Furniture processing multi-drill parallel processing optimization method and system

Abstract

The application discloses a kind of furniture processing multi-drill head parallel processing optimization method and system, it is related to custom furniture production operation optimization technical field, the method includes clustering analysis to initial data set, obtain clustering result, and based on clustering result to initial data set is divided, obtain several grouping data set;Based on the drill bit parameter of all drill bits on drill bag and the drilling parameter of each drill hole in all hole combinations in grouping data set, establish multi-drill head parallel processing optimization model;With the matching value of drill bit and drill hole corresponding to all hole combinations in grouping data set maximum as target, differential evolution algorithm is used to solve multi-drill head parallel processing optimization model, and the drill bit arrangement optimal solution corresponding to grouping data set is obtained.The application adopts differential evolution algorithm to carry out multi-drill head parallel processing optimization, and the drill bit arrangement optimal solution of each grouping data set can be obtained, to carry out operation with drill bit arrangement optimal solution, and operation time can be shortened.

Description

Technical Field

[0001] This invention relates to the field of customized furniture production operation optimization technology, and in particular to a method and system for optimizing multi-drill parallel processing in furniture manufacturing. Background Technology

[0002] Mass customization furniture is one of the most dynamic sub-sectors of the furniture manufacturing industry. Its core characteristics are ultra-high production efficiency (an average of 3 seconds to process one panel) and highly personalized products (almost every panel has different process parameters). This necessitates a higher level of informatization and automation to achieve flexible manufacturing, based on cyber-physical integration and intelligent production as the main line, seeking to optimize cost and efficiency through a mass customization production model. CNC machining centers are the core equipment for resolving the contradictions in customized furniture manufacturing and implementing automated and continuous production. Drilling is one of its main application scenarios. The flexible response mechanism of customized furniture determines that the number and location of holes of different specifications vary on each panel during drilling operations (the number of holes on a panel can vary by more than 140, and holes may be distributed on all six sides). This flexible operation objectively causes significant fluctuations in operation time: the average operation time of CNC drilling (excluding loading, unloading, and positioning time) is as long as 25 seconds, and the difference in operation time between different panels can exceed 300 seconds, making it a major bottleneck and a key point causing production disturbances. Since the layout of the drill bits in the CNC drilling machining center and the hole positions of the custom furniture panels both conform to the 32mm system, if the drill bits on each drill bit can be scientifically arranged based on the characteristics of the panel holes, it is possible to achieve parallel operation of multiple drill bits, thereby reducing the number of drilling operations and shortening the operation time. However, due to the current lack of comprehensive big data in custom furniture manufacturing, insufficient precision in production decisions, and the involvement of interdisciplinary fields such as furniture manufacturing processes, wood processing equipment, big data analysis, and artificial intelligence, related research is still in its early stages. Therefore, there is an urgent need for an optimization method for multi-drill parallel machining in furniture processing to achieve parallel operation of multiple drill bits and thus shorten the operation time. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for optimizing parallel processing of multiple drill bits in furniture manufacturing, which can realize parallel operation of multiple drill bits, thereby shortening the operation time.

[0004] To achieve the above objectives, the present invention provides the following solution:

[0005] A method for optimizing parallel machining with multiple drill bits in furniture processing includes:

[0006] Obtain an initial dataset; the initial dataset includes several hole combinations; the drill holes in each hole combination are located on a plate;

[0007] Cluster analysis is performed on the initial dataset to obtain clustering results, and the initial dataset is divided based on the clustering results to obtain several grouped datasets; the clustering results include several board combinations;

[0008] For each grouped dataset, a multi-drill parallel processing optimization model is established based on the drill bit parameters of all drill bits on the drill bag and the drilling parameters of each hole in all hole combinations in the grouped dataset. With the objective of maximizing the matching value between drill bits and holes corresponding to all hole combinations in the grouped dataset, the multi-drill parallel processing optimization model is solved using a differential evolution algorithm to obtain the optimal solution for the drill bit arrangement corresponding to the grouped dataset. The optimal solution for the drill bit arrangement includes the drill bit parameters of each drill bit. The drill bit parameters include the position coordinates of the drill bit on the drill bag and the drill bit diameter. The drilling parameters include the position coordinates of the drilling hole on the plate and the drilling diameter.

