Progressive multi-section cutting method, system and equipment for scribing machine

Abstract

The invention discloses a progressive multi-section cutting method, system and equipment of a scribing machine, and relates to the related field of cutting management.The method comprises the steps that a cutting task list is recognized, and a cutting structure chart is determined; target material characteristics are obtained, a first decision maker is triggered, a section of cutting decision based on the cutting structure chart is executed through controllable stress distribution, and a first cutting scheme is determined; taking the minimum idle stroke ratio as a constraint, introducing a cutting auxiliary mode, triggering a second decision maker to execute a progressive segmentation decision and a cutting driving decision based on the cutting structure chart, and determining a second cutting scheme; and integrating the first cutting scheme and the second cutting scheme in a time sequence, and responding to a central control system of the dicing saw to perform cutting management under multi-shaft combined drive. The technical problems that in the cutting process of an existing scribing machine, due to uneven stress distribution, materials are damaged, and the cutting efficiency is low are solved, and the technical effects that controllable stress distribution optimization is achieved through progressive multi-section cutting, and the cutting precision and efficiency are improved are achieved.

Description

Technical Field

[0001] This application relates to the field of cutting management, and particularly to a progressive multi-segment cutting method, system, and equipment for a dicing saw. Background Art

[0002] A dicing saw is a key equipment widely used in fields such as semiconductor packaging, optoelectronic component manufacturing, and precision material processing. It is mainly used to cut brittle materials such as wafers, ceramic substrates, and sapphire glass into chips or devices of specified sizes. Traditional dicing processes usually adopt single-segment cutting or simple segmented cutting methods and rely on preset paths and fixed parameters to perform cutting operations. In most cases, standard cutting parameters are set based on the unified thickness, hardness, and structure of the material. However, as the materials to be processed develop towards ultra-thinness, multi-layer compounding, and high stress sensitivity, obvious limitations of traditional methods have gradually emerged in practical applications.

[0003] When existing dicing equipment deals with complex-structured materials (such as interlayer heterogeneous wafers, microvia glass substrates, etc.), problems such as chipping, cracking, delamination, or abnormal tool wear often occur due to inconsistent cutting depths and inaccurate stress control. To reduce processing defects, some solutions introduce path planning based on cutting maps or tension release preprocessing technologies, but still mainly rely on static planning and manual debugging, and cannot achieve dynamic adaptive control under changes in material properties or process parameter perturbations. At the same time, existing cutting systems lack an effective mechanism for coordinated control of multi-segment processes, resulting in problems such as excessive idle travel, discontinuous cutting beats, and low system utilization rate, making it difficult to meet the current industrial requirements that emphasize high precision, high efficiency, and high reliability. Summary of the Invention

[0004] This application provides a progressive multi-segment cutting method, system, and equipment for a dicing saw, solving the technical problems of material damage and low cutting efficiency caused by uneven stress distribution during the cutting process of existing dicing saws, and achieving the technical effect of optimizing the controllable stress distribution through progressive multi-segment cutting and improving the cutting precision and efficiency.

[0005] The present application provides a progressive multi-segment cutting method for a dicing machine. The method includes: identifying a cutting task sheet and determining a cutting structure diagram; obtaining target material characteristics, triggering a first decision-making unit, and performing a one-segment cutting decision based on the cutting structure diagram with a controllable stress distribution to determine a first cutting plan, where the first cutting plan includes a geometric limiting plan based on spatial phase and a tool driving plan based on mechanical driving, and the mechanical driving includes a first triggering decision based on reverse micro-vibration and a second decision based on frequency resonance; introducing a cutting assistance method with a minimum non-cutting ratio as a constraint, triggering a second decision-making unit to perform a progressive segmentation decision and a cutting driving decision based on the cutting structure diagram to determine a second cutting plan; integrating the first cutting plan and the second cutting plan in time sequence, and responding to the central control system of the dicing machine to perform cutting management under multi-axis combined driving.

[0006] The present application also provides a progressive multi-segment cutting system for a dicing machine. The multi-segment cutting system includes: a task identification module: identifying a cutting task sheet and determining a cutting structure diagram; a first cutting decision-making module: obtaining target material characteristics, triggering a first decision-making unit, and performing a one-segment cutting decision based on the cutting structure diagram with a controllable stress distribution to determine a first cutting plan, where the first cutting plan includes a geometric limiting plan based on spatial phase and a tool driving plan based on mechanical driving, and the mechanical driving includes a first triggering decision based on reverse micro-vibration and a second decision based on frequency resonance; a second cutting decision-making module: introducing a cutting assistance method with a minimum non-cutting ratio as a constraint, triggering a second decision-making unit to perform a progressive segmentation decision and a cutting driving decision based on the cutting structure diagram to determine a second cutting plan; a cutting management module: integrating the first cutting plan and the second cutting plan in time sequence, and responding to the central control system of the dicing machine to perform cutting management under multi-axis combined driving.

[0007] The present application also provides an electronic device, including: a memory for storing executable instructions; a processor for implementing a progressive multi-segment cutting method for a dicing machine when executing the executable instructions stored in the memory.

