WO2024027227A1 - 缝制设备的智能工序识别及计件方法、系统、终端及介质 - Google Patents

缝制设备的智能工序识别及计件方法、系统、终端及介质 Download PDF

Info

Publication number
WO2024027227A1
WO2024027227A1 PCT/CN2023/090560 CN2023090560W WO2024027227A1 WO 2024027227 A1 WO2024027227 A1 WO 2024027227A1 CN 2023090560 W CN2023090560 W CN 2023090560W WO 2024027227 A1 WO2024027227 A1 WO 2024027227A1
Authority
WO
WIPO (PCT)
Prior art keywords
sewing
data
template
piece counting
piece
Prior art date
Application number
PCT/CN2023/090560
Other languages
English (en)
French (fr)
Inventor
单一舒
曾树杰
韩安太
栗硕
曲凯朝
Original Assignee
杰克科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 杰克科技股份有限公司 filed Critical 杰克科技股份有限公司
Publication of WO2024027227A1 publication Critical patent/WO2024027227A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06M—COUNTING MECHANISMS; COUNTING OF OBJECTS NOT OTHERWISE PROVIDED FOR
    • G06M1/00—Design features of general application
    • G06M1/08—Design features of general application for actuating the drive
    • G06M1/10—Design features of general application for actuating the drive by electric or magnetic means
    • G06M1/102—Design features of general application for actuating the drive by electric or magnetic means by magnetic or electromagnetic means
    • G06M1/107—Design features of general application for actuating the drive by electric or magnetic means by magnetic or electromagnetic means electromotors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/10—Pre-processing; Data cleansing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06M—COUNTING MECHANISMS; COUNTING OF OBJECTS NOT OTHERWISE PROVIDED FOR
    • G06M1/00—Design features of general application
    • G06M1/08—Design features of general application for actuating the drive
    • G06M1/10—Design features of general application for actuating the drive by electric or magnetic means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Definitions

