Clustering algorithm-based surface-mounted product merging production method, system and equipment
By using clustering algorithms to classify surface-mount products into groups and automatically merge orders, the problem of low equipment utilization in surface-mount product production is solved, thereby improving production efficiency.
Patent Information
- Application Number
- CN202410806916.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-21
- Publication Date
- 2025-12-23
AI Technical Summary
The production of surface-mount products suffers from low equipment utilization and low production efficiency due to the variety of products and small batches, especially the time-consuming and complex process of changing materials.
By employing a clustering algorithm, surface-mount products are classified into product families based on their similarity. Similar orders are automatically merged before production orders are placed. By binding product family information with order information, the production scheduling process is optimized.
It improved equipment uptime and production efficiency, reduced the number of material changes, and enhanced production continuity and efficiency.
Smart Images
Figure CN121189666A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the technical field of watch and jewelry production, and particularly relates to a watch and jewelry production method, system, device and medium based on a clustering algorithm. BACKGROUND
[0002] At present, most watch and jewelry products are produced in a mode of multiple varieties and small batches. Different varieties have different production processes and different required raw materials in the processing process. The watch and jewelry machine device responsible for processing watch and jewelry products has a complex material replacement process and takes a long time when processing different products, resulting in low equipment utilization rate. Therefore, a special person needs to be arranged to perform order merging work on watch and jewelry product orders. However, multiple factors need to be considered in the merging process. If all factors are not considered, the production efficiency will be reduced. SUMMARY
[0003] The purpose of the application is to provide a watch and jewelry production method, system and device based on a clustering algorithm. Before the final production order is issued, the initial order scheduling information is automatically merged according to the set method based on the initial order scheduling information, thereby improving the production efficiency.
[0004] To achieve the above purpose, the solution of the application is as follows:
[0005] A watch and jewelry production method based on a clustering algorithm includes the following steps:
[0006] Step 1: classifying products according to the similarity of watch and jewelry products by using a clustering algorithm to form product families and classifying each product into a corresponding product family.
[0007] Step 2: obtaining initial order scheduling information, matching product family information corresponding to the product based on the order information, and binding the product family information and the order information.
[0008] Step 3: automatically merging product orders based on the binding of product family information and order product information in combination with the initial order scheduling information, and exporting the merged product orders for secondary order scheduling by the order scheduling personnel.
[0009] In step 1, a density clustering algorithm is used to group products according to the similarity of materials between the products that need to be classified. One product family is obtained by clustering and grouping.
[0010] In step 2, the initial order scheduling information includes the product name, product quantity, and order delivery date.
[0011] In step 3, it is determined whether the order contains special remarks. If the special remarks contain requirements that cannot be merged, the order is excluded from the order merging.
[0012] In step 3, based on the product family classification of the order product, the order merging condition is adjusted according to the order quantity range and the order delivery time range, and after the adjustment reaches the ideal condition, if there are order products of the same product family within the delivery time range within the working days of the merging range from the merging operation day, the order products are merged in sequence from near to far according to time.
[0013] In step 3, it is predicted whether the total working hours of the merged order after merging exceed the set single production working hour range, and if the range is exceeded, the last order merging is disassembled.
[0014] A surface-mounted product merging production system based on a clustering algorithm, comprising,
[0015] A product family construction module configured to classify products according to the similarity of surface-mounted products by a clustering algorithm to form product families, and classify each product into a corresponding product family;
[0016] An order acquisition module configured to acquire preliminary order scheduling information, match product family information corresponding to the product based on the order information, and bind the product family information with the order information; and
[0017] An order merging module configured to automatically merge product orders based on the binding of product family information and order product information, in combination with the preliminary order scheduling information, and export the merged product orders for secondary order scheduling by scheduling personnel.
[0018] An electronic device comprising 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 the surface-mounted product merging production method based on the clustering algorithm.
[0019] A computer-readable storage medium storing a computer program; the computer program is executed by a processor to implement the steps of the surface-mounted product merging production method based on the clustering algorithm.