[0009] A computer system includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described furniture processing multi-drill parallel machining optimization method.

[0010] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects: The present invention provides a method and system for optimizing parallel processing of multiple drill bits in furniture manufacturing, wherein an initial dataset is obtained; the initial dataset includes several hole combinations; the drill holes in each hole combination are located on a board; cluster analysis is performed on the initial dataset to obtain clustering results, and the initial dataset is divided based on the clustering results to obtain several group datasets; for each group dataset, a parallel processing optimization model for multiple drill bits is established based on the drill bit parameters of all drill bits on the drill bag and the drill hole parameters of each drill hole in all hole combinations in the group dataset; with the objective of maximizing the matching value of drill bits and drill holes corresponding to all hole combinations in the group dataset, the parallel processing optimization model for multiple drill bits is solved using a differential evolution algorithm to obtain the optimal solution for drill bit arrangement corresponding to the group dataset; the optimal solution for drill bit arrangement includes the drill bit parameters of each drill bit; the drill bit parameters include the position coordinates of the drill bit on the drill bag and the drill bit diameter; the drill hole parameters include the position coordinates of the drill hole on the board and the drill hole diameter. This invention uses a differential evolution algorithm to optimize parallel processing of multiple drill bits, which can obtain the optimal solution for drill bit arrangement in each group dataset. By using the optimal solution for drill bit arrangement, the operation time can be shortened. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic diagram of the multi-drill parallel machining optimization method for furniture processing provided in Embodiment 1 of the present invention;

[0013] Figure 2 This is a schematic diagram of the drilling data extraction and processing flow provided in Embodiment 1 of the present invention;

[0014] Figure 3 This is a schematic diagram of the differential evolution algorithm solution process provided in Embodiment 1 of the present invention;

[0015] Figure 4 An internal structural diagram of the computer device provided by the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] The purpose of this invention is to provide a method and system for optimizing parallel multi-drill machining in furniture manufacturing. It aims to optimize parallel multi-drill machining using a differential evolution algorithm to obtain the optimal drill bit arrangement for each group of data sets. Using this optimal arrangement reduces processing time. By employing a clustering algorithm, custom furniture panels are grouped according to their hole combination characteristics. Based on the hole combination characteristics of each group and the drill bit position of the drilling equipment, an intelligent optimization algorithm is used to arrange drill bits of various diameters on the drill bit, enabling multiple holes to be machined in a single drilling operation. This reduces drilling time and improves production efficiency.

[0018] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] Example 1

[0020] like Figure 1 As shown in this embodiment, a multi-drill parallel machining optimization method for furniture processing includes:

[0021] S1: Obtain the initial dataset; the initial dataset includes several hole combinations; the drill holes in each hole combination are located on a plate.

[0022] S2: Perform cluster analysis on the initial dataset to obtain clustering results, and divide the initial dataset based on the clustering results to obtain several grouped datasets; the clustering results include several board combinations.

[0023] S3: For each group dataset, a multi-drill parallel processing optimization model is established based on the drill bit parameters of all drill bits on the drill bag and the drilling parameters of each hole in all hole combinations in the group dataset. With the objective of maximizing the matching value between drill bits and holes corresponding to all hole combinations in the group dataset, the multi-drill parallel processing optimization model is solved using a differential evolution algorithm to obtain the optimal solution for the drill bit arrangement corresponding to the group dataset. The optimal solution for the drill bit arrangement includes the drill bit parameters of each drill bit. The drill bit parameters include the position coordinates of the drill bit on the drill bag and the drill bit diameter. The drilling parameters include the position coordinates of the drilling hole on the plate and the drilling diameter.

