Optimized utilization method and system for household board excess materials

Abstract

The invention relates to the technical field of reprocessing, in particular to an optimized utilization method and system for household board excess materials, and the system comprises a data collection module which obtains the size, shape and quantity data of the board excess materials based on a sensor and an image processing technology, carries out the data noise removal and abnormal value elimination, and integrates the cleaned data to obtain an excess material data set; and the initial path generation module is used for calling geometric shape and size parameter set operation based on the excess material data set. According to the method, the size, shape and quantity data of the excess materials are automatically obtained by integrating the sensor and the image processing technology, the accuracy and availability of the data are remarkably improved through an effective data cleaning and optimizing scheme, and a solid foundation is laid for reutilization of the excess materials. And a preliminary utilization path is automatically generated by utilizing a set operation and path planning algorithm, so that the dependence on manual operation is reduced, and the processing efficiency and the resource reutilization quality are improved.

Description

Technical Field

[0001] The present invention relates to the field of reprocessing technology, and in particular to a method and system for optimizing utilization of leftover furniture board materials. Background Art

[0002] The field of reprocessing technology mainly involves technologies for recycling, processing and reusing waste materials, residual materials, and discarded products generated in industrial production processes. These technologies aim to reduce resource waste, lower production costs, improve resource utilization efficiency, and reduce negative impacts on the environment. Reprocessing technology includes processes such as material sorting, crushing, cleaning, melting, and reshaping to enable waste materials to become useful production resources again. Such technologies are widely used in many industries such as metals, plastics, paper, glass, and building materials, and achieve resource recycling and sustainable development through reprocessing.

[0003] The method and system for optimizing the utilization of residual materials of home furnishing boards are intended to optimize the utilization of residual materials generated during the production process of home furnishing boards. The method and system classify, cut, splice, and combine the residual materials to make them usable home furnishing materials again. This can not only effectively reduce material waste in the production process and reduce production costs, but also maximize the utilization of resources, providing an efficient and environmentally friendly solution for the home furnishing manufacturing industry.

[0004] However, existing technologies are inefficient when dealing with large-scale or complex waste materials, and resources are not fully utilized. Due to the lack of automation and intelligent tools, traditional methods rely too much on manual labor in data collection and utilization path planning, resulting in waste of resources and rising costs. The shortcomings of existing technologies in real-time data processing and dynamic adjustment capabilities make it difficult to effectively respond to immediate changes in waste materials on the production line, such as adjustments in shape and size, which reduces material utilization and production flexibility. In addition, existing technologies perform poorly in multi-tasking environments, especially in large-scale production scenarios, lack effective parallel processing mechanisms, and cannot maintain continuous and efficient production operations. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a method and system for optimizing the utilization of leftover furniture board materials.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a system for optimizing the utilization of residual furniture board materials, comprising: The data collection module, based on sensors and image processing technology, obtains the size, shape and quantity data of the plate waste, removes data noise and outliers, integrates the cleaned data, and obtains the waste data set; The initial path generation module, based on the residual material data set, calls the geometric shape and size parameter set operation, combines the geometric shape and size characteristics of the residual material, performs path planning operation, generates a path that meets the cutting and utilization requirements, and obtains the initial utilization path; The path optimization module sets the number of ants, pheromone volatility coefficient and pheromone reinforcement factor based on the initial utilization path, performs path selection and analysis, updates the pheromone concentration on the path by comparing the pheromone concentration and the heuristic factor, repeats the path selection and analysis, updates the pheromone concentration, and obtains the optimal utilization path; The dynamic adjustment module obtains the current sheet material surplus data, combines it with the optimal utilization path, calls the current data and path parameters, combines the real-time data of the surplus material and the path characteristics, dynamically adjusts the path, and generates a dynamically optimized path; The multi-batch processing module processes the sheet material surplus data in batches based on the dynamic optimization path, calls parallel computing technology, combines multiple utilization paths, performs multi-task parallel processing, optimizes multiple utilization paths, and obtains a multi-task optimization path.

[0007] As a further solution of the present invention, the residual material data set includes size data, shape data and quantity data, the initial utilization path includes geometric shape parameters, size parameters and path planning results, the optimal utilization path includes ant quantity settings, pheromone volatility coefficients and pheromone reinforcement factors, the dynamic optimization path includes current data, path parameters and path characteristics, and the multi-task optimization path includes batch processing, parallel computing and multi-task optimization.

[0008] As a further solution of the present invention, the data collection module includes: The sensor data submodule obtains the size, shape and quantity data of the sheet material residue based on the sensor, and performs preliminary data sorting to generate the original residue data; The image processing submodule removes data noise, removes outliers, and completes data standardization based on the original residual material data to generate cleaned data; The data integration submodule integrates and classifies data based on the cleaned data, establishes a structured data set, and generates a residual data set.

