Laser positioning stripping system and method for special-shaped neodymium iron boron waste

Abstract

The invention relates to the technical field of material removal in laser processing, in particular to a laser positioning stripping system and method for special-shaped neodymium iron boron waste, and the method comprises the following steps: S1, carrying out multispectral scanning on the surface of the special-shaped neodymium iron boron waste; s2, dynamically adjusting energy parameters of laser lift-off, and constructing an energy thickness matching model; s3, generating a fractal scanning path of the adaptive special-shaped surface based on the geometric contour data of the three-dimensional characteristic spectrum; s4, in-situ surface roughness detection is carried out in the laser lift-off process, a secondary finishing mode is triggered according to a detection result, and the safe lift-off allowance is dynamically corrected based on lift-off depth data; and S5, in-situ separation of the oxide layer fragments and the matrix particles is achieved through the hot air flow field in combination with the gas-solid separation dynamics principle, and matrix particle recovery is assisted and strengthened through the magnetic field. The laser energy, the scanning path and the thermal control strategy can be dynamically adjusted according to real-time data, so that material loss and waste are effectively avoided, and the processing efficiency and the recovery rate are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of material removal in laser processing, and particularly to a laser positioning peeling system and method for special-shaped NdFeB waste materials. Background Art

[0002] As a key functional material in modern industry, NdFeB permanent magnet materials are widely used in new energy vehicles, precision instruments, and the aerospace field. With the sharp increase in the use of complex special-shaped components, the recycling of geometrically irregular waste materials (such as turbine engine magnetic ring fragments, special-shaped sensor magnetic cores, etc.) generated during the production process has become a difficult problem in the industry. Traditional pickling methods face serious limitations when dealing with such special-shaped waste materials: strong acid solutions are difficult to uniformly penetrate complex curved surface structures, resulting in incomplete stripping of the oxide layer and excessive corrosion of the substrate coexisting, with the recovery rate of rare earth elements less than 75%, and a large amount of heavy metal polluted waste liquid is generated. Although mechanical peeling technology can avoid chemical pollution, its adaptability to thin-walled curved surface structures is extremely poor, and there is a risk of matrix microcrack propagation. According to statistics, the breakage rate of special-shaped parts with a thickness less than 1 mm is as high as 34%, seriously restricting the recycling of high-value waste materials.

[0003] Although the laser peeling technology that has emerged in recent years has advantages in terms of environmental protection, significant technical bottlenecks have been exposed in the treatment of special-shaped NdFeB waste materials. First of all, conventional laser scanning systems rely on single-wavelength imaging and cannot penetrate the oxide layer to accurately identify the substrate contour, resulting in positioning deviation and causing substrate ablation. The actual measurement shows that the misprocessing rate in the curved surface transition area exceeds 18%. Secondly, the sudden change in surface curvature of special-shaped parts leads to an intensified heat accumulation effect. The existing equal-energy scanning strategy is prone to causing out-of-control material phase change in the groove area, resulting in the oxidation depth of grain boundaries exceeding 5 μm, seriously damaging the magnetic properties of the substrate. Moreover, traditional straight scanning paths are difficult to match complex geometric features, and there is a processing blind area as high as 27% in the slit area with a curvature radius less than 3 mm. In addition, the sorting link of the peeling product is physically isolated from the processing process, and additional vibrating screening equipment needs to be introduced, resulting in a loss rate of rare earth oxides with a particle size less than 50 μm exceeding 12%, and it is difficult to avoid secondary oxidation of substrate particles. Summary of the Invention

[0004] In order to solve the technical problem of misprocessing of special-shaped NdFeB waste materials, the present invention provides a laser positioning peeling system and method for special-shaped NdFeB waste materials.

[0005] The technical solutions provided by the embodiments of the present invention are as follows: The laser positioning and peeling method for special-shaped NdFeB waste provided by the embodiment of the present invention includes: S1: Perform multispectral scanning on the surface of the special-shaped NdFeB waste. Through the synchronous scanning of long-wavelength laser and short-wavelength laser, obtain the geometric contour data of the substrate material and the oxidation layer thickness distribution data respectively, and establish a three-dimensional characteristic spectrum of the oxidation layer-substrate boundary based on the difference characteristics of the dual-band reflection signals; S2: According to the oxidation layer thickness distribution data in the three-dimensional characteristic spectrum, dynamically adjust the energy parameters of laser peeling, construct an energy-thickness matching model, and implement laser peeling using a stepped energy control strategy. When approaching the substrate interface, monitor in real time through plasma spectroscopy and terminate the irradiation; S3: Generate a fractal scanning path adapted to the special-shaped surface based on the geometric contour data of the three-dimensional characteristic spectrum, and dynamically adjust the scanning path and cooling interval according to the real-time thermal accumulation data; S4: Perform in-situ surface roughness detection during laser peeling, trigger the secondary fine-tuning mode according to the detection results, and dynamically correct the safe peeling margin based on the peeling depth data; S5: Utilize the thermal airflow field generated during laser peeling, combine the gas-solid separation dynamics principle to realize in-situ separation of oxidation layer fragments and substrate particles, and enhance the recovery of substrate particles through magnetic field assistance.

[0006] Correspondingly, the embodiment of the present invention also provides a laser positioning and peeling system for special-shaped NdFeB waste, which is used to run the laser positioning and peeling method for special-shaped NdFeB waste described in the embodiment of the present invention, including: The multispectral scanning module includes: The long-wavelength laser scanning unit is configured to emit near-infrared laser that penetrates the oxidation layer and collect the geometric contour data of the substrate; The short-wavelength laser scanning unit is configured to emit visible laser that interacts with the electron energy level of the oxidation layer and obtain the optical response data of the oxidation layer; The signal fusion processing unit is electrically connected to the long-wavelength and short-wavelength laser scanning units, and is configured to perform phase separation processing on the dual-band reflection signals and generate a three-dimensional characteristic spectrum; The dynamic energy regulation module is connected to the multispectral scanning module through a data bus, and includes: The energy calculation engine is configured to receive the oxidation layer thickness data in the three-dimensional characteristic spectrum and calculate the stepped energy parameters; The laser generation unit is electrically connected to the energy calculation engine and includes an adjustable pulse-width fiber laser and a beam shaping component; The plasma monitoring unit integrates an optical fiber spectrometer and a characteristic peak identification circuit, and outputs a laser termination signal in real time; The path planning control module is respectively connected to the multispectral scanning module and the dynamic energy regulation module through a high-speed data interface, and includes: A fractal path generator configured to generate a Hilbert curve and a spiral progressive path according to the geometric data of a three-dimensional feature spectrum; A thermal field simulation unit with a built-in material thermal property database and a finite element calculation core, which outputs a thermal accumulation warning signal; A motion controller mechanically connected to a laser scanning galvanometer, receiving path commands and driving an optical actuator; A quality feedback correction module, including: A confocal microscopy imaging unit optically coupled to the processing area, configured to collect micro-area surface topography data; A roughness analysis processor connected to the microscopy imaging unit through an image acquisition card, with a built-in three-dimensional Fourier transform algorithm library; A safety margin calculation unit interacting with the dynamic energy regulation module through a data line and outputting a processing termination instruction; A gas-solid separation and recovery module physically connected to the outlet of the processing cavity, including: A high-temperature gas flow generating device integrated with a temperature sensor and a flow control valve, forming a thermodynamic coupling with the thermal field of the laser processing area; A magnetoelectric composite separation channel arranged with a gradient magnetic field generator and an electrode array in sequence along the material movement direction; A particle monitoring component containing a high-speed camera and an image processor, which feeds back and adjusts the separation parameters; A process optimization subsystem communicates with each module through an industrial Ethernet, including: A machine learning acceleration card configured to run a deep neural network model and output a process parameter optimization scheme; A digital twin server storing a multi-physical field coupling simulation model and comparing it with actual processing data in real time; A parameter calibration interface injecting compensation coefficients into the motion controller and the laser generating unit; The output end of the multi-spectral scanning module transmits the three-dimensional feature spectrum to the input end of the dynamic energy regulation module through an optical fiber; The path planning control module receives the geometric data from the multi-spectral scanning module and the thermodynamic parameters from the dynamic energy regulation module, and the generated control signal drives the scanning galvanometer through the motion controller; The optical signal input of the quality feedback correction module is from the reflection optical path of the processing area, and its output correction instruction is synchronously sent to the dynamic energy regulation module and the path planning control module through a digital I / O interface; The gas flow parameters of the gas-solid separation and recovery module are controlled by the real-time energy data of the dynamic energy regulation module, and its particle monitoring signal is fed back to the quality feedback correction module; The process optimization subsystem establishes a data channel with all modules through the OPCUA protocol to form a closed-loop control network.

