KR102126954B1 - Method for measuring smart sewing works and system for performing the same - Google Patents

Abstract

Disclosed are a smart sewing work measuring method capable of extracting the number and time of sewing works from high-speed complex data by using an approximate statistics algorithm and a system for performing the same. The smart sewing work measuring method includes the steps of: (a) extracting a working current profile serving as a reference for each sewing operation; (b) reducing the dimension of the complex working current profile using a piecewise aggregate approximation (PAA) scheme; (c) transposing the simplified profile into alphabetic characters by using a symbolic aggregate approximation (SAX) scheme; and (d) measuring similarity by comparing reference data with real-time data in the production line using a dynamic time warping (DTW) scheme. Accordingly, production data of a clothing production factory can be collected by using a system such as a smart plug and analyzed by using an approximate statistical technique algorithm that can perform analysis without the burden of computing power so that the productivity of an individual worker and a production line is analyzed and predicted in real time to control the clothing production factory, thereby maximizing efficiency and productivity.

Description

METHOD FOR MEASURING SMART SEWING WORKS AND SYSTEM FOR PERFORMING THE SAME

The present invention relates to a method for measuring a smart sewing operation and a system for performing the same, and more specifically, a smart sewing operation measurement method capable of extracting the number and time of sewing operations from high-speed complex data using an approximate statistical algorithm, and performing the same. It relates to a system for.

With the development of technology, various types of smart sensors have been developed and used in industrial sites and homes. For example, fragmentary smart sensors that integrate current sensors, water pressure sensors, and temperature sensors with IoT technology are partially commercialized. The current power consumption, water pressure status, temperature level, etc. measured by these smart sensors are delivered to the operator's smartphone app, and the operator can control power, water pressure, temperature, etc. using a switching means such as a relay. Smart plugs are also used to effectively measure the use of electrical energy, utilize the results of the measurement for various purposes, and effectively cut off the control of the supply of electricity for efficient use of electrical energy.

The need for effective monitoring and control of the production environment continues. For example, in order to implement a smart factory, monitoring of various targets and environmental factors is required. As more various control factors and environmental factors are monitored, means and methods are required to process monitoring results in various ways and take active measures for safe operation of production means and productivity improvement.

The garment manufacturing industry is a traditional labor-intensive industry, where most of the work is done by workers' workforce. In the case of a garment production plant, it is necessary to convert workers' labor-intensive work environment to an IoT-based system in order to improve productivity and improve the stability of the work environment. In order to maximize work efficiency, productivity, and prevent accidents, it is necessary to closely monitor the working situation of the garment production equipment handled by workers and the working environment in the factory.

0001) Korean Patent Publication No. 10-2019-0008515 (January 24, 2019) (Invention name: Process monitoring device and method using improved SAX and RTC techniques) 0002) Korea Registered Patent No. 10-1917157 (Nov. 05, 2018) (Invention name: Smart monitoring method and system for clothing production plant)

Accordingly, the technical problem of the present invention is to solve this problem, and the object of the present invention is to monitor and analyze the power consumption of a sewing machine in real time to measure the work quantity and work time of each worker by performing clothes sewing work in a garment production factory. At the same time, it provides a smart sewing operation measurement method that can monitor the current production volume, production progress, working time, and bottleneck of each worker and production line in real time.

Another object of the present invention is to provide a system for performing the above-described smart sewing operation measuring method.

In order to realize the object of the present invention, a method for measuring a smart sewing operation according to an embodiment includes: (a) extracting a working current profile that is a reference for each sewing operation in a production line; (b) reducing the dimension of the working current profile using a PAA (Piecewise Aggregate Approximation) technique; (c) transposing the reduced working current profile into alphabetic characters using a symbolic aggregation approximation (SAX) technique to generate reference data with reduced dimensions and character representation; And (d) comparing the reference data and actual data collected on the production line using a DTW (Dynamic Time Warping) technique to measure similarity.