[0009] As a further solution of the present invention, the initial path generation module includes: The geometric operation submodule extracts geometric shape features and size parameters based on the residual material data set, performs parameter set operations, and generates geometric feature parameters; The path planning submodule performs path planning operations based on geometric feature parameters, analyzes path feasibility, and generates path planning results; The path generation submodule generates a path that meets the cutting and utilization requirements based on the path planning results and outputs the initial utilization path.

[0010] As a further solution of the present invention, the path optimization module includes: The parameter setting submodule sets the number of ants, pheromone volatility coefficient and pheromone reinforcement factor based on the initial utilization path, and generates parameter setting values; The path analysis submodule performs path selection and analysis based on parameter setting values, evaluates path performance, and generates path analysis results; The pheromone update submodule updates the pheromone concentration on the path based on the path analysis results, repeatedly selects and analyzes the path, and obtains the optimal utilization path.

[0011] As a further solution of the present invention, the dynamic adjustment module includes: The real-time monitoring submodule obtains the current sheet material surplus data, performs real-time data updates, and generates the current surplus material data; The data calling submodule calls the current data and path parameters, updates the path parameters, and generates path adjustment parameters based on the current surplus material data and the optimal utilization path; The path adjustment submodule dynamically adjusts the path based on the path adjustment parameters, combined with real-time data and path characteristics, and outputs a dynamically optimized path.

[0012] As a further solution of the present invention, the multi-batch processing module includes: The data batching submodule processes the sheet material surplus data in batches based on the dynamic optimization path, performs data segmentation, and generates batch data; The parallel computing submodule uses parallel computing technology based on batch data to process multiple utilization paths and generate parallel processing results; The path optimization submodule performs multi-task parallel processing based on the parallel processing results, optimizes multiple utilization paths, and obtains a multi-task optimized path.

[0013] A method for optimizing the utilization of leftover furniture board materials comprises the following steps: S1, based on sensors and image processing technology, obtains the size, shape and quantity data of sheet metal scraps, removes data noise and outliers, and uses data cleaning algorithms to integrate the cleaned data to obtain scrap data sets; S2, based on the residual material data set, calls the geometric shape and size parameter set operation, combines the geometric shape and size characteristics of the residual material, performs path planning operation, uses the path planning algorithm to generate a path that meets the cutting and utilization requirements, and obtains the initial utilization path; S3, based on the initial utilization path, set the number of ants, pheromone volatility coefficient and pheromone reinforcement factor, perform path selection and analysis, and update the pheromone concentration on the path by comparing the pheromone concentration and the heuristic factor. Cycle the path selection and analysis, update the pheromone concentration, and obtain the optimal utilization path; S4, obtain the current sheet material surplus data, combine it with the optimal utilization path, call the current data and path parameters, combine it with the real-time data of the surplus material and the path characteristics, use the dynamic adjustment algorithm to dynamically adjust the path, and generate a dynamic optimization path; S5, based on the dynamic optimization path, the plate waste data is processed in batches, parallel computing technology is called, multiple utilization paths are combined, and a multi-task parallel processing algorithm is used to optimize multiple utilization paths to obtain a multi-task optimization path; S6, based on the multi-task optimization path, integrates multiple batch processing results, adopts the result integration algorithm, summarizes the optimization path, and generates the final optimization utilization plan.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, the size, shape and quantity data of the waste materials are automatically acquired by integrating sensors and image processing technology, and after effective data cleaning, the optimization scheme significantly improves the accuracy and availability of the data, laying a solid foundation for the reuse of the waste materials. The initial utilization path automatically generated by set operations and path planning algorithms reduces the dependence on manual operations, improves the processing efficiency and the quality of resource reuse. The introduced heuristic algorithm and pheromone adjustment mechanism improve the system's adaptive ability and optimization effect, ensure that it can be adjusted quickly in the face of production changes, and maximize resource utilization. The application of parallel processing technology enables the system to maintain high efficiency when processing large quantities or batches of waste materials, greatly improving productivity. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0018] Example: See Figure 1 The present invention provides a technical solution: a system for optimizing the utilization of leftover furniture board materials, comprising: The data collection module, based on sensors and image processing technology, obtains the size, shape and quantity data of the plate waste, removes data noise and outliers, integrates the cleaned data, and obtains the waste data set; The initial path generation module, based on the residual material data set, calls the geometric shape and size parameter set operation, combines the geometric shape and size characteristics of the residual material, performs path planning operation, generates a path that meets the cutting and utilization requirements, and obtains the initial utilization path; The path optimization module sets the number of ants, pheromone volatility coefficient and pheromone reinforcement factor based on the initial utilization path, performs path selection and analysis, updates the pheromone concentration on the path by comparing the pheromone concentration and the heuristic factor, repeats the path selection and analysis, updates the pheromone concentration, and obtains the optimal utilization path; The dynamic adjustment module obtains the current sheet material surplus data, combines it with the optimal utilization path, calls the current data and path parameters, combines the real-time data of the surplus material and the path characteristics, dynamically adjusts the path, and generates a dynamically optimized path; The multi-batch processing module processes the sheet material surplus data in batches based on the dynamic optimization path, calls parallel computing technology, combines multiple utilization paths, performs multi-task parallel processing, optimizes multiple utilization paths, and obtains a multi-task optimization path.