[0007] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include: Through multi-spectral scanning, precise energy control, and intelligent path planning, efficient stripping of the oxide layer and the substrate is achieved, and substrate damage is avoided to the greatest extent. Through real-time monitoring of plasma spectra, in-situ roughness detection, and thermal accumulation control, precise control of surface quality and stripping depth is ensured. Combining gas-solid separation dynamics and magnetic field-assisted recovery technology, the present invention can efficiently separate oxide layer fragments and substrate particles, improving the recovery efficiency. Through continuous optimization of machine learning and digital twin systems, process stability and production efficiency are improved, while production costs are reduced. The present invention has significant advantages in improving the recovery rate of NdFeB waste, optimizing processing quality, and reducing energy consumption. Description of the Drawings

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings 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 these drawings.

[0009] Figure 1 It is a flowchart of the steps of the laser positioning stripping method for special-shaped NdFeB waste provided in the embodiments of the present invention; Figure 2 It is a flowchart of the steps of S1 in the laser positioning stripping method for special-shaped NdFeB waste provided in the embodiments of the present invention; Figure 3 It is a flowchart of the steps of S2 in the laser positioning stripping method for special-shaped NdFeB waste provided in the embodiments of the present invention. Detailed Embodiments

[0010] The following will describe the technical solutions in the present invention in conjunction with the drawings. At the same time, it should be noted here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments. For some well-known technologies, those skilled in the art can also adopt other alternative methods for implementation; and the drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0011] It should be noted that in the specification, references to "an embodiment", "embodiments", "exemplary embodiments", "some embodiments", etc. indicate that the described embodiments may include specific features, structures, or characteristics, but not necessarily every embodiment includes such specific features, structures, or characteristics. Additionally, when describing a specific feature, structure, or characteristic in connection with an embodiment, implementing such feature, structure, or characteristic in connection with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the relevant art.

[0012] Generally, terms can be understood, at least in part, from their use in context. For example, depending at least in part on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in a singular sense, or can be used to describe a combination of features, structures, or characteristics in a plural sense. Additionally, the term "based on" can be understood to not necessarily be intended to convey a set of exclusive factors, but rather, depending at least in part on the context, can alternatively allow for the existence of other factors that are not necessarily explicitly described.

[0013] It can be understood that the meanings of "on", "above", and "over" in the present invention should be construed in the broadest manner such that "on" not only means "directly on" something, but also includes the meaning of being "on" something with intervening features or layers therebetween, and "above" or "over" not only means "above" or "over" something, but also can include the meaning of being "above" or "over" something with no intervening features or layers therebetween.

[0014] Furthermore, spatial relative terms such as "under", "below", "lower", "above", "upper", etc. are used herein for convenience of description to describe the relationship of one element or feature to another or other elements or features, as shown in the figures. The spatial relative terms are intended to cover different orientations in the use or operation of the device in addition to the orientation depicted in the figures. The device may be otherwise oriented, and the spatial relative descriptors used herein may be interpreted accordingly.

[0015] Such as Figures 1 to 3As shown, the embodiment of the present invention provides a laser positioning peeling method for special-shaped NdFeB waste. In step S1, first, the surface of the waste is synchronously scanned by a long-wavelength laser and a short-wavelength laser to obtain the geometric contour data of the matrix material and the thickness distribution data of the oxide layer. The long-wavelength laser can penetrate the oxide layer to obtain the geometric shape information of the matrix, while the short-wavelength laser interacts with the electronic structure of the oxide layer to obtain the thickness distribution data of the oxide layer. Based on the differential characteristics of the dual-band reflection signals, a three-dimensional characteristic spectrum of the oxide layer and the matrix is constructed, providing accurate data support for the subsequent peeling process. This step provides precise three-dimensional geometric data and the thickness distribution of the oxide layer for the subsequent laser peeling operation, ensuring the efficiency and accuracy of laser peeling.

[0016] According to the thickness data of the oxide layer obtained in step S1, the energy parameters of laser peeling are dynamically adjusted, and a stepped energy control strategy is implemented by constructing an energy-thickness matching model. When approaching the interface of the matrix, the energy of laser peeling will be automatically reduced, and the peeling situation of the oxide layer is monitored in real time through plasma spectroscopy. Once abnormal plasma spectroscopy is detected (such as the matrix material being affected), the laser irradiation is immediately terminated. This control mechanism effectively avoids damage to the matrix caused by excessive laser energy, protects the matrix material, reduces the loss of waste, and improves the peeling accuracy.

[0017] In step S3, based on the geometric contour data provided in step S1, an adaptive fractal scanning path is generated to cover the surface of the waste. According to the real-time thermal accumulation data, the scanning path and the cooling interval are dynamically adjusted. This step is particularly important because it can avoid matrix damage or excessive peeling of the oxide layer caused by local overheating. By optimizing the scanning path and the cooling interval, the temperature distribution can be effectively controlled, avoiding overheating from affecting the material quality, and ensuring the stability and efficiency of the laser peeling process.

[0018] During the laser peeling process, an in-situ surface roughness detection technique is adopted to monitor the surface morphology in real time. When the detected surface roughness exceeds the set threshold, a secondary fine-tuning mode is triggered, and parameters such as laser power and scanning speed are adjusted, and the safe peeling margin is dynamically corrected according to the peeling depth to ensure that the surface is smooth and meets the requirements. Through in-situ roughness detection, abnormalities in surface treatment can be detected in a timely manner, avoiding excessive later trimming work, ensuring that the surface quality meets the standards, and improving the accuracy and efficiency of the process.

[0019] During the laser lift-off process, the thermal gas flow field generated by the laser helps to separate the oxide layer fragments from the substrate particles. By utilizing the principles of gas-solid separation kinetics, in-situ separation of the oxide layer fragments and the substrate particles can be achieved. Meanwhile, the magnetic field-assisted recovery system enhances the recovery efficiency of the substrate particles and avoids the loss of valuable neodymium-iron-boron materials. The synergistic effect of the thermal gas flow field and the magnetic field can efficiently separate the oxide layer fragments from the substrate particles, not only improving the recovery rate but also enhancing the separation efficiency, which contributes to the maximum recovery of resources.

[0020] Through the organic combination of the above steps, this laser positioning lift-off method realizes the efficient and precise treatment of special-shaped neodymium-iron-boron waste. In each link, the precise control of laser energy, the optimized adjustment of the scanning path, the real-time roughness detection and trimming, as well as the thermal gas flow and magnetic field-assisted separation system, all contribute to ensuring the efficient recovery of materials and the precision of the lift-off process. This method not only improves the resource recovery rate but also guarantees the integrity of the substrate material, reduces the loss of waste, and has good industrial application prospects.