[0008] A progressive multi-segment cutting method, system and device for a dicing machine proposed in this application identify a cutting task sheet and determine a cutting structure diagram. Subsequently, the target material characteristics are obtained, and the first decision-making device is triggered to perform a one-segment cutting decision based on the cutting structure diagram with a controllable stress distribution to determine a first cutting plan, where the first cutting plan includes a geometric limit plan based on spatial phase and a tool driving plan based on mechanical drive. The mechanical drive includes a first trigger decision based on reverse micro-vibration and a second decision based on frequency resonance. Then, with the minimum idle stroke ratio as a constraint, a cutting assistance method is introduced, and the second decision-making device is triggered to perform a progressive segmentation decision and a cutting drive decision based on the cutting structure diagram to determine a second cutting plan. Finally, the first cutting plan and the second cutting plan are integrated in sequence, and in response to the central control system of the dicing machine, cutting management under multi-axis combined drive is carried out, achieving the technical effects of improving cutting accuracy and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments of the present invention will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the operations described above or below do not necessarily need to be executed precisely in sequence. 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 several operations can be removed from these processes.

[0010] Figure 1 It is a schematic flowchart of a progressive multi-segment cutting method for a dicing machine provided by an embodiment of the present application.

[0011] Figure 2 It is a schematic structural diagram of a progressive multi-segment cutting system for a dicing machine provided by an embodiment of the present application.

[0012] Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0013] Description of reference numerals: Task identification module 11, first cutting decision module 12, second cutting decision module 13, cutting management module 14, processor 21, memory 22, input device 23, output device 24. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] The above description is only an overview of the technical solutions of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically illustrates the specific embodiments of this application.

[0015] To make the objectives, technical solutions, and advantages of this application clearer, the following will further describe this application in detail with reference to the accompanying drawings. The described embodiments should not be construed as limitations on this application. All other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.

[0016] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first / second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0017] An embodiment of this application provides a progressive multi-segment cutting method for a dicing machine, as Figure 1 shown. The method includes: Identifying a cutting task sheet and determining a cutting structure diagram.

[0018] Specifically, before the dicing machine starts to execute the processing operation, it first receives a cutting task sheet sent from an upper production scheduling system or an operation terminal. This cutting task sheet usually includes the number, material type, size specification, batch information, target division unit size (such as chip size), arrangement method (such as grid arrangement or customized path), and other process constraints (such as reserved margins, anti-chipping areas, etc.) of the material to be cut. By analyzing this information, the corresponding cutting structure diagram can be called in the cutting database. This cutting structure diagram is a geometric path diagram that describes the complete cutting path from the original material to the target unit division, including the main cutting path, secondary cutting path, tool entry / exit positions, tool change intervals, connection relationships between path nodes, division unit size, cutting path depth parameters, etc., providing a clear and executable spatial planning basis for subsequent cutting decisions, enabling cutting to be carried out while ensuring processing accuracy.

[0019] In a possible implementation manner, after determining the cutting structure diagram, it includes: Identify the cutting structure diagram, and divide it into a first cutting segment and a second cutting segment. Among them, the segmentation method is subjective segmentation. Among them, the first decision-making device executes the driving decision of the first cutting segment, and the second decision-making device takes the first cutting plan as the reference and executes the segmentation and driving decision of the second cutting segment. Among them, the segmentation method is adaptive objective segmentation.

[0020] Specifically, in the cutting preparation stage, first identify the cutting structure diagram, which contains information such as the overall contour of the raw material, the main cutting path, the secondary cutting path, the tool entry and exit positions, the tool change interval, the connection relationship between path nodes, the division unit size, and the cutting path depth parameter. Then, subjectively segment the cutting structure diagram, that is, according to the preset engineering experience and process planning strategy, manually divide the complete cutting path into a first cutting segment and a second cutting segment. Among them, the first decision-making device is responsible for executing the driving decision of the first cutting segment, including operations such as limit correction, tool micro-vibration control, and stress pre-release, to ensure the stability and controllability of the cutting entry stage. When the first cutting segment is completed or enters the last segment, the second decision-making device is triggered synchronously, and the executed cutting data corresponding to the first cutting segment (such as stress feedback, path stability, edge integrity, etc.) is used as a reference benchmark, and adaptive objective segmentation is performed according to the actual execution results of the first cutting segment (such as cutting resistance fluctuation, stress residue distribution), and then the driving decision of the subsequent cutting sub-segments is based on the segmented structure.

[0021] Obtain the target material properties, trigger the first decision-making device, and execute a one-segment cutting decision based on the cutting structure diagram with a controllable stress distribution to determine the first cutting plan. Among them, the first cutting plan includes a geometric limit plan based on spatial phase and a tool driving plan based on mechanical drive. The mechanical drive includes a first trigger decision based on reverse micro-vibration and a second decision based on frequency resonance.