In one embodiment of the present invention, the step (b) comprises: (b-1) dividing the working current profile which is time series continuous data; (b-2) re-segmenting the divided data into new ranges; (b-3) calculating an average value of data in the divided section; And (b-4) reducing the dimension by designating the calculated average value as a representative value of each section.

In one embodiment of the present invention, the step (c) comprises: (c-1) specifying a range of data values in the dimension; (c-2) dividing a range of data values in a dimension according to a Gaussian distribution; (c-3) representatively representing a section in which the value of the dimension-reduced data is located using alphabetic characters; And (c-4) replacing the reduced-dimensional section with an alphabetic character.

In one embodiment of the present invention, the step (d), (d-1) reducing the dimension of the time-series continuous data collected in real time at the production site; (d-2) representing characters of real-time collection time series continuous data with reduced dimensions; (d-3) comparing the reference data string with a characterized string of data collected in real time; And (d-4) determining whether the reference data string and the real-time data string comparison result are within a reference range.

In one embodiment of the present invention, in step (d-3), the reference data string is sliding with respect to the real-time data string using a moving window technique to recognize a profile having a high degree of similarity as a pattern to calculate the work quantity.

In one embodiment of the present invention, the time required between each operation may be calculated by extracting time information of a pattern recognition start point recognized as the pattern and calculating a difference up to a time to recognize the next pattern.

In order to realize the other object of the present invention described above, a smart sewing operation measurement system according to an embodiment includes a profile extraction unit for extracting a working current profile that is a reference for each sewing operation in a production line; A dimension reduction unit for reducing the dimension of the working current profile using a PAA (Piecewise Aggregate Approximation) technique; A character representative unit that transposes the reduced-working current profile into alphabetic characters using a symbolic aggregate approximation (SAX) technique to generate reference data with reduced dimensions and characterized representations; And a similarity measurement unit that measures the similarity by comparing the reference data and actual data collected on a production line using a DTW (Dynamic Time Warping) technique.

In one embodiment of the present invention, the dimension reduction unit divides the working current profile, which is time series continuous data, redistributes the divided data into a new range of sections, calculates an average value of data in the divided sections, and calculates the average value. You can reduce the dimension by specifying as the representative value of each section.

In one embodiment of the present invention, the character representative unit designates a range of data values in a dimension, divides a range of data values in a dimension according to a Gaussian distribution, and is a section in which data values of reduced dimensions are located. Can be represented as an alphabetic character, and a section with a reduced dimension can be displayed by replacing it with an alphabetic character.

In one embodiment of the present invention, the similarity measurement unit reduces the dimension of the time-series continuous data collected in real-time at the production site, represents the characters of the real-time collected time-series continuous data with reduced dimensions, and the reference data string and real-time. The characterized character strings of the collected data can be compared, and when the comparison result of the reference data character string and the real-time data character string is within a reference range, it can be determined as a job.

In an embodiment of the present invention, the similarity measurement unit may calculate the work quantity by recognizing a profile having a high similarity as a pattern by sliding the reference data string against the real-time data string using a moving window technique.

In one embodiment of the present invention, the similarity measurement unit may extract time information of a pattern recognition start point recognized as the pattern, calculate a difference up to a time to recognize the next pattern, and calculate a required time between each task.

According to such a smart sewing operation measuring method and a system for performing the same, a smart plug system or the like is used to collect the production data of a garment production plant and use an approximate statistical technique algorithm that can analyze it without burden of computing power. By analyzing and analyzing the productivity of individual workers and production lines in semi-real time, it is possible to maximize efficiency and productivity by controlling the garment production plant.

