A method, system and memory for obtaining a piece count algorithm template for a sewing machine

Abstract

The application discloses a kind of sewing machine's piecework algorithm template acquisition method, system and memory, it is related to mechanical equipment technical field, comprising the following steps: obtaining template data, the source of template data is marked;Template data classification is carried out according to marking information;Template data is processed based on classification result;According to data processing result, generate piecework algorithm template;The application obtains algorithm template before piecework algorithm carries out piecework, provides basis for piecework algorithm, improves the efficiency and accuracy of piecework algorithm, obtains a variety of different algorithm templates, can be better applied to a variety of different working conditions, improves the universality of algorithm template use.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mechanical equipment, in particular to a method and system for obtaining a piecework algorithm template of a sewing machine and a memory. BACKGROUND

[0002] At present, Internet of Things sewing equipment has basically replaced ordinary sewing machines, and factories have changed from manual piecework to automatic piecework methods such as using work ticket software, hanging systems, and piecework algorithms. In order to meet the design of the piecework algorithm, a large amount of sewing machine action data (such as the number of stitches, the number of thread cutting times, etc.) is needed to establish and optimize the algorithm model. Different algorithm templates result in a large difference in the accuracy of the piecework algorithm. Most of the algorithms on the market currently require data generated during the worker's sewing process to be labeled (at least the data of the first three pieces of sewing need to be labeled) to obtain a template that matches the data. The piecework algorithm designed based on this has poor accuracy, so it is an urgent problem for the piecework algorithm design to more conveniently obtain a template through technical means.

[0003] For example, the "sewing machine automatic piecework method" provided in Chinese patent CN104018300A adds a piecework device connected to the signal of the sewing machine outside the sewing machine, and the piecework device is connected to the computer through a repeater to finally realize the automatic piecework function of the sewing machine. This method still needs to perform data template matching during the piecework process, has a certain delay, and is prone to piecework errors. In addition, the piecework algorithm template of this method is too single and difficult to meet the requirements of different working conditions. SUMMARY

[0004] The present application mainly solves the problems existing in the prior art, and provides a method for obtaining a piecework algorithm template of a sewing machine. Multiple different piecework algorithm modules are provided, so that the piecework algorithm does not need to perform template data matching again during the piecework process, thereby improving the piecework efficiency and accuracy.

[0005] The above technical problems of the present application are mainly solved by the following technical scheme: a method for obtaining a piecework algorithm template of a sewing machine, comprising the following steps:

[0006] Obtaining template data and marking the source of the template data;

[0007] Classifying the template data according to the marking information;

[0008] Performing data processing on the template data based on the classification result;

[0009] Generating a piecework algorithm template according to the data processing result.

[0010] Preferably, the source of the template data includes a web page and a workstation screen.

[0011] As preferred, the specific method of the template data classification is:

[0012] When the source of the template data is identified as the webpage end, the template data is stored in the webpage end sub-set;

[0013] When the source of the template data is identified as the station screen, the template data is stored in the station screen sub-set.

[0014] As preferred, when the template data comes from the webpage end, the template data includes: the serial number of the sewing machine, the sewing machine action signal with time stamp, the process initial signal with time stamp and the process completion signal with time stamp.

[0015] As preferred, when the template data comes from the station screen, the template data includes: the sewing machine action signal and the key signal interposed between the sewing machine action signals.

[0016] As preferred, when the template data comes from the webpage end, the template data is processed by using the time stamp algorithm, the process types required for sewing a garment are analyzed under the same serial number of the sewing machine, the sewing machine action signal is split according to different process types, the flag bit and the count bit are added to the sewing machine action signal, the process initial signal and the process completion signal, the time stamp data obtained is segmented based on the flag bit to obtain the segmented process curve of a piece of sewing garment, and the sewing integrity of the sewing garment is judged based on the count bit.

[0017] As preferred, when the template data comes from the station screen, a mark bit is generated according to the key signal, and a process is between two mark bits to obtain the process curve of a piece of sewing garment.

[0018] As preferred, the sewing machine action signal includes: the number of needles in the sewing process of the sewing machine and the number of times of cutting thread.

[0019] The application further provides a system for obtaining the piecework algorithm template of a sewing machine, which comprises: a collection module for obtaining template data and marking the source of the template data; an algorithm server for classifying the template data according to the marking information, processing the template data based on the classification result and generating a piecework algorithm template according to the data processing result.