[0021] In a possible implementation, first, long-wavelength laser scanning (S1.1) is used to obtain the geometric information of the substrate that can penetrate the oxide layer, and the original point cloud data is output. At the same time, short-wavelength laser scanning (S1.2) is used to capture the optical response of the oxide layer. Its reflection signal is sensitive to the thickness of the oxide layer, forming optical attenuation data. This synchronous scanning strategy can obtain two types of key information in one round of scanning: the three-dimensional deformation characteristics of the substrate and the thickness change of the oxide layer. Synchronization improves the data acquisition efficiency, avoids errors caused by repeated scanning, ensures the one-to-one correspondence between geometric information and optical characteristics, and realizes high-precision data coupling.

[0022] Furthermore, the above two reflection signals are input into the phase separation model, and the difference characteristics between them are analyzed respectively from the time domain (such as phase delay) and the frequency domain (such as energy distribution), and then a fine interface recognition factor is obtained, such as the reflection intensity ratio and the phase difference. Using the phase and frequency domain information to enhance the signal identification ability can more accurately distinguish the boundary between the oxide layer and the substrate, especially suitable for regions with complex morphologies and small thickness differences.

[0023] Based on the above difference characteristics, the scanning area is divided into sub-regions and feature vectors are extracted. The principal component analysis (PCA) is used to simplify the data dimension and extract key features; then a dynamic classification model is constructed through the support vector machine (SVM) algorithm to generate boundary recognition criteria that adapt to various morphological changes. The dynamic classification boundary can adapt to the changes in material properties in different regions, avoid misjudgment problems caused by static thresholds, and significantly improve the accuracy and robustness of recognition.

[0024] Based on the above precise identification, the Poisson reconstruction algorithm is used to generate the substrate geometric model, and then the optical response data is mapped to the surface to construct the oxide layer thickness field. Finally, non-uniform rational B-spline (NURBS) is used for surface fitting to form a continuous and smooth three-dimensional oxide layer characteristic spectrum. NURBS fitting has high smoothness and local adjustability, which can accurately reflect the tiny fluctuations of the oxide layer thickness under complex morphologies, providing an accurate basic model for subsequent laser energy regulation and path generation.

[0025] The above steps are closely connected through layer-by-layer extraction and coupling of data. From the initial multi-source scanning to the final establishment of the three-dimensional characteristic spectrum, it constitutes a multi-modal information fusion system for special-shaped complex waste materials. It has significant advantages especially in high-contrast interface recognition, intelligent boundary classification, and continuous characterization, significantly improving the accuracy of subsequent laser stripping and the intelligent level of material recognition. This method is applicable to the recycling scenario of rare earth waste materials with high value and difficult separation, and has the characteristics of high efficiency, scalability, and industrial practicability.

[0026] In a possible implementation manner, the S2 stage mainly involves energy control and plasma spectrum monitoring during the laser stripping process. This method ensures precise control of the oxide layer and the substrate during the laser stripping process by reasonably designing an energy-thickness matching model, a stepped energy control strategy, and a real-time plasma spectrum monitoring system, minimizing material damage to the greatest extent while improving the waste material recycling efficiency.

[0027] Specifically, in step S2.1, an energy-thickness matching model is first constructed to describe the relationship between laser energy and oxide layer thickness through an exponential function relationship. The exponential term coefficient of this model is determined by the photothermal conversion efficiency of the material, which can adjust the laser energy according to the characteristics of different materials, ensuring that the heat of the laser is concentrated in the appropriate area and avoiding matrix damage caused by excessive energy. This model also needs to consider the ablation threshold of the oxide layer and the matrix damage threshold simultaneously to form a double constraint condition, ensuring that the energy control in each stage can accurately adapt to the requirements of different levels.

[0028] Through the precise design of the energy matching model, while ensuring the effective stripping of the oxide layer by the laser, it can avoid damage to the substrate caused by excessive energy. This model can dynamically adjust the laser parameters according to the specific conditions of the waste material, significantly improving the stripping efficiency and material utilization rate.

[0029] In step S2.2, a stepped energy control strategy is adopted to adjust the output power of the laser in stages to cope with the different material characteristics of the oxide layer and the substrate: In the first stage, high-energy pulses are used to break through the dense oxide layer, and the pulse width is selected to meet the pressure threshold required for shock phase transformation. The high-energy pulses in this stage can effectively break through the relatively thick oxide layer.

[0030] In the second stage, switch to the low-energy long-pulse-width mode and process the transition layer. In this stage, the parameter setting of the low-energy pulse ensures that the depth of the heat-affected zone is less than the thickness of the transition zone at the interface between the oxide layer and the substrate, thereby avoiding overheating the substrate and ensuring that the oxide layer is completely stripped.

[0031] In the third stage, when the laser approaches the substrate interface, monitor the appearance of the characteristic peaks of the substrate material by real-time acquisition of the plasma emission spectrum, and timely judge whether the substrate interface is reached to avoid excessive damage.

[0032] The stepped energy control strategy precisely controls the processing intensity of different material layers by adjusting the laser power in stages, avoiding out-of-control energy transition between different layers. This method greatly improves the accuracy and safety of laser stripping, which is particularly crucial for the efficient processing of complex waste materials.

[0033] In step S2.3, a fiber optic spectrometer is used to collect the plasma emission spectrum in the wavelength range of 400 - 700 nm, and the spectral data is processed by wavelet denoising technology to extract the relative intensity ratio of the characteristic peaks of rare earth elements. When the intensity ratio of the characteristic peaks exceeds the preset threshold, immediately cut off the laser output. This real-time monitoring system can accurately identify the characteristic peaks of the substrate material and avoid damage to the substrate by the laser.

[0034] The real-time monitoring of the plasma spectrum ensures the dynamic adaptability of the laser stripping process, can detect the appearance of the substrate material characteristics in real time, and then timely cut off the laser output to avoid damage to the substrate caused by overprocessing. This method greatly improves the safety and accuracy of the stripping process and effectively protects valuable materials.

[0035] These three steps, through the organic combination of the energy-thickness matching model, the stepped energy control strategy, and the real-time monitoring of the plasma spectrum, form an efficient and safe laser stripping process. The energy-thickness matching model provides theoretical support to ensure precise energy control; the stepped energy control strategy ensures layer-by-layer control during the actual stripping process and avoids excessive energy input; while the plasma spectrum monitoring provides real-time feedback at critical moments to prevent unnecessary damage to the substrate. Overall, the combination of the three improves the accuracy, efficiency of the waste material recycling process, as well as the material recovery rate, and is a laser stripping method with both high efficiency and safety.

[0036] In a possible implementation manner, the S3 stage mainly involves the optimization of the laser scanning path and the real-time control of heat accumulation. Through the fractal scanning path generation method, the real-time heat accumulation control method, and the method for determining the cooling interval, the accuracy, efficiency, and material safety of laser stripping can be effectively improved.

[0037] Specifically, in step S3.1, the processing area is first decomposed into multi-level substructures, and appropriate filling patterns are selected according to different local curvature characteristics. Specifically, when the curvature radius is less than a certain critical value, a spiral progressive path is adopted, which can perform delicate laser processing in areas with smaller curvature to maximize the effect of material stripping. For areas with larger curvature, a space-filling curve is used to optimize the coverage density of the path and ensure the efficiency of the stripping process.

[0038] A recursive subdivision algorithm is implemented for high-complexity areas to further improve the adaptability of the path. The criteria for recursive subdivision include the curvature change rate, the oxide layer thickness gradient, and the predicted value of heat accumulation. These factors are combined to determine the path optimization method, thus effectively improving the accuracy of laser stripping and avoiding improper processing of high-complexity areas.

[0039] By selecting a path pattern suitable for the curvature characteristics, the accuracy and efficiency of the laser stripping process can be maximized. The fractal scanning path method can adapt to waste materials of different shapes and complexities, ensuring more flexible and efficient laser processing and reducing material waste.

[0040] In step S3.2, by establishing a prediction model of the heat flux density field, combining the scanning path parameters, the thermal diffusivity of the material, and the laser energy parameters, the temperature field distribution is calculated. This model can predict the heat accumulation in local areas to ensure that the material is not damaged due to overheating during the laser stripping process.