1 is a schematic diagram for explaining a smart sewing operation measurement system according to an embodiment of the present invention.
2 is a block diagram illustrating a smart sewing operation measurement system according to an embodiment of the present invention.
Figure 3 is a flow chart for explaining a smart sewing operation measuring method according to an embodiment of the present invention.
FIG. 4 is a flowchart illustrating the dimensionality reduction step illustrated in FIG. 3.
FIG. 5 is a flow chart for explaining the character representation step illustrated in FIG. 3.
6 is a graph for explaining a simplified and representative data example with the approximate statistical algorithm PAA-SAX.
FIG. 7 is a flowchart for explaining the similarity measurement step illustrated in FIG. 3.
8 is a graph for explaining the result of the recognition of the work quantity of the smart sewing operation measurement system according to an embodiment of the present invention.
9 is a graph for explaining a comparison between a work time measured by a manager with a stopwatch and a work time measured by a smart sewing work measurement system according to an embodiment of the present invention.
10 is a graph for explaining the analysis of daily work performance characteristics for each worker.
11 is a graph for explaining the status of overload workers by time.

Hereinafter, the present invention will be described in more detail with reference to the accompanying drawings. The present invention may be variously modified and may have various forms, and specific embodiments will be illustrated in the drawings and described in detail in the text. However, this is not intended to limit the present invention to a specific disclosure form, and it should be understood that all modifications, equivalents, and substitutes included in the spirit and scope of the present invention are included.

In describing each drawing, similar reference numerals are used for similar components. In the accompanying drawings, the dimensions of the structures are shown to be enlarged than actual in order to clarify the present invention.

Terms such as first and second may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from other components. For example, the first component may be referred to as a second component without departing from the scope of the present invention, and similarly, the second component may be referred to as a first component. Singular expressions include plural expressions unless the context clearly indicates otherwise.

In this application, terms such as “include” or “have” are intended to indicate the presence of features, numbers, steps, actions, elements, parts or combinations thereof described in the specification, but one or more other features. It should be understood that the presence or addition possibilities of fields or numbers, steps, actions, components, parts or combinations thereof are not excluded in advance.

In addition, unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by a person skilled in the art to which the present invention pertains. Terms, such as those defined in a commonly used dictionary, should be interpreted to have meanings consistent with meanings in the context of related technologies, and should not be interpreted as ideal or excessively formal meanings unless explicitly defined in the present application. Does not.

1 is a schematic diagram for explaining a smart sewing operation measurement system according to an embodiment of the present invention.

Referring to FIG. 1, a smart plug (or smart monitoring device) of a smart sewing operation measurement system is installed in various clothing production equipment such as a sewing machine or an automated cutting machine in a clothing production factory, and the use of the clothing production equipment measured over time is used. Data of power consumption or power consumption is collected and transmitted to a server computer (local/cloud server) through wireless or wired communication.

The smart sewing operation measurement system extracts the production quantity and work time of the garment production worker from the data transmitted to the server computer by using an approximate statistics technique algorithm. In addition, the smart sewing work measurement system can analyze the extracted data individually or on a production line basis, measure the working time of an individual or a clothing production line, measure the production quantity, and evaluate the production line efficiency. . In addition, the smart sewing operation measurement system can identify bottlenecks and evaluate productivity. In addition, the smart sewing operation measurement system can provide the calculated data in real time to the manager or management department to monitor the operation status of the garment production plant.

The garment production industry is a traditional workforce-intensive industry, where all work is done by manpower. Currently, a large-scale investment that converts garment manufacturing factories from Southeast Asia to other IoT-based systems is a labor-intensive work environment for local workers. In this situation, according to the present invention, production data is collected using a system such as a smart plug and analyzed using an approximate statistical technique algorithm that can analyze it without burden of computing power, thereby real-time productivity of individual workers and production lines. It can maximize efficiency and productivity by analyzing and predicting in real time or in real time to control the garment production factory.

2 is a block diagram illustrating a smart sewing operation measurement system according to an embodiment of the present invention.

