Automatic production method of horse surface skirt

Abstract

The invention relates to the technical field of garment production, in particular to an automatic production method of a horse face skirt, which comprises the following automatic production steps: S1, inputting the characters of the pattern style of the horse face skirt into a background computer terminal, and automatically generating the pattern styles of the horse face skirt with various designs by the background computer in an AI big data mode; and S2, a designer selects an excellent and attractive design according to the pattern style designed by AI, and modifies and perfects the design on the basis to form a design drawing of the pattern style of the horse surface skirt. According to the invention, the image acquisition equipment is used for acquiring processing procedures, uploading the processing procedures to the background computer for analysis and checking whether errors exist or not, and if the errors exist, an alarm is given to warn people in time, so that people stop the equipment and adjust parameters, the processing efficiency can be greatly improved, the errors are reduced, and the working efficiency is improved. And the market requirements can be better met.

Description

Technical Field

[0001] The invention belongs to the technical field of clothing production, and in particular relates to an automatic production method for a horse-faced skirt. Background Art

[0002] The horse-faced skirt, also known as the "horse-faced pleated skirt", is one of the main skirt styles for women in ancient China. It has four skirt doors, which overlap in two. The outer skirt door is decorated, while the inner skirt door is less decorated or not decorated. The sides are pleated, and the waist of the skirt is mostly made of white cloth, which means growing old together. It is fastened with ropes or buttons. The horse-faced skirt is the most typical style of women's clothing in the Ming and Qing Dynasties. It has undergone a series of changes, but its "horse-faced" structure has always been deeply rooted. With the revival of traditional culture in recent years, the horse-faced skirt with distinctive Chinese cultural characteristics has gradually come into people's vision. A large number of young people have taken to wearing Hanfu represented by horse-faced skirts and other clothing as a trend, which fully reflects the cultural confidence of the Chinese people. With the growth of consumer demand, the market for horse-faced skirts has also shown explosive growth, but the existing horse-faced skirts on the market are all purely handmade, and their production efficiency is low, which is difficult to meet the current market demand. In this regard, we propose an automatic production method for horse-faced skirts. Summary of the invention

[0003] In view of the deficiencies in the prior art, the present invention provides an automatic production method for a horse-faced skirt to solve the above technical problems.

[0004] To achieve the above object, the present invention provides the following technical solution: an automatic production method for a horse-faced skirt, the automatic production steps are:

[0005] S1. By inputting the text of the pattern of the horse-faced skirt into the background computer, the background computer automatically generates a variety of designs of the horse-faced skirt pattern through AI big data;

[0006] S2. The designer selects an excellent and beautiful design based on the pattern style designed by AI, and modifies and improves it on this basis to form a design drawing of the horse-faced skirt pattern style;

[0007] S3, converting the format of the design drawing, inputting it into the pattern weaving equipment, and weaving the pattern using the jacquard process to make a patterned cloth;

[0008] S4, feeding the fabric into the automated assembly line and cutting it according to the designed size;

[0009] S5, prepare lavender extract, put the cut fabric into the lavender extract to soak, let the fabric fully absorb the lavender extract, then take it out and dry it;

[0010] S6. Align the edges of the fabric, keep the fabric flat, and sew and splice the cut fabric;

[0011] S7. Fold the two sides of the skirt to make three or four pairs of pleats, use different colored fabrics to make the waist of the skirt, sew laces at both ends of the waist of the skirt, fix the skirt, and arrange the skirt to keep it flat and beautiful;

[0012] S8. Image acquisition equipment is installed in each process of the automated assembly line. The production process is checked through the image acquisition equipment to see if there are any errors. The images are uploaded to the background computer for processing. If a processing deviation is detected in the automated assembly line, an alarm is issued in time, the automated assembly line is stopped, and the processing program is corrected.

[0013] Preferably, the method of obtaining information by AI big data in step S1 is to obtain information data on the network through a web crawler, convert text into images with the help of AI, and generate corresponding images according to the text content.

[0014] Preferably, in step S2, the designer selects one of them and continues to improve the design on this basis; in step S3, the jacquard process is to pick out the two warp threads of each grid to be jacquard according to the designed pattern, so as to produce the jacquard grid of the pattern, and then stand up the jacquard knife, put in the required colored weft threads from left to right, squeeze the weft threads hard, and repeat this process to weave the designed pattern.

