A laser cladding remanufacturing adaptive path planning method based on three-dimensional defect reconstruction
Patent Information
- Application Number
- CN202610887766.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-06-18
- Publication Date
- 2026-09-15
Smart Images
Figure CN122760892A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of laser cladding remanufacturing technology, and in particular to an adaptive path planning method for laser cladding remanufacturing based on three-dimensional defect reconstruction. Background Technology
[0002] Laser cladding remanufacturing technology is a key technology that restores the performance and extends the life of damaged parts by cladding metal materials on the surface of the parts. It is widely used in aerospace, high-end equipment manufacturing and other fields. Its core lies in accurately repairing part defects and controlling the thermal impact during the cladding process.
[0003] Existing laser cladding remanufacturing path planning methods mostly adopt a basic process based on three-dimensional defect reconstruction, that is, first obtain the three-dimensional data of the defect through 3D scanning, and then plan the cladding path. In terms of temperature control, the mainstream technology adopts adaptive scanning path planning based on transient temperature field feedback. The core strategy is to divide the area to be repaired into multiple sub-regions and always select the sub-region with the lowest current temperature for cladding, thereby dispersing heat and reducing part deformation and cracking.
[0004] The existing technology has obvious flaws: First, the path decision-making logic is too simplistic, relying solely on temperature as the only decision-making basis, without comprehensively considering key factors such as material properties, cladding efficiency, and defect geometric constraints, which can easily lead to redundant cladding paths and extended processing time. Second, it passively responds to heat accumulation, lacks forward-looking planning, cannot predict the trend of thermal impact before cladding, and is difficult to adapt to the high-precision repair needs in complex defect scenarios. Third, it is difficult to balance repair quality and efficiency. Choosing a single temperature-guided path can easily lead to insufficient density of the local cladding layer or low overall processing efficiency, which cannot meet the stringent requirements of high-end equipment remanufacturing. Summary of the Invention
[0005] In order to overcome the above-mentioned technical problems, the purpose of this invention is to provide an adaptive path planning method for laser cladding remanufacturing based on three-dimensional defect reconstruction: to solve the problems of the existing technology path decision logic being singular, the technology passively responding to heat accumulation, and the difficulty in balancing the quality and efficiency of technical repair.
[0006] The objective of this invention can be achieved through the following technical solutions: An adaptive path planning method for laser cladding remanufacturing based on three-dimensional defect reconstruction, the method specifically includes the following steps: S1: The defect area of the damaged part is scanned by a high-precision 3D scanning device to obtain the three-dimensional coordinate data, size data and geometric contour data of the defect, complete the three-dimensional defect reconstruction and generate a three-dimensional digital model of the defect. S2: Based on the three-dimensional digital model of the defect, the area to be repaired is divided into several sub-regions, and real-time temperature data, cladding material property data, defect geometric constraint data and preset process parameter data of each sub-region are collected. S3: Construct a multi-factor decision-making model, taking the real-time temperature data, cladding material property data, defect geometric constraint data and preset process parameter data of each sub-region as input variables, and calculate the cladding priority score of each sub-region through a preset multi-objective optimization algorithm; S4: Based on the cladding priority score of each sub-region, select the best cladding path and control the laser cladding head to clad the sub-region with the highest priority score in sequence until the repair of the entire defect area is completed. S5: After the cladding is completed, the repaired area is inspected again using a 3D scanning device. If the inspection result is qualified, the process ends. If it is not qualified, the 3D digital model of the defect is updated, and steps S2 to S4 are repeated until the repair is qualified.
[0007] As a further aspect of the present invention: in step S2, the cladding material property data includes at least the material's thermal conductivity, specific heat capacity, coefficient of linear expansion, and cladding layer density requirements; the defect geometric constraint data includes at least the area and depth of the sub-region, the spacing between adjacent sub-regions, and the defect contour curvature; the preset process parameter data includes at least the laser power, scanning speed, and powder feeding rate.
