Intelligent process identification and piecework method, system, terminal and medium of sewing equipment

Abstract

The application provides a sewing equipment intelligent process identification and piecework method and system, a terminal and a medium. An electric signal converted from mechanical movement of sewing equipment is acquired, and corresponding sewing data based on time sequence is generated according to the electric signal. The sewing data is reduced to two dimensions, including a time interval dimension of each action of a motor in the sewing equipment and a corresponding sewing needle number dimension. The process type of the sewing data is judged, and a process template is determined. The selection of a piecework segmentation point is performed on the sewing data to be segmented according to the motor movement time interval of the process template to perform piecework. The application can identify the process corresponding to the data in a plurality of known process templates, reduces additional manpower, only collects electric signals in a sewing machine, reduces data collection requirements, accurately judges the starting and ending points of each piece, improves the accuracy of the segmentation point by using a dynamic time warping method, is suitable for long processes and short processes, and has a broad market prospect.

Description

Technical Field

[0001] This application relates to the field of sewing technology, and in particular to intelligent process identification and piece counting methods, systems, terminals and media for sewing equipment. Background Technology

[0002] Piece-rate payment is a widely used wage calculation method in factories today, and how to accurately and efficiently calculate piecework has been a subject of ongoing research. Currently, the main intelligent piecework calculation methods are worker-scanned barcodes and hanging systems. Both of these methods require frequent additional operations by workers, resulting in low efficiency, and hanging systems are also costly. Barcode scanning requires that the QR codes be kept intact and not lost or damaged. Therefore, how to enable sewing machines to automatically calculate piecework has become a key research focus.

[0003] Current automatic piece-counting methods for sewing machines still require data collection such as the number of stitches, thread trimmings, presser foot lifting signals, reinforcement seam status, and infrared probe signals indicating the presence or absence of fabric (e.g., patents CN102704214A, CN107345346B). Furthermore, they require prior knowledge of the worker's specific work process (e.g., patents CN107345346B, CN104018300A). All of this necessitates specialized manual operation, increases the computational load, and significantly reduces efficiency. In addition, some current piece-counting methods have specific application requirements for each work process, such as a requirement that the total number of stitches within a process be less than 400, limiting their applicability (e.g., patent CN104018300A). Moreover, current common piece-counting methods only focus on the number of sewn pieces, neglecting the accuracy of the start and end points for each piece. This makes it impossible to accurately record the worker's actual working status and provides no basis for further detailed analysis of the worker's skill level.

[0004] To address these issues and improve efficiency, enabling data to play a greater role in subsequent research and analysis, a simpler, more universal, and more accurate intelligent piece-rate method is needed. Summary of the Invention

[0005] In view of the shortcomings of the prior art described above, the purpose of this application is to provide an intelligent process identification and piece counting method, system, terminal and medium for sewing equipment, so as to solve the problems of low efficiency and low accuracy of sewing piece counting in the prior art.

[0006] To achieve the above and other related objectives, a first aspect of this application provides an intelligent process identification and piece counting method for sewing equipment, comprising: acquiring electrical signals converted from the mechanical motion of the sewing equipment, and generating corresponding time-series-based sewing data based on the electrical signals; reducing the dimensionality of the sewing data to two dimensions, including the time interval dimension of each motor movement in the sewing equipment and the corresponding number of sewing needles; determining the process type to which the sewing data belongs and determining the corresponding process template based on the time interval dimension of each motor movement in the sewing equipment and the corresponding number of sewing needles; after determining the process template, selecting piece counting segmentation points for the sewing data to be segmented based on the motor movement time interval of the process template for piece counting.

[0007] In some embodiments of the first aspect of this application, determining the process type of the sewing data and determining the corresponding process template based on the time interval dimension of each motor action in the sewing equipment and the corresponding number of sewing stitches includes: extracting data segments of appropriate length from the sewing data according to the length of different process templates for comparison with the process templates; predicting whether the process template is divisible based on the pause point of each motor action in each process template, and dividing the divisible process template into multiple sub-processes; for divisible process templates, if the data segments being compared can also be divided according to the time interval of each motor action... If the data segment is divided into the same number of segments, the divisible process template is stored in the candidate library. Each sub-segment divided from the data segment and each sub-process divided from the divisible process template are paired to form a comparison group for similarity calculation. The similarity calculation results of each comparison group are summed to obtain the total similarity calculation result between the divisible process template and the corresponding data segment. For indivisible process templates, the indivisible process template is stored in the candidate library, and the similarity between it and the corresponding data segment is calculated for comparison. The process template with the smallest difference from the input sewing data is selected from the candidate library as the process template for the sewing data.