[0015] Preferably, in step S4, the automated assembly line is controlled and adjusted through a background computer to adjust processing parameters; in step S5, the lavender extract is an essence obtained by extracting lavender plants, and the lavender extract extraction step is to pre-select healthy lavender, clean the lavender, and then crush it, soak the crushed lavender in ethanol, and then filter it to filter out impurities and unnecessary components, and continue to perform purification operations to improve the purity and concentration of the lavender extract.

[0016] Preferably, the soaking time in step S5 is 6 hours, and the cloth is stirred intermittently during the soaking process. The stirring setting parameters are stirring once after every half an hour of soaking. The drying time is 20 minutes and the drying temperature is 60°C.

[0017] Preferably, in step S6, sewing is performed by needle and thread, and decorations are added during the sewing process; in step S7, quality inspection is performed after the skirt is prepared, the appearance of the skirt is inspected to check for color difference, stains and damage, the sewing of the skirt is inspected to check whether each stitching position of the skirt is flat, and whether there are thread ends and broken threads. After passing the inspection, it is packaged.

[0018] Preferably, the image acquisition device in step S8 is a camera, which is installed on the production equipment in each production process to take pictures, and the results of the pictures are uploaded to the background computer for processing. An image processing module is established inside the background computer.

[0019] Preferably, when processing the captured image, the image processing module pre-processes the image in advance, and the pre-processing includes graying and image enhancement. The graying processing step separates the pixel value RGB value in the color image, calculates each processed image through a weighted average algorithm, and replaces the original RGB value; the image enhancement step removes noise in the image by using a filter, and averages the pixel values ​​between pixels by using a mean filter to perform smoothing.

[0020] Prior to this, feature extraction is performed on the preprocessed image to check whether there is any deviation in the processing process on the assembly line. Feature extraction is based on the convolutional neural network method, where the convolution formula is:

[0021] P=s*c+q

[0022] Where P is the output value, s is the input value, c is the convolution kernel, and q is the bias term;

[0023] The convolutional neural network includes input layer, convolution layer, pooling layer and fully connected layer;

[0024] In the detected image, if the extracted features are not consistent with the set positions of the assembly line, it is determined that there is a deviation in the processing.

[0025] Preferably, in step S8, the background computer and the alarm are electrically connected. After the background computer detects a deviation, it issues a command to let the alarm sound an alarm to warn people.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] The present invention achieves automatic production of horse-faced skirts by controlling the assembly line through the use of an automated program, and an image acquisition device is installed on the assembly line to collect images of the processing steps, which are uploaded to a background computer for analysis to check whether there are any errors. If there are any errors, an alarm is issued to warn people in time, so that people can stop the equipment and adjust parameters, which can greatly improve the processing efficiency, reduce errors, and better meet market demand.

[0028] The present invention designs the pattern of the horse-faced skirt by using AI big data, which can greatly reduce people's design time. When processing the fabric, it is pre-impregnated with lavender extract, which can enhance the antibacterial property of the horse-faced skirt, bring a special fragrance, and improve the quality of the horse-faced skirt. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a framework diagram of the production steps of the present invention. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] The present invention provides a technical solution: an automatic production method of a horse face skirt, the automatic production steps are:

[0032] S1. By inputting the text of the pattern of the horse-faced skirt into the background computer, the background computer automatically generates a variety of designs of the horse-faced skirt pattern through AI big data;

[0033] S2. The designer selects an excellent and beautiful design based on the pattern style designed by AI, and modifies and improves it on this basis to form a design drawing of the horse-faced skirt pattern style;

[0034] S3, converting the format of the design drawing, inputting it into the pattern weaving equipment, and weaving the pattern using the jacquard process to make a patterned cloth;

[0035] S4, feeding the fabric into the automated assembly line and cutting it according to the designed size;

[0036] S5, prepare lavender extract, put the cut fabric into the lavender extract to soak, let the fabric fully absorb the lavender extract, then take it out and dry it;

[0037] S6. Align the edges of the fabric, keep the fabric flat, and sew and splice the cut fabric;

[0038] S7. Fold the two sides of the skirt to make three or four pairs of pleats, use different colored fabrics to make the waist of the skirt, sew laces at both ends of the waist of the skirt, fix the skirt, and arrange the skirt to keep it flat and beautiful;

[0039] S8. Image acquisition equipment is installed in each process of the automated assembly line. The production process is checked through the image acquisition equipment to see if there are any errors. The images are uploaded to the background computer for processing. If a processing deviation is detected in the automated assembly line, an alarm is issued in time, the automated assembly line is stopped, and the processing program is corrected.