  • 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.
  • Piece-based pay is a wage calculation method widely used in factories now, and how to accurately and efficiently calculate piecework has been studied.
  • the main intelligent piece counting methods used include piece counting by workers scanning codes and piece counting through hanging systems. Both solutions require workers to frequently perform additional operations, which is less efficient, and the cost of the hanging system is higher. Scanning code for piece counting requires that the QR code be kept intact and cannot be lost or damaged, so how to make the sewing machine automatically count pieces? It has become a key direction of current research.
  • the current automatic piece counting method of sewing machines still needs to collect data such as the number of sewing needles, the number of thread trimmings, the presser foot lifting signal, the reinforcement seam condition, and the infrared tube signal with or without fabric (for example, patents CN102704214A, CN107345346B), and needs to know in advance what the workers are doing. What kind of process is it (such as patent CN107345346B, CN104018300A), these require specialized human operations, also increase the calculation load, and greatly reduce the efficiency.
  • some current piece counting methods have certain application range requirements for the process. For example, the total number of needles in the process is required to be less than 400, and the applicability is not strong (such as patent CN104018300A).
  • the current common piece counting method only focuses on the number of sewing pieces, and does not require the accuracy of the starting and ending points of each piece. However, this makes it impossible to accurately record the actual working status of the workers, and it is also impossible to make subsequent assessments of the workers’ technical level. Provide the basis for further detailed analysis.
  • the purpose of this application is to provide intelligent process identification and piece counting methods, systems, terminals and media for sewing equipment to solve the problem of low efficiency and inaccurate sewing piece counting in the prior art. Advanced questions.
  • the first aspect of the present application provides an intelligent process identification and piece counting method for sewing equipment, including: acquiring an electrical signal converted by the mechanical movement of the sewing equipment, and calculating the electrical signal according to the electrical signal.
  • the signal generates corresponding sewing data based on time series; the dimensionality of the sewing data is reduced to two dimensions, including the time interval dimension of each action of the motor in the sewing equipment and the corresponding sewing needle number dimension; according to the The time interval dimension of each movement of the motor in the sewing equipment and the corresponding sewing needle number dimension are used to determine the process type to which the sewing data belongs and determine the corresponding process template; after determining the process template, treat it according to the motor movement time interval of the process template Use divided sewing data to select piece counting dividing points for piece counting.
  • the process type to which the sewing data belongs is determined and the corresponding The process template includes: extracting data segments with appropriate lengths from the sewing data according to the lengths of different process templates for comparison with the process template; and according to the pause points of each action of the motor in each of the process templates.
  • the process template Predict whether the process template is divisible, and divide the divisible process template into multiple sub-processes; for a divisible process template, if the data segments compared with it 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 the candidate library, and each sub-segment divided from the data segment corresponds to each sub-process divided from the divisible process template to form each 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; for the indivisible process template, the indivisible process template is stored in the backup Select a library and calculate the similarity with the corresponding data segment for comparison; select the process template with the smallest difference from the input sewing data from the candidate library as the process template of the sewing data.
  • each sub-segment segmented from the data segment corresponds to each sub-process segmented from the separable process template to form each comparison group for similarity calculation. , including calculating the degree of difference between the two in terms of the number of needles and the number of sewing segments based on the dynamic time reduction algorithm.
  • the first several items of sewing data in the incoming sewing data are compared and detected, including averaging the similarity between the first several items of sewing data and each process template. Compare the values; if the deviation is too large, it can be judged that a deviation has occurred; if there is no deviation or the deviation is small, it can be judged that no deviation has occurred.
  • the selection of piece counting dividing points for the sewing data to be divided according to the motor movement time interval of the process template for piece counting includes: dividing the sewing data according to the length of the process template.
  • Process templates are divided into long process templates and short process templates.
  • the piece counting process for a long process template includes: comparing the motor movement time interval of the process template with a threshold and then initially screening multiple suspected segmentation points; Split point, calculate the similarity between the split segment and the data in the process template, select the suspected split point with the highest similarity as the final piece-rate split point; re-adjust the piece-rate split point according to the beginning characteristics and end characteristics of the process template, so as to Determine whether the piece counting dividing point is indeed the end point of the sewn parts in the template.
  • 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 result. Piece split point.
  • the second aspect of the present application provides an intelligent process identification of sewing equipment and a piece counting system, including: an acquisition module, used to acquire electrical signals converted by the mechanical movement of the sewing equipment, and generate corresponding time-series-based sewing data based on the electrical signals; a dimensionality reduction module, used to The sewing data is reduced to two dimensions, including the time interval dimension of each action of the motor in the sewing equipment and the corresponding sewing needle number dimension; the template module is based on the time interval of each action of the motor in the sewing equipment.
  • the piece counting module is used to calculate the sewing data to be divided according to the motor movement time interval of the process template after determining the process template. Selection of piece counting split points for piece counting.
  • a third aspect of the present application provides a computer-readable storage medium on which a computer program is stored.
  • the computer program is executed by a processor, the intelligent process identification of the sewing equipment is realized. and piece counting methods.
  • a fourth aspect of the present application provides an electronic terminal, including: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory. , so that the terminal executes the intelligent process identification and piece counting method of the sewing equipment.
  • the intelligent process identification and piece counting method, system, terminal and medium of the sewing equipment of this application have the following beneficial effects:
  • the process corresponding to the data can be identified among multiple known process templates, so that there is no need to set or modify the template every time the process is changed, which can reduce additional manual work and reduce costs.
  • Figure 1 shows a schematic diagram of an embodiment of the present application.
  • Figure 2 shows a schematic diagram of an embodiment of the present application.
  • Figure N shows a schematic structural diagram of an electronic terminal in an embodiment of the present application.
  • connection can be a fixed connection or a fixed connection. It is a detachable connection or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be an internal connection between two components.
  • connection can be a fixed connection or a fixed connection. It is a detachable connection or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be an internal connection between two components.
  • A, B or C or "A, B and/or C” means "any of the following: A; B; C; A and B; A and C; B and C; A, B and C” . Exceptions to this definition occur only when a combination of elements, functions, or operations is inherently mutually exclusive in some manner.
  • the present invention provides an intelligent process identification and piece counting method, system, terminal and storage medium for sewing equipment, by inputting a piece of sewing machine operation data belonging to the same type of process, and based on the operation of the sewing machine recorded therein Status and number of sewing needles, first identify what process the sewing machine is performing, and then perform piece counting analysis based on the template of the process, while recording the starting point and end point of each piece, thereby achieving efficient and accurate intelligent piece counting.
  • FIG. 1 a schematic flow chart showing an intelligent process identification and piece counting method for sewing equipment in an embodiment of the present invention is shown.
  • the intelligent process identification and piece counting method in this embodiment can be applied to computer equipment, such as computers, laptops, tablets, smartphones, smart bracelets, smart watches, smart helmets, smart TVs, etc.; it can also be applied to servers.
  • the server can be arranged on one or more physical servers according to functions, loads and other factors, or can be composed of distributed or centralized server clusters.
  • the intelligent process identification and piece counting method of the sewing equipment mainly includes the following steps. Each step will be explained in detail below with reference to specific examples.
  • Step S11 Obtain the electrical signal converted by the mechanical movement of the sewing equipment, and generate corresponding sewing data based on time series based on the electrical signal.
  • the gateway device can receive electrical signals converted from the mechanical motion of each component of the sewing machine, and process the electrical signals into data about the specific movement of each component (such as a motor, etc.) of the sewing machine at a specific time, according to the time coordinates
  • the axis sequence is uploaded to the platform (i.e., the aforementioned computer equipment or server, etc.).
  • gateway equipment also known as network connectors or protocol converters, implements network interconnection at the network layer. It is a complex network interconnection device and serves as a computer system or device responsible for conversion.
  • Step S12 Reduce the dimensionality of the sewing data to two dimensions, including the dimension of the time interval of each action of the motor in the sewing equipment and the dimension of the corresponding number of sewing needles. After data dimensionality reduction, the data structure can be made more reasonable, subsequent calculation time can be reduced, and calculations related to process identification and piece counting can be facilitated.
  • the sewing data includes multiple dimensions before dimensionality reduction.
  • it may also include sewing row spacing, stitch length and stitch length. Parameters of line and other dimensions.
  • Step S13 Based on the time interval dimension of each action of the motor in the sewing equipment and the corresponding sewing needle number dimension, determine the process type to which the sewing data belongs and determine the corresponding process template; specific steps include:
  • the divisible process template For the divisible process template, if the data segment compared with it can also be divided into the same number of segments according to the time interval of each motor action, then the divisible process template will be stored in the alternative library, and the data segment will be Each divided sub-segment corresponds to each sub-process divided from the divisible process template to form each comparison group for similarity calculation. The similarity calculation results of each comparison group are accumulated to obtain the divisible process template. The total result of similarity calculation with the corresponding data segment.
  • the divisible process template A is divided into the following three sub-processes, namely sub-process A1, sub-process A2 and In sub-process A3, the data segment B used for comparison with the divisible template A can also be divided into three sub-segments, namely sub-segment B1, sub-segment B2 and sub-segment B3.
  • the sub-process A1 and the sub-section B1 constitute the first comparison group
  • the sub-process A2 and the sub-section B2 constitute the second comparison group
  • the sub-process A3 and the sub-section B3 constitute the third comparison group
  • each comparison is calculated separately.
  • the similarity calculation result of the group for example, the calculated values are C1, C2 and C3, then the similarity result of comparing the divisible process template A and the data segment B should be (C1+C2+C3).
  • the template process can also be compared directly without segmenting the template process.