[0008] In some embodiments of the first aspect of this application, the step of forming comparison groups with each sub-segment divided from the data segment and each sub-process divided from the divisible process template for similarity calculation includes calculating the degree of difference between the two in terms of the number of stitches and the number of sewing segments based on a dynamic time-rounding algorithm.

[0009] In some embodiments of the first aspect of this application, the first few sewing data items in the incoming sewing data are compared and detected, including comparing the first few sewing data items with the average similarity of each process template; if the deviation is too large, it can be determined that a deviation has occurred; if there is no deviation or the deviation is small, it can be determined that no deviation has occurred.

[0010] In some embodiments of the first aspect of this application, the step of selecting the piece-counting dividing point for the sewing data to be divided according to the motor movement time interval of the process template for piece counting includes: dividing the process template into long process templates and short process templates according to the different lengths of the process template.

[0011] In some embodiments of the first aspect of this application, the piece counting process for a long process template includes: initially screening multiple suspected segmentation points by comparing the motor movement time interval of the process template with a threshold; for each suspected segmentation point initially screened, calculating the similarity between the segment and the data in the process template, and selecting the suspected segmentation point with the highest similarity as the final piece counting segmentation point; and readjusting the piece counting segmentation point according to the beginning and end features of the process template to determine whether the piece counting segmentation point is indeed the end point of the sewn part in the template.

[0012] In some embodiments of the first aspect of this application, the piece-counting process for short process templates includes: calculating the degree of difference between the data from the starting point to each suspected dividing point and the template data, and selecting the suspected dividing point with the smallest difference as the final piece-counting dividing point.

[0013] To achieve the above and other related objectives, a second aspect of this application provides an intelligent process identification and piece counting system for sewing equipment, comprising: an acquisition module for acquiring electrical signals converted from the mechanical motion of the sewing equipment, and generating corresponding time-series-based sewing data based on the electrical signals; a dimensionality reduction module for reducing the dimensionality of the sewing data to two dimensions, including the time interval dimension of each motor movement in the sewing equipment and the corresponding number of sewing needles; a template module for determining the process type of the sewing data and determining the corresponding process template based on the time interval dimension of each motor movement in the sewing equipment and the corresponding number of sewing needles; and a piece counting module for selecting piece counting segmentation points for the sewing data to be segmented based on the motor movement time interval of the process template after determining the process template.

[0014] To achieve the above and other related objectives, a third aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements an intelligent process identification and piece counting method for the sewing equipment.

[0015] To achieve the above and other related objectives, a fourth aspect of this application provides an electronic terminal, comprising: a processor and a memory; the memory for storing a computer program, and the processor for executing the computer program stored in the memory, so that the terminal executes the intelligent process identification and piece counting method of the sewing equipment.

[0016] As described above, the intelligent process identification and piece counting method, system, terminal, and medium for sewing equipment of this application have the following beneficial effects:

[0017] (1) The process corresponding to the data can be identified from multiple known process templates. This eliminates the need to set or modify the template every time a process is changed, thus reducing additional manpower and lowering costs.

[0018] (2) Only the electrical signals in the sewing machine need to be collected: the data on the number of sewing needles when the motor is moving, the data in time series is recorded and calculated. This greatly reduces the requirements for data collection and recording, while also reducing the data transmission load and the complexity of subsequent calculations.

[0019] (3) The start and end points of each piece were accurately determined, which indirectly helped to improve the accuracy of piece counting, and at the same time provided a basis for further detailed analysis of the workers' technical level.

[0020] (4) The dynamic time warping method is adopted. This method is widely used in template matching problems, but it has not been applied to piece-counting algorithms in previous patent literature. By using this method, the accuracy of the segmentation points is improved.

[0021] (5) It is applicable to both long and short processes, expanding the scope of application of processes and having broad market prospects. Attached Figure Description

[0022] Figure 1 The diagram shown is a schematic diagram of one embodiment of this application.