[0008] As a further aspect of the present invention: in step S3, the multi-objective optimization algorithm includes at least one of the following: genetic algorithm, particle swarm optimization algorithm, or reinforcement learning algorithm.
[0009] As a further aspect of the present invention: when using a reinforcement learning algorithm, the thermal stress of the part, the density of the cladding layer, and the total processing time during the cladding process are used as the core indicators of the reward function. The algorithm model is updated by real-time collected cladding data, and the cladding priority score of the sub-region is dynamically adjusted.
[0010] As a further aspect of the present invention: in step S3, the calculation formula for the cladding priority score is as follows: Priority score = Temperature weight coefficient (1 - real-time temperature of sub-region / highest temperature threshold) + Material property weight coefficient (material compatibility) + Geometric constraint weight coefficient (1 - constraint difficulty of sub-region / maximum constraint difficulty) + Process parameter weight coefficient (process matching degree) Where, , , are preset weight coefficients, and +++=1; temperature threshold and maximum constraint difficulty are preset according to part material and defect type.
[0011] As a further aspect of the present invention: in step S4, when selecting the cladding path, if there are multiple sub-regions with the same priority score, the sub-region closest to the current cladding head position is selected first, so as to reduce the idle travel time of the cladding head.
[0012] As a further aspect of the present invention: In step S4, during the cladding process, the temperature data of each sub-region is collected in real time by an infrared thermal imager. After the cladding of each sub-region is completed, the temperature data and cladding priority score of all sub-regions are updated, and the subsequent cladding path is dynamically adjusted.
[0013] As a further aspect of the present invention: In step S5, the criteria for determining whether the repair is qualified are: the surface flatness deviation of the repair area is 0.05mm, the bonding strength between the cladding layer and the substrate is 90% of the strength of the component substrate, and there are no obvious cracks, pores or other defects.
[0014] As a further aspect of the present invention: the high-precision 3D scanning device is a laser scanner or a structured light scanner, with a scanning accuracy of not less than 0.01mm.
[0015] The beneficial effects of this invention are: To address the shortcomings of existing technologies with their singular decision-making logic, this invention constructs a multi-factor decision-making model that comprehensively considers key factors such as temperature, material properties, geometric constraints, and process parameters. This enables multi-dimensional optimization of the cladding path, avoids path redundancy caused by a single temperature-driven approach, effectively shortens processing time, and improves cladding efficiency.
[0016] In response to the shortcomings of existing technologies that passively address heat accumulation, this invention uses a multi-objective optimization algorithm to proactively predict the trend of thermal impact and actively plan the cladding path, rather than passively selecting low-temperature areas. This allows for precise control of heat distribution before cladding, significantly reducing the risk of part deformation and cracking, and adapting to the high-precision repair needs in complex defect scenarios.
[0017] To address the shortcomings of existing technologies that struggle to balance repair quality and efficiency, this invention achieves a balance between repair quality and processing efficiency by dynamically adjusting the cladding priority score. This control of thermal stress ensures the density and bonding strength of the cladding layer, making it particularly suitable for remanufacturing high-end equipment such as aero-engine blades and precision molds, and can significantly reduce parts replacement costs. Attached Figure Description
[0018] The invention will now be further described with reference to the accompanying drawings.
[0019] Figure 1 This is a flowchart of an adaptive path planning method for laser cladding remanufacturing based on three-dimensional defect reconstruction, as described in this invention. Detailed Implementation
[0020] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.
