectral intensity, peak shape, and peak position, and analyze the change trend in combination with the oxidation kinetic parameters of the titanium alloy to obtain time-sequence characteristic data;

[0132] Perform spatial mapping analysis on the time-sequence characteristic data, calculate the spectral feature difference values between adjacent regions, and determine the propagation direction and rate of the oxidation reaction according to the oxidation diffusion characteristics of the titanium alloy to obtain spatial propagation data;

[0133] According to the spatial propagation data, perform spatio-temporal coupling analysis on the diffusion process of the oxidation reaction, calculate the oxidation reaction activity index of different regions, and analyze the reaction chain effect in combination with the critical oxidation temperature of the titanium alloy to obtain oxidation state prediction data.

[0134] The following is a specific description of the steps involved in the above embodiments: First step, perform time-series segmentation processing on the spectral feature data. Using the continuous spectral data obtained from the spectral acquisition area, perform segmentation processing on the acquired data on the time axis through digital signal processing software. Each segment corresponds to the spectral record within a certain period of time. Adopt methods based on data smoothing and differential analysis to quantitatively calculate the spectral intensity, peak shape, and peak position changes within each segment, thereby generating a characteristic change value for each time period. At the same time, in combination with the oxidation kinetic parameters of titanium alloy (such as material parameters like oxidation reaction rate constant, activation energy, etc.), perform trend analysis on the characteristic change values of each time period to form time-series characteristic data describing the dynamic evolution of the oxidation process. This step uses digital signal processing and statistical analysis methods to achieve quantitative division and description of the change trend of continuous spectral data in the time domain, ensuring that the data can reflect the real-time dynamics of the oxidation reaction during the laser cutting process.

[0135] Second step, perform spatial mapping analysis on the time-series characteristic data. Using the aforementioned time-series characteristic data, by associating the spectral characteristic values corresponding to each time period with the specific positions on the workpiece surface, adopt a spatial mapping algorithm to perform comparative calculations on the spectral characteristics at each position within the acquisition area, and obtain the spectral characteristic difference values between adjacent areas. According to the oxidation diffusion characteristics of titanium alloy, determine the propagation direction and rate of the oxidation reaction diffusion on the workpiece surface by comparing the characteristic differences between different areas. This method uses image processing and data comparison techniques to accurately correspond the time-series data with the spatial coordinates. The output spatial propagation data can intuitively reflect the diffusion path and diffusion speed of the oxidation reaction within the local area, providing a quantitative basis for subsequent dynamic regulation.

[0136] Third step, perform spatio-temporal coupling analysis based on the spatial propagation data. Combine the spatial propagation data with the corresponding time-series information, and adopt comprehensive data analysis methods to perform coupling analysis on the oxidation reaction diffusion process in each area on the workpiece surface, and calculate the oxidation reaction activity index for each area. This activity index reflects the intensity and diffusion trend of the oxidation reaction within each area. During the analysis, in combination with the critical oxidation temperature of titanium alloy, compare the actual temperature within the area with the material oxidation critical temperature, thereby quantifying the reaction chain effect. The finally generated oxidation state prediction data provides an accurate description of the oxidation risk for real-time regulation during the laser cutting process and can guide the adjustment of process parameters to ensure the stable transmission of laser energy during the cutting process.

[0137] Please continue to refer to Figure 1 , according to the oxidation state prediction data, adjust the cutting power in different areas and perform dynamic compensation on the flow field parameters of the shielding gas, and perform the cutting of the titanium alloy structural part.

[0138] In an embodiment of the present invention, performing cutting of the titanium alloy structural member by adjusting the cutting power in regions according to the oxidation state prediction data and dynamically compensating the flow field parameters of the shielding gas includes:

[0139] Performing a partition mapping on the oxidation state prediction data and the cutting path of the titanium alloy structural member, determining the energy coupling efficiency threshold and the critical oxidation temperature of each region, calculating the attenuation coefficient of the laser energy by the oxidation layer thickness, and obtaining the energy compensation parameter;

[0140] Based on the energy compensation parameter, respectively calculating the cutting power correction values for the corner transition section, the straight section, and the curve section, and calculating the power adjustment step according to the oxidation activity of the titanium alloy at different temperatures, to obtain the cutting parameter data;

[0141] Analyzing the cutting parameter data, calculating the flow field deformation of the shielding gas in the high-temperature region, determining the pressure distribution characteristics of the gas flow disturbance region, and adjusting the gas flow direction and flow rate according to the temperature field distribution of the cutting region, to perform the cutting of the titanium alloy structural member.

