Fabricating woven textile on demand

Abstract

An overall process for providing information required for a circular weaving machine (10) to produce a plurality of pieces of clothing on demand is disclosed. Initially, body data or measurements of a person are generated by scanning with a camera or other image capture device (530), or estimation is made based on user input body parameters (550). Measurements are extracted from the body data and then processed with linear regression and other parameter extraction techniques. The extracted measurements are then processed. The resulting cut-piece shape (570) is used to automatically produce the piece of garment as a weaving output (690) using a loom (10).

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of U.S. Provisional Application No. 63 / 304,963, entitled “Manufacturing Woven Textile Products on Demand,” filed on January 31, 2022, which is incorporated herein by reference. Technical Field

[0003] The present invention is in the technical field of manufacturing woven textile products and, more particularly, relates to producing desired garments on demand. Background Art

[0004] The production of textiles and clothing has remained virtually unchanged over time. Clothing is typically produced in large quantities, stored in warehouses, and then shipped to clothing stores for display. Multiple different sizes of each type of clothing must be stored and displayed to accommodate the different sizes of different people shopping in clothing stores. Clothing manufacturers and sellers simply estimate how many pieces of each size of clothing will sell and produce the corresponding number of clothing. There are costs associated with the storage of clothing, and when manufacturers produce the wrong number of clothing, sales are lost due to the lack of clothing in the desired size, and excess inventory of clothing may remain unsold. Excess inventory is often discarded in landfills or incinerated, causing serious environmental damage.

[0005] Woven textiles have several advantages over knitted textiles. For example, woven textiles tend not to stretch out of shape. Woven textiles also tend to be thinner. In addition, woven textiles are lighter because less yarn is required to cover the same area. However, one disadvantage of woven textiles relative to knitted textiles is that creating a three-dimensional final woven product usually requires sewing together several dissimilar pieces of woven textiles. For many years, manufacturers relied on producing clothing through the "cut and sew" technique. The production of woven clothing involves a multi-step process: weaving the original fabric piece, cutting the fabric into panels, and sewing the panels into a three-dimensional garment. Sewing two dissimilar woven textiles together forms a seam. When a product changes size or adds new parts, a different dissimilar woven textile and therefore a seam are usually required.

[0006] When different pieces of fabric are cut and sewn together, a certain amount of fabric will be wasted. Typically at least 15% of a flat woven fabric is discarded during the cutting operation. Furthermore, cutting and sewing fabric is typically an expensive manual process. With this in mind, there are advantages in the garment manufacturing industry to manufacture seamless garments in order to reduce both material and labor costs and take advantage of economies of scale.

[0007] To address some of these problems, a system and method for producing three-dimensional garments using a variable diameter circular loom has been developed, as described in the U.S. patent application entitled “MANUFACTURING WOVEN TEXTILE PRODUCTS” filed on the same date as the present application (Agent Docket No. UNS003P) and incorporated herein by reference.

[0008] However, there is still a need in the art for a method for producing garments on demand to eliminate waste. There is also a need to eliminate waste from cutting patterns and reduce production time and other costs associated with the cutting and sewing production process. Summary of the invention

[0009] The present invention relates to a system and method for measuring the size parameters of a person and then producing woven fabric products on demand by weaving a garment specifically made to fit the person.

[0010] More specifically, the method involves receiving body data to determine the shape and size of the person who will wear the woven fabric product. The body data is preferably generated by a camera or other digital imaging equipment in the form of three-dimensional body scan data. For example, an iPhone or a 3D scanning room can be used. Estimated body data is also obtained from existing videos or pictures. Estimated body data can also be generated based on user input metrics (such as height and weight). Once the body data is recorded, the data is then transferred to a computer or other electronic processing equipment. The next step is to extract the body shape definition measurements of the part of the body of interest from the body data. For example, the measurements of the legs of the body can be extracted when weaving pants. The body shape definition measurements are analyzed using a fit engine in a computer to create the fit of a piece of clothing based on the fit metric. The fit is converted into a set of computer-readable instructions for manufacturing the piece of clothing. The instructions are then passed to a circular loom for weaving a fabric product. Alternatively, the instructions and associated data are passed to a flat loom or a fabric cutting machine.

