A stone plate cutting method, a terminal device, a cutting system and a storage medium

Abstract

The application discloses a stone plate cutting method, a terminal device, a cutting system and a storage medium, and the cutting method comprises the following steps: taking a photo of a rough plate, identifying a profile of the rough plate, identifying defects, planning initial material arrangement, identifying corner materials, arranging the corner materials for reuse, merging and optimizing paths, outputting cutting instructions, and receiving and executing the instructions; the cutting method introduces a dynamic corner material identification and reuse mechanism, significantly improves material utilization, and combines an intelligent optimization algorithm to improve material arrangement efficiency and cutting automation level.

Description

Technical Field

[0001] This application belongs to the field of stone slab cutting technology, specifically referring to a stone slab cutting method, terminal equipment, cutting system and storage medium. Background Technology

[0002] In granite production, granite cutting is a crucial step in the production process. Granite is a natural stone, and each piece has a unique pattern. Furthermore, the stone may contain defects such as black spots, color lines, and cracks. Traditional cutting and layout methods rely primarily on manual experience or software with fixed rules, resulting in low efficiency, poor material utilization, and significant waste of scrap. Especially when dealing with mixed cutting and layout of multi-sized finished products, traditional methods struggle to achieve optimal cutting path planning, leading to the direct discarding of large amounts of reusable small-sized material, causing resource waste and increased costs. Summary of the Invention

[0003] To overcome the shortcomings of the prior art, this application provides a method for cutting stone slabs, a terminal device, a cutting system, and a storage medium, which can dynamically identify and utilize scrap materials while achieving efficient cutting, thereby improving material utilization and reducing raw material waste.

[0004] This invention provides a method for cutting stone slabs, the method comprising: Take photos of the rough stone slabs to be cut to obtain images of the rough stone slabs to be cut; Contour feature recognition is performed on the acquired image of the rough stone slab to be cut to obtain the contour features of the rough stone slab to be cut. The YOLO model is used to select defect locations and label categories based on the contour features of the rough stone slab to be cut. The defect features are automatically learned by the CNN algorithm to identify defects in the rough stone slab to be cut. The defects include at least cracks, black spots and color lines. Based on the Bottom-Left algorithm, production constraints are set to optimize the algorithm. Based on the rules of optimal area, height priority and defect avoidance, the main specification finished products in the order library are automatically matched to generate the initial main specification cutting path. Among them, the production constraints include the inherent defects of the stone, height priority and the goal of maximizing material utilization. After completing the main cutting path planning, the system automatically identifies and marks the scrap areas generated after cutting. The scrap area is reused for material layout. The scrap area is used as a new material layout area. The small specifications in the scrap material library of this order are combined to optimize the secondary material layout and produce the corresponding scrap material cutting path. Merge the main specification cutting path with the scrap cutting path and optimize the path sequence; The final optimized cutting path is then output to the CNC cutting equipment. The CNC cutting equipment receives cutting instructions and performs cutting and plate-moving actions according to the cutting instructions.

[0005] Furthermore, according to the stone slab cutting method provided in this application, the construction of the YOLO model real-time target detection model includes: Data preparation includes: data collection, collecting a large number of rough board images containing defects such as cracks, black spots, and color lines to ensure coverage of all defect types that need to be identified; data annotation, using image annotation methods to annotate the collected images, drawing bounding boxes for each type of defect, and labeling them with corresponding category labels; and data augmentation, performing data augmentation processing on the original images, such as rotation, flipping, scaling, and brightness adjustment, to increase the data diversity and robustness of the model training. Model selection and configuration; including: selecting the YOLO model version, choosing the appropriate YOLO model version based on actual needs and hardware conditions; configuring the model, modifying the YOLO model configuration file according to requirements, including the number of classes, anchor boxes, and input size parameters; Training the model includes: dividing the labeled dataset into training, validation, and test sets; starting training by training the YOLO model using the divided datasets, monitoring the training process by observing changes in the loss function, and adjusting parameters such as the learning rate and batch size; and evaluating the model by assessing its performance on the validation set, focusing on metrics such as accuracy, recall, and F1 score. Defect identification and application include: model deployment, converting the trained model into a Java version and integrating it into the stone cutting path planning scenario; real-time detection, using the YOLO model to process the real-time acquired rough slab images, selecting the location of various defects, and labeling their categories.