[0142] The following specifically describes the steps involved in the above embodiment: First step, performing a partition mapping on the oxidation state prediction data and the cutting path of the titanium alloy structural member. Using the digital cutting path data and the real-time collected oxidation state data, through an image processing software, the area mapping is realized, and the entire cutting path is divided into several independent regions. In each region, according to the monitoring data, the threshold of the laser energy coupling efficiency and the critical temperature shown by the material in the oxidation reaction are determined. Using a conventional optical or infrared microscope instrument to detect the surface of each region, obtaining the oxidation layer thickness information, and combining the quantitative relationship between the oxidation layer and the laser energy attenuation previously determined by experiments, calculating the weakening degree of the laser energy by the unit thickness oxidation layer. Multiplying the oxidation layer thickness by this weakening degree to obtain the energy compensation parameter for each region. This method realizes a quantitative description of the laser energy attenuation caused by oxidation in different regions on the cutting path through accurate mapping and empirical data correction.

[0143] Step 2: Based on the obtained energy compensation parameters, calculate the cutting power correction values for the corner transition section, straight section, and curved section respectively. First, divide the cutting path into three section types according to geometric characteristics, and then combine the energy compensation parameters of each region with the laser cutting data obtained from pre-experiment calibration to dynamically adjust and calculate the laser power for each region. Using standard digital signal processing techniques, compare the actual laser power with the theoretical correction value, and determine a power adjustment step size as the minimum adjustment unit of the laser power based on the oxidation activity of titanium alloy under different temperature conditions. The finally output cutting parameter data includes the laser power correction value required for each cutting section and the corresponding adjustment step size, thereby achieving precise control of the laser energy in different geometric sections.

[0144] Step 3: After parsing the cutting parameter data, adjust the state of the shielding gas flow field in the high-temperature region. Use high-precision pressure sensors and infrared thermal imagers to collect temperature and airflow data in real time in the cutting area, quantify the deformation of the shielding gas flow field in the high-temperature region through digital signal processing techniques, and obtain the pressure distribution characteristics of the disturbed area. Subsequently, compare these pressure and temperature data to determine the position and degree of the airflow disturbance area, and adjust the flow direction and flow rate of the shielding gas (such as nitrogen or argon) supply system based on this information to ensure a stable gas barrier during the cutting process. This method directly uses the real-time data of the sensors and known physical correlations to achieve dynamic regulation of the shielding gas flow field, thereby ensuring the stability of the energy transfer between the laser and the workpiece surface and ensuring the high precision and consistency of the cutting process.

[0145] The intelligent cutting method for titanium alloy structural parts in the embodiments of the present invention has been described above. Next, the intelligent cutting device for titanium alloy structural parts in the embodiments of the present invention will be described. Please refer to Figure 2 , an embodiment of the intelligent cutting device for titanium alloy structural parts in the embodiments of the present invention includes:

[0146] A thermal field prediction module 101, configured to analyze the change rate of the temperature gradient based on the temperature distribution data on the surface of the titanium alloy structural part, and determine the key areas prone to oxidation reaction in combination with the geometric characteristics of the titanium alloy structural part to obtain the target monitoring area data;

[0147] A spectrum acquisition module 102, configured to obtain the reflection spectrum information of the cutting area of the titanium alloy structural part and the comparison spectrum information of the adjacent uncut area according to the target monitoring area data to obtain spectrum feature data;

[0148] An oxidation analysis module 103, configured to perform spatio-temporal collaborative analysis on the spectrum feature data, extract the spectrum intensity change value, peak shape change value, and peak position drift value, and combine the spatial diffusion rate and time evolution data of the oxidation reaction to obtain oxidation state prediction data;

[0149] The parameter adjustment module 104 is configured to adjust the cutting power in regions according to the predicted oxidation state data, dynamically compensate the flow field parameters of the shielding gas, and perform the cutting of the titanium alloy structural part.

[0150] above Figure 2 The intelligent cutting device for titanium alloy structural parts in the embodiments of the present invention is described in detail from the perspective of modular functional entities. Next, the intelligent cutting equipment for titanium alloy structural parts in the embodiments of the present invention is described in detail from the perspective of hardware processing.