[0021] Example 1: Please see Figure 1 As shown, this embodiment presents an adaptive path planning method for laser cladding remanufacturing based on three-dimensional defect reconstruction. The method specifically includes the following steps: S1: The defect area of the damaged part is scanned by a high-precision 3D scanning device to obtain the three-dimensional coordinate data, size data and geometric contour data of the defect, complete the three-dimensional defect reconstruction and generate a three-dimensional digital model of the defect. S2: Based on the three-dimensional digital model of the defect, the area to be repaired is divided into several sub-regions, and real-time temperature data, cladding material property data, defect geometric constraint data and preset process parameter data of each sub-region are collected. S3: Construct a multi-factor decision-making model, taking the real-time temperature data, cladding material property data, defect geometric constraint data and preset process parameter data of each sub-region as input variables, and calculate the cladding priority score of each sub-region through a preset multi-objective optimization algorithm; S4: Based on the cladding priority score of each sub-region, select the best cladding path and control the laser cladding head to clad the sub-region with the highest priority score in sequence until the repair of the entire defect area is completed. S5: After the cladding is completed, the repaired area is inspected again using a 3D scanning device. If the inspection result is qualified, the process ends. If it is not qualified, the 3D digital model of the defect is updated, and steps S2 to S4 are repeated until the repair is qualified.
[0022] In step S2, the cladding material property data includes at least the material's thermal conductivity, specific heat capacity, coefficient of linear expansion, and cladding layer density requirements; the defect geometric constraint data includes at least the area and depth of the sub-region, the spacing between adjacent sub-regions, and the defect contour curvature; and the preset process parameter data includes at least the laser power, scanning speed, and powder feeding rate.
[0023] In step S3, the multi-objective optimization algorithm includes at least one of the following: genetic algorithm, particle swarm optimization algorithm, or reinforcement learning algorithm.
[0024] When using reinforcement learning algorithms, the thermal stress of the parts, the density of the cladding layer, and the total processing time during the cladding process are used as the core indicators of the reward function. The algorithm model is updated by real-time collected cladding data, and the cladding priority score of sub-regions is dynamically adjusted.
[0025] In step S3, the formula for calculating the cladding priority score is: Priority score = Temperature weight coefficient (1 - real-time temperature of sub-region / highest temperature threshold) + Material property weight coefficient (material compatibility) + Geometric constraint weight coefficient (1 - constraint difficulty of sub-region / maximum constraint difficulty) + Process parameter weight coefficient (process matching degree) Where, , , are preset weight coefficients, and +++=1; temperature threshold and maximum constraint difficulty are preset according to part material and defect type.
[0026] In step S4, when selecting the cladding path, if there are multiple sub-regions with the same priority score, the sub-region closest to the current cladding head position is selected first to reduce the idle travel time of the cladding head.
[0027] In step S4, during the cladding process, the temperature data of each sub-region is collected in real time by an infrared thermal imager. After the cladding of each sub-region is completed, the temperature data and cladding priority score of all sub-regions are updated, and the subsequent cladding path is dynamically adjusted.
[0028] In step S5, the criteria for determining whether the repair is qualified are: the surface flatness deviation of the repair area is 0.05mm, the bonding strength between the cladding layer and the substrate is 90% of the strength of the substrate, and there are no obvious cracks, pores or other defects.
[0029] High-precision 3D scanning equipment is a laser scanner or a structured light scanner, with a scanning accuracy of no less than 0.01mm.
[0030] Example 2: This embodiment is illustrated with reference to Embodiment 1, which describes the repair of defects in aero-engine blades. 3D Defect Reconstruction: A laser scanner with an accuracy of 0.008 mm was used to scan the defect area (approximately 12 cm in area and 0.3 mm in maximum depth) of a titanium alloy blade of an aero-engine to obtain the 3D coordinates, dimensions and contour data of the defect, generate a 3D digital model of the defect, and clarify the geometric distribution and depth gradient of the defect.
[0031] Data Acquisition: The area to be repaired was divided into 24 sub-regions with an area of approximately 0.5 cm². Real-time temperature data (initial temperature 25℃), thermal conductivity (15W / (mK)), specific heat capacity (420J / (kg℃)), coefficient of linear expansion (9.210^-6 / ℃), and density requirements of the cladding layer (99.5%) of each sub-region were collected. At the same time, defect geometric constraint data (average depth of sub-region 0.22mm, spacing between adjacent sub-regions 0.1mm, average curvature of defect contour 0.8mm^-1) and preset process parameters (laser power 1800W, scanning speed 8mm / s, powder feeding rate 15g / min) were collected.
