Deburring method and device based on self-adaptive adjustment of water particle flow parameters

Abstract

The invention discloses a deburring method and device based on self-adaptive adjustment of water particle flow parameters, and relates to the technical field of burr removal, the method comprises the following steps: obtaining material information and a burr detection feature set of a target part through a part detection device, and matching initial water particle flow parameters based on the material; dividing N equivalent regions according to the burr feature set, and adjusting the initial parameters to obtain N region parameters; the water particle flow distribution processing device comprises a water particle flow generator, a part fixing component and a surface detection assembly; and after the part is fixed, deburring is carried out based on the N area parameters, meanwhile, the data flow is monitored in real time through the detection assembly, and the area parameters are adjusted and optimized. The technical problems that according to an existing deburring method, water particle flow parameters cannot be adjusted in a self-adaptive mode according to different materials and burr characteristics, so that the deburring precision is not high, and the surface quality of parts is difficult to guarantee are solved, and the technical effect of improving the deburring precision, the workpiece quality and the production efficiency is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of burr removal, and in particular to a burr removal method and device based on adaptive adjustment of water particle flow parameters. Background Art

[0002] With the continuous improvement of the requirements for part surface quality in the field of precision manufacturing, the accuracy and efficiency of the deburring process have become key factors restricting the performance of high-end equipment. Traditional mechanical or chemical deburring methods have problems such as poor processing adaptability, easy damage to the substrate, and environmental pollution, while water particle flow technology has gradually become the mainstream due to its non-contact processing characteristics. However, the existing water particle flow process mostly relies on manual experience to set fixed parameters. When faced with working conditions such as differences in the materials of complex parts and uneven distribution of burrs, insufficient processing or overshoot is prone to occur, resulting in fluctuations in surface roughness and increased rework rate. Especially in mass production, the parameter solidification mode is difficult to balance processing quality and efficiency, and lacks a dynamic feedback mechanism for real-time processing status. To this end, it is urgent to build a data-driven water particle flow parameter intelligent control system. By integrating material identification, burr feature quantitative analysis and closed-loop control technology, it breaks through the static parameter limitations of traditional methods and realizes adaptive optimization of the processing process, thereby meeting the needs of precision manufacturing for high consistency surface quality and flexible production. Summary of the invention

[0003] The present application provides a deburring method and device based on adaptive adjustment of water particle flow parameters, thereby solving the technical problem that the existing deburring method cannot adaptively adjust the water particle flow parameters according to different materials and burr characteristics, resulting in low deburring accuracy and difficulty in ensuring the surface quality of parts.

[0004] The present application provides a deburring method based on adaptive adjustment of water particle flow parameters, the method comprising: obtaining material information and a burr detection feature set of a target part through a part detection device, performing parameter matching retrieval based on the material information, and obtaining initial water particle flow parameters; performing equivalent division of the target part according to the burr detection feature set, determining N equivalent part burr areas, adaptively adjusting the initial water particle flow parameters based on the N equivalent part burr areas, and obtaining N regional water particle flow parameters; arranging a water particle flow processing device, the water particle flow processing device comprising a water particle flow generator, a part fixing component, and a part surface detection component; positioning the target part using the part fixing component, performing deburring processing on the positioned target part based on the N regional water particle flow parameters through the water particle flow generator, and simultaneously obtaining a part deburring monitoring data stream through real-time monitoring of the part surface detection component; and adjusting, compensating, and optimizing the N regional water particle flow parameters based on the part deburring monitoring data stream.

[0005] The present application also provides a deburring device based on adaptive adjustment of water particle flow parameters, including: a parameter matching and retrieval module: obtaining material information and a burr detection feature set of a target part through a part detection device, performing parameter matching and retrieval based on the material information, and obtaining initial water particle flow parameters; an adaptive adjustment module: performing equivalent division of the target part according to the burr detection feature set, determining N equivalent part burr areas, and adaptively adjusting the initial water particle flow parameters based on the N equivalent part burr areas to obtain N regional water particle flow parameters; a processing device layout module: arranging a water particle flow processing device, the water particle flow processing device including a water particle flow generator, a part fixing component and a part surface detection component; a real-time monitoring module: using the part fixing component to locate the target part, performing deburring processing on the located target part based on the N regional water particle flow parameters through the water particle flow generator, and simultaneously obtaining a part deburring monitoring data stream through real-time monitoring of the part surface detection component; an adjustment compensation optimization module: adjusting and compensating and optimizing the N regional water particle flow parameters based on the part deburring monitoring data stream.

[0006] The deburring method and device based on adaptive adjustment of water particle flow parameters proposed in this application are intended to, first, obtain material information and a burr detection feature set of a target part through a part detection device, perform parameter matching retrieval based on the material information, and obtain initial water particle flow parameters; then, perform equivalent division of the target part according to the burr detection feature set, determine N equivalent part burr areas, and adaptively adjust the initial water particle flow parameters based on the N equivalent part burr areas to obtain N regional water particle flow parameters; further, arrange a water particle flow processing device, the water particle flow processing device includes a water particle flow generator, a part fixing component and a part surface detection component; then, use the part fixing component to position the target part, perform deburring processing on the positioned target part based on the N regional water particle flow parameters through the water particle flow generator, and simultaneously obtain the part deburring monitoring data stream through the part surface detection component in real time monitoring; finally, adjust, compensate and optimize the N regional water particle flow parameters based on the part deburring monitoring data stream. The invention solves the technical problem that the existing deburring method cannot adaptively adjust the water particle flow parameters according to different materials and burr characteristics, resulting in low deburring accuracy and difficulty in ensuring the surface quality of parts. The invention achieves the technical effect of intelligently matching and adjusting the water particle flow parameters according to the part material and burr characteristics, thereby improving the deburring accuracy, workpiece quality and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the device according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0008] Figure 1 A schematic flow chart of a deburring method based on adaptive adjustment of water particle flow parameters provided in an embodiment of the present application.

[0009] Figure 2 A schematic diagram of the structure of a deburring device based on adaptive adjustment of water particle flow parameters provided in an embodiment of the present application.

[0010] Explanation of the accompanying drawings: parameter matching and retrieval module 11, adaptive adjustment module 12, processing device layout module 13, real-time monitoring module 14, adjustment compensation optimization module 15. DETAILED DESCRIPTION

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0012] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0013] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0014] The present application embodiment provides a deburring method based on adaptive adjustment of water particle flow parameters, such as Figure 1 As shown, the method includes: The material information and burr detection feature set of the target part are obtained through the part detection device, and parameter matching retrieval is performed based on the material information to obtain the initial water particle flow parameters.