2, the smart sewing operation measurement system according to an embodiment of the present invention includes a profile extraction unit 100, a dimension reduction unit 200, a character representation unit 300 and a similarity measurement unit 400 And, it is specialized in clothing production plants, monitors power consumption of sewing machines, etc., recognizes the worker's work pattern from the current signal, and uses it to analyze the work quantity or work time of the worker or production line to provide basic production information. In addition, the smart sewing operation measurement system can provide management information such as the production amount and progress of each worker-work line-production plant, work time, and bottleneck point using the provided basic production information.

The profile extraction unit 100 extracts a working current profile that is a reference for each sewing operation. The above-described working current profile may be extracted through a smart monitoring device for clothing production equipment. The clothing production equipment smart monitoring device includes a plurality of sensor modules. Each of the sensor modules includes the amount of current, voltage or power consumption of the clothing production equipment, and the temperature, humidity, illuminance, pressure, acceleration, noise, fine dust concentration, and concentration of manganese (CO2, VOC) at various ends, etc. It may be a set of sensors that can detect each. In this embodiment, the sensor module may be a current sensor. In this case, the current sensor can detect the amount of current supplied to the load, including the current conversion coil surrounding the electric line from which power is supplied from the power source to the garment production equipment. Knowing the amount of current supplied to the garment production equipment will also calculate the power consumption.

The dimension reduction unit 200 converts the dimension of the working current profile extracted from the profile extraction unit 100 into a simplified working current profile by reducing the dimension of the PAA (Piecewise Aggregate Approximation). Time-series input data can be simplified to stair-step data, which is expressed as PAA conversion. Text that is changed from a curved expression over time to a stepped shape is symbolized again.

를 길이 M의 시퀀스

으로 나타낸다. The PAA technique is a sequence of length n using Equation 1 below.

The sequence of length M

It is represented by.

[Equation 1]

Here, n and M are natural numbers and satisfy n=M.

That is, in order to reduce the n-dimensional time series data to the M dimension, the PAA technique divides the time series data into frames of the same size, and represents data as an average value of data belonging to each frame.

The character representative 300 transposes the simplified working current profile by the dimension reduction unit 200 into alphabetic characters using a symbolic aggregate approximation (SAX) technique. The SAX technique described above represents each segment of data converted through the PAA technique by symbolizing it as a character string. Here, the character string may include, for example, an alphabet or a number, but in this embodiment, the alphabet is described as an example of the character string.

Typically, SAX is a method of dividing time series data into time windows and dividing the dimensions. In classical data mining techniques such as clustering, classification, and indexing, it is as good as the well-known expression methods DWT (Discrete Wavelet Transform) or DFT (Discrete Fourier Transform) and requires less storage space. That is SAX. In addition, it not only takes advantage of the rich data structures used in bioinformatics or text mining, but also provides solutions to many problems related to current data mining tasks.

The similarity measurement unit 400 measures the similarity by comparing the reference data and real-time data in the production line using a DTW (Dynamic Time Warping) technique. Specifically, the similarity measurement unit 400 reduces the dimension of the time series continuous data collected in real time at the production site, and represents the characters of the time series continuous data collected in real time with reduced dimensions. Subsequently, the similarity measurement unit 400 compares the reference data string and the real-time data string, and determines that the result is a task when the reference data string and the real-time data string comparison result are within the reference range.

The similarity measurement unit 400 calculates a work quantity by recognizing a profile having a high similarity as a pattern by sliding the reference data string with respect to the real-time data using a moving window technique. The similarity measurement unit 400 extracts time information of the pattern recognition start point, calculates a difference up to the time to recognize the next pattern, and calculates the required time between each task.

Figure 3 is a flow chart for explaining a smart sewing operation measuring method according to an embodiment of the present invention.

Referring to FIG. 3, a working current profile as a reference for each sewing operation is extracted from the production line (step S100). The above-described extraction of the working current profile may be performed by the current profile extraction unit 100 shown in FIG. 2.

Subsequently, the dimension of the working current profile is reduced by using a PAA (Piecewise Aggregate Approximation) technique (step S200). The aforementioned dimension reduction may be performed by the dimension reduction unit 200 illustrated in FIG. 2.