[0006] Furthermore, according to the stone slab cutting method provided in this application, generating the initial master specification cutting path includes: Input acquisition includes: acquiring the size information of the rough stone slab to be cut, including length and width; extracting the list of finished products with master specifications to be produced from the order database, including the quantity, length and width of each finished product, and order priority attributes; and acquiring the defect information to be cut, including location, range, and type. Preprocessing and sorting; including: preprocessing the master specification finished products in the order database, and adopting a hybrid sorting strategy based on the principles of "optimal area" and "height priority"; An improved nesting algorithm is applied for layout, including: processing each component to be nested sequentially according to the sorted order, taking into account the number of components; generating all feasible placement postures for the current component and considering whether rotation is allowed; generating a series of candidate placement "corner points" on the inscribed contour of the rough slab to be cut using an improved Bottom-Left algorithm; performing conflict detection on each candidate placement posture and candidate "corner point" to check whether the component exceeds the boundary of the rough slab to be cut after placement; scoring all combinations of conflict-free placement postures and positions according to a multi-rule evaluation function, and selecting the combination with the highest score for placement; placing the selected component on the rough slab to be cut and updating the free space and the list of placed components on the rough slab to be cut; repeating this process until all master-specification finished products have been successfully placed or can no longer be placed. Generate the initial cutting path; including: based on the final determined part layout scheme, according to the geometric center of the part, the adjacent relationship and the cutting process requirements, adopt the shortest path priority strategy to plan the tool movement trajectory; output the initial cutting path data containing the part position coordinates, rotation angle, cutting sequence and specific path point coordinates.

[0007] Furthermore, according to the method for cutting stone slabs provided in this application, The scoring items of the multi-rule evaluation function include the total area of ​​the remaining gaps after placement, the utilization rate of the current material row height, and the distance to the edge of the rough stone slab to be cut. Based on the multiple combinations generated by the multi-rule evaluation function, the scoring combination with the highest area matching degree and height matching degree is generated according to the rules of area matching degree, height matching degree, and defect avoidance. Furthermore, according to the stone slab cutting method provided in this application, the contour feature recognition of the obtained image of the rough stone slab to be cut includes: using the findContours function of the OpenCV library to find all closed contours in the edge image and identifying the maximum cuttable inline size, slab thickness, and defect information of the rough stone slab to be cut. Furthermore, according to the stone slab cutting method provided in this application, the step of reusing and arranging scrap areas also includes: Secondary material layout optimization is performed on the small specifications in the scrap material library combined with this order. If the remaining scrap materials do not match the specifications in the scrap material library, and the length or width of the remaining scrap material is greater than the preset size, the remaining area is marked as the scrap area and reserved for the next production order. If the remaining scrap material matches the specifications in the scrap material library, a corresponding scrap material cutting path will be generated. On the other hand, the present invention provides a terminal device based on a method for cutting stone slabs, including a processor, a memory, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the method for cutting stone slabs as described above. On the other hand, this invention provides a system for generating stone slabs and cutting scrap areas based on intelligent algorithms, including a CNC cutting device, a stone transport device, a stone image input module, a defect recognition module, a material layout optimization module, a scrap recognition module, a path planning module, and an output control module; wherein, the stone image input module, the defect recognition module, the material layout optimization module, the scrap recognition module, the path planning module, and the output control module are integrated together to form a stone slab cutting device; the stone transport device conveys the rough stone slab to be cut to the stone slab cutting device for cutting path calculation, the stone slab cutting device outputs the produced cutting path to the CNC cutting device, and the CNC cutting device cuts the rough stone slab.