[0022] Specifically, after the generation of the cutting structure diagram is completed, it enters the material identification and the first cutting strategy formulation stage. First, key characteristics of the target material are obtained through methods such as material database matching, surface composition scanning, or manual input. For example, the hardness and brittleness grade, thickness range, interlayer structure, internal stress distribution characteristics, and brittle fracture response frequency of the material. These characteristics will serve as the parameter basis for subsequent cutting decisions. After obtaining the target material characteristics, the first decision-making device is automatically triggered. Using the constructed cutting structure diagram as a path template, an initial cutting segment, that is, a strategy for one segment of cutting, is formulated. In this process, the first decision-making device not only pays attention to the execution of the geometric cutting path itself but also synchronously considers how to regulate the stress field distribution inside the material through physical intervention means, so as to minimize cutting-induced defects, especially applicable to ultra-thin or easily cracked materials. Specifically, the first decision-making device will identify the geometric phase information (such as angular deviation, planar warping, or splicing boundary) of the clamped material through optical positioning means, and establish a dynamic geometric limit path based on this phase information to form a geometric limit scheme, ensuring that the cutting path is accurately aligned with the material structure in terms of spatial distribution, thus avoiding problems such as partial cutting or empty cutting caused by deviations. In addition, the first decision-making device will automatically select either reverse micro-vibration or frequency resonance in one of the two analysis directions for mechanical drive decision-making according to the material thickness. During the decision-making process, when the material thickness is relatively thin, cutting stress is likely to induce invisible cracks. At this time, the reverse micro-vibration decision is executed to determine the first trigger decision. This first trigger decision can make the tool generate a slight reverse micro-vibration at the moment of cutting, similar to a negative stiffness response, enabling the tool to relieve the cutting impact in a stress-relieving manner and avoid the formation of micro-cracks or chipping. When the material thickness is relatively thick, the resonant fracture decision is executed to determine the second decision. This second decision can adjust the tool vibration frequency according to the natural frequency of the material, so that the two form resonance at the physical level, thereby realizing the natural fracture of the material under stress resonance conditions. This method not only reduces the cutting resistance but also realizes auxiliary cracking through stress field reconstruction, significantly improving the processing efficiency and edge integrity. By merging the first trigger decision and the second decision into a set, a tool drive scheme is formed. This tool drive scheme will be merged with the geometric limit scheme determined at the beginning into a new set as the first cutting scheme, used to achieve the first segment of cutting based on the coordinated control of space matching and mechanical intervention, providing a stable and low-stress starting condition for subsequent progressive cutting segments.

[0023] In a possible implementation manner, before triggering the first decision-making device, the construction of the first decision-making device includes: Deploy first-order nodes according to the cutting thickness, where the first-order nodes execute triggering decisions and driving decisions for reverse micro-vibrations; deploy second-order nodes guided by frequency resonance, where the second-order nodes execute controllable stress gradient decisions under resonant fracture; cascade the first-order nodes and the second-order nodes, and determine the mechanical drive branch through supervised learning until convergence; parallelize the mechanical drive branch and the limit drive branch as the first decision maker, where the first decision maker is embedded and deployed in the integrated central control system of the dicing machine.

[0024] Specifically, first, taking the preset cutting thickness of the target material as a reference parameter, the deployment of the first-order node is initiated. The first-order node is used to handle the microscopic stress control problem at the moment when the cutting tool penetrates. It executes the triggering decision and driving decision of reverse micro-vibration. Since this stage focuses on short-time dynamic response and lightweight judgment logic, a lightweight temporal convolutional-recurrent hybrid model (1D-CNN+GRU) etc. can be selected as the first-order node model. This first-order node can simulate the negative stiffness response mechanism based on the knowledge learned subsequently and determine the first-order driving scheme. This first-order driving scheme can introduce low-amplitude and short-period reverse micro-vibration at the moment when the cutting tool starts to enter the material, which is used to relieve the stress concentration caused by initial cutting and prevent the generation of hidden cracks or chipping on the material surface or interface due to stress surge. In addition, according to the natural frequency and stress release behavior characteristics of the material, a second-order node is deployed. This second-order node is oriented towards frequency resonance and focuses on the continuous cutting behavior in the later stage when the cutting tool penetrates deep into the material. Its task is to execute the controllable stress gradient decision under resonant fracture. Therefore, this second-order node can be constructed based on a physics-guided neural network model (PGNN), etc. PGNN embeds the prior physical constraints of material stress evolution in the basic deep neural network structure. By jointly learning the material stress field model and the tool resonance frequency spectrum response, it realizes the precise control of the material stress release path and the low-energy consumption cracking process. Subsequently, the first-order node and the second-order node are cascaded to construct a complete cutting stress control link. Then, by introducing a supervised learning mechanism, the first-order node and the second-order node in this link are trained based on the historical cutting structure diagram, historical cutting thickness information, historical first-order driving scheme, historical material natural frequency, historical tool vibration frequency, and historical second-order driving scheme in the historical cutting data. The training process includes forward propagation, loss calculation, backward propagation, and parameter optimization. This training process will be iterated until the convergence and stability of the overall driving strategy, and finally a mechanical driving branch with generalization ability is formed. After that, this mechanical driving branch is integrated with the position-limiting driving branch based on spatial phase constructed before in a parallel structure to form a complete first decision maker. The construction method of this position-limiting driving branch is similar to that of the mechanical driving branch, except that the position-limiting driving branch only contains one position-limiting driving node. This position-limiting driving node can be constructed based on a space-aware convolutional neural network (SP-CNN), 3D convolutional neural network (3D-CNN), etc. Then, the same supervised learning is carried out using the historical cutting structure diagram, historical material spatial phase information, and historical geometric position-limiting scheme in the historical cutting data to improve the generalization ability. The first decision maker constructed by integration can not only select the corresponding mechanical driving scheme according to the different thicknesses and structural stages of the material, but also realize the coordinated optimization of the path and stress by combining the positioning constraint strategy. Finally, the first decision maker is deployed in the integrated central control system of the dicing machine in the form of an embedded component to achieve automated and real-time cutting control response.