[0019] The residual material data set includes size data, shape data and quantity data. The initial utilization path includes geometric shape parameters, size parameters and path planning results. The optimal utilization path includes ant quantity settings, pheromone volatility coefficient and pheromone reinforcement factor. The dynamic optimization path includes current data, path parameters and path characteristics. The multi-task optimization path includes batch processing, parallel computing and multi-task optimization.

[0020] In the data collection module, the size, shape and quantity data of the sheet material waste are obtained through sensors and image processing technology. The sensors use laser rangefinders and high-precision cameras to ensure the accuracy of the data. Image processing technology uses edge detection algorithms and shape recognition algorithms to perform image analysis on sheet material waste and extract boundary and contour features. Data noise removal is achieved through Kalman filters, and outliers are removed by using a statistical box plot method to remove obvious outliers. The cleaned data is integrated to generate a waste data set containing size, shape and quantity information. The data is stored in a matrix form to provide a basis for subsequent path generation and ensure the accuracy and completeness of the data.

[0021] In the initial path generation module, the residual material data set is called to perform path planning based on the geometric shape and size parameter set operation. The path planning operation uses a two-dimensional geometric clipping algorithm, combined with the geometric shape and size characteristics of the residual material, to generate a path that meets the cutting and utilization requirements. The specific operation includes using Boolean operations to split and merge the residual material, determining the optimal clipping position through the minimum enclosing rectangle algorithm, and finally generating the initial utilization path. The initial path is based on the path planning results, geometric shape parameters and size parameters to form an initial path planning file, which provides a basis for path optimization.

[0022] In the path optimization module, the path selection and analysis are performed by setting the number of ants, pheromone volatility coefficient and pheromone reinforcement factor. The ant colony algorithm is used to update the pheromone concentration on the path through multiple iterations. In the initial stage, the number of ants is set to a certain value, and the pheromone volatility coefficient and pheromone reinforcement factor are set according to empirical values. When the ants move on the path, they select the path according to the pheromone concentration and heuristic factor, and update the pheromone concentration after passing the path. After multiple iterations, the pheromone concentrations of different paths are compared to finally obtain the optimal utilization path. The optimal path includes the ant number setting, pheromone volatility coefficient and pheromone reinforcement factor, and forms an optimized path file to improve the path utilization rate.

[0023] In the dynamic adjustment module, the path is dynamically adjusted by obtaining the current sheet material data and combining it with the optimal utilization path. The specific operation includes calling the current material data and the optimal path parameters, and dynamically adjusting the path based on the real-time data and path characteristics using an adaptive algorithm. Real-time data is collected in real time by sensors, and path characteristics are extracted from the optimal path file. The adaptive algorithm adjusts the path parameters according to the changes in real-time data and generates a dynamically optimized path. The dynamic optimization path is based on the current data, path parameters and path characteristics to form a dynamic path file to ensure the real-time and effectiveness of the path adjustment.

[0024] In the multi-batch processing module, the plate surplus data is processed in batches by calling the dynamic optimization path. The specific operation includes multi-task parallel processing based on the dynamic optimization path using parallel computing technology. The surplus data is processed in batches, and multiple utilization paths are calculated in parallel through a distributed computing architecture to optimize processing time and efficiency. Parallel computing technology uses multi-threaded processing and GPU acceleration technology to ensure the simultaneous execution of multiple tasks. The multi-task optimization path includes batch processing, parallel computing and multi-task optimization information, and generates a multi-task optimization path file to improve processing efficiency and path utilization.

[0025] In this embodiment, the data collection module includes: The sensor data submodule obtains the size, shape and quantity data of the sheet material residue based on the sensor, and performs preliminary data sorting to generate the original residue data; The image processing submodule removes data noise, removes outliers, and completes data standardization based on the original residual material data to generate cleaned data; The data integration submodule integrates and classifies data based on the cleaned data, establishes a structured data set, and generates a residual data set.