  • the specific steps are to extract different lengths from the input data according to the lengths of the templates in different processes, and compare them with the template in terms of the total number of stitches, the similarity between the number of sewing stitches at each motor movement and the corresponding number of stitches in the corresponding template. Compare and select the template with the smallest difference as the template for the incoming data.
  • the sub-segments separated from the data segment and the sub-processes separated from the separable process template correspond to each other to form comparison groups for similarity calculation, which refers to calculating the difference between the two.
  • the degree of difference in terms of number, number of sewing segments, etc.
  • the aforementioned similarity calculation can use the similarity or distance function suitable for time series data to calculate the similarity.
  • the similarity between the number of sewing needles when the motor is moving and the number of needles in the template is determined dynamically.
  • Time warping method DTW (Dynamic Time Warping) refers to a dynamic time warping algorithm, which can be used to measure the similarity between two independent time series; DTW is widely used in template matching problems and can better solve two sets of data Difficult to compare due to different lengths.
  • distance is measured using the Euclidean distance method. It should also be noted that in the DTW method, the distance is measured using the Euclidean distance method, and the Manhattan distance can also be used for calculation.
  • the indivisible process template is stored in the candidate library, and the similarity with the corresponding data segment is calculated for comparison.
  • the data segment and the process template can be compared in terms of the total number of stitches, the similarity between the number of sewing stitches each time the motor is running and the corresponding number of stitches in the process template, etc.
  • process templates have been stored in the alternative library.
  • These process templates may be indivisible process templates or divisible process templates. However, regardless of whether they are divisible process templates or indivisible process templates, There is a corresponding similarity calculation result.
  • the candidate library select the process template with the smallest difference (that is, the highest similarity) with the input sewing data as the process template of the sewing data.
  • this embodiment preferably compares and detects the first several items of sewing data in the incoming sewing data, specifically comparing the first several items of sewing data with the average similarity of each process template; if there is a deviation If it is too large, it can be judged that there is a deviation; if there is no deviation If the difference or deviation is small, it can be judged that no deviation has occurred.
  • Step S14 After determining the process template, select piece counting dividing points for the sewing data to be divided according to the motor movement time interval of the process template to perform piece counting.
  • the process templates are divided into long process templates and short process templates according to the different lengths of the process templates, and different methods are used for piece counting for the long process templates and short process templates.
  • different methods are used for piece counting for the long process templates and short process templates. This is because for the long process templates In other words, errors can be accumulated. If there are errors in the previous piece counting, the errors will continue to accumulate, and the final piece counting result will inevitably have a huge deviation.
  • the piece counting process for long process templates is as follows:
  • 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-rate segmentation point. Specifically, calculate the total number of stitches from each starting point to the suspected dividing point. If the total number of stitches meets the range of the target stitch number (the target stitch number is set based on the process template data), then each motor The similarity between the number of sewing stitches during movement and the corresponding number of stitches in the process template is mainly used. Dimensions such as the total number of stitches and the number of sewing segments are used to calculate the degree of difference between the data from the starting point to each suspected segmentation point and the template data. The smallest calculation result is selected. The dividing point is used as the end point of a piece (i.e. the piece counting dividing point) for piece counting.
  • this embodiment also adds the following technical means: readjust the piece-counting dividing point according to the beginning characteristics and ending characteristics of the process template to determine the piece-counting dividing point. Whether the piece counting dividing point is indeed the end point of the sewn parts in the template can be compared with the beginning/end characteristics of the template from dimensions such as time interval or number of stitches. For example, some processes require sewing a pair of trouser legs, so one piece is not completed until two trouser legs are sewn. However, since the sewing data mapped to each trouser leg is completely symmetrical, it is very likely that the first trouser leg will be sewn.
  • the difference between the data from the starting point to each suspected segmentation point and the template data can be calculated directly from the total number of stitches, number of sewing segments and other dimensions, and the suspected segmentation point with the smallest difference (that is, the highest similarity) can be selected. as the final piece split point.
  • determining the starting point of the data select all points where the total stitch number of the sewing machine data satisfies the target stitch number range as the end point. For each end point, take out the data to be compared and calculate the degree of difference between it and the template (the calculation method is the same as the original method). For the point with the smallest calculated result, select the point that is closest in time and meets the time interval requirements as the end point of the piece.
  • the intelligent process identification and piece counting system 400 in this embodiment includes: an acquisition module 401, a dimensionality reduction module 402, a template module 403 and a piece counting module 404.
  • the acquisition module 401 is used to acquire the electrical signals converted by the mechanical movement of the sewing equipment, and generate corresponding sewing data based on time series according to the electrical signals; the dimensionality reduction module 402 is used to analyze the sewing data The dimensionality is reduced to two dimensions, including the time interval dimension of each action of the motor in the sewing equipment and the corresponding sewing needle number dimension; the template module 403 is used to calculate the time interval dimension of each action of the motor in the sewing equipment and According to the corresponding sewing needle number dimension, determine the process type to which the sewing data belongs and determine the corresponding process template; the piece counting module 404 is used to perform piece counting segmentation on the sewing data to be divided according to the motor movement time interval of the process template after determining the process template. Selection of points for piece counting.
  • each module of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into a physical entity, or they can also be physically separated. And these modules can all be implemented in the form of software calling through processing components; they can also all be implemented in the form of hardware; some modules can also be implemented in the form of software calling through processing components, and some modules can be implemented in the form of hardware.
  • the piece counting module can be a separate processing element, or can be integrated into a chip of the above device.
  • it can also be stored in the memory of the above device in the form of program code, and can be processed by a certain processing element of the above device. Call and execute the functions of the above piece counting module.
  • the implementation of other modules is similar.
  • each step of the above method or each of the above modules can be completed by instructions in the form of hardware integrated logic circuits or software in the processor element.
  • the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs for short), or one or more micro A processor (digital signal processor, DSP for short), or one or more Field Programmable Gate Arrays (Field Programmable Gate Array, FPGA for short), etc.
  • ASICs Application Specific Integrated Circuits
  • micro A processor digital signal processor
  • FPGA Field Programmable Gate Array
  • the processing element can be a general-purpose processor, such as a central processing unit (Central Processing Unit, CPU for short) or other processors that can call program code.
  • these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).
  • SOC system-on-a-chip
  • FIG. 5 a schematic structural diagram of an electronic terminal in an embodiment of the present invention is shown.
  • 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 through a system bus and completes mutual communication.
  • the memory 52 is used to store computer programs and communicate with each other.
  • the processor 53 is used to communicate with other equipment, and the processor 51 is used to run a computer program, so that the electronic terminal executes each step of the intelligent process identification and piece counting method of the sewing equipment.
  • the system bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc.
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • the system bus can be divided into address bus, data bus, control bus, etc. For ease of presentation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.
  • the communication interface is used to implement communication between the database access device and other devices (such as clients, read-write libraries, and read-only libraries).
  • the memory may include random access memory (RAM), or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
  • the above-mentioned processor can be a general-purpose processor, including a central processing unit (Central Processing Unit, referred to as CPU), a network processor (Network Processor, referred to as NP), etc.; it can also be a digital signal processor (Digital Signal Processing, referred to as DSP) , Application Specific Integrated Circuit (ASIC for short), Field-Programmable Gate Array (FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.
  • CPU Central Processing Unit
  • NP Network Processor
  • DSP Digital Signal Processing
  • ASIC Application Specific Integrated Circuit
  • FPGA Field-Programmable Gate Array
  • the present invention also provides a computer-readable storage medium on which a computer program is stored.
  • the computer program is executed by a processor, the intelligent process identification and piece counting method of the sewing equipment are implemented.
  • the aforementioned computer program can be stored in a computer-readable storage medium.
  • the steps including the above-mentioned method embodiments are executed; and the aforementioned storage media include: ROM, RAM, magnetic disks, optical disks and other media that can store program codes.
  • the computer readable and writable storage medium may include read-only memory, random access memory, EEPROM, CD-ROM or other optical disk storage devices, magnetic disk storage devices or other magnetic storage devices, flash memory, A USB flash drive, a mobile hard disk, or any other medium that can be used to store the desired program code in the form of instructions or data structures and can be accessed by the computer. Also, any connection is properly termed a computer-readable medium.
  • Coaxial cable, fiber optic cable, twisted pair, DSL or wireless technologies such as infrared, radio, and microwave are included in the definition of medium.
  • computer readable and writable storage media and data storage media do not include connections, carrier waves, signals, or other transitory media, and are instead intended for non-transitory, tangible storage media.
  • Disks and optical disks include compact discs (CDs), laser discs, optical discs, digital versatile discs (DVDs), floppy disks, and Blu-ray discs. Disks typically copy data magnetically, while discs use lasers to optically copy data. Copy the data locally.
  • this application provides intelligent process identification and piece counting methods, systems, terminals and media for sewing equipment.
  • the present invention can identify the process corresponding to the data in multiple known process templates, so that there is no need to change the process every time.
  • Setting or modifying the template during the process can reduce additional manual work and reduce costs; it only needs to collect the electrical signals from the sewing machine: the data of the number of sewing stitches when the motor moves, record the data in the time series and perform calculations. This greatly reduces the requirements for data collection and recording, reduces the data transmission load, and reduces the complexity of subsequent calculations; the starting and ending points of each piece are accurately judged, which indirectly provides information for improving the accuracy of piece counting.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Human Resources & Organizations (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Electromagnetism (AREA)
  • Sewing Machines And Sewing (AREA)