[0151] Figure 3 FIG. is a schematic structural diagram of an intelligent cutting equipment for titanium alloy structural parts provided by an embodiment of the present invention. The intelligent cutting equipment 200 for titanium alloy structural parts may vary greatly due to different configurations or performances, and may include one or more processors (central processing units, CPU) 210 (for example, one or more processors) and a memory 220, and one or more storage media 230 for storing application programs 233 or data 232 (for example, one or more mass storage device terminals). Among them, the memory 220 and the storage media 230 may be transient storage or persistent storage. The program stored in the storage media 230 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the intelligent cutting equipment 200 for titanium alloy structural parts. Further, the processor 210 may be configured to communicate with the storage media 230 and execute a series of instruction operations in the storage media 230 on the intelligent cutting equipment 200 for titanium alloy structural parts to implement the steps of the above-mentioned intelligent cutting method for titanium alloy structural parts.

[0152] The intelligent cutting equipment 200 for titanium alloy structural parts may further include one or more power supplies 240, one or more wired or wireless network interfaces 250, one or more input / output interfaces 260, and / or one or more operating systems 231, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, and so on. Those skilled in the art can understand that Figure 3 the shown structural diagram of the intelligent cutting equipment for titanium alloy structural parts does not limit the intelligent cutting equipment for titanium alloy structural parts provided by the present invention, and may include more or fewer components than shown, or combine some components, or have different component arrangements.

[0153] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions run on a computer, the computer is caused to execute the steps of the intelligent cutting method for the titanium alloy structural member.

[0154] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described system, device, or unit can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0155] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes.

[0156] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structural transformation made by using the description and drawings of the present invention under the inventive concept of the present invention, or direct / indirect application in other related technical fields, is included in the patent protection scope of the present invention.

Claims

1. An intelligent cutting method for titanium alloy structural parts, characterized in that: include: Analyzing the rate of change of the temperature gradient according to the temperature distribution data on the surface of the titanium alloy structural part, and determining the key area prone to oxidation reaction in combination with the geometric characteristics of the titanium alloy structural part, to obtain the target monitoring area data; According to the target monitoring area data, obtaining the reflection spectrum information of the cutting area of ​​the titanium alloy structural part and the contrast spectrum information of the adjacent uncut area to obtain the spectrum characteristic data; Performing spatiotemporal coordinated analysis on the spectral characteristic data, extracting spectral intensity change values, peak shape change values ​​and peak position drift values, and combining the spatial diffusion rate and time evolution data of the oxidation reaction to obtain oxidation state prediction data; According to the oxidation state prediction data, the cutting power is adjusted in different regions, and the flow field parameters of the protective gas are dynamically compensated to execute the cutting of the titanium alloy structural part.

2. The intelligent cutting method for titanium alloy structural parts according to claim 1, characterized in that: The process of acquiring the temperature distribution data on the surface of the titanium alloy structural part comprises: According to the cutting trajectory of the titanium alloy structural part, the cutting path is divided into straight segments, corner segments and curve segments, and the heat accumulation characteristics of different types of segments are determined according to the thermal conductivity parameters of the titanium alloy to obtain the heat accumulation characteristic marking data; According to the heat accumulation characteristic mark data, an initial heat conduction prediction zone is established along the cutting track, wherein the width and shape of the initial heat conduction prediction zone are adapted to the heat accumulation characteristics of different cutting sections, and prediction zone contour data is obtained; Setting a temperature monitoring point array based on the predicted band profile data, collecting real-time temperature of the temperature monitoring point array, calculating the heat diffusion direction and rate according to the temperature change trend, and obtaining heat conduction characteristic data; According to the heat conduction characteristic data, the temperature anomaly points are dynamically spatially clustered, and the boundaries of the clustering areas are adjusted in combination with the heat diffusion direction and rate to generate temperature distribution data on the surface of the titanium alloy structural part.

3. The intelligent cutting method for titanium alloy structural parts according to claim 1, characterized in that: The method of analyzing the rate of change of the temperature gradient according to the temperature distribution data on the surface of the titanium alloy structural part and determining the key area prone to oxidation reaction in combination with the geometric characteristics of the titanium alloy structural part to obtain the target monitoring area data includes: Performing gradient scanning on the temperature distribution data on the surface of the titanium alloy structural part, calculating the rate of change of the temperature gradient, and performing heat partitioning on the surface of the titanium alloy structural part according to the rate of change to obtain heat distribution characteristic data; Performing geometric feature analysis on the surface profile of the titanium alloy structural part, identifying the corner transition area, the groove convergence area and the thickness mutation area, and determining the heat accumulation risk of each characteristic area in combination with the heat distribution characteristic data to obtain regional risk characteristic data; According to the regional risk characteristic data, combined with the thermal conductivity parameters of titanium alloy, the heat transfer rate between different characteristic regions is calculated, and the heat interaction relationship between adjacent regions is analyzed to obtain the heat transfer chain data; Based on the heat transfer chain data and in combination with the oxidation activity parameters of the titanium alloy, the oxidation reaction probability of each area is calculated, and the chain propagation law of the oxidation reaction is analyzed to obtain the target monitoring area data.