[0041] When the temperature gradient in a local area exceeds the set critical value, the following operations are performed: Interrupt the current scanning path and insert a cooling time interval: This operation reduces the temperature of the local area by pausing the laser scanning and inserting a cooling time, avoiding damage to the oxide layer or degradation of the substrate material caused by excessive temperature.

[0042] Switch to an adjacent low-temperature area to continue the operation: This strategy enables the laser processing to continue without affecting the overheated area.

[0043] Dynamically adjust the filling density of the subsequent scanning path: According to the real-time feedback of heat accumulation, dynamically adjust the filling density of the subsequent path to reduce heat accumulation and improve the overall thermal control effect.

[0044] Real-time heat accumulation control can effectively avoid material damage caused by excessive laser energy or excessive heat accumulation. This method ensures the safety and efficiency of the laser stripping process through precise temperature control and improves the quality of waste material recycling.

[0045] In step S3.3, calculate the heat dissipation time according to the heat diffusion equation, and determine the cooling interval time in combination with the material properties and heat diffusion conditions. In addition, by combining the priorities of the subsequent processing areas, re-plan the path sequence. This can maximize the utilization of the processing area priorities while ensuring cooling, making the entire processing process more efficient.

[0046] By accurately calculating the heat dissipation time, effective control of heat accumulation can be ensured. Re-planning the path sequence makes the insertion of cooling intervals more scientific and reasonable, avoiding ineffective waiting times and improving the overall processing efficiency.

[0047] In a possible implementation, stage S4 mainly involves the detection of surface roughness, the triggering of the secondary fine machining mode, and the dynamic correction of the safety peeling margin. Through these three specific steps, the accuracy and safety in the laser peeling process can be optimized to ensure that the surface quality of the material meets the requirements and avoid unnecessary damage.

[0048] Specifically, in step S4.1, first use confocal laser scanning technology to perform optical tomography along the normal direction of the peeling area to obtain micro-region surface topography data. This method can accurately obtain the microscopic morphology of the material surface and provide fine data for subsequent processing.

[0049] Furthermore, perform Fourier transform analysis on the tomographic image to extract the spatial frequency distribution characteristics, especially the energy ratio of the high-frequency components and the directional intensity distribution of the medium-frequency components. Through these characteristics, quantitative analysis of the surface roughness can be carried out and a basis for triggering the subsequent fine machining mode can be provided.

[0050] Furthermore, through weighted calculation of the deviation amount between the spatial frequency characteristics and the preset reference plane, a surface roughness evaluation function is obtained. This function can comprehensively evaluate the surface roughness and provide a standard for triggering the secondary fine machining mode.

[0051] This method realizes the accurate evaluation of surface roughness through high-precision in-situ surface detection, providing data support for the subsequent fine machining mode. Through Fourier transform analysis, the fine features of the material surface can be better captured, thereby improving the accuracy in the laser peeling process.

[0052] Step S4.2 triggers the secondary fine machining mode by setting the critical threshold of the surface roughness evaluation function. When the surface roughness exceeds the first critical threshold, start the fine machining mode for further surface quality trimming.

[0053] During the fine machining process, the system optimizes the processing effect by adjusting the following parameters: Reduce the laser power density: Reduce the power density to a fixed proportion of the original parameters to reduce the impact of excessive laser irradiation on the surface and avoid overheating or excessive peeling of the material.

[0054] Increase the scanning speed: Increase the scanning speed to a fixed multiple of the original speed to reduce the long-term exposure to the surface, thereby reducing the thermal impact.

[0055] Reduce the spot overlap rate: Reduce the spot overlap rate to a preset safe range to ensure the uniform distribution of laser energy and avoid unnecessary surface damage.

[0056] Monitor during the finishing process: During the finishing process, continuously monitor the change rate of the surface roughness. When the roughness change approaches zero, automatically exit the finishing mode to ensure the efficiency and accuracy of the processing process.

[0057] By triggering the secondary finishing mode and precisely adjusting the laser parameters, the surface roughness can be effectively reduced to achieve the required surface quality. At the same time, the real-time monitoring during the finishing process ensures the dynamic optimization of the processing process, which helps to avoid unnecessary overprocessing and material waste.

[0058] In step S4.3, by establishing a peeling depth prediction model, the peeling depth can be predicted based on parameters such as the cumulative laser energy density, the thermal diffusivity of the material, and the porosity of the oxide layer. This model can calculate the proportional relationship between the remaining substrate thickness and the original thickness in real time.

[0059] When this ratio is lower than the second critical threshold, the system will perform the following operations: Immediately terminate the laser irradiation in the current area: Stop the laser irradiation in the current area to prevent material damage caused by excessive peeling.

[0060] Mark the prohibited processing area: Mark this area as a prohibited processing area in the three-dimensional feature spectrum to ensure that the area is no longer irradiated by the laser.

[0061] Re-plan the path density: Re-plan the scanning path density of the surrounding area to ensure the continuity and efficiency of the processing process, and at the same time avoid the unsafe area from being processed again.

[0062] This method ensures the safety during the laser peeling process through real-time peeling depth prediction and safety margin correction, and avoids material loss or unnecessary risks caused by overprocessing. The dynamic correction can adjust the scanning path according to the actual situation, making the laser peeling process more accurate and safe.

[0063] The three steps in the S4 stage cooperate with each other to form a closed-loop control system. In-situ surface roughness detection provides high-precision surface data, providing a basis for triggering the secondary fine-tuning mode, and the parameter adjustment in the fine-tuning mode can effectively improve the surface quality; at the same time, the dynamic correction method for the safe peeling margin ensures the safe processing of materials by real-time monitoring of the peeling depth. The combination of these series of measures not only improves the accuracy and efficiency of laser peeling, but also avoids the damage caused by over-processing, ensuring the quality and safety of materials during the processing.

[0064] In a possible implementation, the specific realization of step S5 involves gas-solid separation dynamics, magnetic field-assisted recovery method, and closed-loop control of the separation process. These three technologies work together to improve the efficiency of waste sorting, ensure the effective recovery of useful matrix particles in the waste, and remove oxide layer fragments at the same time.

[0065] Specifically, step S5.1 uses the high-temperature gas generated during the laser peeling process to construct a vertical air flow field. These high-temperature gases can regulate the turbulence intensity of the fluidized bed by controlling the air flow velocity, thereby affecting the sedimentation process of particles.

[0066] The design of the classification sedimentation chamber is based on the Stokes number difference between the oxide layer fragments and the matrix particles. The particle size of the oxide layer fragments is smaller, while the matrix particles have a higher mass density, which results in different sedimentation speeds of the two in the air flow. Therefore, a classification sedimentation chamber is designed, and multi-stage baffles are set to further refine the sorting. The spacing between the baffles is determined according to the terminal velocity distribution of the particles, thereby improving the sorting accuracy.

[0067] The regulation of the air flow and the design of the classification sedimentation chamber can accurately separate the oxide layer fragments and the matrix particles, ensure that the oxide layer fragments are effectively removed, and retain the matrix particles to the greatest extent. This not only improves the sorting efficiency, but also reduces material waste.

[0068] In step S5.2, a gradient magnetic field generator is arranged at the end of the sorting system, and the magnetic field intensity gradually increases along the movement direction of the particles. This design can enhance the attraction to the matrix particles and contribute to the recovery of the matrix particles.

[0069] By performing pre-magnetization treatment on the matrix particles, the particles generate a residual magnetic moment in the alternating magnetic field, enhancing their response in the magnetic field. According to the principle of the Lorentz force, a particle trajectory control channel is designed, and its curvature radius is inversely proportional to the magnetic field gradient, so as to accurately control the movement trajectory of the particles and achieve the effective recovery of the matrix particles.

