WO2024027225A1

WO2024027225A1 - Optimal-segmentation-based intelligent piece counting method, apparatus, terminal and storage medium

Info

Publication number: WO2024027225A1
Application number: PCT/CN2023/090546
Authority: WO
Inventors: 曾树杰; 韩安太; 单一舒; 栗硕; 曲凯朝
Original assignee: 杰克科技股份有限公司
Priority date: 2022-08-02
Filing date: 2023-04-25
Publication date: 2024-02-08
Also published as: CN117556861A

Abstract

The present invention provides an optimal-segmentation-based intelligent piece counting method, an apparatus, a terminal and a storage medium. The method comprises: acquiring process template data; acquiring sewing apparatus operation data of sewn pieces to be counted, and cropping a piece counting data window; according to sewing feature parameters in the process template data, setting a segmentation point between pieces for the piece counting data window; on the basis of the set segmentation point between pieces in the piece counting data window, carrying out optimal piece counting on the piece counting data window by using an optimal segmentation algorithm; and updating the total piece counting number of said sewn pieces according to a piece counting result of optimal piece counting. The present invention has high applicability and high piece counting accuracy; abnormal sewing situations can be identified during the piece counting process, thus discovering quality problems promptly; the use is easy, requiring no additional operation of workers; and during the piece counting process, sewing start and sewing end time points of each piece can be accurately recognized, thereby facilitating analysis.

Description

Intelligent piece counting method, device, terminal and storage medium based on optimal segmentation

Technical field

The present invention relates to the technical field of garment piece counting, and in particular to an intelligent piece counting method, device, terminal and storage medium based on optimal segmentation.

Background technique

Piece counting is a very important link for garment factory production management and financial settlement. The wage settlement of most garment factories is based on the piece-rate system. The original piece-rate method was that each worker manually recorded the number of pieces processed, and the factory relied on the number of pieces delivered in the order. During settlement, the number of pieces was often inconsistent between the two parties, and it was difficult to trace. Right or wrong often leads to conflicts between factories and workers. In response to this problem, the current solutions mainly fall into two categories: the first is to add a piece counting module to the machine, and record the keystrokes every time a piece is finished (mostly seen in hanging systems); the second is to bundle two pieces on each package of pieces. QR code, scan the code with your mobile phone or RFID every time you complete a package. The above method not only increases the operating steps and increases the labor intensity of workers, but also requires the installation of additional equipment outside the sewing machine, which increases production costs.

Some existing patents propose counting pieces by determining whether data such as sewing machine thread trimming, needle count, and presser foot lift meet set statistical rules. For example, the piece counting module of patent CN 107345346 B counts pieces based on whether the number of sewing stitches and the number of thread trimmings are within the set target value range. The above method requires resetting the target number of thread trimmings and the number of stitches every time the process is switched, which is complicated to operate; it is not suitable for abnormal stops during the processing (such as thread breakage, bobbin thread replacement), rework, and manual thread trimming, and has poor applicability. ; Because the piece counting rules are too simple and cannot cover complex and changeable processes and processing conditions, the accuracy of piece counting is poor, making it difficult to apply and promote in actual production.

Contents of the invention

In view of the above shortcomings of the prior art, the purpose of the present invention is to provide an intelligent piece counting method, device, terminal and storage medium based on optimal segmentation to solve the problems of inaccurate piece counting and low efficiency in the prior art.

In order to achieve the above objectives and other related objectives, the first aspect of the present invention provides an intelligent piece counting method based on optimal segmentation, including: obtaining process template data; obtaining sewing equipment operation data of the pieces to be sewn and intercepting the piece counting data window; according to the sewing characteristic parameters in the process template data, set the segmentation points between pieces for the piece counting data window; based on the segmentation points between pieces set in the piece counting data window, use The optimal segmentation algorithm performs optimal piece counting on the piece counting data window, and updates the total number of pieces to be sewn to be counted based on the piece counting results of the optimal piece counting.

In some embodiments of the first aspect of the present invention, the method of obtaining process template data includes: during the sample sewing process, obtaining the process template data through a data acquisition module and a human-computer interaction module; or, according to standards Hours database compilation Obtain process template data from edited or exported sewing data.