[0020] The application further provides a memory which stores program instructions, and the program instructions execute the above method when running.

[0021] The application has the following beneficial effects:

[0022] 1. The algorithm template is obtained before the piecework algorithm performs piecework, which provides a basis for the piecework algorithm and improves the efficiency and accuracy of the piecework algorithm.

[0023] 2. Obtaining multiple different algorithm templates allows for better application to various working conditions, improving the universality of algorithm template usage. Attached Figure Description

[0024] Figure 1 This is a flowchart of the method for obtaining the piece-counting algorithm template according to an embodiment of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for explaining the present invention and are not intended to limit the invention.

[0026] Example:

[0027] A method for obtaining a piece-counting algorithm template for a sewing machine, such as Figure 1 As shown, it includes the following steps:

[0028] S1: Obtain template data and mark the source of the template data; the data source identifier is displayed in the data header of the template data. The template data is marked according to the data source identifier. The source of the template data includes web page and workstation screen. When the template data is provided from web page and workstation screen, the template data is transmitted to the cloud platform through the gateway device. The algorithm server is set in the cloud platform, and storage devices are set in the cloud platform for data storage. The algorithm server can quickly call the template data in the storage device.

[0029] When the template data comes from a webpage, the template data includes: the sewing machine's serial number, a sewing machine action signal with a timestamp, a process initiation signal with a timestamp, and a process completion signal with a timestamp. The specific method for obtaining template data from the webpage is as follows: using a mobile web app, input the sewing machine's serial number (used to distinguish each sewing machine). When the worker begins the first sewing process, clicking the button representing the start of work on the web app completes the initial signal annotation. When the worker completes a process, clicking the completion button on the web app completes a sewing completion signal annotation. The web app then sends the timestamp generated during annotation and the sewing completion signal to the algorithm server.

[0030] When the template data originates from the workstation screen, it includes sewing machine motion signals and button signals interspersed among them. The specific method for obtaining template data from the workstation screen is as follows: data is labeled using the buttons on both the small workstation screen and the large sewing machine screen. When the worker completes the first piece of sewing, clicking a button on either the small or large screen directly generates a data entry (a marker used to separate data) which is sent to the cloud platform and stored together with the sewing machine motion signals. In actual use, either the small workstation screen or the large sewing machine screen can be configured to meet the requirements, or both can be configured for double protection.

[0031] S2: Classify template data according to the tagging information; the specific method for classifying template data is as follows: when the source of the template data is identified as a web page, store the template data in the web page subset; when the source of the template data is identified as a workstation screen, store the template data in the workstation screen subset; store the web page subset and the workstation screen subset in the storage device.

[0032] The sewing machine action signals mentioned in this invention include the number of stitches and thread cuts during the garment sewing process. They also include the number of presser foot lifts, the stitch count interval, and the thread cut interval. The number of stitches and thread cuts determines whether the current stitch is complete; the stitch count interval and thread cut interval determine the smoothness of the sewing and whether sewing malfunctions have occurred; and comparing the presser foot lift count with the stitch count improves the piece counting accuracy of the algorithm template.

[0033] S3: Data processing of template data based on classification results; specific methods for data processing include processing of web page terminal subset data and workstation screen subset data.

[0034] The processing method for web page terminal set data is as follows: the stored process completion signal is segmented using a timestamp algorithm, each process is marked, and the same process and different processes are identified. When all different processes are completed and the same process is marked with the same number of marks, it indicates that a garment is sewn and a piece count is performed.

[0035] When the template data comes from a web page, a timestamp algorithm is used to process the template data. Under the same sewing machine serial number, the types of processes required for sewing garments are analyzed. The sewing machine action signals are split according to different process types. Flag bits and count bits are added to the sewing machine action signals, process initiation signals and process completion signals. Based on the flag bits, the acquired timestamp data is segmented to obtain the segmented process curve of a sewing garment. The sewing integrity of the garment is judged based on the count bits.

[0036] The processing method for the workstation screen subset data is as follows: The algorithm server obtains the sewing machine action signal corresponding to each button signal, obtains the current process of the garment based on the sewing machine action signal, obtains the number of button signals, generates a label based on the button signal, and the interval between two label positions is one process, thus obtaining the process curve of a sewn garment. When all processes are completed, it means that a garment is sewn and a piece count is performed.