[0026] In the sensor data submodule, the size, shape and quantity data of the scrap are obtained through the sensors installed on the sheet scrap processing equipment. The data collected by the sensor is recorded in a numerical format, and each data point includes dimensional information such as length, width, height, shape parameters and quantity. After data collection, the data preprocessing algorithm is used to preliminarily organize the data, including timestamp alignment, missing value filling and data smoothing of sensor data. The timestamp alignment uses a linear interpolation method to ensure the synchronization of data from different sensors. The missing value filling uses the mean filling method to fill the missing data points, and the data smoothing uses a moving average algorithm to eliminate short-term fluctuations in the data. The sorted data generates the original scrap data file in CSV format, which contains the parameters of each data point. Through preliminary data sorting, the integrity and continuity of the data are ensured, laying the foundation for subsequent data processing.

[0027] In the image processing submodule, data noise removal, outlier elimination and standardization are performed through the data processing process based on the original residual material data. Data noise removal uses the median filtering algorithm to filter out random noise in the data and improve data quality. Outlier elimination uses the box plot method to identify and remove outliers in the data. The box plot method calculates the interquartile range to identify abnormal data points that exceed 1.5 times the upper and lower quartiles. Data standardization uses the Z-score standardization method to convert the data into a standard normal distribution with a mean of zero and a standard deviation of one. In the specific operation, the mean and standard deviation of each data dimension are calculated first, and then each data point is standardized. The processed data generates a cleaned data file in CSV format, which contains standardized data points. Through data cleaning processing, noise and outliers in the data are eliminated, the consistency and comparability of the data are ensured, and the reliability of data analysis is improved.

[0028] In the data integration submodule, a structured data set is established through data integration and classification operations based on cleaned data. Data integration uses a primary key-based merge operation to merge data from different data sources according to a common identifier to ensure data consistency. The classification operation divides the data into different categories through the K-means clustering algorithm. The K-means clustering algorithm first selects the initial cluster center, and then optimizes iteratively to make each data point belong to the cluster center with the closest distance. The clustering results generate sub-datasets of different categories, and each sub-dataset contains data points of the same category. Finally, a structured data set is established to integrate all sub-datasets into a complete data set. The data set format is a relational database, which contains multiple tables, and each table corresponds to a data category. The generated residual data set is used for subsequent data analysis and utilization. Through data integration and classification operations, the organization and systematicness of the data are improved, and the retrieval and use of data are facilitated.

[0029] In this embodiment, the initial path generation module includes: The geometric operation submodule extracts geometric shape features and size parameters based on the residual material data set, performs parameter set operations, and generates geometric feature parameters; The path planning submodule performs path planning operations based on geometric feature parameters, analyzes path feasibility, and generates path planning results; The path generation submodule generates a path that meets the cutting and utilization requirements based on the path planning results and outputs the initial utilization path.

[0030] In the geometric operation submodule, the operation of extracting geometric shape features and size parameters based on the residual material data set specifically includes analyzing each sample in the residual material data set, first using the edge detection algorithm to extract the geometric contour of each sample, and then using the Hough transform algorithm to identify and extract the specific features of the geometric shape, such as straight lines, arcs and other shape parameters. On this basis, the least squares method is used to fit the geometric shape to obtain accurate geometric feature parameters. The parameters include the specific size, angle and other relevant feature values ​​of the shape. Then, parameter set operations are performed, and the geometric feature parameters of different samples are integrated through operations such as intersection and union in set theory to generate a complete and non-redundant set of geometric feature parameters. The geometric feature parameter set generated by this process is output in a standardized data format, such as a CSV file or a JSON format file, which is convenient for subsequent processing and analysis.

[0031] In the path planning submodule, the A* algorithm is first used to calculate the optimal path of the geometric shape by performing path planning operations based on geometric feature parameters. The algorithm evaluates the cost from each node to the target node through a heuristic function to ensure the shortest path. Then, the Dijkstra algorithm is used to optimize the initially planned path, focusing on balancing the path length and safety to ensure the feasibility of the path in actual operation. In the path planning process, a dynamic obstacle avoidance algorithm is also introduced to analyze potential obstacles on the path in real time, and adjust the path according to the real-time data of the obstacles to ensure the continuity and safety of the path. The path planning results are output in XML format, recording the coordinates, angles and other related information of each path node in detail.

[0032] In the path generation submodule, the path planning results are first imported into the cutting path generation algorithm by generating a path that meets the cutting and utilization requirements based on the path planning results. The algorithm performs secondary optimization on the path according to the specific parameters of the cutting machine (such as tool width, cutting speed, etc.) to generate a path that meets the actual cutting requirements. Specifically, the Bezier curve smoothing algorithm is used to smooth the path, eliminate sharp turns and discontinuities in the path, and ensure the smoothness of the cutting process. Subsequently, the overall path is decomposed into several sub-paths through the path segmentation algorithm, each of which contains a specific starting point, end point, and intermediate path points to ensure that the cutting process of each path segment is within the operating range of the device. The generated initial utilization path is output in G-code format, containing detailed cutting instructions and path information.