[0008] On the other hand, the present invention provides a computer-readable storage medium storing a computer program, characterized in that: when the computer program is executed by a processor, it implements the method for cutting stone slabs as described above.

[0009] The beneficial effects of this invention are as follows: The stone slab cutting method provided by this invention, based on a defect identification algorithm, can automatically identify defect locations and automatically avoid them, improving the quality of the stone and reducing the defect rate. Simultaneously, after completing the main specification cutting, it can automatically identify the remaining scrap areas and use them as new material layout areas for secondary optimization, achieving efficient reuse of scrap materials and significantly improving overall material utilization. Furthermore, an improved optimization algorithm is used to dynamically generate the optimal cutting path by combining material characteristics and scrap shape. Compared to traditional fixed-rule layout algorithms, this method has higher flexibility and adaptability, and is particularly suitable for scenarios involving the mixed arrangement of complex shapes and multiple specifications of finished products. Attached Figure Description

[0010] The technical solution and other beneficial effects of this application will become apparent from the following detailed description of specific embodiments in conjunction with the accompanying drawings.

[0011] Figure 1 This is a schematic diagram of the stone slab cutting method provided in this embodiment.

[0012] Figure 2 This is a schematic diagram of the stone slab cutting process provided in this embodiment. Detailed Implementation

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0014] In this embodiment, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0015] The following disclosure provides many different embodiments or examples for implementing different structures of this application. To simplify the disclosure, specific examples of components and arrangements are described below. Of course, these are merely examples and are not intended to limit the scope of this application. Furthermore, reference numerals and / or letters may be repeated in different examples; such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed. In addition, various specific examples of processes and materials are provided in this application, but those skilled in the art will recognize the application of other processes and / or the use of other materials.

[0016] The embodiments of this application will now be further described in conjunction with the accompanying drawings and specific implementation details.

[0017] Example 1: Figure 1 This is a schematic diagram of the stone slab cutting method provided in this embodiment.

[0018] like Figure 1 As shown, the method for cutting stone slabs includes: taking a picture of the rough stone slab to be cut to obtain an image of the rough stone slab to be cut; wherein, when the rough stone slab to be cut is transported to the designated photo-taking position by the stone transport equipment, the camera is automatically triggered to take a picture to obtain an image of the rough stone slab to be cut.

[0019] Contour feature recognition is performed on the acquired image of the rough stone slab to be cut to obtain the contour features of the rough stone slab to be cut. The YOLO model is used to select defect locations and label categories based on the contour features of the rough stone slab to be cut. The defect features are automatically learned by the CNN algorithm to identify defects in the rough stone slab to be cut. The defects include at least cracks, black spots and color lines. Based on the Bottom-Left algorithm, production constraints are set to optimize the algorithm. Based on the rules of optimal area, height priority and defect avoidance, the main specification finished products in the order library are automatically matched to generate the initial main specification cutting path. Among them, the production constraints include the inherent defects of the stone, height priority and the goal of maximizing material utilization. After completing the main cutting path planning, the system automatically identifies and marks the scrap areas generated after cutting. The scrap area is reused for material layout. The scrap area is used as a new material layout area. The small specifications in the scrap material library of this order are combined to optimize the secondary material layout and produce the corresponding scrap material cutting path. Merge the main specification cutting path with the scrap cutting path and optimize the path sequence; The final optimized cutting path is then output to the CNC cutting equipment. The CNC cutting equipment receives cutting instructions and performs cutting and plate-moving actions according to the cutting instructions.

[0020] Specifically, such as Figure 2 As shown, in the contour recognition of the rough stone slabs to be cut, since the length, width, and thickness of each rough stone slab are different, this embodiment uses a contour recognition algorithm and the findContours function from libraries such as OpenCV to find all closed contours in the edge image and identify the maximum cuttable inscribed dimension, slab thickness, and defect information of the rough stone slab. The contour recognition algorithm outputs the cuttable rectangle size.