[0024] S1 specifically includes: the drilling data extraction and processing flow, such as... Figure 2 As shown. During the order breakdown process for customized furniture, various parameters for drilling the panels are automatically generated based on process rules and stored in a parameter file. These parameters can be extracted using a Manufacturing Execution System (MES). A self-written parsing program can extract the position coordinates, diameter, and depth of each hole on each surface of each panel. When several specific holes are combined to form a hole combination that meets certain conditions, parallel processing with multiple drill bits can be achieved. The number of drilling passes is one of the main factors affecting the CNC drilling operation time. This number can be extracted from the CNC program generated by the equipment's industrial control computer (CAM) software using a self-written parsing program. Based on the extracted information such as the number of drilling passes, the processing time can be predicted using an artificial neural network algorithm.

[0025] Because the number of holes on the panels is large (e.g., the top, bottom, and side panels have over a hundred holes), unrestrained arbitrary combinations will inevitably lead to an exponential explosion. It is necessary to eliminate invalid hole combinations based on actual production to reduce the computational scale. Since most custom furniture companies currently use 8mm diameter horizontal holes, which do not involve arrangement issues, the focus is on optimizing the arrangement of vertical drills in the Z+ and Z- directions. Due to structural and technological influences, most groups of vertical holes extend along the X or Y direction, and the drill bits on the drill pack are also arranged accordingly along these two directions. Therefore, hole combinations outside the X and Y directions are not discussed. Considering that only holes that conform to the 32mm hole position system and have equal depth can be drilled simultaneously, hole combinations that do not meet this condition are excluded. Hole combinations on the same side have a certain degree of symmetry on both sides of the feed direction (i.e., the Y+ and Y- directions). For equipment with double drill packs on the same side, to simplify the calculation, the calculation can be carried out on the hole positions on one side.

[0026] Based on the above conditions, a dataset consisting of combinations of holes that may be drilled simultaneously on each board can be obtained. To facilitate subsequent calculations, the hole combinations in the dataset are normalized by arranging the holes in each combination in ascending order of their X or Y coordinates, and then translating all hole combinations in the X or Y direction so that the coordinates of the first hole are adjusted to (0, 0).

[0027] An initial dataset can be obtained through S1, which contains combinations of holes that can be processed simultaneously in a single drilling operation and have been standardized through translation processing. This dataset serves as the foundation for subsequent modeling and solving.

[0028] Solving the problem requires first grouping the initial dataset based on a multi-machine parallel scenario, then establishing a mathematical model based on the operation logic of a CNC drilling machining center to achieve multi-drill parallel processing by optimizing the drill bit arrangement, obtaining the drill bit arrangement scheme through intelligent optimization algorithms, and verifying the improvement of multi-drill parallel processing optimization on the efficiency of CNC drilling operations through theoretical calculations and actual tests.

[0029] S2 performs cluster analysis on the initial dataset to obtain clustering results. Specifically, it uses the k-means algorithm to perform cluster analysis on the initial dataset, obtaining clustering results to classify the board types and obtain several board combinations. Further, it specifically includes:

[0030] In actual production conditions, CNC drilling operations are often performed by multiple machines in parallel. When multiple CNC drilling machining centers use the same drill bit arrangement, the following two problems may arise:

[0031] 1) Due to interference between the equipment fixture and the drill bag, not every drill bit can completely cover the entire plate. Therefore, there is a problem of machine stoppage due to the hole position of a few plates being outside the processing range of the corresponding drill bit, which requires manual intervention and threatens the stability of the production line.

[0032] 2) Although the drilling parameters for almost every panel in custom furniture are different, the hole combinations conforming to the 32mm system on different types of panels share certain commonalities in their structure. Using a uniform drill bit arrangement on all equipment lacks specificity for panels with different hole combinations, which is not conducive to professional processing.

[0033] Considering the above two reasons, the drill bits of multiple CNC drilling machining centers can be arranged differently to make them more targeted at specific types of plates while ensuring full processing capacity. The plates can be sent to the most suitable equipment for processing through an automated conveyor line, thereby expanding the processing range of the entire production line and further improving efficiency.