[0070] The magnetic field-assisted recovery method can effectively improve the recovery rate of matrix particles and avoid the misrecovery of oxide layer fragments by enhancing the magnetism of matrix particles and controlling the movement trajectories of particles. The application of this technology further improves the selectivity and efficiency of the recovery process.

[0071] In step S5.3, the movement trajectories of particles are monitored in real time by using a high-speed camera system. These camera systems can accurately capture the movement information of particles and count the escape rate of target particles through image recognition algorithms.

[0072] Based on the data feedback of the escape rate, the system dynamically adjusts the air flow velocity and magnetic field strength, and adjusts the operating parameters in real time to minimize the escape rate. This can ensure that more matrix particles are effectively sorted and recovered, and reduce the escape of ineffective particles.

[0073] Closed-loop control can adjust the operating conditions in real time to ensure the optimization of the sorting process. By continuously monitoring the movement trajectories of particles and dynamically adjusting the air flow and magnetic field strength, the escape of particles is avoided, the sorting efficiency is improved, and the accuracy of the recovery process is ensured.

[0074] The three technical sub-steps in step S5 achieve efficient waste sorting and recovery through mutual cooperation. Gas-solid separation dynamics provides a preliminary separation for particle sorting, and fractional sedimentation is carried out based on the physical properties of particles, effectively removing oxide layer fragments. Then, magnetic field-assisted recovery further improves the recovery rate of matrix particles by enhancing the magnetism of matrix particles. Finally, the closed-loop control of the sorting process ensures the efficient operation of the entire sorting process through real-time monitoring and dynamic adjustment, minimizing the escape of particles to the greatest extent.

[0075] The combination of these steps can significantly improve the accuracy and efficiency in the neodymium iron boron waste recovery process, ensure a high recovery rate of matrix particles, and effectively reduce the loss of oxide layer fragments. The overall system optimizes each link of waste sorting and provides an efficient and intelligent recovery solution.

[0076] In a possible implementation manner, the step of three-dimensional Fourier transform analysis involved in S4.1 aims to extract the surface features of materials through frequency domain analysis of the image sequence to achieve efficient surface peeling quality evaluation. This process includes the conversion from the spatial domain to the frequency domain, the extraction of spatial frequency features, and the construction of a surface roughness evaluation function.

[0077] Specifically, in step S4.1.1, the purpose of this step is to transform the tomographic image sequence from the spatial domain to the frequency domain in order to reveal the periodic and aperiodic characteristics of the material surface through spectral analysis. First, a two-dimensional discrete Fourier transform (2D FFT) is performed on the image sequence along the XY plane to capture the frequency information of the material surface in the XY plane. Next, a one-dimensional Fourier transform (1D FFT) is implemented in the Z-axis direction to convert this tomographic image data into a three-dimensional spectrum.

[0078] The transformation from the spatial domain to the frequency domain provides a global frequency-domain perspective, capable of capturing the variations of surface features in all directions and at different scales. When dealing with shaped NdFeB waste materials, the surface may have complex morphologies and structures. The frequency-domain conversion can effectively reveal surface features of different sizes, providing basic data for subsequent frequency feature extraction and surface roughness evaluation.

[0079] In step S4.1.2, the three-dimensional spectrum is divided into a low-frequency region, a medium-frequency region, and a high-frequency region. The boundary frequencies of each frequency region are determined by the physical properties of the material surface. Then, the integral energy of the complex modulus value within each frequency band is calculated and normalized to the proportion of the total energy. In addition, directional filtering is specifically performed on the medium-frequency region spectrum to statistically analyze the energy distribution differences in four directions: 0°, 45°, 90°, and 135°.

[0080] Through frequency region division and energy distribution analysis, the directional characteristics of surface roughness and texture can be effectively revealed. The low-frequency region is usually related to large-scale surface features (such as surface flatness, long-wave texture), while the high-frequency region reflects fine surface defects and microstructures. Performing directional filtering on the medium-frequency region can help further analyze surface details, especially directional characteristics, which is crucial for optimizing the focusing and scanning directions of the laser beam during the laser stripping process.

[0081] Step S4.1.3 constructs an evaluation function for surface roughness. First, a theoretical frequency distribution curve of an ideal stripping surface is defined as a reference plane. Then, the root mean square error (RMSE) between the actual surface frequency distribution and the reference curve in different frequency bands is calculated. Next, the errors in each frequency band are weighted and combined, and the weight coefficients are related to surface functional requirements (such as surface finish, stripping effect, etc.).

[0082] This process provides a basis for the quantitative evaluation of surface quality by comparing the differences between the actual surface and the ideal surface. Since different applications may require different surface roughness and texture directionality, the design of the weight coefficients can be adjusted according to specific needs to ensure precise control of the stripping process. By weighted superposition of the errors, a comprehensive evaluation function is finally obtained, which helps to optimize the parameter settings of laser stripping.

[0083] These three steps are closely combined to form a complete surface quality assessment process. First, frequency-domain data is provided through three-dimensional Fourier transform. Then, surface features are extracted through frequency region division and energy statistics. Finally, a quantitative assessment of the actual surface roughness is achieved by constructing an evaluation function. The advantage of this design lies in its ability to accurately optimize the laser peeling process according to the complex features of the material surface (such as roughness and texture in different directions), improve the recycling efficiency, and at the same time control the surface quality after peeling.

[0084] Through this frequency analysis method, an efficient assessment of the surface quality of special-shaped NdFeB waste can be realized, meeting the processing requirements of waste in different forms, improving the flexibility and accuracy of the laser positioning peeling method, and ensuring the high quality of the final recycled materials.

[0085] In a possible implementation manner, the design method of the classification sedimentation chamber in S5.1 aims to effectively separate oxide layer fragments and matrix particles and improve the recovery rate through precise aerodynamic control and optimized analysis of particle behavior.

[0086] Specifically, the purpose of S5.1.1 is to optimize the relative motion of the airflow and particles by calculating the airflow velocity and the terminal velocity of the particles, ensuring the effective separation of oxide layer fragments and matrix particles. First, according to the gas temperature, the dynamic viscosity coefficient of the gas is calculated. Then, Stokes' law is used to derive the terminal velocity of the particles, considering the influence of the particle shape factor to more accurately calculate the terminal velocities of different particles. Finally, through iterative calculations, the airflow velocity that maximizes the velocity difference between oxide layer fragments and matrix particles is determined.

[0087] By precisely controlling the airflow velocity, the best particle separation effect in the sedimentation chamber can be ensured. A reasonable airflow velocity can effectively improve the separation efficiency between fragments and matrix particles, reduce the mixing between particles and recycling losses, and provide a basis for the optimization of subsequent classification sedimentation.

[0088] The design of S5.1.2 focuses on optimizing the distribution and collision behavior of particles through the layout of baffles. First, by establishing a differential equation for the particle motion trajectory and inputting influencing factors such as particle mass, gas flow velocity, and baffle geometric parameters, the particle motion trajectory is accurately simulated. Then, the Monte Carlo simulation method is used to statistically analyze the probability distribution of particle collisions, obtaining the probability of particle collisions under different baffle layouts. Finally, through the genetic algorithm, with the target particle recovery rate as the optimization goal, the optimal solution for the baffle spacing is solved.

[0089] The optimized layout of multi-stage baffles can effectively guide the particle motion trajectory, control the sedimentation velocity and distribution of particles, thereby improving the particle classification effect. The optimized baffle spacing ensures the maximum particle recovery rate, reduces the loss of valuable materials in the waste, and improves the recycling efficiency.

[0090] Furthermore, turbulence control is a key factor in ensuring the stable separation of particles during sedimentation. By setting up a porous medium rectifying layer at the inlet of the sedimentation chamber, the air flow can be effectively smoothed, reducing the instability caused by turbulence. The pressure fluctuation value is monitored in real time, and the PID controller is used to adjust the opening degree of the air supply valve to further precisely control the stability of the air flow. When the Reynolds number exceeds the critical value, the turbulence suppression device is activated to avoid excessive turbulence interfering with the classification sedimentation of particles.