[0015] In the embodiment of the present application, in the process preparation stage, the target parts are firstly scanned and analyzed comprehensively by an integrated parts detection device. The parts detection device integrates sensors such as a spectrometer and a hardness tester, and identifies metal components (such as the proportion of aluminum, silicon, and magnesium in aluminum alloys) through spectral analysis. At the same time, the compressive strength of the material is quantified in combination with hardness testing. For example, for titanium alloy parts, spectral analysis can detect its Ti-6Al-4V composition, and the hardness tester measures the Rockwell hardness HRC38-42, thereby accurately determining the material category. This information will together constitute the material information of the target parts, which is used to match the water particle flow parameters of the material from the part material-water particle flow parameter library. In addition, the characteristic data such as the three-dimensional morphology, distribution density, and bonding strength of the burrs are captured by high-precision sensors (such as high-precision industrial cameras and tactile sensors) to form a complete burr feature quantitative data set. Afterwards, based on the material properties (such as aluminum alloy, titanium alloy, etc.), the preset part material-water particle flow parameter library is called up to match and retrieve the initial water particle flow parameter combination that matches the current material mechanical properties, such as water pressure value, abrasive particle size, spray angle and other core parameters, to provide a benchmark configuration for subsequent dynamic optimization.

[0016] Table 1: Water particle flow deburring processing parameter matching table

[0017] Among them, Table 1 shows the water particle flow processing parameters corresponding to different part materials and burr features. Each row represents a part material and lists the relevant burr height, length and width, as well as the initial water particle flow parameters (such as pressure and flow rate) selected for the material and burr features. These parameters are used to optimize the deburring processing effect and ensure processing accuracy and efficiency.

[0018] Furthermore, the present application provides the method of obtaining material information and burr detection feature set of a target part by a part detection device, including: A parts detection device is obtained, wherein the parts detection device is composed of a spectrum analyzer, a hardness tester, a high-precision industrial camera and a tactile sensor connected in communication; the metal composition and hardness information of the target part are detected and obtained in turn by the spectrum analyzer and the hardness tester, and the material information of the target part is determined according to the metal composition and hardness information; the surface burr image and the burr combination strength set of the target part are acquired by using the high-precision industrial camera and the tactile sensor; the surface burr image is marked for burr recognition to obtain a surface burr area set, and the surface burr area set and the burr combination strength set are combined to form a burr detection feature set for the target part.

[0019] Preferably, the parts detection device is composed of a spectrometer, a hardness tester, a high-precision industrial camera and a tactile sensor. These devices synchronize data between sensors through CAN bus or Ethernet to ensure that the detection data (such as composition and hardness) of the spectrometer and the hardness tester are aligned with the industrial camera image and the mechanical data timestamp of the tactile sensor to form an integrated detection device, wherein the spectrometer uses X-ray fluorescence spectroscopy (XRF) technology to detect metal element composition (such as aluminum, titanium, and iron content); the hardness tester is equipped with a Vickers hardness indenter (HV scale) to measure surface hardness (such as testing under HV0.3 load); the high-precision industrial camera is equipped with a 50-megapixel CMOS sensor and a ring LED light source with a resolution of 5μm / pixel; the tactile sensor is based on a piezoelectric ceramic array to measure the burr bonding force (range 0-50N, accuracy ±0.1N). The target part is placed on the spectrometer detection table in the part detection device, and the spectrometer emits X-rays to excite atomic fluorescence, scans the target part, analyzes the characteristic spectrum wavelength, and obtains its metal composition information. These data include the type of elements and their proportions, which help determine the type of part material. Subsequently, three test points are selected on the surface of the target part, and the hardness of the part is measured using a hardness tester. Units such as Brinell hardness (HB) or Rockwell hardness (HR) are usually used. The hardness information helps to further analyze the physical properties of the part and provide a basis for the subsequent processing process. After obtaining the metal composition information and hardness information, the metal composition information and hardness information are input into a preset material database (such as the SAE standard library) to match the material information of the target part. In addition, according to the preset angle (such as 45°), the target part is scanned by a high-precision industrial camera to collect high-definition images of the surface of the target part, especially the morphology of the surface burrs. These surface burr images will show the shape, distribution and size of the burrs. Then, the tactile probe of the tactile sensor is used to contact the root of the burr at a constant speed (0.5mm / s), and a force is applied laterally along the root of the burr to record the peeling force curve (such as a peak force of 12.3N), thereby measuring the bonding strength of the burr, that is, the adhesion between the burr and the surface of the part, to help determine the difficulty of removing the burr. Afterwards, the burr images captured by the high-precision industrial camera are marked for burr recognition. Specifically, the surface images of the target parts are captured by the high-precision industrial camera. The images usually contain noise and uneven lighting, so preprocessing is required, including noise removal, contrast enhancement, and lighting adjustment, etc., in order to better identify burrs. For example, filtering techniques such as Gaussian filtering or median filtering can be used to smooth the image and remove irrelevant noise. After preprocessing, edge detection algorithms (such as Canny edge detection) are used to identify significant edges in the image. Burrs usually appear as obvious edges or protrusions. Edge detection algorithms help to highlight the shape and boundaries of burrs. Through edge detection, the boundary between the part surface and the burr can be accurately identified, thereby effectively distinguishing the burr area from other parts.Then, the identified edge area in the image is subjected to contour extraction to determine the specific location and shape of each burr. Through contour extraction, the size, shape and distribution of the burr can be identified, thereby obtaining the geometric features of the burr such as height, length, width, etc., which help to confirm the type and degree of the burr. Based on the extracted contour information, the image segmentation algorithm is used to separate the burr area from the surface background of the part to form multiple independent burr areas. These areas can be a single burr or a collection of multiple burrs. Each burr area will be given a unique mark to ensure that different burr areas can be distinguished in the subsequent processing process. After that, all identified and marked burr areas are summarized to form a complete burr area set, namely the surface burr area set. This surface burr area set contains the location information of all burrs in the image and provides data support for subsequent deburring processing. The marks and features (such as size, position, etc.) of each burr area will be used for further adjustment of processing parameters and optimization of deburring effects. Finally, the burr area set and the burr bonding strength set are combined and integrated to form a burr detection feature set. This feature set contains the geometric information (such as size and position) and physical properties (such as bonding strength) of the burrs on the surface of the parts, providing the necessary data support for the subsequent matching and adjustment of water particle flow processing parameters, significantly improving the consistency of the processing quality of complex parts.