[0021] In defect identification, the construction of the YOLO model for real-time target detection includes: Data preparation; including: Data collection: Collect a large number of raw board images containing defects such as cracks, black spots, and color lines to ensure that all defect types that need to be identified are covered; Data annotation: The collected images are annotated using image annotation methods. Bounding boxes are drawn for each type of defect, and the corresponding category labels are marked. Data augmentation: Performing data augmentation processing on the original image, such as rotation, flipping, scaling, brightness adjustment, etc., to increase the data diversity and robustness of model training.

[0022] Model selection and configuration; including: Select the YOLO model version: Choose the appropriate YOLO 7 version based on actual needs and hardware conditions; Configure the model: Modify the YOLO7 model configuration file according to your needs, including parameters such as the number of classes (nc), anchor boxes, and input size.

[0023] Training models; including: Dataset partitioning: Divide the labeled dataset into training set, validation set, and test set; Start training: Train the YOLO model using the divided dataset, monitor the training process by observing the changes in the loss function, and adjust parameters such as learning rate and batch size; Model evaluation: Evaluate model performance on the validation set, focusing on metrics including accuracy, recall, and F1 score; if necessary, return to readjust the model or dataset.

[0024] Defect identification and application; including: Deployment Model: Convert the trained model into a Java version and integrate it into the stone cutting path planning scenario; Real-time detection: The YOLO7 model is used to process the real-time acquired rough board images, select the locations of various defects, and label their categories.

[0025] Specifically, in generating the initial master specification cutting path plan, based on the 'bottom-left' (BL) algorithm, an algorithm optimized according to specific production constraints in this embodiment (such as inherent defects in the stone, height priority, and maximizing material utilization) is used to plan the initial master specification cutting path. The core improvement of the initial master specification cutting path optimization algorithm provided in this embodiment lies in the introduction of a multi-rule dynamic evaluation function and a defect area preprocessing and avoidance mechanism, which solves the problems of the traditional BL algorithm easily generating irregular gaps, failing to effectively handle rough slab defects, and being difficult to balance multi-objective optimization. Based on rules such as area optimization, height priority, and defect avoidance, the algorithm automatically matches the master specification finished products in the order library to generate the initial cutting path. Mainly includes: Input acquisition includes: acquiring the size information of the rough stone slab to be cut, including length and width; extracting the list of finished products with master specifications to be produced from the order database, including the quantity, length and width of each finished product, order priority and other attributes; acquiring the defect information to be cut, including location, range and type. Preprocessing and sorting; including: preprocessing the master specification finished products in the order database, and adopting a hybrid sorting strategy based on the principles of "optimal area" and "height priority"; An improved nesting algorithm is applied for layout, including: processing each component to be nested sequentially according to the sorted order, taking into account the number of components; generating all feasible placement postures for the current component and considering whether rotation is allowed; generating a series of candidate placement "corner points" on the inscribed contour of the rough slab to be cut using an improved Bottom-Left algorithm; performing conflict detection on each candidate placement posture and candidate "corner point" to check whether the component exceeds the boundary of the rough slab to be cut after placement; scoring all combinations of conflict-free placement postures and positions according to a multi-rule evaluation function, and selecting the combination with the highest score for placement; placing the selected component on the rough slab to be cut and updating the free space and the list of placed components on the rough slab to be cut; repeating this process until all master-specification finished products have been successfully placed or can no longer be placed. Generate the initial cutting path; including: based on the final determined part layout scheme, according to the geometric center of the part, the adjacent relationship and the cutting process requirements, adopt the shortest path priority strategy to plan the tool movement trajectory; output the initial cutting path data containing the part position coordinates, rotation angle, cutting sequence and specific path point coordinates.