[0020] After adopting the above scheme, the preliminary scheduling order information is analyzed, the order merging setting condition is combined, and before the final surface-mounted product production order is issued, the small batch similar orders are automatically merged according to the set condition according to the preliminary scheduling order information, the number of line changes in the surface-mounted production process is reduced, and the equipment utilization rate and production efficiency are improved. BRIEF DESCRIPTION OF DRAWINGS
[0021] Figure 1 is a clustering algorithm model schematic diagram in the method of the application;
[0022] Figure 2 is a flow chart of the method of the present application;
[0023] Figure 3 is a module schematic block diagram of the system of the present application. DETAILED DESCRIPTION
[0024] The technical solutions and beneficial effects of the present application will be described in detail below with reference to the accompanying drawings.
[0025] As shown in Figure 2 , the present application provides a surface-mounted product combined production method based on clustering algorithm, comprising the following steps:
[0026] Step 1: classify products according to the similarity of surface-mounted products by clustering algorithm, form product families, and classify each product into the corresponding product family;
[0027] In step 1, in the process of constructing product families, the characteristics of surface-mounted products are combined with the attributes of surface-mounted product materials, chip mounter feeders and material bins, and the clustering algorithm is used to group the products according to the similarity of the materials between the products that need to be classified. One group of clustering grouping results is a product family. The product family information library includes the corresponding relationship of each product and the product family. The materials required for the surface-mounted production process of each product in the same product family are relatively similar.
[0028] Among them, the direct relationship between surface-mounted products and chip mounters, chip mounter feeders and material bins is that the chip mounter feeder sucks the material and pastes it onto the surface-mounted product during the pasting process, and one feeder corresponds to one or two materials according to the size of the material. The chip mounter material bin is used to store the chip mounter feeder, and the feeder works by linking the chip mounter. Usually one chip mounter corresponds to four material bins, one material bin contains multiple slots, and one slot corresponds to one chip mounter feeder.
[0029] In the product family classification process, the clustering algorithm is used to group the materials according to the similarity between the materials of each type required for analysis, and flexible grouping is formed according to the actual production needs and the slot occupancy of the material bin. Based on the maximum capacity of the material bin set before grouping, the material slot occupancy after grouping is as close to the maximum capacity as possible and less than the maximum capacity. The materials in the group completely cover the production needs of the corresponding types in the group, improve the production continuity, and realize the product family screening and grouping function.
[0030] The clustering algorithm in the product family classification process first determines the number of groups, the upper limit of the slot position corresponding to each group, and the range of the card type, and uses the density clustering algorithm to cluster and group the analysis card target. In the clustering and grouping process, all material types covered by each type of card in the analysis range are first considered as a coordinate axis. If a certain type contains the material, the value of the type in the coordinate axis of the material type is 1, otherwise it is 0. If there are N types of materials covered by each type of card in the analysis range, the corresponding coordinate system has N dimensions, which can be matched with the clustering algorithm model shown in Figure 1 .
[0031] The implementation of the clustering algorithm model requires adjustment of two parameters: the maximum distance d between two acceptable points and the number n of elements required in each group. For example, assume that there are seven types of cards (each point represents a type), and three types of materials (material 1, material 2, and material 3), as shown in Figure 1 . According to the clustering strategy, if d<1 and n>1, all points are divided into meaningless groups, i.e., there is no available classification, the maximum distance between two acceptable points is too small, and the classification fails. If d<2 and n>1, all points are divided into meaningful groups, no type is in the meaningless group, and all types are divided into effective groups. However, due to the large maximum distance between two acceptable points, all elements are included, and such grouping is meaningless. Similarly, if the value range of d is reasonable, but the number n of elements required in each group is too large, all points will be divided into meaningless groups, and the classification will fail. If the value range of d is reasonable, but the number n of elements required in each group is too small, the classification that can be combined into a group will be displayed separately, reducing the grouping efficiency.