In some embodiments of the first aspect of the present invention, the interception method of the piece counting data window includes any of the following: intercepting data of a fixed time length from the sewing equipment operation data as a piece counting data window; for the previous For the non-whole-piece legacy data after the piece counting is completed in the piece counting data window, the sewing equipment operating data is added and the needle value is accumulated until the total number of needles in the current piece counting data window is a preset integer multiple of the total number of needles in the process template data or a preset Stop signal; wherein, the calculation process of the total number of stitches in the current piece counting data window includes: taking the total number of stitches in the process template data as a benchmark, and dividing the total number of stitches in the current piece counting data window by the total number of stitches in the process template data. The rounded-up value after is the multiplication multiple, which is obtained by multiplying the base and the multiplication multiple.

In some embodiments of the first aspect of the present invention, it also includes pre-processing the process template data and the intercepted piece-rate data window data. The pre-processing method includes: based on the time stamp, the process template data and the piece-rate data are pre-processed. Add time interval column data to the window data; delete the data items whose spindle motor stop time is less than the preset time to merge the data of the upper and lower adjacent items of the deleted data items; process the piece data window based on the data in the time interval column in the process template Abnormal data in the time interval column; normalize the process template data and piece counting data window data.

In some embodiments of the first aspect of the present invention, setting segmentation points between pieces for the piece counting data window based on sewing characteristic parameters in the process template data includes setting segmentation points between pieces based on the sewing characteristics. Segmenting the material picking and placing time in the parameters includes: using the data item in the time interval column of the piece counting data window that is greater than the product of the material picking and placing time and a preset threshold as the segmentation point.

In some embodiments of the first aspect of the present invention, the use of an optimal segmentation algorithm to perform optimal piece counting on the piece counting data window includes: based on the segmentation points between pieces set in the piece counting data window. , divide the data in the piece counting data window into multiple segments of segmented data; calculate the distance between each segmented data and the process template data; calculate the segmentation based on the distance between all segmented data and the process template data. Segment loss function; find the minimum value of the segmentation loss function to obtain the number of segments and segmentation method corresponding to the minimum value; based on the number of segments and segmentation method corresponding to the minimum value, obtain each segmentation loss function. The total number of needles in the segmented data, and based on whether the total number of needles is less than the needle number threshold set based on the total number of needles in the process template data, determine whether the segment is included in the number of pieces; output the piece count of the piece counting data window Result information.

In some embodiments of the first aspect of the present invention, calculating the segmentation loss function based on the distance between all segmented data and the process template data includes: calculating the distance between each segmented data and the process template data. The sum of distances is the piecewise loss function.

In order to achieve the above objects and other related objects, the second aspect of the present invention provides an intelligent piece counting device based on optimal segmentation, including: a template module for obtaining process template data; an interception module for obtaining sewing parts to be counted The operating data of the sewing equipment and intercept the piece counting data window; the segmentation module is used to calculate the sewing characteristic parameters based on the process template data. Set segmentation points between pieces for the piece counting data window; a piece counting module is configured to use an optimal segmentation algorithm to segment the piece counting based on the segmentation points between pieces set in the piece counting data window. The data window performs optimal piece counting, and updates the total number of pieces to be sewn to be counted based on the piece counting results of the optimal piece counting.

In order to achieve the above objects and other related objects, a third aspect of the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the intelligent piece counting based on optimal segmentation is implemented. method.

In order to achieve the above objects and other related objects, a fourth aspect of the present invention provides an intelligent piece counting terminal, including: a processor and a memory; the memory is used to store computer programs, and the processor is used to execute the computer stored in the memory. A program is provided to cause the terminal to execute the intelligent piece counting method based on optimal division.

As mentioned above, the intelligent piece counting method, device, terminal and storage medium based on optimal segmentation of the present invention have the following beneficial effects:

(1) The technical solution of the present invention has strong applicability and high piece counting accuracy: accurate piece counting can be obtained by using the most basic operating data of the sewing machine (number of stitches, spindle motor start and stop time), combined with the optimal segmentation algorithm and distance algorithm, so There will be no situation where pieces cannot be counted when there is no thread trimming or when the presser foot is raised.

(2) The present invention can identify sewing abnormalities (such as rework, non-compliance with sewing process requirements, etc.) during the piece counting process, and can help workers discover quality problems in time, avoid unnecessary rework, and improve sewing efficiency.

(3) The technical solution of the present invention is easy to use and does not require additional operations by workers, and the process template data can be obtained during sample processing or process decomposition. The entire piece counting process does not require workers to press buttons or scan codes, and is fully automated.

(4) In the piece counting process, the present invention can accurately identify the time point (accurate segmentation) when each piece starts and ends sewing, providing workers with learning curve analysis, efficiency analysis, skill evaluation, and equipment utilization rate analysis. Possibility is provided.