[0037] S4: Generate a piece-counting algorithm template based on the data processing results.

[0038] This invention generates two types of piece-rate algorithm templates: a web-based template and a workstation-based template. The web-based template suffers from latency due to network communication delays and the inability of workers to synchronize web page clicks with process completion. However, its advantage lies in the absence of additional hardware costs; no extra hardware installation is required, only a web app on the worker's phone. The workstation-based template eliminates the latency caused by network communication, but still suffers from asynchronous button clicks. This latency can be eliminated through data processing and is therefore negligible. Its advantage is that when dealing with complex garments with numerous and detailed processes, workers can add more detailed annotations, improving the accuracy of subsequent piece-rate algorithms. However, the workstation-based design requires certain hardware costs.

[0039] This invention also provides a system for obtaining piece-rate algorithm templates for sewing machines, comprising: a data acquisition module for acquiring template data and marking the source of the template data; and an algorithm server for classifying the template data according to the marking information, processing the template data based on the classification results, and generating piece-rate algorithm templates based on the data processing results. The algorithm server of this invention is located within a cloud platform, which includes a storage device for storing the data acquired by the acquisition module. The algorithm server retrieves data from the storage device and stores the generated piece-rate algorithm templates in the storage device for the piece-rate server to retrieve for sewing machine piece-rate calculation.

[0040] The present invention also provides a memory that stores program instructions, which execute the above-described method when the program instructions are run.

[0041] This invention obtains an algorithm template before the piece-counting algorithm performs piece-counting, providing a foundation for the piece-counting algorithm and improving its efficiency and accuracy. By obtaining multiple different algorithm templates, it can be better applied to various working conditions, improving the universality of the algorithm templates.

[0042] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any way. Other variations and modifications are possible without departing from the technical solutions described in the claims.

Claims

1. A method for obtaining a piece-rate algorithm template for a sewing machine, characterized in that, Includes the following steps: Obtain template data and mark the source of the template data; Classify template data based on tagging information; Data processing of template data based on classification results; When template data comes from the web page, a timestamp algorithm is used to process the template data. Under the same sewing machine serial number, the types of processes required for sewing garments are analyzed. Sewing machine action signals are split according to different process types. Flag bits and count bits are added to the sewing machine action signals, process initiation signals and process completion signals. Based on the flag bits, the acquired timestamp data is segmented to obtain the segmented process curve of a sewing garment. The sewing integrity of the garment is judged based on the count bits. When the template data comes from the workstation screen, a marker is generated based on the button signal. The interval between two markers is one process, resulting in the process curve of a sewn garment. A piece-counting algorithm template is generated based on the data processing results.

2. The method for obtaining a piece-counting algorithm template for a sewing machine according to claim 1, characterized in that, The template data comes from web pages and workstation screens.

3. The method for obtaining a piece-counting algorithm template for a sewing machine according to claim 2, characterized in that, The specific method for classifying the template data is as follows: When the source of the template data is identified as a web page, the template data is stored in the web page terminal set. When the source of the template data is identified as a workstation screen, the template data is stored in the workstation screen subset.

4. A method for obtaining a piece-counting algorithm template for a sewing machine according to claim 2 or 3, characterized in that, When the template data comes from a web page, the template data includes: The sewing machine's serial number, sewing machine action signals with timestamps, process initiation signals with timestamps, and process completion signals with timestamps.

5. The method for obtaining a piece-counting algorithm template for a sewing machine according to claim 2, characterized in that, When the template data comes from the workstation screen, the template data includes: Sewing machine action signals and key signals interspersed among the sewing machine action signals.

6. A method for obtaining a piece-counting algorithm template for a sewing machine according to claim 1 or 5, characterized in that, The sewing machine action signals include: The number of stitches and the number of times the thread is cut during the sewing process of a sewing machine.

7. A system for obtaining a piece-rate algorithm template for a sewing machine, applicable to the method for obtaining a piece-rate algorithm template for a sewing machine as described in any one of claims 1-6, characterized in that, include: The acquisition module is used to obtain template data and mark the source of the template data; The algorithm server classifies template data based on the labeling information, processes the template data based on the classification results, and generates piece-rate algorithm templates based on the data processing results.

8. A memory, characterized in that, The memory stores program instructions that, when executed, perform the method as described in any one of claims 1-6.

Images