[0025] In a possible implementation, a geometric limit scheme based on spatial phase includes: Connect the optical positioning system to scan the clamped material and determine the spatial phase of the material; trigger the limit drive branch and perform trajectory positioning based on the first cutting segment with the spatial phase of the material to determine the geometric limit scheme.

[0026] Specifically, before the dicing machine is ready to execute the first cutting segment, first connect the optical positioning system. This optical positioning system usually includes a high-resolution industrial camera, a laser profiler or a structured light scanning device, which is used to scan the surface structure of the material clamped on the platform. During the scanning process, two-dimensional or three-dimensional image information of the key feature points on the material surface (such as chip boundaries, calibration points, dicing grooves, splicing seams, etc.) will be obtained, and these feature points will be spatially registered in combination with the clamping position and the reference coordinate system, and then the spatial phase information of the clamped material will be determined. This material spatial phase information is a geometric distribution map representing the material arrangement, boundary shape, and warping degree, which can truly reflect the spatial attitude of the material in the current clamping state. After the spatial phase extraction is completed, the limit drive branch in the first decision-making unit is automatically triggered. This limit drive branch takes the extracted spatial phase of the material as the input, and combines the first cutting segment in the cutting structure diagram to perform trajectory matching and offset correction operations based on spatial geometric relationships, compares the offset, angular error and local warping between the theoretical cutting path and the actual boundary of the material, and dynamically generates limit adjustment parameters, such as the correction of the starting position of the tool approaching, the fine-tuning trajectory of the cutting path (compensation path), the spatial boundary limit conditions (to prevent mis-cutting and chipping), the multi-axis motion coordination parameters (such as the synchronous boundary adjustment of the XY platform), etc., to form a geometric limit scheme. This geometric limit scheme serves as the spatial input condition before the execution of the first cutting segment, ensuring that the tool motion path is accurately aligned with the actual material boundary, avoiding problems such as empty cutting, offset cutting, and tape breakage, and providing a stable and controllable geometric reference framework for subsequent mechanical drive strategies (such as reverse micro-vibration or resonant fracture), ensuring that the cutting path completely matches the actual state of the material.

[0027] In a possible implementation, a tool drive scheme based on mechanical drive includes: Identify the cutting structure diagram and determine the cutting thickness information; trigger the mechanical drive branch, and the first-order node performs a determination based on the cutting thickness information to determine the determination result; if the determination result is greater than or equal to the preset thickness, the second-order node performs a resonant fracture decision to determine the tool drive scheme.

[0028] Specifically, after the initialization of the cutting task is completed, the cutting structure diagram obtained at the beginning is recognized, and the target cutting thickness information corresponding to the current cutting segment is extracted, that is, the vertical cutting path depth from the material surface to the target interface. This parameter is used to judge the stress level borne by the material during cutting and the required driving mode of the tool. Subsequently, the mechanical drive branch in the first decision maker is triggered, and the first-order node inside this branch is called to judge the extracted cutting thickness information, that is, the cutting thickness information is compared with the preset cutting thickness in the first-order node to generate a judgment result, which is used to indicate whether the current cutting enters the high-stress stage. When the judgment result shows that the cutting thickness information is greater than or equal to the set preset cutting thickness threshold (for example, the resonance critical thickness of a certain type of material is 150 μm), the second-order node will execute the resonance fracture decision. During this process, the natural frequency of the material will be matched based on the previously extracted material characteristic data, and this natural frequency of the material will be combined with the tool vibration frequency and the corresponding cutting segment in the cutting structure diagram and analyzed by the second-order node to generate a second-order drive scheme as the second decision and add it to the corresponding position in the tool drive scheme. At this time, the first trigger decision in the tool drive scheme is temporarily empty. This second-order drive scheme includes parameters such as target resonance frequency matching parameters, dynamic amplitude control parameters, and resonance maintenance time window parameters, which can jointly guide the tool to complete low-stress cutting in a state of frequency resonance with the material, causing the material to crack along its natural stress release path, thereby improving the cutting efficiency, reducing micro-cracks, chipping, and tool load, and improving the yield rate.

[0029] In a possible implementation manner, if the judgment result is less than the preset thickness, the reverse micro-vibration decision is executed to determine the first-order drive scheme.