[0020] Further, the present application provides the composition for obtaining the burr detection feature set of the target part, including: The burr information of each area in the surface burr area set is measured and calculated to obtain a regional burr average height set, a regional burr average length set and a regional burr width distribution set; the regional burr quantity set and the regional burr area set of the burr information of each area are calculated in turn, and the ratio of the regional burr quantity set to the regional burr area set is used as the regional burr distribution density feature set; the morphological features of the burr information of each area are extracted in turn according to the burr morphological type library to obtain a regional burr morphological feature set; the regional burr average height set, the regional burr average length set and the regional burr width distribution set, as well as the regional burr distribution density feature set and the regional burr morphological feature set are feature-associated and mapped with the burr combination strength set to form a burr detection feature set for the target part.

[0021] Optionally, after obtaining the surface burr area set, each burr area in the surface burr area set will be traversed, and for each burr area traversed, the average height of the regional burrs is obtained by calculating the mean of the burr height in the burr area; the average length of the regional burrs is obtained by calculating the mean of the burr length in the burr area; the average length of the regional burrs is obtained by calculating the mean of the burr width in the burr area. By summarizing the regional burr average height, regional burr average length, and regional burr average width of all burr areas, a regional burr average height set, a regional burr average length set, and a regional burr width distribution set are obtained. Subsequently, for each burr area, the number of burrs inside it is counted, and the pixel area of ​​the burrs is obtained from the contour detection result. By summarizing the number of burrs and pixel areas of all burr areas, a regional burr number set and a regional burr area set are obtained. These two sets will together constitute the burr information of each area. Afterwards, the ratio of the number of regional burrs and the area of ​​regional burrs at the corresponding positions in the regional burr number set and the regional burr area set is calculated to obtain the regional burr distribution density feature set. The ratio reflects the number of burrs per unit area and indicates the distribution density of the burrs. The larger the distribution density, the denser the burrs are, the more difficult it is to remove them, and more sophisticated processing parameters are required. Then, the burr morphology type library is used to extract the morphological features of the burrs in each burr area. The burr morphology type library contains the morphological features of different types of burrs (such as sharp burrs, wide and flat burrs, etc.). By comparing the geometric morphology in the burr information of each region with the burr geometric morphology recorded in the library, the burr morphological features of each region are extracted, and these features are summarized into a regional burr morphological feature set. These features help to determine the difficulty of burr removal and the required processing method. For example, sharp burrs usually require higher water particle flow impact force. Finally, the obtained regional burr average height set, regional burr average length set, regional burr width distribution set, regional burr distribution density feature set and regional burr morphology feature set are associated with the burr combination strength set, that is, the feature data of the same region are matched. Through this association mapping, the characteristics of the burrs can be understood more accurately, and a more accurate basis can be provided for the subsequent adjustment of water particle flow parameters. After the above processing, the burr detection feature set of the target part is finally obtained. This feature set contains comprehensive information about the burrs on the surface of the part, including the size, distribution density, morphological characteristics and bonding strength of the burrs, etc., which provides sufficient parameter support for the subsequent deburring process and significantly improves the consistency of the processing quality of complex parts.

[0022] Further, the present application provides the method of obtaining the initial water particle flow parameters, including: Mining and acquiring a parts water particle flow processing data set, the parts water particle flow processing data set includes material data of historical parts, water particle flow processing parameters and corresponding processing effect data; presetting a part deburring benchmark effect, based on the processing effect data, screening the material data and water particle flow processing parameters of the historical parts that meet the part deburring benchmark effect, to obtain available part material data and available water particle flow processing parameters; associating and mapping the available part material data and available water particle flow processing parameters, to construct a part material-water particle flow parameter library; based on the material information, traversing, matching and searching in the part material-water particle flow parameter library, to obtain the initial water particle flow parameters.

[0023] Preferably, the water particle flow processing data of historical parts are collected through the processing database, experimental data records and literature. The data set includes the material data of the historical parts, the water particle flow processing parameters and the corresponding processing effect data, wherein the material data of the historical parts records the material information of each part (such as metal composition, hardness, etc.), helping to understand the performance of different materials in water particle flow processing; the water particle flow processing parameters include the water particle flow parameters used in each processing process (such as water flow pressure, flow rate, etc.), which are used for deburring processing; the corresponding processing effect data records the actual effect data of each processing result, such as the deburring effect, surface roughness, etc., which are used to evaluate the quality of processing. Subsequently, in combination with industry standards and actual needs, a standard deburring effect is set as a benchmark, usually based on indicators such as surface roughness and burr removal rate, to ensure that the surface of the part meets the required quality standards. By comparing the processing effect data of the historical parts with the deburring benchmark effect, the part material data and water particle flow processing parameters that can achieve the benchmark effect are selected. These data are considered to be effective and can achieve the ideal deburring effect, so these data are used as available part material data and available water particle flow processing parameters. After that, the selected available part material data and available water particle flow processing parameters are associated and mapped, that is, a one-to-one correspondence is established between each part material (such as stainless steel, aluminum alloy, etc.) and the corresponding water particle flow processing parameters (such as pressure, flow rate, etc.), thereby forming a part material-water particle flow parameter library, which stores the water particle flow processing parameters corresponding to parts of different materials, so as to quickly find matching parameter combinations. Then, when a new target part needs to be deburred by water particle flow, based on the material information of the target part, a traversal matching search is performed in the part material-water particle flow parameter library to find the water particle flow processing parameter combination that best matches the target part material, thereby obtaining the initial water particle flow parameters of the target part. These initial parameters provide the basis for deburring processing and ensure that the best deburring effect can be provided for parts of this material. Through this series of steps, historical data and experience can be used to provide appropriate water particle flow processing parameters for the target part, ensure the best deburring effect, and improve processing accuracy and efficiency.

[0024] The target part is equivalently divided according to the burr detection feature set to determine N equivalent part burr areas, and the initial water particle flow parameters are adaptively adjusted based on the N equivalent part burr areas to obtain N regional water particle flow parameters.