Description of drawings

Figure 1 shows a schematic flowchart of an intelligent piece counting method based on optimal segmentation in an embodiment of the present invention.

FIG. 2 shows a schematic flowchart of intercepting the piece counting data window in an embodiment of the present invention.

Figure 3 shows a schematic structural diagram of an intelligent piece counting terminal in an embodiment of the present invention.

Figure 4 shows a schematic structural diagram of an intelligent piece counting device based on optimal segmentation in an embodiment of the present invention.

Detailed ways

The following describes the embodiments of the present invention through specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be based on different viewpoints and applications without departing from the spirit of the present invention. God makes various modifications or changes. It should be noted that, as long as there is no conflict, the following embodiments and the features in the embodiments can be combined with each other.

It should be noted that in the following description, reference is made to the accompanying drawings, which describe several embodiments of the present invention. It is to be understood that other embodiments may be utilized and mechanical, structural, electrical, as well as operational changes may be made without departing from the spirit and scope of the present invention. The following detailed description is not to be considered limiting, and the scope of embodiments of the present invention is limited 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 be limiting of the invention. Spatially related terms, such as "upper", "lower", "left", "right", "below", "below", "bottom", "above", "upper", etc., may be used in the text to facilitate explanation The relationship of one element or feature to another illustrated in the figures.

In the present invention, unless otherwise clearly stated and limited, the terms "installation", "connection", "connection", "fixing", "holding" and other terms should be understood in a broad sense. For example, it 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. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

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" and "including" indicate the presence of stated features, operations, elements, components, items, categories, and/or groups, but do not exclude one or more other features, operations, elements, components, The presence, occurrence, or addition of items, categories, and/or groups. The terms "or" and "and/or" as used herein are to be construed as inclusive or to mean any one or any combination. Therefore, "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.

In view of the problems of piece counting in the above background technology, the present invention proposes a piece counting method based on segmentation of sewing machine operating data. The piece counting is performed by optimally segmenting a section of sewing machine operating data and combining it with a similarity measurement method. Among the sewing machine operating data used, only the spindle motor start and stop, and stitch count data can be used to achieve high piece counting accuracy and segmentation accuracy. Data such as thread trimming and presser foot lifting can also be added to further improve piece counting. accuracy. At the same time, this method can identify sewing abnormalities (rework, non-compliance with process sewing requirements) during the piece counting process, helping workers discover quality problems in time and avoid unnecessary rework.

In order to make the purpose, technical solutions and advantages of the present invention more clear, the technical solutions in the embodiments of the present invention are further described in detail through the following embodiments in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to explain the invention and are not intended to limit the invention.

As shown in Figure 1, a schematic flow chart of an intelligent piece counting method based on optimal segmentation in an embodiment of the present invention is shown. The intelligent piece counting method in this embodiment mainly includes the following steps:

Step S11: Obtain process template data.

In some examples, the method of obtaining process template data includes any of the following:

Acquisition method 1) During the sample sewing process, the process template data is obtained through the data collection module and human-computer interaction module. The data collection module includes, but is not limited to, an NFC card reader, a QR code/barcode reader, etc.; the human-computer interaction module includes, but is not limited to, a touch screen that implements data collection in response to a user's touch operation or through a Voice interaction modules that analyze speech and realize data collection, etc.

Obtaining method 2) Obtain the process template data based on the sewing data edited or exported from the standard working hours library. Standard working hours refer to the time required to complete a certain operation at a normal speed by qualified and well-trained operators under certain standard conditions and using certain operating methods; standard working hours consist of standard operating time and standard preparation time. , specifically including effective operating time and time consumed in preparation before and during the event. The standard working hours database is a database used to record and store standard working hours. Therefore, sewing data edited or exported from the standard working hours library can be used as process template data.

In some examples, the process template data includes but is not limited to spindle motor start and stop time data, sewing stitch number data, etc. Generally speaking, the process template data also includes a time interval column. The first data in the time interval column is the material picking and placing time. This material picking and placing time can also be included in the last data item. This is consistent with the collection of the process template. It is related to the setting of data, which is not limited in this embodiment.

Step S12: Obtain the sewing equipment operating data of the piece to be sewn and intercept the piece counting data window.