[0091] The control of turbulence intensity can maintain the uniformity and stability of the air flow in the sedimentation chamber, prevent excessive air flow disturbance, and ensure the precise classification of particles. Through the adjustment of the PID controller, the air flow can be finely adjusted according to real-time data, further improving the classification effect and particle recovery rate.

[0092] The design method in S5.1 forms an efficient classification sedimentation system by integrating fluidized bed dynamics, multi-stage baffle layout optimization, and turbulence control strategies. Each step is interrelated to ensure the efficient separation of particles during sedimentation. The determination of the parameters of fluidized bed dynamics provides a basis for the precise control of air flow velocity. The multi-stage baffle optimization further improves the particle recovery rate, while the turbulence intensity control ensures the stability of the sedimentation process. The beneficial effect of the overall design is to improve the accuracy and efficiency of waste sorting, reduce losses during the recovery process, optimize the recovery process of NdFeB waste, and maximize the recovery value.

[0093] In a possible implementation, section S6 involves the establishment and continuous optimization of a process knowledge base, aiming to continuously improve the processing efficiency and accuracy through machine learning, digital twin, and self-optimization mechanisms.

[0094] Specifically, the purpose of S6.1 is to optimize process parameters using machine learning technology through the collection and analysis of historical processing data. First, by collecting historical processing data (including three-dimensional feature spectrum parameters, laser energy sequences, surface roughness detection results, and sorting efficiency indicators), a training set is constructed to provide sufficient data support for the model. Then, the feature vector is defined, and important indicators such as the mean value of the oxidation layer thickness gradient, the maximum heat accumulation value, and the density of path turning points are included in the feature vector. These features can reflect different states of the material during the laser stripping process. A deep neural network model is used for multi-objective optimization to output the optimal combination of process parameters.

[0095] Through the training of the machine learning model, the optimal combination of process parameters can be found for different processing conditions based on historical data. This method can continuously optimize the process during the process of accumulating data, improving the stripping efficiency, quality, and recovery rate.

[0096] Furthermore, the digital twin method verifies the accuracy of the actual machining process through physical field simulation in the virtual environment. First, a virtual machining environment is established and integrated with multiple physical field simulation modules, including the thermodynamic model of laser-material interaction, the molecular dynamics model of the oxide layer stripping process, and the computational fluid dynamics model of gas-solid two-phase flow. These models can simulate various physical phenomena during the laser stripping process. Then, the actual machining parameters are input into the digital twin system for multi-physical field coupling simulation, and the deviation between the simulation results and the measured data is checked by comparing with the actual machining process. If the deviation exceeds the allowable range, the system will trigger the model parameter calibration process and automatically adjust the model parameters to ensure more accurate simulation results.

[0097] The digital twin technology makes the virtual and actual machining processes highly consistent, can verify the feasibility of the optimization scheme through simulation, and reduces the cost and time in the experimental stage. At the same time, the dynamic calibration mechanism ensures the continuous improvement of the machining process and ensures that the process parameters are always in the best state.

[0098] S6.3 focuses on the continuous monitoring and optimization of process parameters during the production process. First, the actual production data is regularly compared and analyzed with the historical data in the knowledge base to identify the drift patterns of process parameters. Through comparison, anomalies or changes in the production process can be detected in a timely manner. Then, the corresponding compensation coefficients are generated to adjust the process parameters to compensate for the deviation. The optimization results are automatically injected into the control system through online updates, thereby realizing the real-time optimization of the process.

[0099] The self-optimization mechanism of process parameters can automatically adjust according to the changes in production in real time, ensuring the stability and efficiency of the production process. This not only improves the intelligent level of the production line but also ensures the stability and consistency of product quality in the case of parameter fluctuations or environmental changes.

[0100] In part S6, a closed-loop system of dynamic learning and real-time optimization is established through the combination of machine learning, digital twin, and the self-optimization mechanism of process parameters. First, the machine learning model is trained with historical data to provide the optimal process parameters; then, the digital twin technology verifies the process plan through multi-physical field simulation, ensuring the consistency between the design and the actual machining process; finally, the self-optimization mechanism of process parameters ensures the long-term stability and optimization of the machining process through real-time monitoring and adjustment. The beneficial effect of the overall design is to improve production efficiency and product quality, reduce costs, make the production process more intelligent, and have stronger adaptability and sustainability.

[0101] Correspondingly, the embodiment of the present invention also provides a laser positioning and stripping system for special-shaped NdFeB waste, which is used to run any laser positioning and stripping method for special-shaped NdFeB waste described in the embodiment of the present invention, including: Multispectral scanning module, comprising: Long-wavelength laser scanning unit, configured to emit near-infrared laser that penetrates the oxide layer and acquire substrate geometric profile data; Short-wavelength laser scanning unit, configured to emit visible laser that interacts with the electron energy levels of the oxide layer and obtain oxide layer optical response data; Signal fusion processing unit, electrically connected to the long-wavelength and short-wavelength laser scanning units, configured to perform phase separation processing on the dual-band reflection signals and generate a three-dimensional characteristic spectrum; Dynamic energy regulation module, connected to the multispectral scanning module through a data bus, comprising: Energy calculation engine, configured to receive the oxide layer thickness data in the three-dimensional characteristic spectrum and calculate stepped energy parameters; Laser generation unit, electrically connected to the energy calculation engine, including an adjustable pulse-width fiber laser and a beam shaping component; Plasma monitoring unit, integrating an optical fiber spectrometer and a characteristic peak identification circuit, and outputting a laser termination signal in real time; Path planning control module, connected to the multispectral scanning module and the dynamic energy regulation module respectively through a high-speed data interface, comprising: Fractal path generator, configured to generate a Hilbert curve and a spiral progressive path according to the geometric data of the three-dimensional characteristic spectrum; Thermal field simulation unit, built-in with a material thermal property database and a finite element calculation core, and outputting a thermal accumulation warning signal; Motion controller, mechanically connected to the laser scanning galvanometer, receiving path instructions and driving the optical actuator; Quality feedback correction module, comprising: Confocal microscopy imaging unit, optically coupled to the processing area, configured to acquire micro-area surface topography data; Roughness analysis processor, connected to the microscopy imaging unit through an image acquisition card, and built-in with a three-dimensional Fourier transform algorithm library; Safety margin calculation unit, interacting with the dynamic energy regulation module through a data line, and outputting a processing termination instruction; Gas-solid separation and recycling module, physically connected to the processing cavity outlet, comprising: High-temperature gas flow generating device, integrating a temperature sensor and a flow control valve, and forming a thermodynamic coupling with the thermal field of the laser processing area; Magnetoelectric composite separation channel, sequentially arranging a gradient magnetic field generator and an electrode array along the material movement direction; Particle monitoring component, including a high-speed camera and an image processor, and feedback-adjusting the separation parameters; Process optimization subsystem, communicating with each module through an industrial Ethernet, comprising: A machine learning acceleration card configured to run a deep neural network model and output a process parameter optimization solution; A digital twin server that stores a multi-physical field coupling simulation model and compares it with actual processing data in real time; A parameter calibration interface that injects compensation coefficients into a motion controller and a laser generating unit; The output end of the multi-spectral scanning module transmits a three-dimensional characteristic spectrum to the input end of the dynamic energy regulation module through an optical fiber; The path planning control module receives geometric data from the multi-spectral scanning module and thermodynamic parameters from the dynamic energy regulation module, and the generated control signal drives the scanning galvanometer through a motion controller; The optical signal input of the quality feedback correction module originates from the reflection optical path of the processing area, and its output correction instruction is synchronously sent to the dynamic energy regulation module and the path planning control module through a digital I / O interface; The gas-solid separation and recovery module's air flow parameters are controlled by the real-time energy data of the dynamic energy regulation module, and its particle monitoring signal is fed back to the quality feedback correction module; The process optimization subsystem establishes a data channel with all modules through the OPC UA protocol to form a closed-loop control network.