[0025] In one embodiment, the surface of the target part is analyzed according to the acquired burr detection feature set. First, the surface burr area of ​​the part is divided into multiple equivalent areas using K-Means cluster analysis. Each equivalent area represents a part with similar burr features on the surface of the part. The division of these areas is based on the size, shape, distribution density and other characteristics of the burr, so that suitable deburring parameters can be used in each area. Once these equivalent part burr areas are determined, the initial water particle flow parameters can be adaptively adjusted based on the burr characteristics of each area and combined with the deburring effect fitness function. For example, for some areas, higher water flow pressure may be required to remove larger or harder burrs, while other areas may only require lower water flow pressure. In this way, water particle flow parameters are tailored for each area to ensure that the burrs in each area can be effectively removed. Finally, each area after adjustment will have an independent water particle flow parameter set, which can ensure that the deburring effect of different areas is optimal, thereby improving the overall processing effect and part quality.

[0026] Further, the present application provides the method of determining N equivalent part burr areas, comprising: The burr detection feature set is standardized to obtain a standard burr detection feature set; a K-Means clustering analysis is performed based on the standard burr detection feature set to obtain a burr feature cluster set, wherein each cluster in the burr feature cluster set corresponds to an equivalent burr feature group; adjacent regions of the burr position marks in the burr feature cluster set are merged on the target part to obtain an equivalent burr feature continuous region set; each continuous region in the equivalent burr feature continuous region set is numbered and recorded in turn to determine the N equivalent part burr regions.

[0027] Preferably, before analyzing the burr detection feature set, the burr detection feature set needs to be standardized to ensure that feature data of different scales and units can be compared within the same range. The standardization process usually includes normalizing or standardizing each feature (such as burr height, length, width, distribution density, etc.) to eliminate the influence between different dimensions and facilitate subsequent processing and analysis. The method usually adopted is maximum-minimum normalization. After the standardization is completed, the burr features are grouped based on the standardized burr detection feature set using the K-Means clustering algorithm. Specifically, the K value, that is, the number of clusters, is first set. This value is usually determined based on field experience, experimental results or through the elbow rule. The elbow rule selects the position where the error change tends to be flat as the K value by drawing a graph of the sum of squared errors (SSE) as the K value changes. Once the K value is determined, K initial cluster centers are randomly selected. These cluster centers represent the center points of each cluster. The center of each cluster is initially randomly selected. Subsequently, for each burr data point, the distance between it and the centers of K clusters is calculated, usually using the Euclidean distance. Each data point will be assigned to the center of the cluster closest to it to form a different cluster, so that each cluster contains some burr areas with similar features. After the data points are assigned to the clusters, the center of each cluster is recalculated. The new cluster center is the mean of the features of all data points in the cluster. At this time, the position of the cluster center will be updated to reflect the overall situation of the burr features in the cluster. Repeat the above process until the cluster center no longer changes significantly or reaches the preset maximum number of iterations, indicating that the clustering process has converged. After convergence, the burr features in each cluster are similar, forming multiple burr feature clusters. Each cluster represents an equivalent burr feature group, and the center of each cluster represents the overall features of the burr features in the group, which can be used for subsequent processing parameter adjustment. After that, the burr feature position in each cluster is marked on the surface of the target part, and the adjacent burr clusters are merged to form a continuous burr area. The merged area is called an equivalent burr feature continuous area set, which represents the parts with similar burr features on the surface of the part. Then, each continuous region of equivalent burr features is assigned a number, and each region is given a unique identifier for reference in subsequent processing. At the same time, the characteristic information of each region is recorded, including the size, shape and distribution of the burr. These characteristics are helpful for subsequent adjustment of processing parameters and optimization of effects. By numbering and recording the characteristics of each region in the set of continuous regions of equivalent burr features, N equivalent part burr regions are finally determined. These regions represent different burr distribution areas on the surface of the part. The burr characteristics of each region are similar, and the same water particle flow processing parameters can be used for deburring. Through the above steps, the surface of the target part is divided into multiple regions with similar burr characteristics. Each region can customize appropriate processing parameters according to its characteristics to ensure the accuracy and efficiency of the deburring process.

[0028] Table 2: Burr area feature clustering and merging record table

[0029] Among them, Table 2 shows the characteristic data of each burr area and its changes during the clustering and merging process. Each burr area is measured and the geometric features such as height, length, width, etc. are recorded, and the position of the burr on the surface of the part is marked. Through the K-Means clustering algorithm, burr areas with similar characteristics are assigned to the same cluster and merged into continuous burr areas in the subsequent processing process. The regional feature records in the table provide a basis for further adjustment of processing parameters.

[0030] Further, the present application provides the method of obtaining N regional water particle flow parameters, including: According to the N equivalent part burr areas, N equivalent area burr features are determined; based on the N equivalent area burr features, the initial water particle flow parameters are adaptively adjusted and analyzed to obtain N area parameter selection thresholds; a deburring effect fitness function is constructed, and based on the deburring effect fitness function, global optimization is performed within the N area parameter selection thresholds to obtain N area water particle flow parameters.

[0031] Preferably, according to the N equivalent part burr areas divided in the above steps, the burr features of each area are analyzed and extracted. These burr features include but are not limited to the average height, length, width, shape, distribution density, etc. of the burrs. Through these features, the unique attributes of each burr area are determined for subsequent parameter adjustment. The burr features of each area reflect the specific situation of the burrs in the area and provide key data for adjusting the water particle flow parameters. Subsequently, based on the burr features of each area, the maximum and minimum values ​​of each feature of each area are counted, and then the burr features corresponding to the initial water particle flow parameters are obtained from the part material-water particle flow parameter library as standard values. By calculating the ratio of the minimum value of each feature to the corresponding standard value, and then calculating the mean of the calculation results of each feature, and multiplying the calculated results with the initial water particle flow parameters to perform adaptive adjustment of the initial water particle flow parameters, the lower limit threshold in the regional parameter selection threshold of the burr features of each equivalent area is obtained. Similarly, the same operation is performed on the maximum value of each feature to calculate the upper limit threshold in the regional parameter selection threshold. This regional parameter selection threshold can better adapt to the deburring needs of specific areas, ensuring that the deburring effect of each area is optimized, and avoiding the situation where unified parameters cannot meet the needs of different areas. Afterwards, according to actual needs, a deburring effect fitness function is constructed. This deburring effect fitness function is a mathematical function used to quantify the effect of different water particle flow parameters in the deburring process. This function takes into account factors such as surface roughness after processing, burr removal rate, and processing time. The deburring effect fitness function is as follows: ;in, is the fitness of the current water particle flow parameters; Indicates surface roughness. The smaller the roughness, the better the deburring effect. Indicates the burr removal rate. The higher the removal rate, the better the burr removal effect. Indicates processing time. The shorter the time, the higher the processing efficiency. , , is the weight coefficient, which indicates the relative importance of each factor in the fitness function. By adjusting these weights, the influence of certain factors (such as surface roughness or deburring effect) on the final result can be emphasized. After constructing the deburring effect fitness function, the parameter selection threshold of each area is optimized through the global optimization method. Global optimization refers to searching for the optimal solution within the set parameter range through algorithms (such as particle swarm optimization, genetic algorithm, etc.) to obtain the most suitable water particle flow parameters to ensure the best burr removal effect in each area. After the global optimization process, the optimal water particle flow parameters for each area are finally determined. These parameters can ensure the maximum deburring effect of each equivalent burr area. The water particle flow parameters of each area will provide precise control basis for subsequent processing. Through these steps, accurate water particle flow processing parameters can be customized for each burr area, thereby ensuring the efficiency and accuracy of the deburring process and improving the quality of the workpiece.