[0011] The weaving is performed using a loom comprising a weaving ring having a diameter that varies during the production of the garment. Independently actuated heddles are used to further control the weaving process. Each of the heddles comprises an actuator for moving the heddles. The heddles are modular and each heddles can be replaced as needed for maintenance or other reasons. The shuttles are equipped with a bobbin for supporting the weft yarn and a weft insertion arm is attached to each shuttle.

[0012] The method allows for the continuous weaving of fabrics whose diameter varies along the length of the output, thereby enabling the direct weaving of components of a garment (i.e., a single pant leg, shirt sleeve, dress, etc.) according to a set of computer-readable instructions. The system can also be used to produce bifurcated outputs, which would allow for the direct weaving of complete garments. This method of textile manufacturing is similar to 3D printing.

[0013] Additional objects, features and advantages of the present invention will become more readily apparent from the following detailed description of the preferred embodiments when taken in conjunction with the accompanying drawings, wherein like reference numerals designate corresponding parts throughout the several views. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present disclosure may be more fully understood from the following description of various illustrative embodiments considered in conjunction with the accompanying drawings.

[0015] Figure 1 is a perspective view of a loom according to a preferred embodiment of the present invention.

[0016] Figure 2 yes Figure 1 Top view of the loom shown in .

[0017] Figure 3 yes Figure 1 Schematic diagram of the controller of the loom shown in .

[0018] Figure 4 It is shown Figure 3 Diagram of the information flow in the controller.

[0019] Figure 5 A flow chart showing the overall process of producing garments on demand according to a first embodiment of the present invention.

[0020] Figure 6 Shows a depiction Figure 5 Flowchart showing the details of the parameterized pants model shown in .

[0021] Figure 7 A flow chart showing the overall process of producing garments on demand according to a second embodiment of the present invention. DETAILED DESCRIPTION

[0022] The following detailed description should be read with reference to the accompanying drawings, in which similar elements in different drawings are numbered the same. The detailed description and drawings, which are not necessarily drawn to scale, depict illustrative embodiments and are not intended to limit the scope of the present disclosure. Instead, the illustrative embodiments depicted are intended to be examples only. The selected features of any illustrative embodiment may be incorporated into additional embodiments unless there is a clear statement to the contrary. Although the present disclosure may have various modifications and alternative forms, the details thereof have been shown as examples in the accompanying drawings and will be described in detail. However, it should be understood that the intention is not to limit the various aspects of the present disclosure to the specific illustrative embodiments described. On the contrary, the intention is to cover all modifications, equivalents and alternatives that fall within the spirit and scope of the present disclosure.

[0023] definition

[0024] As used throughout this application, the singular forms "a", "an", and "the" include plural forms unless the content clearly dictates otherwise. In addition, the term "or" is generally used in its sense including "and / or" unless the content clearly dictates otherwise.

[0025] "Yarn" refers to any linear input to a weaving process. Yarn is a general term for a strand of continuous textile fiber, filament, or material in a form suitable for knitting, weaving, braiding, or otherwise winding to form a textile fabric, and is often used interchangeably with "thread" and "thread".

[0026] "Weave" refers to a system or pattern of intersecting warp and fill yarns. The term "weave" is used to describe large areas of textile fabric that are not knitted or woven. Plain, twill, and satin are all types of weaves.

[0027] "Weft and warp" are terms that refer to the constituent yarns in weaving. Warp yarns extend longitudinally toward the direction of production, while weft yarns extend transversely to the direction of production and are sometimes called "filling yarns."

[0028] "Headlock" refers to a structure, usually shaped as a loop or eyelet, which is able to control the movement (shedding) of the warp yarns. The specific construction of the heald may vary in different machines.

[0029] "Shedding" refers to the temporary separation between the upper and lower warp yarns and is often used interchangeably with "warp shed". The warp shed is also a triangular opening formed in the warp yarns as the heddle moves. The term is also often used as a verb to describe the action of the upper and lower warp yarns switching positions.

[0030] The "shuttle" is the movable loom component that acts as a carrier for the fill yarn and travels through the warp shed to deposit the fill yarn.

[0031] "Weft insertion" refers to the act of inserting a weft yarn into a woven fabric, usually via a shuttle with a weft bobbin.