[0033] In this embodiment, the path optimization module includes: The parameter setting submodule sets the number of ants, pheromone volatility coefficient and pheromone reinforcement factor based on the initial utilization path, and generates parameter setting values; The path analysis submodule performs path selection and analysis based on parameter setting values, evaluates path performance, and generates path analysis results; The pheromone update submodule updates the pheromone concentration on the path based on the path analysis results, repeatedly selects and analyzes the path, and obtains the optimal utilization path.

[0034] In the parameter setting submodule, the number of ants, pheromone volatility coefficient and pheromone enhancement factor are set through the initial utilization path to generate parameter setting values. The specific operation includes reading the geometric shape parameters and size parameters of the initial utilization path. The number of ants is set based on the complexity of path planning, which is a multiple of the number of path nodes to ensure the comprehensiveness of path exploration. The pheromone volatility coefficient is set between 0 and 1, and the optimal value is determined through experiments to ensure the reasonable distribution of pheromones on the path. The pheromone enhancement factor is set according to the path length and the number of nodes to ensure that the pheromones of high-quality paths are appropriately enhanced.

[0035] In the path analysis submodule, the path selection and analysis are performed through parameter setting values, the path performance is evaluated, and the path analysis results are generated. The specific operations include randomly distributing ants in the path network according to the set number of ants, and simulating the process of ants moving in the path network. During the movement, the ants select the path according to the pheromone concentration and the heuristic factor. The heuristic factor considers factors such as path length and turning angles to ensure the rationality of the path selection. The path performance evaluation uses multiple indicators, including path length, number of turning angles, and time consumption, and the comprehensive score is calculated by the weighted average method. During the path selection and analysis process, the path and corresponding performance indicators of each ant are recorded, and the path analysis result file is generated, including the performance score and selection frequency of each path. The path analysis results are used to guide the update of pheromones to ensure that the pheromones of high-quality paths are strengthened and the pheromones of low-quality paths are gradually weakened.

[0036] In the pheromone update submodule, the pheromone concentration on the path is updated according to the path analysis results, and the path is repeatedly selected and analyzed to obtain the optimal utilization path. The specific operation includes calculating the pheromone increment of each path according to the path analysis results, and the pheromone increment is proportional to the path performance score. The pheromone concentration update adopts the formula C(i,j) = (1 - ρ) *C(i,j) + ΔC(i,j), where C(i,j) is the pheromone concentration on the path (i,j), ρ is the pheromone volatility coefficient, and ΔC(i,j) is the pheromone increment. The path selection and analysis process is repeated. After each iteration, the pheromone concentration on the path is updated, and the pheromone of the high-quality path is gradually enhanced. After multiple iterations, the pheromone concentration of the high-quality path is significantly higher than that of other paths, and the path selection tends to be stable, and finally the optimal utilization path is obtained. Generate the optimal utilization path file, including the path node sequence and pheromone concentration distribution, to provide a basis for subsequent dynamic adjustment and multi-batch processing. The pheromone update process improves the accuracy and stability of path selection and ensures the effectiveness and practicality of the optimal utilization path.

[0037] In this embodiment, the dynamic adjustment module includes: The real-time monitoring submodule obtains the current sheet material surplus data, performs real-time data updates, and generates the current surplus material data; The data calling submodule calls the current data and path parameters, updates the path parameters, and generates path adjustment parameters based on the current surplus material data and the optimal utilization path; The path adjustment submodule dynamically adjusts the path based on the path adjustment parameters, combined with real-time data and path characteristics, and outputs a dynamically optimized path.

[0038] In the real-time monitoring submodule, the current sheet material surplus data is obtained through a high-frequency data acquisition system. The data format is a JSON format including timestamp, sheet number, size, shape and quantity. The data acquisition system uses the WebSocket protocol to achieve real-time data transmission to ensure the timeliness and integrity of the data. The data update adopts a double buffering mechanism to store the latest data in the buffer and write the data of the previous buffer into the database. During the data processing, the sliding window algorithm is used to update and process the data in real time. Each sliding window contains the most recent N data points. The current surplus material data is updated in real time by calculating the mean, variance and other statistics of the data in the window. The generated current surplus material data file is in JSON format, containing detailed information such as timestamp, sheet number, size, shape and quantity. Through real-time data updates, the system can keep abreast of the latest status of sheet material surplus at any time, providing a reliable data basis for subsequent data calls and path adjustments.