[0026] The scoring items of the multi-rule evaluation function include the total area of ​​the remaining gaps after placement, the utilization efficiency of the current discharge line height, and the distance to the edge of the rough stone slab to be cut. Specifically, in the scrap material reuse and layout process, the scrap area is treated as a new layout area. Secondary layout optimization is performed by combining the smaller specifications in the current order's scrap material library. If the remaining scrap does not match the specifications in the scrap material library, and the length or width of the remaining scrap is greater than 200mm, the remaining area is marked as a scrap area and reserved for the next production order. If the remaining scrap matches the specifications in the scrap material library, a corresponding scrap cutting path is generated.

[0027] Furthermore, the stone slab cutting method provided in this embodiment is not only applicable to the cutting and layout of a single material (such as stone), but can also be extended to scenarios involving the cutting of multiple mixed materials. For example, in furniture manufacturing, when cutting wood panels, metal frames, and glass panels simultaneously, the system can optimize the layout and generate paths according to the cutting characteristics of different materials and the availability of scrap materials.

[0028] Meanwhile, the stone slab cutting method provided in this embodiment can be integrated with an enterprise's MES (Manufacturing Execution System) or ERP (Enterprise Resource Planning) system in an intelligent manufacturing system to achieve fully automated control of the entire process from order management to material layout and cutting execution, thereby improving overall production efficiency and resource utilization.

[0029] In summary, the stone slab cutting method provided in this embodiment differs from traditional nesting systems that only focus on the utilization rate of the main material. After completing the main specification cutting, this method automatically identifies the remaining scrap areas and uses them as new nesting areas for secondary optimization, achieving efficient reuse of scraps and significantly improving overall material utilization. Unlike traditional algorithms that cannot identify defects in the rough slab, this method is based on a defect identification algorithm, automatically identifying defect locations and avoiding them, improving stone quality and reducing the defect rate. Furthermore, this method employs an improved optimization algorithm that combines material characteristics and scrap shapes to dynamically generate the optimal cutting path. Compared to traditional fixed-rule nesting algorithms, it offers greater flexibility and adaptability, making it particularly suitable for scenarios involving complex shapes and mixed layouts of finished products of multiple specifications.

[0030] Example 2: This invention also provides a stone slab cutting system, including a CNC cutting device, a stone transport device, a stone image input module, a defect recognition module, a material layout optimization module, a scrap material recognition module, a path planning module, and an output control module.

[0031] The stone image input module acquires images of the rough stone slabs to be cut using a camera; the defect recognition module identifies defect information in the images of the rough stone slabs; the material layout optimization module generates an initial master specification cutting path based on the defect information and the order requirements; the scrap identification module determines the remaining scrap area based on the generated initial master specification cutting path and determines the cutting path for the scrap area based on the order requirements; the path planning module merges the initial master specification cutting path and the scrap cutting path and optimizes the path sequence; the output control module outputs the optimized cutting path to the CNC cutting equipment.

[0032] The stone image input module, the defect recognition module, the material layout optimization module, the scrap material recognition module, the path planning module, and the output control module are integrated together to form a stone slab cutting device. The stone transport device conveys the rough stone slab to be cut to the stone slab cutting device for cutting path calculation. The stone slab cutting device outputs the produced cutting path to the CNC cutting device, and the CNC cutting device cuts the rough stone slab.

[0033] The stone slab cutting system provided in this embodiment integrates an input module, a defect identification module, a material layout optimization module, a scrap identification module, a path planning module, and an output control module in its system architecture, forming a closed-loop intelligent material layout process. This achieves full automation from raw slab input to cutting execution, improving cutting efficiency and intelligence.

[0034] Example 3: This embodiment also provides a terminal device based on a method for cutting stone slabs, including a processor, a memory, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the method for cutting stone slabs as described in any of the embodiments in Example 1.