[0034] Since the differential evolution algorithm used in this embodiment is based on a certain hole combination dataset, if the hole combination dataset can be scientifically grouped by plate, and hole combination datasets of different types of plates can be separated, and the differential evolution algorithm can be used to solve the problem based on these datasets, differentiated drill bit arrangement schemes can be obtained.

[0035] Existing methods of grouping panels based on their location within the cabinet to represent hole combinations are not representative enough. Therefore, this embodiment uses the hole combinations of the panels as the primary basis for grouping, employing clustering. k-means is a classic clustering algorithm with advantages such as low computational complexity, fast convergence speed, and strong interpretability, enabling efficient processing of the scale of data involved in this embodiment. Its basic steps include:

[0036] 1) Set the number of clusters k, and randomly select k samples as the initial cluster centers;

[0037] 2) Calculate the Euclidean distance between each sample and the cluster center, and assign it to the cluster that is closest to it;

[0038] 3) Calculate the center of each cluster and update it;

[0039] 4) Repeat steps (2) and (3) until the cluster centers no longer change, then output the clustering results.

[0040] There are over a hundred possible hole combinations that meet the requirements in custom furniture panels. Most of these combinations account for less than 1%, making it impractical and unnecessary to include them all in the calculation. Therefore, this embodiment extracts the top n key hole combinations by drawing a Pareto chart, with each key hole combination having a quantity 'a'. wConstruct an n-dimensional vector space (w = 1, 2, 3, ..., n), where each board piece is represented by a vector b = [a1, a2, a3, ..., a...]. n Based on this, clustering is carried out. There is no experience or data to support clustering based on the number of keyhole combinations. The elbow method can be used to determine the value of the number of clusters k, that is, the sum of the squared errors (SSE) is used to evaluate the effect of clustering under different k values. The calculation method is formula (1). Plot the k-SSE curve, where the k value corresponding to the elbow is the optimal number of clusters.

[0041]

[0042] In equation (1), SSE is the sum of squared errors corresponding to the number of clusters k; b l For the l-th cluster C l An n-dimensional vector of a plate component; c l Let be the n-dimensional mean vector of this cluster.

[0043] Clustering based on the k-value obtained using the elbow method often results in a larger number of clusters than the actual number of devices and a severe imbalance in the number of plates in each group, making it unsuitable for directly solving drill bit arrangement problems. Therefore, based on clustering, it is necessary to calculate the average number of plates and key hole combinations in each cluster. Combining this with the layout of the vertical drill bit, and considering the similarity between clusters, the number of plates, and potential conflicts in drill bit installation, the clusters are reorganized. The hole combination dataset is then divided according to the group to which the plate belongs, and the drill bit arrangement is solved separately for each group.

[0044] The specific reorganization method is as follows: among the groups of plates obtained by clustering, the groups where the drill bit installation interferes are identified and separated. The groups of plates with high hole combination similarity are listed as the range that can be merged. Then, based on the proportion or quantity of each group of plates, and under the above two conditions, based on the relatively balanced task of each machining center, the groups obtained by clustering are merged in a limited manner to form new groups. Based on this new group, the original dataset is split.

[0045] S3 can be divided into two parts: mathematical modeling of the multi-drill parallel machining optimization problem and solving the multi-drill parallel machining optimization problem.

[0046] I. Mathematical modeling of the multi-drill-bit parallel machining optimization problem, i.e., establishing a multi-drill-bit parallel machining optimization model:

[0047] In this embodiment, the drill bit is a vertical drill, and correspondingly, the drill holes on the plate are vertical holes.

[0048] p vertical drills d are installed on drill bag D. m (m = 1, 2, 3, ..., p), xm y m Let d be the coordinates of the m-th vertical drill bit on the drill bag. m Let be the drill bit diameter. The matrix of position and diameter parameters of all drill bits on drill bag D is given by formula (2):

[0049]

[0050] Hole combination dataset, that is, a grouped dataset with q hole combinations S i (i = 1, 2, 3, ..., q), the i-th hole combination has r vertical holes h. ij (j = 1, 2, 3, ..., r), x ij y ij Let d be the X and Y coordinates of the j-th vertical hole. ij Let S be the diameter of the j-th vertical hole in the i-th hole combination. Since each hole combination has been normalized, hole combinations in the X and Y directions can be represented separately. Hole combination S i The matrix of position and diameter parameters of all boreholes is given by formula (3):

[0051]

[0052] If and only if the hole combination S i Two holes on With two vertical drills on drill bag D When the conditions shown in formula (4) are met, the two holes can be drilled in parallel.