[0032] Multi-factor decision model construction: Particle swarm optimization algorithm is adopted, with weight coefficients set to 0.35, 0.25, 0.2, and 0.2, temperature threshold of 600℃, and maximum constraint difficulty of 1.5; the cladding priority score of each sub-region is calculated according to the formula, with an initial score range of 0.42-0.78.
[0033] Path planning and cladding: Select the sub-region with the highest priority score (score 0.78) as the first cladding region and control the laser cladding head to perform cladding; after each sub-region is clad, update the temperature data of each sub-region through the infrared thermal imager (the highest temperature rises to 180℃), recalculate the priority score, and dynamically adjust the cladding path to avoid continuous cladding of adjacent high-temperature sub-regions.
[0034] Quality inspection: After the cladding is completed, the repaired area is inspected by 3D scanning. The surface flatness deviation is 0.03mm, the bonding strength between the cladding layer and the substrate is 92%, and there are no cracks or pore defects. It is judged to be qualified and the process ends.
[0035] Example 3: This embodiment is illustrated with reference to Embodiment 1, and it describes the repair of defects in precision molds. 3D Defect Reconstruction: A structured light scanner was used to scan the defect area (approximately 8 cm in area and 0.2 mm in maximum depth) of a precision mold (made of H13 steel) to generate a 3D digital model of the defect, clarifying the irregular contour and local depth abrupt change areas of the defect.
[0036] Data Acquisition: The area to be repaired was divided into 16 sub-regions. The initial temperature (23℃), thermal conductivity (24W / (mK)), specific heat capacity (460J / (kg℃)), coefficient of linear expansion (11.5×10^-6 / ℃), and hardness requirements of the cladding layer (HRC52-55) of each sub-region were collected. Defect geometric constraint data (sub-region depth range 0.1-0.2mm, maximum contour curvature 1.2mm^-1) and preset process parameters (laser power 1500W, scanning speed 6mm / s, powder feeding rate 12g / min) were collected.
[0037] Multi-factor decision-making model construction: Reinforcement learning algorithm is adopted, with thermal stress of 300MPa, cladding layer hardness compliance rate of 95%, and total processing time of 20min as the core indicators of the reward function; through pre-trained model, combined with real-time collected cladding data, the cladding priority score of sub-regions is dynamically updated, focusing on reducing the cladding priority of deep abrupt change areas to avoid local heat concentration.
[0038] Path planning and cladding: Sub-regions are clad sequentially according to priority scores. When a sub-region's temperature is detected to rise to 220℃, that region is automatically skipped, and the sub-region with the second highest score and a temperature of 150℃ is selected for cladding. At the same time, if there are sub-regions with the same score, the region closest to the cladding head is selected first to reduce idle travel time.
[0039] Quality inspection: After the cladding was completed, the inspection showed that the surface flatness deviation of the repaired area was 0.02mm, the hardness of the cladding layer was HRC53, the bonding strength was 95%, and there were no obvious defects. It was judged to be qualified.
[0040] Key data comparison table Technical indicators Existing technology (single temperature guidance) This invention (multi-factor decision-making) Increase Part deformation rate 0.8%-1.2% 0.2%-0.4% Reduced by 66.7%-75% Cladding layer density 98.2%-98.8% 99.3%-99.7% Increase by 0.5%-0.9% Average processing time (10cm) 28-32min 18-22min Shortened by 32.1%-35.7% Complicated defect repair pass rate 82%-86% 96%-98% An increase of 11.6%-13.9% The above description is only a preferred embodiment of the present invention and is not intended to limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.
[0041] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0042] The above description is merely an example and illustration of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the invention or exceed the scope defined in the claims, all of which should fall within the protection scope of the present invention.