[0035] Furthermore, as an executable solution, the terminal device for the stone slab cutting method can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The terminal device for the stone slab cutting method may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that the above-described composition of the terminal device for the stone slab cutting method is merely an example and does not constitute a limitation on the terminal device. It may include more or fewer components, or combine certain components, or different components. For example, the terminal device for the stone slab cutting method may also include input / output devices, network access devices, buses, etc., and this embodiment of the invention does not limit this.

[0036] Furthermore, as an executable solution, the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices. The general-purpose processor can be a microprocessor or any conventional processor. This processor is the control center of the terminal equipment for the method of cutting stone slabs, connecting all parts of the terminal equipment using various interfaces and lines.

[0037] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the terminal device based on the stone slab cutting method by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory and non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0038] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method described in the embodiments of the present invention.

[0039] If the modules / units integrated in the terminal equipment of the stone slab cutting method are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution media, etc.

[0040] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the present invention. Finally, it should be noted that in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0041] The foregoing has provided a detailed description of a stone slab cutting method, terminal equipment, cutting system, and storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the technical solutions and core ideas of this application. Those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for cutting stone slabs, characterized in that, The method includes: Take photos of the rough stone slabs to be cut to obtain images of the rough stone slabs to be cut; Contour feature recognition is performed on the acquired image of the rough stone slab to be cut to obtain the contour features of the rough stone slab to be cut. The YOLO model is used to select defect locations and label categories based on the contour features of the rough stone slab to be cut. The defect features are automatically learned by the CNN algorithm to identify defects in the rough stone slab to be cut. The defects include at least cracks, black spots and color lines. Based on the Bottom-Left algorithm, production constraints are set to optimize the algorithm. Based on the rules of optimal area, height priority and defect avoidance, the main specification finished products in the order library are automatically matched to generate the initial main specification cutting path. Among them, the production constraints include the inherent defects of the stone, height priority and the goal of maximizing material utilization. After completing the main cutting path planning, the system automatically identifies and marks the scrap areas generated after cutting. The scrap area is reused for material layout. The scrap area is used as a new material layout area. The small specifications in the scrap material library of this order are combined to optimize the secondary material layout and produce the corresponding scrap material cutting path. Merge the main specification cutting path with the scrap cutting path and optimize the path sequence; The final optimized cutting path is then output to the CNC cutting equipment. The CNC cutting equipment receives cutting instructions and performs cutting and plate-moving actions according to the cutting instructions; The generation of the initial master specification cutting path includes: Preprocessing and sorting; including: preprocessing the master specification finished products in the order database, and adopting a hybrid sorting strategy based on the principles of "optimal area" and "height priority"; An improved nesting algorithm is applied for layout, including: processing each component to be nested sequentially according to the sorted order, taking into account the number of components; generating all feasible placement postures for the current component and considering whether rotation is allowed; generating a series of candidate placement "corner points" on the inscribed contour of the rough slab to be cut according to the improved Bottom-Left algorithm; performing conflict detection on each candidate placement posture and candidate "corner point" to check whether the component exceeds the boundary of the rough slab to be cut after placement; scoring all combinations of conflict-free placement postures and positions according to a multi-rule evaluation function, and selecting the combination with the highest score for placement; placing the selected component on the rough slab to be cut, and updating the free space and the list of placed components on the rough slab to be cut; repeating this process until all master-specification finished products have been successfully placed or can no longer be placed. The scoring items of the multi-rule evaluation function include the total area of ​​the remaining gaps after placement, the utilization rate of the current material row height, and the distance to the edge of the rough stone slab to be cut. Based on the multiple combinations generated by the multi-rule evaluation function, the scoring combination with the highest area matching degree and height matching degree is generated according to the rules of area matching degree, height matching degree, and defect avoidance.