[0032] Further, after analyzing each type, each type has its corresponding unique spatial coordinate point in the coordinate system. According to the distance between points, points with small distances are clustered, and points with large distances are clustered into new classes. The definition of distance and the range of points (and types) covered by each class can be defined according to actual production requirements.
[0033] According to the clustering algorithm results, select the group closest to the slot number as a group of trolleys. For the above trolley group, compare the material types corresponding to the types not included in the trolley group with the material types included in the trolley group, and fill the trolley group slot to the extent that it will exceed the slot limit. Then, the trolley grouping is completed. Similarly, after each group completes the above cycle, the clustering and grouping are completed, and the grouping result is the product family grouping situation.
[0034] In the product family information library construction process, the product model information of the embodiment needs to query the corresponding stored material table file in the Mysql database, and the material table file includes the material details required by the product. After entering the database to read the corresponding material table information, the corresponding bin slot occupancy information bound with the material is obtained in the database, and each binding information is stored. By using a clustering algorithm, the materials are grouped according to the similarity of the materials between each type required for analysis. The grouped material slot occupancy is as close to the maximum capacity as possible and less than the maximum capacity, and the materials in the group completely cover the production needs of the corresponding type in the group. According to the grouping situation, the final product family information library is constructed.
[0035] Step 2, obtaining preliminary order scheduling information, matching product corresponding product family information based on the order information, and binding the product family information with the order information;
[0036] The preliminary order scheduling information includes product name, product quantity, and order delivery date.
[0037] In this embodiment, the preliminary order scheduling information can be manually input or imported from the order management system. The obtained order information includes product name, product quantity, and order delivery period, etc. At the same time, it is identified whether the order contains special remarks. If the special remarks exist and cannot meet the requirements of order merging, such orders are excluded from order merging.
[0038] After obtaining the preliminary order scheduling information, the product family information corresponding to the product can be searched from the product family information library according to the product name in the order information, and the product family information is bound with the order information, so that each order product is classified into each product family.
[0039] Step 3, based on the binding of product family information and order product information, combining the preliminary order scheduling information, automatically merging the product orders, and exporting the merged product orders for secondary order scheduling by the scheduling personnel;
[0040] After obtaining the information required for order merging, based on the product family classification of order products, according to the order quantity range and the order delivery time range, the order merging conditions are adjusted. After adjusting to the ideal conditions, within the working days of the merging range from the merging operation day, if there are order products of the same product family within this period, the orders are merged in order from near to far.
[0041] At the same time, during the order merging process, for the merging process of the same product family, after each merging, it is necessary to predict whether the total production time of the merged order after merging exceeds the set single production time range. If it exceeds the range, the last order merging is disassembled.
[0042] The system merges the preliminary production orders according to the set rules, exports the merged orders, and the merged orders can be exported to the production scheduling personnel or a third-party production scheduling system for secondary production scheduling work, and the production line produces according to the secondary production scheduling plan.
[0043] As shown in Figure 3 The embodiment of the present application also provides a table product merging production system based on a clustering algorithm, which comprises:
[0044] A product family construction module is configured to classify products according to the similarity of table products by a clustering algorithm, form product families, and classify each product into a corresponding product family.
[0045] An order acquisition module is configured to acquire preliminary order scheduling information, match product family information corresponding to the product based on the order information, and bind the product family information and the order information.
[0046] An order merging module is configured to automatically merge product orders based on the binding of the product family information and the order product information in combination with the preliminary order scheduling information, export the merged product orders, and provide the production scheduling personnel for secondary order scheduling.
[0047] The embodiment of the present application also provides an electronic device, which comprises a processor and a memory configured to store a computer program capable of running on the processor; wherein the processor is configured to run the computer program to execute the steps of the table product merging production method based on the clustering algorithm in the foregoing embodiment.
[0048] In actual application, the processor comprises a field-programmable gate array (FPGA), and the processor can be a central processing unit (CPU) or a digital signal processor (DSP). It can be understood that for different devices, the electronic device for realizing the function of the processor can also be other devices, and the embodiment of the present application is not limited in this regard.