Abstract

本申请提供缝制设备的智能工序识别及计件方法、系统、终端及介质，获取由缝制设备的机械运动转化成的电信号，并根据电信号生成对应的基于时间序列的缝制数据；对缝制数据降维至两维，包括缝制设备中电机每次动作的时间间隔维度及相应的缝纫针数维度；判断缝制数据的工序种类并确定工序模板；根据工序模板的电机运动时间间隔对待分割的缝制数据进行计件分割点的选取以进行计件。本发明可在已知的多个工序模板中识别出数据所对应的工序，减少额外的人力工作；仅采集缝纫机中的电信号，降低了数据采集要求；对于每件的起始、结束点进行了准确的判断；采用动态时间规整法，提高了分割点的准确率；对于长工序、短工序都适用，具有广阔的市场前景。

Description

缝制设备的智能工序识别及计件方法、系统、终端及介质 技术领域
本申请涉及缝制技术领域，特别是涉及缝制设备的智能工序识别及计件方法、系统、终端及介质。
背景技术
按件计薪是现在工厂中广泛应用的一种计薪方式，其中如何准确高效地计件一直被研究。目前主要使用的智能计件方式有工人扫码计件和通过吊挂系统计件。这两种方案都需要工人频繁地进行额外的操作，效率较低，而且吊挂系统的成本较高，扫码计件则需要二维码保持完整，不能丢失或者破损，所以如何让缝纫机能够自动计件成为现在研究的一个重点方向。
目前的缝纫机自动计件方法仍需采集缝纫针数、剪线次数、抬压脚信号、加固缝情况、有无布料的红外对管信号等数据(例如专利CN102704214A，CN107345346B)，而且需要预先知道工人做的是哪种工序(例如专利CN107345346B，CN104018300A)，这些都需要专门的人力操作，也增加了计算的运算负荷，大大降低了效率。除此之外，目前的一些计件方法对于工序有一定的使用范围要求，例如工序内总针数要求少于400，适用性不强(例如专利CN104018300A)。此外，现在普遍的计件方法只关注缝纫件数，对于每件起始结束点的准确性并没有要求，但是如此就无法对工人实际的工作状态进行准确的记录，后续也不能对工人的技术水平做进一步细致的分析提供依据。
为解决此类问题并提高效率，使数据能够在后续的研究分析中发挥更大的作用，需要更简单、普适性更强、更准确的智能计件方法。
发明内容
鉴于以上所述现有技术的缺点，本申请的目的在于提供缝制设备的智能工序识别及计件方法、系统、终端及介质，用于解决现有技术中的缝制计件效率低且准确度不高等问题。
为实现上述目的及其他相关目的，本申请的第一方面提供一种缝制设备的智能工序识别及计件方法，包括：获取由缝制设备的机械运动转化成的电信号，并根据所述电信号生成对应的基于时间序列的缝制数据；对所述缝制数据降维至两维，包括所述缝制设备中电机每次动作的时间间隔维度及相应的缝纫针数维度；根据所述缝制设备中电机每次动作的时间间隔维度及相应的缝纫针数维度，判断缝制数据所属的工序种类并确定对应的工序模板；在确定工序模板后，根据工序模板的电机运动时间间隔对待分割的缝制数据进行计件分割点的选取 以进行计件。
于本申请的第一方面的一些实施例中，所述根据所述缝制设备中电机每次动作的时间间隔维度及相应的缝纫针数维度，判断缝制数据所属的工序种类并确定对应的工序模板，包括：根据不同工序模板的长度从所述缝制数据中取出长度相适应的数据段，以用于与工序模板进行比对；根据各所述工序模板中电机每个动作的停顿点预测该工序模板是否可分割，并将可分割工序模板分割为多段子工序；对于可分割工序模板，若与之比对的数据段也能够根据电机每次动作的时间间隔分割成相同的段数，则将所述可分割工序模板存入备选库，并将从该数据段分割出的各子段与从该可分割工序模板分割出的各子工序对应构成各比对组以进行相似度计算，每个比对组的相似度计算结果进行累加后得到该可分割工序模板与对应数据段之间的相似度计算总结果；对于不可分割的工序模板，将所述不可分割工序模板存入备选库，并计算与对应数据段之间的相似度以进行比对；从所述备选库中选取与输入的缝制数据差异度最小的工序模板作为该缝制数据的工序模板。
于本申请的第一方面的一些实施例中，所述将从该数据段分割出的各子段与从该可分割工序模板分割出的各子工序对应构成各比对组以进行相似度计算，包括基于动态时间归整算法计算两者在针数、缝纫段数方面的差异程度。
于本申请的第一方面的一些实施例中，将传入的缝制数据中的前若干项缝制数据进行比对检测，包括将这前若干项缝制数据与各工序模板的相似度平均值进行比较；若偏差太大则可判断出现了偏差；若无偏差或偏差较小则可判断未出现偏差。
于本申请的第一方面的一些实施例中，所述根据工序模板的电机运动时间间隔对待分割的缝制数据进行计件分割点的选取以进行计件，包括：根据所述工序模板长度的不同将工序模板分为长工序模板和短工序模板。
于本申请的第一方面的一些实施例中，对长工序模板的计件过程包括：根据工序模板的电机运动时间间隔与阈值进行比较后初筛多个疑似分割点；对于初筛出的各疑似分割点，计算分割段与工序模板中数据的相似度，选取相似度最高的疑似分割点作为最终的计件分割点；根据工序模板的开头特征和结尾特征对所述计件分割点进行再调整，以判断该计件分割点是否确为模板中缝制件的结束点。
于本申请的第一方面的一些实施例中，对短工序模板的计件过程包括：计算起始点到各疑似分割点的数据与模板数据的差异程度，选取差异度最小的疑似分割点作为最终的计件分割点。
为实现上述目的及其他相关目的，本申请的第二方面提供一种缝制设备的智能工序识别 及计件系统，包括：获取模块，用于获取由缝制设备的机械运动转化成的电信号，并根据所述电信号生成对应的基于时间序列的缝制数据；降维模块，用于对所述缝制数据降维至两维，包括所述缝制设备中电机每次动作的时间间隔维度及相应的缝纫针数维度；模板模块，根据所述缝制设备中电机每次动作的时间间隔维度及相应的缝纫针数维度，判断缝制数据所属的工序种类并确定对应的工序模板；计件模块，用于在确定工序模板后，根据工序模板的电机运动时间间隔对待分割的缝制数据进行计件分割点的选取以进行计件。
为实现上述目的及其他相关目的，本申请的第三方面提供一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现所述缝制设备的智能工序识别及计件方法。
为实现上述目的及其他相关目的，本申请的第四方面提供一种电子终端，包括：处理器及存储器；所述存储器用于存储计算机程序，所述处理器用于执行所述存储器存储的计算机程序，以使所述终端执行所述缝制设备的智能工序识别及计件方法。
如上所述，本申请的缝制设备的智能工序识别及计件方法、系统、终端及介质，具有以下有益效果：
(1)可在已知的多个工序模板中识别出数据所对应的工序，这样不用每次换工序时设定或者修改模板，可以减少额外的人力工作，降低成本。
(2)仅需采集缝纫机中的电信号：电机运动时缝纫针数的数据，记录其时间序列下的数据情况并进行计算。这样大大降低了对数据采集记录的要求，同时减轻了数据传输负荷，也减小了后续计算的复杂程度。
(3)对于每件的起始、结束点进行了准确的判断，为提高计件准确率间接提供了帮助，同时为后续对工人的技术水平进行进一步细致的分析提供了依据。
(4)采纳了动态时间规整法，该方法广泛应用于模板匹配问题中，但是在之前的专利文献中并未应用于计件算法中。通过该方法，本方法提高了分割点的准确率。
(5)对于长工序、短工序都适用，扩大了工序使用范围，具有广阔的市场前景。
附图说明
图1显示为本申请一实施例中示意图。
图2显示为本申请一实施例中示意图。
图N显示为本申请一实施例中电子终端的结构示意图。
具体实施方式
以下通过特定的具体实例说明本申请的实施方式，本领域技术人员可由本说明书所揭露的内容轻易地了解本申请的其他优点与功效。本申请还可以通过另外不同的具体实施方式加以实施或应用，本说明书中的各项细节也可以基于不同观点与应用，在没有背离本申请的精神下进行各种修饰或改变。需说明的是，在不冲突的情况下，以下实施例及实施例中的特征可以相互组合。
需要说明的是，在下述描述中，参考附图，附图描述了本申请的若干实施例。应当理解，还可使用其他实施例，并且可以在不背离本申请的精神和范围的情况下进行机械组成、结构、电气以及操作上的改变。下面的详细描述不应该被认为是限制性的，并且本申请的实施例的范围仅由公布的专利的权利要求书所限定。这里使用的术语仅是为了描述特定实施例，而并非旨在限制本申请。空间相关的术语，例如“上”、“下”、“左”、“右”、“下面”、“下方”、“下部”、“上方”、“上部”等，可在文中使用以便于说明图中所示的一个元件或特征与另一元件或特征的关系。