Subsequently, the dimension-reduced working current profile is transposed into alphabetic characters using a symbolic aggregate approximation (SAX) technique to generate reference data with reduced dimensions and character representation (step S300). The transposition to the above-described alphabetic characters may be performed by the character representative 300 illustrated in FIG. 2.

Subsequently, the similarity between the reference data and real data (ie, real-time data) collected in the production line is measured using a DTW (Dynamic Time Warping) technique (step S400). The similarity measurement described above may be performed by the similarity measurement unit 400 illustrated in FIG. 2.

FIG. 4 is a flowchart illustrating the dimensionality reduction step illustrated in FIG. 3.

3 and 4, the dimension reduction unit 200 divides the working current profile, which is time series continuous data (step S210). For example, if 5 consecutive data per second is divided into 1 minute intervals, it is 300-dimensional.

Subsequently, the dimension reduction unit 200 redistributes the divided data into a new range of sections (step S220). For example, the 300 dimension is subdivided into 15 sections each having 20 data.

Subsequently, the dimension reduction unit 200 calculates an average data value in the divided section (step S230). For example, an average value of 20 data for each 15 sections is calculated.

Subsequently, the dimension reduction unit 200 decreases the dimension by designating the calculated average value as a representative value of each section (step S240). For example, the 300 dimension is reduced to 15 dimensions.

FIG. 5 is a flow chart for explaining the character representation step illustrated in FIG. 3. 6 is a graph for explaining a simplified and representative data example with an approximate statistical technique algorithm PAA-SAX.

3 and 5, the character representative 300 specifies a range of current data values in the dimension (step S310). For example, 0 to 3 when all current data values are in the range of 0 to 3 A.

Subsequently, the character representative 300 divides the current data value range in the dimension according to a Gaussian distribution (step S320). For example, a high density section is arranged in the middle.

Subsequently, the character representative 300 expresses the section in which the value of the dimension-reduced data is located as an alphabetic character (step S330). For example, the lowest section may be represented as a, the next step section b, and the next step section c.

Subsequently, the character representative 300 displays the section in which the dimension is reduced by replacing it with an alphabetic character (step S340). For example, the 15th dimension can be replaced with alphabetic characters such as <afacebaaafcbaa>.

FIG. 7 is a flowchart for explaining the similarity measurement step illustrated in FIG. 3.

3 and 7, the similarity measurement unit 400 reduces the dimension of time series continuous data collected in real time at the production site (step S410).

Subsequently, the similarity measuring unit 400 represents a character of the real-time collected time series continuous data with reduced dimensions to generate a real-time data string (step S420).

Subsequently, the similarity measurement unit 400 compares the reference data string and the real-time data string (step S430), and determines that the comparison result of the reference data string and the real-time data string is a job when the comparison result is within the reference range (step S440). For example, by sliding a reference data string against a real-time data string using a moving window technique, a high-similarity profile can be recognized as a pattern to calculate the work quantity.

8 is a graph for explaining the result of the recognition of the work quantity of the smart sewing operation measurement system according to an embodiment of the present invention. In particular, Figure 8 is a graph showing the result of recognizing the work quantity in the garment sewing production line consisting of 44 workers using a smart sewing operation measurement system.

As shown in FIG. 8, the result of measuring the work using the smart sewing work measurement system showed an average of 92.1% (highest 99.6%, lowest 80.6%) of work quantity recognition rate for 250 reference work quantities.

This error can be minimized by adjusting the sensitivity to similarity.

9 is a graph for explaining a comparison between a work time measured by a manager with a stopwatch and a work time measured by a smart sewing work measurement system according to an embodiment of the present invention.

As shown in FIG. 9, when the sewing operation is performed on the garment sewing production line consisting of 44 workers, the working time actually measured by the stopwatch and the working time measured by the smart sewing measuring system can be confirmed that the trend is similar for each worker. have.