In some examples, the sewing equipment operation data of the pieces to be sewn is obtained through a data interface; the data interface includes but is not limited to a serial port/COM port, USB interface, RS232 interface, RS485 interface, etc. Common formats of the sewing equipment operating data include (time stamp, event type, value), for example, where the event types include but are not limited to spindle motor start, stop, thread trimming, presser foot lift, seam reinforcement, etc.

In some examples, the piece counting data window refers to the data segment used to analyze the number of processed pieces, and the interception method of the piece counting data window includes any of the following:

Interception method 1) intercept data of a fixed time length from the sewing equipment operation data as a piece counting data window.

Interception method 2) For the non-whole-piece legacy data after the piece counting is completed in the previous piece counting data window, add the sewing equipment operating data and accumulate the needle value until the total number of needles in the current piece counting data window is the preset total number of needles in the process template data An integer multiple or a preset stop signal appears; wherein, the calculation process of the total number of stitches in the current piece counting data window includes: taking the total number of stitches in the process template data as a benchmark, and dividing by the total number of stitches in the current piece counting data window The rounded-up value after the total number of stitches in the process template data is used as the multiplication multiple, and is obtained by multiplying the base and the multiplication multiple. Wherein, the preset stop signal includes but does not include It is limited to signals such as resting, changing processes or shutting down the machine.

Taking the flow chart in Figure 2 as an example, the implementation process of the above interception method 2 is as follows:

1) Start.

2) Cache sewing machine operating data, pieces=5.

3) Is Level empty?

It should be understood that pieces are preset integer multiples. Level is a storage space. Whether Level is empty indicates whether there is non-whole piece data left in the previous piece counting data window after piece counting is completed. The flag Level is only initialized to empty when switching processes; if the flag Level is empty, it means the above A piece-rate data window has no incomplete piece data left after piece counting is completed; otherwise, it means that the previous piece-rate data window has incomplete piece data left after piece counting is completed.

4) If Level is empty, in the current piece counting data window, read the sewing machine operating data and accumulate the needle value.

5) If Level is not empty, in the current piece counting data window, first read the data in Level, then read in the additional sewing machine operating data, and accumulate the needle value.

6) Does it satisfy pieces=5 or does a preset stop signal appear?

7) If not satisfied, continue reading data in the current piece counting data window.

8) If satisfied, then

9) Output the current piece counting data window data and pieces value.

In some examples, the process template data and the intercepted piece data window data are preprocessed. The preprocessing process includes but is not limited to the following:

Preprocessing 1) Add time interval column data to the process template data and piece counting data window data according to the timestamp; the time interval column data is one of the main consideration dimensions of piece counting, so it needs to be added to both the process template data and the piece counting data window data. .

Preprocessing 2) Delete the data items whose stop time of the spindle motor is less than the preset time to merge the data of the upper and lower adjacent items of the deleted data items; the merged data includes the spindle motor running needle number data, time interval data, etc. Data merging can effectively reduce the amount of data and reduce the amount of calculations.

Preprocessing 3) Process the abnormal data in the time interval column in the piece counting data window based on the data in the time interval column in the process template. Specifically, you can first take the maximum value max in the time interval column in the process template, and then replace all values greater than the maximum value max in the time interval column in the piece counting data window with the maximum value max.

Preprocessing 4) Normalize the process template data and piece counting data window data. Specifically, normalization processing is to convert multi-dimensional similarity measures into dimensionless data, usually in the range [0,1]; the normalization processing method used can be min-max linear function normalization, min and max are the minimum and maximum values respectively.

Specifically, min-max linear function normalization is to linearly transform the original data so that the result is mapped to the range of [0,1] to achieve proportional scaling of the original data. The normalization formula is as follows: Xnom =(X-Xmin)/(Xmax-Xmin); where X represents the original data, Xmax represents the minimum value, Xmax represents the maximum value, and Xnom represents the normalized value.

Step S13: Set segmentation points between pieces for the piece counting data window according to the sewing characteristic parameters in the process template data.

In this embodiment, the sewing characteristic parameters include but are not limited to: material picking and unloading time data, presser foot lifting data, thread trimming data or bartack data, etc. For ease of understanding, take the pick-and-place time data as an example. The possible segmentation points are set as: data items in the piece counting data window whose time interval column is greater than (pick-and-place time*threshold). The threshold (time_threshold) can be, for example, Set to 0.5, the advantage of this design is to reduce the calculation amount of the optimal split piece counting module, which is especially obvious for long processes (processes with a large amount of data in the last shift).