[0023] Figure 2 The diagram shown is a schematic diagram of one embodiment of this application.

[0024] Figure 3 The diagram shown is a schematic representation of the process identification process in one embodiment of this application. Figure 4 The diagram shown is a structural schematic of an intelligent process identification and piece counting system for a sewing equipment according to an embodiment of this application. Figure 5 The diagram shown is a structural schematic of an electronic terminal according to an embodiment of this application. Detailed Implementation

[0025] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0026] It should be noted that in the following description, reference is made to the accompanying drawings, which illustrate several embodiments of this application. It should be understood that other embodiments may also be used, and changes in mechanical composition, structure, electrical system, and operation may be made without departing from the spirit and scope of this application. The following detailed description should not be considered limiting, and the scope of the embodiments of this application is defined only by the claims of the published patent. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application. Spatially related terms, such as “upper,” “lower,” “left,” “right,” “below,” “below,” “lower part,” “above,” “upper part,” etc., may be used herein to illustrate the relationship between one element or feature shown in the figures and another element or feature.

[0027] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," "fixing," and "holding" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0028] Furthermore, as used herein, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context indicates otherwise. It should be further understood that the terms “comprising,” “including,” indicate the presence of the stated feature, operation, element, component, item, kind, and / or group, but do not preclude the presence, occurrence, or addition of one or more other features, operations, elements, components, items, kinds, and / or groups. The terms “or” and “and / or” as used herein are interpreted as inclusive, or mean any one or any combination thereof. Thus, “A, B, or C” or “A, B, and / or C” means “any one of: A; B; C; A and B; A and C; B and C; A, B, and C.” Exceptions to this definition arise only when combinations of elements, functions, or operations are inherently mutually exclusive in some manner.

[0029] To address the problems mentioned above, this invention provides an intelligent process identification and piece counting method, system, terminal, and storage medium for sewing equipment. By inputting a segment of sewing machine operation data belonging to the same type of process, and based on the recorded sewing machine operating status and stitch count, the method first identifies which process the sewing machine is performing. Then, it performs piece counting analysis based on the process template, while simultaneously recording the start and end points of each piece, thereby achieving efficient and accurate intelligent piece counting.

[0030] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for explaining the present invention and are not intended to limit the invention.

[0031] like Figure 1 The diagram illustrates a flowchart of an intelligent process identification and piece-counting method for a sewing device according to an embodiment of the present invention. It should be understood that the intelligent process identification and piece-counting method in this embodiment can be applied to computer devices, such as computers, laptops, tablets, smartphones, smart bracelets, smartwatches, smart helmets, smart TVs, etc.; it can also be applied to servers, which can be deployed on one or more physical servers based on factors such as function and load, or can be composed of distributed or centralized server clusters.

[0032] In this embodiment, the intelligent process identification and piece counting method of the sewing equipment mainly includes the following steps, which will be explained in detail below with specific examples.

[0033] Step S11: Obtain the electrical signal converted from the mechanical motion of the sewing equipment, and generate corresponding time-series-based sewing data based on the electrical signal.

[0034] Specifically, the gateway device receives electrical signals converted from the mechanical movements of various parts of the sewing machine, processes these signals into data about the specific movements of each part (such as the motor) at a specific time, and uploads this data to the platform (i.e., the aforementioned computer device or server) according to a time axis sequence. It should be understood that the gateway device, also known as an internetwork connector or protocol converter, implements network interconnection at the network layer and is a complex network interconnection device, acting as a computer system or device responsible for conversion.

[0035] Step S12: Reduce the dimensionality of the sewing data to two dimensions, including the time interval dimension of each motor action in the sewing equipment and the corresponding number of sewing needles. After dimensionality reduction, the data structure becomes more reasonable, reducing subsequent computation time and facilitating process identification and piece counting calculations.

[0036] In some examples, the sewing data includes multiple dimensions before dimensionality reduction. In addition to the retained dimensions of the time interval between each motor movement and the corresponding number of sewing stitches, it may also include parameters such as sewing row spacing, stitch length, and thread length.