Claims
1. An adaptive path planning method for laser cladding remanufacturing based on three-dimensional defect reconstruction, characterized in that, The method specifically includes the following steps: S1: The defect area of the damaged part is scanned by a high-precision 3D scanning device to obtain the three-dimensional coordinate data, size data and geometric contour data of the defect, complete the three-dimensional defect reconstruction and generate a three-dimensional digital model of the defect. S2: Based on the three-dimensional digital model of the defect, the area to be repaired is divided into several sub-regions, and real-time temperature data, cladding material property data, defect geometric constraint data and preset process parameter data of each sub-region are collected. S3: Construct a multi-factor decision-making model, taking the real-time temperature data, cladding material property data, defect geometric constraint data and preset process parameter data of each sub-region as input variables, and calculate the cladding priority score of each sub-region through a preset multi-objective optimization algorithm; S4: Based on the cladding priority score of each sub-region, select the best cladding path and control the laser cladding head to clad the sub-region with the highest priority score in sequence until the repair of the entire defect area is completed. S5: After the cladding is completed, the repaired area is inspected again using a 3D scanning device. If the inspection result is qualified, the process ends. If it is not qualified, the 3D digital model of the defect is updated, and steps S2 to S4 are repeated until the repair is qualified.
2. The adaptive path planning method for laser cladding remanufacturing based on three-dimensional defect reconstruction according to claim 1, characterized in that, In step S2, the cladding material property data includes at least the material's thermal conductivity, specific heat capacity, coefficient of linear expansion, and cladding layer density requirements; the defect geometric constraint data includes at least the area and depth of the sub-region, the spacing between adjacent sub-regions, and the defect contour curvature; and the preset process parameter data includes at least the laser power, scanning speed, and powder feeding rate.
3. The adaptive path planning method for laser cladding remanufacturing based on three-dimensional defect reconstruction according to claim 1, characterized in that, In step S3, the multi-objective optimization algorithm includes at least one of the following: genetic algorithm, particle swarm optimization algorithm, or reinforcement learning algorithm.
4. The adaptive path planning method for laser cladding remanufacturing based on three-dimensional defect reconstruction according to claim 3, characterized in that, When using reinforcement learning algorithms, the thermal stress of the parts, the density of the cladding layer, and the total processing time during the cladding process are used as the core indicators of the reward function. The algorithm model is updated by real-time collected cladding data, and the cladding priority score of sub-regions is dynamically adjusted.
5. The adaptive path planning method for laser cladding remanufacturing based on three-dimensional defect reconstruction according to claim 1, characterized in that, In step S3, the formula for calculating the cladding priority score is as follows: Priority score = Temperature weight coefficient (1 - real-time temperature of sub-region / highest temperature threshold) + Material property weight coefficient (material compatibility) + Geometric constraint weight coefficient (1 - constraint difficulty of sub-region / maximum constraint difficulty) + Process parameter weight coefficient (process matching degree) Where, , , are preset weight coefficients, and +++=1; temperature threshold and maximum constraint difficulty are preset according to part material and defect type.
6. The adaptive path planning method for laser cladding remanufacturing based on three-dimensional defect reconstruction according to claim 1, characterized in that, In step S4, when selecting the cladding path, if there are multiple sub-regions with the same priority score, the sub-region closest to the current cladding head position is selected first to reduce the idle travel time of the cladding head.
7. The adaptive path planning method for laser cladding remanufacturing based on three-dimensional defect reconstruction according to claim 1, characterized in that, In step S4, during the cladding process, the temperature data of each sub-region is collected in real time by an infrared thermal imager. After the cladding of each sub-region is completed, the temperature data and cladding priority score of all sub-regions are updated, and the subsequent cladding path is dynamically adjusted.
8. The adaptive path planning method for laser cladding remanufacturing based on three-dimensional defect reconstruction according to claim 1, characterized in that, In step S5, the criteria for determining whether the repair is qualified are: the surface flatness deviation of the repair area is 0.05mm, the bonding strength between the cladding layer and the substrate is 90% of the strength of the substrate, and there are no obvious cracks, pores or other defects.
9. The adaptive path planning method for laser cladding remanufacturing based on three-dimensional defect reconstruction according to any one of claims 1-8, characterized in that, The high-precision 3D scanning equipment is a laser scanner or a structured light scanner, with a scanning accuracy of not less than 0.01 mm.