[0053]

[0054] Solving the optimization problem of parallel machining with multiple drill bits involves finding a set of permutations d1, d2, ..., dn for the installation positions of vertical drill bits of various diameters. p This minimizes the total number of drilling passes when machining a combination of q holes, meaning the drill bit, after translation, can match as many holes as possible in the hole combination. For a specific drill bit arrangement d1, d2, ..., d... p Using formula (4) as the judgment condition, except for S i In addition to the first borehole, for each subsequent borehole that can be drilled simultaneously with the first borehole, S i Matching value t i Add 1, when there are u matching schemes for a hole combination that satisfy the condition, only the largest matching value is calculated. By summing the matching values ​​of q hole combinations, the total matching value T of this drill bit arrangement can be obtained, which is used as the objective function, i.e., formula (5). The goal of solving this multi-drill parallel processing optimization problem is to maximize the objective function.

[0055]

[0056] Where T represents the matching value of drill bit and drill hole for all hole combinations in the grouped dataset; i represents the i-th hole combination, i = 1, 2, 3...q, and q represents the total number of hole combinations in the grouped dataset; t iu The number of matching holes and drill bits in the u-th matching scheme of the i-th hole combination; the matching scheme is the combination of holes that are drilled simultaneously in a hole combination.

[0057] II. Solving the optimization problem of parallel machining with multiple drill bits:

[0058] Solving the optimization problem of parallel machining with multiple drill bits in a CNC drilling machining center requires calculating the minimum number of drill runs required for each hole combination based on a given drill bit arrangement. Clearly, finding the solution that minimizes the total number of drill runs for machining a batch of plates is an NP-hard problem. It is difficult to accurately verify whether a particular solution is optimal before calculating all solutions. When the solution space is large, using a heuristic algorithm to find a suboptimal solution is a good strategy. The Differential Evolution Algorithm (DE) has the characteristics of simple structure, fast convergence, and strong robustness. It can quickly obtain a high-quality solution when the solution space is large. Therefore, this embodiment uses the Differential Evolution Algorithm for solving the problem. The specific solution steps are as follows: Figure 3 As shown.

[0059] In S3, with the objective of maximizing the matching value between drill bits and drill holes for all hole combinations in the grouped dataset, a differential evolution algorithm is used to solve the multi-drill-bit parallel processing optimization model to obtain the optimal solution for the drill bit arrangement corresponding to the grouped dataset. Specifically, this includes:

[0060] The drill bit parameters of each drill bit are encoded to generate an initial drill bit arrangement population;

[0061] Calculate the fitness of each individual in the drill bit arrangement population corresponding to the current iteration number; the fitness is calculated by an objective function; the objective function is a function that aims to maximize the matching value between drill bits and holes for all hole combinations in the grouped dataset;

[0062] Determine whether the termination condition is met; the termination condition is that the current iteration count reaches the maximum iteration count.

[0063] If so, then decode the individuals in the drill bit arrangement population corresponding to the current iteration number to obtain the optimal solution for the drill bit arrangement;

[0064] If not, perform a mutation operation on the individuals in the drill bit arrangement population corresponding to the current iteration number to obtain a mutated population; perform a crossover operation on the mutated population to obtain a crossover population; perform a selection operation on the crossover population according to the fitness to obtain the drill bit arrangement population corresponding to the next iteration number; update the drill bit arrangement population corresponding to the current iteration number to the drill bit arrangement population corresponding to the next iteration number, and return to the step of "calculate the fitness of each individual in the drill bit arrangement population corresponding to the current iteration number".