在本申请中，除非另有明确的规定和限定，术语“安装”、“相连”、“连接”、“固定”、“固持”等术语应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或一体地连接；可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连，可以是两个元件内部的连通。对于本领域的普通技术人员而言，可以根据具体情况理解上述术语在本申请中的具体含义。
再者，如同在本文中所使用的，单数形式“一”、“一个”和“该”旨在也包括复数形式，除非上下文中有相反的指示。应当进一步理解，术语“包含”、“包括”表明存在所述的特征、操作、元件、组件、项目、种类、和/或组，但不排除一个或多个其他特征、操作、元件、组件、项目、种类、和/或组的存在、出现或添加。此处使用的术语“或”和“和/或”被解释为包括性的，或意味着任一个或任何组合。因此，“A、B或C”或者“A、B和/或C”意味着“以下任一个：A；B；C；A和B；A和C；B和C；A、B和C”。仅当元件、功能或操作的组合在某些方式下内在地互相排斥时，才会出现该定义的例外。
为解决上述背景技术中的问题，本发明提供缝制设备的智能工序识别及计件方法、系统、终端及存储介质，通过输入一段属于同一类工序的缝纫机操作数据，并根据其中记录的缝纫机的运行状态和缝纫针数，先识别出缝纫机在执行何种工序，然后根据工序的模板进行计件分析，同时记录每一件的起始点和终点，由此实现高效且精准的智能计件。
为了使本发明的目的、技术方案及优点更加清楚明白，通过下述实施例并结合附图，对本发明实施例中的技术方案的进一步详细说明。应当理解，此处所描述的具体实施例仅用以 解释本发明，并不用于限定发明。
如图1所示，展示了本发明实施例中的一种缝制设备的智能工序识别及计件方法的流程示意图。应理解，本实施例中智能工序识别及计件方法可应用于计算机设备，例如电脑、笔记本电脑、平板电脑、智能手机、智能手环、智能手表、智能头盔、智能电视等；还可应用于服务器，所述服务器可以根据功能、负载等多种因素布置在一个或多个实体服务器上，也可以由分布的或集中的服务器集群构成。
在本实施例中，所述缝制设备的智能工序识别及计件方法主要包括如下步骤，下文将结合具体示例来对各步骤进行详尽的解释说明。
步骤S11：获取由缝制设备的机械运动转化成的电信号，并根据所述电信号生成对应的基于时间序列的缝制数据。
具体而言，可由网关设备接收由缝纫机各部件的机械运动转化成的电信号，并将电信号处理成关于缝纫机在具体时间下的各部件(如电机等)具体运动情况的数据，按照时间坐标轴序列上传至平台(即前述的计算机设备或服务器等)。应理解，网关设备又称为网间连接器或协议转换器，在网络层上实现网络互联，是复杂的网络互联设，充当转换重任的计算机系统或设备。
步骤S12：对所述缝制数据降维至两维，包括所述缝制设备中电机每次动作的时间间隔维度及相应的缝纫针数维度。在进行数据降维后，可使数据结构更合理，减少后续的运算时间，便于进行工序识别和计件的相关计算。
在一些示例中，所述缝制数据在降维前包括多个维度，除了保留的电机每次动作的时间间隔维度及相应的缝纫针数维度之外，还可包括缝纫行距、针距和缝线等维度的参数。
步骤S13：根据所述缝制设备中电机每次动作的时间间隔维度及相应的缝纫针数维度，判断缝制数据所属的工序种类并确定对应的工序模板；具体步骤包括：
首先根据不同工序模板的长度从所述缝制数据中取出长度相适应的数据段，以用于与工序模板进行比对；再根据各所述工序模板中电机每个动作的停顿点预测该工序模板是否可分割，并将可分割工序模板分割为多段子工序。
对于可分割工序模板，若与之比对的数据段也能够根据电机每次动作的时间间隔分割成相同的段数，则将所述可分割工序模板存入备选库，并将从该数据段分割出的各子段与从该可分割工序模板分割出的各子工序对应构成各比对组以进行相似度计算，每个比对组的相似度计算结果进行累加后得到该可分割工序模板与对应数据段之间的相似度计算总结果。
举例来说，可分割工序模板A分为如下3个子工序，分别是子工序A1、子工序A2及 子工序A3，用于与可分割模板A进行比对的数据段B也能分割成3个子段，分别是子段B1、子段B2及子段B3。将子工序A1与子段B1构成第一比对组，将子工序A2与子段B2构成第二比对组，将子工序A3与子段B3构成第三比对组，分别计算每个比对组的相似度计算结果，例如分别计算得到的值为C1、C2及C3，那么可分割工序模板A与数据段B进行比对的相似度结果应是(C1+C2+C3)。
需说明的是，在工序识别过程中，也可以不用将模板工序分段而直接进行比对。具体步骤为根据不同工序模板的长度，相应的从输入数据中取出不同的长度，与模板在总针数、每次电机运动时缝纫针数与相应的模板中对应针数的相似程度等维度进行比对，取差异程度最小的模板作为该传入数据的模板。
在一些示例中，所述将从该数据段分割出的各子段与从该可分割工序模板分割出的各子工序对应构成各比对组以进行相似度计算，是指计算两者在针数、缝纫段数等方面的差异程度。
前述的相似度计算可采用适用于时间序列数据的相似或距离函数来计算相似度，本方法中提到的缝纫机数据中电机运动时缝纫针数与模板中针数的相似程度判定采取的是动态时间规整法；DTW(Dynamic Time Warping)是指动态时间归整算法，可用于度量两个独立时间序列之间的相似度；DTW广泛应用于模板匹配问题中，并且能够较好地解决两组数据由于长度不同而难以对比的问题。在DTW中，距离的测定使用的是欧氏距离法。另需说明的是，在DTW方法中，距离的测定使用的是欧氏距离法，也可以采取曼哈顿距离进行计算。
对于不可分割的工序模板，将所述不可分割工序模板存入备选库，并计算与对应数据段之间的相似度以进行比对。具体来说，可将数据段与工序模板从总针数、每次电机运行时缝纫针数与工序模板对应针数的相似度等维度进行差异比较。
此时，所述备选库中已存入一或多个工序模板，这些工序模板可能是不可分割工序模板，也可能是可分割工序模板，但无论是可分割工序模板还是不可分割工序模板，都有一个对应的相似度计算结果。在备选库中，选择与输入的缝制数据差异度最小(即相似度最高)的工序模板作为该缝制数据的工序模板。
进一步地，为了避免由于人工操作失误或其他非必要的原因所导致的工序数据上的偏差，即为了减小错误概率，例如对于一些新手工人来说，由于业务还不熟练在将第一件的缝制数据与工序模板比较后误认为是错误的模板(实则是正确的模板)，会导致错误率增加。因此，本实施例优选将传入的缝制数据中的前若干项缝制数据进行比对检测，具体是将这前若干项缝制数据与各工序模板的相似度平均值进行比较；若偏差太大则可判断出现了偏差；若无偏 差或偏差较小则可判断未出现偏差。
为便于本领域技术人员理解本实施例中工序识别的过程，除了上述文字解释外，还配以图2进行辅助认知，该图中的流程实际上均已记载于步骤S13及其解释说明中。
步骤S14：在确定工序模板后，根据工序模板的电机运动时间间隔对待分割的缝制数据进行计件分割点的选取以进行计件。
优选的，根据所述工序模板长度的不同将工序模板分为长工序模板和短工序模板，对所述长工序模板和短工序模板分别采用不同的方式进行计件，这是因为对于长工序模板而言，误差是可以累加的，若在先计件出现错误则会导致误差不断累加，最终的计件结果必然偏差巨大。
对于长工序模板的计件过程如下：
首先根据工序模板的电机运动时间间隔与阈值进行比较后初筛多个疑似分割点，作为可能的件与件之间的分割点；应理解，这里所谓的件与件之间的分割点用于区分两件不同的缝制件，因此分割点的数量就决定了计件结果。
随后，对于初筛出的各疑似分割点，计算分割段与工序模板中数据的相似度，选取相似度最高的疑似分割点作为最终的计件分割点。具体而言，计算从每个起始点到疑似分割点的总针数，若总针数满足目标针数的范围(该目标针数是根据工序模板数据设定的)，则再以每次电机运动时缝纫针数与工序模板中对应针数的相似程度为主，总针数、缝制段数等维度为辅计算起始点到各疑似分割点的数据与模板数据的差异程度，选取计算结果最小的分割点作为一件的结束点(即计件分割点)进行计件。
进一步地，为了避免一些特殊情况所导致的对计件分割点的误判，本实施例还增加如下技术手段：根据工序模板的开头特征和结尾特征对所述计件分割点进行再调整，以判断该计件分割点是否确为模板中缝制件的结束点，可从时间间隔或针数等维度与模板的开头/结尾特征做比对。举例来说，有些工序需要缝制一对裤腿，因此缝制完成两条裤腿才算完成一件，但由于每条裤腿所映射的缝制数据是完全对称的，所以就极有可能在完成第一条裤腿的时候就被误认为是计件分割点(即在缝制完一条裤腿的时候就认为两条裤腿都已经缝制完成了)，因此有必要再将与工序模板的开头特征和结尾特征与计件分割点进行比对。