2. The method for cutting stone slabs according to claim 1, characterized in that, The construction of the YOLO model for real-time object detection includes: Data preparation includes: data collection, collecting a large number of rough board images containing defects such as cracks, black spots, and color lines to ensure coverage of all defect types that need to be identified; data annotation, using image annotation methods to annotate the collected images, drawing bounding boxes for each type of defect, and labeling them with corresponding category labels; and data augmentation, performing data augmentation processing on the original images, such as rotation, flipping, scaling, and brightness adjustment, to increase the data diversity and robustness of the model training. Model selection and configuration; including: selecting the YOLO model version, choosing the appropriate YOLO model version based on actual needs and hardware conditions; configuring the model, modifying the YOLO model configuration file according to requirements, including the number of classes, anchor boxes, and input size parameters; Training the model includes: dividing the labeled dataset into training, validation, and test sets; starting training by training the YOLO model using the divided datasets, monitoring the training process by observing changes in the loss function, and adjusting parameters such as the learning rate and batch size; and evaluating the model by assessing its performance on the validation set, focusing on metrics such as accuracy, recall, and F1 score. Defect identification and application include: model deployment, converting the trained model into a Java version and integrating it into the stone cutting path planning scenario; real-time detection, using the YOLO model to process the real-time acquired rough slab images, selecting the location of various defects, and labeling their categories.

3. The method for cutting stone slabs according to claim 1, characterized in that, Generating the initial master specification cut path also includes: Input acquisition includes: acquiring the size information of the rough stone slab to be cut, including length and width; extracting the list of finished products with master specifications to be produced from the order database, including the quantity, length and width of each finished product, and order priority attributes; and acquiring the defect information to be cut, including location, range, and type. Generate the initial cutting path; including: based on the final determined part layout scheme, according to the geometric center of the part, the adjacent relationship and the cutting process requirements, adopt the shortest path priority strategy to plan the tool movement trajectory; output the initial cutting path data containing the part position coordinates, rotation angle, cutting sequence and specific path point coordinates.

4. The method for cutting stone slabs according to claim 1, characterized in that, Contour feature recognition of the acquired image of the rough stone slab to be cut includes: using the findContours function of the OpenCV library to find all closed contours in the edge image and identify the maximum cuttable inline size, slab thickness, and defect information of the rough stone slab to be cut.

5. The method for cutting stone slabs according to claim 1, characterized in that, The process of reusing and sorting scrap materials also includes: Secondary material layout optimization is performed on the small specifications in the scrap material library combined with this order. If the remaining scrap materials do not match the specifications in the scrap material library, and the length or width of the remaining scrap material is greater than the preset size, the remaining area is marked as the scrap area and reserved for the next production order. If the remaining scrap material matches the specifications in the scrap material library, a corresponding scrap material cutting path will be generated.

6. A terminal device based on a method for cutting stone slabs, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the method for cutting stone slabs as described in any one of claims 1 to 5.

7. A stone slab cutting system, characterized in that, It includes CNC cutting equipment, stone transportation equipment, stone image input module, defect recognition module, material layout optimization module, scrap material recognition module, path planning module, and output control module; the stone image input module acquires images of the rough stone slab to be cut through a camera; The defect recognition module identifies defect information in the image of the rough stone slab to be cut; The material layout optimization module generates an initial master specification cutting path based on defect information and order material requirements; The scrap identification module determines the remaining scrap area based on the generated initial master specification cutting path, and determines the cutting path of the scrap area according to the order requirements; The path planning module merges the initial main specification cutting path and the scrap cutting path and optimizes the path sequence; the output control module outputs the optimized cutting path to the CNC cutting equipment; wherein, the stone image input module, the defect recognition module, the material layout optimization module, the scrap recognition module, the path planning module, and the output control module are integrated together to form a stone slab cutting equipment; the stone transport equipment conveys the rough stone slab to be cut to the stone slab cutting equipment for cutting path calculation, the stone slab cutting equipment outputs the produced cutting path to the CNC cutting equipment, and the CNC cutting equipment cuts the rough stone slab; The stone slab cutting equipment and the CNC cutting equipment work together to achieve the stone slab cutting method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, it implements the method for cutting stone slabs as described in any one of claims 1 to 5.

Images