[0065] The mutant population is subjected to a crossover operation to obtain a crossover population. Specifically, this includes performing a crossover operation on the mutant population using an exponential crossover algorithm to obtain a crossover population.

[0066] The selection operation of the crossover population based on the fitness specifically includes: selecting the crossover population using a one-to-one greedy strategy based on the fitness.

[0067] Drill bit arrangement d1, d2, ..., d p The data is an ordered sequence of drill bit diameter parameters. Since the drill bit diameter is discrete data and contains decimals, real numbers are used to encode the drill bit diameters in ascending order. The dimension of each individual is equal to the number of drill bits on the drill bag, and the order is the same as the drill bit numbering order. Each compiled drill bit arrangement constitutes an individual in the drill bit arrangement population of the differential evolution algorithm. The initial drill bit arrangement population is randomly generated, and its expression is:

[0068]

[0069] Among them, X i，0 Let i be the i-th individual in the initial drill bit arrangement population (i = 1, 2, 3, ..., N, where N is the population size). and X i，0 The upper and lower bounds are defined by `rand()`, which means generating a random number within the range [0, 1].

[0070] The differential evolution algorithm first performs differential mutation on the individuals in the population. The method for calculating the new individuals in the mutated population is as follows:

[0071] V i，t+1 =X r1，t +F(X r2，t -X r3，t (7);

[0072] Where V i，t+1 X is the new individual generated from the drill bit arrangement population corresponding to the t-th iteration (t = 1, 2, 3, ..., T-1, where T is the maximum iteration number), that is, the i-th individual in the drill bit arrangement population corresponding to the (t+1)-th iteration;r1，t X r2，t and X r3，t Let r1, r2, r3 be three individuals randomly selected from the drill bit arrangement population corresponding to the t-th iteration, where r1, r2, r3 = 1, 2, 3, ..., N and are all distinct; F∈[0, 2] is the scaling factor.

[0073] The crossover operation uses the exponential crossover algorithm, and the method for calculating the new individuals generated is as follows:

[0074]

[0075] Among them, U ij，t+1 The new individual obtained by crossover is the j-th dimension component of the i-th individual in the crossover population corresponding to the (t+1)-th iteration (j = 1, 2, 3, ..., D, where D is the dimension of each individual, and each individual includes a D-dimensional component). rand(j) ∈ [0, 1] is a uniformly random number for the j-th dimension component. rand ∈[1, D] is a randomly generated natural number, and CR∈[0, 1] is the crossover probability, which determines the proportion of mutated individuals in the new individuals and satisfies an exponential distribution.

[0076] The selection strategy employs a one-to-one greedy approach, and its calculation formula is as follows:

[0077]

[0078] Among them, X i，t+1 Let f be the i-th individual in the drill bit arrangement population corresponding to the (t+1)-th iteration, and let f be the fitness function, i.e., formula (5), with the goal of maximizing it; U i，t+1 X is the i-th individual in the crossover population corresponding to the (t+1)-th iteration; i，t Let be the i-th individual in the drill bit arrangement population corresponding to the t-th iteration. The termination condition is the number of iterations required for the algorithm to essentially converge; that is, a maximum number of iterations is set, and the termination condition is satisfied when the maximum number of iterations is reached. Considering that to simplify computation, the hole combination dataset only retains drill holes that satisfy the 32mm hole position system, and some hole diameters are missing, to ensure that the optimized drill bit arrangement can process all holes, individuals that do not include all hole diameters need to be eliminated after each iteration.

[0079] The above steps involve a similar modeling and solving process for each group of datasets. Ultimately, a suitable drill bit arrangement scheme can be output for each group of datasets. Each group of datasets corresponds to an optimal drill bit arrangement solution, which is the best individual in the drill bit arrangement population corresponding to the current iteration number when the termination condition is met.