[0032] Further, the present application provides the method of obtaining N regional water particle flow parameters, including: A threshold is selected according to the N regional parameters, and the N regional particle swarm spaces are initialized; based on the deburring effect fitness function, global iterative optimization is performed in the N regional particle swarm spaces respectively until a preset termination condition is reached, and the N regional water particle flow parameters with the largest fitness are obtained.

[0033] Optionally, when optimizing the water particle flow parameters in the deburring process, it is necessary to first initialize the particle swarm space of each region. The particle swarm of each region represents the search space of the water particle flow parameters in that region. The position of the particle represents the specific parameters of the water particle flow (such as flow rate and pressure), and the speed of the particle determines the adjustment range of the parameters. Each particle will randomly select a combination of water particle flow parameters during initialization, and these combinations will be adjusted within a given parameter range. Each dimension of the particle swarm is usually consistent with the number of water particle flow parameters. Assuming that each region has two water particle flow parameters, flow rate and pressure, then each particle will contain the initial values ​​of these two parameters. Subsequently, a global iterative optimization is performed based on the fitness function of the deburring effect. The fitness function is used to evaluate the deburring effect of each particle's current position (water particle flow parameter combination). The higher the fitness value, the more suitable the water particle flow parameter combination is for the deburring target. By applying the water particle flow parameter combination to burr removal, the surface roughness, burr removal rate, and processing time of the water particle flow parameter combination after actual removal are obtained. Then, based on the surface roughness, burr removal rate, and processing time, the fitness of the water particle flow parameter combination is calculated through the burr effect fitness function. After that, each particle updates its position according to the calculated fitness value. The update process depends on the particle's speed, the particle's historical best position (personal best), and the global best position (the best of the entire particle group). Through iteration, the particles gradually approach the best water particle flow parameter combination, thereby optimizing the deburring effect. After each iteration, the best solution in the particle group in each region, that is, the optimal water particle flow parameters in the region, is recorded. These optimal solutions will provide the water particle flow parameters with the highest fitness for each region in the final stage. Through continuous iteration and updating until the preset termination condition is reached (such as the maximum number of iterations or the convergence of the fitness value), the water particle flow parameters of the N regions with the largest fitness are finally obtained. These parameter combinations can ensure the efficiency and accuracy of the deburring process and improve the quality of the workpiece.

[0034] A water particle flow processing device is arranged, and the water particle flow processing device includes a water particle flow generator, a part fixing component and a part surface detection component.

[0035] In one embodiment, when performing deburring processing, a complete water particle flow processing device needs to be arranged. This device includes a water particle flow generator, a part fixing component and a part surface detection component, wherein the water particle flow generator is the core part of the entire device, which is responsible for generating a high-speed water flow carrying abrasives. By controlling the pressure, flow rate and particle size of the water flow, the water particle flow generator can provide sufficient energy for the deburring process. The high-speed impact of the water particle flow can effectively remove the burrs on the surface of the part without causing excessive wear to the part; the part fixing component is used to firmly fix the target part in the processing position to ensure that the part does not move or displace during the deburring process. Through precise positioning and fixing, it is ensured that the water particle flow can act evenly and accurately on the surface of the part to improve the processing accuracy. The part surface detection component is used to monitor the surface state of the part in real time, including the burr removal and surface roughness. The detection component can capture the changes on the surface of the part through sensors, cameras or other detection means to obtain key data in the deburring process. These data can be used to feedback and adjust the parameters of the water particle flow to ensure that the effect of the processing process is optimal. By combining these three components, the water jet machining device can perform deburring operations efficiently and accurately, thereby improving the surface quality and machining efficiency of the parts.

[0036] The target part is positioned by using the part fixing component, and the positioned target part is deburred based on the N regional water particle flow parameters by using the water particle flow generator, while the part deburring monitoring data stream is acquired by real-time monitoring through the part surface detection component.

[0037] In one embodiment, during the actual deburring process, the target part is first accurately fixed at the processing position using a part fixing component. The part fixing component ensures that the part will not move or displace during the processing, which is very important for ensuring the accuracy and consistency of deburring. Subsequently, the water particle flow generator generates an appropriate water particle flow according to the previously determined N regional water particle flow parameters. The parameters of the water particle flow (such as flow rate, pressure, etc.) will be adjusted according to different part regions to achieve the best removal effect for different burr features. The water particle flow will impact the surface of the part at a high speed to remove the burrs on the surface while keeping the surface of the part from being excessively worn. At the same time, the part surface detection component monitors the state of the part surface in real time and captures the data flow during the deburring process. These data include the surface roughness of the deburred surface, the degree of burr removal, etc. Through these real-time data feedback, the parameters of the water particle flow (such as flow rate, pressure, etc.) can be dynamically adjusted to ensure that the deburring effect of each region is always kept in the best state. The entire process is adjusted through efficient water particle flow impact and real-time feedback, so that the surface burrs of the target part are accurately removed while maintaining efficient and consistent processing quality.

[0038] The water particle flow parameters of the N regions are adjusted, compensated and optimized based on the part deburring monitoring data stream.