Step S14: Based on the segmentation points between pieces set in the piece counting data window, use an optimal segmentation algorithm to perform optimal piece counting on the piece counting data window.

It should be noted that the ordered sample clustering algorithm is also called the optimal segmentation algorithm. During clustering, samples are mixed together and classified according to distance or similarity coefficient standards, but the order of the original samples cannot be disrupted during clustering. , samples at the same stage are required to be connected to each other, that is, when clustering, samples must be sequentially adjacent to be in one category.

Specifically in this embodiment, the process of using the ordered sample clustering algorithm to perform optimal piece counting on the piece counting data window is stated as follows:

Step S141: Divide the data in the piece counting data window into multiple pieces of segmented data according to the set segmentation points between pieces in the piece counting data window.

Step S142: Calculate the distance between each segmented data and the process template data.

In some examples, a dynamic time warping algorithm may be used to calculate the distance between each piece of segmented data and the process template data. Specifically, each piece of segmented data and the process template data are separately subjected to one-hot encoding processing based on the sewing characteristic parameters; a dynamic time warping algorithm is used to calculate the relationship between each piece of segmented data and the process based on each sewing characteristic parameter. The distance value between the template data, and the smallest distance value is taken as the distance value between this segment data and the process template data; the larger the distance value, the greater the similarity between the segment data and the process template data The worse it is; on the contrary, it means the similarity between the two is better. Among them, the sewing characteristic parameters include but are not limited to: material picking and unloading time data, presser foot lifting data, thread trimming data or bartack seaming data, etc.

It should be noted that DTW (Dynamic Time Warping) refers to the dynamic time warping algorithm, which can be used to measure the similarity between two independent time series; the DTW algorithm is widely used in template matching problems and can better solve the problem of two independent time series. The problem of group data being difficult to compare due to different lengths. In DTW, distance is measured using the Euclidean distance method. Other It should 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.

In some examples, a Euclidean distance algorithm may be used to calculate the distance between each piece of segmented data and the process template data. Specifically, the statistical features between each segmented data and the process template data are respectively extracted, and the Euclidean distance between each segmented data and the process template data is calculated based on the statistical features; the larger the Euclidean distance value, the greater the segmentation. The worse the similarity between the data and the process template data; conversely, the better the similarity between the two; the statistical characteristics include but are not limited to the total number of needles, data length, pick-and-place time (i.e., the time interval column first data) etc.

Furthermore, the calculation formula of Euclidean distance is as follows:

Step S143: Calculate the segmentation loss function based on the distance between all segmented data and the process template data.

In this embodiment, the segmentation loss function is the sum of the distances between each segmented data and the process template data, expressed as: Among them, P(n,k) represents the segmentation method that divides n ordered data into k categories and makes the segmentation loss function reach the minimum value. The larger the value of the segmentation loss function, the worse the segmentation effect, and vice versa.

Step S144: Find the minimum value of the segmentation loss function to obtain the number of segments and the segmentation method corresponding to the minimum value.

In this embodiment, the minimum value of the piecewise loss function can be solved by solving the minimum loss function matrix L[P(n,k)]. The solution formula is as follows:
L[P(n,2)]=min _2<=j<=n (D(1,j-1)+D(j,n));
L[P(n,k)]=min _k<=j<=n (L[P(j-1,k-1)]+D(j,n));

Among them, n = len (possible segmentation point data), and the value range of k is [pieces-2, pieces+2]; the possible segmentation point data is the seam in the process template data in the above step S13. The custom feature parameter sets the segmentation point between pieces in the piece counting data window. Calculate the number of segments k and segmentation method P(n,k) corresponding to the minimum value of L[P(n,k)] in the segmentation loss function matrix.

Step S145: Based on the number of segments and the segmentation method corresponding to the minimum value, obtain the total number of needles in each segment of segmented data, and determine whether the total number of needles is less than the needle number threshold set based on the total number of needles in the process template data. , determine whether the segment is included in the number of pieces.

For example, the needle number threshold set based on the total number of needles of the process template data can be set to (the total number of needles of the process template data * 0.6), if the total number of needles of the segmented data < (the total number of needles of the process template data Number of stitches * 0.6), then the segmented data of this section will not be included in the number of pieces, and it will prompt that the products sewn in this time period are most likely to be defective products (there is rework or abnormal sewing).

Step S146: Output the piece counting result information of the piece counting data window.