That is, about 30% of the work showed an error of less than 10%, but the trend is similar for each worker, and in the case of manager measurement, the measurement is performed once every 2 days (approximately after measuring about 3 times for 1 measurement). In consideration, it can be seen that the result is a level of measurement applicable to the garment production site.

10 is a graph for explaining the analysis of daily work performance characteristics for each worker.

Referring to FIG. 10, a result of analyzing the daily work performance characteristics of two workers using a smart sewing work measurement system is displayed.

For worker #21 (OP#21), the work quantity from 7 to 12 is 4, 10, 8, 11, 14, 16, 10,. There were 13, 13, and 10, and the work quantity from 12:30 to 18:00 was measured as 6, 6, 14, 12, 9, 10, 8, 11, 12, 14, 11, and 3. On the other hand, for worker 37 (OP#37_2), the number of jobs from 7 to 12 is 2, 6, 8, 11, 12, 13, 13, 13, 13, 12, 10, and 12:30 to 18 The quantity of work up to the hour was measured as 4, 12, 10, 13, 13, 12, 12, 10, 4, 14, 12, 10.

As described above, it can be seen that in the case of the worker 21 (OP#21), the work concentration is higher in the morning than in the afternoon, whereas the worker 37 (OP#37_2) shows a higher work characteristic in the afternoon than the morning.

Using the smart sewing work measurement system according to the present invention, these individual worker-specific work characteristics can be built into big data and productivity can be improved by arranging the optimal combination of personnel when designing the production line.

11 is a graph for explaining the status of overload workers by time. In particular, the result of calculating the work load for each daily time zone of seven combined sewing workers using a smart sewing work measurement system is shown.

Referring to Figure 11, 7-8 hours 32 workers (OP#32) is showing a high load rate (approximately 240%), around 11 am 33 workers (OP#33) is a high load rate (approximately 170%) ), and around 1 pm, it can be confirmed that the 35th worker (OP#35) shows a high load rate (approximately 200%). In addition, around 2 pm, the number 37 worker (OP#37 shows a high load rate, around 4 pm the 35th worker (OP#35) shows a high load rate, and at 5 pm, the 32nd worker (OP#32) You can see the phenomenon showing a high load factor.

As such, it is possible to check the current status of overload workers by time using a smart sewing measurement system.

The phenomenon in which the worker shows a high load rate can be analyzed as a sign that a bottleneck may occur in the process, and it is possible to maintain the balance of the sewing production line by checking and eliminating the cause of the increase in the work load of the process.

Real-time monitoring is possible to maintain the balance within this production line as much as possible by using the smart sewing measurement system.

As described above, by attaching a smart plug to the garment production equipment such as a sewing machine of a garment production plant without any additional equipment modification, collecting current data, analyzing the collected data, and calculating the production amount and unit production time, the entire factory Real-time operation status and various production information can be checked.

The methods disclosed herein include one or more steps or operations to achieve the described method. Method steps and/or acts may be interchanged with one another without departing from the scope of the claims. In other words, the order and/or use of specific steps and/or actions can be modified without departing from the scope of the claims, unless a specific order of steps or actions is required for proper operation of the described method.

Although described above with reference to examples, those skilled in the art can variously modify and change the present invention without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand.

The smart sewing operation measuring method and the system for performing the same according to the present invention can be applied to automation and production/time measurement of the production manufacturing system for the garment sewing field. In addition, it is possible to provide management information such as production volume, production progress, working time and bottleneck of each worker-work line-production plant. In addition, it can be applied to equipment and environmental monitoring in various manufacturing equipment factories.