[0039] In one embodiment, during the deburring process, the part deburring monitoring data stream provides real-time feedback data, reflecting the effect of the deburring operation. Based on these real-time monitoring data, the water particle flow parameters of the N regions originally set can be adjusted and compensated to ensure that the deburring effect of each region is maximized. Specifically, the monitoring data stream will provide detailed information about the burr removal of each region. By inputting this information into the prediction model, the effect of part deburring can be predicted. When it is monitored that the deburring effect of a certain area is not ideal, the water particle flow parameters of the area are automatically adjusted according to the predicted effect, such as increasing the flow rate or pressure, or reducing these parameters according to the needs of other areas, so as to achieve a more accurate deburring effect. Through this adjustment, compensation and optimization, the water particle flow processing process can not only respond to changes in real time, but also achieve automated and accurate deburring effects, further improving processing accuracy and part quality.

[0040] Furthermore, the present application provides the method for adjusting, optimizing and compensating the water particle flow parameters of the N regions based on the part deburring monitoring data stream, including: The deburring effect of the target part is predicted based on the part deburring monitoring data stream to obtain the part deburring prediction effect; adjustment optimization analysis is performed based on the difference information between the part deburring prediction effect and the part deburring baseline effect to determine the water particle flow parameter correction amounts of N regions; and compensation closed-loop control is performed on the target part based on the water particle flow parameter correction amounts of N regions.

[0041] Preferably, the deburring effect prediction is to estimate the final effect of the deburring operation based on the real-time monitoring data stream. These data include surface roughness, burr removal degree, etc. By inputting these data into the prediction model, the final removal effect after the deburring operation is completed can be predicted. This prediction model can be constructed based on a multi-layer perceptron. During the construction, the historical removal effect time series data will be input into the multi-layer perceptron. Iterative training is performed through forward propagation, loss calculation, back propagation, parameter optimization and other steps, so that the prediction result gradually approaches the actual result. After obtaining the deburring prediction effect of the part, the deburring benchmark effect is obtained. This deburring benchmark effect is a preset ideal deburring standard, which usually refers to the surface roughness, removal rate and other parameters that the target part should achieve after deburring. By comparing the deburring prediction effect with the benchmark effect, the difference between them is calculated. This difference represents the deviation between the current deburring process and the ideal effect. The larger the difference, the farther the current processing effect is from the ideal state, and vice versa. It means that the effect is better. Subsequently, based on the difference information, the PID controller is used for adjustment optimization analysis to adjust the water particle flow parameters and optimize the deburring effect, thereby obtaining the water particle flow parameter corrections in N regions. Afterwards, the target parts are subjected to compensation closed-loop control based on the water particle flow parameter corrections in N regions. The goal of the compensation closed-loop control is to compensate for the deficiencies in the current processing by dynamically adjusting the water particle flow parameters to ensure that the deburring effect reaches the expected goal. The closed-loop control is a feedback correction process, which continuously adjusts the parameters according to the real-time feedback data until the processing effect reaches the best. After each processing, the current deburring effect will be automatically calculated through monitoring feedback and compared with the target benchmark effect. If a deviation is found, the water particle flow parameters will be automatically adjusted according to the aforementioned corrections (increasing the flow rate, increasing the pressure, etc.), and then the processing process will be re-executed. This process is a cycle, which continuously adjusts and optimizes the water particle flow parameters according to the monitoring data until the target deburring effect is met, thereby achieving real-time optimization and stable control of the deburring effect, ensuring the dual improvement of processing quality and efficiency.

[0042] Furthermore, the present application provides the method of determining the correction amount of water particle flow parameters in N regions, including: Initialize the PID controller, use the difference information between the predicted deburring effect of the part and the baseline deburring effect of the part as the deburring effect optimization parameter, adjust and compensate the deburring effect optimization parameter based on the PID controller, and determine the water particle flow parameter correction amount of the N regions.

[0043] Optionally, during the deburring process, the PID controller is initialized first. The PID controller is a commonly used control algorithm that adjusts the water particle flow parameters through the three terms of proportion, integration and differentiation to optimize the deburring effect. The basic formula of the PID controller includes proportional term, integral term and differential term. The proportional term is corrected according to the current error, the integral term is cumulatively corrected based on the historical error, and the differential term is predicted and adjusted according to the speed of error change. To ensure the control effect, the proportional coefficient needs to be set , integral coefficient and the differential coefficient , these coefficients determine how the controller responds to errors. Once the PID controller is initialized, the next step is to calculate the deburring error. The error is the difference between the predicted deburring effect and the preset baseline effect. The deburring predicted effect is obtained through real-time monitoring data, which represents the deburring effect of the current processed part, while the deburring baseline effect is the preset ideal effect. The size of the error represents the deviation between the current deburring effect and the ideal effect. The PID controller will use this error to adjust the water particle flow parameters. Subsequently, the PID controller adjusts the compensation calculation based on the calculated error. The proportional term P(t) is corrected according to the current error and directly reflects the size of the error; the integral term I(t) is adjusted according to the accumulation of historical errors to eliminate long-standing small errors; the differential term D(t) predicts future changes by analyzing the speed of error change and makes adjustments in advance. After that, the correction u(t) output by the controller is the sum of the proportional, integral and differential terms. This correction represents the water particle flow parameters that need to be adjusted. The water particle flow parameters of each area are adjusted according to the correction calculated by the PID algorithm to ensure that the deburring effect of each area gradually approaches the ideal state. Through the adjustment compensation of the PID controller, the water particle flow parameters of each area will be dynamically optimized according to the deviation of the deburring effect. For the deburring treatment of multiple areas, the corresponding correction amount will be calculated according to the error of each area, and the correction amount of each area will correspond to the adjustment of the water particle flow parameters of the area to ensure that the deburring effect of all areas is optimized. Finally, through the compensation closed-loop control, the water particle flow parameters will be continuously adjusted according to the real-time feedback data to ensure the best deburring effect. After each deburring operation, the correction amount is recalculated through the feedback error, and the water particle flow parameters are adjusted until the predetermined target effect is achieved. In this way, the water particle flow parameters in the entire deburring process are always in a dynamically optimized state, which can accurately control the deburring effect of each area and achieve efficient and accurate deburring processing.

[0044] In the above, refer to Figure 1 The deburring method based on adaptive adjustment of water particle flow parameters according to an embodiment of the present invention is described in detail. Figure 2 A deburring device based on adaptive adjustment of water particle flow parameters according to an embodiment of the present invention is described.