[0030] Specifically, when the cutting structure diagram is recognized and the first-order node completes the judgment of the cutting thickness, if the judgment result shows that the cutting thickness information is less than the preset cutting thickness, it means that the current cutting process belongs to the cutting-in stage of high-brittle and high-sensitive materials. At this time, directly using conventional or high-frequency vibration cutting is likely to cause stress concentration in the material structure, thereby inducing adverse consequences such as micro-cracks, chipping, and hidden defects, affecting the final yield rate. Therefore, the first-order node will continue to execute the reverse micro-vibration decision. During this process, the first-order node will analyze the corresponding cutting segment and cutting thickness information in the cutting structure diagram based on the learned knowledge to determine the specific first-order drive scheme, including the micro-vibration trigger timing, reverse micro-vibration amplitude, reverse micro-vibration frequency, etc. Through these parameters, the dicing machine can control the tool to generate a micro-vibration signal with a low frequency, low amplitude and a direction opposite to the feed direction along the vertical incident direction at the moment when the tool cuts into the material, preventing cutting defects caused by excessive cutting-in stress and establishing a good physical condition basis for subsequent segmented cutting.

[0031] In a possible implementation, the second-order node executes a resonant fracture decision to determine the tool drive scheme, including: For the target material properties, determine the natural frequency of the material based on the material stress distribution; aiming at the resonant fracture of the cutting structure diagram and guided by the resonance between the natural frequency of the material and the vibration frequency of the tool, perform a tool mechanical drive decision to determine the second-order drive scheme; wherein, the tool drive scheme includes the first-order drive scheme and the second-order drive scheme.

[0032] Specifically, after the cutting thickness determination is completed, if it is determined that the cutting thickness information is greater than or equal to the preset cutting thickness, it indicates that the cutting depth area that can accommodate higher vibration energy has been entered. At this time, resonance can be used to assist fracture to improve cutting efficiency and reduce tool load. For this purpose, first, for the target material properties, such as the elastic modulus, density, internal microstructure arrangement (such as single crystal, polycrystalline or composite layered structure), residual stress distribution, etc. of the material, combined with the material database or real-time measurement data, determine the natural frequency of the material. The natural frequency refers to the characteristic frequency at which the material naturally generates a resonance response under an excited state, which is closely related to its geometric dimensions, boundary conditions and stress distribution. Subsequently, the resonant fracture of the cutting structure diagram is used as the cutting target. This resonant fracture is a method of inducing cracking using internal stress under low external force, which is applicable to structures with strong self-cracking ability, high brittleness and concentrated energy response of the material. To achieve this goal, the natural frequency of the material, the vibration frequency of the tool, and the corresponding cutting segment of the cutting structure diagram are input into the second-order node to execute the mechanical drive decision. The second-order node, guided by the resonance between the natural frequency of the material and the vibration frequency of the tool through the learned knowledge, calculates target resonance frequency matching parameters, dynamic amplitude control parameters, resonant maintenance time window parameters, etc., to make them match the natural frequency of the material or form a multiple-frequency harmonic relationship, ensuring low-energy cracking processing within the resonance range. Finally, the generated second-order drive scheme is stored as the second decision in the corresponding position of the tool drive scheme, and together with the first trigger decision composed of the first-order drive scheme, it forms a complete tool drive scheme, thus realizing a high degree of integration of the mechanical control logic and the physical response law and ensuring cutting accuracy and efficiency.

[0033] With the minimum idle stroke ratio as a constraint, introduce a cutting assistance method to trigger the second decision maker to execute the progressive segmentation decision and cutting drive decision based on the cutting structure diagram to determine the second cutting scheme.

[0034] Specifically, after completing the first cutting segment and being driven by the initial stress intervention generated by the first decision maker, the cutting control enters the second stage. The goal of this stage is to further optimize the cutting path efficiency and tool motion state while ensuring the cutting quality of the material. Therefore, the minimum non-cutting ratio is used as the core constraint condition. The minimum non-cutting ratio refers to the ratio of the actual cutting path length of the tool in the unit path to its total running length (including the tool return path and non-cutting movement segments). The more non-cutting paths there are, the lower the utilization rate of equipment resources, the slower the processing rhythm, and the higher the risk of tool fatigue. Therefore, it is necessary to compress the non-effective cutting paths as much as possible in the second cutting segment. To meet this constraint, cutting assistance methods are introduced according to the material characteristics. For example, in high-temperature materials or sections with severe stress release, a water cooling assistance device is started, and the temperature rise in the contact area between the tool and the material is reduced through a precise water spraying system. At the same time, the edge structure of the material is stabilized, and the concentration of thermal stress is slowed down. In addition, according to the material characteristics, methods such as negative pressure adsorption, auxiliary air injection, and micro-lubrication can also be selected to enhance the stability of the tool motion environment and provide guarantee for low non-cutting ratio cutting. Subsequently, the second decision maker is triggered. The second decision maker will start a progressive segmentation decision mechanism according to the identified second cutting segment, the feedback data after the execution of the first cutting plan (such as cutting resistance data and material stress residue), and the parameter control range of the selected cutting assistance method (such as temperature, duration, spraying angle), that is, analyze the second cutting segment, the feedback data after the execution of the first cutting plan, and the parameter control range of the selected cutting assistance method through the segmentation decision branch in the second decision maker, and generate a second cutting plan with the goal of minimizing the number of segments. This segmentation decision branch can be obtained by training a deep neural network using supervised learning. This second cutting plan includes tool path speed, local excitation frequency, water cooling start-stop control, etc., which can make the tool return between each cutting path the shortest or achieve continuous cutting between adjacent paths as much as possible, thereby reducing the overall non-cutting ratio.