100: profile extraction unit 200: dimension reduction unit
300: character representation unit 400: similarity measurement unit

Claims (12)

(a) extracting a working current profile that is the basis of each sewing operation in the production line;
(b) reducing the dimension of the working current profile using a PAA (Piecewise Aggregate Approximation) technique;
(c) transposing the reduced-working current profile into alphabetic characters using a symbolic aggregate approximation (SAX) technique to generate reference data with reduced dimensions and character representation; And
(d) Smart sewing operation measurement method comprising the step of measuring the similarity by comparing the reference data and the actual data collected from the production line using a DTW (Dynamic Time Warping) technique. The method of claim 1, wherein the step (b),
(b-1) dividing the working current profile which is time series continuous data;
(b-2) re-segmenting the divided data into new ranges;
(b-3) calculating an average value of data in the divided section; And
(b-4) Smart sewing operation measurement method comprising the step of reducing the dimension by designating the calculated average value as a representative value of each section. The method of claim 1, wherein step (c),
(c-1) specifying a range of data values in the dimension;
(c-2) dividing a range of data values in a dimension according to a Gaussian distribution;
(c-3) representatively representing a section in which the value of the dimension-reduced data is located using alphabetic characters; And
(c-4) A method of measuring a smart sewing operation, comprising the step of displaying the reduced-dimensional section with alphabet characters. The method of claim 1, wherein the step (d),
(d-1) reducing the dimension of time series continuous data collected in real time at the production site;
(d-2) representing characters of real-time collection time series continuous data with reduced dimensions;
(d-3) comparing the reference data string and a characterized string of data collected in real time; And
(d-4) Smart sewing operation measurement method characterized in that it comprises the step of judging as a task when the comparison result of the reference data string and the real-time data string is within a reference range. The smart sewing according to claim 4, wherein in step (d-3), the reference data string is sliding with respect to the real-time data string using a moving window technique to recognize a profile having a high similarity as a pattern and calculate the work quantity. How to measure work. The method for measuring a smart sewing operation according to claim 5, wherein the time required between each operation is calculated by extracting time information of the starting point of pattern recognition recognized as the pattern and calculating the difference up to the time to recognize the next pattern. A profile extraction unit for extracting a working current profile that is a basis for each sewing operation in the production line;
A dimension reduction unit that reduces the dimension of the working current profile using a PAA (Piecewise Aggregate Approximation) technique;
A character representative unit that transposes the reduced-work current profile into alphabetic characters using a symbolic aggregate approximation (SAX) technique to generate reference data with reduced dimensions and characterized representations; And
Smart sewing operation measurement system comprising a similarity measuring unit for measuring the similarity by comparing the reference data and the actual data collected from the production line using a DTW (Dynamic Time Warping) technique. The method of claim 7, wherein the dimensional reduction unit divides the working current profile, which is time series continuous data, redistributes the divided data into a new range of sections, calculates an average value of data in the divided sections, and calculates the average value of each. Smart sewing operation measurement system characterized by reducing the dimension by specifying the representative value of the section. The character representation unit of claim 7, wherein the character representative designates a range of data values in a dimension, divides a range of data values in a dimension according to a Gaussian distribution, and alphabetizes a section in which a dimension of the reduced data value is located. Smart sewing operation measurement system characterized in that the representation is represented by letters, and the section with reduced dimensions is replaced with alphabet letters and displayed. The method of claim 7, wherein the similarity measurement unit reduces the dimension of the time series continuous data collected in real time at the production site, represents the characters of the time series continuous data collected in reduced dimensions, and collects the reference data string and the real time. Smart sewing operation measurement system, characterized in that comparing the characterized character string of data, and comparing the reference data character string and the real-time data character string as a job within a reference range. The smart sewing operation measurement system according to claim 10, wherein the similarity measurement unit calculates a work quantity by recognizing a profile having a high similarity as a pattern by sliding the reference data string against the real-time data string using a moving window technique. . 12. The method of claim 11, wherein the similarity measuring unit extracts the time information of the pattern recognition start point recognized as the pattern to calculate the difference up to the time to recognize the next pattern smart sewing characterized in that it calculates the time required between each operation Work measurement system.

Images