[0045] The deburring device based on adaptive adjustment of water particle flow parameters according to the embodiment of the present invention is used to solve the technical problem that the existing deburring method cannot adaptively adjust the water particle flow parameters according to different materials and burr characteristics, resulting in low deburring accuracy and difficulty in ensuring the surface quality of parts, and achieves the technical effect of intelligently matching and adjusting the water particle flow parameters according to the material and burr characteristics of the parts, improving the deburring accuracy, workpiece quality and production efficiency. The deburring device based on adaptive adjustment of water particle flow parameters includes: a parameter matching retrieval module 11, an adaptive adjustment module 12, a processing device layout module 13, a real-time monitoring module 14, and an adjustment compensation optimization module 15.

[0046] Parameter matching and retrieval module 11: obtain material information and burr detection feature set of target parts through a part detection device, perform parameter matching and retrieval based on the material information, and obtain initial water particle flow parameters; adaptive adjustment module 12: perform equivalent division of the target part according to the burr detection feature set, determine N equivalent part burr areas, adaptively adjust the initial water particle flow parameters based on the N equivalent part burr areas, and obtain N regional water particle flow parameters; processing device layout module 13: layout water particle flow processing device, the water particle flow processing device includes a water particle flow generator, a part fixing component and a part surface detection component; real-time monitoring module 14: use the part fixing component to locate the target part, perform deburring processing on the located target part based on the N regional water particle flow parameters through the water particle flow generator, and simultaneously obtain the part deburring monitoring data stream through the part surface detection component in real time monitoring; adjustment compensation optimization module 15: adjust and compensate the N regional water particle flow parameters based on the part deburring monitoring data stream.

[0047] Furthermore, the parameter matching retrieval module 11 further includes: A parts detection device is obtained, wherein the parts detection device is composed of a spectrum analyzer, a hardness tester, a high-precision industrial camera and a tactile sensor connected in communication; the metal composition and hardness information of the target part are detected and obtained in turn by the spectrum analyzer and the hardness tester, and the material information of the target part is determined according to the metal composition and hardness information; the surface burr image and the burr combination strength set of the target part are acquired by using the high-precision industrial camera and the tactile sensor; the surface burr image is marked for burr recognition to obtain a surface burr area set, and the surface burr area set and the burr combination strength set are combined to form a burr detection feature set for the target part.

[0048] Furthermore, the parameter matching retrieval module 11 further includes: The burr information of each area in the surface burr area set is measured and calculated to obtain a regional burr average height set, a regional burr average length set and a regional burr width distribution set; the regional burr quantity set and the regional burr area set of the burr information of each area are calculated in turn, and the ratio of the regional burr quantity set to the regional burr area set is used as the regional burr distribution density feature set; the morphological features of the burr information of each area are extracted in turn according to the burr morphological type library to obtain a regional burr morphological feature set; the regional burr average height set, the regional burr average length set and the regional burr width distribution set, as well as the regional burr distribution density feature set and the regional burr morphological feature set are feature-associated and mapped with the burr combination strength set to form a burr detection feature set for the target part.

[0049] Furthermore, the parameter matching retrieval module 11 further includes: Mining and acquiring a parts water particle flow processing data set, the parts water particle flow processing data set includes material data of historical parts, water particle flow processing parameters and corresponding processing effect data; presetting a part deburring benchmark effect, based on the processing effect data, screening the material data and water particle flow processing parameters of the historical parts that meet the part deburring benchmark effect, to obtain available part material data and available water particle flow processing parameters; associating and mapping the available part material data and available water particle flow processing parameters, to construct a part material-water particle flow parameter library; based on the material information, traversing, matching and searching in the part material-water particle flow parameter library, to obtain the initial water particle flow parameters.

[0050] Furthermore, the adaptive adjustment module 12 further includes: The burr detection feature set is standardized to obtain a standard burr detection feature set; a K-Means clustering analysis is performed based on the standard burr detection feature set to obtain a burr feature cluster set, wherein each cluster in the burr feature cluster set corresponds to an equivalent burr feature group; adjacent regions of the burr position marks in the burr feature cluster set are merged on the target part to obtain an equivalent burr feature continuous region set; each continuous region in the equivalent burr feature continuous region set is numbered and recorded in turn to determine the N equivalent part burr regions.

[0051] Furthermore, the adaptive adjustment module 12 further includes: According to the N equivalent part burr areas, N equivalent area burr features are determined; based on the N equivalent area burr features, the initial water particle flow parameters are adaptively adjusted and analyzed to obtain N area parameter selection thresholds; a deburring effect fitness function is constructed, and based on the deburring effect fitness function, global optimization is performed within the N area parameter selection thresholds to obtain N area water particle flow parameters.

[0052] Furthermore, the adaptive adjustment module 12 further includes: A threshold is selected according to the N regional parameters, and the N regional particle swarm spaces are initialized; based on the deburring effect fitness function, global iterative optimization is performed in the N regional particle swarm spaces respectively until a preset termination condition is reached, and the N regional water particle flow parameters with the largest fitness are obtained.

[0053] Furthermore, the adjustment compensation optimization module 15 also includes: The deburring effect of the target part is predicted based on the part deburring monitoring data stream to obtain the part deburring prediction effect; adjustment optimization analysis is performed based on the difference information between the part deburring prediction effect and the part deburring baseline effect to determine the water particle flow parameter correction amounts of N regions; and compensation closed-loop control is performed on the target part based on the water particle flow parameter correction amounts of N regions.

[0054] Furthermore, the adjustment compensation optimization module 15 also includes: Initialize the PID controller, use the difference information between the predicted deburring effect of the part and the baseline deburring effect of the part as the deburring effect optimization parameter, adjust and compensate the deburring effect optimization parameter based on the PID controller, and determine the water particle flow parameter correction amount of the N regions.

[0055] The deburring device based on adaptive adjustment of water particle flow parameters provided in the embodiment of the present invention can execute the deburring method based on adaptive adjustment of water particle flow parameters provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0056] Although the present application makes various references to certain modules in the device according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0057] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A deburring method based on adaptive adjustment of water particle flow parameters, characterized in that: The method comprises: The material information and burr detection feature set of the target part are obtained by the part detection device, and the parameter matching retrieval is performed based on the material information to obtain the initial water particle flow parameters; Equivalently dividing the target part according to the burr detection feature set, determining N equivalent part burr regions, and adaptively adjusting the initial water particle flow parameters based on the N equivalent part burr regions to obtain N regional water particle flow parameters; Arrange a water particle flow processing device, wherein the water particle flow processing device includes a water particle flow generator, a part fixing component and a part surface detection component; The target part is positioned by using the part fixing component, and deburring is performed on the positioned target part based on the N regional water particle flow parameters by using the water particle flow generator, and at the same time, a part deburring monitoring data stream is acquired by real-time monitoring by the part surface detection component; The water particle flow parameters of the N regions are adjusted, compensated and optimized based on the part deburring monitoring data stream.