[0035] Integrate the first cutting plan and the second cutting plan in time sequence, and respond to the cutting management under multi-axis joint drive by the central control system of the dicing machine.

[0036] Specifically, after obtaining the first cutting plan and the second cutting plan, it enters the integration and execution stage of the cutting control process. At this time, timing integration is performed on the generated cutting plans, that is, the first cutting plan (aiming at stress control and precise tool entry) and the second cutting plan (aiming at path optimization and idle stroke compression) are sorted on a unified time axis and connected in process segments to construct a set of continuous and conflict-free full-segment cutting control processes. After completion of the integration, the integrated complete plan is sent to the central control system of the dicing machine. The central control system will perform high-precision synchronous control between each axis under a multi-axis co-drive architecture (such as XY platform, Z-axis up-and-down tool mechanism, θ-axis rotation compensation mechanism), so as to realize the closed-loop execution of a complete, multi-segment and intelligent cutting process, improve cutting accuracy and efficiency, and ensure the continuity, high efficiency and low damage of the whole material processing process.

[0037] In a possible implementation manner, in response to the central control system of the dicing machine performing cutting management under multi-axis co-drive, it includes: Performing timing integration on the first cutting plan and the second cutting plan to determine a progressive cutting plan; for the progressive cutting plan, setting and decomposing the plan for the drive axes of the dicing machine and sending it down, and performing orderly cutting management of multi-axis cascading.

[0038] Specifically, after generating the first cutting plan and the second cutting plan, the execution order, physical path distribution, and tool motion logic of these two plans are integrated in time sequence, and they are uniformly mapped into a continuous and conflict-free machining process to generate a complete progressive cutting plan. This progressive plan not only retains the advantages of high stress control and high tool entry accuracy in the first stage but also incorporates the control logic of segmented path optimization and auxiliary mechanism matching in the second stage, constituting a multi-stage machining process with hierarchical progression and flexible response. Subsequently, according to this progressive cutting plan, precise configuration and control parameter issuance are started for each drive axis of the dicing saw. The dicing saw is usually configured with a multi-axis linkage system, including X-Y axes, Z axis, θ axis or U axis, platform movement axis (such as T axis), etc. Among them, the X-Y axes are responsible for material positioning and tool path movement in the two-dimensional plane; the Z axis controls the up and down movement of the tool to achieve cutting in and detachment; the θ axis or U axis is used for micro-rotation adjustment of the material or tool to achieve angle compensation; the platform movement axis (such as T axis): is used for the production line transfer of the workpiece from the first processing unit to the second processing unit. After that, according to the stage to which the cutting segment belongs, each segment path is mapped to specific axis group control tasks. For example, the first cutting segment is executed by group A drive axes (such as X1-Y1-Z1) to complete the micro-vibration and initial limit cutting operations in the first stage; after cutting is completed, the processed workpiece is transferred to the second cutting station through the platform movement axis, and the second cutting segment is taken over by group B drive axes (such as X2-Y2-Z2), which automatically adjust the initial positions of the drive axes (such as zeroing, aligning the corner points, repositioning), load the drive parameters and auxiliary control logic of the second segment, and continue to execute the subsequent cutting tasks. This division of labor realizes the orderly cutting management of multi-axis cascading, thereby ensuring that each stage of the drive axis group has independent control authority, accurate path execution boundaries, and clear task logic, avoiding inter-axis conflicts or machining beat delays, and improving the collaborative machining ability.

[0039] In the above text, reference is made to Figure 1 A progressive multi-segment cutting method of a dicing saw according to an embodiment of the present invention is described in detail. Next, reference will be made to Figure 2 Describe a progressive multi-segment cutting system of a dicing saw according to an embodiment of the present invention.

[0040] A progressive multi-segment cutting system of a dicing saw according to an embodiment of the present invention is used to solve the technical problems of material damage and low cutting efficiency caused by uneven stress distribution in the existing dicing saw during the cutting process, and achieve the technical effect of optimizing the controllable stress distribution through progressive multi-segment cutting, improving the cutting accuracy and efficiency. A progressive multi-segment cutting system of a dicing saw includes: a task recognition module 11, a first cutting decision module 12, a second cutting decision module 13, and a cutting management module 14.

[0041] Task recognition module 11: Recognize the cutting task sheet and determine the cutting structure diagram; First cutting decision module 12: Obtain the target material characteristics, trigger the first decision maker, and execute a one-segment cutting decision based on the cutting structure diagram with controllable stress distribution to determine the first cutting plan, where the first cutting plan includes a geometric limit plan based on spatial phase and a tool drive plan based on mechanical drive, and the mechanical drive includes a first trigger decision based on reverse micro-vibration and a second decision based on frequency resonance; Second cutting decision module 13: With the minimum idle stroke ratio as a constraint, introduce a cutting assistance method, trigger the second decision maker to execute a progressive segmentation decision and a cutting drive decision based on the cutting structure diagram, and determine the second cutting plan; Cutting management module 14: Integrate the first cutting plan and the second cutting plan in time sequence, and respond to the central control system of the dicing machine to perform cutting management under multi-axis joint drive.