[0080] This embodiment also evaluates the optimization effect of multi-drill parallel processing, and the evaluation method is as follows:

[0081] The core objective of this embodiment is to shorten the operation time of CNC drilling and improve production efficiency. The main approach is to optimize the drill bit arrangement to achieve parallel processing with multiple drill bits, thereby reducing the number of drilling passes. Therefore, the evaluation is primarily based on comparing the number of drilling passes with the operation time. The drill bit arrangement parameters before and after optimization are input into the equipment's industrial control computer. CAM software is used to generate CNC programs for the boards before and after optimization, extracting the number of drilling passes for the front and back sides of each board. An artificial neural network is then used to predict the process operation time for each board before and after optimization, and the average of the number of drilling passes and the operation time is compared. In this embodiment, an ANN neural network can be used to predict the process operation time for each board before and after optimization.

[0082] The optimized drill bit arrangement was validated in actual production. Historical processing data of the equipment for a relatively long period of time before and after the drill bit arrangement optimization were extracted. The mean operation time was compared and an operation time distribution chart was drawn. The significance of the difference was verified by analysis of variance.

[0083] To evaluate the effectiveness of drill bit arrangement differentiation in multi-machine parallel scenarios, for the problem of limited processing range of equipment, the number of CAM software failed to generate CNC programs (i.e., exceeded the processing range) before and after drill bit arrangement optimization can be compared; for the improvement of processing efficiency, the number of drilling times and operation time when PCBs in different groups are processed by equipment with corresponding drill bit arrangements can be calculated.

[0084] This embodiment uses clustering and intelligent optimization algorithms for solving the problem. Traditional mathematical methods can also be used to obtain similar results, but with the production scale of customized furniture reaching tens of thousands, the computation time increases exponentially, making the method impractical.

[0085] This embodiment completely avoids errors caused by fixture interference during processing and overcomes the technical difficulties that can only be addressed through experience in traditional practices. It achieves matching between processing equipment parameters and the process characteristics of the processed sheet metal, significantly improving the processing efficiency of CNC drilling operations. Addressing the error problem caused by interference from machining center fixtures during the processing, under multi-machine parallel conditions, clustering and reorganizing the dataset allows for full coverage of the drilling range through differentiated drill bit arrangements, ensuring that each sheet metal is processed by at least one machine. Based on the big data of hole combination characteristics of customized furniture sheets, combined with the characteristics of the machining center's drill bit layout, an intelligent optimization algorithm enables drill bits of different diameters to be installed on appropriate drill bits, resulting in a more scientific outcome compared to existing methods that rely on simple experience-based decisions.

[0086] This embodiment starts from the actual production of large-scale customized furniture and focuses on the key process of CNC drilling. By comprehensively analyzing the operation logic of CNC drilling machining centers, it studies the basic conditions for parallel processing of multiple drill bits. Based on this, it constructs a data extraction and preprocessing method to solve the problem of missing basic data and create a dataset. Optimizing the drill bit arrangement is the main means, and intelligent optimization algorithms are used to solve the problem. On this basis, clustering algorithms are combined to further explore the operation potential under the scenario of multi-machine parallel operation and form an optimization effect evaluation method. Theoretical and practical verification is carried out using actual production data. Under the premise of ensuring the processing capacity of the equipment, the number of drilling operations is reduced, thereby shortening the processing time and improving the operation efficiency.

[0087] Example 2

[0088] A computer system includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the steps of a multi-drill parallel machining optimization method for furniture processing as described in Embodiment 1.

[0089] Example 3

[0090] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a multi-drill parallel machining optimization method for furniture processing as described in Embodiment 1.

[0091] Example 4

[0092] A computer program product includes a computer program that, when executed by a processor, implements the steps of a multi-drill parallel machining optimization method for furniture processing as described in Embodiment 1.

[0093] Example 5

[0094] A computer device, which may be a database, may have an internal structure diagram as shown below. Figure 4As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores pending transactions. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a multi-drill parallel machining optimization method for furniture processing as described in Embodiment 1.