对于短工序模板而言，可直接从总针数、缝制段数等维度计算起始点到各疑似分割点的数据与模板数据的差异程度，选取差异度最小(即相似度最高)的疑似分割点作为最终的计件分割点。
需说明的是，在计件流程中，可以采取不同的方法进行计件分割。在确定数据起始点的 情况下，挑选出作为结尾点时缝纫机数据的总针数满足目标针数范围的所有点。对于每个结尾点，取出待比较数据，计算其与模板的差异程度(计算方法同原方法)。对于计算结果数值最小的点，选取其时间最接近的并且满足时间间隔要求的点作为该件的结束点。此外，在计件流程中，寻找划分件与件的分割点也可以采取先对模板分段的方式，然后在数据中找到对应模板的子工序，最后将小工序组合成一道完整的对应模板的工序数据，从而完成一件的分割计件。
为便于本领域技术人员理解本实施例中工序识别的过程，除了上述文字解释外，还配以图3进行辅助认知，该图中的流程实际上均已记载于步骤S14及其解释说明中。
如图4所示，展示了本发实施例中的一种缝制设备的智能工序识别及计件系统的结构示意图。本实施例的智能工序识别及计件系统400包括：获取模块401、降维模块402、模板模块403和计件模块404。
所述获取模块401用于获取由缝制设备的机械运动转化成的电信号，并根据所述电信号生成对应的基于时间序列的缝制数据；降维模块402用于对所述缝制数据降维至两维，包括所述缝制设备中电机每次动作的时间间隔维度及相应的缝纫针数维度；模板模块403用于根据所述缝制设备中电机每次动作的时间间隔维度及相应的缝纫针数维度，判断缝制数据所属的工序种类并确定对应的工序模板；计件模块404用于在确定工序模板后，根据工序模板的电机运动时间间隔对待分割的缝制数据进行计件分割点的选取以进行计件。
需说明的是，本实施例中的智能工序识别及计件系统，其实施方式与上文中的智能工序识别及计件方法类似，故不再赘述。
应理解以上装置的各个模块的划分仅仅是一种逻辑功能的划分，实际实现时可以全部或部分集成到一个物理实体上，也可以物理上分开。且这些模块可以全部以软件通过处理元件调用的形式实现；也可以全部以硬件的形式实现；还可以部分模块通过处理元件调用软件的形式实现，部分模块通过硬件的形式实现。例如，计件模块可以为单独设立的处理元件，也可以集成在上述装置的某一个芯片中实现，此外，也可以以程序代码的形式存储于上述装置的存储器中，由上述装置的某一个处理元件调用并执行以上计件模块的功能。其它模块的实现与之类似。此外这些模块全部或部分可以集成在一起，也可以独立实现。这里所述的处理元件可以是一种集成电路，具有信号的处理能力。在实现过程中，上述方法的各步骤或以上各个模块可以通过处理器元件中的硬件的集成逻辑电路或者软件形式的指令完成。
例如，以上这些模块可以是被配置成实施以上方法的一个或多个集成电路，例如：一个或多个特定集成电路(Application Specific Integrated Circuit，简称ASIC)，或，一个或多个微 处理器(digital signal processor，简称DSP)，或，一个或者多个现场可编程门阵列(Field Programmable Gate Array，简称FPGA)等。再如，当以上某个模块通过处理元件调度程序代码的形式实现时，该处理元件可以是通用处理器，例如中央处理器(Central Processing Unit，简称CPU)或其它可以调用程序代码的处理器。再如，这些模块可以集成在一起，以片上系统(system-on-a-chip，简称SOC)的形式实现。
如图5所示，展示了本发明实施例中的一种电子终端的结构示意图。本实例提供的电子终端，包括：处理器51、存储器52、通信器53；存储器52通过系统总线与处理器51和通信器53连接并完成相互间的通信，存储器52用于存储计算机程序，通信器53用于和其他设备进行通信，处理器51用于运行计算机程序，使电子终端执行如上缝制设备的智能工序识别及计件方法的各个步骤。
上述提到的系统总线可以是外设部件互连标准(Peripheral Component Interconnect，简称PCI)总线或扩展工业标准结构(Extended Industry Standard Architecture，简称EISA)总线等。该系统总线可以分为地址总线、数据总线、控制总线等。为便于表示，图中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。通信接口用于实现数据库访问装置与其他设备(例如客户端、读写库和只读库)之间的通信。存储器可能包含随机存取存储器(Random Access Memory，简称RAM)，也可能还包括非易失性存储器(non-volatile memory)，例如至少一个磁盘存储器。
上述的处理器可以是通用处理器，包括中央处理器(Central Processing Unit，简称CPU)、网络处理器(Network Processor，简称NP)等；还可以是数字信号处理器(Digital Signal Processing，简称DSP)、专用集成电路(Application Specific Integrated Circuit，简称ASIC)、现场可编程门阵列(Field－Programmable Gate Array，简称FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。
本发明还提供一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现所述缝制设备的智能工序识别及计件方法。
本领域普通技术人员可以理解：实现上述各方法实施例的全部或部分步骤可以通过计算机程序相关的硬件来完成。前述的计算机程序可以存储于一计算机可读存储介质中。该程序在执行时，执行包括上述各方法实施例的步骤；而前述的存储介质包括：ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
于本申请提供的实施例中，所述计算机可读写存储介质可以包括只读存储器、随机存取存储器、EEPROM、CD-ROM或其它光盘存储装置、磁盘存储装置或其它磁存储设备、闪存、 U盘、移动硬盘、或者能够用于存储具有指令或数据结构形式的期望的程序代码并能够由计算机进行存取的任何其它介质。另外，任何连接都可以适当地称为计算机可读介质。例如，如果指令是使用同轴电缆、光纤光缆、双绞线、数字订户线(DSL)或者诸如红外线、无线电和微波之类的无线技术，从网站、服务器或其它远程源发送的，则所述同轴电缆、光纤光缆、双绞线、DSL或者诸如红外线、无线电和微波之类的无线技术包括在所述介质的定义中。然而，应当理解的是，计算机可读写存储介质和数据存储介质不包括连接、载波、信号或者其它暂时性介质，而是旨在针对于非暂时性、有形的存储介质。如申请中所使用的磁盘和光盘包括压缩光盘(CD)、激光光盘、光盘、数字多功能光盘(DVD)、软盘和蓝光光盘，其中，磁盘通常磁性地复制数据，而光盘则用激光来光学地复制数据。
综上所述，本申请提供缝制设备的智能工序识别及计件方法、系统、终端及介质，本发明可在已知的多个工序模板中识别出数据所对应的工序，这样不用每次换工序时设定或者修改模板，可以减少额外的人力工作，降低成本；仅需采集缝纫机中的电信号：电机运动时缝纫针数的数据，记录其时间序列下的数据情况并进行计算。这样大大降低了对数据采集记录的要求，同时减轻了数据传输负荷，也减小了后续计算的复杂程度；对于每件的起始、结束点进行了准确的判断，为提高计件准确率间接提供了帮助，同时为后续对工人的技术水平进行进一步细致的分析提供了依据；采纳了动态时间规整法，该方法广泛应用于模板匹配问题中，但是在之前的专利文献中并未应用于计件算法中。通过该方法，本方法提高了分割点的准确率；对于长工序、短工序都适用，扩大了工序使用范围，具有广阔的市场前景。所以，本申请有效克服了现有技术中的种种缺点而具高度产业利用价值。
上述实施例仅例示性说明本申请的原理及其功效，而非用于限制本申请。任何熟悉此技术的人士皆可在不违背本申请的精神及范畴下，对上述实施例进行修饰或改变。因此，举凡所属技术领域中具有通常知识者在未脱离本申请所揭示的精神与技术思想下所完成的一切等效修饰或改变，仍应由本申请的权利要求所涵盖。