[0040] Furthermore, in step S1, the method of obtaining information by AI big data is to obtain information data on the network by means of web crawlers, convert text into images with the help of AI, and generate corresponding images according to the text content;

[0041] AI uses a generator and a discriminator. The generator's task is to generate fake data that is as similar to real data as possible, while the discriminator's task is to determine whether the data is true. During the training process, the generator and the discriminator will compete with each other to continuously improve the performance of the generator, and eventually the generator can generate highly realistic images.

[0042] Furthermore, in step S2, the designer selects one of them and continues to improve the design on this basis; in step S3, the jacquard process is to pick out two warp threads of each grid to be jacquard according to the designed pattern, so as to produce a jacquard grid of the pattern, and then the jacquard knife is erected, and the required colored weft threads are inserted from left to right, and the weft threads are squeezed hard, and this is repeated to weave the designed pattern;

[0043] By interlacing and interweaving warp and weft yarns of different colors, patterns of different colors are formed, and automatic weaving can be performed according to the designed pattern style.

[0044] Furthermore, in step S4, the automated assembly line is controlled by a background computer to adjust processing parameters; in step S5, the lavender extract is an essence obtained by extracting lavender plants, and the lavender extract extraction step is to pre-select healthy lavender, clean the lavender, and then crush it, soak the crushed lavender in ethanol, and then filter it to filter out impurities and unnecessary components, and continue to purify it to improve the purity and concentration of the lavender extract;

[0045] Lavender extract has the effects of improving sleep, repelling insects and resisting bacteria, and can bring fragrance to the prepared horse face skirt.

[0046] Furthermore, in step S5, the soaking time is 6 hours, and the cloth is stirred intermittently during the soaking process. The stirring setting parameters are stirring once every half an hour after the cloth is soaked, the drying time is 20 minutes, and the drying temperature is 60°C. Through continuous stirring, the cloth can absorb the lavender extract more fully.

[0047] Furthermore, in step S6, sewing is performed by needle and thread, and decorations are added during the sewing process; in step S7, quality inspection is performed after the skirt is prepared, the appearance of the skirt is inspected to check whether there is color difference, stains and damage, the sewing of the skirt is inspected to check whether each stitching position of the skirt is flat, whether there are thread ends and broken threads, and it is packaged after passing the inspection.

[0048] Furthermore, in step S8, the image acquisition device is a camera, which is installed on the production equipment in each production process to take pictures, and the results of the pictures are uploaded to the background computer for processing. An image processing module is established inside the background computer.

[0049] Furthermore, when the image processing module processes the captured image, it pre-processes the image in advance. The pre-processing includes graying and image enhancement. The graying processing step separates the pixel value RGB value in the color image, calculates each processed image by a weighted average algorithm, and replaces the original RGB value; the image enhancement step removes the noise in the image by using a filter, and averages the pixel values ​​between pixels by using a mean filter to perform smoothing.

[0050] The weighted average algorithm formula is:

[0051] L=(x1*c1)+(x2*c2)+……+(xn*cn) / q

[0052] Where L is the weighted average, x is the value, c is the weight, and q is the total weight;

[0053] The weight of each value is determined to ensure that the sum of the weights is 1, thus ensuring the rationality of the weights.

[0054] Furthermore, feature extraction is performed on the preprocessed image to check whether there is any deviation in the processing process on the assembly line. Feature extraction is based on the convolutional neural network method, where the convolution formula is:

[0055] P=s*c+q

[0056] Where P is the output value, s is the input value, c is the convolution kernel, and q is the bias term;

[0057] The convolutional neural network includes input layer, convolution layer, pooling layer and fully connected layer;

[0058] In the detected image, if the extracted features are not consistent with the set positions of the assembly line, it is determined that there is a deviation in the processing.

[0059] Furthermore, in step S8, the background computer and the alarm are electrically connected. After the background computer detects a deviation, it issues a command to let the alarm sound an alarm to warn people.

[0060] Steps for the appearance inspection of horse skirt

[0061] Prepare materials and equipment for testing;

[0062] Touch and inspect the finished horse-faced skirt to see if there are any damages or stains.

[0063] Take a standard ruler and measure the skirt length, hem and waist to see if they meet the design requirements;

[0064] Check again whether the hem, pattern and zipper of the skirt are intact.