[0032] "Weft yarn insertion point" refers to a point located at a radial distance away from the weaving loop, at which the weft yarn is deposited.

[0033] Loom

[0034] Figure 1 A perspective view of a loom 10 constructed in accordance with a preferred embodiment of the present invention is shown. The loom 10 is a circular loom, which can be considered as a series of flat looms arranged in a circle. The operating principle is generally the same as for a flat loom, with the main difference being the continuous travel of one or more shuttles 15, which are arranged in a circle. Figure 2 One of the shuttles is marked in Figure 2 A top view of a loom 10 is depicted. In the depicted embodiment, the loom 10 has six shuttles 15, of which four are shown. Due to the circular shape of the loom 10, during operation, the shuttles 15 will pass through the heald units 20. When one of the shuttles 15 leaves the warp shed of one of the heald units 20, the shuttle 15 will enter the warp shed of the adjacent heald unit 20. Some of the heald units 20 are upright (such as Figure 1 25 in the loom), and some of the heald units 20 are placed upside down (such as 30). The upside-down heald units 30 provide a space 35 for the operator to enter the inner part of the loom 10. Although Figure 1 Although not shown in the figure, all the heald units 20 can be mounted upside down, and such an arrangement is considered to be preferred. The heald units 20 are adjustable. Although Figure 1 It is not shown, but during operation of the loom 10, a supply of yarn is provided to the heddle unit 20.

[0035] refer to Figure 1 and 2 , the loom 10 includes a variable diameter braiding ring 45 ( Figure 2 ) and a plurality of variable position weft insertion arms 50, one of which is positioned on each shuttle 15. The loom 10 also includes a system of individually actuated heald units 20, all of which are controlled by a controller 70 or a dedicated heald control board 522 ( Figure 1 ) control. Preferably, the loom 10 has 36 individually actuated heddle units 20, and each heddle unit has twenty individual heddles, of which only eighteen are used during weaving. However, if the loom 10 is made larger, many more heddle units will preferably be provided, and preferably each unit will have more heddles. Preferably, the loom 10 has six weft insertion shuttles 15 (in Figure 2 Four of them are shown in FIG. 4 ) and a variable diameter braiding ring 45.

[0036] Further details of the loom 10 are described in US patent application entitled "MANUFACTURING WOVEN TEXTILE PRODUCTS" filed on the same date as the present application (Attorney Docket No. UNS003) and incorporated herein by reference.

[0037] Control System

[0038] Go to Figure 3, details of the control system 70 are shown. The control processor 100 runs in real time. The control processor 100 receives information about the loom 10 from multiple sources. For example, a camera 110 is shown connected to the control processor 100 via a universal serial bus connection (USB) 111. Another camera 120 is connected to the processor 100 via an Ethernet connection 121, and a sensor 130 is also shown connected to the processor 100 via an Ethernet connection 131. The cameras 110, 120 are not required, and other sensors can be used in their place. The control processor 100 is also connected to several main controllers, such as a main controller 140, which has a microprocessor 141 and several communication ports, such as a USB port 142 and serial ports 143, 144 and 145, which are designed to use communication protocols such as RS485 and can preferably handle high-speed data transmission. The main controller includes devices such as USB controllers, converters, Ethernet controllers, etc. The main controller 140 is serially connected to several devices, which are preferably motor controllers, input / output controllers, weft controllers, etc. The main controller 140 is also connected to a wireless module that can wirelessly communicate with several devices, preferably motor controllers, input / output controllers, weft controllers, etc. With particular reference to device 150, device 150 includes serial communication ports 151 and 152 for communicating with the main controller 140 and other devices. A central processing unit 153 provides processing capabilities for device 150. Device 150 can also be connected to DC motors and sensors. Power ports 154, 155, 156 and 157 are also provided, which form a network 158 to link and power other devices. Several additional sensors or cameras can be added to the control system 70. For example, encoders, weighing units, linear potentiometers, weft break sensors, warp break sensors are preferably connected to devices 150, 160 and 170. These are connected through various digital interfaces, including I2C, UART, Modbus and SPI. These devices 150, 160 and 170 are also configured to operate an AC motor 171 and communicate with a sensor 172, as indicated by device 170. The devices 150, 160 and 170 also communicate wirelessly with the main controller via a wireless module, as indicated by device 180 through wireless connection 181. Wireless device 180 contains an onboard battery power source 182, can control a dc motor and can communicate directly with other devices having various sensors 183. Device 180 also has a microcontroller 184. Although only four devices 150, 160, 170 and 180 are shown, many other correspondingly configured devices are located in the control system 70.