[0095] It should be noted that the object information (including but not limited to object device information, object personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this invention are all information and data authorized by the object or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0096] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided by this invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided by this invention may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided by this invention may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0097] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0098] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for optimizing parallel machining with multiple drill bits in furniture processing, characterized in that, include: Obtain an initial dataset; the initial dataset includes several hole combinations; the drill holes in each hole combination are located on a plate; Cluster analysis is performed on the initial dataset to obtain clustering results, and the initial dataset is divided based on the clustering results to obtain several grouped datasets; the clustering results include several board combinations; For each group dataset, a multi-drill parallel processing optimization model is established based on the drill bit parameters of all drill bits on the drill bag and the drill hole parameters of each hole in all hole combinations in the group dataset. With the objective of maximizing the matching value between drill bits and drill holes for all hole combinations in the grouped dataset, the differential evolution algorithm is used to solve the multi-drill-bit parallel processing optimization model to obtain the optimal solution for the drill bit arrangement corresponding to the grouped dataset, specifically including: The drill bit parameters of each drill bit are encoded to generate an initial drill bit arrangement population; Calculate the fitness of each individual in the drill bit arrangement population corresponding to the current iteration number; the fitness is calculated by an objective function; the objective function is a function that aims to maximize the matching value between drill bits and holes for all hole combinations in the grouped dataset; Determine whether the termination condition is met; the termination condition is that the current iteration count reaches the maximum iteration count. If so, then decode the individuals in the drill bit arrangement population corresponding to the current iteration number to obtain the optimal solution for the drill bit arrangement; If not, perform a mutation operation on the individuals in the drill bit arrangement population corresponding to the current iteration number to obtain a mutated population; perform a crossover operation on the mutated population to obtain a crossover population; perform a selection operation on the crossover population according to the fitness to obtain the drill bit arrangement population corresponding to the next iteration number, update the drill bit arrangement population corresponding to the current iteration number to the drill bit arrangement population corresponding to the next iteration number, and return to the step "calculate the fitness of each individual in the drill bit arrangement population corresponding to the current iteration number"; the optimal solution of the drill bit arrangement includes the drill bit parameters of each drill bit; the drill bit parameters include the position coordinates of the drill bit on the drill bag and the drill bit diameter; the drilling parameters include the position coordinates of the drill hole on the plate and the drill hole diameter.

2. The optimized method for parallel multi-drill machining in furniture processing according to claim 1, characterized in that, Performing a crossover operation on the mutant population yields a crossover population, specifically including: The crossover population is obtained by performing a crossover operation on the mutant population using the exponential crossover algorithm.

3. The optimized method for parallel multi-drill machining in furniture processing according to claim 1, characterized in that, The selection operation for the crossover population based on the fitness specifically includes: Based on the fitness, a one-to-one greedy strategy is used to select the crossover population.

4. The optimized method for parallel multi-drill machining in furniture processing according to claim 3, characterized in that, The calculation formula for the selection operation is as follows: ； in, For the first The number of iterations corresponds to the number of drill bit permutations in the population. Individual, The fitness function; For the first The crossover population corresponding to the iteration number is the th Individual; For the first The number of iterations corresponds to the number of drill bit permutations in the population. Individual.

5. The optimized method for parallel multi-drill machining in furniture processing according to claim 1, characterized in that, The formula for calculating the matching value of drill bits and drill holes for all hole combinations in the grouped dataset is as follows: ； in, T This represents the matching values ​​of drill bits and boreholes for all hole combinations in the grouped dataset; i For the first i A combination of holes, i =1,2,3... q , q This represents the total number of hole combinations in the grouped dataset; t iu For the first i The hole combination is number one. The number of matching holes and drill bits in a matching scheme; a matching scheme is a combination of holes that are drilled simultaneously in a hole combination.

6. The optimized method for parallel multi-drill machining in furniture processing according to claim 5, characterized in that, Cluster analysis is performed on the initial dataset to obtain the clustering results, which include: The k-means algorithm was used to perform cluster analysis on the initial dataset to obtain the clustering results.

7. A computer system, comprising: The memory and processor contain a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the furniture processing multi-drill parallel machining optimization method according to any one of claims 1-6.

Images