[0065] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0066] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for automatically producing a horse-faced skirt, characterized in that: The automatic production steps are: S1. By inputting the text of the pattern of the horse-faced skirt into the background computer, the background computer automatically generates a variety of designs of the horse-faced skirt pattern through AI big data; S2. The designer selects an excellent and beautiful design based on the pattern style designed by AI, and modifies and improves it on this basis to form a design drawing of the horse-faced skirt pattern style; S3, converting the format of the design drawing, inputting it into the pattern weaving equipment, and weaving the pattern using the jacquard process to make a patterned cloth; S4, feeding the fabric into the automated assembly line and cutting it according to the designed size; S5, prepare lavender extract, put the cut fabric into the lavender extract to soak, let the fabric fully absorb the lavender extract, then take it out and dry it; S6. Align the edges of the fabric, keep the fabric flat, and sew and splice the cut fabric; S7. Fold the two sides of the skirt to make three or four pairs of pleats, use different colored fabrics to make the waist of the skirt, sew laces at both ends of the waist of the skirt, fix the skirt, and arrange the skirt to keep it flat and beautiful; S8. Image acquisition equipment is installed in each process of the automated assembly line. The production process is checked through the image acquisition equipment to see if there are any errors. The images are uploaded to the background computer for processing. If a processing deviation is detected in the automated assembly line, an alarm is issued in time, the automated assembly line is stopped, and the processing program is corrected.

2. The automatic production method of horse face skirt according to claim 1 is characterized in that: In step S1, the AI ​​big data acquires information by using web crawlers to obtain information data on the Internet, converts text into images with the help of AI, and generates corresponding images based on the text content.

3. The automatic production method of horse face skirt according to claim 1 is characterized in that: In step S2, the designer selects one of them and continues to improve the design on this basis; in step S3, the jacquard process is to pick out the two warp threads of each grid to be jacquard according to the designed pattern, so as to produce the jacquard grid of the pattern, and then stand up the jacquard knife, put in the required colored weft threads from left to right, squeeze the weft threads hard, and repeat this process to weave the designed pattern.

4. The automatic production method of horse face skirt according to claim 1 is characterized in that: In step S4, the automated assembly line is controlled and adjusted through a background computer to adjust processing parameters; in step S5, the lavender extract is an essence obtained by extracting lavender plants. The lavender extract extraction step is to pre-select healthy lavender, clean the lavender, and then crush it. The crushed lavender is soaked in ethanol, and then filtered to filter out impurities and unnecessary components, and continue to perform purification operations to improve the purity and concentration of the lavender extract.

5. The automatic production method of horse face skirt according to claim 1 is characterized in that: The soaking time in step S5 is 6 hours. The cloth is stirred intermittently during the soaking process. The stirring setting parameters are stirring once after every half an hour of soaking. The drying time is 20 minutes and the drying temperature is 60°C.

6. The automatic production method of horse face skirt according to claim 1 is characterized in that: In step S6, sewing is performed by needle and thread, and decorations are added during the sewing process; in step S7, quality inspection is performed after the skirt is prepared, the appearance of the skirt is inspected to check whether there is color difference, stains and damage, the sewing of the skirt is inspected to check whether each stitching position of the skirt is flat, whether there are thread ends and broken threads, and it is packaged after passing the inspection.

7. The automatic production method of horse face skirt according to claim 1 is characterized in that: In step S8, the image acquisition device is a camera, which is installed on the production equipment in each production process to take pictures, and the shooting results are uploaded to the background computer for processing. An image processing module is established inside the background computer.

8. The automatic production method of horse-faced skirt according to claim 7 is characterized in that: When the image processing module processes the captured image, it preprocesses the image in advance. The preprocessing includes grayscale and image enhancement. The grayscale processing step separates the pixel value RGB value in the color image, calculates each processed image through a weighted average algorithm, and replaces the original RGB value; The image enhancement step removes noise from the image by using a filter, and smoothes the image by averaging the pixel values ​​between pixels using a mean filter.

9. The automatic production method of horse-faced skirt according to claim 8 is characterized in that: Feature extraction is performed on the preprocessed image to check whether there is any deviation in the processing process on the assembly line. Feature extraction is based on the convolutional neural network method. The convolution formula is: P=s*c+q Where P is the output value, s is the input value, c is the convolution kernel, and q is the bias term; The convolutional neural network includes input layer, convolution layer, pooling layer and fully connected layer; In the detected image, if the extracted features are not consistent with the set positions of the assembly line, it is determined that there is a deviation in the processing.

10. The automatic production method of horse-faced skirt according to claim 1 is characterized in that: In step S8, the background computer and the alarm are electrically connected. After the background computer detects a deviation, it issues a command to let the alarm sound an alarm to warn people.

Images