[0039] In the data calling submodule, by reading the current surplus material data generated by the real-time monitoring submodule and combining it with the preset optimal utilization path, the current data and path parameters are called to update the path parameters. During the data calling process, the key parameters in the current surplus material data are first extracted, including the plate size, shape and quantity. The path parameters include the starting point, end point, path length and path characteristics. The dynamic programming algorithm is used to optimize the path parameters. The specific operations include initializing the path matrix, updating the weight value in the path matrix according to the current surplus material data, using the Bellman-Ford algorithm to calculate the shortest path, and updating the path parameters according to the calculation results. The generated path adjustment parameter file is in JSON format and contains detailed information such as the starting point, end point, path length and path characteristics. By updating the path parameters, it is ensured that the system can be dynamically adjusted according to the real-time surplus material data to improve the plate utilization efficiency and path optimization degree.

[0040] In the path adjustment submodule, the path adjustment parameters generated by the data calling submodule are read, and the path is adjusted dynamically in combination with the real-time data and path characteristics provided by the real-time monitoring submodule. During the path adjustment process, the key data in the path adjustment parameters are first extracted, including the path starting point, end point, path length and path characteristics. Combined with real-time data, the A* algorithm is used for path optimization. The specific operations include initializing the open list and the closed list, adding the starting point to the open list, calculating the estimated cost from the current node to the end point, and selecting the node with the smallest estimated cost for expansion until the optimal path is found. During the dynamic adjustment process, the node information in the open list and the closed list is updated in real time to ensure the real-time and accuracy of the path adjustment. The generated dynamic optimization path file is in JSON format, containing detailed information such as path node sequence, path length and path characteristics. By dynamically adjusting the path, the real-time optimization of the plate waste utilization path is realized, and the plate utilization efficiency and system response speed are improved.

[0041] In this embodiment, the multi-batch processing module includes: The data batching submodule processes the sheet material surplus data in batches based on the dynamic optimization path, performs data segmentation, and generates batch data; The parallel computing submodule uses parallel computing technology based on batch data to process multiple utilization paths and generate parallel processing results; The path optimization submodule performs multi-task parallel processing based on the parallel processing results, optimizes multiple utilization paths, and obtains a multi-task optimized path.

[0042] In the data batching submodule, the sheet material waste data is processed in batches based on a dynamic optimization path. The specific operation includes first extracting the original data of the sheet material waste from the database. The data is stored in CSV or JSON format, including the geometric features and dimensional parameters of the waste. Then, the dynamic programming algorithm is used to optimize the waste data in batches. The dynamic programming algorithm selects the optimal batching scheme by calculating the cost function of different batching strategies. Specifically, the similarity of the geometric features and dimensional parameters of each batch of data is calculated, and the data with high similarity is divided into a batch, thereby improving the efficiency of subsequent processing. The k-means clustering algorithm is used in the data segmentation process to divide the waste data into multiple subsets according to feature clustering. Each subset represents a batch of data, and the clustering results are output in the form of batch data files, such as multiple CSV files, each of which contains the specific waste data of the corresponding batch.

[0043] In the parallel computing submodule, multiple utilization paths are processed by calling parallel computing technology based on batch data. The specific operation includes first importing the batch data into a parallel computing framework, such as Hadoop or Spark, which can effectively process large-scale data. Then, the MapReduce algorithm is used to process each batch of data in parallel. The Map stage distributes the data to different computing nodes, and the Reduce stage summarizes the processing results of each node. During the processing, multi-threading or multi-process technology is called to calculate the optimal utilization path for each batch of data based on the utilization path to ensure processing efficiency and accuracy of the results. The calculation results are output in the form of parallel processing result files, such as multiple JSON files containing utilization path information.

[0044] In the path optimization submodule, multiple utilization paths are optimized by performing multi-task parallel processing based on the parallel processing results. The specific operation includes first extracting the initial utilization path data from the parallel processing result file. The data is stored in JSON format and contains the specific node information of each utilization path. Then, a genetic algorithm is used to globally optimize multiple utilization paths. The genetic algorithm continuously iterates and optimizes the path selection by simulating natural selection and genetic mutation. The specific process includes encoding the initial path as a chromosome, defining a fitness function to evaluate the quality of each path, generating a new generation of path populations through operations such as selection, crossover, and mutation, and continuously evolving until the optimization goal is met. During the optimization process, a multi-task optimization strategy is also used to process multiple utilization paths at the same time to ensure the effect of global optimization. The multi-task optimized path finally generated is output in the form of an optimized path file, such as an XML file containing detailed information of the optimized path.