Claims (10)

  1. 一种缝制设备的智能工序识别及计件方法，其特征在于，包括：
    获取由缝制设备的机械运动转化成的电信号，并根据所述电信号生成对应的基于时间序列的缝制数据；
    对所述缝制数据降维至两维，包括所述缝制设备中电机每次动作的时间间隔维度及相应的缝纫针数维度；
    根据所述缝制设备中电机每次动作的时间间隔维度及相应的缝纫针数维度，判断缝制数据所属的工序种类并确定对应的工序模板；
    在确定工序模板后，根据工序模板的电机运动时间间隔对待分割的缝制数据进行计件分割点的选取以进行计件。
  2. 根据权利要求1所述的缝制设备的智能工序识别及计件方法，其特征在于，所述根据所述缝制设备中电机每次动作的时间间隔维度及相应的缝纫针数维度，判断缝制数据所属的工序种类并确定对应的工序模板，包括：
    根据不同工序模板的长度从所述缝制数据中取出长度相适应的数据段，以用于与工序模板进行比对；
    根据各所述工序模板中电机每个动作的停顿点预测该工序模板是否可分割，并将可分割工序模板分割为多段子工序；
    对于可分割工序模板，若与之比对的数据段也能够根据电机每次动作的时间间隔分割成相同的段数，则将所述可分割工序模板存入备选库，并将从该数据段分割出的各子段与从该可分割工序模板分割出的各子工序对应构成各比对组以进行相似度计算，每个比对组的相似度计算结果进行累加后得到该可分割工序模板与对应数据段之间的相似度计算总结果；
    对于不可分割的工序模板，将所述不可分割工序模板存入备选库，并计算与对应数据段之间的相似度以进行比对；
    从所述备选库中选取与输入的缝制数据差异度最小的工序模板作为该缝制数据的工序模板。
  3. 根据权利要求1所述的缝制设备的智能工序识别及计件方法，其特征在于，所述将从该数据段分割出的各子段与从该可分割工序模板分割出的各子工序对应构成各比对组以进行相似度计算，包括基于动态时间归整算法计算两者在针数、缝纫段数方面的差异程度。
  4. 根据权利要求1所述的缝制设备的智能工序识别及计件方法，其特征在于，将传入的缝制数据中的前若干项缝制数据进行比对检测，包括将这前若干项缝制数据与各工序模板的相似度平均值进行比较；若偏差太大则可判断出现了偏差；若无偏差或偏差较小则可判断未出现偏差。
  5. 根据权利要求1所述的缝制设备的智能工序识别及计件方法，其特征在于，所述根据工序模板的电机运动时间间隔对待分割的缝制数据进行计件分割点的选取以进行计件，包括：根据所述工序模板长度的不同将工序模板分为长工序模板和短工序模板。
  6. 根据权利要求5所述的缝制设备的智能工序识别及计件方法，其特征在于，对长工序模板的计件过程包括：
    根据工序模板的电机运动时间间隔与阈值进行比较后初筛多个疑似分割点；
    对于初筛出的各疑似分割点，计算分割段与工序模板中数据的相似度，选取相似度最高的疑似分割点作为最终的计件分割点；
    根据工序模板的开头特征和结尾特征对所述计件分割点进行再调整，以判断该计件分割点是否确为模板中缝制件的结束点。
  7. 根据权利要求5所述的缝制设备的智能工序识别及计件方法，其特征在于，对短工序模板的计件过程包括：计算起始点到各疑似分割点的数据与模板数据的差异程度，选取差异度最小的疑似分割点作为最终的计件分割点。
  8. 一种缝制设备的智能工序识别及计件系统，其特征在于，包括：
    获取模块，用于获取由缝制设备的机械运动转化成的电信号，并根据所述电信号生成对应的基于时间序列的缝制数据；
    降维模块，用于对所述缝制数据降维至两维，包括所述缝制设备中电机每次动作的时间间隔维度及相应的缝纫针数维度；
    模板模块，根据所述缝制设备中电机每次动作的时间间隔维度及相应的缝纫针数维度，判断缝制数据所属的工序种类并确定对应的工序模板；
    计件模块，用于在确定工序模板后，根据工序模板的电机运动时间间隔对待分割的缝制数据进行计件分割点的选取以进行计件。
  9. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现权利要求1至7中任一项所述缝制设备的智能工序识别及计件方法。
  10. 一种电子终端，其特征在于，包括：处理器及存储器；
    所述存储器用于存储计算机程序；
    所述处理器用于执行所述存储器存储的计算机程序，以使所述终端执行如权利要求1至7中任一项所述缝制设备的智能工序识别及计件方法。
PCT/CN2023/090560 2022-08-02 2023-04-25 缝制设备的智能工序识别及计件方法、系统、终端及介质 WO2024027227A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210921944.7 2022-08-02
CN202210921944.7A CN117556185A (zh) 2022-08-02 2022-08-02 缝制设备的智能工序识别及计件方法、系统、终端及介质