[0039] The power supply 190 includes a direct current ("DC") power port 191 and a DC power communication port 192, and an alternating current ("AC") power port 193. The DC power travels to an emergency stop relay 200, which includes DC communication ports 201 and 202, DC power ports 203 and 204, and a stop switch 205, which, when activated, is arranged to stop the DC power. The stop switch 205 is connected to a three-phase relay 210 through a communication port 206. The three-phase relay 210 includes a communication port 211 connected to the communication port 206, two AC power ports 212 and 213, and a stop switch 214 connected to a communication port 215. The communication port 215 is connected to an emergency stop switch 220. When activated, the stop switch 220 is used to stop providing both AC and DC power to all devices.

[0040] Now go to Figure 4 , showing a control overview of the loom 10. Since the control of the loom 10 occurs in real time, the loom control system 70 requires real-time measurements from various parts of the loom 10 in order to establish a feedback control system. The measurements are stored as variables, some of which need to be updated quickly and some of which do not. In order to achieve real-time control, the loom control system 70 follows a control scope 300, which defines how often or how quickly the variables used to control the loom 10 are updated. The main control scope 310 has components such as a core control system 315, which includes weft and warp tension control loops and a graphical user interface ("GUI") 316. Different aspects of the loom 10 can be controlled at different levels. For example, warp tension control can be implemented on the main control level 320, thereby achieving faster updates. In addition, the main control scope 310 has various programs that interact with the loom user using high-level commands. The high-level commands are updated at a relatively low rate, such as using a 200Hz control loop. At the main control level 320, which includes items such as a loom controller 321 and a router 322, commands are treated as intermediate commands and are updated at a faster rate and use a 2kHz control loop. The main control level 320 may also include a warp tension control, which would otherwise be grouped within the main control scope 310 as discussed above. At the lowest level, the device scope level 350 commands are updated using a 20kHz loop. Such devices include input-output relay controllers, annular ring controllers, heald controllers, and weft controllers. Additional devices 360 and controllers are also part of the loom control system 70. For example, intelligent servo motor controllers 361 and 362 can be used for heald control 363 or weft insertion 364, and such controllers are updated at the same rate as the associated devices. The VFD controller 363 will be updated using the main loom controller 321.

[0041] The process of producing clothing

[0042] Figure 5 4. The parametric pipeline 400 is shown for use in the manufacture of a garment or apparel, specifically pants for the purposes of this example. The process begins with a scan 410 of a person who will wear the pants being produced. The scan produces a three-dimensional mesh 411, which is then processed. The scanned mesh 411 is aligned and cropped at 420. Certain portions of the mesh are not required for producing the pants and are removed to produce a clean scan 421 with unnecessary features removed 422. Next, two-dimensional parameters are extracted from the three-dimensional mesh data at 430 to create body parameters 435, which are in digital form at 436. The parametric pants model is used to process (at 440) the body parameters to form a pants pattern 451. As discussed below, reference is made to Figure 6 The model is discussed in more detail. Parametric designs can be hand-made, generated by a rule-based algorithm, or generated by a machine learning algorithm. Hand-made designs are inspired by traditional pattern making, where body and trouser measurements must be selected manually. In contrast, rule-based designs are processed automatically, where trouser measurements are defined by geometric relationships and body measurement offsets. Finally, machine learning designs are processed by automatically selecting and learning parameters based on trousers designed in previous attempts. Such machine learning is preferably combined with principal component analysis and uses neural networks to process the design. The advantage of using artificial intelligence techniques (such as machine learning neural networks) is that the process is simplified, easy, and runs faster. Such a process can be changed by adding constraints to the machine learning process. For example, the machine learning process can be required to produce a pattern that is easy to sew; can learn from previous attempts; and can provide suggestions for modifying the current process. Thereafter, decorations such as seams, labels, and notches are added at 460. This step produces a decorative pattern 465, which can be exported at 470 in a DXF production-ready format 480, which is used to enable the loom 10 to produce garment pieces for forming the decorative pattern 465.