4. The intelligent cutting method for titanium alloy structural parts according to claim 3 is characterized in that: The geometric feature analysis of the surface profile of the titanium alloy structural part is performed to identify the corner transition area, the groove convergence area and the thickness mutation area, and the heat accumulation risk of each characteristic area is determined in combination with the heat distribution characteristic data to obtain the regional risk characteristic data, including: Performing curvature analysis on the surface profile of the titanium alloy structural part, calculating the curvature value of each point on the surface, identifying the geometric feature mutation point according to the change rate of the curvature value, and obtaining feature point distribution data; According to the characteristic point distribution data, the connectivity analysis of adjacent characteristic points is performed to divide the corner transition area, the groove convergence area and the thickness mutation area, and the area and depth parameters of each area are calculated to obtain characteristic area parameter data; Cross-mapping the characteristic area parameter data with the heat distribution characteristic data, calculating the heat density value in each characteristic area, and analyzing the flow trend of heat in the characteristic area to obtain heat accumulation pattern data; According to the heat accumulation pattern data, combined with the specific heat capacity parameters of titanium alloy, the heat storage capacity and heat diffusion coefficient of each characteristic area are calculated to obtain the regional risk characteristic data.

5. The intelligent cutting method for titanium alloy structural parts according to claim 4, characterized in that: The cross-mapping of the characteristic area parameter data with the heat distribution characteristic data, calculating the heat density value in each characteristic area, and analyzing the flow trend of heat in the characteristic area to obtain heat accumulation pattern data includes: Performing weight calculation on the regional area and depth parameters in the characteristic regional parameter data to generate a regional shape coefficient, and correcting each regional shape coefficient according to the thermal conductivity of the titanium alloy to obtain regional characteristic weight data; According to the regional characteristic weight data, the heat distribution characteristic data is divided into regions, and the heat density gradient and heat flow direction in each region are calculated to obtain heat flow distribution data; Performing a time series analysis on the heat flux distribution data, calculating the rate of change of heat density in each region, and analyzing the retention time of heat in the region in combination with the thermal diffusion coefficient of the titanium alloy to obtain heat retention characteristic data; According to the heat retention characteristic data, the heat accumulation rate and diffusion pattern of each area are analyzed, and the heat accumulation risk index is calculated in combination with the critical oxidation temperature of the titanium alloy to obtain the heat accumulation pattern data.

6. The intelligent cutting method for titanium alloy structural parts according to claim 1, characterized in that: The step of obtaining the reflection spectrum information of the cutting area of ​​the titanium alloy structural part and the contrast spectrum information of the adjacent uncut area according to the target monitoring area data to obtain the spectrum characteristic data includes: Performing regional stratification processing on the target monitoring area data, dividing the surface of the titanium alloy structural part into a core cutting area, an edge transition area and a reference comparison area, and determining the acquisition frequency band of each area according to the spectral characteristic band of the titanium alloy to obtain spectral acquisition area data; According to the spectral acquisition area data, a multi-band spectral scan is performed on each area to identify the characteristic spectral peaks of the titanium alloy oxidation reaction, and the spectral reflection intensity of different acquisition frequency bands is calculated to obtain multi-band spectral data; Performing spatial distribution analysis on the multi-band spectral data, calculating the spectral intensity gradient between adjacent acquisition points, and analyzing the spatial migration law of characteristic spectral peaks to obtain spectral distribution characteristic data; According to the spectral distribution characteristic data, the spectral characteristics of the cut area and the adjacent uncut area are compared and analyzed, the spectral difference coefficient is calculated, and the oxidation degree index is calculated in combination with the oxidation spectral characteristics of the titanium alloy to obtain the spectral characteristic data.