[0037] Step S13: Based on the time interval of each motor action in the sewing equipment and the corresponding number of sewing stitches, determine the process type of the sewing data and identify the corresponding process template; specific steps include:

[0038] First, data segments of appropriate length are extracted from the sewing data according to the length of different process templates for comparison with the process templates; then, the process template is predicted to be divisible based on the pause point of each motor action in each process template, and the divisible process template is divided into multiple sub-processes.

[0039] For a divisible process template, if the data segment being compared can also be divided into the same number of segments according to the time interval of each motor action, then the divisible process template is stored in the candidate library, and each sub-segment divided from the data segment and each sub-process divided from the divisible process template are correspondingly formed into comparison groups for similarity calculation. The similarity calculation results of each comparison group are accumulated to obtain the total similarity calculation result between the divisible process template and the corresponding data segment.

[0040] For example, a divisible process template A is divided into three sub-processes: sub-process A1, sub-process A2, and sub-process A3. Data segment B, used for comparison with template A, can also be divided into three sub-segments: sub-segment B1, sub-segment B2, and sub-segment B3. Sub-process A1 and sub-segment B1 form the first comparison group, sub-process A2 and sub-segment B2 form the second comparison group, and sub-process A3 and sub-segment B3 form the third comparison group. The similarity calculation results for each comparison group are calculated separately; for example, the calculated values ​​are C1, C2, and C3. Therefore, the similarity result between the divisible process template A and data segment B should be (C1 + C2 + C3).

[0041] It should be noted that during the process identification, it is also possible to directly compare the template processes without dividing them into segments. The specific steps are as follows: based on the length of the templates for different processes, different lengths are extracted from the input data and compared with the templates in terms of similarity in dimensions such as the total number of stitches, the number of stitches sewn during each motor movement, and the corresponding number of stitches in the template. The template with the smallest difference is selected as the template for the input data.

[0042] In some examples, the statement that each sub-segment divided from the data segment and each sub-process divided from the divisible process template form a comparison group for similarity calculation refers to calculating the degree of difference between the two in terms of the number of stitches, the number of sewing segments, etc.

[0043] The aforementioned similarity calculation can employ similarity or distance functions suitable for time series data. In this method, the similarity assessment of the number of stitches during motor movement and the number of stitches in the template in the sewing machine data uses Dynamic Time Warping (DTW). DTW is a dynamic time warping algorithm that can be used to measure the similarity between two independent time series. DTW is widely used in template matching problems and can effectively solve the problem of comparing two sets of data due to their different lengths. In DTW, the distance is determined using Euclidean distance. It should also be noted that while Euclidean distance is used in DTW, Manhattan distance can also be used for calculation.

[0044] For indivisible process templates, the indivisible process templates are stored in a candidate library, and the similarity between them and the corresponding data segments is calculated for comparison. Specifically, the data segments and process templates can be compared in terms of similarity to dimensions such as the total number of stitches, the number of stitches sewn per motor run, and the corresponding number of stitches in the process template.

[0045] At this point, one or more process templates have been stored in the candidate library. These process templates may be indivisible or divisible, but regardless of whether they are divisible or indivisible, they all have a corresponding similarity calculation result. From the candidate library, the process template with the smallest difference from the input sewing data (i.e., the highest similarity) is selected as the process template for that sewing data.

[0046] Furthermore, to avoid deviations in process data due to human error or other unnecessary reasons, i.e., to reduce the probability of errors—for example, some novice workers, due to their lack of experience, might mistakenly identify the first piece's sewing data as an incorrect template (when it is actually correct), leading to an increased error rate—this embodiment preferably compares and checks the first few sewing data items in the input sewing data. Specifically, it compares these first few sewing data items with the average similarity of each process template. If the deviation is too large, it can be determined that a deviation has occurred; if there is no deviation or the deviation is small, it can be determined that no deviation has occurred.

[0047] To facilitate understanding of the process identification in this embodiment by those skilled in the art, in addition to the above textual explanation, the following are also provided: Figure 2 To aid understanding, the process shown in the diagram is actually recorded in step S13 and its explanation.

[0048] Step S14: After determining the process template, select the piece-counting dividing point for the sewing data to be divided according to the motor movement time interval of the process template.