[0102] The beneficial effects brought by the technical solution provided by the embodiments of the present invention at least include: In the present invention, through the precise connection of the above steps, efficient and accurate laser stripping, oxide layer separation, substrate recovery, and surface quality control can be achieved. Especially in the process of processing irregular waste materials, the laser energy, scanning path, and thermal control strategy can be dynamically adjusted according to real-time data, thereby effectively avoiding material loss and waste and improving the processing efficiency and recovery rate.

[0103] The present invention covers any alternatives, modifications, equivalent methods, and solutions made on the essence and scope of the present invention. In order to enable the public to have a thorough understanding of the present invention, specific details are described in detail in the preferred embodiments of the present invention, and those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion to the essence of the present invention, well-known methods, processes, procedures, components, and circuits are not described in detail.

[0104] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A laser positioning stripping method for special-shaped NdFeB waste, characterized in that: The following steps are involved: S1: Perform multi-spectral scanning on the surface of special-shaped NdFeB scraps. Through synchronous scanning of long-wavelength laser and short-wavelength laser, obtain the geometric profile data of the matrix material and the thickness distribution data of the oxide layer respectively, and establish the three-dimensional characteristic spectrum of the oxide layer-matrix boundary based on the difference characteristics of the dual-band reflection signal; S2: dynamically adjusting the energy parameters of laser stripping according to the oxide layer thickness distribution data in the three-dimensional characteristic spectrum, constructing an energy thickness matching model, implementing laser stripping using a step-by-step energy control strategy, and monitoring and terminating irradiation in real time through the plasma spectrum when approaching the substrate interface; S3: Based on the geometric profile data of the three-dimensional characteristic spectrum, a fractal scanning path of an adaptive profiled surface is generated, and the scanning path and cooling interval are dynamically adjusted according to real-time heat accumulation data; S4: Perform in-situ surface roughness detection during laser stripping, trigger the secondary finishing mode based on the detection results, and dynamically correct the safe stripping margin based on the stripping depth data; S5: The hot gas flow field generated during laser stripping is used in combination with the gas-solid separation kinetics to achieve in-situ separation of oxide layer fragments and matrix particles, and the recovery of matrix particles is enhanced by magnetic field assistance.

2. The laser positioning and stripping method for special-shaped NdFeB waste according to claim 1, characterized in that: The S1 specifically includes: S1.1: Scan the surface of the waste material using a long-wavelength laser, wherein the wavelength of the long-wavelength laser is selected to penetrate the surface oxide layer and reflect the geometric deformation characteristics of the matrix material, and obtain the original point cloud data of the matrix contour; S1.2: Scanning is performed synchronously using a short-wavelength laser, wherein the wavelength of the short-wavelength laser is selected to interact with the electron energy level transition of the oxide layer, and the reflection intensity thereof decays nonlinearly with the thickness of the oxide layer, thereby obtaining optical response data of the oxide layer; S1.3: Establish a phase separation model for dual-band reflection signals by calculating the difference characteristics between the long-wavelength reflection signal and the short-wavelength reflection signal in the time domain and the frequency domain, wherein the difference characteristics include but are not limited to the reflection intensity ratio, the phase delay difference and the spectrum energy distribution difference; S1.4: Construct a dynamic threshold decision mechanism to dynamically adjust the boundary judgment standard according to the spectral feature distribution of the local area. The judgment standard includes the following steps: The scanning area is divided into several sub-areas, and the characteristic vector of the dual-band reflection signal in each sub-area is calculated; Perform principal component analysis on the eigenvectors to extract the principal component factors that characterize the transition state of the oxide layer matrix; Construct a multidimensional decision space based on principal component factors and use support vector machine algorithm to generate dynamic classification boundaries; S1.5: Converting discrete optical data into a continuous oxide layer distribution surface through a three-dimensional topological reconstruction engine, wherein the reconstruction process includes: Perform Poisson surface reconstruction on the original point cloud data to generate a matrix geometry model; Mapping the oxide layer optical response data to the geometric model surface to establish the oxide layer thickness field; The three-dimensional characteristic spectrum of the oxide layer is generated by using the non-uniform rational B-spline surface fitting algorithm.

3. The laser positioning and stripping method for special-shaped NdFeB waste according to claim 1, characterized in that: The S2 specifically includes: S2.1: Construct an energy thickness matching model, the model meeting the following conditions: The relationship between the energy parameter and the oxide layer thickness follows the law of an exponential function, and the coefficient of the exponential term is determined by the light-to-heat conversion efficiency of the material; The model includes dual constraints of oxide layer ablation threshold and substrate damage threshold; S2.2: Implement a stepped energy control strategy, including: In the first stage, a high-energy pulse is used to break the dense oxide layer, and the pulse width of the high-energy pulse is selected to meet the pressure threshold required for the impact phase transition; In the second stage, the transition layer is processed by switching to a low-energy long pulse width mode. The low-energy parameters are set to ensure that the depth of the heat-affected zone is less than the thickness of the interface transition zone between the oxide layer and the substrate. In the third stage, when approaching the matrix interface, the plasma emission spectrum is collected in real time, and the appearance of the characteristic peak of the matrix material is detected by the characteristic spectrum line recognition algorithm; S2.3: Real-time monitoring of plasma spectrum, including: A fiber optic spectrometer was used to collect the emission spectrum in the wavelength range of 400-700 nm; After the spectral data were processed by wavelet denoising, the relative intensity ratio of the characteristic peaks of rare earth elements was extracted; When the characteristic peak intensity ratio exceeds the preset threshold, the laser output is immediately cut off.

4. The laser positioning and stripping method for special-shaped NdFeB waste according to claim 1, characterized in that: The S3 specifically includes: S3.1: The fractal scanning path generation method comprises: The processing area is decomposed into multi-level substructures, and the filling mode is selected according to the local curvature characteristics. When the curvature radius is less than the critical value, a spiral progressive path is used, otherwise a space filling curve is used; Implementing a recursive subdivision algorithm for high complexity areas, wherein the subdivision criteria include curvature change rate, oxide layer thickness gradient, and heat accumulation prediction value; S3.2: The real-time heat accumulation control method includes: Establishing a heat flux density field prediction model, wherein the model calculates the temperature field distribution based on scanning path parameters, material thermal diffusion coefficient and laser energy parameters; Set the heat accumulation warning threshold. When the temperature gradient in the local area exceeds the critical value, the following operations are performed: a: interrupt the current scanning path and insert a cooling time interval; b: Switch to the adjacent low-temperature area to continue working; c: Dynamically adjust the filling density of the subsequent scanning path; S3.3: The cooling interval is determined by: Calculate the heat dissipation time according to the heat diffusion equation; Replan the path sequence based on the priority of subsequent processing areas.

5. The laser positioning and stripping method for special-shaped NdFeB waste according to claim 1, characterized in that: The S4 specifically includes: S4.1: In-situ surface roughness testing methods include: Confocal laser scanning technology was used to perform optical tomography along the normal direction of the peeling area, and the surface morphology data of the micro-area was obtained by axial scanning; Performing three-dimensional Fourier transform analysis on the tomographic image to extract spatial frequency distribution characteristics, including but not limited to the energy proportion of high-frequency components and the directional intensity distribution of medium-frequency components; Establishing a surface roughness evaluation function, wherein the function is obtained by weighted calculation of the deviation between the spatial frequency characteristics and a preset reference surface; S4.2: The triggering mechanism of the secondary refinement mode includes: When the surface roughness evaluation function value exceeds the first critical threshold, the finishing mode is started, which includes the following parameter adjustments: a: Reduce the laser power density to a fixed ratio of the original parameters; b: Increase the scanning speed to a fixed multiple of the original speed; c: Reduce the spot overlap rate to the preset safety range; During the finishing process, the surface roughness change rate is continuously monitored, and the finishing mode is automatically exited when the change rate approaches zero; S4.3: The method for dynamic correction of safe stripping margin includes: Establishing a peeling depth prediction model, wherein the model input parameters include cumulative laser energy density, material thermal diffusivity and oxide layer porosity; The ratio of the remaining substrate thickness to the original thickness is calculated in real time. When the ratio is lower than a second critical threshold, the following operations are performed: a: Immediately terminate laser irradiation in the current area; b: Mark the area as a prohibited processing area in the three-dimensional characteristic spectrum; c: Replan the scan path density in the surrounding area.