7. The intelligent cutting method for titanium alloy structural parts according to claim 6, characterized in that: According to the spectral acquisition area data, a multi-band spectral scan is performed on each area to identify the characteristic spectral peaks of the titanium alloy oxidation reaction, and the spectral reflection intensity of different acquisition frequency bands is calculated to obtain multi-band spectral data, including: Performing multi-band scanning on each area in the spectrum collection area data, setting a scanning band group based on the oxidation reaction characteristics of the titanium alloy, and classifying and collecting spectral information of different bands to obtain band spectral data; Characteristic peaks are identified on the spectrum data of the bands, the peak positions and peak intensities of the spectrum of the titanium alloy oxidation reaction in different bands are calculated, and the evolution characteristics of the spectrum peaks are analyzed according to the growth law of the oxide film to obtain the spectrum peak characteristic data; According to the spectral peak characteristic data, the spectral reflection intensity of different acquisition frequency bands is calculated, and the intensity correction is performed in combination with the energy coupling characteristics of the titanium alloy oxide film to obtain multi-band spectral data.

8. The intelligent cutting method for titanium alloy structural parts according to claim 1, characterized in that: The spectral characteristic data is subjected to a spatiotemporal coordinated analysis to extract spectral intensity change values, peak shape change values ​​and peak position drift values, and the oxidation state prediction data is obtained by combining the spatial diffusion rate and time evolution data of the oxidation reaction, including: The spectral characteristic data are processed in time series segments, characteristic change values ​​of each time period are calculated according to the change rates of spectral intensity, peak shape and peak position, and the change trend is analyzed in combination with the oxidation kinetic parameters of the titanium alloy to obtain time series characteristic data; Performing spatial mapping analysis on the time series characteristic data, calculating the spectral characteristic difference values ​​between adjacent regions, and determining the propagation direction and rate of the oxidation reaction according to the oxidation diffusion characteristics of the titanium alloy to obtain spatial propagation data; According to the spatial propagation data, the diffusion process of the oxidation reaction is analyzed in time and space, the oxidation reaction activity index of different regions is calculated, and the reaction chain effect is analyzed in combination with the critical oxidation temperature of the titanium alloy to obtain the oxidation state prediction data.

9. The intelligent cutting method for titanium alloy structural parts according to claim 1, characterized in that: The method of adjusting the cutting power by region according to the oxidation state prediction data and dynamically compensating the flow field parameters of the shielding gas to cut the titanium alloy structural part comprises: Performing partition mapping on the oxidation state prediction data and the cutting path of the titanium alloy structural part, determining the energy coupling efficiency threshold and critical oxidation temperature of each region, calculating the attenuation coefficient of the oxide layer thickness to the laser energy, and obtaining the energy compensation parameter; Based on the energy compensation parameters, the cutting power correction values ​​of the corner transition segment, the straight segment and the curved segment are calculated respectively, and the power adjustment step is calculated according to the oxidation activity of the titanium alloy at different temperatures to obtain the cutting parameter data; The cutting parameter data is analyzed, the flow field deformation of the protective gas in the high temperature area is calculated, the pressure distribution characteristics of the airflow disturbance area are determined, and the gas flow direction and flow rate are adjusted according to the temperature field distribution in the cutting area to execute the cutting of the titanium alloy structural part.

10. An intelligent cutting device for titanium alloy structural parts, characterized in that: The intelligent cutting device for titanium alloy structural parts adopts the intelligent cutting method for titanium alloy structural parts according to any one of claims 1 to 9, and the intelligent cutting device for titanium alloy structural parts comprises: A thermal field prediction module is used to analyze the rate of change of the temperature gradient according to the temperature distribution data on the surface of the titanium alloy structural part, and determine the key area prone to oxidation reaction in combination with the geometric characteristics of the titanium alloy structural part to obtain the target monitoring area data; A spectrum acquisition module is used to obtain the reflection spectrum information of the cutting area of ​​the titanium alloy structural part and the contrast spectrum information of the adjacent uncut area according to the target monitoring area data, so as to obtain spectrum characteristic data; An oxidation analysis module is used to perform spatiotemporal coordinated analysis on the spectral feature data, extract spectral intensity change values, peak shape change values ​​and peak position drift values, and obtain oxidation state prediction data by combining the spatial diffusion rate and time evolution data of the oxidation reaction; The parameter control module is used to adjust the cutting power in different regions according to the oxidation state prediction data, and dynamically compensate the flow field parameters of the protective gas to execute the cutting of the titanium alloy structural part.

Images