[0043] Figure 6 Shown from Figure 5 Flowchart of parameterized pants model 440 of FIG. As discussed above, a person is scanned by a camera or other type of image capture device to obtain a three-dimensional scan in the form of points defining a three-dimensional surface. The scan is designed not only to obtain the overall shape of the person, but also to highlight landmarks on the person's body. At step 510, the results of the scan and the landmarks are input into model 440.

[0044] Next, at 520, measurements are extracted from the three-dimensional scan to obtain body measurements 530. The extraction is performed by slicing the three-dimensional scan into two-dimensional slices and passing other processing techniques. The body measurements 530 that constitute the three-dimensional measurements of the portion of the body of interest are then processed at 540 using linear regression and other parameter extraction techniques. When linear regression is used, an automatic guess is made about the required deviation and looseness based on previous production of pants. As an example, pants parameters are extracted. As a formula, the linear regression preferably starts with "PantsParams = Measurements * Factor 1 + Factor 2", or for example Seatline = Hips * 0.5 + 20. The extracted pants parameters 550 are measurements on the two-dimensional cut piece. The pants parameters include waist, inseam, thigh, calf, and cuff measurements, although additional parameters or fewer parameters may be used.

[0045] The parameters 550 are then processed at 560 using a fit engine or shape model of principal component analysis. Important features for a set of shapes are automatically extracted. Related portions of the pieces are deformed together to provide shapes that appear natural. In addition, principal component analysis reduces the number of dimensions required for the machine learning model. A shape model or fit for a garment is selected based on the desired garment, and the model is used to generate piece shapes based on the measurements. Again, as an example, a trouser shape model can be used to form piece shapes associated with a pair of trousers 570.

[0046] The piece shape 570 is then processed through a shape correction algorithm at 580. If a model or algorithm was used to make a prediction, the difference between the model's prediction and the result is classified as "energy". In one example, the energy required by the learned model can be minimized. Other improvements include, for example, that seam lengths can be reduced, jagged seams can be eliminated, and the lengths of various parameters can be set closer to their final target lengths. The piece shape is then exported 582 at 585 for virtual fit simulation and evaluation. The piece shape is adjusted based on the virtual fit evaluation before it is exported to 560 for trimming. The piece is then equivalent to the one from Figure 5 The pants pattern 450 is ultimately exported as a DXF file at 480 and used in the cut and sew manufacturing method.

[0047] Figure 7A pipeline or process 600 of data flow from starting body data 630 all the way to the output of the loom is shown. The body data is preferably generated by a camera or other digital imaging equipment in the form of three-dimensional body scan data. Estimated body data is also obtained from existing videos or pictures. Estimated body data can also be generated based on user input measurements (such as height and weight). Process 600 begins with order information 610, which includes details 615 such as materials, styles, and sizes. Process 600 includes software 620, which receives body data 630 of the person who will wear the pants being produced. Then, a shape generation algorithm 640 extracts useful measurements from the body data 630 and generates knitting shape data preferably in the form of a knitting shape file 650 in combination with the provided order information 610. Examples of order information details 615 may include, but are not limited to, customer ID, material, fit, preference, and style information. Fit information may include typical pants fit, such as slim, casual, or loose, while style information may include waist circumference and hem length. The output weaving shape data or file 650 is in a human readable format, similar to an XML or YAML file, and is generic enough to not include any loom specific commands. Alternatively, the weaving shape file 650 can be structured data stored in a database and accessed via an API for processing.

[0048] Next, at 660, loom parameters 661, weaving parameters 662 and weaving shape data or file 650 are all processed. Specifically, weaving shape file 650 is added to weaving queue 663, in which it can be grouped with other weaving files according to multiple metrics. Weaving files can be queued according to factors such as material, shape, style or order of reception. Then, WCode converter 664 uses the weaving shape data / file from weaving queue, loom parameters 661 and weaving parameters 662 as input. Queuing and WCode 665 generation preferably occur on remote computers, cloud servers or local computers. Loom parameters 661 can include loom-specific attributes, such as the gear ratio of the motor of the available warp number or loom. Weaving parameters 662 can include loom-agnostic parameters, such as desired speed or weaving density. Weaving parameters 662 may be subject to the constraints of the physical limitations imposed by loom parameters.