[0049] Preferably, the process templates are divided into long process templates and short process templates according to their different lengths. Different methods are used to count the pieces for the long process templates and the short process templates. This is because for long process templates, errors can be accumulated. If an error occurs in the initial piece counting, the error will continue to accumulate, and the final piece counting result will inevitably have a huge deviation.

[0050] The piece-rate process for long-process templates is as follows:

[0051] First, after comparing the motor movement time interval of the process template with the threshold, several suspected dividing points are initially screened as possible dividing points between pieces. It should be understood that the so-called dividing points between pieces are used to distinguish two different sewn pieces, so the number of dividing points determines the piece counting result.

[0052] Subsequently, for each suspected segmentation point identified in the initial screening, the similarity between the segmentation segment and the data in the process template is calculated, and the suspected segmentation point with the highest similarity is selected as the final piece-counting segmentation point. Specifically, the total number of stitches from each starting point to the suspected segmentation point is calculated. If the total number of stitches meets the target number of stitches (which is set based on the process template data), then the similarity between the number of sewing stitches during each motor movement and the corresponding number of stitches in the process template is used as the primary factor, supplemented by dimensions such as the total number of stitches and the number of sewing segments, to calculate the degree of difference between the data from the starting point to each suspected segmentation point and the template data. The segmentation point with the smallest calculation result is selected as the end point of one piece (i.e., the piece-counting segmentation point) for piece counting.

[0053] Furthermore, to avoid misjudgment of piecework division points due to certain special circumstances, this embodiment adds the following technical means: The piecework division point is readjusted based on the beginning and ending features of the process template to determine whether it is indeed the end point of the sewn part in the template. This can be done by comparing it with the beginning / ending features of the template from dimensions such as time interval or stitch count. For example, some processes require sewing a pair of trouser legs, so one piece is considered complete only after sewing both trouser legs. However, since the sewing data mapped to each trouser leg is completely symmetrical, it is highly likely that the piecework division point will be mistakenly identified when the first trouser leg is completed (i.e., both trouser legs are considered complete when one trouser leg is sewn). Therefore, it is necessary to compare the piecework division point with the beginning and ending features of the process template.

[0054] For short-process templates, the difference between the data from the starting point to each suspected dividing point and the template data can be calculated directly from dimensions such as the total number of stitches and the number of sewing segments. The suspected dividing point with the smallest difference (i.e. the highest similarity) is selected as the final piece-count dividing point.

[0055] It should be noted that different methods can be used for piecework segmentation in the piecework process. Given a defined starting point, select all points where the total stitch count of the sewing machine data meets the target stitch count range at the ending point. For each ending point, extract the data to be compared and calculate its difference from the template (calculation method is the same as the original method). For the point with the smallest calculated value, select the point with the closest time and that meets the time interval requirement as the end point of that piece. Alternatively, in the piecework process, finding the segmentation points between pieces can also be done by first segmenting the template, then finding the corresponding sub-processes in the data, and finally combining the sub-processes into a complete set of process data corresponding to the template, thus completing the piecework segmentation.

[0056] To facilitate understanding of the process identification in this embodiment by those skilled in the art, in addition to the above textual explanation, the following are also provided: Figure 3 To aid understanding, the process shown in the diagram is actually recorded in step S14 and its explanation.

[0057] like Figure 4 The diagram shows a structural schematic of an intelligent process identification and piece counting system for a sewing machine according to an embodiment of the present invention. The intelligent process identification and piece counting system 400 of this embodiment includes: an acquisition module 401, a dimensionality reduction module 402, a template module 403, and a piece counting module 404.

[0058] The acquisition module 401 is used to acquire electrical signals converted from the mechanical motion of the sewing equipment, and generate corresponding time-series-based sewing data based on the electrical signals; the dimensionality reduction module 402 is used to reduce the dimensionality of the sewing data to two dimensions, including the time interval dimension of each motor action in the sewing equipment and the corresponding number of sewing needles; the template module 403 is used to determine the process type of the sewing data and determine the corresponding process template based on the time interval dimension of each motor action in the sewing equipment and the corresponding number of sewing needles; the piece counting module 404 is used to select piece counting division points for the sewing data to be divided according to the motor motion time interval of the process template after determining the process template.