[0045] A method for optimizing the utilization of leftover furniture board materials comprises the following steps: Based on sensors and image processing technology, the size, shape and quantity data of sheet metal scraps are obtained, data noise and outliers are removed, and the cleaned data are integrated using data cleaning algorithms to obtain scrap data sets; Based on the data set of the residual material, the geometric shape and size parameter set operation is called, and the path planning operation is performed in combination with the geometric shape and size characteristics of the residual material. The path planning algorithm is used to generate a path that meets the cutting and utilization requirements to obtain the initial utilization path; Based on the initial utilization path, the number of ants, pheromone volatility coefficient and pheromone reinforcement factor are set to select and analyze the path. By comparing the pheromone concentration and the heuristic factor, the ant colony optimization algorithm is used to update the pheromone concentration on the path. The path selection and analysis are repeated to update the pheromone concentration and obtain the optimal utilization path. Obtain the current sheet material surplus data, combine it with the optimal utilization path, call the current data and path parameters, combine it with the real-time data of the surplus material and the path characteristics, use the dynamic adjustment algorithm to dynamically adjust the path, and generate a dynamic optimization path; Based on the dynamic optimization path, the sheet material surplus data is processed in batches, and the parallel computing technology is called to combine multiple utilization paths. The multi-task parallel processing algorithm is used to optimize multiple utilization paths to obtain the multi-task optimization path; Based on the multi-task optimization path, multiple batch processing results are integrated, and the result integration algorithm is used to summarize the optimization path to generate the final optimization utilization plan.

[0046] Through the above method, the optimization utilization system of home board waste can significantly improve the utilization efficiency of boards, reduce waste and improve production efficiency. Based on sensors and image processing technology, the system can accurately obtain the size, shape and quantity data of board waste to ensure high accuracy and reliability of the data. The data noise removal and outlier elimination process improves the purity and accuracy of the data. The waste data set integrated by the data cleaning algorithm lays a solid foundation for subsequent path planning. By calling the geometric shape and size parameter set operation, combined with the geometric shape and size characteristics of the waste, the system can perform efficient path planning operations. The initial utilization path generated by the path planning algorithm meets the cutting and utilization requirements, ensuring the maximum utilization of board waste.

[0047] In the path optimization stage, the number of ants, pheromone volatility coefficient and pheromone reinforcement factor are set based on the initial utilization path. Through the ant colony optimization algorithm, the system can perform effective path selection and analysis. The comparison of pheromone concentration and heuristic factor makes the path optimization process more scientific and reasonable. The pheromone concentration on the path is updated iteratively multiple times to gradually obtain the optimal utilization path, which significantly improves the accuracy and stability of path selection. In the dynamic adjustment stage, the system can obtain the current sheet material data in real time, combine the optimal utilization path, and use the dynamic adjustment algorithm to dynamically adjust the path. This process ensures that the system can still generate a dynamic optimization path when facing real-time changing data, thereby improving the flexibility and adaptability of sheet material utilization.

[0048] The application of multi-task parallel processing algorithm in multi-batch processing module enables the system to process multiple utilization paths at the same time, significantly improving processing efficiency. Through parallel computing technology, the system can quickly optimize multiple utilization paths and reduce processing time. The integration of multi-task optimization paths further improves the comprehensiveness and effectiveness of path optimization. In the result integration stage, the result integration algorithm is used, and the system can summarize the results of multiple batches to generate the final optimization utilization plan. This plan integrates all optimization paths to ensure the maximum utilization of sheet material residues, reduce material waste, and reduce production costs.

[0049] In summary, the method for optimizing the utilization of household board waste has many beneficial effects. First, the accuracy and reliability of waste data are ensured through high-precision data acquisition and processing technology. Secondly, the accuracy and stability of path selection are improved through scientific path planning and optimization algorithms. The application of dynamic adjustment algorithms enhances the flexibility and adaptability of the system in processing real-time data. The combination of parallel computing technology and multi-task parallel processing algorithms significantly improves the processing efficiency and optimization effect of the system. Finally, through the result integration algorithm, a comprehensive and effective final optimization utilization plan is generated, which realizes the maximum utilization of board waste, reduces material waste and production costs, and improves production efficiency and resource utilization.

[0050] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A system for optimizing the utilization of leftover furniture board materials, characterized in that: The system comprises: The data collection module, based on sensors and image processing technology, obtains the size, shape and quantity data of the plate waste, removes data noise and outliers, integrates the cleaned data, and obtains the waste data set; The initial path generation module, based on the residual material data set, calls the geometric shape and size parameter set operation, combines the geometric shape and size characteristics of the residual material, performs path planning operation, generates a path that meets the cutting and utilization requirements, and obtains the initial utilization path; The path optimization module sets the number of ants, pheromone volatility coefficient and pheromone reinforcement factor based on the initial utilization path, performs path selection and analysis, updates the pheromone concentration on the path by comparing the pheromone concentration and the heuristic factor, repeats the path selection and analysis, updates the pheromone concentration, and obtains the optimal utilization path; The dynamic adjustment module obtains the current sheet material surplus data, combines it with the optimal utilization path, calls the current data and path parameters, combines the real-time data of the surplus material and the path characteristics, dynamically adjusts the path, and generates a dynamically optimized path; The multi-batch processing module processes the sheet material surplus data in batches based on the dynamic optimization path, calls parallel computing technology, combines multiple utilization paths, performs multi-task parallel processing, optimizes multiple utilization paths, and obtains a multi-task optimization path.