Publications (1)

Publication Number Publication Date
WO2024027227A1 true WO2024027227A1 (zh) 2024-02-08

Family

ID=89819058

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/090560 WO2024027227A1 (zh) 2022-08-02 2023-04-25 缝制设备的智能工序识别及计件方法、系统、终端及介质

Country Status (2)

Country Link
CN (1) CN117556185A (zh)
WO (1) WO2024027227A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101469486A (zh) * 2007-12-28 2009-07-01 Juki株式会社 缝纫机的作业分析装置
JP2010061519A (ja) * 2008-09-05 2010-03-18 Juki Corp 作業分析装置
KR20190064859A (ko) * 2017-12-01 2019-06-11 김태강 사물 인터넷을 이용한 봉제품 제조용 스마트 계수기 및 방법, 그리고 이를 구비하는 봉제 생산 관리 시스템 및 그 처리 방법
WO2021125727A1 (ko) * 2019-12-18 2021-06-24 한국생산기술연구원 의류생산 통합시스템

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101469486A (zh) * 2007-12-28 2009-07-01 Juki株式会社 缝纫机的作业分析装置
JP2010061519A (ja) * 2008-09-05 2010-03-18 Juki Corp 作業分析装置
KR20190064859A (ko) * 2017-12-01 2019-06-11 김태강 사물 인터넷을 이용한 봉제품 제조용 스마트 계수기 및 방법, 그리고 이를 구비하는 봉제 생산 관리 시스템 및 그 처리 방법
WO2021125727A1 (ko) * 2019-12-18 2021-06-24 한국생산기술연구원 의류생산 통합시스템

Also Published As

Publication number Publication date
CN117556185A (zh) 2024-02-13

Similar Documents

Publication Publication Date Title
US11836996B2 (en) Method and apparatus for recognizing text
CN110210294A (zh) 优化模型的评价方法、装置、存储介质及计算机设备
JP2017138989A (ja) 画像に含まれるテキストを検出する方法、装置及びコンピュータ読み取り可能な記録媒体
CN113409555B (zh) 一种基于物联网的实时报警联动方法及系统
CN115392501A (zh) 数据采集方法、装置、电子设备及存储介质
CN111738120A (zh) 人物识别方法、装置、电子设备及存储介质
WO2024027227A1 (zh) 缝制设备的智能工序识别及计件方法、系统、终端及介质
CN114742124A (zh) 一种异常数据处理方法、系统及装置
US10402303B2 (en) Determining similarities in computer software codes for performance analysis
Zhou et al. An efficient high-quality medical lesion image data labeling method based on active learning
CN117272646A (zh) 一种基于孪生神经网络的仿真软件自动操作优化方法
CN111858285B (zh) 视频操作行为的异常识别方法、装置、服务器及存储介质
CN116467360A (zh) 产品信息分析方法、装置及电子设备
CN114187658A (zh) 一种输入操作的识别方法及设备
CN110177006B (zh) 基于接口预测模型的节点测试方法及装置
Wang et al. The design of intelligent production line for clothing industry
CN112506565A (zh) 处理器微体系结构事件的重要性确定方法、介质和设备
CN112749781A (zh) 关键点预测方法、系统、电子设备、存储介质
WO2022267070A1 (en) Devices and methods for supporting intent driven networking
CN105447017A (zh) 一种制程生产管控系统及其方法
Zhang et al. Local feature based dynamic time warping
WO2024027225A1 (zh) 基于最优分割的智能计件方法、装置、终端及存储介质
JP2020101900A (ja) 画像検査装置、画像検査のための学習方法および画像検査プログラム
US20230237420A1 (en) Business data course management system and business data course management method thereof
CN116612302A (zh) 一种图像检测方法、设备及计算机可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23848938

Country of ref document: EP

Kind code of ref document: A1