[0059] It should be noted that the implementation method of the intelligent process identification and piece counting system in this embodiment is similar to that of the intelligent process identification and piece counting method described above, so it will not be repeated here.

[0060] It should be understood that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. For example, the piece counting module can be a separate processing element, or it can be integrated into a chip in the above device. Alternatively, it can be stored as program code in the memory of the above device, and its functions can be called and executed by a processing element of the device. The implementation of other modules is similar. Moreover, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element mentioned here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0061] For example, these modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more digital signal processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together to form a system-on-a-chip (SOC).

[0062] like Figure 5 The diagram illustrates the structure of an electronic terminal according to an embodiment of the present invention. The electronic terminal provided in this example includes: a processor 51, a memory 52, and a communicator 53. The memory 52 is connected to the processor 51 and the communicator 53 via a system bus and communicates with them. The memory 52 stores computer programs, the communicator 53 communicates with other devices, and the processor 51 runs the computer programs, enabling the electronic terminal to execute the various steps of the intelligent process identification and piece counting method for the sewing equipment described above.

[0063] The system bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in the diagram, but this does not indicate that there is only one bus or one type of bus. The communication interface is used to enable communication between the database access device and other devices (e.g., clients, read-write libraries, and read-only libraries). Memory may include Random Access Memory (RAM) and may also include non-volatile memory, such as at least one disk storage device.

[0064] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0065] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the intelligent process identification and piece counting method of the sewing equipment.

[0066] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented using computer program-related hardware. The aforementioned computer program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0067] In the embodiments provided in this application, the computer-readable and writable storage medium may include read-only memory, random access memory, EEPROM, CD-ROM or other optical disc storage devices, disk storage devices or other magnetic storage devices, flash memory, USB flash drive, portable hard drive, or any other medium capable of storing desired program code in the form of instructions or data structures and accessible by a computer. Additionally, any connection may be appropriately referred to as a computer-readable medium. For example, if instructions are transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of the medium. However, it should be understood that computer-readable and writable storage media and data storage media do not include connections, carrier waves, signals, or other transient media, but are intended for non-transient, tangible storage media. The disks and optical discs used in the application include compact discs (CDs), laser discs, optical discs, digital multifunction discs (DVDs), floppy disks, and Blu-ray discs, where disks typically copy data magnetically, while optical discs use lasers to copy data optically.

[0068] In summary, this application provides an intelligent process identification and piece-counting method, system, terminal, and medium for sewing equipment. This invention can identify the process corresponding to the data from multiple known process templates, eliminating the need to set or modify templates each time a process changes, thus reducing additional manpower and costs. It only requires collecting electrical signals from the sewing machine: data on the number of stitches during motor movement, recording the data in its time series, and performing calculations. This significantly reduces the requirements for data collection and recording, while also reducing the data transmission load and the complexity of subsequent calculations. Accurate determination of the start and end points of each piece indirectly helps improve piece-counting accuracy and provides a basis for further detailed analysis of worker skill levels. It adopts a dynamic time warping method, widely used in template matching problems but not previously applied to piece-counting algorithms in patent literature. This method improves the accuracy of segmentation points and is applicable to both long and short processes, expanding the scope of process application and possessing broad market prospects. Therefore, this application effectively overcomes the various shortcomings of existing technologies and has high industrial applicability.

[0069] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method for intelligent process identification and piece counting in sewing equipment, characterized in that, include: The electrical signals converted from the mechanical motion of the sewing equipment are acquired, and corresponding time-series-based sewing data are generated based on the electrical signals. The sewing data is reduced to two dimensions, including the time interval dimension of each motor action in the sewing equipment and the corresponding number of sewing needles. Based on the time interval of each motor movement in the sewing equipment and the corresponding number of sewing needles, the process type of the sewing data is determined and the corresponding process template is identified; including: According to the length of different process templates, extract data segments of appropriate length from the sewing data for comparison with the process templates; Based on the pause point of each motor action in each process template, predict whether the process template is divisible, and divide the divisible process template into multiple process segments; For a divisible process template, if the data segment being compared can also be divided into the same number of segments based on the time interval of each motor action, then the divisible process template is stored in a candidate library. Each sub-segment divided from the data segment and each sub-process divided from the divisible process template are then paired to form comparison groups for similarity calculation. The similarity calculation results of each comparison group are summed to obtain the total similarity calculation result between the divisible process template and the corresponding data segment. The process of forming comparison groups based on each sub-segment divided from the data segment and each sub-process divided from the divisible process template for similarity calculation includes calculating the degree of difference between the two in terms of the number of stitches and the number of sewing segments based on a dynamic time-normalization algorithm. For indivisible process templates, the indivisible process templates are stored in the candidate library, and the similarity between them and the corresponding data segments is calculated for comparison. Select the process template with the smallest difference from the input sewing data from the candidate library as the process template for the sewing data; After determining the process template, the piece-counting dividing points are selected based on the motor movement time interval of the process template for the sewing data to be divided.