Specifically, after the piece counting is completed, the piece counting result information is output, and the last segment of data is assigned to level. Therefore, except for the last segment of data and the data that is judged to be defective and is not included in the piece count, the other segments of data are included in the piece count. .

Step S15: Update the total piece number of the sewing parts to be counted according to the optimal piece counting result of the piece counting data window.

Specifically, the piece count obtained in the above step S14 is added to the total piece count; if a preset stop signal (such as a break, process change, or shutdown signal) appears at the end of the piece count window data, the total piece count is added. Increment the number of pieces by 1 and initialize level to empty.

The smart piece counting method provided by the embodiment of the present invention can be implemented on the terminal side or the server side. As for the hardware structure of the smart piece counting terminal, please refer to Figure 3, which is an optional hardware of the smart piece counting terminal 300 provided by the embodiment of the present invention. Structural diagram shows that the terminal 300 can be a mobile phone, a computer device, a tablet device, a personal digital processing device, a factory backend processing device, etc. The smart piece counting terminal 300 includes: at least one processor 301, a memory 302, at least one network interface 304 and a user interface 306. The various components in the device are coupled together through bus system 305 . It can be understood that the bus system 305 is used to implement connection communication between these components. In addition to the data bus, the bus system 305 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, various buses are labeled as bus systems in Figure 3.

The user interface 306 may include a display, keyboard, mouse, trackball, click gun, keys, buttons, touch pad or touch screen, etc.

It can be understood that the memory 302 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM, Read Only Memory) or a programmable read-only memory (PROM, Programmable Read-Only Memory), which is used as an external cache. By way of illustration, but not limitation, many forms of RAM are available, such as static random access memory (SRAM, StaticRandom Access Memory), synchronous static random access memory (SSRAM, Synchronous Static RandomAccess Memory). Memories described in embodiments of the present invention are intended to include, but are not limited to, these and any other suitable categories of memory.

The memory 302 in the embodiment of the present invention is used to store various types of data to support the operation of the intelligent piece counting terminal 300 . Examples of these data include: any executable program used to operate on the intelligent piecework terminal 300, such as operating system 3021 and application program 3022; operating system 3021 includes various system programs, such as framework layer, core library layer, driver layer, etc. , used to implement various basic services and handle hardware-based tasks. The application program 3022 may include various application programs, such as a media player (MediaPlayer), a browser (Browser), etc., and is used to implement various application services. Implementation of the intelligent piece counting method provided by the embodiment of the present invention may be included in the application program 3022.

The methods disclosed in the above embodiments of the present invention can be applied to the processor 301 or implemented by the processor 301. The processor 301 may be an integrated circuit chip with signal processing capabilities. During the implementation process, each step of the above method can be completed by instructions in the form of hardware integrated logic circuits or software in the processor 301 . The above-mentioned processor 301 may be a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 301 can implement or execute each method, step and logical block diagram disclosed in the embodiment of the present invention. The general processor 301 may be a microprocessor or any conventional processor, etc. The steps of the accessory optimization method provided by the embodiments of the present invention can be directly implemented by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, and the storage medium is located in a memory. The processor reads the information in the memory and completes the steps of the foregoing method in combination with its hardware.

In an exemplary embodiment, the smart piece counting terminal 300 may be configured by one or more Application Specific Integrated Circuits (ASICs, Application Specific Integrated Circuits), DSPs, Programmable Logic Devices (PLDs, Programmable Logic Devices), Complex Programmable Logic Devices ( CPLD, Complex Programmable LogicDevice), used to execute the aforementioned method.

As shown in Figure 4, a schematic structural diagram of an intelligent piece counting device based on optimal segmentation in an embodiment of the present invention is shown. The intelligent piece counting device 400 in this embodiment includes a template module 401, an interception module 402, a segmentation module 403 and a piece counting module 404.

A template module 401 is included for obtaining process template data.

In some examples, the template module 401 obtains the process template data by: during the sample sewing process, obtaining the process template data through the data collection module and the human-computer interaction module; or, editing or exporting it according to the standard working hours library The sewing data obtains the process template data.

The interception module 402 is used to obtain the sewing equipment operating data of the pieces to be sewn and intercept the piece counting data window.

In some examples, the interception module 402 intercepts the piece counting data window by: intercepting data of a fixed time length from the sewing equipment operating data as the piece counting data window; or, for the piece counting data window after completing the piece counting, For non-whole-piece legacy data, add sewing equipment operating data and accumulate needle values until the total number of needles in the current piece counting data window is a preset integer multiple of the total number of needles in the process template data or a preset stop signal appears; wherein, the The calculation process of the total number of stitches in the current piece-counting data window includes: taking the total number of stitches in the process template data as the benchmark, and dividing the total number of stitches in the current piece-counting data window by the total number of stitches in the process template data, and the rounded-up value is The multiplication factor is obtained by multiplying the base and the multiplication factor.