2. The system for optimizing the utilization of residual furniture board materials according to claim 1 is characterized in that: The residual material data set includes size data, shape data and quantity data, the initial utilization path includes geometric shape parameters, size parameters and path planning results, the optimal utilization path includes ant quantity settings, pheromone volatility coefficients and pheromone reinforcement factors, the dynamic optimization path includes current data, path parameters and path characteristics, and the multi-task optimization path includes batch processing, parallel computing and multi-task optimization.

3. The system for optimizing the utilization of residual furniture board materials according to claim 1, characterized in that: The data collection module comprises: The sensor data submodule obtains the size, shape and quantity data of the sheet material residue based on the sensor, and performs preliminary data sorting to generate the original residue data; The image processing submodule removes data noise, removes outliers, and completes data standardization based on the original residual material data to generate cleaned data; The data integration submodule integrates and classifies data based on the cleaned data, establishes a structured data set, and generates a residual data set.

4. The system for optimizing the utilization of residual furniture board materials according to claim 1, characterized in that: The initial path generation module comprises: The geometric operation submodule extracts geometric shape features and size parameters based on the residual material data set, performs parameter set operations, and generates geometric feature parameters; The path planning submodule performs path planning operations based on geometric feature parameters, analyzes path feasibility, and generates path planning results; The path generation submodule generates a path that meets the cutting and utilization requirements based on the path planning results and outputs the initial utilization path.

5. The system for optimizing the utilization of residual furniture board materials according to claim 1, characterized in that: The path optimization module includes: The parameter setting submodule sets the number of ants, pheromone volatility coefficient and pheromone reinforcement factor based on the initial utilization path, and generates parameter setting values; The path analysis submodule performs path selection and analysis based on parameter setting values, evaluates path performance, and generates path analysis results; The pheromone update submodule updates the pheromone concentration on the path based on the path analysis results, repeatedly selects and analyzes the path, and obtains the optimal utilization path.

6. The system for optimizing the utilization of residual furniture board materials according to claim 1, characterized in that: The dynamic adjustment module comprises: The real-time monitoring submodule obtains the current sheet material surplus data, performs real-time data updates, and generates the current surplus material data; The data calling submodule calls the current data and path parameters, updates the path parameters, and generates the path adjustment parameters based on the current surplus material data and the optimal utilization path; The path adjustment submodule dynamically adjusts the path based on the path adjustment parameters, combined with real-time data and path characteristics, and outputs a dynamically optimized path.

7. The system for optimizing the utilization of residual furniture board materials according to claim 1, characterized in that: The multi-batch processing module comprises: The data batching submodule processes the sheet material data in batches based on the dynamic optimization path, performs data segmentation, and generates batch data; The parallel computing submodule uses parallel computing technology based on batch data to process multiple utilization paths and generate parallel processing results; The path optimization submodule performs multi-task parallel processing based on the parallel processing results, optimizes multiple utilization paths, and obtains a multi-task optimized path.

8. A method for optimizing the utilization of leftover furniture board materials, characterized in that: The system for optimizing the utilization of residual furniture board materials according to any one of claims 1 to 7 comprises the following steps: Based on sensors and image processing technology, the size, shape and quantity data of sheet metal scraps are obtained, data noise and outliers are removed, and the cleaned data are integrated using data cleaning algorithms to obtain scrap data sets; Based on the data set of the residual material, the geometric shape and size parameter set operation is called, and the path planning operation is performed in combination with the geometric shape and size characteristics of the residual material. The path planning algorithm is used to generate a path that meets the cutting and utilization requirements to obtain the initial utilization path; Based on the initial utilization path, the number of ants, pheromone volatility coefficient and pheromone reinforcement factor are set to select and analyze the path. By comparing the pheromone concentration and the heuristic factor, the ant colony optimization algorithm is used to update the pheromone concentration on the path. The path selection and analysis are repeated to update the pheromone concentration and obtain the optimal utilization path. Obtain the current sheet material surplus data, combine it with the optimal utilization path, call the current data and path parameters, combine it with the real-time data of the surplus material and the path characteristics, use the dynamic adjustment algorithm to dynamically adjust the path, and generate a dynamic optimization path; Based on the dynamic optimization path, the sheet material surplus data is processed in batches, and the parallel computing technology is called to combine multiple utilization paths. The multi-task parallel processing algorithm is used to optimize multiple utilization paths to obtain the multi-task optimization path; Based on the multi-task optimization path, multiple batch processing results are integrated, and the result integration algorithm is used to summarize the optimization path to generate the final optimization utilization plan.

Images