2. The deburring method based on adaptive adjustment of water particle flow parameters according to claim 1, characterized in that: The method of obtaining material information and burr detection feature set of a target part by a part detection device includes: Obtain a parts detection device, wherein the parts detection device is composed of a spectrum analyzer, a hardness tester, a high-precision industrial camera, and a tactile sensor connected in communication; The metal composition and hardness information of the target part are detected and acquired by the spectrum analyzer and the hardness tester in sequence, and the material information of the target part is determined according to the metal composition and hardness information; The high-precision industrial camera and the tactile sensor are used to collect and acquire the surface burr image and the burr combination strength set of the target part; The surface burr image is marked for burr recognition to obtain a surface burr area set, and the surface burr area set and the burr combination strength set are combined to form a burr detection feature set for the target part.

3. The deburring method based on adaptive adjustment of water particle flow parameters according to claim 2, characterized in that: The composition obtains a burr detection feature set of the target part, including: Dimensional measurement and calculation are performed on the burr information of each region in the surface burr region set to obtain a regional burr average height set, a regional burr average length set and a regional burr width distribution set; Calculating and obtaining the regional burr quantity set and the regional burr area set of the burr information of each region in sequence, and taking the ratio of the regional burr quantity set to the regional burr area set as the regional burr distribution density feature set; Extracting morphological features of the burr information of each region in turn according to the burr morphological type library to obtain a regional burr morphological feature set; The regional burr average height set, the regional burr average length set and the regional burr width distribution set, as well as the regional burr distribution density feature set and the regional burr morphology feature set are feature-associated mapped with the burr combination strength set to form a burr detection feature set for the target part.

4. The deburring method based on adaptive adjustment of water particle flow parameters according to claim 1, characterized in that: The initial water particle flow parameters are obtained, including: Mining and acquiring a parts water particle flow processing data set, wherein the parts water particle flow processing data set includes material data of historical parts, water particle flow processing parameters and corresponding processing effect data; A part deburring benchmark effect is preset, and based on the processing effect data, the material data and water particle flow processing parameters of the historical parts are screened to meet the part deburring benchmark effect, so as to obtain available part material data and available water particle flow processing parameters; Associatively mapping the available part material data and the available water particle flow processing parameters to construct a part material-water particle flow parameter library; Based on the material information, a traversal matching search is performed in the part material-water particle flow parameter library to obtain the initial water particle flow parameters.

5. The deburring method based on adaptive adjustment of water particle flow parameters according to claim 1, characterized in that: The determining of N equivalent part burr areas comprises: Standardizing the burr detection feature set to obtain a standard burr detection feature set; Performing K-Means clustering analysis based on the standard burr detection feature set to obtain a burr feature cluster set, wherein each cluster in the burr feature cluster set corresponds to an equivalent burr feature group; Merge adjacent regions of burr position marks in the burr feature cluster set on the target part to obtain a continuous region set of equivalent burr features; The continuous regions in the set of equivalent burr feature continuous regions are assigned numbers and feature records in sequence to determine the N equivalent part burr regions.

6. The deburring method based on adaptive adjustment of water particle flow parameters according to claim 1, characterized in that: The N regional water particle flow parameters are obtained, including: Determine N equivalent area burr features according to the N equivalent part burr areas; Adaptively adjusting and analyzing the initial water particle flow parameters based on the N equivalent regional burr features to obtain N regional parameter selection thresholds; A deburring effect fitness function is constructed, and based on the deburring effect fitness function, global optimization is performed within the N regional parameter selection thresholds to obtain N regional water particle flow parameters.

7. The deburring method based on adaptive adjustment of water particle flow parameters according to claim 6, characterized in that: The N regional water particle flow parameters are obtained, including: Selecting a threshold value according to the N regional parameters and initializing the N regional particle swarm spaces; Based on the deburring effect fitness function, global iterative optimization is performed in the N regional particle swarm spaces respectively until a preset termination condition is reached, so as to obtain the N regional water particle flow parameters with the largest fitness.

8. The deburring method based on adaptive adjustment of water particle flow parameters according to claim 4, characterized in that: The adjusting, optimizing and compensating control of the water particle flow parameters in the N regions based on the part deburring monitoring data stream includes: Predicting the deburring effect of the target part based on the part deburring monitoring data stream to obtain a part deburring prediction effect; Based on the difference information between the predicted effect of deburring the part and the benchmark effect of deburring the part, adjustment optimization analysis is performed to determine the correction amount of water particle flow parameters in N regions; Based on the N regional water particle flow parameter correction amounts, a compensation closed-loop control is performed on the target part.

9. The deburring method based on adaptive adjustment of water particle flow parameters according to claim 8, characterized in that: The step of determining the correction values ​​of water particle flow parameters in N regions includes: Initialize the PID controller, use the difference information between the predicted deburring effect of the part and the baseline deburring effect of the part as the deburring effect optimization parameter, adjust and compensate the deburring effect optimization parameter based on the PID controller, and determine the water particle flow parameter correction amount of the N regions.

10. A deburring device based on adaptive adjustment of water particle flow parameters, characterized in that: The device is used to implement the deburring method based on adaptive adjustment of water particle flow parameters according to any one of claims 1 to 9, comprising: Parameter matching and retrieval module: obtains the material information and burr detection feature set of the target part through the part detection device, performs parameter matching and retrieval based on the material information, and obtains the initial water particle flow parameters; Adaptive adjustment module: performing equivalent division of the target part according to the burr detection feature set, determining N equivalent part burr regions, and adaptively adjusting the initial water particle flow parameters based on the N equivalent part burr regions to obtain N regional water particle flow parameters; Processing device layout module: layout of water particle flow processing device, the water particle flow processing device includes a water particle flow generator, a part fixing component and a part surface detection component; Real-time monitoring module: using the part fixing component to locate the target part, performing deburring processing on the located target part based on the N-region water particle flow parameters through the water particle flow generator, and acquiring part deburring monitoring data stream through the part surface detection component in real time monitoring; Adjustment compensation optimization module: adjusts, compensates and optimizes the water particle flow parameters of the N regions based on the part deburring monitoring data stream.

Images