[0042] Next, the specific configuration of the task recognition module 11 will be described in detail. As described above, after determining the cutting structure diagram, the task recognition module 11 may further include: Recognize the cutting structure diagram, divide the first cutting segment and the second cutting segment, where the segmentation method is subjective segmentation; where the first decision maker executes the drive decision for the first cutting segment, and the second decision maker takes the first cutting plan as a reference and executes the segmentation and drive decision for the second cutting segment, where the segmentation method is adaptive objective segmentation.

[0043] Next, the specific configuration of the first cutting decision module 12 will be described in detail. As described above, before triggering the first decision maker, in the construction of the first decision maker, the first cutting decision module 12 may further include: Deploy first-order nodes according to the cutting thickness, where the first-order nodes execute the trigger decision and the drive decision for reverse micro-vibration; Deploy second-order nodes guided by frequency resonance, where the second-order nodes execute the controllable stress gradient decision under resonant fracture; Cascade the first-order nodes and the second-order nodes, and determine the mechanical drive branch through supervised learning until convergence; Parallelize the mechanical drive branch and the limit drive branch as the first decision maker, where the first decision maker is embedded in the integrated central control system of the dicing machine.

[0044] Among them, for the geometric limit plan based on spatial phase, the first cutting decision module 12 may further include: Connect the optical positioning system, scan the clamped material, and determine the material spatial phase; Trigger the limit drive branch, and perform trajectory positioning based on the first cutting segment with the material spatial phase to determine the geometric limit plan.

[0045] Among them, based on the mechanical drive tool drive solution, the first cutting decision module 12 may further include: identifying the cutting structure diagram to determine the cutting thickness information; triggering the mechanical drive branch, and the first-order node performs a determination based on the cutting thickness information to determine the determination result; if the determination result is greater than or equal to the preset thickness, the second-order node performs a resonant fracture decision to determine the tool drive solution.

[0046] Among them, the first cutting decision module 12 may further include: if the determination result is less than the preset thickness, perform a reverse micro-vibration decision to determine the first-order drive solution.

[0047] Among them, when the second-order node performs a resonant fracture decision to determine the tool drive solution, the first cutting decision module 12 may further include: determining the material natural frequency based on the material stress distribution for the target material characteristics; aiming at the resonant fracture based on the cutting structure diagram and guiding by the resonance of the material natural frequency and the tool vibration frequency, performing a tool mechanical drive decision to determine the second-order drive solution; where the tool drive solution includes the first-order drive solution and the second-order drive solution.

[0048] Next, the specific configuration of the cutting management module 14 will be described in detail. As described above, in response to the cutting management under multi-axis co-drive by the central control system of the dicing machine, the cutting management module 14 may further include: integrating the first cutting plan and the second cutting plan in time sequence to determine the progressive cutting plan; for the progressive cutting plan, setting and decomposing the plan for the drive shafts of the dicing machine and issuing it, and performing orderly cutting management of multi-axis cascading.

[0049] The progressive multi-segment cutting system of a dicing machine provided by the embodiments of the present invention can execute the progressive multi-segment cutting method of a dicing machine provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0050] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The included various units and modules are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0051] Based on the foregoing embodiments, the embodiments of the present application also provide an electronic device. Figure 3 It is a schematic structural diagram of the electronic device provided by the embodiments of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing the embodiments of the present invention. Figure 3The electronic device shown is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present invention. The electronic device is presented in the form of a general-purpose computing device, and its components may include, but are not limited to, a processor 21, a memory 22, an input device 23, and an output device 24. Among them, the processor 21 may be one or more; the memory 22 may include a computer-readable medium and at least one program product, and this program product has a set (at least one) of program modules, and these program modules are configured to execute the functions of the embodiments of the present application.

[0052] The memory 22 shown in the embodiments of the present invention may adopt any combination of one or more computer-readable media; the computer-readable storage medium may be, but is not limited to, infrared rays, semiconductor systems, devices or components, or any combination of the above, for storing software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to a progressive multi-segment cutting method of a dicing machine in the embodiments of the present invention. The processor 21 executes various functional applications and data processing of the computer device by running the software programs, instructions, and modules stored in the memory 22, that is, implements the above-mentioned progressive multi-segment cutting method of a dicing machine.

[0053] The above specific implementation manners do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand 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 principle of the present application shall be included within the protection scope of the present application. In some cases, the actions or steps recorded in the present application may be executed in a different order from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In certain embodiments, multi-tasking and parallel processing are also possible or may be advantageous.