Further, the intelligent piece counting device 400 also includes a preprocessing module 405 for processing the process template data with and intercepted piece-counting data window data for preprocessing. The pre-processing methods include: adding time interval column data to the process template data and piece-counting data window data according to the timestamp; deleting data items whose spindle motor stop time is less than the preset time. To merge the data of the upper and lower adjacent items of the deleted data items; according to the data of the time interval column in the process template, process the abnormal data of the time interval column in the piece-rate data window; classify the process template data and piece-rate data window data Unified processing.

The segmentation module 403 is used to set segmentation points between pieces for the piece counting data window according to the sewing characteristic parameters in the process template data.

In some examples, the segmentation method of the segmentation module 403 includes: using the data items in the time interval column of the piece counting data window that are greater than the product of the pick-and-place material time and a preset threshold as segmentation points.

The piece counting module 404 is configured to perform optimal piece counting on the piece counting data window using an optimal segmentation algorithm based on the segmentation points between pieces set in the piece counting data window, and update the piece counting results according to the optimal piece counting result. Indicates the total number of pieces to be sewn.

In some examples, the piece counting module 404 uses an optimal segmentation algorithm to perform optimal piece counting on the piece counting data window, including: dividing the piece counting data according to the segmentation points between pieces set in the piece counting data window. The data in the data window is divided into multiple segments of segmented data; the distance between each segmented data and the process template data is calculated; the segmentation loss function is calculated based on the distance between all segmented data and the process template data; and Take the minimum value of the segmentation loss function to obtain the segmentation number and segmentation method corresponding to the minimum value; based on the segmentation number and segmentation method corresponding to the minimum value, obtain the segmentation data of each segment The total number of stitches, and based on whether the total number of stitches is less than the stitch number threshold set based on the total stitch number of the process template data, determine whether the segment is included in the number of pieces; output the piece counting result information of the piece counting data window.

Further, calculating the segmentation loss function based on the distance between all segmented data and the process template data includes: taking the sum of the distances between each segmented data and the process template data as the segmentation loss. function.

The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the intelligent piece counting method based on optimal segmentation is implemented.

Persons of ordinary skill in the art can understand that all or part of the steps to implement the above method embodiments can be completed by hardware related to computer programs. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, 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.

In the embodiments provided by the present invention, 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. For example, If instructions are sent 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, the coaxial Electrical cables, fiber optic cables, twisted pairs, DSL or wireless technologies such as infrared, radio and microwave are included in the definition of 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 transitory media, and are instead intended for non-transitory, tangible storage media. Disks and optical disks, as used in the application, 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.

To sum up, the present invention provides an intelligent piece counting method, device, terminal and storage medium based on optimal segmentation. The technical solution of the present invention has strong applicability and high piece counting accuracy: using the most basic operating data of the sewing machine (number of needles, spindle motor Start and stop time), combined with the optimal segmentation algorithm and distance algorithm, accurate piece counting can be obtained, so there will be no situation where piece counting cannot occur when there is no thread trimming or presser foot lifting data; the present invention can identify sewing abnormalities during the piece counting process ( Such as rework, non-compliance with sewing process requirements, etc.), it can help workers find quality problems in time, avoid unnecessary rework, and improve sewing efficiency; the technical solution of the present invention is easy to use, does not require additional operations by workers, and has process template data It can be obtained during sample processing or process decomposition. The entire piece counting process does not require workers to press buttons or scan codes, and is completed automatically; during the piece counting process, the present invention can accurately identify the time points at which each piece starts and ends sewing ( Accurate segmentation) provides the possibility for worker learning curve analysis, efficiency analysis, skill evaluation, and equipment utilization rate analysis. Therefore, the present invention effectively overcomes various shortcomings in the prior art and has high industrial utilization value.

The above embodiments only illustrate the principles and effects of the present invention, but are not intended to limit the present invention. Anyone familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the invention. Therefore, all equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed in the present invention shall still be covered by the claims of the present invention.