2. The intelligent process identification and piece counting method for sewing equipment according to claim 1, characterized in that, The first few sewing data items in the input sewing data are compared and checked, including comparing these first few sewing data items with the average similarity of each process template; if the deviation is too large, it can be determined that a deviation has occurred; if there is no deviation or the deviation is small, it can be determined that no deviation has occurred.

3. The intelligent process identification and piece counting method for sewing equipment according to claim 1, characterized in that, The step of selecting the piece-counting dividing point for the sewing data to be divided according to the motor movement time interval of the process template for piece counting includes: dividing the process template into long process templates and short process templates according to the different lengths of the process template.

4. The intelligent process identification and piece counting method for sewing equipment according to claim 3, characterized in that, The piece-rate process for long-process templates includes: After comparing the motor movement time interval of the process template with the threshold, several suspected segmentation points were initially screened. For each suspected segmentation point identified in the initial screening, the similarity between the segmentation segment and the data in the process template is calculated, and the suspected segmentation point with the highest similarity is selected as the final piece counting segmentation point. The piece-counting dividing point is readjusted based on the beginning and ending features of the process template to determine whether the piece-counting dividing point is indeed the end point of the sewn part in the template.

5. The intelligent process identification and piece counting method for sewing equipment according to claim 3, characterized in that, The piece-rate calculation process for short-process templates includes: calculating the degree of difference between the data from the starting point to each suspected dividing point and the template data, and selecting the suspected dividing point with the smallest difference as the final piece-rate dividing point.

6. An intelligent process identification and piece counting system for sewing equipment, characterized in that, include: The acquisition module is used to acquire electrical signals converted from the mechanical motion of the sewing equipment, and generate corresponding time-series-based sewing data based on the electrical signals. The dimensionality reduction module is used to reduce the sewing data to two dimensions, including the time interval dimension of each motor action in the sewing equipment and the corresponding number of sewing needles. The template module determines the process type of the sewing data and the corresponding process template based on the time interval of each motor action in the sewing equipment and the corresponding number of sewing stitches. This includes: extracting data segments of appropriate length from the sewing data according to the length of different process templates for comparison with the process templates; predicting whether the process template is divisible based on the pause point of each motor action in each process template, and dividing divisible process templates into multiple sub-processes; for divisible process templates, if the data segment being compared can also be divided into the same number of segments based on the time interval of each motor action, then storing the divisible process template in a candidate library, and comparing each sub-segment divided from the data segment with the sub-processes from the divisible process template. Each segmented sub-process corresponds to a comparison group for similarity calculation. The similarity calculation results of each comparison group are accumulated to obtain the total similarity calculation result between the divisible process template and the corresponding data segment. The process of forming comparison groups for similarity calculation between each sub-segment segmented from the data segment and each sub-process segmented from the divisible process template includes calculating the degree of difference between the two in terms of stitch count and sewing segment count based on a dynamic time-rounding algorithm. For indivisible process templates, the indivisible process templates are stored in a candidate library, and the similarity between them and the corresponding data segment is calculated for comparison. The process template with the smallest difference from the input sewing data is selected from the candidate library as the process template for the sewing data. The piece counting module is used to select piece counting division points for the sewing data to be divided based on the motor movement time interval of the process template after the process template is determined.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the intelligent process identification and piece counting method of the sewing equipment according to any one of claims 1 to 5.

8. An electronic terminal, characterized in that, include: Processor and memory; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory to enable the terminal to perform the intelligent process identification and piece counting method of the sewing equipment as described in any one of claims 1 to 5.

Images