[0049] The above-mentioned memory can be a volatile memory, such as a random-access memory (RAM), or a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk (HDD) or a solid-state disk (SSD), or a combination of the above-mentioned memories, and provides instructions and data to the processor.
[0050] In the exemplary embodiments, the present application also provides a computer readable storage medium for storing a computer program, which, when executed, implements the above-mentioned clustering algorithm-based table product merging production method.
[0051] Optionally, the computer readable storage medium can be applied to any one of the methods of the embodiments of the present application, and the computer program causes the computer to execute the corresponding processes realized by the processor in each method of the embodiments of the present application. For the sake of brevity, details are not repeated here.
[0052] In the several embodiments of the present application, it should be understood that the disclosed device and method can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the various components shown or discussed can be through some interface, indirect coupling or communication connection between devices or units, which can be electrical, mechanical or in other forms.
[0053] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application can be implemented in various computer languages, such as object-oriented programming languages Java and interpreted scripting languages JavaScript.
[0054] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams block or blocks. Figure 1 Figure 1
[0055] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart illustrations and / or block diagrams block or blocks. Figure 1 Figure 1
[0056] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart illustrations and / or block diagrams block or blocks. Figure 1 Figure 1
[0057] While the preferred embodiments of the application have been described, it should be understood that various modifications and changes can be made by those skilled in the art which follow in the spirit of the application. Accordingly, the drawings and descriptions are to be regarded as illustrative in nature and not as restrictive.
[0058] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.
Claims
1. A method for merging surface-mount products based on clustering algorithms, characterized in that... Includes the following steps: Step 1: Classify products based on the similarity of the products on the table using a clustering algorithm to form product families, and classify each product into the corresponding product family; Step 2: Obtain preliminary order scheduling information, match the product family information corresponding to the product based on the order information, and bind the product family information to the order information; Step 3: Based on the binding of product family information and order product information, and combined with the preliminary order scheduling information, automatically merge the product orders and export the merged product orders for scheduling personnel to perform secondary order scheduling.
2. The method as described in claim 1, characterized in that: In step 1, a density clustering algorithm is used to group products based on the similarity of materials between them, and each group of clustering results constitutes a product family.
3. The method as described in claim 1, characterized in that: In step 2, the preliminary order scheduling information includes the product name, product quantity, and order delivery date.
4. The method as described in claim 1, characterized in that: In step 3, it is determined whether the order contains special remarks. If the special remarks contain requirements that prevent the orders from being merged, then such orders are excluded from order merging.
5. The method as described in claim 1, characterized in that: In step 3, based on the product family classification of the order products, the order merging conditions are adjusted according to the order quantity range and the order delivery time range. After the adjustment reaches the ideal conditions, within the merging range working days from the merging operation date, if there are order products of the same product family with delivery dates within this period, the orders are merged in order of time from the nearest to the oldest.
6. The method as described in claim 1, characterized in that: In step 3, it is predicted whether the total production time of the merged order exceeds the set range of single production time. If it exceeds the range, the most recent merged order will be broken up.
7. A production system for merging surface-mount products based on clustering algorithms, characterized in that: include, The product family building module is configured to classify products based on the similarity of the products on the table using a clustering algorithm, forming product families and assigning each product to the corresponding product family. The order acquisition module is configured to acquire preliminary order scheduling information, match product family information corresponding to the product based on the order information, and bind the product family information to the order information; and, The order merging module is configured to automatically merge product orders based on the binding of product family information and order product information, combined with the initial order scheduling information, and export the merged product orders for scheduling personnel to perform secondary order scheduling.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor; characterized in that: When the processor executes the computer program, it implements the steps of the method for merging production of surface-mount products based on clustering algorithms as described in any one of claims 1 to 6.
9. A computer-readable storage medium storing a computer program; characterized in that: When the computer program is executed by the processor, it implements the steps of the method for merging production of surface-mount products based on clustering algorithms as described in any one of claims 1 to 6.