Claims

An intelligent piece counting method based on optimal segmentation, which is characterized by including:

Get process template data;

Obtain the sewing equipment operating data of the pieces to be sewn and intercept the piece counting data window;

Set segmentation points between pieces for the piece counting data window according to the sewing characteristic parameters in the process template data;

Based on the segmentation points between pieces set in the piece counting data window, use the optimal segmentation algorithm to perform optimal piece counting on the piece counting data window, and update the sewing of the pieces to be counted based on the piece counting results of the optimal piece counting The total number of pieces.
The intelligent piece counting method based on optimal segmentation according to claim 1, characterized in that the method of obtaining process template data includes: during the sample sewing process, obtaining the process through a data acquisition module and a human-computer interaction module. Template data; or, obtain process template data based on sewing data edited or exported from the standard working hours library.
The intelligent piece counting method based on optimal segmentation according to claim 1, characterized in that the interception method of the piece counting data window includes any of the following:

Intercept data of a fixed length of time from the sewing equipment operating data as a piece counting data window;

For the non-whole piece data left after the piece counting is completed in the previous piece counting data window, add the sewing equipment operating data and accumulate the needle value until the total number of needles in the current piece counting data window is the preset integer multiple of the total number of needles in the process template data or an Preset stop signal; wherein, the calculation process of the total number of stitches in the current piece counting data window includes: taking the total number of stitches in the process template data as a benchmark, and dividing the total number of stitches in the current piece counting data window by the process template data The rounded-up value after the total number of stitches is the multiplication factor, which is obtained by multiplying the base and the multiplication factor.
The intelligent piece counting method based on optimal segmentation according to claim 1, characterized in that it also includes preprocessing the process template data and the intercepted piece counting data window data, and the preprocessing method includes:

Add time interval column data to the process template data and piece counting data window data according to the timestamp;

Delete the data items whose spindle motor stop time is less than the preset time to merge the data of the upper and lower adjacent items of the deleted data items;

Process the abnormal data in the time interval column in the piece counting data window based on the data in the time interval column in the process template;

The process template data and piece counting data window data are normalized.
The intelligent piece counting method based on optimal segmentation according to claim 1, wherein the segmentation points between pieces are set for the piece counting data window according to the sewing characteristic parameters in the process template data, Including segmenting based on the picking and placing time in the sewing characteristic parameters, including: dividing the time interval column in the piece counting data window by greater than the The data item that is the product of the discharging time and a preset threshold is taken as the segmentation point.
The intelligent piece counting method based on optimal segmentation according to claim 1, characterized in that the use of the optimal segmentation algorithm to perform optimal piece counting on the piece counting data window includes:

According to the segmentation points between pieces set in the piece counting data window, divide the data in the piece counting data window into multiple segments of segmented data;

Calculate the distance between each segmented data and the process template data;

Calculate a segmentation loss function based on the distance between all segmented data and the process template data;

Find the minimum value of the segmentation loss function to obtain the number of segments and the segmentation method corresponding to the minimum value;

Based on the number of segments and the segmentation method corresponding to the minimum value, the total number of stitches in each segment of segmented data is obtained, and based on whether the total number of stitches is less than the stitch number threshold set based on the total number of stitches in the process template data, the number of stitches is determined. Whether segments are counted in the piece count;

Output the piece counting result information of the piece counting data window.
The intelligent piece counting method based on optimal segmentation according to claim 6, wherein calculating the segmentation loss function based on the distance between all segmented data and the process template data includes: segmenting each segment into The sum of the distances between the data and the process template data is the piecewise loss function.
An intelligent piece counting device based on optimal segmentation, characterized by including:

Template module, used to obtain process template data;

The interception module is used to obtain the sewing equipment operating data of the pieces to be sewn and intercept the piece counting data window;

A segmentation module, used to set segmentation points between pieces for the piece counting data window based on the sewing characteristic parameters in the process template data;

The piece counting module is configured to use the optimal segmentation algorithm to perform optimal piece counting on the piece counting data window based on the segmentation points between pieces set in the piece counting data window, and update the piece counting results according to the optimal piece counting. Indicates the total number of pieces to be sewn.
A computer-readable storage medium on which a computer program is stored, characterized in that when the computer program is executed by a processor, the intelligent piece counting method based on optimal segmentation described in any one of claims 1 to 7 is implemented.
An intelligent piece counting terminal is characterized by including: a processor and a memory;

The memory is used to store computer programs;

The processor is used to execute the computer program stored in the memory, so that the terminal executes the method of claim 1 The intelligent piece counting method based on optimal segmentation described in any one of to 7.