[0049] The WCode Converter 664 is a module that interprets the simple dimensional aspects of the weave defined in the weave shape data / file and converts it into the appropriate WCode command set to be read into the operating system of the loom. The WCode Converter 664 also verifies whether the desired shape can be weaved on a particular loom and will report an error if it is not possible.

[0050] WCode 665 is a set of computer readable instructions that define control parameters for a loom. As distinct from the weave shape file 650, which is a high-level description of the output of a given weave, WCode file 665 allows finer control of loom parameters such as warp tension, motor speed, and weave pattern.

[0051] The completed WCode 665 is then provided to the operating system 670 of a given loom, which is preferably executed on a processor (such as described above with respect to Figure 3 The operating system 670 then directs a loom 680 (which may be the loom 10 discussed above) to produce a woven output 690 according to the instructions specified in the WCode 665. Multiple outputs may be produced sequentially before being removed from the loom 680 and post-processed at 695. The post-processing step 695 prepares the woven output 690 to become a usable product and may include adding buttons, zippers, or other steps not included in the weaving process 600.

[0052] Based on the above, it should be readily apparent that the present method is capable of producing a production-ready format representing a garment that can then be produced by a loom. Thus, the loom can directly weave components of a garment, such as individual trouser legs, shirt sleeves, dresses, etc., based on the body data of the person who will wear the garment. In some cases, a complete garment can be directly woven on demand to precisely fit the body data of a person.

Claims

1. A method for making a garment, comprising: Receive body data; generating knitting shape data based on the body data; as well as A woven piece of garment is automatically produced on a variable diameter circular loom based on the weaving shape data.

2. The method according to claim 1, wherein generating the braiding shape data comprises: extracting shape-defining measurements of a body portion of interest from the body data; analyzing the body shape definition measurements via a fit engine to create a fit of a garment based on a fit metric; as well as A set of computer readable instructions for manufacturing the knitted piece of clothing is output, wherein the knitted piece of clothing is automatically produced based on the set of computer readable instructions on the variable diameter circular loom.

3. The method of claim 2, wherein receiving body data comprises taking a picture of a portion of the body of interest and highlighting landmarks on the body of interest. The method of claim 2 , wherein receiving body data comprises performing a three-dimensional body scan. The method of claim 2 , wherein receiving the physical data comprises generating the physical data based on user input measurements.

6. The method of claim 2, wherein extracting body shape defining measurements comprises using linear regression on the measurements.

7. The method of claim 2, wherein analyzing the body shape definition measurements comprises performing a principal component analysis to reduce the number of dimensions in the measurements, and then applying machine learning techniques to the measurements.

8. The method of claim 2, wherein analyzing the body shape defining measurements comprises forming a piece shape from the measurements and processing the piece shape using a shape correction algorithm.

9. The method of claim 1, wherein generating the braid shape data comprises combining order information details with the received body data.

10. The method of claim 1, wherein the order information details include at least one of customer ID, material, fit, preference, or style information.

11. The method of claim 9, wherein the weaving shape data is first converted into computer readable instructions defining control parameters for the weaving machine.

12. The method of claim 11, wherein generating computer readable instructions comprises combining loom parameters with weave shape data.

13. The method of claim 11, wherein generating computer readable instructions comprises combining braiding parameters with braid shape data.

14. The method of claim 12, wherein the loom parameters include the number of available warp threads.

15. The method of claim 12, wherein the loom parameters include a gear ratio of a loom motor.

16. The method of claim 13, wherein the braiding parameters include a desired speed. The method of claim 13 , wherein the braiding parameters include braid density.

18. The method of claim 1, wherein a plurality of braided outputs are generated sequentially.

19. The method of claim 1, wherein the body data is a three-dimensional body scan.

20. The method of claim 1, wherein the physical data is generated based on user input metrics.

21. The method of claim 1, wherein the body data is generated based on a two-dimensional video or picture.

Images