Claims

1. A progressive multi-segment cutting method for a dicing machine, characterized in that, The method includes: Identifying a cutting task sheet and determining a cutting structure diagram; Obtaining target material characteristics, triggering a first decision maker to perform a one-segment cutting decision based on the cutting structure diagram with a controllable stress distribution, and determining a first cutting plan, where the first cutting plan includes a geometric limiting plan based on spatial phase and a tool driving plan based on mechanical drive, and the mechanical drive includes a first triggering decision based on reverse micro-vibration and a second decision based on frequency resonance; Taking the minimum idle stroke ratio as a constraint, introducing a cutting assistance method, triggering a second decision maker to perform a progressive segmentation decision and a cutting drive decision based on the cutting structure diagram, and determining a second cutting plan; Integrating the first cutting plan and the second cutting plan in time sequence, and responding to the central control system of the dicing machine to perform cutting management under multi-axis combined drive.

2. The progressive multi-segment cutting method of a dicing machine according to claim 1, characterized in that Before triggering the first decision maker, the construction of the first decision maker includes: Deploying first-order nodes according to the cutting thickness, where the first-order nodes perform triggering decisions and driving decisions for reverse micro-vibration; Deploying second-order nodes with frequency resonance as the guide, where the second-order nodes perform controllable stress gradient decisions under resonant fracture; Cascading the first-order nodes and the second-order nodes, and determining the mechanical drive branch through supervised learning until convergence; Parallelizing the mechanical drive branch and the limit drive branch as the first decision maker, where the first decision maker is embedded in the integrated central control system of the dicing machine.

3. The progressive multi-stage cutting method of a dicing machine according to claim 2, characterized in that The geometric limiting plan based on spatial phase includes: Connecting an optical positioning system to scan the clamped material and determine the material spatial phase; Triggering the limit drive branch, and performing trajectory positioning based on the first cutting segment with the material spatial phase to determine the geometric limiting plan.

4. The progressive multi-stage cutting method of a dicing machine according to claim 3, characterized in that, The tool driving plan based on mechanical drive includes: Identifying the cutting structure diagram and determining the cutting thickness information; Triggering the mechanical drive branch, and the first-order nodes perform a determination based on the cutting thickness information to determine a determination result; If the determination result is greater than or equal to a preset thickness, the second-order nodes perform a resonant fracture decision to determine the tool driving plan.

5. The progressive multi-segment cutting method of a dicing machine according to claim 4, characterized in that, If the determination result is less than the preset thickness, a reverse micro-vibration decision is performed to determine a first-order drive plan.

6. The progressive multi-stage cutting method of a dicing machine according to claim 5, characterized in that, The second-order nodes perform a resonant fracture decision to determine the tool driving plan, including: Determining the material natural frequency based on the material stress distribution for the target material characteristics; Taking resonant fracture based on the cutting structure diagram as the target and resonance between the material natural frequency and the tool vibration frequency as the guide, performing a tool mechanical drive decision to determine a second-order drive plan; Wherein, the tool driving plan includes the first-order drive plan and the second-order drive plan.

7. The progressive multi-stage cutting method of a dicing machine according to claim 1, characterized in that, After determining the cutting structure diagram, it includes: Identifying the cutting structure diagram, dividing it into a first cutting segment and a second cutting segment, where the segmentation method is subjective segmentation; Wherein, the first decision maker performs a driving decision for the first cutting segment, and the second decision maker takes the first cutting plan as a reference and performs segmentation and driving decisions for the second cutting segment, where the segmentation method is adaptive objective segmentation.

8. The progressive multi-segment cutting method of a dicing machine according to claim 1, characterized in that, In response to the central control system of the dicing machine performing cutting management under multi-axis combined drive, including: Integrating the first cutting plan and the second cutting plan in terms of time sequence to determine a progressive cutting plan; For the progressive cutting plan, set the drive shafts of the dicing machine and decompose and distribute the plan, and execute orderly cutting management of multi-axis cascading.

9. A progressive multi-segment cutting system for a dicing machine, characterized in that, The multi-segment cutting system is used to implement the progressive multi-segment cutting method of a dicing machine according to any one of claims 1-8. The multi-segment cutting system includes: A task recognition module: recognizing a cutting task sheet and determining a cutting structure diagram; A first cutting decision module: obtaining target material characteristics, triggering a first decision maker, and performing a one-segment cutting decision based on the cutting structure diagram with controllable stress distribution to determine a first cutting plan. Among them, the first cutting plan includes a geometric limit plan based on spatial phase and a tool drive plan based on mechanical drive. The mechanical drive includes a first trigger decision based on reverse micro-vibration and a second decision based on frequency resonance; A second cutting decision module: taking the minimum non-cutting ratio as a constraint, introducing a cutting assistance method, triggering a second decision maker to execute a progressive segmentation decision and a cutting drive decision based on the cutting structure diagram, and determining a second cutting plan; A cutting management module: integrating the first cutting plan and the second cutting plan in terms of time sequence, and performing cutting management under multi-axis combined drive in response to the central control system of the dicing machine.

10. An electronic device, characterized in that, The electronic device includes: A memory for storing executable instructions; A processor for implementing the progressive multi-segment cutting method of a dicing machine according to any one of claims 1 to 8 when executing the executable instructions stored in the memory.

Images