6. The laser positioning and stripping method for special-shaped NdFeB waste according to claim 1, characterized in that: The specific implementation of S5 includes: S5.1: Gas-solid separation kinetics include: The high-temperature gas generated during the laser stripping process is used to construct a vertical airflow field, and the turbulence intensity of the fluidized bed is controlled by adjusting the gas flow rate. The classification settling chamber is designed based on the difference in Stokes numbers between the oxide layer fragments and the matrix particles, which is derived from: The oxide layer fragments have a smaller size distribution range; The matrix particles have a higher mass density; A multi-stage baffle is set at the exit of the settling chamber, and the spacing between the baffles is determined according to the terminal velocity distribution of the particles; S5.2: Magnetic field assisted recovery methods include: A gradient magnetic field generator is arranged at the end of the sorting process, and the magnetic field strength increases along the direction of particle movement; Pre-magnetizing the matrix particles to generate residual magnetic moments in the particles through an alternating magnetic field; A particle trajectory control channel is designed based on the Lorentz force action principle, wherein the radius of curvature of the channel is inversely proportional to the magnetic field gradient; S5.3: Closed-loop control of the sorting process includes: A high-speed camera system is used to monitor the particle movement trajectory in real time; Count the escape rate of target particles through image recognition algorithm; Dynamically adjust the air flow speed and magnetic field strength to minimize the escape rate.

7. The laser positioning and stripping method for special-shaped NdFeB waste according to claim 5, characterized in that: The specific steps of the three-dimensional Fourier transform analysis in S4.1 include: S4.1.1: Convert the tomographic image sequence from the spatial domain to the frequency domain: Perform two-dimensional discrete Fourier transform layer by layer along the XY plane; Perform one-dimensional Fourier transform in the Z-axis direction to generate a three-dimensional spectrum; S4.1.2: Spatial frequency feature extraction method: The three-dimensional spectrum is divided into low-frequency area, medium-frequency area and high-frequency area. The boundary frequency of each area is determined by the surface characteristics of the material. Calculate the integrated energy of the complex modulus value in each frequency region and normalize it to the total energy percentage; Directional filtering is performed on the spectrum in the intermediate frequency region, and the energy distribution differences at the directions of 0°, 45°, 90°, and 135° are counted; S4.1.3: Construction process of surface roughness evaluation function: The reference surface is defined as the theoretical frequency distribution curve of the ideal peeling surface; Calculate the root mean square error between the measured data and the reference curve in each frequency band; Different weight coefficients are applied to the errors of each frequency band and then linearly superimposed, wherein the weight coefficients are related to the surface functional requirements.

8. The laser positioning and stripping method for special-shaped NdFeB waste according to claim 6, characterized in that: The design method of the graded settling chamber in S5.1 includes: S5.1.1: Determination of fluidized bed kinetic parameters: Calculate the dynamic viscosity coefficient based on the gas temperature; The formula for the terminal velocity of particles is derived based on Stokes' law, taking into account the influence of particle shape factors; The gas flow velocity which maximizes the velocity difference between the oxide layer fragments and the matrix particles is determined by iterative calculation; S5.1.2: Multi-level baffle optimization method: The differential equation of particle motion trajectory is established, and the input parameters include particle mass, gas flow rate and baffle geometric parameters; Monte Carlo simulation method is used to calculate the probability distribution of particle collisions; Taking the target particle recovery rate as the optimization goal, the optimal solution of the baffle spacing is solved by genetic algorithm; S5.1.3: Turbulence intensity control strategy: A porous medium rectifying layer is arranged at the inlet of the settling chamber; Monitor the pressure fluctuation value in real time and adjust the opening of the air supply valve through the PID controller; The turbulence suppression device is activated when the Reynolds number exceeds a critical value.

9. The laser positioning and stripping method for special-shaped NdFeB waste according to claim 1, characterized in that: The following post-processing steps are also included: S6: Establish a process knowledge base and conduct continuous optimization, including: S6.1: Machine Learning Model Training Methods: Collect historical processing data to build a training set, the data including three-dimensional characteristic spectrum parameters, laser energy sequence, surface roughness detection results and sorting efficiency indicators; The defined characteristic vector includes the mean value of the oxide layer thickness gradient, the maximum heat accumulation value and the path turning point density; Use deep neural networks to build a multi-objective optimization model and output the optimal process parameter combination; S6.2: Digital Twin Verification Methodology: Build a virtual machining environment and integrate the following physical field simulation modules: a: Thermodynamic model of laser-material interaction; b: Molecular dynamics model of the oxide layer stripping process; c: Computational fluid dynamics model of gas-solid two-phase flow; Input the actual processing parameters into the digital twin system for multi-physics field coupling simulation; When the deviation between the simulation result and the measured data exceeds the allowable range, the model parameter calibration process is triggered; S6.3: Process parameter self-optimization mechanism: Regularly compare and analyze actual production data with the knowledge base; Identify process parameter drift patterns and generate compensation coefficients; The optimization results are injected into the control system through online updating.

10. A laser positioning and stripping system for special-shaped NdFeB waste, used for running the laser positioning and stripping method for special-shaped NdFeB waste according to any of claims 1 to 9, characterized in that ,include: Multi-spectral scanning module, including: a long wavelength laser scanning unit configured to emit near infrared laser light that penetrates the oxide layer and collects geometric profile data of the substrate; a short wavelength laser scanning unit configured to emit visible laser light that interacts with the electron energy levels of the oxide layer and acquires optical response data of the oxide layer; A signal fusion processing unit, electrically connected to the long-wavelength and short-wavelength laser scanning units, configured to perform phase separation processing on the dual-band reflection signal and generate a three-dimensional characteristic spectrum; The dynamic energy control module is connected to the multi-spectral scanning module via a data bus, and includes: an energy calculation engine configured to receive oxide thickness data in a three-dimensional characteristic spectrum and calculate a step-wise energy parameter; A laser generating unit, electrically connected to the energy calculation engine, comprising an adjustable pulse width fiber laser and a beam shaping component; Plasma monitoring unit, integrating fiber optic spectrometer and characteristic peak recognition circuit, outputs laser termination signal in real time; The path planning control module is respectively connected to the multi-spectral scanning module and the dynamic energy regulation module through a high-speed data interface; Quality feedback correction module, including: a confocal microscopic imaging unit, optically coupled to the processing area and configured to collect surface topography data of a micro-area; The roughness analysis processor is connected to the microscopic imaging unit through an image acquisition card and has a built-in three-dimensional Fourier transform algorithm library; The safety margin calculation unit interacts with the dynamic energy control module through the data line and outputs the processing termination instruction; The gas-solid separation and recovery module is physically connected to the processing chamber outlet and includes: High-temperature airflow generating device, integrated with temperature sensor and flow control valve, forms thermodynamic coupling with the thermal field of laser processing area; The magneto-electric composite separation channel has gradient magnetic field generators and electrode arrays arranged in sequence along the material movement direction; The particle monitoring component includes a high-speed camera and an image processor, which provides feedback to adjust the sorting parameters.

Images